From anadelonbrin at users.sourceforge.net  Thu Apr  3 15:30:38 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr  3 18:30:44 2003
Subject: [Spambayes-checkins] spambayes pop3proxy.py,1.66,1.67
Message-ID: <E191EAI-00010F-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv3792

Modified Files:
	pop3proxy.py 
Log Message:
Expire messages from the unknown cache as well as the ham
and spam caches.  Also spin off threads to expire messages
(if necessary) each time a client connects to the proxy.

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.66
retrieving revision 1.67
diff -C2 -d -r1.66 -r1.67
*** pop3proxy.py	12 Mar 2003 03:29:58 -0000	1.66
--- pop3proxy.py	3 Apr 2003 23:30:34 -0000	1.67
***************
*** 141,144 ****
--- 141,145 ----
  import socket, asyncore, asynchat, cgi
  import mailbox, email.Header
+ from thread import start_new_thread
  from email.Iterators import typed_subpart_iterator
  import spambayes
***************
*** 391,394 ****
--- 392,399 ----
            make multiple calls, or will cope with the headers being
            different.
+ 
+      o USER:
+         o Does no processing based on the USER command itself, but
+           expires any old messages in the three caches.
      """
  
***************
*** 396,400 ****
          POP3ProxyBase.__init__(self, clientSocket, serverName, serverPort)
          self.handlers = {'STAT': self.onStat, 'LIST': self.onList,
!                          'RETR': self.onRetr, 'TOP': self.onTop}
          state.totalSessions += 1
          state.activeSessions += 1
--- 401,406 ----
          POP3ProxyBase.__init__(self, clientSocket, serverName, serverPort)
          self.handlers = {'STAT': self.onStat, 'LIST': self.onList,
!                          'RETR': self.onRetr, 'TOP': self.onTop,
!                          'USER': self.onUser}
          state.totalSessions += 1
          state.activeSessions += 1
***************
*** 571,574 ****
--- 577,589 ----
          return self.onRetr(command, args, response)
  
+     def onUser(self, command, args, response):
+         """Spins off three separate threads that expires any old messages
+         in the three caches, but does not do any processing of the USER
+         command itself."""
+         start_new_thread(state.spamCorpus.removeExpiredMessages, ())
+         start_new_thread(state.hamCorpus.removeExpiredMessages, ())
+         start_new_thread(state.unknownCorpus.removeExpiredMessages, ())
+         return response
+ 
      def onUnknown(self, command, args, response):
          """Default handler; returns the server's response verbatim."""
***************
*** 1298,1304 ****
                                              '[0123456789]*', cacheSize=20)
  
!             # Expire old messages from the trained corpuses.
              self.spamCorpus.removeExpiredMessages()
              self.hamCorpus.removeExpiredMessages()
  
              # Create the Trainers.
--- 1313,1324 ----
                                              '[0123456789]*', cacheSize=20)
  
!             # Given that (hopefully) users will get to the stage
!             # where they do not need to do any more regular training to
!             # be satisfied with spambayes' performance, we expire old
!             # messages from not only the trained corpii, but the unknown
!             # as well.
              self.spamCorpus.removeExpiredMessages()
              self.hamCorpus.removeExpiredMessages()
+             self.unknownCorpus.removeExpiredMessages()
  
              # Create the Trainers.



From anadelonbrin at users.sourceforge.net  Thu Apr  3 16:00:53 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr  3 19:00:56 2003
Subject: [Spambayes-checkins] spambayes pop3proxy.py,1.67,1.68
Message-ID: <E191EdZ-0003aD-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv13747

Modified Files:
	pop3proxy.py 
Log Message:
Opps.  Fix bug from the last commit.

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.67
retrieving revision 1.68
diff -C2 -d -r1.67 -r1.68
*** pop3proxy.py	3 Apr 2003 23:30:34 -0000	1.67
--- pop3proxy.py	4 Apr 2003 00:00:48 -0000	1.68
***************
*** 1309,1313 ****
                                                options.pop3proxy_ham_cache,
                                                '[0123456789]*', cacheSize=20)
!             self.unknownCorpus = FileCorpus(factory,
                                              options.pop3proxy_unknown_cache,
                                              '[0123456789]*', cacheSize=20)
--- 1309,1313 ----
                                                options.pop3proxy_ham_cache,
                                                '[0123456789]*', cacheSize=20)
!             self.unknownCorpus = ExpiryFileCorpus(age, factory,
                                              options.pop3proxy_unknown_cache,
                                              '[0123456789]*', cacheSize=20)



From anadelonbrin at users.sourceforge.net  Thu Apr  3 17:11:59 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr  3 20:12:04 2003
Subject: [Spambayes-checkins] spambayes pop3proxy.py,1.68,1.69
Message-ID: <E191FkN-0000p4-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv3132

Modified Files:
	pop3proxy.py 
Log Message:
Add 'show clues' button to the review messages page
as requested by Paul Moore.

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.68
retrieving revision 1.69
diff -C2 -d -r1.68 -r1.69
*** pop3proxy.py	4 Apr 2003 00:00:48 -0000	1.68
--- pop3proxy.py	4 Apr 2003 01:11:57 -0000	1.69
***************
*** 906,909 ****
--- 906,911 ----
              row.subject.href="view?key=%s&corpus=%s" % (key, label)
              row.from_ = messageInfo.fromHeader
+             subj = cgi.escape(messageInfo.subjectHeader)
+             row.classify.href="showclues?key=%s&subject=%s" % (key, subj)
              setattr(row, 'class', ['stripe_on', 'stripe_off'][stripe]) # Grr!
              row = str(row).replace('TYPE', label).replace('KEY', key)
***************
*** 1084,1092 ****
          self._writePostamble()
  
!     def onClassify(self, file, text, which):
!         """Classify an uploaded or pasted message."""
!         message = file or text
!         message = message.replace('\r\n', '\n').replace('\r', '\n') # For Macs
! 
          cluesTable = self.html.cluesTable.clone()
          cluesRow = cluesTable.cluesRow.clone()
--- 1086,1090 ----
          self._writePostamble()
  
!     def _buildCluesTable(self, message, subject=None):
          cluesTable = self.html.cluesTable.clone()
          cluesRow = cluesTable.cluesRow.clone()
***************
*** 1099,1103 ****
          results = self.html.classifyResults.clone()
          results.probability = probability
!         results.cluesBox = self._buildBox("Clues:", 'status.gif', cluesTable)
          results.classifyAnother = self._buildClassifyBox()
          self._writePreamble("Classify")
--- 1097,1125 ----
          results = self.html.classifyResults.clone()
          results.probability = probability
!         if subject is None:
!             heading = "Clues:"
!         else:
!             heading = "Clues for: " + subject
!         results.cluesBox = self._buildBox(heading, 'status.gif', cluesTable)
!         return results
! 
!     def onShowclues(self, key, subject):
!         """Show clues for a message - linked from the Review page."""
!         self._writePreamble("Message clues", parent=('review', 'Review'))
!         message = state.unknownCorpus.get(key).getSubstance()
!         message = message.replace('\r\n', '\n').replace('\r', '\n') # For Macs
!         if message:
!             results = self._buildCluesTable(message, subject)
!             del results.classifyAnother
!             self.write(results)
!         else:
!             self.write("<p>Can't find message %r. Maybe it expired.</p>" % key)
!         self._writePostamble()
! 
!     def onClassify(self, file, text, which):
!         """Classify an uploaded or pasted message."""
!         message = file or text
!         message = message.replace('\r\n', '\n').replace('\r', '\n') # For Macs
!         results = self._buildCluesTable(message)
          results.classifyAnother = self._buildClassifyBox()
          self._writePreamble("Classify")



From anadelonbrin at users.sourceforge.net  Thu Apr  3 17:12:00 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr  3 20:12:05 2003
Subject: [Spambayes-checkins] spambayes/spambayes/resources ui.html, 1.6,
	1.7 ui_html.py, 1.6, 1.7
Message-ID: <E191FkO-0000p7-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes/resources
In directory sc8-pr-cvs1:/tmp/cvs-serv3132/spambayes/resources

Modified Files:
	ui.html ui_html.py 
Log Message:
Add 'show clues' button to the review messages page
as requested by Paul Moore.

Index: ui.html
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui.html,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** ui.html	13 Mar 2003 03:24:57 -0000	1.6
--- ui.html	4 Apr 2003 01:11:57 -0000	1.7
***************
*** 224,227 ****
--- 224,228 ----
                     id="spam"    value='spam'/>
          </td>
+         <td><a id="classify" href="classify">Show clues</a></td>
      </tr>
      <tr id="blankRow"><td>&nbsp;</td><td>&nbsp;</td><td>&nbsp;</td></tr>

Index: ui_html.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui_html.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** ui_html.py	13 Mar 2003 03:24:58 -0000	1.6
--- ui_html.py	4 Apr 2003 01:11:57 -0000	1.7
***************
*** 5,80 ****
  
  import zlib
! data = zlib.decompress("x��[{oܸ\021����\016<\025�l��]�Iz]��&�S\037�\\\\{���p\010�\022wW�$�\022��6��ޙ!)Q\017;\
! �\036�\000�\004^�H\016��y�fHϾ��p>����]�߿c�?�y��9�\016�㿞���\027�\013��b49b�ge\
! �b��d<���\013��j�ViB��G��b�\010\026Gg\036=y�m��\005ߊ��P��}�)Q,y(fc�cJ����\
! ���\023[�LM��'�\030/b�\034�r\023��\001[��^�8�,��*Φl�~��+�\0270�\016��R\026)�m\021��+\
! >M��\016އ2�Ŕ�f\002?!5��}\014�\026�#�ky\017�j�^M^L�Kl\033����\024ㆹÍ�Wk�q!��z�\
! �bC3��d�'O4w�\005�2�d�ûU!�,��‰��NYΣ(�Vg/���D,����ӯ�b��B\026�(\016\
! �̡)`�L�-\022�9�o!��i�+�M\014\021�e�\017\001�NN����H��%5��,�J��R(�\016��Y\
! B��\000�hl)B�<�ךG���|;��l\023Gj\015z��;\0209\006�\035\031.�K.&�\003|�\002��`��C��7�p\
! e4�L\017$'����B�rhA�lPA'������j:7\032�\004E��S�p\035��s�Qfz?[�)B�g:V�\025x�\
! �!�9�<;��K�O��6\033[W1\033\033�\003�$D�8���;\024�,��Y��<�\001��i)s��\010p\015�P^0\
! ��\025+����oF�x�3�ī���2��(\021�8x�-��\024�\000\012-jf\"�\013v��dy!�*T���\026���\
! �P�:��P�\002��c�B,a\002��\007W�{6��Ӏ�e4��:eU<B\037�f��\005\004�%�\022C\022)��smŞ\
! Y�g�Z�w�~\021�'�\013\002=��x�\010>\017��d�8\021\007l\026�H\0045\027��Eb\031g�x�\026,���g��R�D\
! ��Kj�0b�6bط��nE\001�w��\034^߃חU�\011�1�^�#(~��\"\010\005��� �xP\005\017Q�ab�SY�\
! 'U���$�*Sq\012�J�h\013\002�\000�$[�wQ\020'D[��j��k�X�\037%�rv\010��X\030�\015�\012���\023��\
! ��걡Ls���KX������H�w`�F�,��K�\037���\0060w\037G�\003�\"��C��\033�\034Xi��\033L��B\
! �I�\035�\007k���,cp�#M㒇k-�Z�4*\023\"*Q6\013��g���EeF\021��8�\014+�: y/\004,\020'e�\
! [�\006�a�\003�F��8w\025�5R�]�i�\020'k���ndqGA\036v5ֽ�X-�\003\004\002��\004�e�\027 �_\031�0�\
! 4\031\033��Y^)2�����6\027�m@<и�\022u��П�yG\023olL��3\006�\\���\034a5*\004۶*x�r��l\
! �Z=Z%�=�c���j��jז�\030lg�\031�HW\003�S7�����j_|摧?�x\001����\002:\007zY(ga;�\
! C�ggL�\"��3�\016�W(o\037\002\030���w�\024�\020\0105\014��Q��\022�\036\022ݕL^�_Ab�fw��\007�\023u:��\
! �\026?�\010ct��q\034�$��\021Q�5z�k��D��\027�dY�.i\014z֋\037�Vo%i�1m�)�\023U\014A�V��k\
! ǠU\002��|�����%\0078�\027\022X�y��{!��V�~\000M��\0370Y�\011���7\036TS[\0262eeXp\005�,�l\
! �o}�E�\030�~\004�]!�\004x\000C\023��\027[�U�\031H�yț\037�\020儓#1��r-�:`\012�&�vl��J\023ߐk\
! p�٪…�W$S\004���M�n;B:$/��`)jnP\022\030� �l����<߈\004�%v�^�\027X\033aA\017\011|��\
! Ďq1���z\006�\002\005��Yn������\000Q�\006��Ó\003�L�g�I#|\003�\\��P$\011�\0141��\033���`\006�\
! Ӓ�V�3޼��zp�3�\0300\024M���\010�\010��(�1(�9��E\020\034�����G����\003HO\\���\017Х\
! %�k�Y*��R�L3��ć0����-�t0\036��|5��\025t�Z�/g\004�2\014��\021<X�{Y�a�UZ$\005��\
! �\001�/a:�\036X\022���I\003Ś1`��ގ���\001:���\015bEt\001�^B���<���\013�Xdd]��@���b\
! �l���\030w��\016��w���Z7Q�q��=�\027�y�B]\025��m~\016��\0126\010�5e�\014�a{\001\011t��z\\\
! �>�y\004�\014=\011�h�\010:C�!v���<����hb�1\033/�\003w{�/93�&BX��)�(\002\011�\020\032�\012��\
! 6\033�?�A7�f\032\014\002)Ҧ�ӎٸSs\032t+\000�BO/pY\037u&�S�N�ԣ��FIœ�f�Lq\033����\030\
! �Վ�dU��B�>�����aW�Q��\016�!+�Bt�U����9.�\011�2\010]�4uV��O;s �m��1W�\
! !��\016'�\024�6\026tz\006ߚB�+��\033W���q��;M����,��S\016��\003�H仼�'���\021��u\002\
! �\006D��@�䌝��B�ܖJ��\015��h\0017\025\003=�\037����\003E��\025��+''\004�~��~R���\032۰�\
! ��i��j����*�,�\034\024�I]'�P���Di<�\025!�%u�m\017�\037/�\002�\016��eCB��E�HE3�\0077\
! �Y�G��l�Ȳ#�1\013E�\015#\035݁�Z�\001,�@8�\025\011ct�\\o�J!\026�\017�\027l�\003��!ܞ�ExGK��\
! ���\003`f���\002Y,\001\026\013L���A]\025�rU\014��9R�!\037\007�\010��\013�\024�\017�*�7�\031#\030=\024��I��w\
! @�c2K�\020�\006\017�A\027q\031�\"bcF��\023�\001�F%`�j\0114CZI�p�h��RC\007��@��\002��l�]*�s�\
! R�1�\001�\002��\037/��\004��\036\035G\021�\025���3\037�(A\014\010�̣N���k�O\020�@��x�48\\�\011\003\036�\
! �\005\026��>�u�C���Z���\034����\033\022�?T��\037��5�KV��q@�Q\\\"@�ȩ{�@�v��p�R�\
! ����2����>@�ԹH[h��ܰ�s�,L����\\����x��O�\027��2\011f�i͔��\011\
! {8�\016� �KS����\023/�\036d�U\012�x�|���s�~3JD��\\,8c����Om)�֟u��t��i�\033\
! ۋ����lF��\004�ⷿ�ow��ߪ\022\0208\025��\010��)�y�;=��=��\017\034��B�vEgg�\004�[7\
! \000��\022�\006����iJ$g�tGJ��\033Q�C\030������4Ar>��`��\022\003k�����j\036��x���M�\
! Aʲ�w��p;��n����W'v�\021ڮ\016\003��\023�n���Y�T\022\000X��\006^\007���\001�0Z/\001�Qo\013�\
! >�l�n\035Q�s����h�8~\030�x��M\033��\027�\000\"��*�o^`�)v��5j\024��\026>�\012J\020ۈ\016|�\012\
! *\030\033�\014>�\017z�f-���@�������4�\001{f�\017o�=���;CI`E�zs �ao/�\033̍�:8\017���\
! f�\012\031�}�ط���\023���\006\026�>z�M\034�c���,\002��jfAo�\000�\0160O�I��Q��\030�\036b\015��{U�\
! ^(/x\024K\033��%l�d\004��q8�!��VC[;���:x��;�@���xJ���,`j�t���e��Q�\
! \001��w��E³;4��\001\027�����>%��;P�A_;�aOV\026w�%k`�Ú\037�C_R+��D��Q\010�\
! ͫ�\036\011��y�\010�\004�(ZRZ%*�y���È+n]�eL\005tM�q��8�,>�x�\021\000�I��K��z}��\
! OO�ﭪ�g#I\020�#�\017\005\035B\010J>6k��\031\022 �,L**�@�O\011�ԭ?\"��l���\024e\007�܀�=��\
! �3\037O�`_LOwv�LR��G��C�{�\006���\007�差-�魿��ՓԬ��B���m�Ye���=�\035�\
! ='�Z�j��?Bۅ�C\013䌎R���\030�e\036:%�8s��Z�\012��{�\003P\037D��\\\002�@&��J\024�a;\
! ��\033S�W�W~_���YI�s��NJ���;�d�݅a�\000�\020�՜����hH�]�\022\"�����u:x�\
! ��f�8֫�1{z�G�-�\022�)�4��\036vX��cF��_\021\004J�VqU\016�}�f\013����\0050\002\034��֕�N\
! �\024�BYᅛ��G��\015����5�\027/_=B躐\013��!\023��2K�RC}��\013hFa�\014\011\031����8��\
! �\013&��}��G&���b��F�\020\021\036\021s��Sb�:S�,\020�c�D�;d�ČIL\036�W�t\016)񇜑N�@\
! �ԃ��9�:`I|'��\026���,Y}��^�jΔ���-\0206���\007�>��x\031�x�D޽L\011���ܡ�\
! }�SZ��\004�\033���!@�V���F��Ț*l�6\033���}\004�M�����Н^�>��\0146���`�b��\
! �.�G\025�@�\021���ku{���uv\036]\012\0202\007u�\016�C�����a�\031K�\000\004��K�P\034L^\012(�C,��\
! �\004�\000e�t\010d�(��\002\025}GT7/j\032��\007ɂNc���~�\\�����؜�s�eџ��ysi�\
! ��_�yw��\031>@\03580�߸����\025\034�*\030�\013\003�=Rv�-2t4�f4�\013�x�;��70�����<O�\
! psyF_�9~��,�n��Ng\001Ԧ\037��~Ly�Azw2ڔ�Hr��\020k�\010\026�\012��d�\007O�\020=AN�ih\
! \021{�̢�+\030�p��mYt4�?<�\014����t�(�t�l^߂�\027�S\037�@lo\023�-��M����-O�'\
! �\016�_�s���\034{(|tԿ�c�MkK\037���S�����c>�W�������/\016\0064\013�\013\025��e\016�\
! �����渫F���\002\014i�\037�WE��B�\016��Q9��&\022�4\024P\012��~\035@�b�)BA7G�n�1\
! ��>��W��~T��RA�\032Y\035[cq�(�-�\027^��k\"�\005\002��k\013�\024B\003\013��\004�{��W�u�i�\021�&\
! >�b��/����T$7�PJ��2tzxxtqk�\021\030b�2Zl���fJ�k\025{E\026��\004YJ��Z�\033� �~\
! fl\022\004�}&�gC�<3��\030\015��KS����\010��\026\020o����\024�^\013snIŐ\035*��^�^f�)!;���\
! \027�ɋ��1;�L���G���\\J���x�ٌJ;�H\026���\000~��;�xZ��Yfk�\010X��i��Pu\000�a\
! G�#jSx\000��טM1\001̈́=\007\011�2;\030\013��[�\0225��SN\000M��V�\005����\002J��=")
  ### end
--- 5,81 ----
  
  import zlib
! data = zlib.decompress("x��[{o\033�\021����\016�-��Q[��$��Ң��ԇ&\027�ֵ8\034\016\001��$ֻ��>,��}��\014�]�Ê\
! �C\037@���.��p8��\014��7�\037.f?�\\����w��7ﾻ`��p�׳���rv�\033^\014F'l��$�\
! �T\011����&�\"��S�\020?\013YD��p��7/�Ky<�[��\037r���BdK�\020�!u�1y��/s\
! \025n�'�TI1f�\037=c<�<:b�F��\021[��A\024r��Y̳�L�l�~�����a�=�a��b�� ��W\
! |\034��\036�/T��1��\010~\026���\017\022V-�'Z��\001�U��\032�\030-��6X\000C\")\0307�\035o�\\��ǹ�B��\
!  ņf�tI�O\036i�\006s�$4ɜ/�W�*�\020fZ�\004�t�R\036�2YM_V_�#�\004\032'/Ͽ��U?s��\";\
! .T\012M�#�U$C6��f_��*\012\025w�\022߸��\020��\010�wv����Z�'/�!\026y�WB�W�\002m�+\036�\
! %dZ\016����b��g�Z��2��oG��mdX�A\017^>s\007\"�@�%��r��輇\017W �\025���oP��\033\
! ��ƛ��(}4{�\011T\016-��*�T�ӳ__M�Z�vPt:�\"��(2���*����O���c)��S\
! \\������yE�[�~�/����8\034�JBD��_<z�����-\"��S_\033�\037��<�\011�\000�\020��\013\
! &2^�<[L}�f��K��H�����y,�0\022�0x����\034�\000\012\015jf\"�\013v��di��rQ|��[�׏\
! [Cq��C\025\013�\012��3��\011��\017���d���\001\023Kh��✕r�>��r�\001\004�%�\022C\0221�Ʌ�b�\
! ��3V��;Y�\010���\005�\036�v��\005�\006����RF�M\026*\024A�\005=\035�P,e\002�/ւEJ�\037�$<^\012\021i\
! \022jI-%F\014i#�}[��Nd�|\007����\003x}U�@*A�r\034A�KO\027B(�\004D\007��c��\005*6L\014~*�i\
! TF�^\024�DV&���Q)\026nA�\020@�h��.\012�h\027k^4���5s,Ǐ��);�^F,\014�\006S��`��(\012\
! aY�c\027*NU\002��aqZ�7��\"\012߁1\032!2��\027\003?�O�\015`�A��\003�\"��c5�\033�\034Xi��\033���L\
! ���=�\007k��*�%8ف�q�\027k-�J�4*\021\"�Q6s��g���E%F\021�O\031Z�\013�:\"y�\005,\020'e7\
! �b\015��p\007t��\007�a�*�k�\012���4\"N�j��ݨ잂<�ԽBY��#\004�b�\011��6/@B�24a�\
! i268�IZ\026d\016u\027�\025�T\000�\001��@�RT�\036C6�NF�ИV�g\01469g[U:ªU\010�m��8�V�\
! qc�h�����u�ޫ\021��\\[\012b��]gl#]\005|�ݨS\015G��}��#O1�\002��\014�\005t\016�2+���9\
! \016��M�JEr�\031g�\0351/+�C\010`<<8ܓR�\026@�f`��\012���\016��d�\014�\012\022\033Իk7>x\036\025���\
! _m�.E\030��\014e���\034.\006D\015��]�y�\022��_\\�e���!�Y'~\030[�S��ƴѦ�O�\022�x��-�\
! �A+\007�E��������K\016p��\025���@#Y��\0014\011��T�'�V�_{PMm���勌\027�Ϥf\
! \013|��$�� �#\030�2\025E�\003\030�\000�?�Z�\012�@Z�C���-PN89\022#���B\024G���\011�\035�`���7�\
! \032�p�*q��\025�\024�!&bS�ۖ���K�(���\033�\004�4�6[&x�m;�7\"\002o�]���\004�ZX�C\001\037�\
! :���z=y^̀P Cw7I-Pp��\027\020 \012ߠwuxr\000�i��6i�o����}�\020Q\004#\027�����*�`\002\
! �Ӓ�V�5޼��zp�\012\030��f���\020�\010�t(�\022\024�\002���\"\010\016B���#��u�\001�G.���\007�\
! �\022�5��\013^��ƙf���\017a\014\021/}�`��xȧ�h\026\015+h��\006_�\010�e\030$�#x���*/�1Wn�\024h\
! OM\007�?��@z`Ih\012V'\015\024�ǀ57{;��S�G訃wҋ\025�\005�\007\005�.,�\010�#.�b��uAv\003�\027�\
! �Y�A��l�\006�{h�ޡ��j�D���\031>{&/�z�B]\025��6?�禂��wM�{*�x�^B\002-�F��\
! \0177g:�@���'\001\031M�Ak�\015������\027�����<&�yp�n/�%g��D\010�f\025\005\023E �\035B\003Wa�\
! �z\003��5���L�A E��|�2\033wjN��\004�S��\005.��\004]��i�z��i\012U�h�Y�b�\006�;r)\
! 1X�9IRƘ+��3�\026\037�\036v�\035���\037���DkXI/�k����+�ЅISk%���5\007rޤ�\034s�\
! \035�n�hq�JQ+cA�g�)��\022��q����\030�{��T�?��R�v9d[\017�\"���ڝ���G��\013�\023\
! �4 zL\006�:gl-\037��6/D\014\016����\026pS1�3����Y;P\004\\XA\030�rrB`�G?�'u�i\006��\011;\
! h��F�f�\014^;��PY��B>��\020�\0120'�\033�bEHzI\035+�\003��s�@�C�U^��#+\021�Rь��\
! -}V�Q$$�*��s�BQh�HGw �Va\000\013%\020\016uE�\030\035&�[�R��胫\005��@�j\010�\027k����A\
! f�)�\0010���E\001�X\002,\026��\023�*��*\011��\031R�!\037\007�\010��K�\024�\017�*0�\031#\030=\024���I��\
! w@�c2K�\020�\032\017�A�2_�,dCF��\023�\001�F%`�j\0114\027��\032���z%��\016\034����\005\036+�\004�T��\
! ԥ�cX\003(\005��?^�\034�7\011>%=�Z�!�\025����\017RT \006�l�N���k�;\010$��z���;\\�\011\003\036\
! ��\001\026�s\027�:���A^�cYX\016V���\015\011��+O���\006�JH�8��P��\037�8q�\015Т]�>\\�\024\
! �c�{���\014<� �x�\013\0201u��\006Z�-w���.\013�����\003�o�`8�|�������L�Y&Z3U�}\
! �\001��C(H9g�\024&>���%;�l��\001\034\017���=Κo\006�HV��\005SvzX\017�Ԕ\"i��5�����;�\
! ؁���s&ل��\011��o{�����U9 p*`\003\021\034���y�;=��\003�\037�\034��B��vE�);��V\015\
! �/�D���~5�s�\022ɴ��P��Fd\027\020\006\016\016\017��?�&H�\007�\031̟��g\015�4_9���\030\016��N6\
! HY��N7\037�f~��4|�����=B��a��p\"�]9�1��J\002\000\013����Z�3< \036\023F�$�8�m��\
! '�-ۍ#*p\016j��\024\015\033���\026���qmS>��\037A��Q\005��\013�w����\032�=���~\005%�mD\007>\005\
! \025��D\006�4\017z�f̓޲@���������\001{f��o�=��;CI`I�zs �ao/�\032̭\030;8\017���\
! f�2�����o�\017['X��\015,�}�[�XK��e\022�a`53�7\000\007�'�$T�(;T\014l_`\015\"�;U�\
! N(�x(��`�\022�c2�?]��\037���P������\012^���\016&P�:����\005L�ܐ\016��Y\006(\035u\030\
! �g�S�\002��v\026���sp�'N\013�G9�n��G<�G�\013jx�kT�\037��\010e�Ai\017�oe�\035i[�f��S\
! �����Ӏ�K�me\032)\036v�<\012A�yU�$�4��\021C�\000$FK�˨�)�\012��8�\005�N�JR\011^�f��9\
! N¦��1\036�\004��b�\022�j���<#ԓ�{�����$\010ё����1\004�/����\034\013�Y\002\012F\007\001&T\036R�\
! 5v+��D!_�f���Lm�q��\002����@�\027�ӝ�9����Q\033K\037x߬��6�\001���kM]z�/$w\
! ��Zm��'ya���2V��\001V\037̞�z��X���\001���c\017�\016c��\002!��\036;E\026���v]�f��\
! �\003�\"���\017�.\"l \027�s)�m�\035T͵)૿�+�+Bl��{��NR���?�l�ޅ~�\000\010\023�՜\
! ��\003��O�]�\022b�A���u:x���z�8֫�1ٽ���\026�\"2��%�v�\022��W\004�\022�+x\
! ��W��f\013��/�90\002\034��V��V�\025�\026��+;'�gO\024�kR�)�+B/^�z��M��|.!���BM\
! �R\027��^�����)\0242h\035i�q���\027�\006����OL�%��Z��!\"<!�V'�HG���^ ��\036��w\
! �,�\031Ӡ4�\022\007��\034s�\0179#����\007[)s\034v�\"y/�����,Yuhw�^\024�O����-1֝��\007\
! �.z��\033�x��޾�\011������}�\026d\032��\004�\031���>@�\003���(�,����px\017��#�o:f\
! \037����Z��td�\021��\006�\027�����Q<���\005jO�\\�^���\017�ﭳ��Z�P)��ux\036:<�s�\016\
! k�X<\005 @�c*��`�R@�\034���^m�+T榚[��@��\\�NP�x@�����醑��<�k���w�\
! �5�_?\030�s�aj^5,�3r���\035R���7ﮜ>�G�=G��[w\0248���F\015dvi��G��e���\
! V�F|.\"/x�\037�\016g��~vٜg\007\0147�o����W\036�B�&��\030@m�\021|�ǘ�^\023��'�MY�(�m\
! ^`u\037�\"]�8\031��`�\031�\016r�VD��S�l\026}]�0�\013�mˢ�\036���m�����G��\022Vg�f�=�Y\
! �>��\015��&��r�Δo�)��(�9'u��Ҝ�����c哓�\015!{�Z[z_Du7���ty�\032�\036�\
! ���~���8\030��,�/Tfw�٫��\002���\013R�Ӷ\032Պc\0130�Q~pQf\031�A\014�sܳ\036G�̚�H��\
! �P@)���U\000�ŨS��n�,ݾC��]d�/�Q��ⵡ�:5�:���Q�;� �\032�WD�\013\0048�c\003\
! �dB\003\013��\004�;��W�u�i�!�&��b��/�/�.�Pm���V_�h�����μ#0���T8�ַ��\
! ���.��-|�\023d�\012����8\007�w3c� X�3\032=�;)�8�ǰ��f�C\000_ό��o\000�\032J��?k��\
! �2瞕��\000X�\005�U\002��`g#v�b<z1>;e��ѩ���1���(��p��l\006��p����a\000�ە\
! ں4�-����&\021�D\007�0��\000�Î2�ܦ�\000�׭R�b\002�\011{\016\0228gv0\026\0125�&%�S!��\000���\
! ��\033(�Ǘ�\004\015B\006h")
  ### end



From anadelonbrin at users.sourceforge.net  Sun Apr  6 18:15:53 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr  6 20:15:57 2003
Subject: [Spambayes-checkins] spambayes FAQ.txt,NONE,1.1
Message-ID: <E192KIj-0003ZN-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv13697

Added Files:
	FAQ.txt 
Log Message:
Frequently asked questions about the spambayes project.

--- NEW FILE: FAQ.txt ---
Q: Hey!  Why don't you implement cool tokenizer trick X?  I think it
   would really foil those spammers!
A: Have you run your tokenizer trick against a set of messages to see if
   it actually works?  Many times what seems like a good idea turns out
   not to help much, and sometimes even hurts.  If you have a good idea,
   you've run it against a batch of messages and can prove that it
   helps, paste the code for your technique and the proof to the mailing
   list.  If you're not a coder, but are really keen on your idea, post
   a feature request on the project page, and wait for someone else to
   code it for you (but make sure you do some testing when it's done).
   Otherwise, you will likely get a message from Tim Peters about
   why you need to test your idea :)

Q: I just got a spam, but the system said it was "unsure". Why
   couldn't it tell that it was spam - it's obvious?
A: It may be obvious to you, but the classifier only works on
   the information it has been given. Maybe this is "new" (you've
   never seen this particular flavour of spam before), or maybe
   there aren't enough clues in the message which the system is
   aware of as strong spam clues.

Q: OK, I trained on that message. But I just got *another* one,
   and the stupid system still thinks it's unsure. Why did it
   ignore me???
A: It didn't, but you may need to train on a few more of this type
   of message to get it classified as "spam". The classification
   algorithm weights its results based on the number of times it
   has seen a particular clue, so that clues unique to this type
   of message may need a few more instances to become "convincing".



From anadelonbrin at users.sourceforge.net  Sun Apr  6 18:53:48 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr  6 20:53:51 2003
Subject: [Spambayes-checkins] spambayes FAQ.txt,1.1,1.2
Message-ID: <E192KtQ-0007FM-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv27837

Modified Files:
	FAQ.txt 
Log Message:
Add FAQ about training from scratch.

Index: FAQ.txt
===================================================================
RCS file: /cvsroot/spambayes/spambayes/FAQ.txt,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** FAQ.txt	7 Apr 2003 00:15:51 -0000	1.1
--- FAQ.txt	7 Apr 2003 00:53:45 -0000	1.2
***************
*** 28,29 ****
--- 28,41 ----
     has seen a particular clue, so that clues unique to this type
     of message may need a few more instances to become "convincing".
+ 
+ Q: I've mucked up my training and I want to start all over again,
+    but there isn't an option for this anywhere.  What do I do?
+ A: Because training from scratch is a very rare occurance, and because
+    deleting all your training information is something you don't want
+    to do by accident, there isn't an option for this.  However, you
+    can quite simply do this manually.  All the training data is stored
+    in a file, usually called hammie.db, and if you delete (or rename)
+    this, then you will start training from scratch.  If you are using
+    the web interface for the POP3 proxy, the configuration page tells
+    you what this file is called (and where it is) down towards the
+    bottom of the page.



From anadelonbrin at users.sourceforge.net  Mon Apr  7 01:26:29 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Mon Apr  7 03:26:38 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,NONE,1.1
Message-ID: <E192R1R-0003DA-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv12257

Added Files:
	imapfilter.py 
Log Message:
First steps towards an IMAP spambayes solution.

Currently will do (very) basic filtering and training.

--- NEW FILE: imapfilter.py ---
#!/usr/bin/env python

"""An IMAP filter.  An IMAP message box is scanned and all non-scored
messages are scored and (where necessary) filtered.

It is suggested that this filter is set to run at certain intervals.
Note that it is (currently) fairly slow, so this should not be too
often.  An alternative to this would be to keep the filter running
and logged in, and periodically check for new mail.

The original filter design owed much to isbg by Roger Binns
(http://www.rogerbinns.com/isbg).
"""

# This module is part of the spambayes project, which is Copyright 2002-3
# The Python Software Foundation and is covered by the Python Software
# Foundation license.

__author__ = "Tony Meyer <ta-meyer@ihug.co.nz>"
__credits__ = "All the Spambayes folk."

# This code will benefit immensely from
# (a) The new message class, which can hold information such as
#     whether a message has been seen before
# (b) The new header stuff, which will abstract out adding all
#     the headers

try:
    True, False
except NameError:
    # Maintain compatibility with Python 2.2
    True, False = 1, 0

import socket
import imaplib
import os
import re
import time

from spambayes.Options import options
from spambayes import tokenizer, storage

class IMAPFilter(object):
    def __init__(self):
        self.imap = imaplib.IMAP4(options.imap_server, options.imap_port)
        if options.verbose:
            print "Loading database...",
        filename = options.pop3proxy_persistent_storage_file
        filename = os.path.expanduser(filename)
        if options.pop3proxy_persistent_use_database:
            self.bayes = storage.DBDictClassifier(filename)
        else:
            self.bayes = storage.PickledClassifier(filename)
        if options.verbose:
            print "Done."
        # Unique names for cached messages - see getNewMessageName() below.
        self.lastBaseMessageName = ''
        self.uniquifier = 2

    def Login(self):
        lgn = self.imap.login(options.imap_username, options.imap_password)
        self._check(lgn, 'login')

    def _check(self, response, command):
        if response[0] != "OK":
            print "Invalid response to %s:\n%s" % (command, response)
            sys.exit(-1)

    def _getUIDs(self, low, high):
        # Retreive a list of uids corresponding to the given range
        if high < low: return []
        # request message range
        range = str(low) + ":" + str(high)
        res = self.imap.fetch(range, "UID")
        self._check(res, 'fetch')
        r = re.compile(r"[0-9]+ \(UID ([0-9]+)\)")
        res2 = []
        for i in res[1]:
            mo = r.match(i)
            if mo is not None:
                res2.append(mo.group(1))
        return res2

    def getNewMessageName(self):
        # The message name is the time it arrived, with a uniquifier
        # appended if two arrive within one clock tick of each other.
        # (This is completely taken from the same function in pop3proxy's
        # State class.)
        messageName = "%10.10d" % long(time.time())
        if messageName == self.lastBaseMessageName:
            messageName = "%s-%d" % (messageName, self.uniquifier)
            self.uniquifier += 1
        else:
            self.lastBaseMessageName = messageName
            self.uniquifier = 2
        return messageName

    def _selectFolder(self, name, read_only):
        folder = self.imap.select(name, read_only)
        self._check(folder, 'select')
        return folder

    def RetrieveMessage(self, uid):
        response = self.imap.uid("FETCH", uid, "(RFC822.PEEK)")
        self._check(response, 'uid fetch')
        try:
            messageText = response[1][0][1]
        except:
            print "Could not retrieve message (id %s)" % uid
            messageText = ""
        return messageText

    def TrainFolder(self, folder_name, isSpam):
        response = self._selectFolder(folder_name, True)
        uids = self._getUIDs(1, int(response[1][0]))
        for uid in uids:
            messageText = self.RetrieveMessage(uid)
            self.bayes.learn(tokenizer.tokenize(messageText), isSpam)

    def Train(self):
        if options.verbose:
            t = time.time()
        if options.imap_ham_train_folders != "":
            ham_training_folders = options.imap_ham_train_folders.split()
            for fol in ham_training_folders:
                self.TrainFolder(fol, False)
        if options.imap_spam_train_folders != "":
            spam_training_folders = options.imap_spam_train_folders.split(' ' )
            for fol in spam_training_folders:
                self.TrainFolder(fol, True)
        self.bayes.store()
        if options.verbose:
            print "Training took", time.time() - t, "seconds."

    def Filter(self):
        if options.verbose:
            t = time.time()
        inbox = self._selectFolder(options.imap_inbox, False)
        # the number of messages are returned
        # get all the corresponding UIDs
        uids = self._getUIDs(1, int(inbox[1][0]))
        
        for uid in uids:
            messageText = self.RetrieveMessage(uid)
            (prob, clues) = self.bayes.spamprob\
                            (tokenizer.tokenize(messageText),
                             evidence=True)
            messageText = self._addHeaders(messageText, prob, clues)
            #uid = self._updateMessage(uid, messageText)
            self._filterMessage(uid, prob)
        if options.verbose:
            print "Filtering took", time.time() - t, "seconds."

    def Logout(self):
        # sign off
        if options.imap_expunge:
            self.imap.expunge()
        self.imap.logout()

    def _addHeaders(self, messageText, prob, clues):
        if options.pop3proxy_strip_incoming_mailids == True:
            s = re.compile(options.pop3proxy_mailid_header_name + \
                           ': [\d-]+[\\r]?[\\n]?')
            messageText = s.sub('', messageText)

        headers, body = re.split(r'\n\r?\n', messageText, 1)
        messageName = self.getNewMessageName()
        headers += '\n'
        if options.pop3proxy_add_mailid_to.find("header") != -1:
            headers += options.pop3proxy_mailid_header_name \
                    + ": " + messageName + "\r\n"
        if options.pop3proxy_add_mailid_to.find("body") != -1:
            body = body[:len(body)-3] + \
                   options.pop3proxy_mailid_header_name + ": " \
                    + messageName + "\r\n.\r\n"

        if options.pop3proxy_include_prob:
            headers += '%s: %s\r\n' % (options.pop3proxy_prob_header_name,
                                       prob)
        if options.pop3proxy_include_thermostat:
            thermostat = '**********'
            headers += '%s: %s\r\n' % \
                      (options.pop3proxy_thermostat_header_name,
                       thermostat[int(prob*10):])
        if options.pop3proxy_include_evidence:
            headers += options.pop3proxy_evidence_header_name + ": "
            headers += "; ".join(["%r: %.2f" % (word, prob)
                     for word, score in clues
                     if (word[0] == '*' or
                         score <= options.clue_mailheader_cutoff or
                         score >= 1.0 - options.clue_mailheader_cutoff)])
            headers += "\r\n"
        headers += "\r\n"
        return headers + body

    def _updateMessage(self, uid, messageText):
        # we can't actually update the message with IMAP
        # XXX (someone tell me if this is wrong!)
        # so what we do is create a new message and delete the old one
        # we return the new uid, which we obtain by searching for the
        # spambayes id
        res = self.imap.append(options.imap_inbox, None,
                               self._extractTimeFromMessage(messageText),
                               messageText)
        self._check(res, "append")
        res = self.imap.uid("STORE", uid, "+FLAGS.SILENT", "(\\Deleted)")
        self._check(res, "uid store")
        res = self.imap.uid("SEARCH", "(TEXT)", messageText)
        self._check(res, "uid search")
        return res[1][0]

    def _extractTimeFromMessage(self, messageText):
        # When we create a new copy of a message, we need to specify
        # a timestamp for the message.  Ideally, this would be the
        # timestamp from the message itself, but for the moment, we
        # just use the current time.
        return imaplib.Time2Internaldate(time.time())

    def _moveMessage(self, uid, dest):
        # The IMAP copy command makes an alias, not a whole new
        # copy, so what we need to do (sigh) is create a new message
        # in the correct folder, and delete the old one
        # XXX (someone tell me if this is wrong, too!)
        response = self.imap.uid("FETCH", uid, "(RFC822.PEEK)")
        self._check(response, 'uid fetch')
        messageText = response[1][0][1]
        response = self.imap.append(dest, None,
                                    self._extractTimeFromMessage(messageText),
                                    messageText)
        self._check(response, "append")
        res = self.imap.uid("STORE", uid, "+FLAGS.SILENT", "(\\Deleted)")
        self._check(response, "uid store")

    def _filterMessage(self, uid, prob):
        if prob < options.ham_cutoff:
            # we leave ham alone
            pass
        elif prob > options.spam_cutoff:
            self._moveMessage(uid, options.imap_spam_folder)
        else:
            self._moveMessage(uid, options.imap_unsure_folder)

if __name__ == '__main__':
    options.verbose = True
    imap_filter = IMAPFilter()
    imap_filter.Login()
    imap_filter.Train()
    imap_filter.Filter()
    imap_filter.Logout()



From anadelonbrin at users.sourceforge.net  Mon Apr  7 01:26:54 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Mon Apr  7 03:26:57 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.24,1.25
Message-ID: <E192R1q-0003CY-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv12257/spambayes

Modified Files:
	Options.py 
Log Message:
First steps towards an IMAP spambayes solution.

Currently will do (very) basic filtering and training.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.24
retrieving revision 1.25
diff -C2 -d -r1.24 -r1.25
*** Options.py	14 Mar 2003 02:14:37 -0000	1.24
--- Options.py	7 Apr 2003 07:26:17 -0000	1.25
***************
*** 415,418 ****
--- 415,434 ----
  smtpproxy_shutdown_address = spambayes_shutdown@localhost
  
+ [imap]
+ imap_server:
+ # the default IMAP port is 143, or 993 if using SSL
+ imap_port: 143
+ imap_username:
+ imap_password:
+ imap_expunge: False
+ imap_inbox: inbox
+ imap_unsure_folder:
+ imap_spam_folder:
+ # comma delimited list of folders that will be examined for messages
+ # to train as ham
+ imap_ham_train_folders:
+ # as for imap_ham_train_folders, but scan for messages to train as spam
+ imap_spam_train_folders:
+ 
  [html_ui]
  html_ui_port: 8880
***************
*** 533,536 ****
--- 549,563 ----
                    'smtpproxy_ports' : string_cracker, 
                    },
+     'imap': {'imap_server' : string_cracker,
+              'imap_port' : int_cracker,
+              'imap_username' : string_cracker,
+              'imap_password' : string_cracker,
+              'imap_inbox' : string_cracker,
+              'imap_unsure_folder' : string_cracker,
+              'imap_spam_folder' : string_cracker,
+              'imap_ham_train_folders' : string_cracker,
+              'imap_spam_train_folders' : string_cracker,
+              'imap_expunge' : boolean_cracker, 
+             },
      'html_ui': {'html_ui_port': int_cracker,
                  'html_ui_launch_browser': boolean_cracker,



From timstone4 at users.sourceforge.net  Mon Apr  7 19:21:30 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr  7 21:21:34 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,NONE,1.1
Message-ID: <E192hnm-0003fc-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv14085

Added Files:
	message.py 
Log Message:
An extension of email.message which includes methods that are useful for
spambayes.  Specifically, message training and classification is remembered
in a simple pickle, by message id.  This allows for convenient untraining by
any client that uses it to handle messages.

--- NEW FILE: message.py ---
#! /usr/bin/env python

'''message.py - Core Spambayes classes.

Classes:
    Message - an email.Message.Message, extended with spambayes methods
    MessageInfoDB - persistent state storage for Message

Abstract:

    MessageInfoDB is a simple shelve persistency class for the persistent
    state of a Message obect.  For the moment, the db name is hard-coded,
    but we'll have to do this a different way.  Mark Hammond's idea is to
    have a master database, that simply keeps track of the names and instances
    of other databases, such as the wordinfo and msginfo databases.  The
    MessageInfoDB currently does not provide iterators, but should at some
    point.  This would allow us to, for example, see how many messages
    have been trained differently than their classification, for fp/fn
    assessment purposes.
    
    Message is an extension of the email package Message class, to include
    persistent message information and Spambayes specific header manipulations.
    The persistent state -currently- consists of the message id, its current
    classification, and its current training.  The payload is not persisted.
    Payload persistence is left to whatever mail client software is being used.
    
Usage:
    A typical classification usage pattern would be something like:
    
    >>>msg = spambayes.message.Message()
    >>>msg.setPayload(substance) # substance comes from somewhere else
    >>>id = msg.setIdFromPayload()
    
    >>>if id is None:
    >>>    msg.setId(time())   # or some unique identifier
     
    >>>msg.delSBHeaders()      # never include sb headers in a classification
    
    >>># bayes object is your responsibility   
    >>>(prob, clues) = bayes.spamprob(msg.asTokens(), evidence=True)

    >>>msg.addSBHeaders(prob, clues)
    
    
    A typical usage pattern to train as spam would be something like:
    
    >>>msg = spambayes.message.Message()
    >>>msg.setPayload(substance) # substance comes from somewhere else
    >>>id = msg.setId(msgid)     # id is a fname, outlook msg id, something...

    >>>msg.delSBHeaders()        # never include sb headers in a train
    
    >>>if msg.isTrndHam():
    >>>    bayes.unlearn(msg.asTokens(), False)  # untrain the ham
    
    >>>bayes.learn(msg.asTokens(), True) # train as spam
    >>>msg.trndAsSpam()
    

To Do:
    o Master DB module
    o Suggestions?

    '''

# This module is part of the spambayes project, which is Copyright 2002
# The Python Software Foundation and is covered by the Python Software
# Foundation license.

__author__ = "Tim Stone <tim@fourstonesExpressions.com>"
__credits__ = "Mark Hammond, Tony Meyers, all the spambayes contributors."

from __future__ import generators

try:
    True, False
except NameError:
    # Maintain compatibility with Python 2.2
    True, False = 1, 0
    def bool(val):
        return not not val

import sys

import email.Message
import email.Parser

from spambayes.tokenizer import tokenize
from spambayes.Options import options

from cStringIO import StringIO

from spambayes import dbmstorage
import shelve

# Make shelve use binary pickles by default.
oldShelvePickler = shelve.Pickler
def binaryDefaultPickler(f, binary=1):
    return oldShelvePickler(f, binary)
shelve.Pickler = binaryDefaultPickler


class MessageInfoDB:
    def __init__(self, db_name, mode='c'):
        self.mode = mode
        self.db_name = db_name
        self.dbm = dbmstorage.open(self.db_name, self.mode)
        self.db = shelve.Shelf(self.dbm)

    def store(self):
        self.db.sync()

    def _getState(self, msg):
        try:
            return self.db[msg.getId()]
        except KeyError:
            return None

    def _setState(self, msg):
        self.db[msg.getId()] = msg

    def _delState(self, msg):
        del self.db[msg.getId()]
        
# this should come from a mark hammond idea of a master db
msginfoDB = MessageInfoDB("spambayes.messageinfo.db")


class Message(email.Message.Message):
    '''An email.Message.Message extended for Spambayes'''

    def __init__(self):
        email.Message.Message.__init__(self)

        # persistent state
        self.id = None
        self.c = None
        self.t = None
        
        # non-persistent state includes all of email.Message.Message state

        
    def setPayload(self, payload):
        prs = email.Parser.HeaderParser()
        prs._parseheaders(self, StringIO(payload))
        # we may want to do some header parsing error handling here
        # to try to extract important headers regardless of malformations
        prs._parsebody(self, StringIO(payload))
        
    def setIdFromPayload(self):
        try:
            self.setId(self[options.pop3proxy_mailid_header_name])
        except KeyError:
            return None

        return self.id
    
    def setId(self, id):
        if self.id:
            raise ValueError, "MsgId has already been set, cannot be changed"
            
        # we should probably enforce type(id) is StringType.
        # the database will insist upon it, but at that point, it's harder
        # to diagnose
        if id is None:
            raise ValueError, "MsgId must not be None"
            
        self.id = id
        msginfoDB._getState(self)
        
    def getId(self):
        return self.id
        
    def addSBHeaders(self, prob, clues):
        '''Add hammie header, and remember message's classification.  Also,
        add optional headers if needed.'''
        
        if prob < options.ham_cutoff:
            disposition = options.header_ham_string
            self.clsfyAsHam()
        elif prob > options.spam_cutoff:
            disposition = options.header_spam_string
            self.clsfyAsSpam()
        else:
            disposition = options.header_unsure_string
            self.clsfyAsUnsure()

        self[options.hammie_header_name] = disposition
        
        if options.pop3proxy_include_prob:
            self[options.pop3proxy_prob_header_name] = prob
            
        if options.pop3proxy_include_thermostat:
            thermostat = '**********'
            self[options.pop3proxy_thermostat_header_name] = \
                               thermostat[:int(prob*10)]
                               
        if options.pop3proxy_include_evidence:
            evd = "; ".join(["%r: %.2f" % (word, score)
                     for word, score in clues
                     if (word[0] == '*' or
                         score <= options.clue_mailheader_cutoff or
                         score >= 1.0 - options.clue_mailheader_cutoff)])
                         
            self[options.pop3proxy_evidence_header_name] = evd
        
        if options.pop3proxy_add_mailid_to.find("header") != -1:
            self[options.pop3proxy_mailid_header_name] = self.id

# This won't work for now, because email.Message does not isolate message body
# This is also not consistent with the function of this method...
#        if options.pop3proxy_add_mailid_to.find("body") != -1:
#            body = body[:len(body)-3] + \
#                   options.pop3proxy_mailid_header_name + ": " \
#                    + messageName + "\r\n.\r\n"


    def delSBHeaders(self):
        del self[options.hammie_header_name]
        del self[options.pop3proxy_mailid_header_name]
        del self[options.hammie_header_name + "-ID"]  # test mode header
        del self[options.pop3proxy_prob_header_name]
        del self[options.pop3proxy_thermostat_header_name]
        del self[options.pop3proxy_evidence_header_name]
    
    def asTokens(self):
        # use as_string() here because multipart/digest will return
        # a list of message objects if get_payload() is used
        return tokenize(self.as_string())
        
    def modified(self):
        if self.id:    # only persist if key is present
            msginfoDB._setState(self)
        
    def isClsfdSpam(self):
        return self.c == 's'
        
    def isClsfdHam(self):
        return self.c == 'h'
        
    def isClsfdUnsure(self):
        return self.c == 'u'
        
    def isClassified(self):
        return not self.c is None
        
    def clsfyAsSpam(self):
        self.c = 's'
        self.modified()
        
    def clsfyAsHam(self):
        self.c = 'h'
        self.modified()
        
    def clsfyAsUnsure(self):
        self.c = 'u'
        self.modified()
    
    def getClassification(self):
        return self.c
        
    def isTrndSpam(self):
        return self.t == 's'
        
    def isTrndHam(self):
        return self.t == 'h'
    
    def trndAsSpam(self):
        self.t = 's'
        self.modified()
        
    def trndAsHam(self):
        self.t = 'h'
        self.modified()
        
    def notTrained(self):
        self.t = None
        self.modified()
        
    def isTrained(self):
        return not self.t is None
    
    def getTraining(self):
        return self.t
        
    def __repr__(self):
        return "core.Message%r" % repr(self.__getstate__())

    def __getstate__(self):
        return (self.id, self.c, self.t)

    def __setstate__(self, t):
        (self.id, self.c, self.t) = t


From timstone4 at users.sourceforge.net  Mon Apr  7 19:25:04 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr  7 21:25:13 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.1,1.2
Message-ID: <E192hrE-0003tV-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv14906

Modified Files:
	imapfilter.py 
Log Message:
Changed to use the message class.  Untested at this point.  Your turn, Tony.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** imapfilter.py	7 Apr 2003 07:26:24 -0000	1.1
--- imapfilter.py	8 Apr 2003 01:24:17 -0000	1.2
***************
*** 49,55 ****
          filename = os.path.expanduser(filename)
          if options.pop3proxy_persistent_use_database:
!             self.bayes = storage.DBDictClassifier(filename)
          else:
!             self.bayes = storage.PickledClassifier(filename)
          if options.verbose:
              print "Done."
--- 49,55 ----
          filename = os.path.expanduser(filename)
          if options.pop3proxy_persistent_use_database:
!             self.classifier = storage.DBDictClassifier(filename)
          else:
!             self.classifier = storage.PickledClassifier(filename)
          if options.verbose:
              print "Done."
***************
*** 109,113 ****
              print "Could not retrieve message (id %s)" % uid
              messageText = ""
!         return messageText
  
      def TrainFolder(self, folder_name, isSpam):
--- 109,120 ----
              print "Could not retrieve message (id %s)" % uid
              messageText = ""
! 
!         msg = spambayes.message.Message()
!         msg.setPayload(messageText)
!         msg.setId(uid)
! 
!         msg.delSBHeaders()  # never include sb headers in a train
!                 
!         return msg
  
      def TrainFolder(self, folder_name, isSpam):
***************
*** 115,120 ****
          uids = self._getUIDs(1, int(response[1][0]))
          for uid in uids:
!             messageText = self.RetrieveMessage(uid)
!             self.bayes.learn(tokenizer.tokenize(messageText), isSpam)
  
      def Train(self):
--- 122,139 ----
          uids = self._getUIDs(1, int(response[1][0]))
          for uid in uids:
!             msg = self.RetrieveMessage(uid)
! 
!             if msg.isTrained():
!                 if isSpam and msg.isTrndHam():
!                     bayes.unlearn(msg.asTokens(), False)  # untrain the ham
!                 elif not isSpam and msg.isTrndSpam():
!                     bayes.unlearn(msg.asTokens(), True)
!                 
!             bayes.learn(msg.asTokens(), isSpam) # train as spam
! 
!             if isSpam:
!                 msg.trndAsSpam()
!             else:
!                 msg.trndAsHam()
  
      def Train(self):
***************
*** 129,133 ****
              for fol in spam_training_folders:
                  self.TrainFolder(fol, True)
!         self.bayes.store()
          if options.verbose:
              print "Training took", time.time() - t, "seconds."
--- 148,152 ----
              for fol in spam_training_folders:
                  self.TrainFolder(fol, True)
!         self.classifier.store()
          if options.verbose:
              print "Training took", time.time() - t, "seconds."
***************
*** 142,152 ****
          
          for uid in uids:
!             messageText = self.RetrieveMessage(uid)
!             (prob, clues) = self.bayes.spamprob\
!                             (tokenizer.tokenize(messageText),
!                              evidence=True)
!             messageText = self._addHeaders(messageText, prob, clues)
!             #uid = self._updateMessage(uid, messageText)
!             self._filterMessage(uid, prob)
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
--- 161,169 ----
          
          for uid in uids:
!             msg = self.RetrieveMessage(uid)
!             (prob, clues) = self.classifier.spamprob(msg.asTokens(), evidence=True)
!             msg.addSBHeaders(prob, clues) # adds headers and remembers classification
!             self._updateMessage(msg)
!             self._filterMessage(msg)
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
***************
*** 158,198 ****
          self.imap.logout()
  
!     def _addHeaders(self, messageText, prob, clues):
!         if options.pop3proxy_strip_incoming_mailids == True:
!             s = re.compile(options.pop3proxy_mailid_header_name + \
!                            ': [\d-]+[\\r]?[\\n]?')
!             messageText = s.sub('', messageText)
! 
!         headers, body = re.split(r'\n\r?\n', messageText, 1)
!         messageName = self.getNewMessageName()
!         headers += '\n'
!         if options.pop3proxy_add_mailid_to.find("header") != -1:
!             headers += options.pop3proxy_mailid_header_name \
!                     + ": " + messageName + "\r\n"
!         if options.pop3proxy_add_mailid_to.find("body") != -1:
!             body = body[:len(body)-3] + \
!                    options.pop3proxy_mailid_header_name + ": " \
!                     + messageName + "\r\n.\r\n"
! 
!         if options.pop3proxy_include_prob:
!             headers += '%s: %s\r\n' % (options.pop3proxy_prob_header_name,
!                                        prob)
!         if options.pop3proxy_include_thermostat:
!             thermostat = '**********'
!             headers += '%s: %s\r\n' % \
!                       (options.pop3proxy_thermostat_header_name,
!                        thermostat[int(prob*10):])
!         if options.pop3proxy_include_evidence:
!             headers += options.pop3proxy_evidence_header_name + ": "
!             headers += "; ".join(["%r: %.2f" % (word, prob)
!                      for word, score in clues
!                      if (word[0] == '*' or
!                          score <= options.clue_mailheader_cutoff or
!                          score >= 1.0 - options.clue_mailheader_cutoff)])
!             headers += "\r\n"
!         headers += "\r\n"
!         return headers + body
! 
!     def _updateMessage(self, uid, messageText):
          # we can't actually update the message with IMAP
          # XXX (someone tell me if this is wrong!)
--- 175,179 ----
          self.imap.logout()
  
!     def _updateMessage(self, msg):
          # we can't actually update the message with IMAP
          # XXX (someone tell me if this is wrong!)
***************
*** 201,214 ****
          # spambayes id
          res = self.imap.append(options.imap_inbox, None,
!                                self._extractTimeFromMessage(messageText),
!                                messageText)
          self._check(res, "append")
!         res = self.imap.uid("STORE", uid, "+FLAGS.SILENT", "(\\Deleted)")
          self._check(res, "uid store")
!         res = self.imap.uid("SEARCH", "(TEXT)", messageText)
          self._check(res, "uid search")
          return res[1][0]
  
!     def _extractTimeFromMessage(self, messageText):
          # When we create a new copy of a message, we need to specify
          # a timestamp for the message.  Ideally, this would be the
--- 182,195 ----
          # spambayes id
          res = self.imap.append(options.imap_inbox, None,
!                                self._extractTimeFromMessage(msg),
!                                msg.payload())
          self._check(res, "append")
!         res = self.imap.uid("STORE", msg.getId(), "+FLAGS.SILENT", "(\\Deleted)")
          self._check(res, "uid store")
!         res = self.imap.uid("SEARCH", "(TEXT)", msg.payload())
          self._check(res, "uid search")
          return res[1][0]
  
!     def _extractTimeFromMessage(self, msg):
          # When we create a new copy of a message, we need to specify
          # a timestamp for the message.  Ideally, this would be the
***************
*** 217,243 ****
          return imaplib.Time2Internaldate(time.time())
  
!     def _moveMessage(self, uid, dest):
          # The IMAP copy command makes an alias, not a whole new
          # copy, so what we need to do (sigh) is create a new message
          # in the correct folder, and delete the old one
          # XXX (someone tell me if this is wrong, too!)
!         response = self.imap.uid("FETCH", uid, "(RFC822.PEEK)")
          self._check(response, 'uid fetch')
!         messageText = response[1][0][1]
!         response = self.imap.append(dest, None,
!                                     self._extractTimeFromMessage(messageText),
!                                     messageText)
          self._check(response, "append")
!         res = self.imap.uid("STORE", uid, "+FLAGS.SILENT", "(\\Deleted)")
          self._check(response, "uid store")
  
!     def _filterMessage(self, uid, prob):
!         if prob < options.ham_cutoff:
              # we leave ham alone
              pass
!         elif prob > options.spam_cutoff:
!             self._moveMessage(uid, options.imap_spam_folder)
          else:
!             self._moveMessage(uid, options.imap_unsure_folder)
  
  if __name__ == '__main__':
--- 198,226 ----
          return imaplib.Time2Internaldate(time.time())
  
!     def _moveMessage(self, msg, dest):
          # The IMAP copy command makes an alias, not a whole new
          # copy, so what we need to do (sigh) is create a new message
          # in the correct folder, and delete the old one
          # XXX (someone tell me if this is wrong, too!)
!         response = self.imap.uid("FETCH", msg.getId(), "(RFC822.PEEK)")
          self._check(response, 'uid fetch')
! 
!         msg = spambayes.message.Message()
!         msg.setPayload(response[1][0][1])
!         msg.setId(_extractTimeFromMessage(msg))
! 
!         response = self.imap.append(dest, None, msg.getId(), msg.payload())
          self._check(response, "append")
!         res = self.imap.uid("STORE", msg.getId(), "+FLAGS.SILENT", "(\\Deleted)")
          self._check(response, "uid store")
  
!     def _filterMessage(self, msg, prob):
!         if msg.isClsfdHam():
              # we leave ham alone
              pass
!         elif msg.isClsfdSpam():
!             self._moveMessage(msg, options.imap_spam_folder)
          else:
!             self._moveMessage(msg, options.imap_unsure_folder)
  
  if __name__ == '__main__':



From anadelonbrin at users.sourceforge.net  Tue Apr  8 01:35:44 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Tue Apr  8 03:35:50 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.1,1.2
Message-ID: <E192ndw-0000oU-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv3092/spambayes

Modified Files:
	message.py 
Log Message:
Fixes the spelling of my name ;)
Temp fix for infinite recursion error.
Adds a couple of little functions to simply use.
Adds a changeId function.

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** message.py	8 Apr 2003 01:21:28 -0000	1.1
--- message.py	8 Apr 2003 07:35:42 -0000	1.2
***************
*** 69,73 ****
  
  __author__ = "Tim Stone <tim@fourstonesExpressions.com>"
! __credits__ = "Mark Hammond, Tony Meyers, all the spambayes contributors."
  
  from __future__ import generators
--- 69,73 ----
  
  __author__ = "Tim Stone <tim@fourstonesExpressions.com>"
! __credits__ = "Mark Hammond, Tony Meyer, all the spambayes contributors."
  
  from __future__ import generators
***************
*** 94,102 ****
  import shelve
  
  # Make shelve use binary pickles by default.
! oldShelvePickler = shelve.Pickler
! def binaryDefaultPickler(f, binary=1):
!     return oldShelvePickler(f, binary)
! shelve.Pickler = binaryDefaultPickler
  
  
--- 94,104 ----
  import shelve
  
+ # XXX Tim, what do you want to do here?  This
+ # XXX recurses infinately at the moment
  # Make shelve use binary pickles by default.
! #oldShelvePickler = shelve.Pickler
! #def binaryDefaultPickler(f, binary=1):
! #    return oldShelvePickler(f, binary)
! #shelve.Pickler = binaryDefaultPickler
  
  
***************
*** 155,163 ****
  
          return self.id
      
      def setId(self, id):
          if self.id:
              raise ValueError, "MsgId has already been set, cannot be changed"
!             
          # we should probably enforce type(id) is StringType.
          # the database will insist upon it, but at that point, it's harder
--- 157,179 ----
  
          return self.id
+ 
+     def changeID(self, id):
+         # We cannot re-set an id (see below).  However there are
+         # occasionally times when the id for a message will change,
+         # for example, on an IMAP server (or possibly an exchange
+         # server), the server may change the ids that we are using
+         # We enforce that this must be an explicit *change* rather
+         # than simply re-setting, by having this as a separate
+         # function
+         if not self.id:
+             raise ValueError, "MsgID has not been set, cannot be changed"
+         self._setId(id)
      
      def setId(self, id):
          if self.id:
              raise ValueError, "MsgId has already been set, cannot be changed"
!         self._setId(id)
! 
!     def _setId(self, id):    
          # we should probably enforce type(id) is StringType.
          # the database will insist upon it, but at that point, it's harder
***************
*** 274,277 ****
--- 290,306 ----
          self.modified()
          
+     def isTrndAs(self, isSpam):
+         if self.t == 'h' and not isSpam:
+             return True
+         if self.t == 's' and isSpam:
+             return True
+         return False
+ 
+     def trndAs(self, isSpam):
+         if isSpam:
+             self.t = 's'
+         else:
+             self.t = 'h'
+ 
      def notTrained(self):
          self.t = None



From anadelonbrin at users.sourceforge.net  Tue Apr  8 01:37:31 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Tue Apr  8 03:37:35 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.2,1.3
Message-ID: <E192nff-00019i-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv4387

Modified Files:
	imapfilter.py 
Log Message:
Introduces an IMAPMessage class based on the
spambayes Message class.
Introduces an iterable IMAPFolder class.
Changes the code to use all of this.
Changed to allow multiple folders to filter.
Training seems to work, although filtering isn't.  I'll get to it.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** imapfilter.py	8 Apr 2003 01:24:17 -0000	1.2
--- imapfilter.py	8 Apr 2003 07:37:28 -0000	1.3
***************
*** 1,4 ****
--- 1,6 ----
  #!/usr/bin/env python
  
+ from __future__ import generators
+ 
  """An IMAP filter.  An IMAP message box is scanned and all non-scored
  messages are scored and (where necessary) filtered.
***************
*** 18,28 ****
  
  __author__ = "Tony Meyer <ta-meyer@ihug.co.nz>"
! __credits__ = "All the Spambayes folk."
  
! # This code will benefit immensely from
! # (a) The new message class, which can hold information such as
! #     whether a message has been seen before
! # (b) The new header stuff, which will abstract out adding all
! #     the headers
  
  try:
--- 20,31 ----
  
  __author__ = "Tony Meyer <ta-meyer@ihug.co.nz>"
! __credits__ = "Tim Stone, All the Spambayes folk."
  
! # Tony thinks it would be nice if there was a web ui to
! # this for the initial setup (i.e. like pop3proxy), which offered
! # a list of folders to filter/train/etc.  It could then record a
! # uid for the folder rather than a name, and it avoids the problems
! # with different imap servers having different naming styles
! # a list is retrieved via imap.list()
  
  try:
***************
*** 37,47 ****
  import re
  import time
  
  from spambayes.Options import options
! from spambayes import tokenizer, storage
  
  class IMAPFilter(object):
      def __init__(self):
!         self.imap = imaplib.IMAP4(options.imap_server, options.imap_port)
          if options.verbose:
              print "Loading database...",
--- 40,138 ----
  import re
  import time
+ import sys
  
  from spambayes.Options import options
! from spambayes import tokenizer, storage, message
! 
! # global IMAPlib object
! imap = None
! 
! class IMAPMessage(message.Message):
!     # response checking is necessary throughout this class
!     def __init__(self, folder_id, folder_name, message_id):
!         message.Message.__init__(self)
!         self.setId(message_id)
!         self.folder_id = folder_id
!         self.folder_name = folder_name
! 
!     def extractTime(self):
!         # When we create a new copy of a message, we need to specify
!         # a timestamp for the message.  Ideally, this would be the
!         # timestamp from the message itself, but for the moment, we
!         # just use the current time.
!         return imaplib.Time2Internaldate(time.time())
! 
!     def Update(self):
!         # we can't actually update the message with IMAP
!         # so what we do is create a new message and delete the old one
!         response = imap.append(self.folder_name, None,
!                                self.extractTime(), self.get_payload())
!         response = imap.select(self.folder_name, False)
!         response = imap.uid("STORE", self.getId(), "+FLAGS.SILENT",
!                                  "(\\Deleted)")
!         # we need to update the uid, as it will have changed
!         response = imap.uid("SEARCH", "(TEXT)", self.get_payload())
!         self.changeId(response[1][0])
! 
! 
! class IMAPFolder(object):
!     # response checking is necessary throughout this class
!     def __init__(self, folder_name, readOnly=True):
!         self.name = folder_name
!         # Convert folder name to a uid
!         self.uid = None
!         response = imap.select(self.name, readOnly)
!         responses = imap.response("OK")[1]
!         for response in responses:
!             if response[:13] == "[UIDVALIDITY ":
!                 r = re.compile(r"(?P<uid>\d+)")
!                 self.uid = r.search(response[13:]).group('uid')
!         # We really want to use RFC822.PEEK here, as that doesn't effect
!         # the status of the message.  Unfortunately, it appears that not
!         # all IMAP servers support this, even though it is in RFC1730
!         self.rfc822_command = "(RFC822.PEEK)"
!         response = imap.fetch("1:1", self.rfc822_command)
!         if response[0] != "OK":
!             self.rfc822_command = "(RFC822)"
!         
!     def __iter__(self):
!         '''IMAPFolder is iterable'''
!         for key in self.keys():
!             try:
!                 yield self[key]
!             except KeyError:
!                 pass
! 
!     def keys(self):
!         '''Returns uids for all the messages in the folder'''
!         # request message range
!         response = imap.select(self.name, True)
!         total_messages = response[1][0]
!         if total_messages == '0':
!             return []
!         response = imap.fetch("1:" + total_messages, "UID")
!         r = re.compile(r"[0-9]+ \(UID ([0-9]+)\)")
!         uids = []
!         for i in response[1]:
!             mo = r.match(i)
!             if mo is not None:
!                 uids.append(mo.group(1))
!         return uids
! 
!     def __getitem__(self, key):
!         '''Return message matching the given uid'''
!         response = imap.uid("FETCH", key, self.rfc822_command)
!         messageText = response[1][0][1]
!         # we return an instance of *our* message class, not the
!         # raw rfc822 message
!         msg = IMAPMessage(self.uid, self.name, key)
!         msg.setPayload(messageText)
!         return msg
!        
  
  class IMAPFilter(object):
      def __init__(self):
!         global imap
!         imap = imaplib.IMAP4(options.imap_server, options.imap_port)
          if options.verbose:
              print "Loading database...",
***************
*** 54,64 ****
          if options.verbose:
              print "Done."
-         # Unique names for cached messages - see getNewMessageName() below.
-         self.lastBaseMessageName = ''
-         self.uniquifier = 2
- 
-     def Login(self):
-         lgn = self.imap.login(options.imap_username, options.imap_password)
-         self._check(lgn, 'login')
  
      def _check(self, response, command):
--- 145,148 ----
***************
*** 67,139 ****
              sys.exit(-1)
  
-     def _getUIDs(self, low, high):
-         # Retreive a list of uids corresponding to the given range
-         if high < low: return []
-         # request message range
-         range = str(low) + ":" + str(high)
-         res = self.imap.fetch(range, "UID")
-         self._check(res, 'fetch')
-         r = re.compile(r"[0-9]+ \(UID ([0-9]+)\)")
-         res2 = []
-         for i in res[1]:
-             mo = r.match(i)
-             if mo is not None:
-                 res2.append(mo.group(1))
-         return res2
- 
-     def getNewMessageName(self):
-         # The message name is the time it arrived, with a uniquifier
-         # appended if two arrive within one clock tick of each other.
-         # (This is completely taken from the same function in pop3proxy's
-         # State class.)
-         messageName = "%10.10d" % long(time.time())
-         if messageName == self.lastBaseMessageName:
-             messageName = "%s-%d" % (messageName, self.uniquifier)
-             self.uniquifier += 1
-         else:
-             self.lastBaseMessageName = messageName
-             self.uniquifier = 2
-         return messageName
- 
      def _selectFolder(self, name, read_only):
!         folder = self.imap.select(name, read_only)
          self._check(folder, 'select')
          return folder
  
!     def RetrieveMessage(self, uid):
!         response = self.imap.uid("FETCH", uid, "(RFC822.PEEK)")
!         self._check(response, 'uid fetch')
!         try:
!             messageText = response[1][0][1]
!         except:
!             print "Could not retrieve message (id %s)" % uid
!             messageText = ""
! 
!         msg = spambayes.message.Message()
!         msg.setPayload(messageText)
!         msg.setId(uid)
! 
!         msg.delSBHeaders()  # never include sb headers in a train
!                 
!         return msg
  
      def TrainFolder(self, folder_name, isSpam):
!         response = self._selectFolder(folder_name, True)
!         uids = self._getUIDs(1, int(response[1][0]))
!         for uid in uids:
!             msg = self.RetrieveMessage(uid)
! 
              if msg.isTrained():
!                 if isSpam and msg.isTrndHam():
!                     bayes.unlearn(msg.asTokens(), False)  # untrain the ham
!                 elif not isSpam and msg.isTrndSpam():
!                     bayes.unlearn(msg.asTokens(), True)
!                 
!             bayes.learn(msg.asTokens(), isSpam) # train as spam
! 
!             if isSpam:
!                 msg.trndAsSpam()
!             else:
!                 msg.trndAsHam()
  
      def Train(self):
--- 151,175 ----
              sys.exit(-1)
  
      def _selectFolder(self, name, read_only):
!         folder = imap.select(name, read_only)
          self._check(folder, 'select')
          return folder
  
!     def Login(self):
!         lgn = imap.login(options.imap_username, options.imap_password)
!         self._check(lgn, 'login')
  
      def TrainFolder(self, folder_name, isSpam):
!         folder = IMAPFolder(folder_name)
!         for msg in folder:
              if msg.isTrained():
!                 if msg.isTrndAs(isSpam):
!                     # already trained, nothing for us to do here
!                     # (we don't want to train the same message twice)
!                     continue
!                 if msg.isTrained():
!                     self.classifier.unlearn(msg.asTokens(), not isSpam)
!             self.classifier.learn(msg.asTokens(), isSpam)
!             msg.trndAs(isSpam)
  
      def Train(self):
***************
*** 155,169 ****
          if options.verbose:
              t = time.time()
!         inbox = self._selectFolder(options.imap_inbox, False)
!         # the number of messages are returned
!         # get all the corresponding UIDs
!         uids = self._getUIDs(1, int(inbox[1][0]))
!         
!         for uid in uids:
!             msg = self.RetrieveMessage(uid)
!             (prob, clues) = self.classifier.spamprob(msg.asTokens(), evidence=True)
!             msg.addSBHeaders(prob, clues) # adds headers and remembers classification
!             self._updateMessage(msg)
!             self._filterMessage(msg)
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
--- 191,204 ----
          if options.verbose:
              t = time.time()
!         for filter_folder in options.imap_filter_folders.split():
!             folder = IMAPFolder(filter_folder, False)
!             for msg in folder:
!                 (prob, clues) = self.classifier.spamprob(msg.asTokens(),
!                                                          evidence=True)
!                 # add headers and remember classification
!                 msg.addSBHeaders(prob, clues)
!                 # XXX updating is disabled for the moment
!                 # msg.Update()
!                 self._filterMessage(msg)
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
***************
*** 172,193 ****
          # sign off
          if options.imap_expunge:
!             self.imap.expunge()
!         self.imap.logout()
! 
!     def _updateMessage(self, msg):
!         # we can't actually update the message with IMAP
!         # XXX (someone tell me if this is wrong!)
!         # so what we do is create a new message and delete the old one
!         # we return the new uid, which we obtain by searching for the
!         # spambayes id
!         res = self.imap.append(options.imap_inbox, None,
!                                self._extractTimeFromMessage(msg),
!                                msg.payload())
!         self._check(res, "append")
!         res = self.imap.uid("STORE", msg.getId(), "+FLAGS.SILENT", "(\\Deleted)")
!         self._check(res, "uid store")
!         res = self.imap.uid("SEARCH", "(TEXT)", msg.payload())
!         self._check(res, "uid search")
!         return res[1][0]
  
      def _extractTimeFromMessage(self, msg):
--- 207,212 ----
          # sign off
          if options.imap_expunge:
!             imap.expunge()
!         imap.logout()
  
      def _extractTimeFromMessage(self, msg):
***************
*** 198,221 ****
          return imaplib.Time2Internaldate(time.time())
  
!     def _moveMessage(self, msg, dest):
          # The IMAP copy command makes an alias, not a whole new
          # copy, so what we need to do (sigh) is create a new message
          # in the correct folder, and delete the old one
!         # XXX (someone tell me if this is wrong, too!)
!         response = self.imap.uid("FETCH", msg.getId(), "(RFC822.PEEK)")
          self._check(response, 'uid fetch')
! 
!         msg = spambayes.message.Message()
          msg.setPayload(response[1][0][1])
!         msg.setId(_extractTimeFromMessage(msg))
  
!         response = self.imap.append(dest, None, msg.getId(), msg.payload())
          self._check(response, "append")
!         res = self.imap.uid("STORE", msg.getId(), "+FLAGS.SILENT", "(\\Deleted)")
          self._check(response, "uid store")
  
!     def _filterMessage(self, msg, prob):
          if msg.isClsfdHam():
              # we leave ham alone
              pass
          elif msg.isClsfdSpam():
--- 217,246 ----
          return imaplib.Time2Internaldate(time.time())
  
!     def _moveMessage(self, old_msg, dest):
          # The IMAP copy command makes an alias, not a whole new
          # copy, so what we need to do (sigh) is create a new message
          # in the correct folder, and delete the old one
!         # XXX (someone tell me if this is wrong)
!         response = imap.uid("FETCH", old_msg.getId(), "(RFC822)")
          self._check(response, 'uid fetch')
!         msg = message.Message()
          msg.setPayload(response[1][0][1])
!         #response = imap.uid("SEARCH", "(TEXT)", msg.get_payload())
!         #self._check(response, "search")
!         #self.changeId(response[1][0])
  
!         response = imap.append(dest, None,
!                                self._extractTimeFromMessage(msg),
!                                msg.get_payload())
          self._check(response, "append")
!         self._selectFolder(old_msg.folder_name, False)
!         response = imap.uid("STORE", old_msg.getId(), "+FLAGS.SILENT",
!                             "(\\Deleted)")
          self._check(response, "uid store")
  
!     def _filterMessage(self, msg):
          if msg.isClsfdHam():
              # we leave ham alone
+             print "untouched"
              pass
          elif msg.isClsfdSpam():
***************
*** 227,230 ****
--- 252,256 ----
      options.verbose = True
      imap_filter = IMAPFilter()
+ #    imap_filter.imap.debug = 10
      imap_filter.Login()
      imap_filter.Train()



From anadelonbrin at users.sourceforge.net  Tue Apr  8 01:37:33 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Tue Apr  8 03:37:37 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.25,1.26
Message-ID: <E192nfh-00019w-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv4387/spambayes

Modified Files:
	Options.py 
Log Message:
Introduces an IMAPMessage class based on the
spambayes Message class.
Introduces an iterable IMAPFolder class.
Changes the code to use all of this.
Changed to allow multiple folders to filter.
Training seems to work, although filtering isn't.  I'll get to it.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** Options.py	7 Apr 2003 07:26:17 -0000	1.25
--- Options.py	8 Apr 2003 07:37:29 -0000	1.26
***************
*** 422,426 ****
  imap_password:
  imap_expunge: False
! imap_inbox: inbox
  imap_unsure_folder:
  imap_spam_folder:
--- 422,426 ----
  imap_password:
  imap_expunge: False
! imap_filter_folders: INBOX
  imap_unsure_folder:
  imap_spam_folder:
***************
*** 553,557 ****
               'imap_username' : string_cracker,
               'imap_password' : string_cracker,
!              'imap_inbox' : string_cracker,
               'imap_unsure_folder' : string_cracker,
               'imap_spam_folder' : string_cracker,
--- 553,557 ----
               'imap_username' : string_cracker,
               'imap_password' : string_cracker,
!              'imap_filter_folders' : string_cracker,
               'imap_unsure_folder' : string_cracker,
               'imap_spam_folder' : string_cracker,



From timstone4 at users.sourceforge.net  Tue Apr  8 09:24:46 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Tue Apr  8 11:24:49 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.2,1.3
Message-ID: <E192uxq-0006I7-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv24156

Modified Files:
	message.py 
Log Message:
Added a couple more methods to support copying one message to another

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** message.py	8 Apr 2003 07:35:42 -0000	1.2
--- message.py	8 Apr 2003 15:24:43 -0000	1.3
***************
*** 187,190 ****
--- 187,195 ----
      def getId(self):
          return self.id
+ 
+     def copy(self, old_msg):
+         self.setPayload(old_msg.payload())  # this is expensive...
+         self.setClassification(old_msg.getClassification())
+         self.setTraining(old_msg.getTraining())
          
      def addSBHeaders(self, prob, clues):
***************
*** 275,278 ****
--- 280,290 ----
      def getClassification(self):
          return self.c
+ 
+     def setClassification(self, cls):
+         if cls == 's' or cls == 'h' or cls == 'u' or cls is None:
+             self.c = cls
+             self.modified()
+         else:
+             raise ValueError
          
      def isTrndSpam(self):
***************
*** 312,316 ****
      def getTraining(self):
          return self.t
!         
      def __repr__(self):
          return "core.Message%r" % repr(self.__getstate__())
--- 324,335 ----
      def getTraining(self):
          return self.t
! 
!     def setTraining(self, trn):
!         if trn == 's' or trn == 'h' or trn is None:
!             self.t = trn
!             self.modified()
!         else:
!             raise ValueError
!          
      def __repr__(self):
          return "core.Message%r" % repr(self.__getstate__())



From timstone4 at users.sourceforge.net  Tue Apr  8 09:28:06 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Tue Apr  8 11:28:10 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.3,1.4
Message-ID: <E192v14-0006d2-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv25441

Modified Files:
	imapfilter.py 
Log Message:
Added logic to ensure that classification and training memory is preserved
when IMAP messages are altered (i.e. deleted and added with a new id),
and when messages are retrained.  Again... unable to test, so your turn,
Tony.  I'm gonna have to get an IMAP thingy if I'm going to do much work
on this <wink>.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** imapfilter.py	8 Apr 2003 07:37:28 -0000	1.3
--- imapfilter.py	8 Apr 2003 15:28:03 -0000	1.4
***************
*** 75,78 ****
--- 75,95 ----
          self.changeId(response[1][0])
  
+     def Delete(self):
+         self._selectFolder(self.folder_name, False)
+         response = imap.uid("STORE", self.getId(), "+FLAGS.SILENT",
+                             "(\\Deleted)")
+         self._check(response, "uid store")
+ 
+         # XXX there should actually be a delete from the msgid database here...
+         self.notTrained()
+         self.notClassified()
+ 
+     def Append(self):
+         response = imap.append(self.folder_name, None,
+                                self.getId(),
+                                self.get_payload())
+         self._check(response, "append")
+ 
+ 
  
  class IMAPFolder(object):
***************
*** 135,138 ****
--- 152,159 ----
          global imap
          imap = imaplib.IMAP4(options.imap_server, options.imap_port)
+         
+         self.spam_folder = IMAPFolder(options.imap_spam_folder)
+         self.unsure_folder = IMAPFolder(options.imap_unsure_folder)
+         
          if options.verbose:
              print "Loading database...",
***************
*** 163,175 ****
          folder = IMAPFolder(folder_name)
          for msg in folder:
!             if msg.isTrained():
!                 if msg.isTrndAs(isSpam):
!                     # already trained, nothing for us to do here
!                     # (we don't want to train the same message twice)
!                     continue
!                 if msg.isTrained():
!                     self.classifier.unlearn(msg.asTokens(), not isSpam)
!             self.classifier.learn(msg.asTokens(), isSpam)
!             msg.trndAs(isSpam)
  
      def Train(self):
--- 184,200 ----
          folder = IMAPFolder(folder_name)
          for msg in folder:
!             # XXX I've rewritten this logic.  It looks a bit strange,
!             # because of the msg.notTrained call immediately before the
!             # test for isTrained, but this is safer.  Once the message has
!             # been untrained, it's training memory should reflect that
!             # on the off chance that for some reason the training breaks,
!             # which happens on occasion (the tokenizer is not yet perfect)
!             if msg.isTrndAs(not isSpam):
!                 self.classifier.unlearn(msg.asTokens(), not isSpam)
!                 msg.notTrained()
! 
!             if not msg.isTrained():
!                 self.classifier.learn(msg.asTokens(), isSpam)
!                 msg.trndAs(isSpam)
  
      def Train(self):
***************
*** 210,220 ****
          imap.logout()
  
-     def _extractTimeFromMessage(self, msg):
-         # When we create a new copy of a message, we need to specify
-         # a timestamp for the message.  Ideally, this would be the
-         # timestamp from the message itself, but for the moment, we
-         # just use the current time.
-         return imaplib.Time2Internaldate(time.time())
- 
      def _moveMessage(self, old_msg, dest):
          # The IMAP copy command makes an alias, not a whole new
--- 235,238 ----
***************
*** 222,241 ****
          # in the correct folder, and delete the old one
          # XXX (someone tell me if this is wrong)
!         response = imap.uid("FETCH", old_msg.getId(), "(RFC822)")
!         self._check(response, 'uid fetch')
!         msg = message.Message()
!         msg.setPayload(response[1][0][1])
          #response = imap.uid("SEARCH", "(TEXT)", msg.get_payload())
          #self._check(response, "search")
          #self.changeId(response[1][0])
  
!         response = imap.append(dest, None,
!                                self._extractTimeFromMessage(msg),
!                                msg.get_payload())
!         self._check(response, "append")
!         self._selectFolder(old_msg.folder_name, False)
!         response = imap.uid("STORE", old_msg.getId(), "+FLAGS.SILENT",
!                             "(\\Deleted)")
!         self._check(response, "uid store")
  
      def _filterMessage(self, msg):
--- 240,275 ----
          # in the correct folder, and delete the old one
          # XXX (someone tell me if this is wrong)
! 
!         # XXX I've redone this logic to use the IMAPMessage class.  It
!         # may be a bit of overkill, but it allows us to maintain the
!         # proper training and classification memory for the message
!         # as it's moved
!         
!         #response = imap.uid("FETCH", old_msg.getId(), "(RFC822)")
!         #self._check(response, 'uid fetch')
!         #msg = message.Message()
!         #msg.setPayload(response[1][0][1])
!         
!         msg = IMAPMessage(dest.uid, dest.folder_name, None)
!         msg.setId(msg.extractTime())  # this is kinda silly
!         msg.copy(old_msg)
!         
          #response = imap.uid("SEARCH", "(TEXT)", msg.get_payload())
          #self._check(response, "search")
          #self.changeId(response[1][0])
  
!         #response = imap.append(dest.folder_name, None,
!         #                       msg.getId(),
!         #                       msg.get_payload())
!         #self._check(response, "append")
! 
!         msg.Append()        
! 
!         #self._selectFolder(old_msg.folder_name, False)
!         #response = imap.uid("STORE", old_msg.getId(), "+FLAGS.SILENT",
!         #                    "(\\Deleted)")
!         #self._check(response, "uid store")
!         
!         old_msg.Delete()
  
      def _filterMessage(self, msg):
***************
*** 245,251 ****
              pass
          elif msg.isClsfdSpam():
!             self._moveMessage(msg, options.imap_spam_folder)
          else:
!             self._moveMessage(msg, options.imap_unsure_folder)
  
  if __name__ == '__main__':
--- 279,287 ----
              pass
          elif msg.isClsfdSpam():
!             #XXX I actually think move should be a method on IMAPMessage
!             #but I'm running out of time.
!             self._moveMessage(msg, self.spam_folder)
          else:
!             self._moveMessage(msg, self.unsure_folder)
  
  if __name__ == '__main__':



From timstone4 at users.sourceforge.net  Tue Apr  8 21:25:27 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Tue Apr  8 23:25:30 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.3,1.4
Message-ID: <E1936DH-000279-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv8117

Modified Files:
	message.py 
Log Message:
A few corrections.

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** message.py	8 Apr 2003 15:24:43 -0000	1.3
--- message.py	9 Apr 2003 03:25:24 -0000	1.4
***************
*** 82,85 ****
--- 82,86 ----
  
  import sys
+ import types
  
  import email.Message
***************
*** 158,162 ****
          return self.id
  
!     def changeID(self, id):
          # We cannot re-set an id (see below).  However there are
          # occasionally times when the id for a message will change,
--- 159,163 ----
          return self.id
  
!     def changeId(self, id):
          # We cannot re-set an id (see below).  However there are
          # occasionally times when the id for a message will change,
***************
*** 181,187 ****
--- 182,192 ----
          if id is None:
              raise ValueError, "MsgId must not be None"
+ 
+         if not type(id) in types.StringTypes:
+             raise TypeError, "Id must be a string" 
              
          self.id = id
          msginfoDB._getState(self)
+         self.modified()   # id has changed, force storage
          
      def getId(self):



From anadelonbrin at users.sourceforge.net  Wed Apr  9 00:14:31 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Wed Apr  9 02:14:39 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.4,1.5
Message-ID: <E1938qt-0005Sh-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv20980/spambayes

Modified Files:
	message.py 
Log Message:
Changes the message class so that the base class is more
abstract and introduces a sub-class to add header add/remove
functions.  Changes the set/get classify/training information
methods to a simpler version.
As per messages on list - if you don't like this version Tim feel free to change it back! :)

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -d -r1.4 -r1.5
*** message.py	9 Apr 2003 03:25:24 -0000	1.4
--- message.py	9 Apr 2003 06:14:29 -0000	1.5
***************
*** 126,133 ****
          del self.db[msg.getId()]
          
! # this should come from a mark hammond idea of a master db
  msginfoDB = MessageInfoDB("spambayes.messageinfo.db")
  
- 
  class Message(email.Message.Message):
      '''An email.Message.Message extended for Spambayes'''
--- 126,132 ----
          del self.db[msg.getId()]
          
! # this should come from a Mark Hammond idea of a master db
  msginfoDB = MessageInfoDB("spambayes.messageinfo.db")
  
  class Message(email.Message.Message):
      '''An email.Message.Message extended for Spambayes'''
***************
*** 151,183 ****
          prs._parsebody(self, StringIO(payload))
          
-     def setIdFromPayload(self):
-         try:
-             self.setId(self[options.pop3proxy_mailid_header_name])
-         except KeyError:
-             return None
- 
-         return self.id
- 
-     def changeId(self, id):
-         # We cannot re-set an id (see below).  However there are
-         # occasionally times when the id for a message will change,
-         # for example, on an IMAP server (or possibly an exchange
-         # server), the server may change the ids that we are using
-         # We enforce that this must be an explicit *change* rather
-         # than simply re-setting, by having this as a separate
-         # function
-         if not self.id:
-             raise ValueError, "MsgID has not been set, cannot be changed"
-         self._setId(id)
-     
      def setId(self, id):
          if self.id:
              raise ValueError, "MsgId has already been set, cannot be changed"
-         self._setId(id)
  
!     def _setId(self, id):    
!         # we should probably enforce type(id) is StringType.
!         # the database will insist upon it, but at that point, it's harder
!         # to diagnose
          if id is None:
              raise ValueError, "MsgId must not be None"
--- 150,160 ----
          prs._parsebody(self, StringIO(payload))
          
      def setId(self, id):
          if self.id:
              raise ValueError, "MsgId has already been set, cannot be changed"
  
!         # XXX This isn't really needed since type(None) is not
!         # XXX in types.StringTypes - do we still want it for the
!         # XXX more informative error message?
          if id is None:
              raise ValueError, "MsgId must not be None"
***************
*** 193,201 ****
          return self.id
  
!     def copy(self, old_msg):
!         self.setPayload(old_msg.payload())  # this is expensive...
!         self.setClassification(old_msg.getClassification())
!         self.setTraining(old_msg.getTraining())
          
      def addSBHeaders(self, prob, clues):
          '''Add hammie header, and remember message's classification.  Also,
--- 170,218 ----
          return self.id
  
!     def asTokens(self):
!         # use as_string() here because multipart/digest will return
!         # a list of message objects if get_payload() is used
!         return tokenize(self.as_string())
          
+     def modified(self):
+         if self.id:    # only persist if key is present
+             msginfoDB._setState(self)
+ 
+     def GetClassification(self):
+         return self.c
+     def GetTrained(self):
+         return self.t
+     def RememberClassification(self, cls):
+         self.c = cls
+         self.modified()
+     def RememberTrained(self, isSpam):
+         self.t = isSpam
+         self.modified()
+          
+     def __repr__(self):
+         return "core.Message%r" % repr(self.__getstate__())
+ 
+     def __getstate__(self):
+         return (self.id, self.c, self.t)
+ 
+     def __setstate__(self, t):
+         (self.id, self.c, self.t) = t
+ 
+ # XXX I can't think of a good name.  Someone change
+ # XXX HeaderMessage to something better before it gets used
+ # XXX all over the place.
+ class HeaderMessage(Message):
+     '''Adds routines to add/remove headers for Spambayes'''
+     def __init__(self):
+         Message.__init__(self)
+         
+     def setIdFromPayload(self):
+         try:
+             self.setId(self[options.pop3proxy_mailid_header_name])
+         except KeyError:
+             return None
+ 
+         return self.id
+ 
      def addSBHeaders(self, prob, clues):
          '''Add hammie header, and remember message's classification.  Also,
***************
*** 204,215 ****
          if prob < options.ham_cutoff:
              disposition = options.header_ham_string
-             self.clsfyAsHam()
          elif prob > options.spam_cutoff:
              disposition = options.header_spam_string
-             self.clsfyAsSpam()
          else:
              disposition = options.header_unsure_string
!             self.clsfyAsUnsure()
! 
          self[options.hammie_header_name] = disposition
          
--- 221,229 ----
          if prob < options.ham_cutoff:
              disposition = options.header_ham_string
          elif prob > options.spam_cutoff:
              disposition = options.header_spam_string
          else:
              disposition = options.header_unsure_string
!         self.RememberClassification(disposition)
          self[options.hammie_header_name] = disposition
          
***************
*** 228,232 ****
                           score <= options.clue_mailheader_cutoff or
                           score >= 1.0 - options.clue_mailheader_cutoff)])
-                          
              self[options.pop3proxy_evidence_header_name] = evd
          
--- 242,245 ----
***************
*** 241,245 ****
  #                    + messageName + "\r\n.\r\n"
  
- 
      def delSBHeaders(self):
          del self[options.hammie_header_name]
--- 254,257 ----
***************
*** 249,346 ****
          del self[options.pop3proxy_thermostat_header_name]
          del self[options.pop3proxy_evidence_header_name]
-     
-     def asTokens(self):
-         # use as_string() here because multipart/digest will return
-         # a list of message objects if get_payload() is used
-         return tokenize(self.as_string())
-         
-     def modified(self):
-         if self.id:    # only persist if key is present
-             msginfoDB._setState(self)
-         
-     def isClsfdSpam(self):
-         return self.c == 's'
-         
-     def isClsfdHam(self):
-         return self.c == 'h'
-         
-     def isClsfdUnsure(self):
-         return self.c == 'u'
-         
-     def isClassified(self):
-         return not self.c is None
-         
-     def clsfyAsSpam(self):
-         self.c = 's'
-         self.modified()
-         
-     def clsfyAsHam(self):
-         self.c = 'h'
-         self.modified()
-         
-     def clsfyAsUnsure(self):
-         self.c = 'u'
-         self.modified()
-     
-     def getClassification(self):
-         return self.c
- 
-     def setClassification(self, cls):
-         if cls == 's' or cls == 'h' or cls == 'u' or cls is None:
-             self.c = cls
-             self.modified()
-         else:
-             raise ValueError
-         
-     def isTrndSpam(self):
-         return self.t == 's'
-         
-     def isTrndHam(self):
-         return self.t == 'h'
-     
-     def trndAsSpam(self):
-         self.t = 's'
-         self.modified()
-         
-     def trndAsHam(self):
-         self.t = 'h'
-         self.modified()
-         
-     def isTrndAs(self, isSpam):
-         if self.t == 'h' and not isSpam:
-             return True
-         if self.t == 's' and isSpam:
-             return True
-         return False
- 
-     def trndAs(self, isSpam):
-         if isSpam:
-             self.t = 's'
-         else:
-             self.t = 'h'
- 
-     def notTrained(self):
-         self.t = None
-         self.modified()
-         
-     def isTrained(self):
-         return not self.t is None
-     
-     def getTraining(self):
-         return self.t
- 
-     def setTraining(self, trn):
-         if trn == 's' or trn == 'h' or trn is None:
-             self.t = trn
-             self.modified()
-         else:
-             raise ValueError
-          
-     def __repr__(self):
-         return "core.Message%r" % repr(self.__getstate__())
- 
-     def __getstate__(self):
-         return (self.id, self.c, self.t)
- 
-     def __setstate__(self, t):
-         (self.id, self.c, self.t) = t
\ No newline at end of file
--- 261,262 ----



From anadelonbrin at users.sourceforge.net  Wed Apr  9 00:16:18 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Wed Apr  9 02:16:22 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.4,1.5
Message-ID: <E1938sc-0005cf-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv21599

Modified Files:
	imapfilter.py 
Log Message:
Updates the IMAPFilter to reflect the changes in the message class.
Lots of changes all over the place, integrating (and changing!)
Tim's code.
WARNING: It still seems to train fine (although maybe the saving
is also broken), but the filtering is still buggy.  Over to people with
more time today.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -d -r1.4 -r1.5
*** imapfilter.py	8 Apr 2003 15:28:03 -0000	1.4
--- imapfilter.py	9 Apr 2003 06:16:15 -0000	1.5
***************
*** 29,32 ****
--- 29,39 ----
  # a list is retrieved via imap.list()
  
+ # IMAPFolder objects get created all over the place, and don't persist
+ # at all.  It would probably be good to change this, especially if
+ # the filter doesn't run just once
+ 
+ # All the imap responses should be checked - [0] should be "OK"
+ # otherwise an error will occur and who knows what will happen
+ 
  try:
      True, False
***************
*** 48,53 ****
  imap = None
  
! class IMAPMessage(message.Message):
!     # response checking is necessary throughout this class
      def __init__(self, folder_id, folder_name, message_id):
          message.Message.__init__(self)
--- 55,59 ----
  imap = None
  
! class IMAPMessage(message.HeaderMessage):
      def __init__(self, folder_id, folder_name, message_id):
          message.Message.__init__(self)
***************
*** 55,58 ****
--- 61,65 ----
          self.folder_id = folder_id
          self.folder_name = folder_name
+         self.previous_folder = None
  
      def extractTime(self):
***************
*** 63,98 ****
          return imaplib.Time2Internaldate(time.time())
  
!     def Update(self):
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
          response = imap.append(self.folder_name, None,
                                 self.extractTime(), self.get_payload())
-         response = imap.select(self.folder_name, False)
-         response = imap.uid("STORE", self.getId(), "+FLAGS.SILENT",
-                                  "(\\Deleted)")
          # we need to update the uid, as it will have changed
          response = imap.uid("SEARCH", "(TEXT)", self.get_payload())
!         self.changeId(response[1][0])
! 
!     def Delete(self):
!         self._selectFolder(self.folder_name, False)
!         response = imap.uid("STORE", self.getId(), "+FLAGS.SILENT",
!                             "(\\Deleted)")
!         self._check(response, "uid store")
! 
!         # XXX there should actually be a delete from the msgid database here...
!         self.notTrained()
!         self.notClassified()
! 
!     def Append(self):
!         response = imap.append(self.folder_name, None,
!                                self.getId(),
!                                self.get_payload())
!         self._check(response, "append")
! 
! 
  
  class IMAPFolder(object):
-     # response checking is necessary throughout this class
      def __init__(self, folder_name, readOnly=True):
          self.name = folder_name
--- 70,100 ----
          return imaplib.Time2Internaldate(time.time())
  
!     def MoveTo(self, dest):
!         # The move just changes where we think we are,
!         # and we do an actual move on save (to avoid doing
!         # this more than once)
!         if self.previous_folder is not None:
!             self.previous_folder = self.folder_name
!         self.folder_name = dest
! 
!     def Save(self):
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
          response = imap.append(self.folder_name, None,
                                 self.extractTime(), self.get_payload())
          # we need to update the uid, as it will have changed
+         # XXX there will be problems here if the message *has not*
+         # XXX changed, as the message to be deleted will be found first
+         # XXX (if they are in the same folder)
          response = imap.uid("SEARCH", "(TEXT)", self.get_payload())
!         old_id = self.id
!         self.id = response[1][0]
!         if self.previous_folder is not None:
!             response = imap.select(self.previous_folder, False)
!             self.previous_folder = None
!         # this line is raising an error, but WHY?
!         #response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
  
  class IMAPFolder(object):
      def __init__(self, folder_name, readOnly=True):
          self.name = folder_name
***************
*** 147,150 ****
--- 149,184 ----
          return msg
         
+     def Train(self, classifier, isSpam):
+         '''Train folder as spam/ham'''
+         for msg in self:
+             if msg.GetTrained() == isSpam:
+                 classifier.unlearn(msg.asTokens(), not isSpam)
+                 # Once the message has been untrained, it's training memory
+                 # should reflect that on the off chance that for some reason
+                 # the training breaks, which happens on occasion (the
+                 # tokenizer is not yet perfect)
+                 msg.RememberTrained(None)
+ 
+             if msg.GetTrained() is not None:
+                 classifier.learn(msg.asTokens(), isSpam)
+                 msg.RememberTrained(isSpam)
+ 
+     def FilterMessage(self, msg):
+         if msg.GetClassification() == options.header_ham_string:
+             # we leave ham alone
+             pass
+         elif msg.GetClassification() == options.header_spam_string:
+             msg.MoveTo(options.imap_spam_folder)
+         else:
+             msg.MoveTo(options.imap_unsure_folder)
+ 
+     def Filter(self, classifier):
+         for msg in self:
+             (prob, clues) = classifier.spamprob(msg.asTokens(), evidence=True)
+             # add headers and remember classification
+             msg.addSBHeaders(prob, clues)
+             self.FilterMessage(msg)
+             msg.Save()
+ 
  
  class IMAPFilter(object):
***************
*** 153,159 ****
          imap = imaplib.IMAP4(options.imap_server, options.imap_port)
          
-         self.spam_folder = IMAPFolder(options.imap_spam_folder)
-         self.unsure_folder = IMAPFolder(options.imap_unsure_folder)
-         
          if options.verbose:
              print "Loading database...",
--- 187,190 ----
***************
*** 167,200 ****
              print "Done."
  
-     def _check(self, response, command):
-         if response[0] != "OK":
-             print "Invalid response to %s:\n%s" % (command, response)
-             sys.exit(-1)
- 
-     def _selectFolder(self, name, read_only):
-         folder = imap.select(name, read_only)
-         self._check(folder, 'select')
-         return folder
- 
      def Login(self):
          lgn = imap.login(options.imap_username, options.imap_password)
-         self._check(lgn, 'login')
- 
-     def TrainFolder(self, folder_name, isSpam):
-         folder = IMAPFolder(folder_name)
-         for msg in folder:
-             # XXX I've rewritten this logic.  It looks a bit strange,
-             # because of the msg.notTrained call immediately before the
-             # test for isTrained, but this is safer.  Once the message has
-             # been untrained, it's training memory should reflect that
-             # on the off chance that for some reason the training breaks,
-             # which happens on occasion (the tokenizer is not yet perfect)
-             if msg.isTrndAs(not isSpam):
-                 self.classifier.unlearn(msg.asTokens(), not isSpam)
-                 msg.notTrained()
- 
-             if not msg.isTrained():
-                 self.classifier.learn(msg.asTokens(), isSpam)
-                 msg.trndAs(isSpam)
  
      def Train(self):
--- 198,204 ----
              print "Done."
  
      def Login(self):
+         '''Log in to the IMAP server'''
          lgn = imap.login(options.imap_username, options.imap_password)
  
      def Train(self):
***************
*** 204,212 ****
              ham_training_folders = options.imap_ham_train_folders.split()
              for fol in ham_training_folders:
!                 self.TrainFolder(fol, False)
          if options.imap_spam_train_folders != "":
              spam_training_folders = options.imap_spam_train_folders.split(' ' )
              for fol in spam_training_folders:
!                 self.TrainFolder(fol, True)
          self.classifier.store()
          if options.verbose:
--- 208,218 ----
              ham_training_folders = options.imap_ham_train_folders.split()
              for fol in ham_training_folders:
!                 folder = IMAPFolder(fol)
!                 folder.Train(self.classifier, False)
          if options.imap_spam_train_folders != "":
              spam_training_folders = options.imap_spam_train_folders.split(' ' )
              for fol in spam_training_folders:
!                 folder = IMAPFolder(fol)
!                 folder.Train(self.classifier, True)
          self.classifier.store()
          if options.verbose:
***************
*** 218,288 ****
          for filter_folder in options.imap_filter_folders.split():
              folder = IMAPFolder(filter_folder, False)
!             for msg in folder:
!                 (prob, clues) = self.classifier.spamprob(msg.asTokens(),
!                                                          evidence=True)
!                 # add headers and remember classification
!                 msg.addSBHeaders(prob, clues)
!                 # XXX updating is disabled for the moment
!                 # msg.Update()
!                 self._filterMessage(msg)
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
  
      def Logout(self):
!         # sign off
          if options.imap_expunge:
              imap.expunge()
          imap.logout()
  
-     def _moveMessage(self, old_msg, dest):
-         # The IMAP copy command makes an alias, not a whole new
-         # copy, so what we need to do (sigh) is create a new message
-         # in the correct folder, and delete the old one
-         # XXX (someone tell me if this is wrong)
- 
-         # XXX I've redone this logic to use the IMAPMessage class.  It
-         # may be a bit of overkill, but it allows us to maintain the
-         # proper training and classification memory for the message
-         # as it's moved
-         
-         #response = imap.uid("FETCH", old_msg.getId(), "(RFC822)")
-         #self._check(response, 'uid fetch')
-         #msg = message.Message()
-         #msg.setPayload(response[1][0][1])
-         
-         msg = IMAPMessage(dest.uid, dest.folder_name, None)
-         msg.setId(msg.extractTime())  # this is kinda silly
-         msg.copy(old_msg)
-         
-         #response = imap.uid("SEARCH", "(TEXT)", msg.get_payload())
-         #self._check(response, "search")
-         #self.changeId(response[1][0])
- 
-         #response = imap.append(dest.folder_name, None,
-         #                       msg.getId(),
-         #                       msg.get_payload())
-         #self._check(response, "append")
- 
-         msg.Append()        
- 
-         #self._selectFolder(old_msg.folder_name, False)
-         #response = imap.uid("STORE", old_msg.getId(), "+FLAGS.SILENT",
-         #                    "(\\Deleted)")
-         #self._check(response, "uid store")
-         
-         old_msg.Delete()
- 
-     def _filterMessage(self, msg):
-         if msg.isClsfdHam():
-             # we leave ham alone
-             print "untouched"
-             pass
-         elif msg.isClsfdSpam():
-             #XXX I actually think move should be a method on IMAPMessage
-             #but I'm running out of time.
-             self._moveMessage(msg, self.spam_folder)
-         else:
-             self._moveMessage(msg, self.unsure_folder)
- 
  if __name__ == '__main__':
      options.verbose = True
--- 224,237 ----
          for filter_folder in options.imap_filter_folders.split():
              folder = IMAPFolder(filter_folder, False)
!             folder.Filter(self.classifier)
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
  
      def Logout(self):
!         '''Log out of the IMAP server'''
          if options.imap_expunge:
              imap.expunge()
          imap.logout()
  
  if __name__ == '__main__':
      options.verbose = True
***************
*** 290,294 ****
  #    imap_filter.imap.debug = 10
      imap_filter.Login()
!     imap_filter.Train()
      imap_filter.Filter()
      imap_filter.Logout()
--- 239,243 ----
  #    imap_filter.imap.debug = 10
      imap_filter.Login()
!     #imap_filter.Train()
      imap_filter.Filter()
      imap_filter.Logout()



From montanaro at users.sourceforge.net  Thu Apr 10 07:28:31 2003
From: montanaro at users.sourceforge.net (Skip Montanaro)
Date: Thu Apr 10 09:28:35 2003
Subject: [Spambayes-checkins] spambayes mailsort.py,1.6,1.7
Message-ID: <E193c6R-0002Ic-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv8670

Modified Files:
	mailsort.py 
Log Message:
correct misspelling of "Classifier"


Index: mailsort.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/mailsort.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** mailsort.py	16 Feb 2003 17:05:07 -0000	1.6
--- mailsort.py	10 Apr 2003 13:28:27 -0000	1.7
***************
*** 31,39 ****
  
  def import_spambayes():
!     global mboxutils, CdbClassifer, tokenize
      if not os.environ.has_key('BAYESCUSTOMIZE'):
          os.environ['BAYESCUSTOMIZE'] = os.path.expanduser(CONFIG_FILE)
      from spambayes import mboxutils
!     from spambayes.cdb_classifier import CdbClassifer
      from spambayes.tokenizer import tokenize
  
--- 31,39 ----
  
  def import_spambayes():
!     global mboxutils, CdbClassifier, tokenize
      if not os.environ.has_key('BAYESCUSTOMIZE'):
          os.environ['BAYESCUSTOMIZE'] = os.path.expanduser(CONFIG_FILE)
      from spambayes import mboxutils
!     from spambayes.cdb_classifier import CdbClassifier
      from spambayes.tokenizer import tokenize
  
***************
*** 88,92 ****
          print "Creating", RC_DIR, "directory..."
          os.mkdir(rc_dir)
!     bayes = CdbClassifer()
      print 'Training with ham...'
      train(bayes, ham_name, False)
--- 88,92 ----
          print "Creating", RC_DIR, "directory..."
          os.mkdir(rc_dir)
!     bayes = CdbClassifier()
      print 'Training with ham...'
      train(bayes, ham_name, False)
***************
*** 124,128 ****
              msg = email.message_from_string(msgdata)
              del msgdata
!             bayes = CdbClassifer(open(DB_FILE, 'rb'))
              prob = bayes.spamprob(tokenize(msg))
          else:
--- 124,128 ----
              msg = email.message_from_string(msgdata)
              del msgdata
!             bayes = CdbClassifier(open(DB_FILE, 'rb'))
              prob = bayes.spamprob(tokenize(msg))
          else:
***************
*** 139,143 ****
  def print_message_score(msg_name, msg_fp):
      msg = email.message_from_file(msg_fp)
!     bayes = CdbClassifer(open(DB_FILE, 'rb'))
      prob, evidence = bayes.spamprob(tokenize(msg), evidence=True)
      print msg_name, prob
--- 139,143 ----
  def print_message_score(msg_name, msg_fp):
      msg = email.message_from_file(msg_fp)
!     bayes = CdbClassifier(open(DB_FILE, 'rb'))
      prob, evidence = bayes.spamprob(tokenize(msg), evidence=True)
      print msg_name, prob



From montanaro at users.sourceforge.net  Thu Apr 10 07:28:31 2003
From: montanaro at users.sourceforge.net (Skip Montanaro)
Date: Thu Apr 10 09:28:36 2003
Subject: [Spambayes-checkins] spambayes/spambayes cdb_classifier.py,1.1,1.2
Message-ID: <E193c6R-0002Ij-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv8670/spambayes

Modified Files:
	cdb_classifier.py 
Log Message:
correct misspelling of "Classifier"


Index: cdb_classifier.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/cdb_classifier.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** cdb_classifier.py	20 Jan 2003 03:14:32 -0000	1.1
--- cdb_classifier.py	10 Apr 2003 13:28:28 -0000	1.2
***************
*** 11,15 ****
  from spambayes.classifier import Classifier
  
! class CdbClassifer(Classifier):
      def __init__(self, cdbfile=None):
          Classifier.__init__(self)
--- 11,15 ----
  from spambayes.classifier import Classifier
  
! class CdbClassifier(Classifier):
      def __init__(self, cdbfile=None):
          Classifier.__init__(self)



From timstone4 at users.sourceforge.net  Thu Apr 10 20:08:01 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Thu Apr 10 22:08:05 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.5,1.6
Message-ID: <E193nxR-0004ot-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv18493

Modified Files:
	message.py 
Log Message:
A start at addressing Mark's concerns/suggestions for this class.  Eliminated
a bunch of YAGNI, moved some non-base methods into a subclass.

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** message.py	9 Apr 2003 06:14:29 -0000	1.5
--- message.py	11 Apr 2003 02:07:57 -0000	1.6
***************
*** 5,8 ****
--- 5,9 ----
  Classes:
      Message - an email.Message.Message, extended with spambayes methods
+     SBHeaderMessage - A Message with spambayes header manipulations
      MessageInfoDB - persistent state storage for Message
  
***************
*** 19,32 ****
      assessment purposes.
      
!     Message is an extension of the email package Message class, to include
!     persistent message information and Spambayes specific header manipulations.
!     The persistent state -currently- consists of the message id, its current
!     classification, and its current training.  The payload is not persisted.
!     Payload persistence is left to whatever mail client software is being used.
      
  Usage:
      A typical classification usage pattern would be something like:
      
!     >>>msg = spambayes.message.Message()
      >>>msg.setPayload(substance) # substance comes from somewhere else
      >>>id = msg.setIdFromPayload()
--- 20,37 ----
      assessment purposes.
      
!     Message is an extension of the email package Message class, to
!     include persistent message information. The persistent state
!     -currently- consists of the message id, its current
!     classification, and its current training.  The payload is not
!     persisted. Payload persistence is left to whatever mail client
!     software is being used.
! 
!     SBHeaderMessage extends Message to include spambayes header specific
!     manipulations.
      
  Usage:
      A typical classification usage pattern would be something like:
      
!     >>>msg = spambayes.message.SBHeaderMessage()
      >>>msg.setPayload(substance) # substance comes from somewhere else
      >>>id = msg.setIdFromPayload()
***************
*** 45,49 ****
      A typical usage pattern to train as spam would be something like:
      
!     >>>msg = spambayes.message.Message()
      >>>msg.setPayload(substance) # substance comes from somewhere else
      >>>id = msg.setId(msgid)     # id is a fname, outlook msg id, something...
--- 50,54 ----
      A typical usage pattern to train as spam would be something like:
      
!     >>>msg = spambayes.message.SBHeaderMessage()
      >>>msg.setPayload(substance) # substance comes from somewhere else
      >>>id = msg.setId(msgid)     # id is a fname, outlook msg id, something...
***************
*** 51,59 ****
      >>>msg.delSBHeaders()        # never include sb headers in a train
      
!     >>>if msg.isTrndHam():
      >>>    bayes.unlearn(msg.asTokens(), False)  # untrain the ham
      
      >>>bayes.learn(msg.asTokens(), True) # train as spam
!     >>>msg.trndAsSpam()
      
  
--- 56,64 ----
      >>>msg.delSBHeaders()        # never include sb headers in a train
      
!     >>>if msg.getTraining() == False:   # could be None, can't do boolean test
      >>>    bayes.unlearn(msg.asTokens(), False)  # untrain the ham
      
      >>>bayes.learn(msg.asTokens(), True) # train as spam
!     >>>msg.rememberTraining(True)
      
  
***************
*** 95,106 ****
  import shelve
  
- # XXX Tim, what do you want to do here?  This
- # XXX recurses infinately at the moment
- # Make shelve use binary pickles by default.
- #oldShelvePickler = shelve.Pickler
- #def binaryDefaultPickler(f, binary=1):
- #    return oldShelvePickler(f, binary)
- #shelve.Pickler = binaryDefaultPickler
- 
  
  class MessageInfoDB:
--- 100,103 ----
***************
*** 180,190 ****
  
      def GetClassification(self):
!         return self.c
!     def GetTrained(self):
!         return self.t
      def RememberClassification(self, cls):
!         self.c = cls
          self.modified()
      def RememberTrained(self, isSpam):
          self.t = isSpam
          self.modified()
--- 177,210 ----
  
      def GetClassification(self):
!         if self.c == 's':
!             return options.header_spam_string
!         if self.c == 'h':
!             return options.header_ham_string
!         if self.c == 'u':
!             return options.header_unsure_string
!         
!         return None
! 
      def RememberClassification(self, cls):
!         # this must store state independent of options settings, as they
!         # may change, which would really screw this database up
! 
!         # an unrecoginzed string here is interpreted as unsure.  Should
!         # that condition actually raise an exception instead?
! 
!         if cls == options.header_spam_string:
!             self.c = 's'
!         elif cls == options.header_ham_string:
!             self.c = 'h'
!         else
!             self.c = 'u'
! 
          self.modified()
+ 
+     def GetTrained(self):
+         return self.t
+ 
      def RememberTrained(self, isSpam):
+         # isSpam == None means no training has been done
          self.t = isSpam
          self.modified()
***************
*** 199,207 ****
          (self.id, self.c, self.t) = t
  
! # XXX I can't think of a good name.  Someone change
! # XXX HeaderMessage to something better before it gets used
! # XXX all over the place.
! class HeaderMessage(Message):
!     '''Adds routines to add/remove headers for Spambayes'''
      def __init__(self):
          Message.__init__(self)
--- 219,227 ----
          (self.id, self.c, self.t) = t
  
! 
! class SBHeaderMessage(Message):
!     '''Message class that is cognizant of Spambayes headers.
!     Adds routines to add/remove headers for Spambayes'''
!     
      def __init__(self):
          Message.__init__(self)



From timstone4 at users.sourceforge.net  Thu Apr 10 20:09:12 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Thu Apr 10 22:09:18 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.6,1.7
Message-ID: <E193nya-0004xY-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv19044

Modified Files:
	message.py 
Log Message:
Missed a syntax error.

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** message.py	11 Apr 2003 02:07:57 -0000	1.6
--- message.py	11 Apr 2003 02:09:09 -0000	1.7
***************
*** 197,201 ****
          elif cls == options.header_ham_string:
              self.c = 'h'
!         else
              self.c = 'u'
  
--- 197,201 ----
          elif cls == options.header_ham_string:
              self.c = 'h'
!         else:
              self.c = 'u'
  



From timstone4 at users.sourceforge.net  Thu Apr 10 20:11:24 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Thu Apr 10 22:11:29 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.5,1.6
Message-ID: <E193o0i-0005E2-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv20052

Modified Files:
	imapfilter.py 
Log Message:
Made some changes to accomodate the new message class.  Not tested
yet, but checked in on the chance that Tony wants to see it sooner than
I can get it tested.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** imapfilter.py	9 Apr 2003 06:16:15 -0000	1.5
--- imapfilter.py	11 Apr 2003 02:11:21 -0000	1.6
***************
*** 29,39 ****
  # a list is retrieved via imap.list()
  
- # IMAPFolder objects get created all over the place, and don't persist
- # at all.  It would probably be good to change this, especially if
- # the filter doesn't run just once
- 
- # All the imap responses should be checked - [0] should be "OK"
- # otherwise an error will occur and who knows what will happen
- 
  try:
      True, False
--- 29,32 ----
***************
*** 55,65 ****
  imap = None
  
! class IMAPMessage(message.HeaderMessage):
!     def __init__(self, folder_id, folder_name, message_id):
          message.Message.__init__(self)
          self.setId(message_id)
!         self.folder_id = folder_id
!         self.folder_name = folder_name
!         self.previous_folder = None
  
      def extractTime(self):
--- 48,62 ----
  imap = None
  
! class IMAPMessage(message.SBHeaderMessage):
!     # response checking is necessary throughout this class
!     def __init__(self, folder, message_id):
          message.Message.__init__(self)
          self.setId(message_id)
!         self.folder = folder
! 
!     def _check(self, response, command):
!         if response[0] != "OK":
!             print "Invalid response to %s:\n%s" % (command, response)
!             sys.exit(-1)
  
      def extractTime(self):
***************
*** 75,85 ****
          # this more than once)
          if self.previous_folder is not None:
!             self.previous_folder = self.folder_name
!         self.folder_name = dest
  
      def Save(self):
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
!         response = imap.append(self.folder_name, None,
                                 self.extractTime(), self.get_payload())
          # we need to update the uid, as it will have changed
--- 72,82 ----
          # this more than once)
          if self.previous_folder is not None:
!             self.previous_folder = self.folder
!         self.folder = dest
  
      def Save(self):
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
!         response = imap.append(self.folder.name, None,
                                 self.extractTime(), self.get_payload())
          # we need to update the uid, as it will have changed
***************
*** 91,100 ****
          self.id = response[1][0]
          if self.previous_folder is not None:
!             response = imap.select(self.previous_folder, False)
              self.previous_folder = None
          # this line is raising an error, but WHY?
          #response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
  
  class IMAPFolder(object):
      def __init__(self, folder_name, readOnly=True):
          self.name = folder_name
--- 88,99 ----
          self.id = response[1][0]
          if self.previous_folder is not None:
!             response = imap.select(self.previous_folder.name, False)
              self.previous_folder = None
          # this line is raising an error, but WHY?
          #response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
  
+ 
  class IMAPFolder(object):
+     # response checking is necessary throughout this class
      def __init__(self, folder_name, readOnly=True):
          self.name = folder_name
***************
*** 114,118 ****
          if response[0] != "OK":
              self.rfc822_command = "(RFC822)"
!         
      def __iter__(self):
          '''IMAPFolder is iterable'''
--- 113,126 ----
          if response[0] != "OK":
              self.rfc822_command = "(RFC822)"
! 
!     def Select(self):
!         imap.select(self.name, False)
!         self._check(folder, 'select')
! 
!     def _check(self, response, command):
!         if response[0] != "OK":
!             print "Invalid response to %s:\n%s" % (command, response)
!             sys.exit(-1)
! 
      def __iter__(self):
          '''IMAPFolder is iterable'''
***************
*** 145,152 ****
          # we return an instance of *our* message class, not the
          # raw rfc822 message
!         msg = IMAPMessage(self.uid, self.name, key)
          msg.setPayload(messageText)
          return msg
!        
      def Train(self, classifier, isSpam):
          '''Train folder as spam/ham'''
--- 153,160 ----
          # we return an instance of *our* message class, not the
          # raw rfc822 message
!         msg = IMAPMessage(self, key)
          msg.setPayload(messageText)
          return msg
! 
      def Train(self, classifier, isSpam):
          '''Train folder as spam/ham'''
***************
*** 164,184 ****
                  msg.RememberTrained(isSpam)
  
!     def FilterMessage(self, msg):
          if msg.GetClassification() == options.header_ham_string:
              # we leave ham alone
              pass
          elif msg.GetClassification() == options.header_spam_string:
!             msg.MoveTo(options.imap_spam_folder)
          else:
!             msg.MoveTo(options.imap_unsure_folder)
! 
!     def Filter(self, classifier):
!         for msg in self:
!             (prob, clues) = classifier.spamprob(msg.asTokens(), evidence=True)
!             # add headers and remember classification
!             msg.addSBHeaders(prob, clues)
!             self.FilterMessage(msg)
!             msg.Save()
  
  
  class IMAPFilter(object):
--- 172,190 ----
                  msg.RememberTrained(isSpam)
  
!     def Filter(self, classifier, spamfolder, unsurefolder):
!         for msg in self:
!             (prob, clues) = classifier.spamprob(msg.asTokens(), evidence=True)
!             # add headers and remember classification
!             msg.addSBHeaders(prob, clues)
! 
          if msg.GetClassification() == options.header_ham_string:
              # we leave ham alone
              pass
          elif msg.GetClassification() == options.header_spam_string:
!             msg.MoveTo(spamfolder)
          else:
!             msg.MoveTo(unsurefolder)
  
+         msg.Save()            
  
  class IMAPFilter(object):
***************
*** 187,203 ****
          imap = imaplib.IMAP4(options.imap_server, options.imap_port)
          
!         if options.verbose:
!             print "Loading database...",
          filename = options.pop3proxy_persistent_storage_file
          filename = os.path.expanduser(filename)
          if options.pop3proxy_persistent_use_database:
              self.classifier = storage.DBDictClassifier(filename)
          else:
              self.classifier = storage.PickledClassifier(filename)
          if options.verbose:
              print "Done."
  
      def Login(self):
-         '''Log in to the IMAP server'''
          lgn = imap.login(options.imap_username, options.imap_password)
  
--- 193,214 ----
          imap = imaplib.IMAP4(options.imap_server, options.imap_port)
          
!         self.spam_folder = IMAPFolder(options.imap_spam_folder)
!         self.unsure_folder = IMAPFolder(options.imap_unsure_folder)
!         
          filename = options.pop3proxy_persistent_storage_file
          filename = os.path.expanduser(filename)
+ 
+         if options.verbose:
+             print "Loading database %s..." % (filename),
+         
          if options.pop3proxy_persistent_use_database:
              self.classifier = storage.DBDictClassifier(filename)
          else:
              self.classifier = storage.PickledClassifier(filename)
+             
          if options.verbose:
              print "Done."
  
      def Login(self):
          lgn = imap.login(options.imap_username, options.imap_password)
  
***************
*** 205,208 ****
--- 216,220 ----
          if options.verbose:
              t = time.time()
+ 
          if options.imap_ham_train_folders != "":
              ham_training_folders = options.imap_ham_train_folders.split()
***************
*** 210,213 ****
--- 222,226 ----
                  folder = IMAPFolder(fol)
                  folder.Train(self.classifier, False)
+ 
          if options.imap_spam_train_folders != "":
              spam_training_folders = options.imap_spam_train_folders.split(' ' )
***************
*** 215,219 ****
--- 228,234 ----
                  folder = IMAPFolder(fol)
                  folder.Train(self.classifier, True)
+ 
          self.classifier.store()
+         
          if options.verbose:
              print "Training took", time.time() - t, "seconds."
***************
*** 222,237 ****
          if options.verbose:
              t = time.time()
          for filter_folder in options.imap_filter_folders.split():
              folder = IMAPFolder(filter_folder, False)
!             folder.Filter(self.classifier)
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
  
      def Logout(self):
!         '''Log out of the IMAP server'''
          if options.imap_expunge:
              imap.expunge()
          imap.logout()
  
  if __name__ == '__main__':
      options.verbose = True
--- 237,255 ----
          if options.verbose:
              t = time.time()
+             
          for filter_folder in options.imap_filter_folders.split():
              folder = IMAPFolder(filter_folder, False)
!             folder.Filter(self.classifier, self.spam_folder, self.unsure_folder)
!  
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
  
      def Logout(self):
!         # sign off
          if options.imap_expunge:
              imap.expunge()
          imap.logout()
  
+  
  if __name__ == '__main__':
      options.verbose = True
***************
*** 239,243 ****
  #    imap_filter.imap.debug = 10
      imap_filter.Login()
!     #imap_filter.Train()
      imap_filter.Filter()
      imap_filter.Logout()
--- 257,261 ----
  #    imap_filter.imap.debug = 10
      imap_filter.Login()
!     imap_filter.Train()
      imap_filter.Filter()
      imap_filter.Logout()



From timstone4 at users.sourceforge.net  Sat Apr 12 20:02:57 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Sat Apr 12 22:02:59 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.7,1.8
Message-ID: <E194Wpd-0006j1-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv25842

Modified Files:
	message.py 
Log Message:
A few corrections

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** message.py	11 Apr 2003 02:09:09 -0000	1.7
--- message.py	13 Apr 2003 02:02:54 -0000	1.8
***************
*** 141,145 ****
          
      def setPayload(self, payload):
!         prs = email.Parser.HeaderParser()
          prs._parseheaders(self, StringIO(payload))
          # we may want to do some header parsing error handling here
--- 141,147 ----
          
      def setPayload(self, payload):
!         prs = email.Parser.Parser()
!         # this is kindof a hack, due to the fact that the parser creates a
!         # new message object, and we already have the message object
          prs._parseheaders(self, StringIO(payload))
          # we may want to do some header parsing error handling here
***************
*** 183,187 ****
          if self.c == 'u':
              return options.header_unsure_string
!         
          return None
  
--- 185,189 ----
          if self.c == 'u':
              return options.header_unsure_string
! 
          return None
  
***************
*** 266,269 ****
--- 268,274 ----
          if options.pop3proxy_add_mailid_to.find("header") != -1:
              self[options.pop3proxy_mailid_header_name] = self.id
+ 
+ #        print self._headers
+  #       print self.as_string()
  
  # This won't work for now, because email.Message does not isolate message body



From timstone4 at users.sourceforge.net  Sat Apr 12 20:04:48 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Sat Apr 12 22:04:52 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.6,1.7
Message-ID: <E194WrQ-0006qM-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv26297

Modified Files:
	imapfilter.py 
Log Message:
Lots and lots of development work, this is the first basically functional version
of the imap filter, and it's actually been 'tested'.  Tested is quoted, because
IMAP seems to be a really flukey kind of interface, and until it's been used
on lots of imap servers, by lots of people, I won't be convinced that it's
really correct.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** imapfilter.py	11 Apr 2003 02:11:21 -0000	1.6
--- imapfilter.py	13 Apr 2003 02:04:45 -0000	1.7
***************
*** 13,16 ****
--- 13,43 ----
  The original filter design owed much to isbg by Roger Binns
  (http://www.rogerbinns.com/isbg).
+ 
+ Usage:
+     imapfilter [options]
+ 
+ 	note: option values with spaces in them must be enclosed
+ 	      in double quotes
+ 
+         options:
+             -d  dbname  : pickled training database filename
+             -D  dbname  : dbm training database filename
+             -t          : train contents of spam folder and ham folder
+             -c          : classify inbox
+             -h          : help
+ 
+ Examples:
+ 
+     Classify inbox, with dbm database
+         imapfilter -c -D bayes.db
+         
+     Train Spam and Ham, then classify inbox, with dbm database
+         imapfilter -t -c -D bayes.db
+ 
+     Train Spam and Ham only, with pickled database
+         imapfilter -t -d bayes.db
+  
+ To Do:
+     o Suggestions?
  """
  
***************
*** 41,44 ****
--- 68,73 ----
  import time
  import sys
+ import getopt
+ import email.Parser
  
  from spambayes.Options import options
***************
*** 50,57 ****
  class IMAPMessage(message.SBHeaderMessage):
      # response checking is necessary throughout this class
!     def __init__(self, folder, message_id):
          message.Message.__init__(self)
!         self.setId(message_id)
!         self.folder = folder
  
      def _check(self, response, command):
--- 79,91 ----
  class IMAPMessage(message.SBHeaderMessage):
      # response checking is necessary throughout this class
!     def __init__(self):        
          message.Message.__init__(self)
!         #XXX When a message object is created, an id and a folder should
!         #XXX immediately be set.  These cannot be passed in on the
!         #XXX constructor, due to the quirky way that email.Parser.Parser
!         #XXX does its thing.
!         self.id = None
!         self.folder = None
!         self.previous_folder = None
  
      def _check(self, response, command):
***************
*** 65,69 ****
          # timestamp from the message itself, but for the moment, we
          # just use the current time.
!         return imaplib.Time2Internaldate(time.time())
  
      def MoveTo(self, dest):
--- 99,108 ----
          # timestamp from the message itself, but for the moment, we
          # just use the current time.
!         #XXX the imaplib time function returns a string like
!         #XXX "12-Apr-2003 19:56:28 -0500"  This seems like a bad message id.
!         #XXX For one thing, it only resolves to one second.  Even a cheap
!         #XXX refractor telescope can resolve better than that ;)
! #        return imaplib.Time2Internaldate(time.time())
!         return time.time()
  
      def MoveTo(self, dest):
***************
*** 71,95 ****
          # and we do an actual move on save (to avoid doing
          # this more than once)
!         if self.previous_folder is not None:
              self.previous_folder = self.folder
!         self.folder = dest
  
      def Save(self):
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
          response = imap.append(self.folder.name, None,
!                                self.extractTime(), self.get_payload())
          # we need to update the uid, as it will have changed
          # XXX there will be problems here if the message *has not*
          # XXX changed, as the message to be deleted will be found first
          # XXX (if they are in the same folder)
!         response = imap.uid("SEARCH", "(TEXT)", self.get_payload())
          old_id = self.id
!         self.id = response[1][0]
          if self.previous_folder is not None:
              response = imap.select(self.previous_folder.name, False)
              self.previous_folder = None
!         # this line is raising an error, but WHY?
!         #response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
  
  
--- 110,143 ----
          # and we do an actual move on save (to avoid doing
          # this more than once)
!         if self.previous_folder is None and not self.folder == dest:
              self.previous_folder = self.folder
!             self.folder = dest
  
      def Save(self):
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
+         new_id = self.extractTime()
          response = imap.append(self.folder.name, None,
!                                new_id, self.as_string())
!         self._check(response, 'append')
          # we need to update the uid, as it will have changed
          # XXX there will be problems here if the message *has not*
          # XXX changed, as the message to be deleted will be found first
          # XXX (if they are in the same folder)
!         #response = imap.uid("SEARCH", "(TEXT)", self.as_string())
!         #self._check(response, 'search')
!         #self.id = response[1][0]
! 
          old_id = self.id
!         self.id = new_id
          if self.previous_folder is not None:
              response = imap.select(self.previous_folder.name, False)
+             self._check(response, 'folder select')
              self.previous_folder = None
!             response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
!             self._check(response, 'store')
! 
!             #XXX We really should delete the old message from the msgid db.
!             #XXX There is currently no interface to do this with.
  
  
***************
*** 153,162 ****
          # we return an instance of *our* message class, not the
          # raw rfc822 message
!         msg = IMAPMessage(self, key)
!         msg.setPayload(messageText)
          return msg
  
      def Train(self, classifier, isSpam):
          '''Train folder as spam/ham'''
          for msg in self:
              if msg.GetTrained() == isSpam:
--- 201,218 ----
          # we return an instance of *our* message class, not the
          # raw rfc822 message
!         #XXX I can't get parsing to work correctly if I pull the guts
!         #XXX out of Parser.parse() and do that in the setPayload method
!         #XXX of the message class.  Why?  I have **NO** idea.
!         #msg = IMAPMessage(self, key)
!         #msg.setPayload(messageText)
!         msg = email.Parser.Parser(_class=IMAPMessage).parsestr(messageText)
!         msg.folder = self
!         msg.setId(key)
!         
          return msg
  
      def Train(self, classifier, isSpam):
          '''Train folder as spam/ham'''
+         num_trained = 0
          for msg in self:
              if msg.GetTrained() == isSpam:
***************
*** 170,216 ****
              if msg.GetTrained() is not None:
                  classifier.learn(msg.asTokens(), isSpam)
                  msg.RememberTrained(isSpam)
  
      def Filter(self, classifier, spamfolder, unsurefolder):
          for msg in self:
!             (prob, clues) = classifier.spamprob(msg.asTokens(), evidence=True)
!             # add headers and remember classification
!             msg.addSBHeaders(prob, clues)
! 
!         if msg.GetClassification() == options.header_ham_string:
!             # we leave ham alone
!             pass
!         elif msg.GetClassification() == options.header_spam_string:
!             msg.MoveTo(spamfolder)
!         else:
!             msg.MoveTo(unsurefolder)
  
!         msg.Save()            
  
  class IMAPFilter(object):
!     def __init__(self):
          global imap
          imap = imaplib.IMAP4(options.imap_server, options.imap_port)
          
          self.spam_folder = IMAPFolder(options.imap_spam_folder)
          self.unsure_folder = IMAPFolder(options.imap_unsure_folder)
-         
-         filename = options.pop3proxy_persistent_storage_file
-         filename = os.path.expanduser(filename)
  
!         if options.verbose:
!             print "Loading database %s..." % (filename),
          
-         if options.pop3proxy_persistent_use_database:
-             self.classifier = storage.DBDictClassifier(filename)
-         else:
-             self.classifier = storage.PickledClassifier(filename)
-             
-         if options.verbose:
-             print "Done."
- 
-     def Login(self):
-         lgn = imap.login(options.imap_username, options.imap_password)
- 
      def Train(self):
          if options.verbose:
--- 226,263 ----
              if msg.GetTrained() is not None:
                  classifier.learn(msg.asTokens(), isSpam)
+                 num_trained += 1
                  msg.RememberTrained(isSpam)
  
+         return num_trained                
+ 
      def Filter(self, classifier, spamfolder, unsurefolder):
          for msg in self:
!             if msg.GetClassification() is None:
!                 (prob, clues) = classifier.spamprob(msg.asTokens(), evidence=True)
!                 # add headers and remember classification
!                 msg.addSBHeaders(prob, clues)
  
!                 cls = msg.GetClassification()
!                 if cls == options.header_ham_string:
!                     # we leave ham alone
!                     pass
!                 elif cls == options.header_spam_string:
!                     msg.MoveTo(spamfolder)
!                 else:
!                     msg.MoveTo(unsurefolder)
  
+                 msg.Save()
+             
  class IMAPFilter(object):
!     def __init__(self, classifier):
          global imap
          imap = imaplib.IMAP4(options.imap_server, options.imap_port)
+         lgn = imap.login(options.imap_username, options.imap_password)
          
          self.spam_folder = IMAPFolder(options.imap_spam_folder)
          self.unsure_folder = IMAPFolder(options.imap_unsure_folder)
  
!         self.classifier = classifier
          
      def Train(self):
          if options.verbose:
***************
*** 221,225 ****
              for fol in ham_training_folders:
                  folder = IMAPFolder(fol)
!                 folder.Train(self.classifier, False)
  
          if options.imap_spam_train_folders != "":
--- 268,272 ----
              for fol in ham_training_folders:
                  folder = IMAPFolder(fol)
!                 num_ham_trained = folder.Train(self.classifier, False)
  
          if options.imap_spam_train_folders != "":
***************
*** 227,236 ****
              for fol in spam_training_folders:
                  folder = IMAPFolder(fol)
!                 folder.Train(self.classifier, True)
  
!         self.classifier.store()
          
          if options.verbose:
!             print "Training took", time.time() - t, "seconds."
  
      def Filter(self):
--- 274,285 ----
              for fol in spam_training_folders:
                  folder = IMAPFolder(fol)
!                 num_spam_trained = folder.Train(self.classifier, True)
  
!         if num_ham_trained or num_spam_trained:
!             self.classifier.store()
          
          if options.verbose:
!             print "Training took %s seconds, %s messages were trained" \
!                   % (time.time() - t, num_ham_trained + num_spam_trained)
  
      def Filter(self):
***************
*** 253,261 ****
   
  if __name__ == '__main__':
!     options.verbose = True
!     imap_filter = IMAPFilter()
  #    imap_filter.imap.debug = 10
!     imap_filter.Login()
!     imap_filter.Train()
!     imap_filter.Filter()
      imap_filter.Logout()
--- 302,355 ----
   
  if __name__ == '__main__':
! 
!     try:
!         opts, args = getopt.getopt(sys.argv[1:], 'htcvd:D:')
!     except getopt.error, msg:
!         print >>sys.stderr, str(msg) + '\n\n' + __doc__
!         sys.exit()
! 
!     bdbname = options.pop3proxy_persistent_storage_file
!     useDBM = options.pop3proxy_persistent_use_database
!     doTrain = False
!     doClassify = False
! 
!     for opt, arg in opts:
!         if opt == '-h':
!             print >>sys.stderr, __doc__
!             sys.exit()
!         elif opt == '-d':
!             useDBM = False
!             bdbname = arg
!         elif opt == '-D':
!             useDBM = True
!             bdbname = arg
!         elif opt == '-t':
!             doTrain = True
!         elif opt == '-c':
!             doClassify = True
!         elif opt == '-v':
!             options.verbose = True
! 
! 
!         bdbname = os.path.expanduser(bdbname)
!         
!         if options.verbose:
!             print "Loading database %s..." % (bdbname),
!         
!         if useDBM:
!             classifier = storage.DBDictClassifier(bdbname)
!         else:
!             classifier = storage.PickledClassifier(bdbname)
! 
!         if options.verbose:
!             print "Done."            
!                 
!     imap_filter = IMAPFilter(classifier)
  #    imap_filter.imap.debug = 10
! #    imap_filter.Login()
!     if doTrain:
!         imap_filter.Train()
!     if doClassify:
!         imap_filter.Filter()
!         
      imap_filter.Logout()



From timstone4 at users.sourceforge.net  Sun Apr 13 06:54:05 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Sun Apr 13 08:54:08 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.8,1.9
Message-ID: <E194gzl-0007Yc-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv29022

Modified Files:
	message.py 
Log Message:
Raised an error on RememberClassification if the classification to be
remembered is not recognizable.

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** message.py	13 Apr 2003 02:02:54 -0000	1.8
--- message.py	13 Apr 2003 12:54:02 -0000	1.9
***************
*** 142,151 ****
      def setPayload(self, payload):
          prs = email.Parser.Parser()
          # this is kindof a hack, due to the fact that the parser creates a
          # new message object, and we already have the message object
!         prs._parseheaders(self, StringIO(payload))
          # we may want to do some header parsing error handling here
          # to try to extract important headers regardless of malformations
!         prs._parsebody(self, StringIO(payload))
          
      def setId(self, id):
--- 142,152 ----
      def setPayload(self, payload):
          prs = email.Parser.Parser()
+         fp = StringIO(payload)
          # this is kindof a hack, due to the fact that the parser creates a
          # new message object, and we already have the message object
!         prs._parseheaders(self, fp)
          # we may want to do some header parsing error handling here
          # to try to extract important headers regardless of malformations
!         prs._parsebody(self, fp)
          
      def setId(self, id):
***************
*** 153,159 ****
              raise ValueError, "MsgId has already been set, cannot be changed"
  
-         # XXX This isn't really needed since type(None) is not
-         # XXX in types.StringTypes - do we still want it for the
-         # XXX more informative error message?
          if id is None:
              raise ValueError, "MsgId must not be None"
--- 154,157 ----
***************
*** 170,175 ****
  
      def asTokens(self):
-         # use as_string() here because multipart/digest will return
-         # a list of message objects if get_payload() is used
          return tokenize(self.as_string())
          
--- 168,171 ----
***************
*** 199,204 ****
          elif cls == options.header_ham_string:
              self.c = 'h'
!         else:
              self.c = 'u'
  
          self.modified()
--- 195,203 ----
          elif cls == options.header_ham_string:
              self.c = 'h'
!         elif cls == options.header_unsure_string:
              self.c = 'u'
+         else:
+             raise ValueError, \
+                   "Classification must match header strings in options"
  
          self.modified()
***************
*** 213,217 ****
           
      def __repr__(self):
!         return "core.Message%r" % repr(self.__getstate__())
  
      def __getstate__(self):
--- 212,216 ----
           
      def __repr__(self):
!         return "spambayes.message.Message%r" % repr(self.__getstate__())
  
      def __getstate__(self):



From timstone4 at users.sourceforge.net  Sun Apr 13 06:54:57 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Sun Apr 13 08:55:01 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.7,1.8
Message-ID: <E194h0b-0007fh-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv29478

Modified Files:
	imapfilter.py 
Log Message:
Made the message constructor work the way I wanted it to originally. Added
a couple of options, refactored a few methods, general code cleanup.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** imapfilter.py	13 Apr 2003 02:04:45 -0000	1.7
--- imapfilter.py	13 Apr 2003 12:54:54 -0000	1.8
***************
*** 26,29 ****
--- 26,32 ----
              -c          : classify inbox
              -h          : help
+             -v          : verbose mode
+             -e          : sets expunge to the *opposite* of options.imap_expunge
+             -i debuglvl : a somewhat mysterious imaplib debugging level
  
  Examples:
***************
*** 39,42 ****
--- 42,53 ----
   
  To Do:
+     o Remove old msg from info database when saveing modified messages
+     o Use DELETE rather than storing //DELETED flag when saving modified messages
+     o Web UI for configuration and setup. # Tony thinks it would be
+         nice if there was a web ui to this for the initial setup (i.e. like
+         pop3proxy), which offered a list of folders to filter/train/etc.  It
+         could then record a uid for the folder rather than a name, and it
+         avoids the problems with different imap servers having different
+         naming styles a list is retrieved via imap.list()
      o Suggestions?
  """
***************
*** 49,59 ****
  __credits__ = "Tim Stone, All the Spambayes folk."
  
- # Tony thinks it would be nice if there was a web ui to
- # this for the initial setup (i.e. like pop3proxy), which offered
- # a list of folders to filter/train/etc.  It could then record a
- # uid for the folder rather than a name, and it avoids the problems
- # with different imap servers having different naming styles
- # a list is retrieved via imap.list()
- 
  try:
      True, False
--- 60,63 ----
***************
*** 79,90 ****
  class IMAPMessage(message.SBHeaderMessage):
      # response checking is necessary throughout this class
!     def __init__(self):        
          message.Message.__init__(self)
!         #XXX When a message object is created, an id and a folder should
!         #XXX immediately be set.  These cannot be passed in on the
!         #XXX constructor, due to the quirky way that email.Parser.Parser
!         #XXX does its thing.
!         self.id = None
!         self.folder = None
          self.previous_folder = None
  
--- 83,91 ----
  class IMAPMessage(message.SBHeaderMessage):
      # response checking is necessary throughout this class
!     def __init__(self, folder, id):        
          message.Message.__init__(self)
! 
!         self.id = id
!         self.folder = folder
          self.previous_folder = None
  
***************
*** 110,114 ****
          # and we do an actual move on save (to avoid doing
          # this more than once)
!         if self.previous_folder is None and not self.folder == dest:
              self.previous_folder = self.folder
              self.folder = dest
--- 111,115 ----
          # and we do an actual move on save (to avoid doing
          # this more than once)
!         if self.previous_folder is None:
              self.previous_folder = self.folder
              self.folder = dest
***************
*** 201,212 ****
          # we return an instance of *our* message class, not the
          # raw rfc822 message
!         #XXX I can't get parsing to work correctly if I pull the guts
!         #XXX out of Parser.parse() and do that in the setPayload method
!         #XXX of the message class.  Why?  I have **NO** idea.
!         #msg = IMAPMessage(self, key)
!         #msg.setPayload(messageText)
!         msg = email.Parser.Parser(_class=IMAPMessage).parsestr(messageText)
!         msg.folder = self
!         msg.setId(key)
          
          return msg
--- 202,208 ----
          # we return an instance of *our* message class, not the
          # raw rfc822 message
! 
!         msg = IMAPMessage(self, key)
!         msg.setPayload(messageText)
          
          return msg
***************
*** 253,257 ****
          global imap
          imap = imaplib.IMAP4(options.imap_server, options.imap_port)
!         lgn = imap.login(options.imap_username, options.imap_password)
          
          self.spam_folder = IMAPFolder(options.imap_spam_folder)
--- 249,254 ----
          global imap
          imap = imaplib.IMAP4(options.imap_server, options.imap_port)
! 
!         self.Login(options.imap_username, options.imap_password)
          
          self.spam_folder = IMAPFolder(options.imap_spam_folder)
***************
*** 294,300 ****
              print "Filtering took", time.time() - t, "seconds."
  
!     def Logout(self):
          # sign off
!         if options.imap_expunge:
              imap.expunge()
          imap.logout()
--- 291,308 ----
              print "Filtering took", time.time() - t, "seconds."
  
!     def Login(self, uid, pw):
!         try:
!             lgn = imap.login(uid, pw)
!         except imaplib.IMAP4.error, e:
!             if str(e) == "permission denied":
!                 print "There was an error logging in to the IMAP server."
!                 print "The userid and/or password may be in error."
!                 sys.exit()
!             else:
!                 raise
!     
!     def Logout(self, expunge):
          # sign off
!         if expunge:
              imap.expunge()
          imap.logout()
***************
*** 304,308 ****
  
      try:
!         opts, args = getopt.getopt(sys.argv[1:], 'htcvd:D:')
      except getopt.error, msg:
          print >>sys.stderr, str(msg) + '\n\n' + __doc__
--- 312,316 ----
  
      try:
!         opts, args = getopt.getopt(sys.argv[1:], 'htcvei:d:D:')
      except getopt.error, msg:
          print >>sys.stderr, str(msg) + '\n\n' + __doc__
***************
*** 313,316 ****
--- 321,326 ----
      doTrain = False
      doClassify = False
+     doExpunge = options.imap_expunge
+     imapDebug = 0
  
      for opt, arg in opts:
***************
*** 330,351 ****
          elif opt == '-v':
              options.verbose = True
  
  
!         bdbname = os.path.expanduser(bdbname)
!         
!         if options.verbose:
!             print "Loading database %s..." % (bdbname),
!         
!         if useDBM:
!             classifier = storage.DBDictClassifier(bdbname)
!         else:
!             classifier = storage.PickledClassifier(bdbname)
  
!         if options.verbose:
!             print "Done."            
                  
      imap_filter = IMAPFilter(classifier)
! #    imap_filter.imap.debug = 10
! #    imap_filter.Login()
      if doTrain:
          imap_filter.Train()
--- 340,365 ----
          elif opt == '-v':
              options.verbose = True
+         elif opt == '-e':
+             doExpunge = not doExpunge
+         elif opt == '-i:':
+             imapDebug = int(arg)
  
  
!     bdbname = os.path.expanduser(bdbname)
!     
!     if options.verbose:
!         print "Loading database %s..." % (bdbname),
!     
!     if useDBM:
!         classifier = storage.DBDictClassifier(bdbname)
!     else:
!         classifier = storage.PickledClassifier(bdbname)
  
!     if options.verbose:
!         print "Done."            
                  
      imap_filter = IMAPFilter(classifier)
!     imap.debug = imapDebug
! 
      if doTrain:
          imap_filter.Train()
***************
*** 353,355 ****
          imap_filter.Filter()
          
!     imap_filter.Logout()
--- 367,369 ----
          imap_filter.Filter()
          
!     imap_filter.Logout(doExpunge)



From timstone4 at users.sourceforge.net  Sun Apr 13 14:45:33 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Sun Apr 13 16:45:37 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.8,1.9
Message-ID: <E194oM1-0005H7-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv20262

Modified Files:
	imapfilter.py 
Log Message:
Cobbled together a hack to remove old message ids from the message info db.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** imapfilter.py	13 Apr 2003 12:54:54 -0000	1.8
--- imapfilter.py	13 Apr 2003 20:45:30 -0000	1.9
***************
*** 42,46 ****
   
  To Do:
!     o Remove old msg from info database when saveing modified messages
      o Use DELETE rather than storing //DELETED flag when saving modified messages
      o Web UI for configuration and setup. # Tony thinks it would be
--- 42,47 ----
   
  To Do:
!     o Find a better way to remove old msg from info database when saving
!       modified messages
      o Use DELETE rather than storing //DELETED flag when saving modified messages
      o Web UI for configuration and setup. # Tony thinks it would be
***************
*** 131,135 ****
  
          old_id = self.id
-         self.id = new_id
          if self.previous_folder is not None:
              response = imap.select(self.previous_folder.name, False)
--- 132,135 ----
***************
*** 139,144 ****
              self._check(response, 'store')
  
!             #XXX We really should delete the old message from the msgid db.
!             #XXX There is currently no interface to do this with.
  
  
--- 139,150 ----
              self._check(response, 'store')
  
!             #XXX This code to deletd the old message id from the message
!             #XXX info db and manipulate the message id, is a *serious* hack.
!             #XXX There's gotta be a better way to do this.
! 
!             message.msginfoDB._delState(self)
!             
!         self.id = str(new_id)
!         self.modified()
  
  



From montanaro at users.sourceforge.net  Sun Apr 13 16:24:27 2003
From: montanaro at users.sourceforge.net (Skip Montanaro)
Date: Sun Apr 13 18:24:30 2003
Subject: [Spambayes-checkins] spambayes mboxtrain.py,1.6,1.7
Message-ID: <E194ptj-0001dn-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv6250

Modified Files:
	mboxtrain.py 
Log Message:
train() clearly couldn't be correct the way it was written.  Pass in
trainnew from main() and test for the existence of path.  (Not tested - I
don't use this code.  Just responding to a note on the spambayes list.)


Index: mboxtrain.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/mboxtrain.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** mboxtrain.py	21 Mar 2003 01:33:19 -0000	1.6
--- mboxtrain.py	13 Apr 2003 22:24:24 -0000	1.7
***************
*** 208,213 ****
                 (trained, counter))
  
! def train(h, path, is_spam, force):
!     if os.path.isfile(path):
          mbox_train(h, path, is_spam, force)
      elif os.path.isdir(os.path.join(path, "cur")):
--- 208,215 ----
                 (trained, counter))
  
! def train(h, path, is_spam, force, trainnew):
!     if not os.path.exists(path):
!         raise ValueError("Nonexistent path: %s" % path)
!     elif os.path.isfile(path):
          mbox_train(h, path, is_spam, force)
      elif os.path.isdir(os.path.join(path, "cur")):
***************
*** 277,286 ****
      for g in good:
          if loud: print "Training ham (%s):" % g
!         train(h, g, False, force)
          save = True
  
      for s in spam:
          if loud: print "Training spam (%s):" % s
!         train(h, s, True, force)
          save = True
  
--- 279,288 ----
      for g in good:
          if loud: print "Training ham (%s):" % g
!         train(h, g, False, force, trainnew)
          save = True
  
      for s in spam:
          if loud: print "Training spam (%s):" % s
!         train(h, s, True, force, trainnew)
          save = True
  



From anadelonbrin at users.sourceforge.net  Sun Apr 13 16:52:16 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 13 18:52:19 2003
Subject: [Spambayes-checkins] spambayes/windows pop3proxy_service.py, 1.3,
	1.4
Message-ID: <E194qKe-00069L-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/windows
In directory sc8-pr-cvs1:/tmp/cvs-serv23596/windows

Modified Files:
	pop3proxy_service.py 
Log Message:
Fix for UI showing incorrect server strings as discovered 
and solved by Paul Moore.

Index: pop3proxy_service.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/windows/pop3proxy_service.py,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** pop3proxy_service.py	23 Mar 2003 07:21:52 -0000	1.3
--- pop3proxy_service.py	13 Apr 2003 22:52:13 -0000	1.4
***************
*** 102,105 ****
--- 102,106 ----
      def ServerThread(self):
          state = pop3proxy.state
+         state.buildServerStrings()
          pop3proxy.main(state.servers, state.proxyPorts, state.uiPort, state.launchUI)
  



From anadelonbrin at users.sourceforge.net  Sun Apr 13 18:15:53 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 13 20:15:57 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.9,1.10
Message-ID: <E194rdZ-0008Ja-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv31908

Modified Files:
	imapfilter.py 
Log Message:
Various speed improvements.
Some comment changes.
Various small changes.
Tested with two IMAP servers and seems to still work :)

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** imapfilter.py	13 Apr 2003 20:45:30 -0000	1.9
--- imapfilter.py	14 Apr 2003 00:15:50 -0000	1.10
***************
*** 6,14 ****
  messages are scored and (where necessary) filtered.
  
- It is suggested that this filter is set to run at certain intervals.
- Note that it is (currently) fairly slow, so this should not be too
- often.  An alternative to this would be to keep the filter running
- and logged in, and periodically check for new mail.
- 
  The original filter design owed much to isbg by Roger Binns
  (http://www.rogerbinns.com/isbg).
--- 6,9 ----
***************
*** 45,49 ****
        modified messages
      o Use DELETE rather than storing //DELETED flag when saving modified messages
!     o Web UI for configuration and setup. # Tony thinks it would be
          nice if there was a web ui to this for the initial setup (i.e. like
          pop3proxy), which offered a list of folders to filter/train/etc.  It
--- 40,44 ----
        modified messages
      o Use DELETE rather than storing //DELETED flag when saving modified messages
!     o Web UI for configuration and setup. Tony thinks it would be
          nice if there was a web ui to this for the initial setup (i.e. like
          pop3proxy), which offered a list of folders to filter/train/etc.  It
***************
*** 51,54 ****
--- 46,58 ----
          avoids the problems with different imap servers having different
          naming styles a list is retrieved via imap.list()
+     o IMAPMessage and IMAPFolder currently carry out very simple checks
+       of responses received from IMAP commands, but if the response is not
+       "OK", then the filter terminates.  Handling of these errors could be
+       much nicer.
+     o The filter is currently designed to be periodically run (with cron,
+       for example).  It would probably be nicer if it was continually
+       running (like pop3proxy, for example) and periodically checked for
+       any new messages to process (with the RECENT command).  The period
+       could be an option.
      o Suggestions?
  """
***************
*** 82,87 ****
  imap = None
  
  class IMAPMessage(message.SBHeaderMessage):
-     # response checking is necessary throughout this class
      def __init__(self, folder, id):        
          message.Message.__init__(self)
--- 86,116 ----
  imap = None
  
+ # global rfc822 fetch command
+ rfc822_command = "(RFC822.PEEK)"
+ 
+ # For efficiency, we remember which folder we are currently
+ # in, and only send a select command to the IMAP server if
+ # we want to *change* folders.  This function is used by
+ # both IMAPMessage and IMAPFolder.
+ # Occaisionally, we need to force a command, because we
+ # are interested in the response.  Things would be much
+ # nicer if we cached this information somewhere.
+ # XXX If we wanted to be nice and tidy, this really belongs
+ # XXX in an IMAPUtilities class, or something like that.
+ current_folder = None
+ current_folder_readonly = None
+ def Select(folder, readOnly=True, force=False):
+     global current_folder
+     global current_folder_readonly
+     if current_folder != folder or current_folder_readonly != readOnly or force:
+         response = imap.select(folder, readOnly)
+         if response[0] != "OK":
+             print "Invalid response to %s:\n%s" % (command, response)
+             sys.exit(-1)
+         current_folder = folder
+         current_folder_readonly = readOnly
+         return response
+ 
  class IMAPMessage(message.SBHeaderMessage):
      def __init__(self, folder, id):        
          message.Message.__init__(self)
***************
*** 101,110 ****
          # timestamp from the message itself, but for the moment, we
          # just use the current time.
!         #XXX the imaplib time function returns a string like
!         #XXX "12-Apr-2003 19:56:28 -0500"  This seems like a bad message id.
!         #XXX For one thing, it only resolves to one second.  Even a cheap
!         #XXX refractor telescope can resolve better than that ;)
! #        return imaplib.Time2Internaldate(time.time())
!         return time.time()
  
      def MoveTo(self, dest):
--- 130,134 ----
          # timestamp from the message itself, but for the moment, we
          # just use the current time.
!         return imaplib.Time2Internaldate(time.time())
  
      def MoveTo(self, dest):
***************
*** 119,125 ****
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
!         new_id = self.extractTime()
          response = imap.append(self.folder.name, None,
!                                new_id, self.as_string())
          self._check(response, 'append')
          # we need to update the uid, as it will have changed
--- 143,149 ----
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
!         time_stamp = self.extractTime()
          response = imap.append(self.folder.name, None,
!                                time_stamp, self.as_string())
          self._check(response, 'append')
          # we need to update the uid, as it will have changed
***************
*** 127,175 ****
          # XXX changed, as the message to be deleted will be found first
          # XXX (if they are in the same folder)
!         #response = imap.uid("SEARCH", "(TEXT)", self.as_string())
!         #self._check(response, 'search')
!         #self.id = response[1][0]
  
          old_id = self.id
!         if self.previous_folder is not None:
!             response = imap.select(self.previous_folder.name, False)
!             self._check(response, 'folder select')
              self.previous_folder = None
!             response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
!             self._check(response, 'store')
  
!             #XXX This code to deletd the old message id from the message
!             #XXX info db and manipulate the message id, is a *serious* hack.
!             #XXX There's gotta be a better way to do this.
  
!             message.msginfoDB._delState(self)
              
!         self.id = str(new_id)
          self.modified()
  
  
  class IMAPFolder(object):
-     # response checking is necessary throughout this class
      def __init__(self, folder_name, readOnly=True):
          self.name = folder_name
-         # Convert folder name to a uid
-         self.uid = None
-         response = imap.select(self.name, readOnly)
-         responses = imap.response("OK")[1]
-         for response in responses:
-             if response[:13] == "[UIDVALIDITY ":
-                 r = re.compile(r"(?P<uid>\d+)")
-                 self.uid = r.search(response[13:]).group('uid')
-         # We really want to use RFC822.PEEK here, as that doesn't effect
-         # the status of the message.  Unfortunately, it appears that not
-         # all IMAP servers support this, even though it is in RFC1730
-         self.rfc822_command = "(RFC822.PEEK)"
-         response = imap.fetch("1:1", self.rfc822_command)
-         if response[0] != "OK":
-             self.rfc822_command = "(RFC822)"
- 
-     def Select(self):
-         imap.select(self.name, False)
-         self._check(folder, 'select')
  
      def _check(self, response, command):
--- 151,187 ----
          # XXX changed, as the message to be deleted will be found first
          # XXX (if they are in the same folder)
! #        response = imap.uid("SEARCH", "(TEXT)", self.as_string())
! #        self._check(response, 'search')
! #        new_id = response[1][0]
!         # XXX This fails at the moment and needs to be resolved,
!         # XXX but it can't be properly checked until the header
!         # XXX adding part of the message class works.
!         # XXX For the moment, having a new empty-string id just
!         # XXX mucks up our message database, not the training or
!         # XXX filtering itself
!         new_id = ""
  
          old_id = self.id
!         if self.previous_folder is None:
!             self.folder.Select(False)
!         else:
!             self.previous_folder.Select(False)
              self.previous_folder = None
!         response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
!         self._check(response, 'store')
  
!         #XXX This code to delete the old message id from the message
!         #XXX info db and manipulate the message id, is a *serious* hack.
!         #XXX There's gotta be a better way to do this.
  
!         message.msginfoDB._delState(self)
              
!         self.id = new_id
          self.modified()
  
  
  class IMAPFolder(object):
      def __init__(self, folder_name, readOnly=True):
          self.name = folder_name
  
      def _check(self, response, command):
***************
*** 189,193 ****
          '''Returns uids for all the messages in the folder'''
          # request message range
!         response = imap.select(self.name, True)
          total_messages = response[1][0]
          if total_messages == '0':
--- 201,205 ----
          '''Returns uids for all the messages in the folder'''
          # request message range
!         response = Select(self.name, True, True)
          total_messages = response[1][0]
          if total_messages == '0':
***************
*** 204,208 ****
      def __getitem__(self, key):
          '''Return message matching the given uid'''
!         response = imap.uid("FETCH", key, self.rfc822_command)
          messageText = response[1][0][1]
          # we return an instance of *our* message class, not the
--- 216,229 ----
      def __getitem__(self, key):
          '''Return message matching the given uid'''
!         global rfc822_command
!         Select(self.name, True)
!         # We really want to use RFC822.PEEK here, as that doesn't effect
!         # the status of the message.  Unfortunately, it appears that not
!         # all IMAP servers support this, even though it is in RFC1730
!         response = imap.uid("FETCH", key, rfc822_command)
!         if response[0] != "OK":
!             rfc822_command = "(RFC822)"
!             response = imap.uid("FETCH", key, rfc822_command)
!         self._check(response, "uid fetch")
          messageText = response[1][0][1]
          # we return an instance of *our* message class, not the
***************
*** 214,217 ****
--- 235,241 ----
          return msg
  
+     def Select(self, readOnly):
+         return Select(self.name, readOnly)
+ 
      def Train(self, classifier, isSpam):
          '''Train folder as spam/ham'''
***************
*** 252,258 ****
              
  class IMAPFilter(object):
!     def __init__(self, classifier):
          global imap
          imap = imaplib.IMAP4(options.imap_server, options.imap_port)
  
          self.Login(options.imap_username, options.imap_password)
--- 276,283 ----
              
  class IMAPFilter(object):
!     def __init__(self, classifier, debug):
          global imap
          imap = imaplib.IMAP4(options.imap_server, options.imap_port)
+         imap.debug = imapDebug
  
          self.Login(options.imap_username, options.imap_password)
***************
*** 274,278 ****
  
          if options.imap_spam_train_folders != "":
!             spam_training_folders = options.imap_spam_train_folders.split(' ' )
              for fol in spam_training_folders:
                  folder = IMAPFolder(fol)
--- 299,303 ----
  
          if options.imap_spam_train_folders != "":
!             spam_training_folders = options.imap_spam_train_folders.split()
              for fol in spam_training_folders:
                  folder = IMAPFolder(fol)
***************
*** 303,307 ****
              if str(e) == "permission denied":
                  print "There was an error logging in to the IMAP server."
!                 print "The userid and/or password may be in error."
                  sys.exit()
              else:
--- 328,332 ----
              if str(e) == "permission denied":
                  print "There was an error logging in to the IMAP server."
!                 print "The userid and/or password may be incorrect."
                  sys.exit()
              else:
***************
*** 348,355 ****
          elif opt == '-e':
              doExpunge = not doExpunge
!         elif opt == '-i:':
              imapDebug = int(arg)
  
- 
      bdbname = os.path.expanduser(bdbname)
      
--- 373,379 ----
          elif opt == '-e':
              doExpunge = not doExpunge
!         elif opt == '-i':
              imapDebug = int(arg)
  
      bdbname = os.path.expanduser(bdbname)
      
***************
*** 365,370 ****
          print "Done."            
                  
!     imap_filter = IMAPFilter(classifier)
!     imap.debug = imapDebug
  
      if doTrain:
--- 389,393 ----
          print "Done."            
                  
!     imap_filter = IMAPFilter(classifier, imapDebug)
  
      if doTrain:



From timstone4 at users.sourceforge.net  Sun Apr 13 23:07:34 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 14 01:07:38 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.10,1.11
Message-ID: <E194wBq-0008HN-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv31805

Modified Files:
	imapfilter.py 
Log Message:
Fixed the docstring not printing on -h, changed -e operand to have a value
argument of y/n to control expunging, and added a -l value operand for
looping the filter with a sleep time interval.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** imapfilter.py	14 Apr 2003 00:15:50 -0000	1.10
--- imapfilter.py	14 Apr 2003 05:07:32 -0000	1.11
***************
*** 1,6 ****
  #!/usr/bin/env python
  
- from __future__ import generators
- 
  """An IMAP filter.  An IMAP message box is scanned and all non-scored
  messages are scored and (where necessary) filtered.
--- 1,4 ----
***************
*** 22,27 ****
              -h          : help
              -v          : verbose mode
!             -e          : sets expunge to the *opposite* of options.imap_expunge
              -i debuglvl : a somewhat mysterious imaplib debugging level
  
  Examples:
--- 20,26 ----
              -h          : help
              -v          : verbose mode
!             -e y/n      : sets expunge to the *opposite* of options.imap_expunge
              -i debuglvl : a somewhat mysterious imaplib debugging level
+             -l minutes  : period of time between filtering operations
  
  Examples:
***************
*** 39,43 ****
      o Find a better way to remove old msg from info database when saving
        modified messages
-     o Use DELETE rather than storing //DELETED flag when saving modified messages
      o Web UI for configuration and setup. Tony thinks it would be
          nice if there was a web ui to this for the initial setup (i.e. like
--- 38,41 ----
***************
*** 54,58 ****
        running (like pop3proxy, for example) and periodically checked for
        any new messages to process (with the RECENT command).  The period
!       could be an option.
      o Suggestions?
  """
--- 52,56 ----
        running (like pop3proxy, for example) and periodically checked for
        any new messages to process (with the RECENT command).  The period
!       could be an option.  This is partially done with the -l operand.
      o Suggestions?
  """
***************
*** 65,68 ****
--- 63,68 ----
  __credits__ = "Tim Stone, All the Spambayes folk."
  
+ from __future__ import generators
+ 
  try:
      True, False
***************
*** 343,347 ****
  
      try:
!         opts, args = getopt.getopt(sys.argv[1:], 'htcvei:d:D:')
      except getopt.error, msg:
          print >>sys.stderr, str(msg) + '\n\n' + __doc__
--- 343,347 ----
  
      try:
!         opts, args = getopt.getopt(sys.argv[1:], 'htcvl:e:i:d:D:')
      except getopt.error, msg:
          print >>sys.stderr, str(msg) + '\n\n' + __doc__
***************
*** 354,357 ****
--- 354,358 ----
      doExpunge = options.imap_expunge
      imapDebug = 0
+     sleepTime = 0
  
      for opt, arg in opts:
***************
*** 372,378 ****
              options.verbose = True
          elif opt == '-e':
!             doExpunge = not doExpunge
          elif opt == '-i':
              imapDebug = int(arg)
  
      bdbname = os.path.expanduser(bdbname)
--- 373,388 ----
              options.verbose = True
          elif opt == '-e':
!             if arg == 'y':
!                 doExpunge = True
!             else:
!                 doExpunge = False
          elif opt == '-i':
              imapDebug = int(arg)
+         elif opt == '-l':
+             sleepTime = int(arg) * 60
+ 
+     if not (doClassify or doTrain):
+         print "-c and/or -t operands must be specified"
+         sys.exit()
  
      bdbname = os.path.expanduser(bdbname)
***************
*** 390,398 ****
                  
      imap_filter = IMAPFilter(classifier, imapDebug)
  
!     if doTrain:
!         imap_filter.Train()
!     if doClassify:
!         imap_filter.Filter()
          
      imap_filter.Logout(doExpunge)
--- 400,418 ----
                  
      imap_filter = IMAPFilter(classifier, imapDebug)
+     print sleepTime
+     while 1:
+         if doTrain:
+             if options.verbose:
+                 print "Training"
+             imap_filter.Train()
+         if doClassify:
+             if options.verbose:
+                 print "Classifying"
+             imap_filter.Filter()
  
!         if sleepTime:
!             time.sleep(sleepTime)
!         else:
!             break
          
      imap_filter.Logout(doExpunge)



From timstone4 at users.sourceforge.net  Sun Apr 13 23:15:32 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 14 01:15:35 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.11,1.12
Message-ID: <E194wJY-00011f-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv3899

Modified Files:
	imapfilter.py 
Log Message:
Left a debug message in.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.11
retrieving revision 1.12
diff -C2 -d -r1.11 -r1.12
*** imapfilter.py	14 Apr 2003 05:07:32 -0000	1.11
--- imapfilter.py	14 Apr 2003 05:15:27 -0000	1.12
***************
*** 400,404 ****
                  
      imap_filter = IMAPFilter(classifier, imapDebug)
!     print sleepTime
      while 1:
          if doTrain:
--- 400,404 ----
                  
      imap_filter = IMAPFilter(classifier, imapDebug)
! 
      while 1:
          if doTrain:



From timstone4 at users.sourceforge.net  Mon Apr 14 20:22:45 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 14 22:22:48 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.12,1.13
Message-ID: <E195G5t-0005lH-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv22122

Modified Files:
	imapfilter.py 
Log Message:
Timestamp for new messages extracted correctly

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.12
retrieving revision 1.13
diff -C2 -d -r1.12 -r1.13
*** imapfilter.py	14 Apr 2003 05:15:27 -0000	1.12
--- imapfilter.py	15 Apr 2003 02:22:42 -0000	1.13
***************
*** 130,134 ****
          # timestamp from the message itself, but for the moment, we
          # just use the current time.
!         return imaplib.Time2Internaldate(time.time())
  
      def MoveTo(self, dest):
--- 130,137 ----
          # timestamp from the message itself, but for the moment, we
          # just use the current time.
!         try:
!             return self["Date"]
!         except KeyError:
!             return imaplib.Time2Internaldate(time.time())
  
      def MoveTo(self, dest):



From anadelonbrin at users.sourceforge.net  Wed Apr 16 18:08:20 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Wed Apr 16 20:08:23 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.13,1.14
Message-ID: <E195wwu-0008Nw-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv32173

Modified Files:
	imapfilter.py 
Log Message:
Fix the invalid date problem reported by Oliver Maunder.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.13
retrieving revision 1.14
diff -C2 -d -r1.13 -r1.14
*** imapfilter.py	15 Apr 2003 02:22:42 -0000	1.13
--- imapfilter.py	17 Apr 2003 00:08:17 -0000	1.14
***************
*** 20,24 ****
              -h          : help
              -v          : verbose mode
!             -e y/n      : sets expunge to the *opposite* of options.imap_expunge
              -i debuglvl : a somewhat mysterious imaplib debugging level
              -l minutes  : period of time between filtering operations
--- 20,24 ----
              -h          : help
              -v          : verbose mode
!             -e y/n      : expunge/purge messages on exit (y) or not (n)
              -i debuglvl : a somewhat mysterious imaplib debugging level
              -l minutes  : period of time between filtering operations
***************
*** 79,82 ****
--- 79,83 ----
  import getopt
  import email.Parser
+ from email.Utils import parsedate
  
  from spambayes.Options import options
***************
*** 131,135 ****
          # just use the current time.
          try:
!             return self["Date"]
          except KeyError:
              return imaplib.Time2Internaldate(time.time())
--- 132,136 ----
          # just use the current time.
          try:
!             return imaplib.Time2Internaldate(time.mktime(parsedate(self["Date"])))
          except KeyError:
              return imaplib.Time2Internaldate(time.time())
***************
*** 150,167 ****
                                 time_stamp, self.as_string())
          self._check(response, 'append')
-         # we need to update the uid, as it will have changed
-         # XXX there will be problems here if the message *has not*
-         # XXX changed, as the message to be deleted will be found first
-         # XXX (if they are in the same folder)
- #        response = imap.uid("SEARCH", "(TEXT)", self.as_string())
- #        self._check(response, 'search')
- #        new_id = response[1][0]
-         # XXX This fails at the moment and needs to be resolved,
-         # XXX but it can't be properly checked until the header
-         # XXX adding part of the message class works.
-         # XXX For the moment, having a new empty-string id just
-         # XXX mucks up our message database, not the training or
-         # XXX filtering itself
-         new_id = ""
  
          old_id = self.id
--- 151,154 ----
***************
*** 174,177 ****
--- 161,174 ----
          self._check(response, 'store')
  
+         # We need to update the uid, as it will have changed
+         # XXX There will be problems here if the message *has not*
+         # XXX changed, as the message to be deleted will be found first
+         # XXX (if they are in the same folder)
+         self.folder.Select(True)
+         #response = imap.uid("SEARCH", "TEXT", self.as_string())
+         #self._check(response, 'search')
+         #new_id = response[1][0]
+         new_id = ""
+ 
          #XXX This code to delete the old message id from the message
          #XXX info db and manipulate the message id, is a *serious* hack.
***************
*** 179,183 ****
  
          message.msginfoDB._delState(self)
-             
          self.id = new_id
          self.modified()
--- 176,179 ----
***************
*** 404,408 ****
      imap_filter = IMAPFilter(classifier, imapDebug)
  
!     while 1:
          if doTrain:
              if options.verbose:
--- 400,404 ----
      imap_filter = IMAPFilter(classifier, imapDebug)
  
!     while True:
          if doTrain:
              if options.verbose:



From anadelonbrin at users.sourceforge.net  Wed Apr 16 18:41:32 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Wed Apr 16 20:42:02 2003
Subject: [Spambayes-checkins] spambayes INTEGRATION.txt,1.7,1.8
Message-ID: <E195xT2-0002z5-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv11441

Modified Files:
	INTEGRATION.txt 
Log Message:
Update to include basic information about the IMAP filter.
Also updated SMTP proxy information so that it is (hopefully!)
clearer.
Updated the POP3 proxy information so that users are
directed to configure spambayes via the web user interface
rather than mucking about in bayescustomize.ini.

Index: INTEGRATION.txt
===================================================================
RCS file: /cvsroot/spambayes/spambayes/INTEGRATION.txt,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** INTEGRATION.txt	11 Mar 2003 01:51:05 -0000	1.7
--- INTEGRATION.txt	17 Apr 2003 00:41:30 -0000	1.8
***************
*** 63,67 ****
  --------
  
! There are six main components to the Spambayes system:
  
   o A database.  Loosely speaking, this is a collection of words and
--- 63,67 ----
  --------
  
! There are eight main components to the Spambayes system:
  
   o A database.  Loosely speaking, this is a collection of words and
***************
*** 80,86 ****
  
   o The POP3 proxy.  This sits between your email client (Eudora, Outlook
!    Express, etc) and your email server, and adds the classification header
!    to emails as you download them.  A typical user's email setup looks
!    like this:
  
         +-----------------+                              +-------------+
--- 80,86 ----
  
   o The POP3 proxy.  This sits between your email client (Eudora, Outlook
!    Express, etc) and your incoming email server, and adds the
!    classification header to emails as you download them.  A typical
!    user's email setup looks like this:
  
         +-----------------+                              +-------------+
***************
*** 109,116 ****
     servers, if you have more than one email account.
  
!  o The web interface.  This is a server that runs alongside the POP3 proxy
!    and lets you control it through the web.  You can upload emails to it
!    for training or classification, query the probabilities database ("How
!    many of my emails really *do* contain the word Viagra"?) and most
     importantly, train it on the emails you've received.  When you start
     using the system, unless you train it using the Hammie script it will
--- 109,148 ----
     servers, if you have more than one email account.
  
!  o The SMTP proxy.  This sits between your email client (Eudora, Outlook
!    Express, etc) and your outgoing email server.  Any mail sent to
!    spambayes_spam@localhost or spambayes_ham@localhost is intercepted
!    and trained appropriately.  A typical user's email setup looks like
!    this:
! 
!        +-----------------+                              +-------------+
!        | Outlook Express |      Internet or intranet    |             |
!        |  (or similar)   | <--------------------------> | SMTP server |
!        |                 |                              |             |
!        +-----------------+                              +-------------+
! 
!    The SMTP server runs either at your ISP for internet mail, or somewhere
!    on your internal network for corporate mail.  The SMTP proxy sits in the
!    middle and checks for mail to train on as you send your email:
! 
!        +-----------------+        +------------+        +-------------+
!        | Outlook Express |        | Spambayes  |        |             |
!        |  (or similar)   | <----> | SMTP proxy | <----> | SMTP server |
!        |                 |        |            |        |             |
!        +-----------------+        +------------+        +-------------+
! 
!    So where you currently have your email client configured to talk to
!    say, "smtp.my-isp.com", you instead configure the *proxy* to talk to
!    "smtp.my-isp.com" and configure your email client to talk to the proxy.
!    The SMTP proxy can live on your PC, or on the same machine as the SMTP
!    server, or on a different machine entirely, it really doesn't matter.
!    Say it's living on your PC, you'd configure your email client to talk
!    to "localhost".  You can configure the proxy to talk to multiple SMTP
!    servers, if you have more than one email account.
! 
!  o The web interface.  This is a server that runs alongside the POP3 proxy,
!    SMTP proxy, and IMAP filter (see below) and lets you control it through
!    the web.  You can upload emails to it for training or classification,
!    query the probabilities database ("How many of my emails really *do*
!    contain the word Viagra"?), find particular messages, and most
     importantly, train it on the emails you've received.  When you start
     using the system, unless you train it using the Hammie script it will
***************
*** 124,133 ****
     to do it correct the odd mistake - it's very quick and easy.
  
!  o The Outlook plug-in.  For Outlook 2000 users (not Outlook Express) this
!    lets you manage the whole thing from within Outlook.  You set up a Ham
!    folder and a Spam folder, and train it simply by dragging messages into
!    those folders.  Alternatively there are buttons to do the same thing.
!    And it integrates into Outlook's filtering system to make it easy to
!    file all the suspected spam into its own folder, for instance.
  
   o The Hammie script.  This does three jobs: command-line training,
--- 156,165 ----
     to do it correct the odd mistake - it's very quick and easy.
  
!  o The Outlook plug-in.  For Outlook 2000 and Outlook XP users (not Outlook
!    Express) this lets you manage the whole thing from within Outlook.  You
!    set up a Ham folder and a Spam folder, and train it simply by dragging
!    messages into those folders.  Alternatively there are buttons to do the
!    same thing. And it integrates into Outlook's filtering system to make it
!    easy to file all the suspected spam into its own folder, for instance.
  
   o The Hammie script.  This does three jobs: command-line training,
***************
*** 138,149 ****
     hammiesrv.py.
  
  
  Where things live
  -----------------
  
! The Hammie script is called hammie.py.  The POP3 proxy and the web
! interface live in pop3proxy.py.  The Outlook plug-in lives in the
! Outlook2000 subdirectory - see the README.txt in that directory for more
! information on that.
  
  As well as these components, there's also a whole pile of utility scripts,
--- 170,189 ----
     hammiesrv.py.
  
+  o The IMAP filter.  This is a cross between the POP3 proxy and the Outlook
+    plugin.  If your mail sits on an IMAP server, you can use the this to
+    filter your mail.  You can designate folders that contain mail to train
+    as ham and folders that contain mail to train as spam, and the filter
+    does this for you.  You can also designate folders to filter, along with
+    a folder for messages Spambayes is unsure about, and a folder for
+    suspected spam. When new mail arrives, the filter will move mail to the
+    appropriate location (ham is left in the original folder).
  
  Where things live
  -----------------
  
! The Hammie script is called hammie.py.  The POP3 proxy lives in pop3proxy.py,
! and the smtpproxy lives in smtpproxy.py.  The IMAP filter lives in
! imapfilter.py.  The Outlook plug-in lives in the Outlook2000 subdirectory
! - see the README.txt in that directory for more information on that.
  
  As well as these components, there's also a whole pile of utility scripts,
***************
*** 163,166 ****
--- 203,211 ----
  them, all lives in Options.py.  To change an option, create a
  bayescustomize.ini and add the option to that - don't edit Options.py.
+ If you are using the POP3 proxy, SMTP proxy or IMAP filter, you can also
+ change most of the options you will need to access via the web user
+ interface.  You will probably find this at <http://localhost:8880>. To
+ configure the Outlook plugin, you should click on the Anti-Spam button on
+ the toolbar.
  
  
***************
*** 181,213 ****
  --------------------------------------------------------
  
! The minimum you need to do to get started is create a bayescustomize.ini
! containing the following:
! 
! [pop3proxy]
! pop3proxy_servers: pop3.my-isp.com
! 
! where "pop3.my-isp.com" is wherever you currently have your email client
! configured to collect mail from.  The proxy will run on port 110 - if you're
! already running a real POP3 proxy on that port, or you're running on a
! platform that won't let unprivileged processes use that port (eg. unix),
! you can use a different one by adding a line like this:
! 
! pop3proxy_ports: 1110
! 
! to the [pop3proxy] section of bayescustomize.ini.
! 
! You can now run the proxy by running "python pop3proxy.py".  This will
! print some status messages, which should include:
! 
! BayesProxyListener listening on port 110.
! UserInterfaceListener listening on port 8880.
  
! What that means is that the POP3 proxy is ready for your email client to
! connect to it on port 110 and that the web interface is ready for your
! browser to connect to it.  The address of the web interface is
! http://localhost:8880/ (or if you're running it on a different machine,
! replace 'localhost' with the name of the machine).  You can have a look
! at the web interface now, but it won't be very interesting because the
! system hasn't seen any messages yet.
  
  
--- 226,238 ----
  --------------------------------------------------------
  
! To setup the POP3 and SMTP proxies, run
!     pop3proxy.py -b
! from the command line.  The web interface should open in your default
! browser.  You need to click on the "Configuration Link" to go to the setup
! page.  The minimum you need to do to get started is enter the servers and
! ports information in the POP3 proxy and SMTP proxy sections.
  
! The POP3 proxy is then ready for your email client to connect to it on
! port 110 and the SMTP proxy is ready for connections on port 25.
  
  
***************
*** 215,222 ****
  ------------------------------------------
  
! You now need to configure your email client to talk to the proxy instead of
! the real email server.  Change your equivalent of "pop3.my-isp.com" to
  "localhost" (or to the name of the machine you're running the proxy on) in
! your email client's setup.  Hit "Get new email" and look at the headers of
  the emails (send yourself an email if you don't have any!) - there should
  be an X-Spambayes-Classification header there.  It probably says "unsure",
--- 240,248 ----
  ------------------------------------------
  
! You now need to configure your email client to talk to the proxies instead of
! the real email servers.  Change your equivalent of "pop3.my-isp.com" to
  "localhost" (or to the name of the machine you're running the proxy on) in
! your email client's setup, and do the same with your equivalent of
! "smtp.my-isp.com". Hit "Get new email" and look at the headers of
  the emails (send yourself an email if you don't have any!) - there should
  be an X-Spambayes-Classification header there.  It probably says "unsure",
***************
*** 234,237 ****
--- 260,277 ----
  "Total emails trained" has increased.
  
+ Alternatively, when you receive an incorrectly classified message, you can
+ forward it to the SMTP proxy for training.  If the message should have been
+ classified as spam, forward or bounce the message to spambayes_spam@localhost,
+ and if the message should have been classified as ham, forward it to
+ spambayes_ham@localhost.  You can still review the training through the web
+ interface, if you wish to do so.
+ 
+ Note that some mail clients (particularly Outlook Express) do not forward
+ all headers when you bounce, forward or redirect mail.  For these clients,
+ you will need to set (via the web interface) the "add mail id to" option
+ to body, which will add a unique id to the body of each message you
+ receive.  You can also use this id to find a particular message via the
+ web interface.
+ 
  Once you've done this on a few spams and a few hams, you'll find that the
  X-Spambayes-Classification header is getting it right most of the time.  The
***************
*** 245,268 ****
  messages to the web interface via the "Train" form on the Home page.  You
  can train on individual messages (which is tedious) or using mbox files.
- 
- An alternative to training via the web interface is to run the SMTP proxy.
- Just as the POP3 proxy sits between your mail client and your POP3 server,
- the SMTP proxy sits between your mail client and your SMTP server.  To run
- the server, start pop3proxy with the "-s" switch.  You will need to setup
- your mail client just as with the POP3 proxy - change the outgoing mail
- (SMTP) server to localhost (or if you are running pop3proxy on a different
- machine, replace localhost with the name of the machine).  In the web
- interface, set the SMTP options to the address and port of your SMTP
- server.  You will also need to set the "add mail id to" option to "header".
- To train, you can now forward or bounce mail to spambayes_ham@localhost,
- or spambayes_spam@localhost (you can change these addresses via the web
- interface).
- 
- Note that some mail clients (particularly Outlook Express) do not forward
- all headers when you bounce, forward or redirect mail.  For these clients,
- you will need to set (via the web interface) the "add mail id to" option
- to body, which will add a unique id to the body of each message you
- receive.  You can also use this id to find a particular message via the
- web interface.
  
  
--- 285,288 ----



From anadelonbrin at users.sourceforge.net  Wed Apr 16 19:52:20 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Wed Apr 16 21:52:25 2003
Subject: [Spambayes-checkins] 
	website faq.ht, NONE, 1.1 applications.ht, 1.2,
	1.3 background.ht, 1.13, 1.14 developer.ht, 1.7, 1.8 docs.ht,
	1.8, 1.9 download.ht, 1.2, 1.3 index.ht, 1.11, 1.12 links.h,
	1.5, 1.6
Message-ID: <E195yZY-0000N9-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/website
In directory sc8-pr-cvs1:/tmp/cvs-serv1396

Modified Files:
	applications.ht background.ht developer.ht docs.ht download.ht 
	index.ht links.h 
Added Files:
	faq.ht 
Log Message:
General update to cover the new applications,
the alpha2 release, and an increase in
documentation.

--- NEW FILE: faq.ht ---
Title: SpamBayes: Frequently Asked Questions
Author-Email: spambayes@python.org
Author: spambayes

<h2>Frequently Asked Questions</h2>
<ol>
<li>Development</li>
<ol>
<li><a href="#tokentrick">Hey!  Why don't you implement cool tokenizer trick X?  I think it would really foil those spammers!</a></li>
<li><a href="#serverside">This software is great!  I want to implement it for all my users. Are there plans to develop a server-side spambayes solution?</a></li>
</ol>
<li>Using Spambayes</li>
<ol>
<li><a href="#unsure">I just got a spam, but the system said it was "unsure". Why couldn't it tell that it was spam - it's obvious?</a></li>
<li><a href="#stillunsure">OK, I trained on that message. But I just got *another* one, and the stupid system still thinks it's unsure. Why did it ignore me???</a></li>
<li><a href="#wipetraining">I've mucked up my training and I want to start all over again, but there isn't an option for this anywhere.  What do I do?</a></li>
</ol>
</ol>
<p>If you have any suggestions about other questions and answers that should be included
here, please mail <a href="mailto:spambayes@python.org">the list</a> with them.</p>
<h3><a name="#tokentrick">Hey!  Why don't you implement cool tokenizer trick X?  I think it
   would really foil those spammers!</a></h3>
<p>Have you run your tokenizer trick against a set of messages to see if
   it actually works?  Many times what seems like a good idea turns out
   not to help much, and sometimes even hurts.  If you have a good idea,
   you've run it against a batch of messages and can prove that it
   helps, paste the code for your technique and the proof to the mailing
   list.  If you're not a coder, but are really keen on your idea, post
   a feature request on the project page, and wait for someone else to
   code it for you (but make sure you do some testing when it's done).
   Otherwise, you will likely get a message from Tim Peters about
   why you need to test your idea :)</p>

<h3><a name="#serverside">This software is great!  I want to implement it for all my users.
   Are there plans to develop a server-side spambayes solution?</a></h3>
<p>The problem with a server-side solution is that everyone has a
   different idea of what is spam - that's the whole strength of the
   bayesian-style filtering concept.  If you are certain that *all*
   of your users would agree on what is spam and what is not, then
   this might work for you, but otherwise you really have to have
   individual databases for each user.  Either way, you should be
   able to modify spambayes easily enough to fit into your setup.
   Please let the list know if you do have success in this area, and
   we'll update this answer.</p>

<h3><a name="#unsure">I just got a spam, but the system said it was "unsure". Why
   couldn't it tell that it was spam - it's obvious?</a></h3>
<p>It may be obvious to you, but the classifier only works on
   the information it has been given. Maybe this is "new" (you've
   never seen this particular flavour of spam before), or maybe
   there aren't enough clues in the message which the system is
   aware of as strong spam clues.</p>

<h3><a name="#stillunsure">OK, I trained on that message. But I just got *another* one,
   and the stupid system still thinks it's unsure. Why did it
   ignore me???</a></h3>
<p>It didn't, but you may need to train on a few more of this type
   of message to get it classified as "spam". The classification
   algorithm weights its results based on the number of times it
   has seen a particular clue, so that clues unique to this type
   of message may need a few more instances to become "convincing".</p>

<h3><a name="#wipetraining">I've mucked up my training and I want to start all over again,
   but there isn't an option for this anywhere.  What do I do?</a></h3>
<p>Because training from scratch is a very rare occurance, and because
   deleting all your training information is something you don't want
   to do by accident, there isn't an option for this.  However, you
   can quite simply do this manually.  All the training data is stored
   in a file, usually called hammie.db, and if you delete (or rename)
   this, then you will start training from scratch.  If you are using
   the web interface for the POP3 proxy, the configuration page tells
   you what this file is called (and where it is) down towards the
   bottom of the page.</p>

Index: applications.ht
===================================================================
RCS file: /cvsroot/spambayes/website/applications.ht,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** applications.ht	3 Mar 2003 22:24:39 -0000	1.2
--- applications.ht	17 Apr 2003 01:52:17 -0000	1.3
***************
*** 8,18 ****
  getting there (and help is always appreciated).
  </p>
! <h3>Outlook2000</h3>
! <p>Sean True and Mark Hammond have developed an addin for Outlook2000 that
  adds support for the spambayes classifier. 
  <h4>Requirements</h4>
  <ul>
! <li>Python2.2 or later (2.2.2 recommended)
! <li>Outlook 2000 (<b>not</b> Outlook Express)
  <li>Python's <a href="http://starship.python.net/crew/mhammond">win32com</a>
  extensions (win32all-149 or later - currently ActivePython is not suitable)
--- 8,18 ----
  getting there (and help is always appreciated).
  </p>
! <h3>Outlook</h3>
! <p>Sean True and Mark Hammond have developed an addin for Outlook (2000 and XP) that
  adds support for the spambayes classifier. 
  <h4>Requirements</h4>
  <ul>
! <li>Python 2.2 or later (2.2.2 recommended)
! <li>Outlook 2000 or Outlook XP (<b>not</b> Outlook Express)
  <li>Python's <a href="http://starship.python.net/crew/mhammond">win32com</a>
  extensions (win32all-149 or later - currently ActivePython is not suitable)
***************
*** 22,33 ****
  </p>
  <h4>Availability</h4>
! <p>At the moment, you'll need to use CVS to get the code - go <a href="http://sourceforge.net/cvs/?group_id=61702">to the CVS page</a> on the project's sourceforge site for more.</p>
  
  <h3>hammie.py</h3>
! <p>hammie is a command line tool for marking mail as ham or spam. Skip Montanaro has started a <a href="http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/*checkout*/spambayes/spambayes/INTEGRATION.txt?rev=HEAD&content-type=text/plain">guide to integrating hammie with your mailer</a> (Unix-only instructions at the moment - additions welcome!). 
  Currently it focusses on running hammie via procmail. </p>
  <h4>Requirements</h4>
  <ul>
! <li>Python2.2 or later (2.2.2 recommended)
  <li>Currently documentation focusses on Unix.
  </ul>
--- 22,37 ----
  </p>
  <h4>Availability</h4>
! <p>Mark has packaged together <a href="http://starship.python.net/crew/mhammond/downloads/SpamBayes-Outlook-Setup-002.exe">an installer for the plugin</a>.
! You can download it from <a href="http://starship.python.net/crew/mhammond/spambayes/">his website</a>.
! This is currently at version 002.</p>
! <p>Alternatively, you can use CVS to get the code - go <a href="http://sourceforge.net/cvs/?group_id=61702">to the CVS page</a> on the project's sourceforge site for more.</p>
  
  <h3>hammie.py</h3>
! <p>hammie is a command line tool for marking mail as ham or spam. Skip Montanaro has started a
! <a href="http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/*checkout*/spambayes/spambayes/INTEGRATION.txt?rev=HEAD&content-type=text/plain">guide to integrating hammie with your mailer</a> (Unix-only instructions at the moment - additions welcome!). 
  Currently it focusses on running hammie via procmail. </p>
  <h4>Requirements</h4>
  <ul>
! <li>Python 2.2 or later (2.2.2 recommended)
  <li>Currently documentation focusses on Unix.
  </ul>
***************
*** 38,41 ****
--- 42,58 ----
  <p>pop3proxy sits between your mail client and your real POP3 server and marks
  mail as ham or spam as it passes through. See the <a href="http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/*checkout*/spambayes/spambayes/pop3proxy.py?rev=HEAD&content-type=text/plain">docstring at the top of pop3proxy.py</a> for more.
+ <h4>Requirements</h4>
+ <ul>
+ <li>Python2.2 or later (2.2.2 recommended)
+ <li>Should work on windows/unix/whatever... ?
+ </ul>
+ </p>
+ <h4>Availability</h4>
+ <p>At the moment, you'll need to use CVS to get the code - go <a href="http://sourceforge.net/cvs/?group_id=61702">to the CVS page</a> on the project's sourceforge site for more.</p>
+ 
+ <h3>imapfilter.py</h3>
+ <p>imap filter connects to your imap server and marks mail as ham or spam,
+ moving it to appropriate folders as it arrives.
+ See the <a href="http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/*checkout*/spambayes/spambayes/pop3proxy.py?rev=HEAD&content-type=text/plain">docstring at the top of imapfilter.py</a> for more.
  <h4>Requirements</h4>
  <ul>

Index: background.ht
===================================================================
RCS file: /cvsroot/spambayes/website/background.ht,v
retrieving revision 1.13
retrieving revision 1.14
diff -C2 -d -r1.13 -r1.14
*** background.ht	22 Jan 2003 08:30:05 -0000	1.13
--- background.ht	17 Apr 2003 01:52:17 -0000	1.14
***************
*** 97,101 ****
  them wrong, but it's completely confident in its (wrong) score. (Note that the difference isn't as apparent as it could be - it's a logarithmic scale graph!)
  </p>
! <p class="todo">Add more here - cancellation disease, fudge factors, &c</p>
  
  <p>Gary Robinson's 
--- 97,101 ----
  them wrong, but it's completely confident in its (wrong) score. (Note that the difference isn't as apparent as it could be - it's a logarithmic scale graph!)
  </p>
! <!--Add more here - cancellation disease, fudge factors, &c-->
  
  <p>Gary Robinson's 
***************
*** 230,235 ****
  <p>There's a lot of background on what's been tried available from
  the mailing list archives. Initially, the discussion started on 
! the <a href="">python-dev</a> list, but then moved to the 
! <a href="">spambayes</a> list. 
  
  <ul>
--- 230,235 ----
  <p>There's a lot of background on what's been tried available from
  the mailing list archives. Initially, the discussion started on 
! the <a href="http://mail.python.org/pipermail/python-dev/">python-dev</a> list, but then moved to the 
! <a href="http://mail.python.org/pipermail-21/spambayes/">spambayes</a> list. 
  
  <ul>
***************
*** 251,255 ****
  
  <ul>
! <li>The older CVS repository via <a href="http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/python/python/nondist/sandbox/spambayes/?hideattic=0">view CVS</a>, or the <a href="presfchangelog.html">entire changelog</a>. Development here stopped on the 6th of September 2002.
  <li>After that, work moved to this project's <a href="http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/spambayes/spambayes/">CVS tree</a>
  </ul>
--- 251,256 ----
  
  <ul>
! <li>The older CVS repository via <a href="http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/python/python/nondist/sandbox/spambayes/?hideattic=0">view CVS</a>, or the <a href="presfchangelog.html">entire changelog</a>.
! Development here stopped on the 6th of September 2002.
  <li>After that, work moved to this project's <a href="http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/spambayes/spambayes/">CVS tree</a>
  </ul>

Index: developer.ht
===================================================================
RCS file: /cvsroot/spambayes/website/developer.ht,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** developer.ht	17 Jan 2003 07:34:44 -0000	1.7
--- developer.ht	17 Apr 2003 01:52:18 -0000	1.8
***************
*** 6,10 ****
  <p>So you want to get involved?</p>
  <h2>Running the code</h2>
! <p>This project works with either Python 2.2.2, Python2.3 (currently in alpha), 
  or on the bleeding edge of python code,
  available from <a href="http://sourceforge.net/cvs/?group_id=5470">CVS on
--- 6,10 ----
  <p>So you want to get involved?</p>
  <h2>Running the code</h2>
! <p>This project works with either Python 2.2.2, Python 2.3 (currently in alpha), 
  or on the bleeding edge of python code,
  available from <a href="http://sourceforge.net/cvs/?group_id=5470">CVS on
***************
*** 30,39 ****
  
  <h3>So what needs to be done</h3>
! <p>Currently (early November) work is now being focussed on finding 
! additional things that are beneficial to the tokenizer. The combining
! scheme is now pretty solid and pretty amazing. The other big body of
! work at the moment is producing something that's useful to end-users -
! actually building the applications and the code so that Tim's sister
! &lt;wink&gt; can use the system.</p>
  
  <h2>Collecting training data</h2>
--- 30,42 ----
  
  <h3>So what needs to be done</h3>
! <p>Currently (April) work is now being focused on improving deployment
! of the system (actually building the applications and the code so that
! Tim's sister &lt;wink&gt; can use the system), with the aim of eventually
! putting out a beta (or even full!) release.  There is still a certain
! amount of interest in finding additional things that are beneficial to
! the tokenizer, although most people are pretty happy with how it works
! at the moment. The combining scheme is now pretty solid and pretty amazing.
! The other big body of work is monitoring the bug reports and feature requests
! that come in and trying to resolve those.</p>
  
  <h2>Collecting training data</h2>

Index: docs.ht
===================================================================
RCS file: /cvsroot/spambayes/website/docs.ht,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** docs.ht	17 Jan 2003 06:26:50 -0000	1.8
--- docs.ht	17 Apr 2003 01:52:18 -0000	1.9
***************
*** 8,12 ****
  <li>The <a href="http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/*checkout*/spambayes/spambayes/TESTING.txt?rev=HEAD&content-type=text/plain">TESTING.txt</a> file -- Clues about the practice of statistical testing, adapted from Tim
   comments on python-dev.
! <li>There's also a vast number of clues and notes scattered as block comments through the code.
  </ul>
  
--- 8,14 ----
  <li>The <a href="http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/*checkout*/spambayes/spambayes/TESTING.txt?rev=HEAD&content-type=text/plain">TESTING.txt</a> file -- Clues about the practice of statistical testing, adapted from Tim
   comments on python-dev.
! <li>A rudimentary set of <a href="faq.html">Frequently Asked Questions (FAQ)</a>.</li>
! <li>Instructions on <a href="http://cvs.sourceforge.net/cgi-bin/viewcvs.cgi/*checkout*/spambayes/spambayes/INTEGRATION.txt?rev=HEAD&content-type=text/plain">integrating Spambayes</a> into your mail system.</li>
! <li>There're also a vast number of clues and notes scattered as block comments through the code.
  </ul>
  

Index: download.ht
===================================================================
RCS file: /cvsroot/spambayes/website/download.ht,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** download.ht	17 Jan 2003 17:00:52 -0000	1.2
--- download.ht	17 Apr 2003 01:52:18 -0000	1.3
***************
*** 4,9 ****
  
  <h2>Source Releases</h2>
! <p>The first pre-release of version 1.0 of the SpamBayes project is available.
! Download version 1.0a1 from the sourceforge <a href="https://sourceforge.net/project/showfiles.php?group_id=61702">Files</a> page as either a gzipped tarball or a zip file of the source files.
  </p>
  
--- 4,9 ----
  
  <h2>Source Releases</h2>
! <p>The second pre-release of version 1.0 of the SpamBayes project is available.
! Download version 1.0a2 from the sourceforge <a href="https://sourceforge.net/project/showfiles.php?group_id=61702">Files</a> page as either a gzipped tarball or a zip file of the source files.
  </p>
  
***************
*** 22,25 ****
--- 22,30 ----
  
  <h2>Binary Releases</h2>
+ <h3>Outlook Plugin</h3>
+ <p>Mark has packaged together <a href="http://starship.python.net/crew/mhammond/downloads/SpamBayes-Outlook-Setup-002.exe">an installer for the plugin</a>.
+ You can download it from <a href="http://starship.python.net/crew/mhammond/spambayes/">his website</a>.
+ This is currently at version 002.</p>
+ <h3>Other</h3>
  <p>None as yet.</p>
  
***************
*** 29,45 ****
  more details. 
  </p>
- <p><b>Update:</b></p>
- <p class="note">
- (2003-01-14 14:04:19 - Project CVS Services)   As of 2003-01-14,
- pserver-based CVS repository access and ViewCVS (web-based) CVS repository
- access have been taken offline as to stabilize CVS server performance for
- developers. These services will be re-enabled as soon as the underlying
- scalability issues have been analyzed and resolved (as soon as 2003-01-15,
- if possible). Additional updates will be posted to the Site Status page as
- they become available. Your patience is appreciated.
- </p>
- 
- <a name="snapshot"><h2>Nightly snapshots</h2></a>
- <p>A nightly snapshot is available: <a href="download/spambayes-nightly.tar.gz">spambayes-nightly.tar.gz</a>. </p>
- <p class="note">Note that due to some Sourceforge issues, this is currently being built with a "manual cron" (i.e. when I remember). Once Sourceforge's CVS issues are resolved, this will be available automatically.</p>
- 
--- 34,35 ----

Index: index.ht
===================================================================
RCS file: /cvsroot/spambayes/website/index.ht,v
retrieving revision 1.11
retrieving revision 1.12
diff -C2 -d -r1.11 -r1.12
*** index.ht	20 Jan 2003 20:32:52 -0000	1.11
--- index.ht	17 Apr 2003 01:52:18 -0000	1.12
***************
*** 5,10 ****
  
  <h2>News</h2>
! <p>First pre-release available. See the <a href="download.html">download</a> page for more.</p>
! <H2>What is SpamBayes?</h2>
  <p>
  The SpamBayes 
--- 5,10 ----
  
  <h2>News</h2>
! <p>Second pre-release available. See the <a href="download.html">download</a> page for more.</p>
! <h2>What is SpamBayes?</h2>
  <p>
  The SpamBayes 
***************
*** 92,96 ****
  <p>The code is currently available from a variety of methods from the
  <a href="download.html">downloads</a> page. The current release is
! 1.0 prerelease 1.
  </p>
  
--- 92,96 ----
  <p>The code is currently available from a variety of methods from the
  <a href="download.html">downloads</a> page. The current release is
! 1.0 alpha 2.
  </p>
  

Index: links.h
===================================================================
RCS file: /cvsroot/spambayes/website/links.h,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** links.h	17 Jan 2003 07:34:44 -0000	1.5
--- links.h	17 Apr 2003 01:52:18 -0000	1.6
***************
*** 8,11 ****
  <h3>Getting the code</h3>
  <li><a href="download.html">Releases</a>
- <li><a href="download.html#snapshot">Snapshots</a>
  <li><a href="download.html#cvs">CVS access</a>
--- 8,10 ----



From anthonybaxter at users.sourceforge.net  Wed Apr 16 23:14:39 2003
From: anthonybaxter at users.sourceforge.net (Anthony Baxter)
Date: Thu Apr 17 01:14:43 2003
Subject: [Spambayes-checkins] website faq.ht,1.1,1.2
Message-ID: <E1961jL-0006iu-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/website
In directory sc8-pr-cvs1:/tmp/cvs-serv25804

Modified Files:
	faq.ht 
Log Message:
note about stupid beats smart in the tokenizer tricks q.


Index: faq.ht
===================================================================
RCS file: /cvsroot/spambayes/website/faq.ht,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** faq.ht	17 Apr 2003 01:52:18 -0000	1.1
--- faq.ht	17 Apr 2003 05:14:36 -0000	1.2
***************
*** 19,24 ****
  <p>If you have any suggestions about other questions and answers that should be included
  here, please mail <a href="mailto:spambayes@python.org">the list</a> with them.</p>
! <h3><a name="#tokentrick">Hey!  Why don't you implement cool tokenizer trick X?  I think it
!    would really foil those spammers!</a></h3>
  <p>Have you run your tokenizer trick against a set of messages to see if
     it actually works?  Many times what seems like a good idea turns out
--- 19,24 ----
  <p>If you have any suggestions about other questions and answers that should be included
  here, please mail <a href="mailto:spambayes@python.org">the list</a> with them.</p>
! <h3><a name="#tokentrick">Hey!  Why don't you implement cool tokenizer trick 
!    X?  I think it would really foil those spammers!</a></h3>
  <p>Have you run your tokenizer trick against a set of messages to see if
     it actually works?  Many times what seems like a good idea turns out
***************
*** 30,36 ****
     code it for you (but make sure you do some testing when it's done).
     Otherwise, you will likely get a message from Tim Peters about
!    why you need to test your idea :)</p>
  
! <h3><a name="#serverside">This software is great!  I want to implement it for all my users.
     Are there plans to develop a server-side spambayes solution?</a></h3>
  <p>The problem with a server-side solution is that everyone has a
--- 30,41 ----
     code it for you (but make sure you do some testing when it's done).
     Otherwise, you will likely get a message from Tim Peters about
!    why you need to test your idea :)  Note that as a general rule,
!    we've found that with the tokenizer, "stupid beats smart" -- that is, 
!    very specialised tokenizer behaviour usually produces worse results than
!    a more general approach that just generates tokens and throws them at the 
!    classifier.</p>
  
! <h3><a name="#serverside">This software is great!  I want to implement it 
!    for all my users.
     Are there plans to develop a server-side spambayes solution?</a></h3>
  <p>The problem with a server-side solution is that everyone has a
***************
*** 44,49 ****
     we'll update this answer.</p>
  
! <h3><a name="#unsure">I just got a spam, but the system said it was "unsure". Why
!    couldn't it tell that it was spam - it's obvious?</a></h3>
  <p>It may be obvious to you, but the classifier only works on
     the information it has been given. Maybe this is "new" (you've
--- 49,54 ----
     we'll update this answer.</p>
  
! <h3><a name="#unsure">I just got a spam, but the system said it was "unsure". 
!    Why couldn't it tell that it was spam - it's obvious?</a></h3>
  <p>It may be obvious to you, but the classifier only works on
     the information it has been given. Maybe this is "new" (you've
***************
*** 52,58 ****
     aware of as strong spam clues.</p>
  
! <h3><a name="#stillunsure">OK, I trained on that message. But I just got *another* one,
!    and the stupid system still thinks it's unsure. Why did it
!    ignore me???</a></h3>
  <p>It didn't, but you may need to train on a few more of this type
     of message to get it classified as "spam". The classification
--- 57,63 ----
     aware of as strong spam clues.</p>
  
! <h3><a name="#stillunsure">OK, I trained on that message. But I just got 
!    <i>another</i> one, and the stupid system still thinks it's unsure. Why 
!     did it ignore me???</a></h3>
  <p>It didn't, but you may need to train on a few more of this type
     of message to get it classified as "spam". The classification
***************
*** 61,66 ****
     of message may need a few more instances to become "convincing".</p>
  
! <h3><a name="#wipetraining">I've mucked up my training and I want to start all over again,
!    but there isn't an option for this anywhere.  What do I do?</a></h3>
  <p>Because training from scratch is a very rare occurance, and because
     deleting all your training information is something you don't want
--- 66,72 ----
     of message may need a few more instances to become "convincing".</p>
  
! <h3><a name="#wipetraining">I've mucked up my training and I want to 
!    start all over again, but there isn't an option for this anywhere.  
!    What do I do?</a></h3>
  <p>Because training from scratch is a very rare occurance, and because
     deleting all your training information is something you don't want



From timstone4 at users.sourceforge.net  Thu Apr 17 09:47:25 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Thu Apr 17 11:47:32 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.14,1.15
Message-ID: <E196Bbh-00026Q-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv8030

Modified Files:
	imapfilter.py 
Log Message:
1. Corrected newline mangling (I hope), variations of which caused problems
    for Oliver Maunder and probably for David Abrahams (see mailing list)
2. Corrected folder comparison operation
3. Refactored functionality into an IMAPSession class, which results in a
    more consistent IMAP semantic
4. Added -p option to prompt for password, negating the necessity of storing the
    imap password in clear text in Options
5. Corrected error in training, which resulted in no training being performed

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.14
retrieving revision 1.15
diff -C2 -d -r1.14 -r1.15
*** imapfilter.py	17 Apr 2003 00:08:17 -0000	1.14
--- imapfilter.py	17 Apr 2003 15:47:20 -0000	1.15
***************
*** 20,23 ****
--- 20,25 ----
              -h          : help
              -v          : verbose mode
+             -p          : security option to prompt for imap password,
+                           rather than look in options.imap_password
              -e y/n      : expunge/purge messages on exit (y) or not (n)
              -i debuglvl : a somewhat mysterious imaplib debugging level
***************
*** 78,81 ****
--- 80,84 ----
  import sys
  import getopt
+ from getpass import getpass
  import email.Parser
  from email.Utils import parsedate
***************
*** 85,88 ****
--- 88,92 ----
  
  # global IMAPlib object
+ global imap
  imap = None
  
***************
*** 98,118 ****
  # nicer if we cached this information somewhere.
  # XXX If we wanted to be nice and tidy, this really belongs
! # XXX in an IMAPUtilities class, or something like that.
! current_folder = None
! current_folder_readonly = None
! def Select(folder, readOnly=True, force=False):
!     global current_folder
!     global current_folder_readonly
!     if current_folder != folder or current_folder_readonly != readOnly or force:
!         response = imap.select(folder, readOnly)
!         if response[0] != "OK":
!             print "Invalid response to %s:\n%s" % (command, response)
!             sys.exit(-1)
!         current_folder = folder
!         current_folder_readonly = readOnly
!         return response
  
  class IMAPMessage(message.SBHeaderMessage):
!     def __init__(self, folder, id):        
          message.Message.__init__(self)
  
--- 102,149 ----
  # nicer if we cached this information somewhere.
  # XXX If we wanted to be nice and tidy, this really belongs
! # XXX in an IMAPUtilities class, or something like that,
! # XXX or something like this:
! 
! class IMAPSession(imaplib.IMAP4):
!     '''A class extending the IMAP4 class, with a few optimizations'''
!     
!     def __init__(self, server, port, debug):
!         imaplib.Debug = debug  # this is a global in the imaplib module
!         imaplib.IMAP4.__init__(self, server, port)
!         self.current_folder = None
!         self.current_folder_readonly = None
! 
!     def login(self, uid, pw):
!         try:
!             imaplib.IMAP4.login(self, uid, pw)  # superclass login
!         except imaplib.IMAP4.error, e:
!             if str(e) == "permission denied":
!                 print "There was an error logging in to the IMAP server."
!                 print "The userid and/or password may be incorrect."
!                 sys.exit()
!             else:
!                 raise
!     
!     def logout(self, expunge):
!         # sign off
!         if expunge:
!             self.expunge()
!         imaplib.IMAP4.logout(self)  # superclass logout
!         
!     def SelectFolder(self, folder, readOnly=True, force=False):
!         '''A method to point ensuing imap operations at a target folder'''
!         
!         if self.current_folder != folder or \
!            self.current_folder_readonly != readOnly or force:
!             response = self.select(folder, readOnly)
!             if response[0] != "OK":
!                 print "Invalid response to %s:\n%s" % (command, response)
!                 sys.exit(-1)
!             self.current_folder = folder
!             self.current_folder_readonly = readOnly
!             return response
  
  class IMAPMessage(message.SBHeaderMessage):
!     def __init__(self, folder, id):
          message.Message.__init__(self)
  
***************
*** 128,141 ****
      def extractTime(self):
          # When we create a new copy of a message, we need to specify
!         # a timestamp for the message.  Ideally, this would be the
!         # timestamp from the message itself, but for the moment, we
!         # just use the current time.
          try:
!             return imaplib.Time2Internaldate(time.mktime(parsedate(self["Date"])))
          except KeyError:
              return imaplib.Time2Internaldate(time.time())
  
      def MoveTo(self, dest):
!         # The move just changes where we think we are,
          # and we do an actual move on save (to avoid doing
          # this more than once)
--- 159,172 ----
      def extractTime(self):
          # When we create a new copy of a message, we need to specify
!         # a timestamp for the message.  If the message has a date header
!         # we use that.  Otherwise, we use the current time.
          try:
!             return imaplib.Time2Internaldate(\
!                        time.mktime(parsedate(self["Date"])))
          except KeyError:
              return imaplib.Time2Internaldate(time.time())
  
      def MoveTo(self, dest):
!         # This move operation just changes where we think we are,
          # and we do an actual move on save (to avoid doing
          # this more than once)
***************
*** 148,160 ****
          # so what we do is create a new message and delete the old one
          time_stamp = self.extractTime()
          response = imap.append(self.folder.name, None,
!                                time_stamp, self.as_string())
          self._check(response, 'append')
  
          old_id = self.id
          if self.previous_folder is None:
!             self.folder.Select(False)
          else:
!             self.previous_folder.Select(False)
              self.previous_folder = None
          response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
--- 179,193 ----
          # so what we do is create a new message and delete the old one
          time_stamp = self.extractTime()
+         msgstr = re.sub('([^\r])\n', r'\1\r\n', self.as_string())
+         
          response = imap.append(self.folder.name, None,
!                                time_stamp, msgstr)
          self._check(response, 'append')
  
          old_id = self.id
          if self.previous_folder is None:
!             imap.SelectFolder(self.folder.name, False)
          else:
!             imap.SelectFolder(self.previous_folder.name, False)
              self.previous_folder = None
          response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
***************
*** 165,169 ****
          # XXX changed, as the message to be deleted will be found first
          # XXX (if they are in the same folder)
!         self.folder.Select(True)
          #response = imap.uid("SEARCH", "TEXT", self.as_string())
          #self._check(response, 'search')
--- 198,202 ----
          # XXX changed, as the message to be deleted will be found first
          # XXX (if they are in the same folder)
!         imap.SelectFolder(self.folder.name, True)
          #response = imap.uid("SEARCH", "TEXT", self.as_string())
          #self._check(response, 'search')
***************
*** 184,187 ****
--- 217,224 ----
          self.name = folder_name
  
+     def __cmp__(self, obj):
+         '''Two folders are equal if their names are equal'''
+         return cmp(self.name, obj.name)
+ 
      def _check(self, response, command):
          if response[0] != "OK":
***************
*** 200,204 ****
          '''Returns uids for all the messages in the folder'''
          # request message range
!         response = Select(self.name, True, True)
          total_messages = response[1][0]
          if total_messages == '0':
--- 237,241 ----
          '''Returns uids for all the messages in the folder'''
          # request message range
!         response = imap.SelectFolder(self.name, True, True)
          total_messages = response[1][0]
          if total_messages == '0':
***************
*** 216,220 ****
          '''Return message matching the given uid'''
          global rfc822_command
!         Select(self.name, True)
          # We really want to use RFC822.PEEK here, as that doesn't effect
          # the status of the message.  Unfortunately, it appears that not
--- 253,257 ----
          '''Return message matching the given uid'''
          global rfc822_command
!         imap.SelectFolder(self.name, True)
          # We really want to use RFC822.PEEK here, as that doesn't effect
          # the status of the message.  Unfortunately, it appears that not
***************
*** 233,240 ****
          
          return msg
! 
!     def Select(self, readOnly):
!         return Select(self.name, readOnly)
! 
      def Train(self, classifier, isSpam):
          '''Train folder as spam/ham'''
--- 270,274 ----
          
          return msg
!    
      def Train(self, classifier, isSpam):
          '''Train folder as spam/ham'''
***************
*** 249,253 ****
                  msg.RememberTrained(None)
  
!             if msg.GetTrained() is not None:
                  classifier.learn(msg.asTokens(), isSpam)
                  num_trained += 1
--- 283,287 ----
                  msg.RememberTrained(None)
  
!             if msg.GetTrained() is None:
                  classifier.learn(msg.asTokens(), isSpam)
                  num_trained += 1
***************
*** 276,285 ****
  class IMAPFilter(object):
      def __init__(self, classifier, debug):
-         global imap
-         imap = imaplib.IMAP4(options.imap_server, options.imap_port)
-         imap.debug = imapDebug
- 
-         self.Login(options.imap_username, options.imap_password)
-         
          self.spam_folder = IMAPFolder(options.imap_spam_folder)
          self.unsure_folder = IMAPFolder(options.imap_unsure_folder)
--- 310,313 ----
***************
*** 320,340 ****
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
! 
!     def Login(self, uid, pw):
!         try:
!             lgn = imap.login(uid, pw)
!         except imaplib.IMAP4.error, e:
!             if str(e) == "permission denied":
!                 print "There was an error logging in to the IMAP server."
!                 print "The userid and/or password may be incorrect."
!                 sys.exit()
!             else:
!                 raise
!     
!     def Logout(self, expunge):
!         # sign off
!         if expunge:
!             imap.expunge()
!         imap.logout()
  
   
--- 348,352 ----
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
!             
  
   
***************
*** 342,346 ****
  
      try:
!         opts, args = getopt.getopt(sys.argv[1:], 'htcvl:e:i:d:D:')
      except getopt.error, msg:
          print >>sys.stderr, str(msg) + '\n\n' + __doc__
--- 354,358 ----
  
      try:
!         opts, args = getopt.getopt(sys.argv[1:], 'htcvpl:e:i:d:D:')
      except getopt.error, msg:
          print >>sys.stderr, str(msg) + '\n\n' + __doc__
***************
*** 354,357 ****
--- 366,370 ----
      imapDebug = 0
      sleepTime = 0
+     promptForPass = 0
  
      for opt, arg in opts:
***************
*** 367,370 ****
--- 380,385 ----
          elif opt == '-t':
              doTrain = True
+         elif opt == '-p':
+             promptForPass = 1
          elif opt == '-c':
              doClassify = True
***************
*** 385,388 ****
--- 400,413 ----
          sys.exit()
  
+     imap = IMAPSession(options.imap_server, options.imap_port, \
+                        imapDebug)
+ 
+     if promptForPass:
+         pwd = getpass()
+     else:
+         pwd = options.imap_password
+ 
+     imap.login(options.imap_username, pwd)
+     
      bdbname = os.path.expanduser(bdbname)
      
***************
*** 415,417 ****
              break
          
!     imap_filter.Logout(doExpunge)
--- 440,442 ----
              break
          
!     imap.logout(doExpunge)



From timstone4 at users.sourceforge.net  Thu Apr 17 13:54:14 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Thu Apr 17 15:54:18 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.15,1.16
Message-ID: <E196FSY-00082O-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv30858

Modified Files:
	imapfilter.py 
Log Message:
1. Corrected an error in the timed loop, that kept an imap session open while
    the filter was sleeping

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.15
retrieving revision 1.16
diff -C2 -d -r1.15 -r1.16
*** imapfilter.py	17 Apr 2003 15:47:20 -0000	1.15
--- imapfilter.py	17 Apr 2003 19:54:10 -0000	1.16
***************
*** 400,406 ****
          sys.exit()
  
-     imap = IMAPSession(options.imap_server, options.imap_port, \
-                        imapDebug)
- 
      if promptForPass:
          pwd = getpass()
--- 400,403 ----
***************
*** 408,413 ****
          pwd = options.imap_password
  
-     imap.login(options.imap_username, pwd)
-     
      bdbname = os.path.expanduser(bdbname)
      
--- 405,408 ----
***************
*** 423,429 ****
--- 418,429 ----
          print "Done."            
                  
+     imap = IMAPSession(options.imap_server, options.imap_port, \
+                        imapDebug)
+ 
      imap_filter = IMAPFilter(classifier, imapDebug)
  
      while True:
+         imap.login(options.imap_username, pwd)
+ 
          if doTrain:
              if options.verbose:
***************
*** 435,442 ****
              imap_filter.Filter()
  
          if sleepTime:
              time.sleep(sleepTime)
          else:
              break
-         
-     imap.logout(doExpunge)
--- 435,442 ----
              imap_filter.Filter()
  
+         imap.logout(doExpunge)
+         
          if sleepTime:
              time.sleep(sleepTime)
          else:
              break



From timstone4 at users.sourceforge.net  Thu Apr 17 15:14:57 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Thu Apr 17 17:15:01 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.16,1.17
Message-ID: <E196Gif-0007jI-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv29664

Modified Files:
	imapfilter.py 
Log Message:
Removed debug from IMAPFilter constructor.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.16
retrieving revision 1.17
diff -C2 -d -r1.16 -r1.17
*** imapfilter.py	17 Apr 2003 19:54:10 -0000	1.16
--- imapfilter.py	17 Apr 2003 21:14:53 -0000	1.17
***************
*** 309,313 ****
              
  class IMAPFilter(object):
!     def __init__(self, classifier, debug):
          self.spam_folder = IMAPFolder(options.imap_spam_folder)
          self.unsure_folder = IMAPFolder(options.imap_unsure_folder)
--- 309,313 ----
              
  class IMAPFilter(object):
!     def __init__(self, classifier):
          self.spam_folder = IMAPFolder(options.imap_spam_folder)
          self.unsure_folder = IMAPFolder(options.imap_unsure_folder)
***************
*** 421,425 ****
                         imapDebug)
  
!     imap_filter = IMAPFilter(classifier, imapDebug)
  
      while True:
--- 421,425 ----
                         imapDebug)
  
!     imap_filter = IMAPFilter(classifier)
  
      while True:



From anadelonbrin at users.sourceforge.net  Thu Apr 17 17:49:43 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 17 19:49:46 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.9,1.10
Message-ID: <E196J8R-00061u-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv23128/spambayes

Modified Files:
	message.py 
Log Message:
Documentation fixes/additions.

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** message.py	13 Apr 2003 12:54:02 -0000	1.9
--- message.py	17 Apr 2003 23:49:41 -0000	1.10
***************
*** 188,192 ****
          # may change, which would really screw this database up
  
!         # an unrecoginzed string here is interpreted as unsure.  Should
          # that condition actually raise an exception instead?
  
--- 188,192 ----
          # may change, which would really screw this database up
  
!         # an unrecognized string here is interpreted as unsure.  Should
          # that condition actually raise an exception instead?
  



From anadelonbrin at users.sourceforge.net  Thu Apr 17 17:49:43 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 17 19:49:48 2003
Subject: [Spambayes-checkins] 
	spambayes FAQ.txt, 1.2, 1.3 imapfilter.py, 1.17, 1.18
Message-ID: <E196J8R-00061l-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv23128

Modified Files:
	FAQ.txt imapfilter.py 
Log Message:
Documentation fixes/additions.

Index: FAQ.txt
===================================================================
RCS file: /cvsroot/spambayes/spambayes/FAQ.txt,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** FAQ.txt	7 Apr 2003 00:53:45 -0000	1.2
--- FAQ.txt	17 Apr 2003 23:49:40 -0000	1.3
***************
*** 40,41 ****
--- 40,53 ----
     you what this file is called (and where it is) down towards the
     bottom of the page.
+ 
+ Q: This software is great!  I want to implement it for all my users.
+    Are there plans to develop a server-side spambayes solution?
+ A: The problem with a server-side solution is that everyone has a
+    different idea of what is spam - that's the whole strength of the
+    bayesian-style filtering concept.  If you are certain that *all*
+    of your users would agree on what is spam and what is not, then
+    this might work for you, but otherwise you really have to have
+    individual databases for each user.  Either way, you should be
+    able to modify spambayes easily enough to fit into your setup.
+    Please let the list know if you do have success in this area, and
+    we'll update this answer.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.17
retrieving revision 1.18
diff -C2 -d -r1.17 -r1.18
*** imapfilter.py	17 Apr 2003 21:14:53 -0000	1.17
--- imapfilter.py	17 Apr 2003 23:49:40 -0000	1.18
***************
*** 36,40 ****
      Train Spam and Ham only, with pickled database
          imapfilter -t -d bayes.db
!  
  To Do:
      o Find a better way to remove old msg from info database when saving
--- 36,58 ----
      Train Spam and Ham only, with pickled database
          imapfilter -t -d bayes.db
! 
! Warnings:
!     o This is very alpha.  The filter is currently being developed and
!       tested.  We do *not* recommend using it on a production system unless
!       you are confident that you can get your mail back if you lose it.  On
!       the other hand, we do recommend that you test it for us and let us
!       know if anything does go wrong.  Once this appears in a release,
!       rather than just cvs, you can feel a *little* <wink> more confident
!       about using it.
!     o By default, the filter does *not* delete, modify or move any of your
!       mail.  Due to quirks in how imap works, new versions of your mail are
!       modified and placed in new folders, but there originals are still
!       available.  These are flagged with the /Deleted flag so that you know
!       that they can be removed.  Your mailer may not show these messages
!       by default, but there should be an option to do so.  *However*, if
!       your mailer automatically purges/expunges (i.e. permantently deletes)
!       mail flagged as such, *or* if you set the imap_expunge option to
!       True, then this mail will be irretrievably lost.
!     
  To Do:
      o Find a better way to remove old msg from info database when saving
***************
*** 62,67 ****
  # Foundation license.
  
! __author__ = "Tony Meyer <ta-meyer@ihug.co.nz>"
! __credits__ = "Tim Stone, All the Spambayes folk."
  
  from __future__ import generators
--- 80,85 ----
  # Foundation license.
  
! __author__ = "Tony Meyer <ta-meyer@ihug.co.nz>, Tim Stone"
! __credits__ = "All the Spambayes folk."
  
  from __future__ import generators
***************
*** 94,108 ****
  rfc822_command = "(RFC822.PEEK)"
  
- # For efficiency, we remember which folder we are currently
- # in, and only send a select command to the IMAP server if
- # we want to *change* folders.  This function is used by
- # both IMAPMessage and IMAPFolder.
- # Occaisionally, we need to force a command, because we
- # are interested in the response.  Things would be much
- # nicer if we cached this information somewhere.
- # XXX If we wanted to be nice and tidy, this really belongs
- # XXX in an IMAPUtilities class, or something like that,
- # XXX or something like this:
- 
  class IMAPSession(imaplib.IMAP4):
      '''A class extending the IMAP4 class, with a few optimizations'''
--- 112,115 ----
***************
*** 111,114 ****
--- 118,125 ----
          imaplib.Debug = debug  # this is a global in the imaplib module
          imaplib.IMAP4.__init__(self, server, port)
+         # For efficiency, we remember which folder we are currently
+         # in, and only send a select command to the IMAP server if
+         # we want to *change* folders.  This function is used by
+         # both IMAPMessage and IMAPFolder.
          self.current_folder = None
          self.current_folder_readonly = None
***************
*** 136,139 ****
--- 147,153 ----
          if self.current_folder != folder or \
             self.current_folder_readonly != readOnly or force:
+             # Occasionally, we need to force a command, because we
+             # are interested in the response.  Things would be much
+             # nicer if we cached this information somewhere.
              response = self.select(folder, readOnly)
              if response[0] != "OK":
***************
*** 348,356 ****
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
-             
  
   
! if __name__ == '__main__':
! 
      try:
          opts, args = getopt.getopt(sys.argv[1:], 'htcvpl:e:i:d:D:')
--- 362,368 ----
          if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
  
   
! def run():
      try:
          opts, args = getopt.getopt(sys.argv[1:], 'htcvpl:e:i:d:D:')
***************
*** 381,385 ****
              doTrain = True
          elif opt == '-p':
!             promptForPass = 1
          elif opt == '-c':
              doClassify = True
--- 393,397 ----
              doTrain = True
          elif opt == '-p':
!             promptForPass = True
          elif opt == '-c':
              doClassify = True
***************
*** 441,442 ****
--- 453,457 ----
          else:
              break
+ 
+ if __name__ == '__main__':
+     run()
\ No newline at end of file



From anadelonbrin at users.sourceforge.net  Thu Apr 17 17:55:31 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 17 19:55:34 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.18,1.19
Message-ID: <E196JE3-0006XL-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv25118

Modified Files:
	imapfilter.py 
Log Message:
Opps.  That last commit broke it.  Here's the fix.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.18
retrieving revision 1.19
diff -C2 -d -r1.18 -r1.19
*** imapfilter.py	17 Apr 2003 23:49:40 -0000	1.18
--- imapfilter.py	17 Apr 2003 23:55:28 -0000	1.19
***************
*** 51,55 ****
        that they can be removed.  Your mailer may not show these messages
        by default, but there should be an option to do so.  *However*, if
!       your mailer automatically purges/expunges (i.e. permantently deletes)
        mail flagged as such, *or* if you set the imap_expunge option to
        True, then this mail will be irretrievably lost.
--- 51,55 ----
        that they can be removed.  Your mailer may not show these messages
        by default, but there should be an option to do so.  *However*, if
!       your mailer automatically purges/expunges (i.e. permanently deletes)
        mail flagged as such, *or* if you set the imap_expunge option to
        True, then this mail will be irretrievably lost.
***************
*** 193,197 ****
          # so what we do is create a new message and delete the old one
          time_stamp = self.extractTime()
!         msgstr = re.sub('([^\r])\n', r'\1\r\n', self.as_string())
          
          response = imap.append(self.folder.name, None,
--- 193,198 ----
          # so what we do is create a new message and delete the old one
          time_stamp = self.extractTime()
!         #msgstr = re.sub('([^\r])\n', r'\1\r\n', self.as_string())
!         msgstr = self.as_string()
          
          response = imap.append(self.folder.name, None,
***************
*** 365,368 ****
--- 366,370 ----
   
  def run():
+     global imap
      try:
          opts, args = getopt.getopt(sys.argv[1:], 'htcvpl:e:i:d:D:')



From anadelonbrin at users.sourceforge.net  Thu Apr 17 18:00:20 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 17 20:00:25 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.19,1.20
Message-ID: <E196JIi-0006vw-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv26622

Modified Files:
	imapfilter.py 
Log Message:
Last commit included testing code.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** imapfilter.py	17 Apr 2003 23:55:28 -0000	1.19
--- imapfilter.py	18 Apr 2003 00:00:13 -0000	1.20
***************
*** 193,198 ****
          # so what we do is create a new message and delete the old one
          time_stamp = self.extractTime()
!         #msgstr = re.sub('([^\r])\n', r'\1\r\n', self.as_string())
!         msgstr = self.as_string()
          
          response = imap.append(self.folder.name, None,
--- 193,197 ----
          # so what we do is create a new message and delete the old one
          time_stamp = self.extractTime()
!         msgstr = re.sub('([^\r])\n', r'\1\r\n', self.as_string())
          
          response = imap.append(self.folder.name, None,



From timstone4 at users.sourceforge.net  Thu Apr 17 18:56:10 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Thu Apr 17 20:56:13 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.20,1.21
Message-ID: <E196KAk-0003DC-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv12325

Modified Files:
	imapfilter.py 
Log Message:
Moved the header repair regex into the message class

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** imapfilter.py	18 Apr 2003 00:00:13 -0000	1.20
--- imapfilter.py	18 Apr 2003 00:56:06 -0000	1.21
***************
*** 192,200 ****
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
-         time_stamp = self.extractTime()
-         msgstr = re.sub('([^\r])\n', r'\1\r\n', self.as_string())
-         
          response = imap.append(self.folder.name, None,
!                                time_stamp, msgstr)
          self._check(response, 'append')
  
--- 192,197 ----
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
          response = imap.append(self.folder.name, None,
!                                self.extractTime(), self.as_string())
          self._check(response, 'append')
  



From timstone4 at users.sourceforge.net  Thu Apr 17 18:56:22 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Thu Apr 17 20:56:26 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.10,1.11
Message-ID: <E196KAw-0003Eb-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv12424

Modified Files:
	message.py 
Log Message:
Moved the header repair regex into the message class

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** message.py	17 Apr 2003 23:49:41 -0000	1.10
--- message.py	18 Apr 2003 00:56:20 -0000	1.11
***************
*** 88,91 ****
--- 88,92 ----
  import sys
  import types
+ import re
  
  import email.Message
***************
*** 169,172 ****
--- 170,180 ----
      def asTokens(self):
          return tokenize(self.as_string())
+ 
+     def as_string(self):
+         # This override is currently needed because of an apparent bug
+         # in the email package, where header lines are not properly
+         # terminated with \r\n
+         return re.sub('([^\r])\n', r'\1\r\n', \
+                       email.Message.Message.as_string(self))
          
      def modified(self):



From anadelonbrin at users.sourceforge.net  Thu Apr 17 20:36:13 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 17 22:36:19 2003
Subject: [Spambayes-checkins] 
	spambayes/spambayes CompatConfigParser.py, NONE,
	1.1 UpdatableConfigParser.py, 1.1, 1.2
Message-ID: <E196LjY-0002Ug-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv9543/spambayes

Modified Files:
	UpdatableConfigParser.py 
Added Files:
	CompatConfigParser.py 
Log Message:
A much improved ConfigParser (from Python 2.3).
Updates UpdatableConfigParser to use this (this module is
still not used by any spambayes module, but stay tuned!)

--- NEW FILE: CompatConfigParser.py ---
from __future__ import generators
# kludge for Python pre 2.3

"""Configuration file parser.

A setup file consists of sections, lead by a "[section]" header,
and followed by "name: value" entries, with continuations and such in
the style of RFC 822.

The option values can contain format strings which refer to other values in
the same section, or values in a special [DEFAULT] section.

For example:

    something: %(dir)s/whatever

would resolve the "%(dir)s" to the value of dir.  All reference
expansions are done late, on demand.

Intrinsic defaults can be specified by passing them into the
ConfigParser constructor as a dictionary.

class:

ConfigParser -- responsible for for parsing a list of
                configuration files, and managing the parsed database.

    methods:

    __init__(defaults=None)
        create the parser and specify a dictionary of intrinsic defaults.  The
        keys must be strings, the values must be appropriate for %()s string
        interpolation.  Note that `__name__' is always an intrinsic default;
        it's value is the section's name.

    sections()
        return all the configuration section names, sans DEFAULT

    has_section(section)
        return whether the given section exists

    has_option(section, option)
        return whether the given option exists in the given section

    options(section)
        return list of configuration options for the named section

    read(filenames)
        read and parse the list of named configuration files, given by
        name.  A single filename is also allowed.  Non-existing files
        are ignored.

    readfp(fp, filename=None)
        read and parse one configuration file, given as a file object.
        The filename defaults to fp.name; it is only used in error
        messages (if fp has no `name' attribute, the string `<???>' is used).

    get(section, option, raw=False, vars=None)
        return a string value for the named option.  All % interpolations are
        expanded in the return values, based on the defaults passed into the
        constructor and the DEFAULT section.  Additional substitutions may be
        provided using the `vars' argument, which must be a dictionary whose
        contents override any pre-existing defaults.

    getint(section, options)
        like get(), but convert value to an integer

    getfloat(section, options)
        like get(), but convert value to a float

    getboolean(section, options)
        like get(), but convert value to a boolean (currently case
        insensitively defined as 0, false, no, off for False, and 1, true,
        yes, on for True).  Returns False or True.

    items(section, raw=False, vars=None)
        return a list of tuples with (name, value) for each option
        in the section.

    remove_section(section)
        remove the given file section and all its options

    remove_option(section, option)
        remove the given option from the given section

    set(section, option, value)
        set the given option

    write(fp)
        write the configuration state in .ini format
"""

import re

__all__ = ["NoSectionError", "DuplicateSectionError", "NoOptionError",
           "InterpolationError", "InterpolationDepthError",
           "InterpolationSyntaxError", "ParsingError",
           "MissingSectionHeaderError", "ConfigParser",
           "DEFAULTSECT", "MAX_INTERPOLATION_DEPTH"]

DEFAULTSECT = "DEFAULT"

MAX_INTERPOLATION_DEPTH = 10



# exception classes
class Error(Exception):
    """Base class for ConfigParser exceptions."""

    def __init__(self, msg=''):
        self.message = msg
        Exception.__init__(self, msg)

    def __repr__(self):
        return self.message

    __str__ = __repr__

class NoSectionError(Error):
    """Raised when no section matches a requested option."""

    def __init__(self, section):
        Error.__init__(self, 'No section: ' + `section`)
        self.section = section

class DuplicateSectionError(Error):
    """Raised when a section is multiply-created."""

    def __init__(self, section):
        Error.__init__(self, "Section %r already exists" % section)
        self.section = section

class NoOptionError(Error):
    """A requested option was not found."""

    def __init__(self, option, section):
        Error.__init__(self, "No option %r in section: %r" %
                       (option, section))
        self.option = option
        self.section = section

class InterpolationError(Error):
    """Base class for interpolation-related exceptions."""

    def __init__(self, option, section, msg):
        Error.__init__(self, msg)
        self.option = option
        self.section = section

class InterpolationMissingOptionError(InterpolationError):
    """A string substitution required a setting which was not available."""

    def __init__(self, option, section, rawval, reference):
        msg = ("Bad value substitution:\n"
               "\tsection: [%s]\n"
               "\toption : %s\n"
               "\tkey    : %s\n"
               "\trawval : %s\n"
               % (section, option, reference, rawval))
        InterpolationError.__init__(self, option, section, msg)
        self.reference = reference

class InterpolationSyntaxError(InterpolationError):
    """Raised when the source text into which substitutions are made
    does not conform to the required syntax."""

class InterpolationDepthError(InterpolationError):
    """Raised when substitutions are nested too deeply."""

    def __init__(self, option, section, rawval):
        msg = ("Value interpolation too deeply recursive:\n"
               "\tsection: [%s]\n"
               "\toption : %s\n"
               "\trawval : %s\n"
               % (section, option, rawval))
        InterpolationError.__init__(self, option, section, msg)

class ParsingError(Error):
    """Raised when a configuration file does not follow legal syntax."""

    def __init__(self, filename):
        Error.__init__(self, 'File contains parsing errors: %s' % filename)
        self.filename = filename
        self.errors = []

    def append(self, lineno, line):
        self.errors.append((lineno, line))
        self.message += '\n\t[line %2d]: %s' % (lineno, line)

class MissingSectionHeaderError(ParsingError):
    """Raised when a key-value pair is found before any section header."""

    def __init__(self, filename, lineno, line):
        Error.__init__(
            self,
            'File contains no section headers.\nfile: %s, line: %d\n%s' %
            (filename, lineno, line))
        self.filename = filename
        self.lineno = lineno
        self.line = line



class RawConfigParser:
    def __init__(self, defaults=None):
        self._sections = {}
        if defaults is None:
            self._defaults = {}
        else:
            self._defaults = defaults

    def defaults(self):
        return self._defaults

    def sections(self):
        """Return a list of section names, excluding [DEFAULT]"""
        # self._sections will never have [DEFAULT] in it
        return self._sections.keys()

    def add_section(self, section):
        """Create a new section in the configuration.

        Raise DuplicateSectionError if a section by the specified name
        already exists.
        """
        if section in self._sections:
            raise DuplicateSectionError(section)
        self._sections[section] = {}

    def has_section(self, section):
        """Indicate whether the named section is present in the configuration.

        The DEFAULT section is not acknowledged.
        """
        return section in self._sections

    def options(self, section):
        """Return a list of option names for the given section name."""
        try:
            opts = self._sections[section].copy()
        except KeyError:
            raise NoSectionError(section)
        opts.update(self._defaults)
        if '__name__' in opts:
            del opts['__name__']
        return opts.keys()

    def read(self, filenames):
        """Read and parse a filename or a list of filenames.

        Files that cannot be opened are silently ignored; this is
        designed so that you can specify a list of potential
        configuration file locations (e.g. current directory, user's
        home directory, systemwide directory), and all existing
        configuration files in the list will be read.  A single
        filename may also be given.
        """
        # we kludge this for Python pre 2.3
        if isinstance(filenames, type("basestring")):
            filenames = [filenames]
        for filename in filenames:
            try:
                fp = open(filename)
            except IOError:
                continue
            self._read(fp, filename)
            fp.close()

    def readfp(self, fp, filename=None):
        """Like read() but the argument must be a file-like object.

        The `fp' argument must have a `readline' method.  Optional
        second argument is the `filename', which if not given, is
        taken from fp.name.  If fp has no `name' attribute, `<???>' is
        used.

        """
        if filename is None:
            try:
                filename = fp.name
            except AttributeError:
                filename = '<???>'
        self._read(fp, filename)

    def get(self, section, option):
        opt = self.optionxform(option)
        if section not in self._sections:
            if section != DEFAULTSECT:
                raise NoSectionError(section)
            if opt in self._defaults:
                return self._defaults[opt]
            else:
                raise NoOptionError(option, section)
        elif opt in self._sections[section]:
            return self._sections[section][opt]
        elif opt in self._defaults:
            return self._defaults[opt]
        else:
            raise NoOptionError(option, section)

    def items(self, section):
        try:
            d2 = self._sections[section]
        except KeyError:
            if section != DEFAULTSECT:
                raise NoSectionError(section)
            d2 = {}
        d = self._defaults.copy()
        d.update(d2)
        if "__name__" in d:
            del d["__name__"]
        return d.items()

    def _get(self, section, conv, option):
        return conv(self.get(section, option))

    def getint(self, section, option):
        return self._get(section, int, option)

    def getfloat(self, section, option):
        return self._get(section, float, option)

    _boolean_states = {'1': True, 'yes': True, 'true': True, 'on': True,
                       '0': False, 'no': False, 'false': False, 'off': False}

    def getboolean(self, section, option):
        v = self.get(section, option)
        if v.lower() not in self._boolean_states:
            raise ValueError, 'Not a boolean: %s' % v
        return self._boolean_states[v.lower()]

    def optionxform(self, optionstr):
        return optionstr.lower()

    def has_option(self, section, option):
        """Check for the existence of a given option in a given section."""
        if not section or section == DEFAULTSECT:
            option = self.optionxform(option)
            return option in self._defaults
        elif section not in self._sections:
            return False
        else:
            option = self.optionxform(option)
            return (option in self._sections[section]
                    or option in self._defaults)

    def set(self, section, option, value):
        """Set an option."""
        if not section or section == DEFAULTSECT:
            sectdict = self._defaults
        else:
            try:
                sectdict = self._sections[section]
            except KeyError:
                raise NoSectionError(section)
        sectdict[self.optionxform(option)] = value

    def write(self, fp):
        """Write an .ini-format representation of the configuration state."""
        if self._defaults:
            fp.write("[%s]\n" % DEFAULTSECT)
            for (key, value) in self._defaults.items():
                fp.write("%s = %s\n" % (key, str(value).replace('\n', '\n\t')))
            fp.write("\n")
        for section in self._sections:
            fp.write("[%s]\n" % section)
            for (key, value) in self._sections[section].items():
                if key != "__name__":
                    fp.write("%s = %s\n" %
                             (key, str(value).replace('\n', '\n\t')))
            fp.write("\n")

    def remove_option(self, section, option):
        """Remove an option."""
        if not section or section == DEFAULTSECT:
            sectdict = self._defaults
        else:
            try:
                sectdict = self._sections[section]
            except KeyError:
                raise NoSectionError(section)
        option = self.optionxform(option)
        existed = option in sectdict
        if existed:
            del sectdict[option]
        return existed

    def remove_section(self, section):
        """Remove a file section."""
        existed = section in self._sections
        if existed:
            del self._sections[section]
        return existed

    #
    # Regular expressions for parsing section headers and options.
    #
    SECTCRE = re.compile(
        r'\['                                 # [
        r'(?P<header>[^]]+)'                  # very permissive!
        r'\]'                                 # ]
        )
    OPTCRE = re.compile(
        r'(?P<option>[^:=\s][^:=]*)'          # very permissive!
        r'\s*(?P<vi>[:=])\s*'                 # any number of space/tab,
                                              # followed by separator
                                              # (either : or =), followed
                                              # by any # space/tab
        r'(?P<value>.*)$'                     # everything up to eol
        )

    def _read(self, fp, fpname):
        """Parse a sectioned setup file.

        The sections in setup file contains a title line at the top,
        indicated by a name in square brackets (`[]'), plus key/value
        options lines, indicated by `name: value' format lines.
        Continuations are represented by an embedded newline then
        leading whitespace.  Blank lines, lines beginning with a '#',
        and just about everything else are ignored.
        """
        cursect = None                            # None, or a dictionary
        optname = None
        lineno = 0
        e = None                                  # None, or an exception
        while True:
            line = fp.readline()
            if not line:
                break
            lineno = lineno + 1
            # comment or blank line?
            if line.strip() == '' or line[0] in '#;':
                continue
            if line.split(None, 1)[0].lower() == 'rem' and line[0] in "rR":
                # no leading whitespace
                continue
            # continuation line?
            if line[0].isspace() and cursect is not None and optname:
                value = line.strip()
                if value:
                    cursect[optname] = "%s\n%s" % (cursect[optname], value)
            # a section header or option header?
            else:
                # is it a section header?
                mo = self.SECTCRE.match(line)
                if mo:
                    sectname = mo.group('header')
                    if sectname in self._sections:
                        cursect = self._sections[sectname]
                    elif sectname == DEFAULTSECT:
                        cursect = self._defaults
                    else:
                        cursect = {'__name__': sectname}
                        self._sections[sectname] = cursect
                    # So sections can't start with a continuation line
                    optname = None
                # no section header in the file?
                elif cursect is None:
                    raise MissingSectionHeaderError(fpname, lineno, `line`)
                # an option line?
                else:
                    mo = self.OPTCRE.match(line)
                    if mo:
                        optname, vi, optval = mo.group('option', 'vi', 'value')
                        if vi in ('=', ':') and ';' in optval:
                            # ';' is a comment delimiter only if it follows
                            # a spacing character
                            pos = optval.find(';')
                            if pos != -1 and optval[pos-1].isspace():
                                optval = optval[:pos]
                        optval = optval.strip()
                        # allow empty values
                        if optval == '""':
                            optval = ''
                        optname = self.optionxform(optname.rstrip())
                        cursect[optname] = optval
                    else:
                        # a non-fatal parsing error occurred.  set up the
                        # exception but keep going. the exception will be
                        # raised at the end of the file and will contain a
                        # list of all bogus lines
                        if not e:
                            e = ParsingError(fpname)
                        e.append(lineno, `line`)
        # if any parsing errors occurred, raise an exception
        if e:
            raise e


class ConfigParser(RawConfigParser):

    def get(self, section, option, raw=False, vars=None):
        """Get an option value for a given section.

        All % interpolations are expanded in the return values, based on the
        defaults passed into the constructor, unless the optional argument
        `raw' is true.  Additional substitutions may be provided using the
        `vars' argument, which must be a dictionary whose contents overrides
        any pre-existing defaults.

        The section DEFAULT is special.
        """
        d = self._defaults.copy()
        try:
            d.update(self._sections[section])
        except KeyError:
            if section != DEFAULTSECT:
                raise NoSectionError(section)
        # Update with the entry specific variables
        if vars is not None:
            d.update(vars)
        option = self.optionxform(option)
        try:
            value = d[option]
        except KeyError:
            raise NoOptionError(option, section)

        if raw:
            return value
        else:
            return self._interpolate(section, option, value, d)

    def items(self, section, raw=False, vars=None):
        """Return a list of tuples with (name, value) for each option
        in the section.

        All % interpolations are expanded in the return values, based on the
        defaults passed into the constructor, unless the optional argument
        `raw' is true.  Additional substitutions may be provided using the
        `vars' argument, which must be a dictionary whose contents overrides
        any pre-existing defaults.

        The section DEFAULT is special.
        """
        d = self._defaults.copy()
        try:
            d.update(self._sections[section])
        except KeyError:
            if section != DEFAULTSECT:
                raise NoSectionError(section)
        # Update with the entry specific variables
        if vars:
            d.update(vars)
        options = d.keys()
        if "__name__" in options:
            options.remove("__name__")
        if raw:
            for option in options:
                yield (option, d[option])
        else:
            for option in options:
                yield (option,
                       self._interpolate(section, option, d[option], d))

    def _interpolate(self, section, option, rawval, vars):
        # do the string interpolation
        value = rawval
        depth = MAX_INTERPOLATION_DEPTH
        while depth:                    # Loop through this until it's done
            depth -= 1
            if value.find("%(") != -1:
                try:
                    value = value % vars
                except KeyError, e:
                    raise InterpolationMissingOptionError(
                        option, section, rawval, e[0])
            else:
                break
        if value.find("%(") != -1:
            raise InterpolationDepthError(option, section, rawval)
        return value


class SafeConfigParser(ConfigParser):

    def _interpolate(self, section, option, rawval, vars):
        # do the string interpolation
        L = []
        self._interpolate_some(option, L, rawval, section, vars, 1)
        return ''.join(L)

    _interpvar_match = re.compile(r"%\(([^)]+)\)s").match

    def _interpolate_some(self, option, accum, rest, section, map, depth):
        if depth > MAX_INTERPOLATION_DEPTH:
            raise InterpolationDepthError(option, section, rest)
        while rest:
            p = rest.find("%")
            if p < 0:
                accum.append(rest)
                return
            if p > 0:
                accum.append(rest[:p])
                rest = rest[p:]
            # p is no longer used
            c = rest[1:2]
            if c == "%":
                accum.append("%")
                rest = rest[2:]
            elif c == "(":
                m = self._interpvar_match(rest)
                if m is None:
                    raise InterpolationSyntaxError(
                        "bad interpolation variable reference", rest)
                var = m.group(1)
                rest = rest[m.end():]
                try:
                    v = map[var]
                except KeyError:
                    raise InterpolationMissingOptionError(
                        option, section, rest, var)
                if "%" in v:
                    self._interpolate_some(option, accum, v,
                                           section, map, depth + 1)
                else:
                    accum.append(v)
            else:
                raise InterpolationSyntaxError(
                    option, section, rest,
                    "'%' must be followed by '%' or '(', found: " + `rest`)

Index: UpdatableConfigParser.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/UpdatableConfigParser.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** UpdatableConfigParser.py	13 Mar 2003 04:29:55 -0000	1.1
--- UpdatableConfigParser.py	18 Apr 2003 02:36:10 -0000	1.2
***************
*** 3,7 ****
  """Configuration file parser with update facility.
  
! Handles configuration files in the exact manner as ConfigParser, but
  has the ability to update the configuration files.  Handles multiple
  files, and does not touch whitespace or comment lines.
--- 3,7 ----
  """Configuration file parser with update facility.
  
! Handles configuration files in the same manner as ConfigParser, but
  has the ability to update the configuration files.  Handles multiple
  files, and does not touch whitespace or comment lines.
***************
*** 117,122 ****
      True, False = 1, 0
  
! from ConfigParser import ConfigParser, ParsingError
! from ConfigParser import DEFAULTSECT, NoSectionError, NoOptionError
  from os import rename, remove, tempnam
  import types
--- 117,122 ----
      True, False = 1, 0
  
! from CompatConfigParser import ConfigParser, ParsingError
! from CompatConfigParser import DEFAULTSECT, NoSectionError, NoOptionError
  from os import rename, remove, tempnam
  import types
***************
*** 145,154 ****
      def __init__(self, defaults=None):
          ConfigParser.__init__(self, defaults)
!         self.__data = {}
!         self.__changed_options = {}
!         self.__pruned = {}
!         # override base class
!         self.__sections = self._ConfigParser__sections
!         self._ConfigParser__read = self.__read
          # configuration defaults
          self.vi = ": "
--- 145,151 ----
      def __init__(self, defaults=None):
          ConfigParser.__init__(self, defaults)
!         self._data = {}
!         self._changed_options = {}
!         self._pruned = {}
          # configuration defaults
          self.vi = ": "
***************
*** 160,167 ****
          existed = ConfigParser.remove_option(self, section, option)
          if existed:
!             for sect, opt in self.__data.keys():
                  if sect == section and opt == option:
!                     del self.__data[(sect, opt)]
!                     self.__pruned[sect] = opt
          return existed
  
--- 157,164 ----
          existed = ConfigParser.remove_option(self, section, option)
          if existed:
!             for sect, opt in self._data.keys():
                  if sect == section and opt == option:
!                     del self._data[(sect, opt)]
!                     self._pruned[sect] = opt
          return existed
  
***************
*** 170,197 ****
          existed = ConfigParser.remove_section(self, section)
          if existed:
!             for sect, opt in self.__data.keys():
                  if sect == section:
!                     del self.__data[(sect, opt)]
!                     self.__pruned[sect] = None
          return existed
  
      def set(self, section, option, value):
          # c.f. ConfigParser.set()
          ConfigParser.set(self, section, option, value)
          if self.record_original_values == False:
!             for file, sect in self.__data.items():
                  if sect == section:
                      sectdict = {}
                      optdict = {}
!                     if self.__changed_options.has_key(file):
!                         sectdict = self.__changed_options[file]
                          if sectdict.has_key(section):
                              optdict = sectdict[section]
                      optdict[option] = value
                      sectdict[section] = optdict
!                     self.__changed_options[file] = sectdict
  
!     def __read(self, fp, fpname):
!         # c.f. ConfigParser.__read()
          cursect = None                            # None, or a dictionary
          optname = None
--- 167,195 ----
          existed = ConfigParser.remove_section(self, section)
          if existed:
!             for sect, opt in self._data.keys():
                  if sect == section:
!                     del self._data[(sect, opt)]
!                     self._pruned[sect] = None
          return existed
  
      def set(self, section, option, value):
          # c.f. ConfigParser.set()
+         print "setting", section, option, value
          ConfigParser.set(self, section, option, value)
          if self.record_original_values == False:
!             for file, sect in self._data.items():
                  if sect == section:
                      sectdict = {}
                      optdict = {}
!                     if self._changed_options.has_key(file):
!                         sectdict = self._changed_options[file]
                          if sectdict.has_key(section):
                              optdict = sectdict[section]
                      optdict[option] = value
                      sectdict[section] = optdict
!                     self._changed_options[file] = sectdict
  
!     def _read(self, fp, fpname):
!         # c.f. ConfigParser._read()
          cursect = None                            # None, or a dictionary
          optname = None
***************
*** 220,230 ****
                  if mo:
                      sectname = mo.group('header')
!                     if sectname in self.__sections:
!                         cursect = self.__sections[sectname]
                      elif sectname == DEFAULTSECT:
!                         cursect = self.__defaults
                      else:
                          cursect = {'__name__': sectname}
!                         self.__sections[sectname] = cursect
                      # So sections can't start with a continuation line
                      optname = None
--- 218,228 ----
                  if mo:
                      sectname = mo.group('header')
!                     if sectname in self._sections:
!                         cursect = self._sections[sectname]
                      elif sectname == DEFAULTSECT:
!                         cursect = self._defaults
                      else:
                          cursect = {'__name__': sectname}
!                         self._sections[sectname] = cursect
                      # So sections can't start with a continuation line
                      optname = None
***************
*** 252,256 ****
                          cursect[optname] = optval
                          sectname = cursect['__name__']
!                         self.__updateData(fpname, sectname, optname, optval)
                      else:
                          # a non-fatal parsing error occurred.  set up the
--- 250,254 ----
                          cursect[optname] = optval
                          sectname = cursect['__name__']
!                         self._updateData(fpname, sectname, optname, optval)
                      else:
                          # a non-fatal parsing error occurred.  set up the
***************
*** 265,306 ****
              raise e
  
!     def __updateData(self, filename, sectname, optname, value):
          if filename == "<???>":
              return
          if self.record_original_values == True:
!             self.__updateDataIncludingOriginalValue(filename,
                                                       sectname,
                                                       optname,
                                                       value)
          else:
!             self.__updateDataNoOriginalValue(filename, sectname,
                                                optname)
  
!     def __updateDataIncludingOriginalValue(self, filename,
                                              sectname, optname, value):
!         if self.__data.has_key((sectname, optname)):
!             existing_files, original = self.__data[(sectname, optname)]
              if filename not in existing_files:
                  existing_files += filename,
!             self.__data[(sectname, optname)] = (existing_files, value)
          else:
!             self.__data[(sectname, optname)] = ((filename,), value)
  
!     def __updateDataNoOriginalValue(self, filename, sectname, optname):
!         if self.__data.has_key((sectname, optname)):
!             existing_data = self.__data[(sectname, optname)]
              if filename not in existing_files:
                  existing_files += filename,
!             self.__data[(sectname, optname)] = existing_files
          else:
!             self.__data[(sectname, optname)] = (filename,)
  
      def changed_options(self):
          """Return any options that have changed since reading or updating."""
          if self.record_original_values == False:
!             return self.__changed_options
          else:            
              files_to_update = {}
!             for sectname, sectdict in self.__sections.items():
                  if sectname == '__name__':
                      continue
--- 263,304 ----
              raise e
  
!     def _updateData(self, filename, sectname, optname, value):
          if filename == "<???>":
              return
          if self.record_original_values == True:
!             self._updateDataIncludingOriginalValue(filename,
                                                       sectname,
                                                       optname,
                                                       value)
          else:
!             self._updateDataNoOriginalValue(filename, sectname,
                                                optname)
  
!     def _updateDataIncludingOriginalValue(self, filename,
                                              sectname, optname, value):
!         if self._data.has_key((sectname, optname)):
!             existing_files, original = self._data[(sectname, optname)]
              if filename not in existing_files:
                  existing_files += filename,
!             self._data[(sectname, optname)] = (existing_files, value)
          else:
!             self._data[(sectname, optname)] = ((filename,), value)
  
!     def _updateDataNoOriginalValue(self, filename, sectname, optname):
!         if self._data.has_key((sectname, optname)):
!             existing_data = self._data[(sectname, optname)]
              if filename not in existing_files:
                  existing_files += filename,
!             self._data[(sectname, optname)] = existing_files
          else:
!             self._data[(sectname, optname)] = (filename,)
  
      def changed_options(self):
          """Return any options that have changed since reading or updating."""
          if self.record_original_values == False:
!             return self._changed_options
          else:            
              files_to_update = {}
!             for sectname, sectdict in self._sections.items():
                  if sectname == '__name__':
                      continue
***************
*** 308,313 ****
                      if optname == '__name__':
                          continue
!                     if self.__data.has_key((sectname, optname)):
!                         source_files, original = self.__data[(sectname, optname)]
                          if optvalue != original:
                              for file in source_files:
--- 306,311 ----
                      if optname == '__name__':
                          continue
!                     if self._data.has_key((sectname, optname)):
!                         source_files, original = self._data[(sectname, optname)]
                          if optvalue != original:
                              for file in source_files:
***************
*** 330,338 ****
      def restore_option(section, option):
          """ restore an option to the value in the source file"""
!         if self.__data.has_key((section, option)):
              if self.record_original_values:
!                 file, original = self.__data[(section, option)]
              else:
!                 file = self.__data[(section, option)]
                  c = ConfigParser()
                  c.read(file)
--- 328,336 ----
      def restore_option(section, option):
          """ restore an option to the value in the source file"""
!         if self._data.has_key((section, option)):
              if self.record_original_values:
!                 file, original = self._data[(section, option)]
              else:
!                 file = self._data[(section, option)]
                  c = ConfigParser()
                  c.read(file)
***************
*** 350,354 ****
          for file, info in files_to_update.items():
              old_cfg = open(file, "r")
!             self.__updateFile(old_cfg, info, prune, add_missing)
              old_cfg.close()
  
--- 348,352 ----
          for file, info in files_to_update.items():
              old_cfg = open(file, "r")
!             self._updateFile(old_cfg, info, prune, add_missing)
              old_cfg.close()
  
***************
*** 357,361 ****
          files_to_update = self.changed_options()
          if files_to_update.has_key(fp.name):
!             self.__updateFile(fp, files_to_update[fp.name],
                                prune, add_missing)
  
--- 355,359 ----
          files_to_update = self.changed_options()
          if files_to_update.has_key(fp.name):
!             self._updateFile(fp, files_to_update[fp.name],
                                prune, add_missing)
  
***************
*** 366,370 ****
              if files_to_update.has_key(file):
                  old_cfg = open(file, "r")
!                 self.__updateFile(old_cfg, files_to_update[file],
                                    prune, add_missing)
                  old_cfg.close()
--- 364,368 ----
              if files_to_update.has_key(file):
                  old_cfg = open(file, "r")
!                 self._updateFile(old_cfg, files_to_update[file],
                                    prune, add_missing)
                  old_cfg.close()
***************
*** 384,388 ****
          c.write(fp)
  
!     def __updateFile(self, old_cfg, info, prune=False, add_missing=False):
          temp_name = tempnam()
          new_cfg = open(temp_name, "w")
--- 382,386 ----
          c.write(fp)
  
!     def _updateFile(self, old_cfg, info, prune=False, add_missing=False):
          temp_name = tempnam()
          new_cfg = open(temp_name, "w")
***************
*** 437,442 ****
                              self.vi = vi
                          optname = optname.rstrip().lower()
!                         if self.__pruned.has_key(current_section):
!                             opt = self.__pruned[current_section]
                              if opt is None or opt == optname:
                                  continue
--- 435,440 ----
                              self.vi = vi
                          optname = optname.rstrip().lower()
!                         if self._pruned.has_key(current_section):
!                             opt = self._pruned[current_section]
                              if opt is None or opt == optname:
                                  continue
***************
*** 445,449 ****
                              new_cfg.write(optname + ' ' + vi + ' ' + \
                                            update_section[optname] + '\n')
!                             self.__updateData(old_cfg.name, current_section, \
                                                 optname, update_section[optname])
                              del update_section[optname]
--- 443,447 ----
                              new_cfg.write(optname + ' ' + vi + ' ' + \
                                            update_section[optname] + '\n')
!                             self._updateData(old_cfg.name, current_section, \
                                                 optname, update_section[optname])
                              del update_section[optname]



From anadelonbrin at users.sourceforge.net  Thu Apr 17 22:46:30 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 00:46:34 2003
Subject: [Spambayes-checkins] spambayes pop3proxy.py,1.69,1.70
Message-ID: <E196Nle-0001Tp-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv5661

Modified Files:
	pop3proxy.py 
Log Message:
Remove ability to use the (long depreciated) pop3proxy_port,
pop3proxy_server_name and pop3proxy_server_port options.

If you are *really* slow at updating, this may break your
configuration!

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.69
retrieving revision 1.70
diff -C2 -d -r1.69 -r1.70
*** pop3proxy.py	4 Apr 2003 01:11:57 -0000	1.69
--- pop3proxy.py	18 Apr 2003 04:46:28 -0000	1.70
***************
*** 1228,1247 ****
              self.logFile = open('_pop3proxy.log', 'wb', 0)
  
-         # Load up the old proxy settings from Options.py / bayescustomize.ini
-         # and give warnings if they're present.   XXX Remove these soon.
          self.servers = []
          self.proxyPorts = []
-         if options.pop3proxy_port != 110 or \
-            options.pop3proxy_server_name != '' or \
-            options.pop3proxy_server_port != 110:
-             print "\n    pop3proxy_port, pop3proxy_server_name and"
-             print "    pop3proxy_server_port are deprecated!  Please use"
-             print "    pop3proxy_servers and pop3proxy_ports instead.\n"
-             self.servers = [(options.pop3proxy_server_name,
-                              options.pop3proxy_server_port)]
-             self.proxyPorts = [options.pop3proxy_port]
  
-         # Load the new proxy settings - these will override the old ones
-         # if both are present.
          if options.pop3proxy_servers:
              for server in options.pop3proxy_servers.split(','):
--- 1228,1234 ----



From anadelonbrin at users.sourceforge.net  Thu Apr 17 23:26:29 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 01:26:38 2003
Subject: [Spambayes-checkins] spambayes pop3proxy.py,1.70,1.71
Message-ID: <E196OOL-0006mQ-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv26028

Modified Files:
	pop3proxy.py 
Log Message:
Remove option to launch smtpproxy and always do this.
If you haven't specified a smtp server then nothing will
happen anyway and this is simpler to explain to people.

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.70
retrieving revision 1.71
diff -C2 -d -r1.70 -r1.71
*** pop3proxy.py	18 Apr 2003 04:46:28 -0000	1.70
--- pop3proxy.py	18 Apr 2003 05:26:26 -0000	1.71
***************
*** 23,27 ****
                        (default 8880; Browse http://localhost:8880/)
              -b      : Launch a web browser showing the user interface.
-             -s      : Start a SMTPProxy server for training use.
  
          All command line arguments and switches take their default
--- 23,26 ----
***************
*** 1653,1657 ****
  
      runSelfTest = False
-     launchSMTPProxy = False
      for opt, arg in opts:
          if opt == '-h':
--- 1652,1655 ----
***************
*** 1663,1668 ****
          elif opt == '-b':
              state.launchUI = True
-         elif opt == '-s':
-             launchSMTPProxy = True
          elif opt == '-d':   # dbm file
              state.useDB = True
--- 1661,1664 ----
***************
*** 1686,1694 ****
      state.createWorkers()
  
!     if launchSMTPProxy:
!         from smtpproxy import LoadServerInfo, CreateProxies
!         servers, proxyPorts = LoadServerInfo()
!         CreateProxies(servers, proxyPorts, state)
!         LoadServerInfo()
      
      if runSelfTest:
--- 1682,1693 ----
      state.createWorkers()
  
!     # Launch any SMTP proxies.  This was once an option, but
!     # is now always carried out - if the user hasn't specified any
!     # SMTP proxy information in their configuration, then nothing
!     # will happen anyway, and this is much clearer for documentation.
!     from smtpproxy import LoadServerInfo, CreateProxies
!     servers, proxyPorts = LoadServerInfo()
!     CreateProxies(servers, proxyPorts, state)
!     LoadServerInfo()
      
      if runSelfTest:



From anadelonbrin at users.sourceforge.net  Thu Apr 17 23:52:16 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 01:52:22 2003
Subject: [Spambayes-checkins] spambayes smtpproxy.py,1.4,1.5
Message-ID: <E196OnI-0000Oo-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv1483

Modified Files:
	smtpproxy.py 
Log Message:
Fix bug that would cause mail send in the same session as
training mail to not be sent.

Index: smtpproxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/smtpproxy.py,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -d -r1.4 -r1.5
*** smtpproxy.py	12 Mar 2003 03:30:01 -0000	1.4
--- smtpproxy.py	18 Apr 2003 05:52:13 -0000	1.5
***************
*** 7,14 ****
  server, and configure your email client to send mail through the proxy
  then forward/bounce any incorrectly classified messages to the ham/spam
! training address. To use, run pop3proxy.py with the switch '-s'.
! 
! All options are found in the [pop3proxy] and [smtpproxy] sections of the
! .ini file.
  """
  
--- 7,13 ----
  server, and configure your email client to send mail through the proxy
  then forward/bounce any incorrectly classified messages to the ham/spam
! training address. To use, run pop3proxy and enter appropriate values for
! the smtp proxy options.  All options are found in the [pop3proxy] and
! [smtpproxy] sections of the configuration file.
  """
  
***************
*** 41,44 ****
--- 40,53 ----
     it to be sent every time, or as a x days/hours digest.
     
+  o Clean up the above documentation ;)
+  
+  o We could change things so that if this script is executed, then
+    the proxy operates independantly of pop3proxy.  The options would be
+    the same, but instead of extracting an id and using that to find a
+    message in pop3proxy's cache, it trains on the text of whatever is
+    sent to it.  This (hopefully) will allow use by mailers like procmail.
+ 
+  o Suggestions?
+ 
  Testing:
  
***************
*** 304,310 ****
--- 313,321 ----
          if self.train_as_spam:
              self.train(data, True)
+             self.train_as_spam = False
              return ""
          elif self.train_as_ham:
              self.train(data, False)
+             self.train_as_ham = False
              return ""
          return data



From anadelonbrin at users.sourceforge.net  Fri Apr 18 00:20:42 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 02:20:46 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.26,1.27
Message-ID: <E196PEo-00063u-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv23204/spambayes

Modified Files:
	Options.py 
Log Message:
Major change in how options work.  No longer do we use the
ugly getattr hack, and no longer do we ignore section names.
We also have access to lots more information about options,
including some information about valid values.

At the moment this includes code to make it 100% backwards
compatible - this will go sooner or later.  I will gradually commit
all the modules that need changing; for the moment nothing
changes.

Note that some options are renamed (all those that included the
section name in the option name have had it removed).

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** Options.py	8 Apr 2003 07:37:29 -0000	1.26
--- Options.py	18 Apr 2003 06:20:38 -0000	1.27
***************
*** 1,6 ****
! # Options.options is a globally shared options object.
  
! # XXX As this code is, option names must be unique across ini sections,
! # XXX and must not conflict with OptionsClass method names.
  
  import sys, os
--- 1,81 ----
! """Options
  
! Classes:
[...1698 lines suppressed...]
+ 
  
  # `optionsPathname` is the pathname of the last ini file in the list.
***************
*** 620,627 ****
  
  options = OptionsClass()
! 
! d = StringIO.StringIO(defaults)
! options.mergefilelike(d)
! del d
  
  alternate = None
--- 1257,1262 ----
  
  options = OptionsClass()
! options.load_defaults()
! options.display()
  
  alternate = None



From anadelonbrin at users.sourceforge.net  Fri Apr 18 00:52:03 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 02:52:07 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.27,1.28
Message-ID: <E196Pj8-0004LX-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv16550/spambayes

Modified Files:
	Options.py 
Log Message:
Quick bug fixes before anyone actually tries this out <wink>

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.27
retrieving revision 1.28
diff -C2 -d -r1.27 -r1.28
*** Options.py	18 Apr 2003 06:20:38 -0000	1.27
--- Options.py	18 Apr 2003 06:51:59 -0000	1.28
***************
*** 333,340 ****
  "Best cutoff false positive weight", 10.00, "", "[\d]+[\.]?[\d]*",
   False, True),
! ("TestDriver", "best_cutoff_fn_weight",
  "Best cutoff false negative weight", 1.00, "", "[\d]+[\.]?[\d]*",
   False, True),
! ("TestDriver", "best_cutoff_unsure_weight",
  "Best cutoff unsure weight", 0.20, "", "[\d]+[\.]?[\d]*",
   False, True),
--- 333,340 ----
  "Best cutoff false positive weight", 10.00, "", "[\d]+[\.]?[\d]*",
   False, True),
! ("best_cutoff_fn_weight",
  "Best cutoff false negative weight", 1.00, "", "[\d]+[\.]?[\d]*",
   False, True),
! ("best_cutoff_unsure_weight",
  "Best cutoff unsure weight", 0.20, "", "[\d]+[\.]?[\d]*",
   False, True),
***************
*** 1116,1123 ****
                  # *** This will vanish soon, so do not make use of it in
                  #     new code ***
                  old_name = section[0:1].lower() + section[1:] + "_" + opt[0]
!                 setattr(options, old_name, opt[2])
                  old_name = opt[0]
!                 setattr(options, old_name, opt[2])
  
      # not necessary, but convenient shortcuts to self._options
--- 1116,1126 ----
                  # *** This will vanish soon, so do not make use of it in
                  #     new code ***
+                 garbage, converter = all_options[section][opt[0]]
+                 if converter is not None:
+                     value = converter(opt[2])
                  old_name = section[0:1].lower() + section[1:] + "_" + opt[0]
!                 setattr(options, old_name, value)
                  old_name = opt[0]
!                 setattr(options, old_name, value)
  
      # not necessary, but convenient shortcuts to self._options
***************
*** 1216,1220 ****
                      garbage, new_name = option.split('_', 1)
                      if self._options.has_key((section, new_name)):
!                         value = c.get(section, option)
                          setattr(options, option, value) # ugly!
                          option = new_name
--- 1219,1226 ----
                      garbage, new_name = option.split('_', 1)
                      if self._options.has_key((section, new_name)):
!                         fetcher, converter = goodopts[new_name]
!                         value = getattr(c, fetcher)(section, option)
!                         if converter is not None:
!                             value = converter(value)
                          setattr(options, option, value) # ugly!
                          option = new_name



From anadelonbrin at users.sourceforge.net  Fri Apr 18 00:57:03 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 02:57:10 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.21,1.22
Message-ID: <E196Pnz-0005lu-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv22066

Modified Files:
	imapfilter.py 
Log Message:
Update to use new options style.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** imapfilter.py	18 Apr 2003 00:56:06 -0000	1.21
--- imapfilter.py	18 Apr 2003 06:56:59 -0000	1.22
***************
*** 21,25 ****
              -v          : verbose mode
              -p          : security option to prompt for imap password,
!                           rather than look in options.imap_password
              -e y/n      : expunge/purge messages on exit (y) or not (n)
              -i debuglvl : a somewhat mysterious imaplib debugging level
--- 21,25 ----
              -v          : verbose mode
              -p          : security option to prompt for imap password,
!                           rather than look in options["imap", "password"]
              -e y/n      : expunge/purge messages on exit (y) or not (n)
              -i debuglvl : a somewhat mysterious imaplib debugging level
***************
*** 73,76 ****
--- 73,79 ----
        any new messages to process (with the RECENT command).  The period
        could be an option.  This is partially done with the -l operand.
+     o Mail flagged with /Deleted shouldn't be filtered.
+     o The flags should be copied along with the message (especially
+       the /Seen flag, but all of them, really).
      o Suggestions?
  """
***************
*** 309,316 ****
  
                  cls = msg.GetClassification()
!                 if cls == options.header_ham_string:
                      # we leave ham alone
                      pass
!                 elif cls == options.header_spam_string:
                      msg.MoveTo(spamfolder)
                  else:
--- 312,319 ----
  
                  cls = msg.GetClassification()
!                 if cls == options["Hammie", "header_ham_string"]:
                      # we leave ham alone
                      pass
!                 elif cls == options["Hammie", "header_spam_string"]:
                      msg.MoveTo(spamfolder)
                  else:
***************
*** 321,341 ****
  class IMAPFilter(object):
      def __init__(self, classifier):
!         self.spam_folder = IMAPFolder(options.imap_spam_folder)
!         self.unsure_folder = IMAPFolder(options.imap_unsure_folder)
  
          self.classifier = classifier
          
      def Train(self):
!         if options.verbose:
              t = time.time()
  
!         if options.imap_ham_train_folders != "":
!             ham_training_folders = options.imap_ham_train_folders.split()
              for fol in ham_training_folders:
                  folder = IMAPFolder(fol)
                  num_ham_trained = folder.Train(self.classifier, False)
  
!         if options.imap_spam_train_folders != "":
!             spam_training_folders = options.imap_spam_train_folders.split()
              for fol in spam_training_folders:
                  folder = IMAPFolder(fol)
--- 324,346 ----
  class IMAPFilter(object):
      def __init__(self, classifier):
!         self.spam_folder = IMAPFolder(options["imap", "spam_folder"])
!         self.unsure_folder = IMAPFolder(options["imap", "unsure_folder"])
  
          self.classifier = classifier
          
      def Train(self):
!         if options["globals", "verbose"]:
              t = time.time()
  
!         if options["imap", "ham_train_folders"] != "":
!             ham_training_folders = \
!                                  options["imap", "ham_train_folders"].split()
              for fol in ham_training_folders:
                  folder = IMAPFolder(fol)
                  num_ham_trained = folder.Train(self.classifier, False)
  
!         if options["imap", "spam_train_folders"] != "":
!             spam_training_folders = \
!                                   options["imap", "spam_train_folders"].split()
              for fol in spam_training_folders:
                  folder = IMAPFolder(fol)
***************
*** 345,361 ****
              self.classifier.store()
          
!         if options.verbose:
              print "Training took %s seconds, %s messages were trained" \
                    % (time.time() - t, num_ham_trained + num_spam_trained)
  
      def Filter(self):
!         if options.verbose:
              t = time.time()
              
!         for filter_folder in options.imap_filter_folders.split():
              folder = IMAPFolder(filter_folder, False)
              folder.Filter(self.classifier, self.spam_folder, self.unsure_folder)
   
!         if options.verbose:
              print "Filtering took", time.time() - t, "seconds."
  
--- 350,366 ----
              self.classifier.store()
          
!         if options["globals", "verbose"]:
              print "Training took %s seconds, %s messages were trained" \
                    % (time.time() - t, num_ham_trained + num_spam_trained)
  
      def Filter(self):
!         if options["globals", "verbose"]:
              t = time.time()
              
!         for filter_folder in options["imap", "filter_folders"].split():
              folder = IMAPFolder(filter_folder, False)
              folder.Filter(self.classifier, self.spam_folder, self.unsure_folder)
   
!         if options["globals", "verbose"]:
              print "Filtering took", time.time() - t, "seconds."
  
***************
*** 369,377 ****
          sys.exit()
  
!     bdbname = options.pop3proxy_persistent_storage_file
!     useDBM = options.pop3proxy_persistent_use_database
      doTrain = False
      doClassify = False
!     doExpunge = options.imap_expunge
      imapDebug = 0
      sleepTime = 0
--- 374,382 ----
          sys.exit()
  
!     bdbname = options["pop3proxy", "persistent_storage_file"]
!     useDBM = options["pop3proxy", "persistent_use_database"]
      doTrain = False
      doClassify = False
!     doExpunge = options["imap", "expunge"]
      imapDebug = 0
      sleepTime = 0
***************
*** 395,399 ****
              doClassify = True
          elif opt == '-v':
!             options.verbose = True
          elif opt == '-e':
              if arg == 'y':
--- 400,404 ----
              doClassify = True
          elif opt == '-v':
!             options["globals", "verbose"] = True
          elif opt == '-e':
              if arg == 'y':
***************
*** 413,421 ****
          pwd = getpass()
      else:
!         pwd = options.imap_password
  
      bdbname = os.path.expanduser(bdbname)
      
!     if options.verbose:
          print "Loading database %s..." % (bdbname),
      
--- 418,426 ----
          pwd = getpass()
      else:
!         pwd = options["imap", "password"]
  
      bdbname = os.path.expanduser(bdbname)
      
!     if options["globals", "verbose"]:
          print "Loading database %s..." % (bdbname),
      
***************
*** 425,445 ****
          classifier = storage.PickledClassifier(bdbname)
  
!     if options.verbose:
          print "Done."            
                  
!     imap = IMAPSession(options.imap_server, options.imap_port, \
!                        imapDebug)
  
      imap_filter = IMAPFilter(classifier)
  
      while True:
!         imap.login(options.imap_username, pwd)
  
          if doTrain:
!             if options.verbose:
                  print "Training"
              imap_filter.Train()
          if doClassify:
!             if options.verbose:
                  print "Classifying"
              imap_filter.Filter()
--- 430,450 ----
          classifier = storage.PickledClassifier(bdbname)
  
!     if options["globals", "verbose"]:
          print "Done."            
                  
!     imap = IMAPSession(options["imap", "server"],
!                        options["imap", "port"], imapDebug)
  
      imap_filter = IMAPFilter(classifier)
  
      while True:
!         imap.login(options["imap", "username"], pwd)
  
          if doTrain:
!             if options["globals", "verbose"]:
                  print "Training"
              imap_filter.Train()
          if doClassify:
!             if options["globals", "verbose"]:
                  print "Classifying"
              imap_filter.Filter()



From anadelonbrin at users.sourceforge.net  Fri Apr 18 03:24:32 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 05:24:39 2003
Subject: [Spambayes-checkins] spambayes/spambayes ImapUI.py, NONE,
	1.1 ProxyUI.py, NONE, 1.1 UserInterface.py, NONE,
	1.1 tokenizer.py, 1.7, 1.8
Message-ID: <E196S6i-0004oM-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv18385/spambayes

Modified Files:
	tokenizer.py 
Added Files:
	ImapUI.py ProxyUI.py UserInterface.py 
Log Message:
More modular user interface files (code mostly ripped out
of pop3proxy.py, as the comments indicate it will be).

--- NEW FILE: ImapUI.py ---
"""IMAPFilter Web Interface

Classes:
    IMAPUserInterface - Interface class for the IMAP filter

Abstract:

This module implements a browser based Spambayes user interface for the
IMAP filter.  Users may use it to interface with the filter - it is
expected that this will primarily be for configuration, although users
may also wish to look up words in the database, or classify a message.

The following functions are currently included:
[From the base class UserInterface]
  onClassify - classify a given message
  onWordquery - query a word from the database
  onTrain - train a message or mbox
  onSave - save the database and possibly shutdown
[Here]
  onHome - a home page with various options

To do:
 o There is a function to get a list of all the folders available on
   the server, but nothing is done with this.  Obviously what we would
   like is to present a page where the user selects (checkboxes) the
   folders that s/he wishes to filter, the folders s/he wishes to use
   as train-as-ham and train-as-spam, and (radio buttons) the folders
   to move suspected spam and unsures into.  I think this should be
   a separate page from the standard config as it's already going to
   be really big if there are lots of folders to choose from.
   An alternative design would be to have a single list of the folders
   and five columns - three of checkboxes (filter, train-as-spam and
   train-as-ham) and two of radio buttons (spam folder and ham folder).
   I think this might be more confusing, though.
 o This could have a neat review page, like pop3proxy, built up by
   asking the IMAP server appropriate questions.  I don't know whether
   this is needed, however.  This would then allow viewing a message,
   showing the clues for it, and so on.  Finding a message (via the
   spambayes id) could also be done.
 o Suggestions?
"""

# This module is part of the spambayes project, which is Copyright 2002-3
# The Python Software Foundation and is covered by the Python Software
# Foundation license.

__author__ = "Tony Meyer <ta-meyer@ihug.co.nz>, Tim Stone"
__credits__ = "All the Spambayes folk."

try:
    True, False
except NameError:
    # Maintain compatibility with Python 2.2
    True, False = 1, 0

import re

import UserInterface
from Options import options

global classifier

# This control dictionary maps http request parameters and template fields
# to ConfigParser sections and options.  The key matches both the input
# field that corresponds to a section/option, and also the HTML template
# variable that is used to display the value of that section/option.
parm_map = \
   {'hamcutoff':    ('Categorization',  'ham_cutoff'),
    'spamcutoff':   ('Categorization',  'spam_cutoff'),
    'dbname':       ('pop3proxy',       'persistent_storage_file'),
    'imapserver':   ('imap',            'server'),
    'imapport':     ('imap',            'port'),
    'imapusername': ('imap',            'username'),
    'imappassword': ('imap',            'password'),
    'p3notateto':   ('pop3proxy',       'notate_to'),
    'p3notatesub':  ('pop3proxy',       'notate_subject'),
    'p3addid':      ('pop3proxy',       'add_mailid_to'),
    'p3stripid':    ('pop3proxy',       'strip_incoming_mailids'),
    'p3prob':       ('pop3proxy',       'include_prob'),
    'p3thermostat': ('pop3proxy',       'include_thermostat'),
    'p3evidence':   ('pop3proxy',       'include_evidence'),
   }

display = ('IMAP Options', 'imapserver', 'imapport', 'imapusername',
           # to display, or not to display; that is the question
           # if we show this here, it's in plain text for everyone to
           # see (and worse - if we don't restrict connections to
           # localhost, it's available for the world to see)
           # on the other hand, we have to be able to enter it somehow...
           'imappassword',
           'Header Options', 'p3notateto', 'p3notatesub', 
           'p3prob', 'p3thermostat', 'p3evidence', 
           'p3addid', 'p3stripid',
           'Statistics Options', 'dbname', 'hamcutoff', 'spamcutoff')

class IMAPUserInterface(UserInterface.UserInterface):
    """Serves the HTML user interface for the proxies."""

    def __init__(self, cls, imap):
        global classifier
        UserInterface.UserInterface.__init__(self, cls, parm_map, display)
        classifier = cls
        self.imap = imap

    def onHome(self):
        """Serve up the homepage."""
        stateDict = classifier.__dict__.copy()
        stateDict.update(classifier.__dict__)
        statusTable = self.html.statusTable.clone()
        del statusTable.proxyDetails
        content = (self._buildBox('Status and Configuration',
                                  'status.gif', statusTable % stateDict)+
                   self._buildTrainBox() +
                   self._buildClassifyBox() +
                   self._buildBox('Word query', 'query.gif',
                                  self.html.wordQuery)
                   )
        self._writePreamble("Home")
        self.write(content)
        self._writePostamble()

    def reReadOptions(self):
        """Called by the config page when the user saves some new options, or
        restores the defaults."""
        # Reload the options.
        global classifier
        classifier.store()
        import Options
        reload(Options)
        global options
        from Options import options

    def _folder_list(self):
        '''Return a alphabetical list of all folders available
        on the server'''
        response = imap.list()
        if response[0] != "OK" return ()
        all_folders = response[1]
        folders = []
        for fol in all_folders:
            r = re.compile(r"\(([\w\\ ]*)\) ")
            m = r.search(fol)
            name_attributes = fol[:m.end()-1]
            folder_delimiter = fol[m.end()+1:m.end()+2]
            folders.append(fol[m.end()+5:-1])
        folders.sort()
        return folders

--- NEW FILE: ProxyUI.py ---
"""POP3Proxy and SMTPProxy Web Interface

Classes:
    ProxyUserInterface - Interface class for pop3proxy and smtpproxy

Abstract:

This module implements a browser based Spambayes user interface for the
POP3 proxy and SMTP proxy.  Users may use it to interface with the
proxies.

The following functions are currently included:
[From the base class UserInterface]
  onClassify - classify a given message
  onWordquery - query a word from the database
  onTrain - train a message or mbox
  onSave - save the database and possibly shutdown
[Here]
  onHome - a home page with various options
  onUpload - upload a message for later training (used by proxytee.py)
  onReview - show messages in corpii
  onView - view a message from one of the corpii
  onShowclues - show clues for a message

To do:

Web training interface:

 o Review already-trained messages, and purge them.
 o Put in a link to view a message (plain text, html, multipart...?)
   Include a Reply link that launches the registered email client, eg.
   mailto:tim@fourstonesExpressions.com?subject=Re:%20pop3proxy&body=Hi%21%0D
 o [Francois Granger] Show the raw spambrob number close to the buttons
   (this would mean using the extra X-Hammie header by default).
 o Add Today and Refresh buttons on the Review page.

User interface improvements:

 o Can it cleanly dynamically update its status display while having a POP3
   conversation?  Hammering reload sucks.

 o Suggestions?
"""

# This module is part of the spambayes project, which is Copyright 2002
# The Python Software Foundation and is covered by the Python Software
# Foundation license.

# This module was once part of pop3proxy.py; if you are looking through
# the history of the file, you may need to go back there.

__author__ = "Richie Hindle <richie@entrian.com>"
__credits__ = "Tim Peters, Neale Pickett, Tim Stone, all the Spambayes folk."

try:
    True, False
except NameError:
    # Maintain compatibility with Python 2.2
    True, False = 1, 0

import re
import time
import bisect

import tokenizer
import UserInterface
from Options import options

global state

# This control dictionary maps http request parameters and template fields
# to ConfigParser sections and options.  The key matches both the input
# field that corresponds to a section/option, and also the HTML template
# variable that is used to display the value of that section/option.
parm_ini_map = \
   {'hamcutoff':    ('Categorization',  'ham_cutoff'),
    'spamcutoff':   ('Categorization',  'spam_cutoff'),
    'dbname':       ('pop3proxy',       'persistent_storage_file'),
    'p3servers':    ('pop3proxy',       'servers'),
    'p3ports':      ('pop3proxy',       'ports'),
    'p3notateto':   ('pop3proxy',       'notate_to'),
    'p3notatesub':  ('pop3proxy',       'notate_subject'),
    'p3cachemsg':   ('pop3proxy',       'cache_messages'),
    'p3addid':      ('pop3proxy',       'add_mailid_to'),
    'p3stripid':    ('pop3proxy',       'strip_incoming_mailids'),
    'p3prob':       ('pop3proxy',       'include_prob'),
    'p3thermostat': ('pop3proxy',       'include_thermostat'),
    'p3evidence':   ('pop3proxy',       'include_evidence'),
    'smtpservers':  ('smtpproxy',       'servers'),
    'smtpports':    ('smtpproxy',       'ports'),
    'smtpham':      ('smtpproxy',       'ham_address'),
    'smtpspam':     ('smtpproxy',       'spam_address'),
   }

display = ('POP3 Proxy Options', 'p3servers', 'p3ports', 'p3cachemsg',
           'Header Options', 'p3notateto', 'p3notatesub', 
           'p3prob', 'p3thermostat', 'p3evidence', 
           'p3addid', 'p3stripid',
           'SMTP Proxy Options', 'smtpservers', 'smtpports', 'smtpham',
           'smtpspam',
           'Statistics Options', 'dbname', 'hamcutoff', 'spamcutoff')


class ProxyUserInterface(UserInterface.UserInterface):
    """Serves the HTML user interface for the proxies."""

    def __init__(self, proxy_state, state_recreator):
        global state
        UserInterface.UserInterface.__init__(self, proxy_state.bayes,
                                             parm_ini_map, display)
        state = proxy_state
        self.state_recreator = state_recreator # ugly

    def onHome(self):
        """Serve up the homepage."""
        stateDict = state.__dict__.copy()
        stateDict.update(state.bayes.__dict__)
        statusTable = self.html.statusTable.clone()
        if not state.servers:
            statusTable.proxyDetails = "No POP3 proxies running."
        content = (self._buildBox('Status and Configuration',
                                  'status.gif', statusTable % stateDict)+
                   self._buildBox('Train on proxied messages',
                                  'train.gif', self.html.reviewText) +
                   self._buildTrainBox() +
                   self._buildClassifyBox() +
                   self._buildBox('Word query', 'query.gif',
                                  self.html.wordQuery) +
                   self._buildBox('Find message', 'query.gif',
                                  self.html.findMessage)
                   )
        self._writePreamble("Home")
        self.write(content)
        self._writePostamble()

    def onUpload(self, file):
        """Save a message for later training - used by Skip's proxytee.py."""
        # Convert platform-specific line endings into unix-style.
        file = file.replace('\r\n', '\n').replace('\r', '\n')

        # Get a message list from the upload and write it into the cache.
        messages = self._convertUploadToMessageList(file)
        for m in messages:
            messageName = state.getNewMessageName()
            message = state.unknownCorpus.makeMessage(messageName)
            message.setSubstance(m)
            state.unknownCorpus.addMessage(message)

        # Return a link Home.
        self.write("<p>OK. Return <a href='home'>Home</a>.</p>")

    def _keyToTimestamp(self, key):
        """Given a message key (as seen in a Corpus), returns the timestamp
        for that message.  This is the time that the message was received,
        not the Date header."""
        return long(key[:10])

    def _getTimeRange(self, timestamp):
        """Given a unix timestamp, returns a 3-tuple: the start timestamp
        of the given day, the end timestamp of the given day, and the
        formatted date of the given day."""
        # This probably works on Summertime-shift days; time will tell.  8-)
        this = time.localtime(timestamp)
        start = (this[0], this[1], this[2], 0, 0, 0, this[6], this[7], this[8])
        end = time.localtime(time.mktime(start) + 36*60*60)
        end = (end[0], end[1], end[2], 0, 0, 0, end[6], end[7], end[8])
        date = time.strftime("%A, %B %d, %Y", start)
        return time.mktime(start), time.mktime(end), date

    def _buildReviewKeys(self, timestamp):
        """Builds an ordered list of untrained message keys, ready for output
        in the Review list.  Returns a 5-tuple: the keys, the formatted date
        for the list (eg. "Friday, November 15, 2002"), the start of the prior
        page or zero if there isn't one, likewise the start of the given page,
        and likewise the start of the next page."""
        # Fetch all the message keys and sort them into timestamp order.
        allKeys = state.unknownCorpus.keys()
        allKeys.sort()

        # The default start timestamp is derived from the most recent message,
        # or the system time if there are no messages (not that it gets used).
        if not timestamp:
            if allKeys:
                timestamp = self._keyToTimestamp(allKeys[-1])
            else:
                timestamp = time.time()
        start, end, date = self._getTimeRange(timestamp)

        # Find the subset of the keys within this range.
        startKeyIndex = bisect.bisect(allKeys, "%d" % long(start))
        endKeyIndex = bisect.bisect(allKeys, "%d" % long(end))
        keys = allKeys[startKeyIndex:endKeyIndex]
        keys.reverse()

        # What timestamps to use for the prior and next days?  If there any
        # messages before/after this day's range, use the timestamps of those
        # messages - this will skip empty days.
        prior = end = 0
        if startKeyIndex != 0:
            prior = self._keyToTimestamp(allKeys[startKeyIndex-1])
        if endKeyIndex != len(allKeys):
            end = self._keyToTimestamp(allKeys[endKeyIndex])

        # Return the keys and their date.
        return keys, date, prior, start, end

    def _appendMessages(self, table, keyedMessageInfo, label):
        """Appends the rows of a table of messages to 'table'."""
        stripe = 0
        for key, messageInfo in keyedMessageInfo:
            row = self.html.reviewRow.clone()
            if label == 'Spam':
                row.spam.checked = 1
            elif label == 'Ham':
                row.ham.checked = 1
            else:
                row.defer.checked = 1
            row.subject = messageInfo.subjectHeader
            row.subject.title = messageInfo.bodySummary
            row.subject.href="view?key=%s&corpus=%s" % (key, label)
            row.from_ = messageInfo.fromHeader
            subj = cgi.escape(messageInfo.subjectHeader)
            row.classify.href="showclues?key=%s&subject=%s" % (key, subj)
            setattr(row, 'class', ['stripe_on', 'stripe_off'][stripe]) # Grr!
            row = str(row).replace('TYPE', label).replace('KEY', key)
            table += row
            stripe = stripe ^ 1

    def onReview(self, **params):
        """Present a list of message for (re)training."""
        # Train/discard sumbitted messages.
        self._writePreamble("Review")
        id = ''
        numTrained = 0
        numDeferred = 0
        for key, value in params.items():
            if key.startswith('classify:'):
                id = key.split(':')[2]
                if value == 'spam':
                    targetCorpus = state.spamCorpus
                elif value == 'ham':
                    targetCorpus = state.hamCorpus
                elif value == 'discard':
                    targetCorpus = None
                    try:
                        state.unknownCorpus.removeMessage(state.unknownCorpus[id])
                    except KeyError:
                        pass  # Must be a reload.
                else: # defer
                    targetCorpus = None
                    numDeferred += 1
                if targetCorpus:
                    sourceCorpus = None
                    if state.unknownCorpus.get(id) is not None:
                        sourceCorpus = state.unknownCorpus
                    elif state.hamCorpus.get(id) is not None:
                        sourceCorpus = state.hamCorpus
                    elif state.spamCorpus.get(id) is not None:
                        sourceCorpus = state.spamCorpus
                    if sourceCorpus is not None:
                        try:
                            targetCorpus.takeMessage(id, sourceCorpus)
                            if numTrained == 0:
                                self.write("<p><b>Training... ")
                                self.flush()
                            numTrained += 1
                        except KeyError:
                            pass  # Must be a reload.

        # Report on any training, and save the database if there was any.
        if numTrained > 0:
            plural = ''
            if numTrained != 1:
                plural = 's'
            self.write("Trained on %d message%s. " % (numTrained, plural))
            self._doSave()
            self.write("<br>&nbsp;")

        title = ""
        keys = []
        sourceCorpus = state.unknownCorpus
        # If any messages were deferred, show the same page again.
        if numDeferred > 0:
            start = self._keyToTimestamp(id)

        # Else after submitting a whole page, display the prior page or the
        # next one.  Derive the day of the submitted page from the ID of the
        # last processed message.
        elif id:
            start = self._keyToTimestamp(id)
            unused, unused, prior, unused, next = self._buildReviewKeys(start)
            if prior:
                start = prior
            else:
                start = next

        # Else if they've hit Previous or Next, display that page.
        elif params.get('go') == 'Next day':
            start = self._keyToTimestamp(params['next'])
        elif params.get('go') == 'Previous day':
            start = self._keyToTimestamp(params['prior'])

        # Else if an id has been specified, just show that message
        elif params.get('find') is not None:
            key = params['find']
            error = False
            if key == "":
                error = True
                page = "<p>You must enter an id to find.</p>"
            elif state.unknownCorpus.get(key) == None:
                # maybe this message has been moved to the spam
                # or ham corpus
                if state.hamCorpus.get(key) != None:
                    sourceCorpus = state.hamCorpus
                elif state.spamCorpus.get(key) != None:
                    sourceCorpus = state.spamCorpus
                else:
                    error = True
                    page = "<p>Could not find message with id '"
                    page += key + "' - maybe it expired.</p>"
            if error == True:
                title = "Did not find message"
                box = self._buildBox(title, 'status.gif', page)
                self.write(box)
                self.write(self._buildBox('Find message', 'query.gif',
                                          self.html.findMessage))
                self._writePostamble()
                return
            keys.append(params['find'])
            prior = this = next = 0
            title = "Found message"

        # Else show the most recent day's page, as decided by _buildReviewKeys.
        else:
            start = 0

        # Build the lists of messages: spams, hams and unsure.
        if len(keys) == 0:
            keys, date, prior, this, next = self._buildReviewKeys(start)
        keyedMessageInfo = {options.header_spam_string: [],
                            options.header_ham_string: [],
                            options.header_unsure_string: []}
        for key in keys:
            # Parse the message, get the judgement header and build a message
            # info object for each message.
            cachedMessage = sourceCorpus[key]
            message = mboxutils.get_message(cachedMessage.getSubstance())
            judgement = message[options.hammie_header_name]
            if judgement is None:
                judgement = options.header_unsure_string
            else:
                judgement = judgement.split(';')[0].strip()
            messageInfo = self._makeMessageInfo(message)
            keyedMessageInfo[judgement].append((key, messageInfo))

        # Present the list of messages in their groups in reverse order of
        # appearance.
        if keys:
            page = self.html.reviewtable.clone()
            if prior:
                page.prior.value = prior
                del page.priorButton.disabled
            if next:
                page.next.value = next
                del page.nextButton.disabled
            templateRow = page.reviewRow.clone()
            page.table = ""  # To make way for the real rows.
            for header, label in ((options.header_spam_string, 'Spam'),
                                  (options.header_ham_string, 'Ham'),
                                  (options.header_unsure_string, 'Unsure')):
                messages = keyedMessageInfo[header]
                if messages:
                    subHeader = str(self.html.reviewSubHeader)
                    subHeader = subHeader.replace('TYPE', label)
                    page.table += self.html.blankRow
                    page.table += subHeader
                    self._appendMessages(page.table, messages, label)

            page.table += self.html.trainRow
            if title == "":
                title = "Untrained messages received on %s" % date
            box = self._buildBox(title, None, page)  # No icon, to save space.
        else:
            page = "<p>There are no untrained messages to display. "
            page += "Return <a href='home'>Home</a>.</p>"
            title = "No untrained messages"
            box = self._buildBox(title, 'status.gif', page)

        self.write(box)
        self._writePostamble()

    def onView(self, key, corpus):
        """View a message - linked from the Review page."""
        self._writePreamble("View message", parent=('review', 'Review'))
        message = state.unknownCorpus.get(key)
        if message:
            self.write("<pre>%s</pre>" % cgi.escape(message.getSubstance()))
        else:
            self.write("<p>Can't find message %r. Maybe it expired.</p>" % key)
        self._writePostamble()

    def onShowclues(self, key, subject):
        """Show clues for a message - linked from the Review page."""
        self._writePreamble("Message clues", parent=('review', 'Review'))
        message = state.unknownCorpus.get(key).getSubstance()
        message = message.replace('\r\n', '\n').replace('\r', '\n') # For Macs
        if message:
            results = self._buildCluesTable(message, subject)
            del results.classifyAnother
            self.write(results)
        else:
            self.write("<p>Can't find message %r. Maybe it expired.</p>" % key)
        self._writePostamble()

    def _makeMessageInfo(self, message):
        """Given an email.Message, return an object with subjectHeader,
        fromHeader and bodySummary attributes.  These objects are passed into
        appendMessages by onReview - passing email.Message objects directly
        uses too much memory."""
        subjectHeader = message["Subject"] or "(none)"
        fromHeader = message["From"] or "(none)"
        try:
            part = typed_subpart_iterator(message, 'text', 'plain').next()
            text = part.get_payload()
        except StopIteration:
            try:
                part = typed_subpart_iterator(message, 'text', 'html').next()
                text = part.get_payload()
                text, unused = tokenizer.crack_html_style(text)
                text, unused = tokenizer.crack_html_comment(text)
                text = tokenizer.html_re.sub(' ', text)
                text = '(this message only has an HTML body)\n' + text
            except StopIteration:
                text = '(this message has no text body)'
        if type(text) == type([]):  # gotta be a 'right' way to do this
            text = "(this message is a digest of %s messages)" % (len(text))
        else:
            text = text.replace('&nbsp;', ' ')      # Else they'll be quoted
            text = re.sub(r'(\s)\s+', r'\1', text)  # Eg. multiple blank lines
            text = text.strip()

        class _MessageInfo:
            pass
        messageInfo = _MessageInfo()
        messageInfo.subjectHeader = self._trimHeader(subjectHeader, 50, True)
        messageInfo.fromHeader = self._trimHeader(fromHeader, 40, True)
        messageInfo.bodySummary = self._trimHeader(text, 200)
        return messageInfo

    def reReadOptions(self):
        """Called by the config page when the user saves some new options, or
        restores the defaults."""
        # Reload the options.
        global state
        state.bayes.store()
        import Options
        reload(Options)
        global options
        from Options import options

        # Recreate the state.
        self.state_recreator()

--- NEW FILE: UserInterface.py ---
"""Web User Interface

Classes:
    UserInterfaceServer - Implements the web server component
                          via a Dibbler plugin.
    BaseUserInterface - Just has utilities for creating boxes and so forth.
                        (Does not include any pages)
    UserInterface - A base class for Spambayes web user interfaces.

Abstract:

This module implements a browser based Spambayes user interface.  Users can
*not* use this class (there is no 'home' page), but developments should
sub-class it to provide an appropriate interface for their application.

Functions deemed appropriate for all application interfaces are included.
These currently include:
  onClassify - classify a given message
  onWordquery - query a word from the database
  onTrain - train a message or mbox
  onSave - save the database and possibly shutdown
  onConfig - present the appropriate configuration page

To Do:

Web training interface:

 o Functional tests.
 o Keyboard navigation (David Ascher).  But aren't Tab and left/right
   arrow enough?


User interface improvements:

 o Once the pieces are on separate pages, make the paste box bigger.
 o Deployment: Windows executable?  atlaxwin and ctypes?  Or just
   webbrowser?
 o Save the stats (num classified, etc.) between sessions.
 o "Reload database" button.
 o Checkboxes need a default value (i.e. what to set the option as
   when no boxes are checked).  This needs to be thought about and
   then implemented.  add_id is an example of what it does at the
   moment.

 o Suggestions?

"""

# This module is part of the spambayes project, which is Copyright 2002
# The Python Software Foundation and is covered by the Python Software
# Foundation license.

# This module was once part of pop3proxy.py; if you are looking through
# the history of the file, you may need to go back there.
# The options/configuration section started life in OptionConfig.py.
# You can find this file in the cvs attic if you want to trawl through
# its history.

__author__ = """Richie Hindle <richie@entrian.com>,
                Tim Stone <tim@fourstonesExpressions.com>"""
__credits__ = "Tim Peters, Neale Pickett, Tony Meyer, all the Spambayes folk."

try:
    True, False
except NameError:
    # Maintain compatibility with Python 2.2
    True, False = 1, 0

import re
import time
import email
import binascii
import cgi
import mailbox

import PyMeldLite
import Dibbler
import tokenizer
from Options import options, optionsPathname, defaults

IMAGES = ('helmet', 'status', 'config',
          'message', 'train', 'classify', 'query')

global classifier

class UserInterfaceServer(Dibbler.HTTPServer):
    """Implements the web server component via a Dibbler plugin."""

    def __init__(self, uiPort):
        Dibbler.HTTPServer.__init__(self, uiPort)
        print 'User interface url is http://localhost:%d/' % (uiPort)


class BaseUserInterface(Dibbler.HTTPPlugin):
    def __init__(self):
        Dibbler.HTTPPlugin.__init__(self)
        htmlSource, self._images = self.readUIResources()
        self.html = PyMeldLite.Meld(htmlSource, readonly=True)
  
    def onIncomingConnection(self, clientSocket):
        """Checks the security settings."""
        return options.html_ui_allow_remote_connections or \
               clientSocket.getpeername()[0] == clientSocket.getsockname()[0]

    def _writePreamble(self, name, parent=None, showImage=True):
        """Writes the HTML for the beginning of a page - time-consuming
        methlets use this and `_writePostamble` to write the page in
        pieces, including progress messages.  `parent` (if given) should
        be a pair: `(url, label)`, eg. `('review', 'Review')`."""

        # Take the whole palette and remove the content and the footer,
        # leaving the header and an empty body.
        html = self.html.clone()
        html.mainContent = " "
        del html.footer

        # Add in the name of the page and remove the link to Home if this
        # *is* Home.
        html.title = name
        if name == 'Home':
            del html.homelink
            html.pagename = "Home"
        elif parent:
            html.pagename = "> <a href='%s'>%s</a> > %s" % \
                            (parent[0], parent[1], name)
        else:
            html.pagename = "> " + name

        # Remove the helmet image if we're not showing it - this happens on
        # shutdown because the browser might ask for the image after we've
        # exited.
        if not showImage:
            del html.helmet

        # Strip the closing tags, so we push as far as the start of the main
        # content.  We'll push the closing tags at the end.
        self.writeOKHeaders('text/html')
        self.write(re.sub(r'</div>\s*</body>\s*</html>', '', str(html)))

    def _writePostamble(self):
        """Writes the end of time-consuming pages - see `_writePreamble`."""
        footer = self.html.footer.clone()
        footer.timestamp = time.asctime(time.localtime())
        self.write("</div>" + self.html.footer)
        self.write("</body></html>")

    def _trimHeader(self, field, limit, quote=False):
        """Trims a string, adding an ellipsis if necessary and HTML-quoting
        on request.  Also pumps it through email.Header.decode_header, which
        understands charset sections in email headers - I suspect this will
        only work for Latin character sets, but hey, it works for Francois
        Granger's name.  8-)"""

        try:
            sections = email.Header.decode_header(field)
        except (binascii.Error, email.Errors.HeaderParseError):
            sections = [(field, None)]
        field = ' '.join([text for text, unused in sections])
        if len(field) > limit:
            field = field[:limit-3] + "..."
        if quote:
            field = cgi.escape(field)
        return field

    def onHome(self):
        """Serve up the homepage."""
        raise NotImplementedError

    def _writeImage(self, image):
        self.writeOKHeaders('image/gif')
        self.write(self._images[image])

    # If you are easily offended, look away now...
    for imageName in IMAGES:
        exec "def %s(self): self._writeImage('%s')" % \
             ("on%sGif" % imageName.capitalize(), imageName)

    def _buildBox(self, heading, icon, content):
        """Builds a yellow-headed HTML box."""
        box = self.html.headedBox.clone()
        box.heading = heading
        if icon:
            box.icon.src = icon
        else:
            del box.iconCell
        box.boxContent = content
        return box

    def readUIResources(self):
        """Returns ui.html and a dictionary of Gifs."""

        # Using `exec` is nasty, but I couldn't figure out a way of making
        # `getattr` or `__import__` work with ResourcePackage.
        from spambayes.resources import ui_html
        images = {}
        for baseName in IMAGES:
            moduleName = '%s.%s_gif' % ('spambayes.resources', baseName)
            module = __import__(moduleName, {}, {}, ('spambayes', 'resources'))
            images[baseName] = module.data
        return ui_html.data, images


class UserInterface(BaseUserInterface):
    """Serves the HTML user interface."""

    def __init__(self, bayes, config_parms=[], config_display=[]):
        """Load up the necessary resources: ui.html and helmet.gif."""
        global classifier
        BaseUserInterface.__init__(self)
        classifier = bayes
        self.parm_ini_map = config_parms
        self.display = config_display

    def onClassify(self, file, text, which):
        """Classify an uploaded or pasted message."""
        message = file or text
        message = message.replace('\r\n', '\n').replace('\r', '\n') # For Macs
        results = self._buildCluesTable(message)
        results.classifyAnother = self._buildClassifyBox()
        self._writePreamble("Classify")
        self.write(results)
        self._writePostamble()

    def _buildCluesTable(self, message, subject=None):
        cluesTable = self.html.cluesTable.clone()
        cluesRow = cluesTable.cluesRow.clone()
        del cluesTable.cluesRow   # Delete dummy row to make way for real ones
        (probability, clues) = classifier.spamprob(tokenizer.tokenize(message),\
                                                    evidence=True)
        for word, wordProb in clues:
            cluesTable += cluesRow % (cgi.escape(word), wordProb)

        results = self.html.classifyResults.clone()
        results.probability = probability
        if subject is None:
            heading = "Clues:"
        else:
            heading = "Clues for: " + subject
        results.cluesBox = self._buildBox(heading, 'status.gif', cluesTable)
        return results

    def onWordquery(self, word):
        if word == "":
            stats = "You must enter a word."
        else:
            word = word.lower()
            wordinfo = classifier._wordinfoget(word)
            if wordinfo:
                stats = self.html.wordStats.clone()
                stats.spamcount = wordinfo.spamcount
                stats.hamcount = wordinfo.hamcount
                stats.spamprob = classifier.probability(wordinfo)
            else:
                stats = "%r does not exist in the database." % cgi.escape(word)

        query = self.html.wordQuery.clone()
        query.word.value = word
        statsBox = self._buildBox("Statistics for %r" % cgi.escape(word),
                                  'status.gif', stats)
        queryBox = self._buildBox("Word query", 'query.gif', query)
        self._writePreamble("Word query")
        self.write(statsBox + queryBox)
        self._writePostamble()

    def onTrain(self, file, text, which):
        """Train on an uploaded or pasted message."""
        self._writePreamble("Train")

        # Upload or paste?  Spam or ham?
        content = file or text
        isSpam = (which == 'Train as Spam')

        # Convert platform-specific line endings into unix-style.
        content = content.replace('\r\n', '\n').replace('\r', '\n')

        # The upload might be a single message or am mbox file.
        messages = self._convertUploadToMessageList(content)

        # Append the message(s) to a file, to make it easier to rebuild
        # the database later.   This is a temporary implementation -
        # it should keep a Corpus of trained messages.
        if isSpam:
            f = open("_pop3proxyspam.mbox", "a")
        else:
            f = open("_pop3proxyham.mbox", "a")

        # Train on the uploaded message(s).
        self.write("<b>Training...</b>\n")
        self.flush()
        for message in messages:
            tokens = tokenizer.tokenize(message)
            classifier.learn(tokens, isSpam)
            f.write("From pop3proxy@spambayes.org Sat Jan 31 00:00:00 2000\n")
            f.write(message)
            f.write("\n\n")

        # Save the database and return a link Home and another training form.
        f.close()
        self._doSave()
        self.write("<p>OK. Return <a href='home'>Home</a> or train again:</p>")
        self.write(self._buildTrainBox())
        self._writePostamble()

    def _convertUploadToMessageList(self, content):
        """Returns a list of raw messages extracted from uploaded content.
        You can upload either a single message or an mbox file."""
        if content.startswith('From '):
            # Get a list of raw messages from the mbox content.
            class SimpleMessage:
                def __init__(self, fp):
                    self.guts = fp.read()
            contentFile = StringIO.StringIO(content)
            mbox = mailbox.PortableUnixMailbox(contentFile, SimpleMessage)
            return map(lambda m: m.guts, mbox)
        else:
            # Just the one message.
            return [content]

    def _doSave(self):
        """Saves the database."""
        self.write("<b>Saving... ")
        self.flush()
        classifier.store()
        self.write("Done</b>.\n")

    def onSave(self, how):
        """Command handler for "Save" and "Save & shutdown"."""
        isShutdown = how.lower().find('shutdown') >= 0
        self._writePreamble("Save", showImage=(not isShutdown))
        self._doSave()
        if isShutdown:
            self.write("<p>%s</p>" % self.html.shutdownMessage)
            self.write("</div></body></html>")
            self.flush()
            ## Is this still required?: self.shutdown(2)
            self.close()
            raise SystemExit
        self._writePostamble()

    def _buildClassifyBox(self):
        """Returns a "Classify a message" box.  This is used on both the Home
        page and the classify results page.  The Classify form is based on the
        Upload form."""

        form = self.html.upload.clone()
        del form.or_mbox
        del form.submit_spam
        del form.submit_ham
        form.action = "classify"
        return self._buildBox("Classify a message", 'classify.gif', form)

    def _buildTrainBox(self):
        """Returns a "Train on a given message" box.  This is used on both
        the Home page and the training results page.  The Train form is
        based on the Upload form."""

        form = self.html.upload.clone()
        del form.submit_classify
        return self._buildBox("Train on a given message", 'message.gif', form)

    def reReadOptions(self):
        """Called by the config page when the user saves some new options,
        or restores the defaults."""
        pass

    def onConfig(self):
        # Start with an empty config form then add the sections.
        html = self.html.clone()
        # "Save and Shutdown" is confusing here - it means "Save database"
        # but that's not clear.
        html.shutdownTableCell = "&nbsp;"
        html.mainContent = self.html.configForm.clone()
        html.mainContent.configFormContent = ""
        html.mainContent.optionsPathname = optionsPathname
        configTable = None
        section = None

        # Loop though the sections.
        for html_key in self.display:
            if not self.parm_ini_map.has_key(html_key):
                if configTable is not None and section is not None:
                    # Finish off the box for this section and add it
                    # to the form.
                    section.boxContent = configTable
                    html.configFormContent += section
                # Start the yellow-headed box for this section.
                section = self.html.headedBox.clone()
                # Get a clone of the config table and a clone of each
                # example row, then blank out the example rows to make way
                # for the real ones.
                configTable = self.html.configTable.clone()
                configTextRow1 = configTable.configTextRow1.clone()
                configCbRow1 = configTable.configCbRow1.clone()
                configRow2 = configTable.configRow2.clone()
                blankRow = configTable.blankRow.clone()
                del configTable.configTextRow1
                del configTable.configCbRow1
                del configTable.configRow2
                del configTable.blankRow
                section.heading = html_key
                del section.iconCell
                continue
            (sect, opt) = self.parm_ini_map[html_key]

            # Populate the rows with the details and add them to the table.
            if type(options.valid_input(sect, opt)) == type(""):
                # we provide a text input
                newConfigRow1 = configTextRow1.clone()
                newConfigRow1.label = options.display_name(sect, opt)
                newConfigRow1.input.name = html_key
                newConfigRow1.input.value = options.get(sect, opt)
            else:
                # we provide checkboxes/radio buttons
                newConfigRow1 = configCbRow1.clone()
                newConfigRow1.label = options.display_name(sect, opt)
                blankOption = newConfigRow1.input.clone()
                firstOpt = True
                i = 0
                for val in options.valid_input(sect, opt):
                    newOption = blankOption.clone()
                    if str(val) in str(options[sect, opt]).split():
                        newOption.input_box.checked = "checked" 
                    # help for Python 2.2
                    if options.is_boolean(sect, opt):
                        if str(val) == "0":
                            val = "False"
                        elif str(val) == "1":
                            val = "True"
                    newOption.val_label = str(val)
                    if options.multiple_values_allowed(sect, opt):
                        newOption.input_box.type = "checkbox"
                        newOption.input_box.name = html_key + '-' + str(i)
                        i += 1
                    else:
                        newOption.input_box.type = "radio"
                        newOption.input_box.name = html_key
                    newOption.input_box.value = str(val)
                    if firstOpt: 
                        newConfigRow1.input = newOption
                        firstOpt = False
                    else:                   
                        newConfigRow1.input += newOption
            # Insert the help text in a cell
            newConfigRow1.helpCell = '<strong>' + \
                                     options.display_name(sect, opt) + \
                                     ':</strong> ' + \
                                     cgi.escape(options.doc(sect, opt))

            newConfigRow2 = configRow2.clone()
            currentValue = options[sect, opt]
            # for Python 2.2
            if options.is_boolean(sect, opt):
                if str(currentValue) == '0':
                    currentValue = "False"
                elif str(currentValue) == '1':
                    currentValue = "True"
            newConfigRow2.currentValue = currentValue
            configTable += newConfigRow1 + newConfigRow2 + blankRow

        # Finish off the box for this section and add it to the form.
        if section is not None:
            section.boxContent = configTable
            html.configFormContent += section
        html.title = 'Home &gt; Configure'
        html.pagename = '&gt; Configure'
        self.writeOKHeaders('text/html')
        self.write(html)

    def onChangeopts(self, **parms):
        html = self.html.clone()
        html.shutdownTableCell = "&nbsp;"
        html.mainContent = self.html.headedBox.clone()
        errmsg = self.verifyInput(parms)
        if errmsg != '':
            html.mainContent.heading = "Errors Detected"
            html.mainContent.boxContent = errmsg
            html.title = 'Home &gt; Error'
            html.pagename = '&gt; Error'
            self.writeOKHeaders('text/html')
            self.write(html)
            return

        for name, value in parms.items():
           if self.parm_ini_map.has_key(name):
               sect, opt = self.parm_ini_map[name]
               options.set(sect, opt, value)

        op = open(optionsPathname, "r")
        options.update_file(op)
        op.close()
        self.reReadOptions()

        html.mainContent.heading = "Options Changed"
        html.mainContent.boxContent = "%s.  Return <a href='home'>Home</a>." \
                                      % "Options changed"
        html.title = 'Home &gt; Options Changed'
        html.pagename = '&gt; Options Changed'
        self.writeOKHeaders('text/html')
        self.write(html)

    def onRestoredefaults(self, how):
        self.restoreConfigDefaults()
        self.reReadOptions()

        html = self.html.clone()
        html.shutdownTableCell = "&nbsp;"
        html.mainContent = self.html.headedBox.clone()
        html.mainContent.heading = "Option Defaults Restored"
        html.mainContent.boxContent = "%s.  Return <a href='home'>Home</a>." \
                                      % "Defaults restored"
        html.title = 'Home &gt; Defaults Restored'
        html.pagename = '&gt; Defaults Restored'
        self.writeOKHeaders('text/html')
        self.write(html)

    def verifyInput(self, parms):
        '''Check that the given input is valid.'''
        # Most of the work here is done by the options class, but
        # we have a few extra checks that are beyond its capabilities
        errmsg = ''

        # mumbo-jumbo to deal with the checkboxes
        # XXX This will break with more than 9 checkboxes
        # XXX A better solution is needed than this
        for name, value in parms.items():
            if name[-2:-1] == '-':
                if parms.has_key(name[:-2]):
                    parms[name[:-2]].append(value)
                else:
                    parms[name[:-2]] = (value,)
                del parms[name]

        for html_key in self.display:
            if not self.parm_ini_map.has_key(html_key):
                nice_section_name = html_key
                continue
            sect, opt = self.parm_ini_map[html_key]
            if not parms.has_key(html_key):
                # This is a set of checkboxes where none are selected
                value = None
            else:
                value = parms[html_key]
            if value is not None:
                if type(value) == type((0,1)):
                    value_string = ""
                    for val in value:
                        value_string += val
                        value_string += ','
                    value = value_string[:-1]
                value = options.convert(sect, opt, value)
            if not options.is_valid(sect, opt, value):
                errmsg += '<li>\'%s\' is not a value valid for [%s] %s' % \
                          (value, nice_section_name,
                           options.display_name(sect, opt))
                if type(options.valid_input(sect, opt)) == type((0,1)):
                    errmsg += '. Valid values are: '
                    for valid in options.valid_input(sect, opt):
                        errmsg += str(valid) + ','
                    errmsg = errmsg[:-1] # cut last ','
                errmsg += '</li>'
            parms[html_key] = value

        # check for equal number of pop3servers and ports
        slist = parms['p3servers'].split(',')
        plist = parms['p3ports'].split(',')
        if len(slist) != len(plist):
            errmsg += '<li>The number of POP3 proxy ports specified ' + \
                      'must match the number of servers specified</li>\n'

        # check for duplicate ports
        plist.sort()
        for p in range(len(plist)-1):
            try:
                if plist[p] == plist[p+1]:
                    errmsg += '<li>All POP3 port numbers must be unique</li>'
                    break
            except IndexError:
                pass

        # check for equal number of smtpservers and ports
        slist = parms['smtpservers'].split(',')
        plist = parms['smtpports'].split(',')
        if len(slist) != len(plist):
            errmsg += '<li>The number of SMTP proxy ports specified ' + \
                      'must match the number of servers specified</li>\n'

        # check for duplicate ports
        plist.sort()
        for p in range(len(plist)-1):
            try:
                if plist[p] == plist[p+1]:
                    errmsg += '<li>All SMTP port numbers must be unique</li>'
                    break
            except IndexError:
                pass

        return errmsg

    def restoreConfigDefaults(self):
        # note that the behaviour of this function has subtly changed
        # previously options were removed from the config file, now the
        # config file is updated to match the defaults
        c = ConfigParser()
        d = StringIO(defaults)
        c.readfp(d)
        del d

        # Only restore the settings that appear on the form.
        for section, option in self.parm_ini_map.values():
            if not options.no_restore(section, option):
                options.set(section, option, c.get(section,option))

        op = open(optionsPathname, "r")
        options.update_file(op)
        op.close()

Index: tokenizer.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/tokenizer.py,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** tokenizer.py	6 Mar 2003 15:47:19 -0000	1.7
--- tokenizer.py	18 Apr 2003 09:24:29 -0000	1.8
***************
*** 17,21 ****
      from sets import Set
  except ImportError:
!     from spambayes.compatsets import Set
  
  
--- 17,21 ----
      from sets import Set
  except ImportError:
!     from compatsets import Set
  
  



From anadelonbrin at users.sourceforge.net  Fri Apr 18 16:49:00 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 18:49:03 2003
Subject: [Spambayes-checkins] spambayes/spambayes ImapUI.py,1.1,1.2
Message-ID: <E196efE-0003AA-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv12138/spambayes

Modified Files:
	ImapUI.py 
Log Message:
Syntax error in unused part of the code.

Index: ImapUI.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/ImapUI.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** ImapUI.py	18 Apr 2003 09:24:29 -0000	1.1
--- ImapUI.py	18 Apr 2003 22:48:57 -0000	1.2
***************
*** 135,139 ****
          on the server'''
          response = imap.list()
!         if response[0] != "OK" return ()
          all_folders = response[1]
          folders = []
--- 135,140 ----
          on the server'''
          response = imap.list()
!         if response[0] != "OK":
!             return ()
          all_folders = response[1]
          folders = []



From tim at fourstonesExpressions.com  Fri Apr 18 18:50:25 2003
From: tim at fourstonesExpressions.com (Tim Stone - Four Stones Expressions)
Date: Fri Apr 18 18:50:31 2003
Subject: [Spambayes-checkins] spambayes/spambayes ImapUI.py,1.1,1.2
In-Reply-To: <E196efE-0003AA-00@sc8-pr-cvs1.sourceforge.net>
Message-ID: <TR7182WNH1VLK1ZUQXULFXVHFTOLF86.3ea08131@myst>

Tony, how do you run this ImapUI?

4/18/2003 5:49:00 PM, "Tony Meyer" <anadelonbrin@users.sourceforge.net> wrote:

>Update of /cvsroot/spambayes/spambayes/spambayes
>In directory sc8-pr-cvs1:/tmp/cvs-serv12138/spambayes
>
>Modified Files:
>	ImapUI.py 
>Log Message:
>Syntax error in unused part of the code.
>
>Index: ImapUI.py
>===================================================================
>RCS file: /cvsroot/spambayes/spambayes/spambayes/ImapUI.py,v
>retrieving revision 1.1
>retrieving revision 1.2
>diff -C2 -d -r1.1 -r1.2
>*** ImapUI.py	18 Apr 2003 09:24:29 -0000	1.1
>--- ImapUI.py	18 Apr 2003 22:48:57 -0000	1.2
>***************
>*** 135,139 ****
>          on the server'''
>          response = imap.list()
>!         if response[0] != "OK" return ()
>          all_folders = response[1]
>          folders = []
>--- 135,140 ----
>          on the server'''
>          response = imap.list()
>!         if response[0] != "OK":
>!             return ()
>          all_folders = response[1]
>          folders = []
>
>
>
>_______________________________________________
>Spambayes-checkins mailing list
>Spambayes-checkins@python.org
>http://mail.python.org/mailman/listinfo/spambayes-checkins
>
>


c'est moi - TimS
http://www.fourstonesExpressions.com
http://wecanstopspam.org

There are 10 kinds of people in the world:
  those who understand binary,
  and those who don't.



From tim at fourstonesExpressions.com  Fri Apr 18 18:52:54 2003
From: tim at fourstonesExpressions.com (Tim Stone - Four Stones Expressions)
Date: Fri Apr 18 18:52:59 2003
Subject: [Spambayes-checkins] spambayes/spambayes ImapUI.py,1.1,1.2
In-Reply-To: <TR7182WNH1VLK1ZUQXULFXVHFTOLF86.3ea08131@myst>
Message-ID: <B8PKFCB8571DQNNJ06YPNLK64ZUQ.3ea081c6@myst>

Ah, I see, it's in the imapfilter... I'd forgotten that you'd sent me that for 
checkout.

4/18/2003 5:50:25 PM, Tim Stone - Four Stones Expressions 
<tim@fourstonesExpressions.com> wrote:

>Tony, how do you run this ImapUI?
>
>4/18/2003 5:49:00 PM, "Tony Meyer" <anadelonbrin@users.sourceforge.net> 
wrote:
>
>>Update of /cvsroot/spambayes/spambayes/spambayes
>>In directory sc8-pr-cvs1:/tmp/cvs-serv12138/spambayes
>>
>>Modified Files:
>>	ImapUI.py 
>>Log Message:
>>Syntax error in unused part of the code.
>>
>>Index: ImapUI.py
>>===================================================================
>>RCS file: /cvsroot/spambayes/spambayes/spambayes/ImapUI.py,v
>>retrieving revision 1.1
>>retrieving revision 1.2
>>diff -C2 -d -r1.1 -r1.2
>>*** ImapUI.py	18 Apr 2003 09:24:29 -0000	1.1
>>--- ImapUI.py	18 Apr 2003 22:48:57 -0000	1.2
>>***************
>>*** 135,139 ****
>>          on the server'''
>>          response = imap.list()
>>!         if response[0] != "OK" return ()
>>          all_folders = response[1]
>>          folders = []
>>--- 135,140 ----
>>          on the server'''
>>          response = imap.list()
>>!         if response[0] != "OK":
>>!             return ()
>>          all_folders = response[1]
>>          folders = []
>>
>>
>>
>>_______________________________________________
>>Spambayes-checkins mailing list
>>Spambayes-checkins@python.org
>>http://mail.python.org/mailman/listinfo/spambayes-checkins
>>
>>
>
>
>c'est moi - TimS
>http://www.fourstonesExpressions.com
>http://wecanstopspam.org
>
>There are 10 kinds of people in the world:
>  those who understand binary,
>  and those who don't.
>
>
>
>_______________________________________________
>Spambayes-checkins mailing list
>Spambayes-checkins@python.org
>http://mail.python.org/mailman/listinfo/spambayes-checkins
>
>


c'est moi - TimS
http://www.fourstonesExpressions.com
http://wecanstopspam.org

There are 10 kinds of people in the world:
  those who understand binary,
  and those who don't.



From anadelonbrin at users.sourceforge.net  Fri Apr 18 17:03:35 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 19:03:38 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.22,1.23
Message-ID: <E196etL-0004fV-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv17924

Modified Files:
	imapfilter.py 
Log Message:
Add support for the web ui (for configuration, mostly).

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.22
retrieving revision 1.23
diff -C2 -d -r1.22 -r1.23
*** imapfilter.py	18 Apr 2003 06:56:59 -0000	1.22
--- imapfilter.py	18 Apr 2003 23:03:32 -0000	1.23
***************
*** 25,28 ****
--- 25,29 ----
              -i debuglvl : a somewhat mysterious imaplib debugging level
              -l minutes  : period of time between filtering operations
+             -b          : Launch a web browser showing the user interface.
  
  Examples:
***************
*** 58,67 ****
      o Find a better way to remove old msg from info database when saving
        modified messages
-     o Web UI for configuration and setup. Tony thinks it would be
-         nice if there was a web ui to this for the initial setup (i.e. like
-         pop3proxy), which offered a list of folders to filter/train/etc.  It
-         could then record a uid for the folder rather than a name, and it
-         avoids the problems with different imap servers having different
-         naming styles a list is retrieved via imap.list()
      o IMAPMessage and IMAPFolder currently carry out very simple checks
        of responses received from IMAP commands, but if the response is not
--- 59,62 ----
***************
*** 106,110 ****
  
  from spambayes.Options import options
! from spambayes import tokenizer, storage, message
  
  # global IMAPlib object
--- 101,107 ----
  
  from spambayes.Options import options
! from spambayes import tokenizer, storage, message, Dibbler
! from spambayes.UserInterface import UserInterfaceServer
! from spambayes.ImapUI import IMAPUserInterface
  
  # global IMAPlib object
***************
*** 369,373 ****
      global imap
      try:
!         opts, args = getopt.getopt(sys.argv[1:], 'htcvpl:e:i:d:D:')
      except getopt.error, msg:
          print >>sys.stderr, str(msg) + '\n\n' + __doc__
--- 366,370 ----
      global imap
      try:
!         opts, args = getopt.getopt(sys.argv[1:], 'hbtcvpl:e:i:d:D:')
      except getopt.error, msg:
          print >>sys.stderr, str(msg) + '\n\n' + __doc__
***************
*** 381,385 ****
      imapDebug = 0
      sleepTime = 0
!     promptForPass = 0
  
      for opt, arg in opts:
--- 378,383 ----
      imapDebug = 0
      sleepTime = 0
!     promptForPass = False
!     launchUI = False
  
      for opt, arg in opts:
***************
*** 393,396 ****
--- 391,396 ----
              useDBM = True
              bdbname = arg
+         elif opt == "-b":
+             launchUI = True
          elif opt == '-t':
              doTrain = True
***************
*** 411,415 ****
              sleepTime = int(arg) * 60
  
!     if not (doClassify or doTrain):
          print "-c and/or -t operands must be specified"
          sys.exit()
--- 411,415 ----
              sleepTime = int(arg) * 60
  
!     if not (doClassify or doTrain or launchUI):
          print "-c and/or -t operands must be specified"
          sys.exit()
***************
*** 437,440 ****
--- 437,448 ----
  
      imap_filter = IMAPFilter(classifier)
+ 
+     # Web interface
+     # XXX If someone is running *both* pop3proxy and imapfilter
+     # XXX then there will be trouble since both interfaces are
+     # XXX using the same port by default.
+     httpServer = UserInterfaceServer(options["html_ui", "port"])
+     httpServer.register(IMAPUserInterface(classifier, imap))
+     Dibbler.run(launchBrowser=launchUI)
  
      while True:



From timstone4 at users.sourceforge.net  Fri Apr 18 17:13:25 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Fri Apr 18 19:13:28 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.23,1.24
Message-ID: <E196f2r-0005c2-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv21566

Modified Files:
	imapfilter.py 
Log Message:
Added check for browser startup, so browser only starts up if required.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.23
retrieving revision 1.24
diff -C2 -d -r1.23 -r1.24
*** imapfilter.py	18 Apr 2003 23:03:32 -0000	1.23
--- imapfilter.py	18 Apr 2003 23:13:23 -0000	1.24
***************
*** 412,418 ****
  
      if not (doClassify or doTrain or launchUI):
!         print "-c and/or -t operands must be specified"
          sys.exit()
  
      if promptForPass:
          pwd = getpass()
--- 412,424 ----
  
      if not (doClassify or doTrain or launchUI):
!         print "-b, -c, or -t operands must be specified"
          sys.exit()
  
+     if (launchUI and (doClassify or doTrain)):
+         print """
+ -b option is exclusive with -c and -t options.
+ The user interface will be launched, but no classification
+ or training will be performed."""
+ 
      if promptForPass:
          pwd = getpass()
***************
*** 442,468 ****
      # XXX then there will be trouble since both interfaces are
      # XXX using the same port by default.
!     httpServer = UserInterfaceServer(options["html_ui", "port"])
!     httpServer.register(IMAPUserInterface(classifier, imap))
!     Dibbler.run(launchBrowser=launchUI)
! 
!     while True:
!         imap.login(options["imap", "username"], pwd)
  
!         if doTrain:
!             if options["globals", "verbose"]:
!                 print "Training"
!             imap_filter.Train()
!         if doClassify:
!             if options["globals", "verbose"]:
!                 print "Classifying"
!             imap_filter.Filter()
  
!         imap.logout(doExpunge)
!         
!         if sleepTime:
!             time.sleep(sleepTime)
!         else:
!             break
  
  if __name__ == '__main__':
!     run()
\ No newline at end of file
--- 448,475 ----
      # XXX then there will be trouble since both interfaces are
      # XXX using the same port by default.
!     if launchUI:
!         httpServer = UserInterfaceServer(options["html_ui", "port"])
!         httpServer.register(IMAPUserInterface(classifier, imap))
!         Dibbler.run(launchBrowser=launchUI)
!     else:
!         while True:
!             imap.login(options["imap", "username"], pwd)
  
!             if doTrain:
!                 if options["globals", "verbose"]:
!                     print "Training"
!                 imap_filter.Train()
!             if doClassify:
!                 if options["globals", "verbose"]:
!                     print "Classifying"
!                 imap_filter.Filter()
  
!             imap.logout(doExpunge)
!             
!             if sleepTime:
!                 time.sleep(sleepTime)
!             else:
!                 break
  
  if __name__ == '__main__':
!     run()



From anadelonbrin at users.sourceforge.net  Fri Apr 18 18:02:16 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 20:02:19 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.28,1.29
Message-ID: <E196fo8-0001Cv-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv4607/spambayes

Modified Files:
	Options.py 
Log Message:
An extra backwards compatibility option.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.28
retrieving revision 1.29
diff -C2 -d -r1.28 -r1.29
*** Options.py	18 Apr 2003 06:51:59 -0000	1.28
--- Options.py	19 Apr 2003 00:02:13 -0000	1.29
***************
*** 1234,1237 ****
--- 1234,1242 ----
                          value = converter(value)
                  self._options[section, option].set(value)
+                 # just for the moment, here's some more
+                 # backwards compatability - this will go
+                 # away very soon, so don't rely on this working
+                 old_name = section[0:1].lower() + section[1:] + '_' + option
+                 setattr(options, old_name, value) # ugly!
          if nerrors:
              raise ValueError("errors while parsing .ini file")



From anadelonbrin at users.sourceforge.net  Fri Apr 18 18:11:37 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 20:14:59 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.24,1.25
Message-ID: <E196fxB-0001uu-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv7328

Modified Files:
	imapfilter.py 
Log Message:
Fix for missing date header time retrieval function.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.24
retrieving revision 1.25
diff -C2 -d -r1.24 -r1.25
*** imapfilter.py	18 Apr 2003 23:13:23 -0000	1.24
--- imapfilter.py	19 Apr 2003 00:11:33 -0000	1.25
***************
*** 175,182 ****
          # a timestamp for the message.  If the message has a date header
          # we use that.  Otherwise, we use the current time.
!         try:
              return imaplib.Time2Internaldate(\
!                        time.mktime(parsedate(self["Date"])))
!         except KeyError:
              return imaplib.Time2Internaldate(time.time())
  
--- 175,183 ----
          # a timestamp for the message.  If the message has a date header
          # we use that.  Otherwise, we use the current time.
!         message_date = self["Date"]
!         if message_date is not None:
              return imaplib.Time2Internaldate(\
!                        time.mktime(parsedate(message_date)))
!         else:
              return imaplib.Time2Internaldate(time.time())
  



From anadelonbrin at users.sourceforge.net  Fri Apr 18 18:51:04 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 20:51:09 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.11,1.12
Message-ID: <E196gZM-0004gv-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv18017/spambayes

Modified Files:
	message.py 
Log Message:
Update the comments about the line endings fix and change
the regex to a more robust one (stolen from smtplib).

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.11
retrieving revision 1.12
diff -C2 -d -r1.11 -r1.12
*** message.py	18 Apr 2003 00:56:20 -0000	1.11
--- message.py	19 Apr 2003 00:51:02 -0000	1.12
***************
*** 171,180 ****
          return tokenize(self.as_string())
  
      def as_string(self):
!         # This override is currently needed because of an apparent bug
!         # in the email package, where header lines are not properly
!         # terminated with \r\n
!         return re.sub('([^\r])\n', r'\1\r\n', \
!                       email.Message.Message.as_string(self))
          
      def modified(self):
--- 171,190 ----
          return tokenize(self.as_string())
  
+     def _force_CRLF(self, data):
+         """Make sure data uses CRLF for line termination.
+ 
+         Nicked the regex from smtplib.quotedata.
+         """
+         return re.sub(r'(?:\r\n|\n|\r(?!\n))', "\r\n", data)
+ 
      def as_string(self):
!         # The email package stores line endings in the "internal" Python
!         # format ('\n').  According to that package, it is up to the
!         # server of that information to convert to appropriate line
!         # endings (according to RFC822, that is \r\n *only*).
!         # We, however, always want to return correct endings from
!         # as_string(), so we make the change here, rather than having
!         # the same code in imapfilter, pop3proxy, and so on.
!         return self._force_CRLF(email.Message.Message.as_string(self))
          
      def modified(self):



From anadelonbrin at users.sourceforge.net  Fri Apr 18 19:11:29 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 21:11:32 2003
Subject: [Spambayes-checkins] spambayes pop3proxy.py,1.71,1.72
Message-ID: <E196gt7-0006CM-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv23776

Modified Files:
	pop3proxy.py 
Log Message:
Update pop3proxy to use the new options style.
Update pop3proxy to use the new UI modules.
(Note that OptionConfig is no longer used by anyone as its
code is integrated into ProxyUI.py and UserInterface.py.
If all goes well it will be moved into the attic shortly).
Update ui.html (and ui_html.py) to work with the new UI
modules.

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.71
retrieving revision 1.72
diff -C2 -d -r1.71 -r1.72
*** pop3proxy.py	18 Apr 2003 05:26:26 -0000	1.71
--- pop3proxy.py	19 Apr 2003 01:11:26 -0000	1.72
***************
*** 29,33 ****
  
  For safety, and to help debugging, the whole POP3 conversation is
! written out to _pop3proxy.log for each run, if options.verbose is True.
  
  To make rebuilding the database easier, uploaded messages are appended
--- 29,34 ----
  
  For safety, and to help debugging, the whole POP3 conversation is
! written out to _pop3proxy.log for each run, if
! options["globals", "verbose"] is True.
[...1066 lines suppressed...]
      # Smoke-test the HTML UI.
***************
*** 1663,1670 ****
          elif opt == '-d':   # dbm file
              state.useDB = True
!             options.pop3proxy_persistent_storage_file = arg
          elif opt == '-D':   # pickle file
              state.useDB = False
!             options.pop3proxy_persistent_storage_file = arg
          elif opt == '-p':   # dead option
              print >>sys.stderr, "-p option is no longer supported, use -D\n"
--- 1054,1061 ----
          elif opt == '-d':   # dbm file
              state.useDB = True
!             options["pop3proxy", "persistent_storage_file"] = arg
          elif opt == '-D':   # pickle file
              state.useDB = False
!             options["pop3proxy", "persistent_storage_file"] = arg
          elif opt == '-p':   # dead option
              print >>sys.stderr, "-p option is no longer supported, use -D\n"



From anadelonbrin at users.sourceforge.net  Fri Apr 18 19:11:29 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 21:11:36 2003
Subject: [Spambayes-checkins] spambayes/spambayes/resources ui.html, 1.7,
	1.8 ui_html.py, 1.7, 1.8
Message-ID: <E196gt7-0006CT-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes/resources
In directory sc8-pr-cvs1:/tmp/cvs-serv23776/spambayes/resources

Modified Files:
	ui.html ui_html.py 
Log Message:
Update pop3proxy to use the new options style.
Update pop3proxy to use the new UI modules.
(Note that OptionConfig is no longer used by anyone as its
code is integrated into ProxyUI.py and UserInterface.py.
If all goes well it will be moved into the attic shortly).
Update ui.html (and ui_html.py) to work with the new UI
modules.

Index: ui.html
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui.html,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** ui.html	4 Apr 2003 01:11:57 -0000	1.7
--- ui.html	19 Apr 2003 01:11:26 -0000	1.8
***************
*** 42,46 ****
      <span id="helmet"><img src='helmet.gif' align='absmiddle'/>&nbsp;</span>
      <span class='header'>
!         <span id="productName">Spambayes proxy</span>:
          <a id="homelink" href='home'>Home</a>
          <span id="pagename">&gt; ui.html</span>
--- 42,46 ----
      <span id="helmet"><img src='helmet.gif' align='absmiddle'/>&nbsp;</span>
      <span class='header'>
!         <span id="productName">Spambayes Web Interface</span>:
          <a id="homelink" href='home'>Home</a>
          <span id="pagename">&gt; ui.html</span>
***************
*** 118,126 ****
          POP3 proxy running on <b><span id="proxyPortsString">1110</span></b>,
          proxying to <b><span id="serversString">example.com</span></b>.
!         </span><br/>
          Active POP3 conversations:
              <b><span id="activeSessions">0</span></b>.<br/>
          POP3 conversations this session:
              <b><span id="totalSessions">0</span></b>.<br/>
          Emails classified this session:
              <b><span id="numSpams">0</span></b> spam,
--- 118,127 ----
          POP3 proxy running on <b><span id="proxyPortsString">1110</span></b>,
          proxying to <b><span id="serversString">example.com</span></b>.
!         <br/>
          Active POP3 conversations:
              <b><span id="activeSessions">0</span></b>.<br/>
          POP3 conversations this session:
              <b><span id="totalSessions">0</span></b>.<br/>
+         </span>
          Emails classified this session:
              <b><span id="numSpams">0</span></b> spam,
***************
*** 322,341 ****
              <input type="text" size="26" id="input" name="from_parm_ini_map"/>
          </TD>
!         <TD id='helpSpacer' rowspan='100'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
!         <TD id='helpCell' rowspan='100' valign='top'>
!             <p>(Help text goes here.)</p>
!         </TD>
!     </TR>
!     <TR id="configRbRow1">
!         <TD align="right" nowrap='1'>
!             <span id="label">Label</span>:&nbsp;
!         </TD>
!         <TD>
!             <input type="radio" id="inputT" value="True" name="from_parm_ini_map"/>True
!             &nbsp;&nbsp;
!             <input type="radio" id="inputF" value="False" name="from_parm_ini_map"/>False
!         </TD>
!         <TD id='helpSpacer' rowspan='100'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
!         <TD id='helpCell' rowspan='100' valign='top'>
              <p>(Help text goes here.)</p>
          </TD>
--- 323,328 ----
              <input type="text" size="26" id="input" name="from_parm_ini_map"/>
          </TD>
!         <TD id='helpSpacer'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
!         <TD id='helpCell' valign='top'>
              <p>(Help text goes here.)</p>
          </TD>
***************
*** 351,356 ****
              </div>
          </TD>
!         <TD id='helpSpacer' rowspan='100'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
!         <TD id='helpCell' rowspan='100' valign='top'>
              <p>(Help text goes here.)</p>
          </TD>
--- 338,343 ----
              </div>
          </TD>
!         <TD id='helpSpacer'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
!         <TD id='helpCell' valign='top'>
              <p>(Help text goes here.)</p>
          </TD>
***************
*** 392,396 ****
  <tr>
      <td class='banner'>
!         <a id='footerHome' href='home'>Spambayes Proxy</a>,
          <span id="timestamp">Mon Dec 30 14:04:32 2002</span>.
          <a href='http://www.spambayes.org/'>Spambayes.org</a></td>
--- 379,383 ----
  <tr>
      <td class='banner'>
!         <a id='footerHome' href='home'>Spambayes Web Interface</a>,
          <span id="timestamp">Mon Dec 30 14:04:32 2002</span>.
          <a href='http://www.spambayes.org/'>Spambayes.org</a></td>

Index: ui_html.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui_html.py,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** ui_html.py	4 Apr 2003 01:11:57 -0000	1.7
--- ui_html.py	19 Apr 2003 01:11:27 -0000	1.8
***************
*** 5,81 ****
  
  import zlib
! data = zlib.decompress("x��[{o\033�\021����\016�-��Q[��$��Ң��ԇ&\027�ֵ8\034\016\001��$ֻ��>,��}��\014�]�Ê\
! �C\037@���.��p8��\014��7�\037.f?�\\����w��7ﾻ`��p�׳���rv�\033^\014F'l��$�\
! �T\011����&�\"��S�\020?\013YD��p��7/�Ky<�[��\037r���BdK�\020�!u�1y��/s\
! \025n�'�TI1f�\037=c<�<:b�F��\021[��A\024r��Y̳�L�l�~�����a�=�a��b�� ��W\
! |\034��\036�/T��1��\010~\026���\017\022V-�'Z��\001�U��\032�\030-��6X\000C\")\0307�\035o�\\��ǹ�B��\
!  ņf�tI�O\036i�\006s�$4ɜ/�W�*�\020fZ�\004�t�R\036�2YM_V_�#�\004\032'/Ͽ��U?s��\";\
! .T\012M�#�U$C6��f_��*\012\025w�\022߸��\020��\010�wv����Z�'/�!\026y�WB�W�\002m�+\036�\
! %dZ\016����b��g�Z��2��oG��mdX�A\017^>s\007\"�@�%��r��輇\017W �\025���oP��\033\
! ��ƛ��(}4{�\011T\016-��*�T�ӳ__M�Z�vPt:�\"��(2���*����O���c)��S\
! \\������yE�[�~�/����8\034�JBD��_<z�����-\"��S_\033�\037��<�\011�\000�\020��\013\
! &2^�<[L}�f��K��H�����y,�0\022�0x����\034�\000\012\015jf\"�\013v��di��rQ|��[�׏\
! [Cq��C\025\013�\012��3��\011��\017���d���\001\023Kh��✕r�>��r�\001\004�%�\022C\0221�Ʌ�b�\
! ��3V��;Y�\010���\005�\036�v��\005�\006����RF�M\026*\024A�\005=\035�P,e\002�/ւEJ�\037�$<^\012\021i\
! \022jI-%F\014i#�}[��Nd�|\007����\003x}U�@*A�r\034A�KO\027B(�\004D\007��c��\005*6L\014~*�i\
! TF�^\024�DV&���Q)\026nA�\020@�h��.\012�h\027k^4���5s,Ǐ��);�^F,\014�\006S��`��(\012\
! aY�c\027*NU\002��aqZ�7��\"\012߁1\032!2��\027\003?�O�\015`�A��\003�\"��c5�\033�\034Xi��\033���L\
! ���=�\007k��*�%8ف�q�\027k-�J�4*\021\"�Q6s��g���E%F\021�O\031Z�\013�:\"y�\005,\020'e7\
! �b\015��p\007t��\007�a�*�k�\012���4\"N�j��ݨ잂<�ԽBY��#\004�b�\011��6/@B�24a�\
! i268�IZ\026d\016u\027�\025�T\000�\001��@�RT�\036C6�NF�ИV�g\01469g[U:ªU\010�m��8�V�\
! qc�h�����u�ޫ\021��\\[\012b��]gl#]\005|�ݨS\015G��}��#O1�\002��\014�\005t\016�2+���9\
! \016��M�JEr�\031g�\0351/+�C\010`<<8ܓR�\026@�f`��\012���\016��d�\014�\012\022\033Իk7>x\036\025���\
! _m�.E\030��\014e���\034.\006D\015��]�y�\022��_\\�e���!�Y'~\030[�S��ƴѦ�O�\022�x��-�\
! �A+\007�E��������K\016p��\025���@#Y��\0014\011��T�'�V�_{PMm���勌\027�Ϥf\
! \013|��$�� �#\030�2\025E�\003\030�\000�?�Z�\012�@Z�C���-PN89\022#���B\024G���\011�\035�`���7�\
! \032�p�*q��\025�\024�!&bS�ۖ���K�(���\033�\004�4�6[&x�m;�7\"\002o�]���\004�ZX�C\001\037�\
! :���z=y^̀P Cw7I-Pp��\027\020 \012ߠwuxr\000�i��6i�o����}�\020Q\004#\027�����*�`\002\
! �Ӓ�V�5޼��zp�\012\030��f���\020�\010�t(�\022\024�\002���\"\010\016B���#��u�\001�G.���\007�\
! �\022�5��\013^��ƙf���\017a\014\021/}�`��xȧ�h\026\015+h��\006_�\010�e\030$�#x���*/�1Wn�\024h\
! OM\007�?��@z`Ih\012V'\015\024�ǀ57{;��S�G訃wҋ\025�\005�\007\005�.,�\010�#.�b��uAv\003�\027�\
! �Y�A��l�\006�{h�ޡ��j�D���\031>{&/�z�B]\025��6?�禂��wM�{*�x�^B\002-�F��\
! \0177g:�@���'\001\031M�Ak�\015������\027�����<&�yp�n/�%g��D\010�f\025\005\023E �\035B\003Wa�\
! �z\003��5���L�A E��|�2\033wjN��\004�S��\005.��\004]��i�z��i\012U�h�Y�b�\006�;r)\
! 1X�9IRƘ+��3�\026\037�\036v�\035���\037���DkXI/�k����+�ЅISk%���5\007rޤ�\034s�\
! \035�n�hq�JQ+cA�g�)��\022��q����\030�{��T�?��R�v9d[\017�\"���ڝ���G��\013�\023\
! �4 zL\006�:gl-\037��6/D\014\016����\026pS1�3����Y;P\004\\XA\030�rrB`�G?�'u�i\006��\011;\
! h��F�f�\014^;��PY��B>��\020�\0120'�\033�bEHzI\035+�\003��s�@�C�U^��#+\021�Rь��\
! -}V�Q$$�*��s�BQh�HGw �Va\000\013%\020\016uE�\030\035&�[�R��胫\005��@�j\010�\027k����A\
! f�)�\0010���E\001�X\002,\026��\023�*��*\011��\031R�!\037\007�\010��K�\024�\017�*0�\031#\030=\024���I��\
! w@�c2K�\020�\032\017�A�2_�,dCF��\023�\001�F%`�j\0114\027��\032���z%��\016\034����\005\036+�\004�T��\
! ԥ�cX\003(\005��?^�\034�7\011>%=�Z�!�\025����\017RT \006�l�N���k�;\010$��z���;\\�\011\003\036\
! ��\001\026�s\027�:���A^�cYX\016V���\015\011��+O���\006�JH�8��P��\037�8q�\015Т]�>\\�\024\
! �c�{���\014<� �x�\013\0201u��\006Z�-w���.\013�����\003�o�`8�|�������L�Y&Z3U�}\
! �\001��C(H9g�\024&>���%;�l��\001\034\017���=Κo\006�HV��\005SvzX\017�Ԕ\"i��5�����;�\
! ؁���s&ل��\011��o{�����U9 p*`\003\021\034���y�;=��\003�\037�\034��B��vE�);��V\015\
! �/�D���~5�s�\022ɴ��P��Fd\027\020\006\016\016\017��?�&H�\007�\031̟��g\015�4_9���\030\016��N6\
! HY��N7\037�f~��4|�����=B��a��p\"�]9�1��J\002\000\013����Z�3< \036\023F�$�8�m��\
! '�-ۍ#*p\016j��\024\015\033���\026���qmS>��\037A��Q\005��\013�w����\032�=���~\005%�mD\007>\005\
! \025��D\006�4\017z�f̓޲@���������\001{f��o�=��;CI`I�zs �ao/�\032̭\030;8\017���\
! f�2�����o�\017['X��\015,�}�[�XK��e\022�a`53�7\000\007�'�$T�(;T\014l_`\015\"�;U�\
! N(�x(��`�\022�c2�?]��\037���P������\012^���\016&P�:����\005L�ܐ\016��Y\006(\035u\030\
! �g�S�\002��v\026���sp�'N\013�G9�n��G<�G�\013jx�kT�\037��\010e�Ai\017�oe�\035i[�f��S\
! �����Ӏ�K�me\032)\036v�<\012A�yU�$�4��\021C�\000$FK�˨�)�\012��8�\005�N�JR\011^�f��9\
! N¦��1\036�\004��b�\022�j���<#ԓ�{�����$\010ё����1\004�/����\034\013�Y\002\012F\007\001&T\036R�\
! 5v+��D!_�f���Lm�q��\002����@�\027�ӝ�9����Q\033K\037x߬��6�\001���kM]z�/$w\
! ��Zm��'ya���2V��\001V\037̞�z��X���\001���c\017�\016c��\002!��\036;E\026���v]�f��\
! �\003�\"���\017�.\"l \027�s)�m�\035T͵)૿�+�+Bl��{��NR���?�l�ޅ~�\000\010\023�՜\
! ��\003��O�]�\022b�A���u:x���z�8֫�1ٽ���\026�\"2��%�v�\022��W\004�\022�+x\
! ��W��f\013��/�90\002\034��V��V�\025�\026��+;'�gO\024�kR�)�+B/^�z��M��|.!���BM\
! �R\027��^�����)\0242h\035i�q���\027�\006����OL�%��Z��!\"<!�V'�HG���^ ��\036��w\
! �,�\031Ӡ4�\022\007��\034s�\0179#����\007[)s\034v�\"y/�����,Yuhw�^\024�O����-1֝��\007\
! �.z��\033�x��޾�\011������}�\026d\032��\004�\031���>@�\003���(�,����px\017��#�o:f\
! \037����Z��td�\021��\006�\027�����Q<���\005jO�\\�^���\017�ﭳ��Z�P)��ux\036:<�s�\016\
! k�X<\005 @�c*��`�R@�\034���^m�+T榚[��@��\\�NP�x@�����醑��<�k���w�\
! �5�_?\030�s�aj^5,�3r���\035R���7ﮜ>�G�=G��[w\0248���F\015dvi��G��e���\
! V�F|.\"/x�\037�\016g��~vٜg\007\0147�o����W\036�B�&��\030@m�\021|�ǘ�^\023��'�MY�(�m\
! ^`u\037�\"]�8\031��`�\031�\016r�VD��S�l\026}]�0�\013�mˢ�\036���m�����G��\022Vg�f�=�Y\
! �>��\015��&��r�Δo�)��(�9'u��Ҝ�����c哓�\015!{�Z[z_Du7���ty�\032�\036�\
! ���~���8\030��,�/Tfw�٫��\002���\013R�Ӷ\032Պc\0130�Q~pQf\031�A\014�sܳ\036G�̚�H��\
! �P@)���U\000�ŨS��n�,ݾC��]d�/�Q��ⵡ�:5�:���Q�;� �\032�WD�\013\0048�c\003\
! �dB\003\013��\004�;��W�u�i�!�&��b��/�/�.�Pm���V_�h�����μ#0���T8�ַ��\
! ���.��-|�\023d�\012����8\007�w3c� X�3\032=�;)�8�ǰ��f�C\000_ό��o\000�\032J��?k��\
! �2瞕��\000X�\005�U\002��`g#v�b<z1>;e��ѩ���1���(��p��l\006��p����a\000�ە\
! ں4�-����&\021�D\007�0��\000�Î2�ܦ�\000�׭R�b\002�\011{\016\0228gv0\026\0125�&%�S!��\000���\
! ��\033(�Ǘ�\004\015B\006h")
  ### end
--- 5,80 ----
  
  import zlib
! data = zlib.decompress("x��[�o۸\025����\037x\032Z%Xb;I��\034[X��a�5K|\033\016�CAY���$j\022\025�+���GR��$u\
! w�\006,-bK$\037\037\037���/df�\\��X�xsŮ\027�޲�\037޼��\005��㿝]�Ǘ�K��b49a��ge\
! �b��d<���\013��j�QiB��G��b�\010\026Gs��y�]�Ӑ�D�~(E���)Q��R���\001ǔjG_B\
! \031��'������O�1^�<9b�6.�#�\021ɃP񒟳�\027�8��\011���_)\036”{���+Y�зE��\
! �4��{x���,��7\023�YR#�>İj\021=Һ�\017�������d�¶�\022\030\022�b�0w�\025�z\003<�2���\
! C,�4s�K\006|�Ds7\012y��$!_ޯ\013Ye\021̴�\010���<��l=Y=N�\012h��<��+V����Dq\
! �d\016M�GV�$�X�\000͡~�TJ����7�61D<��?\004�;;{�Zv#哗Ԑ���k��K�@;����\
! \022\012-\007xGcK�Dͳ{�yt��ͷ\023�wζq�6�\007/��\003�c ۑ�j��br>��+��\012��=4hx�\015\
! WF���@r�4{^\010T\016-�\015*�T��sX_M�F㞠�tz�\030�C\025q.>�L�gK?�\022���U|\015H\
! q=�7��g�5�o�����fc\013\025��\001\034�JBD��/\036�C�Ϣ��-\023^�s_\033�\037��2�\031�\000hH��\
! Y��YY,�~3Z�+��$^gs��e\032GQ\"�q�<\013��\034�\000\012-jf\"�\013v��dy!�j���i\013\026�&B\
! \027\025���\031�5�2\025�%\036�\024b\005\023��\037\\��٘\017O\007���\\���U�\010���z�\001\004�%��C\022)��\013m�\
! �Y�g�[�y�y\021\000�za�ϰ-/�\015ȃ�&.�*N�\021�-e$��\013z:b�X�\031\010Am\004K��?�Yt�\022\"\
! �$�Z*�\034���}ۈ�N\024\000�#�\026��\001�_V�&�Ǡ�%� ?����%\024\002��`�*�\022\025\034&\006���\
! <�\022N/�&QT��S\000,ɢ\035\010\024\034I���MA�\020m��͗\036��c%~����1�2ba07�,�\007\014H�R\
! ²��.e��\014�]��\004ov�D\022�\005�4Bd�\026_\012� �\"\033��C\034Y\016,�\000��2�\005�\007V��\010�\011�Y�\
! 1)�\007�`m��\\�e\014`;�4��r��Y\013�FeBD%�&\024Z|Fz\033\\Tf\024���#˰��#�w(`�8)��\
! �\015���\016�\032��f��U��H\025v��yB�l�V��=9{��X��b\025ʏ�\020�F\023��]^��~eh�\000�\
! dlp\026gy��\034�.\036S�\\@�\003���%���=��6�N&�ؘV�g\0146�d;Y9�jT\010�m]�4�J+ٴ\
! �z�J�?����{5�5�� \006��\005e���\000���>�p�_��s�\020�b�\005�3\033c\013�\034�e����9\016�\
! �͙�Ev�\0310���W(�\020\034\031�\016\016��\024�%\020j\030\030!P\001^��\000��K&/\000W�ب�]����D�\017o��\
! O)�\030�w6�����p1\"j�F�b���,\013�%�A�z����$�6��6E8Q���k��@;:�\
! \022x\027e�\033�E���+\016a5\017%���R!za���\021~ �\004�?b��\023`+�o\020TS[\0252e��\012�,�l\001��\
! ΢�\017B\034AwW�$\001\036��\004\000���\012�@Z�Ch~̖('�\034����\033!�\021S�<��c\033,W\032��\\\003\010g�\
! \012\027\016�H�\010���m\003�\035!\035\023Jk/X��\033�\004�4�6;&x���\033�\000Zb\027��=��\010\013zH�\003�\023;�� \
! ���\014\030\012\024\010w��\006\012n��\005\024\030Eo\020]\035��@�4{V�t�o�*7���R$\011�\\b��7���`\006Q�%\007�\
! ^g�y�����s�\024b(��\021�\010�\010��(�1(�\005��EPX\010y�ߡ�\001��\023\020 =q�@m~\020eZb��\
! 7K�UU�x�\014|1���a�K�m���xȧ�h\026\015+�\004k-��\021\024���d���\012��R\015�\\���@{\032:`\
! �%L\007�\003KBS�:iB�f\014Xs����:��\010\035���\006cE�\000� ��EU��ą�Xdd!�n �B]1k6\
! Q{X����\036��w���Z7Q�q�Ϟ�\017�\036@���������V���]S�\036�$>�.!���V���7g\
! �\0321~�\020I@F�0�\014�\001�]�\021xz������c6\016�#w{�/��l\023�X��)\030/\002��\020\0329�7�ǟ�\
! ��\017Bs\013���h7�i�^�99\015�\023\020�BO/py\036u&�S�h]��OM����~���'��S�\020�E�*F�\
! ��Y�b�Й������a��Q��\016�!+�Bt�U����\005ʃ\011�2pb�>uV��O;s �m��1��!\
! ���@ Ÿ�tM����\033�twƸ8�NS�\002@�V��)h�\025\002,\033�.������$`��\003�\006D\
! �iA�d����C�ܕJ�\000�&\002�h\0017�\003=�\037\\��5�b腵��+'�\031ֈ�Y��\005�\005ď�\000���i\
! �ȵh��\032�J%�:\033��RW\016�i)0'Q\032l�\"$�����A\034�K�@�Lmdِ�#k\0215Rь��-}��\
! Q$$����\031񘅢Іc\036݁�Z;\004,��cԵ\011ct�f��J�+#\032�\0136e�z��x/6byOK�\034���\
! \015`�\031VJ�,V\020 \013L��Q]\037�\002V\014��\005R�!3�P\021���b%\012\037�V�`�4F0z(z�#��\033t@�c\
! ZK�\020�&2Ѓ.�rɋ��\031Q�O�\003��J�l\035\023h.i%M��G땔:��\017\024��\020d-�a/\025�9u��\
! \030�\000J\001��\037�\026��T��\037\023G\021�-\014Khs\037�(A\014\030���:1�'��?A \003�������:�0a\004��\
! �\006�܏|�H��AY�i�,\007k������\017\025���pw��\025$d\034��(.�? q�TB[዆�}�@)��\
! ����K\031x\014 ��s?T�$�H[qcc��\"���0=\036��\037�~�\007��웟.._/^�dR�*Ӛ)3�\011\007\
! 8��� �\\HS����\023��\001��U\012a�\010�(����f��l\015YY0g����Om)���;C:���׍\035\
! ��qr�b6�af\002x���\036���oU\011�8���\010��)�y�;=��\003�\037\016\034��B�vE�9;���\015�\
! /�D���a5�s�bɼ��Hɷr+�\013p\003\007���џ�&H�\003h\006�\027�\030X�?ۯ�G��|��?�ܤ\035�\
! ,{������\037ts\016�f�:�s\017��\005\014@\013�\003�U��Y��\022\002���u�NP�K�G�S��z�(�����#\
! ͖�֡\025���\026<G����q��X۴�)\037y��Si�\002��\005�;���G��\036��o��\022�6�\003���\012\
! �F\"�_�G>Z��`�@�.g8�~+�M�����Ûe�\003���P:XQ��\034My��\013�\006s+�N���]�\
! e�\\��طLJ����:\007��>x�m��Ă]�Y\004��u͂��\001�\016b�\014�Q]��Q1a�\022�\021�߫��\
! \\y��XZ\017f,a7%#��Տ�\016\0149��\032�*�o�k�����`\002��k�)=�wY���u����e��Q�\001\
! |��O�Z`���b��~\016���i\011�(Gx��„g�hrA\023��j�ӏ}J\024e�Ai\017��d�=i���\010M�\
! \006�����\001՗�ݪ<�<���(\004��՞������\017e\002\"1ZRZ%*�y����+nA�*�b�&͸�s\
! ��M\026\037R<*\011 jJ�^L�����PO�ﭲ��F� DG��\013:�\020��l72�s,��2P0:\0220��R\
! ��[��H\024�EnfR�_\024r\013�}�K�s\037O\006a_LOwv�|S��\007m,C��v\003\010��\007�\006�\\k���|!�\
! �'�5��y�\027�oC�*c�n\037`���9��\032\017h+,\035`p\034J<\000A��X&�l Du�c��\022gn��T�Y!\
! R�@�\011�C�ý�\010[�\005�R�b7l\007usc\012������\020�<+)��(�����$�?�twa\030\025 �\004}5\
! 's�(>\032\022�gW�\002_n\"���:\035����f�8֫�1{z�'�-�\012ᔪ\"qd\017N���%N��\010\002%x�\
! �*�+Gu�\015����\020\030\001\016�x��U�ĊmKY�坓ӳG*�\015���65�\027/_=B覐!\017c��v�P\
! �@�R\037��\022�Q\030<�B\006-�v\031\007�\012�`2�ݷ�d�/q.֊oE\011\036�\0211w:9E:�T��\002Q<�xž\
! CfI̘\006�A�8\004\016΁'�\020\030�D\017�O=�Z���#���B\013,D�\006�d��ݡ{e�9�\"\032\013���t*�\036\
! \024O��'\033qc\037�\026ٻ\0274��\\��8����L�Ԑ�z\003�`b(�p�\001��V��Ț:n�f\034�\010��\010�M\007\
! ����Н^�>��\014փ\030�`��p�\032�>�G5���#:W�������w\026�<�` d\016�h\001�C��z��\
! �f��S\010\004�|L\005U\034L(\005\024̹\030W��\003^�2w��r<8�R��t���#��\0275\015Nw�dA'�}��M�\033\
! �6\010�~06'��ܼjY�g�r�\\@�.��o�^9}�\017c\007\016_\027��(\000���V\015dqi\002g���s�\024\035�\
! �\031Mx(\022/x�\037�6g�\000qٞ�0�\\���sN_y4\013�\033o�\023b\010j�\017��\037R�{� �;\031m�F$9l\
! �I\007\036/�>J�#��\020����#�E4�c#�\001\036����\016]�����\007�''�[\035���ޓ!�sw��t\
! �\036�\036�M+��og����\037�\002�J\005Qw��ٵ�����,�*�]Ui�æä5~pQ\025\005��\002�l:�\002\
! G��*\033\\�ci(�\014ڽ�\032Ξb�)\011@7Gzn�1�[����X��׼��L\007�V�6X�3\012v�\037���L5\
! \021�\002�M��r>��0/V�\002��\007�\025l�j�x$��\017��b����l*\025�m6�`��N\017\017K�w�\035�&�G\
! )�p��J6S��#�ˏ�IW�TX{��J\011���)&\\�\0103�<\033��ϜJP4�w\015MI��3c\020�¢G\
! �쀻\027��0���\012��\027��\031lΒ�M�ɋ����씝N&�f\017F-\036̜J���x�ݎJ;�H\026��\
! \010>w�gM�J[hg���\"w���2���\015�bG��G�\016�\036�k�&�Csa�A\002��\016����\004�M��$y\
! �12��U�$�/0�_�")
  ### end



From timstone4 at users.sourceforge.net  Fri Apr 18 19:20:23 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Fri Apr 18 21:20:27 2003
Subject: [Spambayes-checkins] spambayes pop3proxy.py,1.72,1.73
Message-ID: <E196h1j-0006rN-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv26329

Modified Files:
	pop3proxy.py 
Log Message:
Syntax error

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.72
retrieving revision 1.73
diff -C2 -d -r1.72 -r1.73
*** pop3proxy.py	19 Apr 2003 01:11:26 -0000	1.72
--- pop3proxy.py	19 Apr 2003 01:20:19 -0000	1.73
***************
*** 680,684 ****
              map(ensureDir, [options["pop3proxy", "spam_cache"],
                              options["pop3proxy", "ham_cache"],
!                             options["pop3proxy", "unknown_cache]"])
              if self.gzipCache:
                  factory = GzipFileMessageFactory()
--- 680,684 ----
              map(ensureDir, [options["pop3proxy", "spam_cache"],
                              options["pop3proxy", "ham_cache"],
!                             options["pop3proxy", "unknown_cache"]])
              if self.gzipCache:
                  factory = GzipFileMessageFactory()



From anadelonbrin at users.sourceforge.net  Fri Apr 18 19:45:23 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 21:59:31 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.25,1.26
Message-ID: <E196hPv-0008Uf-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv32621

Modified Files:
	imapfilter.py 
Log Message:
Improve documentation for imap options.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.25
retrieving revision 1.26
diff -C2 -d -r1.25 -r1.26
*** imapfilter.py	19 Apr 2003 00:11:33 -0000	1.25
--- imapfilter.py	19 Apr 2003 01:45:20 -0000	1.26
***************
*** 71,74 ****
--- 71,78 ----
      o The flags should be copied along with the message (especially
        the /Seen flag, but all of them, really).
+     o Should the imap options server and port be combined?  i.e. instead
+       of having server=imap.example.com and port=143, have
+       server=imap.example.com:143?  This would be more consistent with
+       pop3proxy and would get rid of one option at no real cost.
      o Suggestions?
  """
***************
*** 413,417 ****
  
      if not (doClassify or doTrain or launchUI):
!         print "-b, -c, or -t operands must be specified"
          sys.exit()
  
--- 417,422 ----
  
      if not (doClassify or doTrain or launchUI):
!         print "-b, -c, or -t operands must be specified."
!         print "Please use the -h operand for help."
          sys.exit()
  



From anadelonbrin at users.sourceforge.net  Fri Apr 18 19:45:24 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 18 21:59:34 2003
Subject: [Spambayes-checkins] spambayes/spambayes ImapUI.py, 1.2,
	1.3 Options.py, 1.29, 1.30
Message-ID: <E196hPw-0008Uo-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv32621/spambayes

Modified Files:
	ImapUI.py Options.py 
Log Message:
Improve documentation for imap options.

Index: ImapUI.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/ImapUI.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** ImapUI.py	18 Apr 2003 22:48:57 -0000	1.2
--- ImapUI.py	19 Apr 2003 01:45:20 -0000	1.3
***************
*** 144,147 ****
--- 144,152 ----
              name_attributes = fol[:m.end()-1]
              folder_delimiter = fol[m.end()+1:m.end()+2]
+             # a bit of a hack, but we really need to know if this is
+             # the case
+             if folder_delimiter == ',':
+                 print """WARNING: Your imap server uses commas as the folder
+                 delimiter.  This may cause unpredictable errors."""
              folders.append(fol[m.end()+5:-1])
          folders.sort()

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.29
retrieving revision 1.30
diff -C2 -d -r1.29 -r1.30
*** Options.py	19 Apr 2003 00:02:13 -0000	1.29
--- Options.py	19 Apr 2003 01:45:21 -0000	1.30
***************
*** 836,849 ****
  "imap" : (
  ("server", "Server", "",
! "", r"[\w\.\-]+(: [\d]+)?", False, False),
  ("port", "Port", 143,
! """The default IMAP port is 143, or 993 if using SSL""",
  r"[\d]+", False, False),
  ("username", "Username", "",
! "", r"[\w]+", False, False),
  ("password", "Password", "",
! "", r"[\w]+", False, False),
  ("expunge", "Purge//Expunge", False,
! """Permanently remove *all* messages flagged with //Deleted on logout""",
  (False, True), False, True),
  # IMAP seems to allow any character at all in a folder name,
--- 836,875 ----
  "imap" : (
  ("server", "Server", "",
! """This is the name of the imap server that stores your mail,
! and which the imap filter will connect to - for example: mail.example.com
! or imap.example.com.  If you use more than one server, then things are
! a bit more complicated for you at the moment, sorry.  You will need to have
! multiple instances of the imap filter running, each with a different
! server (and possibly username and password) value.  You can do this if you
! have a different configuration file for each instance, but you'll have to
! do it by hand for the moment.  Please let the mailing list know if you are
! in this situation so that we can consider coming up with a better solution.
! """,
! r"[\w\.\-]+(: [\d]+)?", False, False),
  ("port", "Port", 143,
! """This is the port of the imap server that stores your mail, and which the
! imap filter will connect to.  The default IMAP port is 143, or 993 if using
! SSL, you will probably have one of those values here.  If you are using
! multiple imap servers, please see the comments regarding the server value.
! """,
  r"[\d]+", False, False),
  ("username", "Username", "",
! """This is the id that you use to log into your imap server.  If your
! address is funkyguy@example.com, then your username is probably funkyguy.
! If you are using multiple imap servers, or multiple accounts on the same
! server, please see the comments regarding the server value.""",
! r"[\w]+", False, False),
  ("password", "Password", "",
! """That is that password that you use to log into your imap server. This
! will be stored in plain text in your configuration file, and if you have
! set the web user interface to allow remote connections, then it will be
! available for the whole world to see in plain text.  If I've just
! freaked you out, don't panic <wink>.  You can leave this blank and use
! the -p command line option to imapfilter.py and you will be prompted for
! your password.""",
! r"[\w]+", False, False),
  ("expunge", "Purge//Expunge", False,
! """Permanently remove *all* messages flagged with //Deleted on logout.
! If you do not know what this means, then please leave this as False.""",
  (False, True), False, True),
  # IMAP seems to allow any character at all in a folder name,
***************
*** 851,854 ****
--- 877,881 ----
  # we don't allow this.  If anyone has folders with commas in the
  # names, please let us know and we'll figure out something else.
+ # ImapUI.py prints out a warning if this is the case.
  ("filter_folders", "Folders to filter", "INBOX",
  """Comma delimited list of folders to be filtered""",



From timstone4 at users.sourceforge.net  Fri Apr 18 20:09:52 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Fri Apr 18 22:09:54 2003
Subject: [Spambayes-checkins] spambayes/spambayes ProxyUI.py,1.1,1.2
Message-ID: <E196hnc-0001fe-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv6408

Modified Files:
	ProxyUI.py 
Log Message:
Added a couple of missing imports

Index: ProxyUI.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/ProxyUI.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** ProxyUI.py	18 Apr 2003 09:24:29 -0000	1.1
--- ProxyUI.py	19 Apr 2003 02:09:49 -0000	1.2
***************
*** 62,69 ****
--- 62,72 ----
  import time
  import bisect
+ import cgi
  
  import tokenizer
  import UserInterface
  from Options import options
+ import spambayes.mboxutils
+ from email.Iterators import typed_subpart_iterator
  
  global state
***************
*** 345,349 ****
              # info object for each message.
              cachedMessage = sourceCorpus[key]
!             message = mboxutils.get_message(cachedMessage.getSubstance())
              judgement = message[options.hammie_header_name]
              if judgement is None:
--- 348,352 ----
              # info object for each message.
              cachedMessage = sourceCorpus[key]
!             message = spambayes.mboxutils.get_message(cachedMessage.getSubstance())
              judgement = message[options.hammie_header_name]
              if judgement is None:



From timstone4 at users.sourceforge.net  Fri Apr 18 20:11:57 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Fri Apr 18 22:12:01 2003
Subject: [Spambayes-checkins] spambayes pop3proxy.py,1.73,1.74
Message-ID: <E196hpd-0001oo-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv6973

Modified Files:
	pop3proxy.py 
Log Message:
Converted to use the new SBHeaderMessage class.  Note that this currently
does NOT implement notate-body, so for now it will not work with at least one
very dumb mailer (which shall remain unidentified, but whose name rhymes
with 'poutlook rexpress').

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.73
retrieving revision 1.74
diff -C2 -d -r1.73 -r1.74
*** pop3proxy.py	19 Apr 2003 01:20:19 -0000	1.73
--- pop3proxy.py	19 Apr 2003 02:11:54 -0000	1.74
***************
*** 146,149 ****
--- 146,150 ----
  from spambayes.UserInterface import UserInterfaceServer
  from spambayes.ProxyUI import ProxyUserInterface
+ import spambayes.message
  
  # Increase the stack size on MacOS X.  Stolen from Lib/test/regrtest.py
***************
*** 481,568 ****
              ok, messageText = response.split('\n', 1)
  
              # Now find the spam disposition and add the header.
!             (prob, clues) = state.bayes.spamprob\
!                             (tokenizer.tokenize(messageText),
                               evidence=True)
!             if prob < options["Categorization", "ham_cutoff"]:
!                 disposition = options["Hammie", "header_ham_string"]
!                 if command == 'RETR':
                      state.numHams += 1
!             elif prob > options["Categorization", "spam_cutoff"]:
!                 disposition = options["Hammie", "header_spam_string"]
!                 if command == 'RETR':
                      state.numSpams += 1
!             else:
!                 disposition = options["Hammie", "header_unsure_string"]
!                 if command == 'RETR':
                      state.numUnsure += 1
  
-             if options["pop3proxy", "strip_incoming_mailids"] == True:
-                 s = re.compile(options["pop3proxy", "mailid_header_name"] + \
-                                ': [\d-]+[\\r]?[\\n]?')
-                 messageText = s.sub('', messageText)
- 
-             headers, body = re.split(r'\n\r?\n', messageText, 1)
-             messageName = state.getNewMessageName()
-             headers += '\n%s: %s\r\n' % (options["Hammie", "header_name"],
-                                            disposition)
-             if command == 'RETR' and not state.isTest:
-                 if options["pop3proxy", "add_mailid_to"].find("header") != -1:
-                     headers += options["pop3proxy", "mailid_header_name"] \
-                             + ": " + messageName + "\r\n"
-                 if options["pop3proxy", "add_mailid_to"].find("body") != -1:
-                     body = body[:len(body)-3] + \
-                            options["pop3proxy", "mailid_header_name"] + \
-                            ": " + messageName + "\r\n.\r\n"
-             else:
-                 headers += options["Hammie", "header_name"] + "-ID: Test\r\n"
- 
-             if options["pop3proxy", "include_prob"]:
-                 headers += '%s: %s\r\n' % (options["pop3proxy",
-                                                    "prob_header_name"],
-                                            prob)
-             if options["pop3proxy", "include_thermostat"]:
-                 thermostat = '**********'
-                 headers += '%s: %s\r\n' % \
-                           (options["pop3proxy", "thermostat_header_name"],
-                            thermostat[int(prob*10):])
-             if options["pop3proxy", "include_evidence"]:
-                 headers += options["pop3proxy", "evidence_header_name"] \
-                            + ": "
-                 headers += "; ".join(["%r: %.2f" % (word, prob)
-                          for word, score in clues
-                          if (word[0] == '*' or
-                              score <= options["Hammie",
-                                               "clue_mailheader_cutoff"] or
-                              score >= 1.0 - options["Hammie",
-                                                     "clue_mailheader_cutoff"])])
-             headers += "\r\n"
-             
-             if options["pop3proxy", "notate_to"] \
-                 and disposition == options["Hammie", "header_spam_string"]:
-                 # add 'spam' as recip only if spam
-                 tore = re.compile("^To: ", re.IGNORECASE | re.MULTILINE)
-                 headers = re.sub(tore,"To: %s," % (disposition),
-                      headers)
-                 
-             if options["pop3proxy", "notate_subject"] \
-                 and disposition == options["Hammie", "header_spam_string"]:
-                 # add 'spam' to subject if spam
-                 tore = re.compile("^Subject: ", re.IGNORECASE | re.MULTILINE)
-                 headers = re.sub(tore,"Subject: %s " % (disposition),
-                      headers)
-                 
-             messageText = headers + body
- 
              # Cache the message; don't pollute the cache with test messages.
!             if command == 'RETR' and not state.isTest \
                      and options["pop3proxy", "cache_messages"]:
!                 # Write the message into the Unknown cache.
!                 message = state.unknownCorpus.makeMessage(messageName)
!                 message.setSubstance(messageText)
!                 state.unknownCorpus.addMessage(message)
  
              # Return the +OK and the message with the header added.
!             return ok + "\n" + messageText
  
          else:
--- 482,513 ----
              ok, messageText = response.split('\n', 1)
  
+             msg = spambayes.message.SBHeaderMessage()
+             msg.setPayload(messageText)
+             msg.setId(state.getNewMessageName())
              # Now find the spam disposition and add the header.
!             (prob, clues) = state.bayes.spamprob(msg.asTokens(),\
                               evidence=True)
! 
!             msg.addSBHeaders(prob, clues)            
!             
!             if command == 'RETR':
!                 cls = msg.GetClassification()
!                 if cls == options["Hammie", "header_ham_string"]:
                      state.numHams += 1
!                 elif cls == options["Hammie", "header_spam_string"]:
                      state.numSpams += 1
!                 else:
                      state.numUnsure += 1
  
              # Cache the message; don't pollute the cache with test messages.
!                 if not state.isTest \
                      and options["pop3proxy", "cache_messages"]:
!                     # Write the message into the Unknown cache.
!                     message = state.unknownCorpus.makeMessage(msg.getId())
!                     message.setSubstance(msg.as_string())
!                     state.unknownCorpus.addMessage(message)
  
              # Return the +OK and the message with the header added.
!             return ok + "\n" + msg.as_string()
  
          else:



From mhammond at users.sourceforge.net  Fri Apr 18 20:26:38 2003
From: mhammond at users.sourceforge.net (Mark Hammond)
Date: Fri Apr 18 22:26:42 2003
Subject: [Spambayes-checkins] spambayes/Outlook2000 addin.py,1.53,1.54
Message-ID: <E196i3q-0002o6-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/Outlook2000
In directory sc8-pr-cvs1:/tmp/cvs-serv10721

Modified Files:
	addin.py 
Log Message:
Work in non-English locales


Index: addin.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/Outlook2000/addin.py,v
retrieving revision 1.53
retrieving revision 1.54
diff -C2 -d -r1.53 -r1.54
*** addin.py	18 Mar 2003 05:32:45 -0000	1.53
--- addin.py	19 Apr 2003 02:26:36 -0000	1.54
***************
*** 54,57 ****
--- 54,64 ----
          import win32traceutil
  
+ # Set our locale to be English, so our config parser works OK
+ # (This should almost certainly be done elsewhere, but as no one
+ # else seems to have an opinion on where this is, here is as good
+ # as any!
+ import locale
+ locale.setlocale(locale.LC_NUMERIC, "en")
+ 
  # Attempt to catch the most common errors - COM objects not installed.
  try:



From timstone4 at users.sourceforge.net  Fri Apr 18 21:46:59 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Fri Apr 18 23:47:03 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.12,1.13
Message-ID: <E196jJb-000869-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv31121

Modified Files:
	message.py 
Log Message:
Converted to use the new options style.

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.12
retrieving revision 1.13
diff -C2 -d -r1.12 -r1.13
*** message.py	19 Apr 2003 00:51:02 -0000	1.12
--- message.py	19 Apr 2003 03:46:56 -0000	1.13
***************
*** 176,179 ****
--- 176,182 ----
          Nicked the regex from smtplib.quotedata.
          """
+         #XXX Tim doesn't like this regex.  He will study it to
+         #XXX see if he can learn to like it, or come up with
+         #XXX something he likes better.  - Tim
          return re.sub(r'(?:\r\n|\n|\r(?!\n))', "\r\n", data)
  
***************
*** 194,202 ****
      def GetClassification(self):
          if self.c == 's':
!             return options.header_spam_string
          if self.c == 'h':
!             return options.header_ham_string
          if self.c == 'u':
!             return options.header_unsure_string
  
          return None
--- 197,205 ----
      def GetClassification(self):
          if self.c == 's':
!             return options['hammie','header_spam_string']
          if self.c == 'h':
!             return options['hammie','header_ham_string']
          if self.c == 'u':
!             return options['hammie','header_unsure_string']
  
          return None
***************
*** 206,217 ****
          # may change, which would really screw this database up
  
!         # an unrecognized string here is interpreted as unsure.  Should
!         # that condition actually raise an exception instead?
! 
!         if cls == options.header_spam_string:
              self.c = 's'
!         elif cls == options.header_ham_string:
              self.c = 'h'
!         elif cls == options.header_unsure_string:
              self.c = 'u'
          else:
--- 209,217 ----
          # may change, which would really screw this database up
  
!         if cls == options['hammie','header_spam_string']:
              self.c = 's'
!         elif cls == options['hammie','header_ham_string']:
              self.c = 'h'
!         elif cls == options['hammie','header_unsure_string']:
              self.c = 'u'
          else:
***************
*** 248,252 ****
      def setIdFromPayload(self):
          try:
!             self.setId(self[options.pop3proxy_mailid_header_name])
          except KeyError:
              return None
--- 248,252 ----
      def setIdFromPayload(self):
          try:
!             self.setId(self[options['pop3proxy','mailid_header_name']])
          except KeyError:
              return None
***************
*** 258,291 ****
          add optional headers if needed.'''
          
!         if prob < options.ham_cutoff:
!             disposition = options.header_ham_string
!         elif prob > options.spam_cutoff:
!             disposition = options.header_spam_string
          else:
!             disposition = options.header_unsure_string
          self.RememberClassification(disposition)
!         self[options.hammie_header_name] = disposition
          
!         if options.pop3proxy_include_prob:
!             self[options.pop3proxy_prob_header_name] = prob
              
!         if options.pop3proxy_include_thermostat:
              thermostat = '**********'
!             self[options.pop3proxy_thermostat_header_name] = \
                                 thermostat[:int(prob*10)]
                                 
!         if options.pop3proxy_include_evidence:
              evd = "; ".join(["%r: %.2f" % (word, score)
!                      for word, score in clues
!                      if (word[0] == '*' or
!                          score <= options.clue_mailheader_cutoff or
!                          score >= 1.0 - options.clue_mailheader_cutoff)])
!             self[options.pop3proxy_evidence_header_name] = evd
          
!         if options.pop3proxy_add_mailid_to.find("header") != -1:
!             self[options.pop3proxy_mailid_header_name] = self.id
! 
! #        print self._headers
!  #       print self.as_string()
  
  # This won't work for now, because email.Message does not isolate message body
--- 258,288 ----
          add optional headers if needed.'''
          
!         if prob < options['hammie','ham_cutoff']:
!             disposition = options['hammie','header_ham_string']
!         elif prob > options['hammie','spam_cutoff']:
!             disposition = options['hammie','header_spam_string']
          else:
!             disposition = options['hammie','header_unsure_string']
          self.RememberClassification(disposition)
!         self[options['hammie','header_name']] = disposition
          
!         if options['pop3proxy','include_prob']:
!             self[options['pop3proxy','prob_header_name']] = prob
              
!         if options['pop3proxy','include_thermostat']:
              thermostat = '**********'
!             self[options['pop3proxy','thermostat_header_name']] = \
                                 thermostat[:int(prob*10)]
                                 
!         if options['pop3proxy','include_evidence']:
              evd = "; ".join(["%r: %.2f" % (word, score)
!              for word, score in clues
!              if (word[0] == '*' or
!                  score <= options['hammie','clue_mailheader_cutoff'] or
!                  score >= 1.0 - options['hammie','clue_mailheader_cutoff'])])
!             self[options['pop3proxy','evidence_header_name']] = evd
          
!         if options['pop3proxy','add_mailid_to'].find("header") != -1:
!             self[options['pop3proxy','mailid_header_name']] = self.id
  
  # This won't work for now, because email.Message does not isolate message body
***************
*** 297,304 ****
  
      def delSBHeaders(self):
!         del self[options.hammie_header_name]
!         del self[options.pop3proxy_mailid_header_name]
!         del self[options.hammie_header_name + "-ID"]  # test mode header
!         del self[options.pop3proxy_prob_header_name]
!         del self[options.pop3proxy_thermostat_header_name]
!         del self[options.pop3proxy_evidence_header_name]
--- 294,301 ----
  
      def delSBHeaders(self):
!         del self[options['hammie','header_name']]
!         del self[options['pop3proxy','mailid_header_name']]
!         del self[options['hammie','header_name' + "-ID"]]  # test mode header
!         del self[options['pop3proxy','prob_header_name']]
!         del self[options['pop3proxy','thermostat_header_name']]
!         del self[options['pop3proxy','evidence_header_name']]



From timstone4 at users.sourceforge.net  Fri Apr 18 22:13:46 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Sat Apr 19 00:13:49 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.13,1.14
Message-ID: <E196jjW-0001Fw-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv4814

Modified Files:
	message.py 
Log Message:
Corrected an incorrectly specified option

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.13
retrieving revision 1.14
diff -C2 -d -r1.13 -r1.14
*** message.py	19 Apr 2003 03:46:56 -0000	1.13
--- message.py	19 Apr 2003 04:13:44 -0000	1.14
***************
*** 197,205 ****
      def GetClassification(self):
          if self.c == 's':
!             return options['hammie','header_spam_string']
          if self.c == 'h':
!             return options['hammie','header_ham_string']
          if self.c == 'u':
!             return options['hammie','header_unsure_string']
  
          return None
--- 197,205 ----
      def GetClassification(self):
          if self.c == 's':
!             return options['Hammie','header_spam_string']
          if self.c == 'h':
!             return options['Hammie','header_ham_string']
          if self.c == 'u':
!             return options['Hammie','header_unsure_string']
  
          return None
***************
*** 209,217 ****
          # may change, which would really screw this database up
  
!         if cls == options['hammie','header_spam_string']:
              self.c = 's'
!         elif cls == options['hammie','header_ham_string']:
              self.c = 'h'
!         elif cls == options['hammie','header_unsure_string']:
              self.c = 'u'
          else:
--- 209,217 ----
          # may change, which would really screw this database up
  
!         if cls == options['Hammie','header_spam_string']:
              self.c = 's'
!         elif cls == options['Hammie','header_ham_string']:
              self.c = 'h'
!         elif cls == options['Hammie','header_unsure_string']:
              self.c = 'u'
          else:
***************
*** 258,269 ****
          add optional headers if needed.'''
          
!         if prob < options['hammie','ham_cutoff']:
!             disposition = options['hammie','header_ham_string']
!         elif prob > options['hammie','spam_cutoff']:
!             disposition = options['hammie','header_spam_string']
          else:
!             disposition = options['hammie','header_unsure_string']
          self.RememberClassification(disposition)
!         self[options['hammie','header_name']] = disposition
          
          if options['pop3proxy','include_prob']:
--- 258,269 ----
          add optional headers if needed.'''
          
!         if prob < options['Categorization','ham_cutoff']:
!             disposition = options['Hammie','header_ham_string']
!         elif prob > options['Categorization','spam_cutoff']:
!             disposition = options['Hammie','header_spam_string']
          else:
!             disposition = options['Hammie','header_unsure_string']
          self.RememberClassification(disposition)
!         self[options['Hammie','header_name']] = disposition
          
          if options['pop3proxy','include_prob']:
***************
*** 279,284 ****
               for word, score in clues
               if (word[0] == '*' or
!                  score <= options['hammie','clue_mailheader_cutoff'] or
!                  score >= 1.0 - options['hammie','clue_mailheader_cutoff'])])
              self[options['pop3proxy','evidence_header_name']] = evd
          
--- 279,284 ----
               for word, score in clues
               if (word[0] == '*' or
!                  score <= options['Hammie','clue_mailheader_cutoff'] or
!                  score >= 1.0 - options['Hammie','clue_mailheader_cutoff'])])
              self[options['pop3proxy','evidence_header_name']] = evd
          
***************
*** 294,300 ****
  
      def delSBHeaders(self):
!         del self[options['hammie','header_name']]
          del self[options['pop3proxy','mailid_header_name']]
!         del self[options['hammie','header_name' + "-ID"]]  # test mode header
          del self[options['pop3proxy','prob_header_name']]
          del self[options['pop3proxy','thermostat_header_name']]
--- 294,300 ----
  
      def delSBHeaders(self):
!         del self[options['Hammie','header_name']]
          del self[options['pop3proxy','mailid_header_name']]
!         del self[options['Hammie','header_name' + "-ID"]]  # test mode header
          del self[options['pop3proxy','prob_header_name']]
          del self[options['pop3proxy','thermostat_header_name']]



From anadelonbrin at users.sourceforge.net  Fri Apr 18 23:19:53 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sat Apr 19 01:19:57 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py, 1.30,
	1.31 UpdatableConfigParser.py, 1.2, 1.3
Message-ID: <E196klV-0005Te-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv21026/spambayes

Modified Files:
	Options.py UpdatableConfigParser.py 
Log Message:
The options should now actually update when update_file
is called.  Works for me, at least.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.30
retrieving revision 1.31
diff -C2 -d -r1.30 -r1.31
*** Options.py	19 Apr 2003 01:45:21 -0000	1.30
--- Options.py	19 Apr 2003 05:19:50 -0000	1.31
***************
*** 1122,1125 ****
--- 1122,1132 ----
          return strval
  
+     def write_config(self, file):
+         '''Output value in configuration file format.'''
+         file.write(self.name)
+         file.write(':')
+         file.write(str(self.value))
+         file.write('\n')
+ 
  class OptionsClass(object):
      def __init__(self):
***************
*** 1129,1132 ****
--- 1136,1150 ----
      def update_file(self, file):
          '''Update the specified configuration file.'''
+         # The underlying config object doesn't get kept up-to-date
+         # because option values are stored in the nice option objects
+         # and the config object can't handle those.  So we do a quick
+         # update here (no-one else access the config object anyway).
+         for sect, opt in self._options.keys():
+             if self._config.has_option(sect, opt):
+                 self._config.set(sect, opt, str(self.get(sect, opt)))
+             else:
+                 self._config.add_option(sect, opt,
+                                         str(self.get(sect, opt)),
+                                         optionsPathname)
          self._config.update_file(file)
  
***************
*** 1198,1202 ****
          if sect is None or opt is None:
              return None
!         return self._options[sect, opt].value
  
      def __getitem__(self, key):
--- 1216,1220 ----
          if sect is None or opt is None:
              return None
!         return self._options[sect, opt].get()
  
      def __getitem__(self, key):
***************
*** 1207,1216 ****
          if sect is None or opt is None:
              raise KeyError
-         if not self._options.has_key((sect, opt)):
-             o = Option(opt)
-             self._options[sect, opt] = o
          self.convert(sect, opt, val)
!         if self._options[sect, opt].is_valid(val):
!             self._options[sect, opt].value = val
          else:
              print "Attempted to set [%s] %s with invalid value %s (%s)" % \
--- 1225,1231 ----
          if sect is None or opt is None:
              raise KeyError
          self.convert(sect, opt, val)
!         if self.is_valid(sect, opt, val):
!             self._options[sect, opt].set(val)
          else:
              print "Attempted to set [%s] %s with invalid value %s (%s)" % \
***************
*** 1260,1264 ****
                      if converter is not None:
                          value = converter(value)
!                 self._options[section, option].set(value)
                  # just for the moment, here's some more
                  # backwards compatability - this will go
--- 1275,1279 ----
                      if converter is not None:
                          value = converter(value)
!                 self.set(section, option, value)
                  # just for the moment, here's some more
                  # backwards compatability - this will go
***************
*** 1272,1276 ****
          '''Display options in a config file form.'''
          output = StringIO.StringIO()
!         self._config.write(output)
          return output.getvalue()
  
--- 1287,1302 ----
          '''Display options in a config file form.'''
          output = StringIO.StringIO()
!         keys = self._options.keys()
!         keys.sort()
!         currentSection = None
!         for sect, opt in keys:
!             if sect != currentSection:
!                 if currentSection is not None:
!                     output.write('\n')
!                 output.write('[')
!                 output.write(sect)
!                 output.write("]\n")
!                 currentSection = sect
!             self._options[sect, opt].write_config(output)
          return output.getvalue()
  
***************
*** 1281,1288 ****
         # the doc, default values, and so on
         output = StringIO.StringIO()
!        keys = self._options.keys()
!        keys.sort()
!        for (s, o) in keys:
!            output.write(self._options[s, o].as_nice_string(s))
         return output.getvalue()
  
--- 1307,1313 ----
         # the doc, default values, and so on
         output = StringIO.StringIO()
!        for sect in self._config.sections():
!            for opt in self._config.options(sect):
!                output.write(self.as_nice_string(sect, opt))
         return output.getvalue()
  

Index: UpdatableConfigParser.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/UpdatableConfigParser.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** UpdatableConfigParser.py	18 Apr 2003 02:36:10 -0000	1.2
--- UpdatableConfigParser.py	19 Apr 2003 05:19:50 -0000	1.3
***************
*** 117,120 ****
--- 117,124 ----
      True, False = 1, 0
  
+ # The ConfigParser included with Python 2.2 is not exensible in this
+ # fashion.  The wise Python developers realised this (sort of) and changed
+ # this for Python 2.3.  We offer a version of the 2.3 ConfigParser
+ # for those using 2.2, however.
  from CompatConfigParser import ConfigParser, ParsingError
  from CompatConfigParser import DEFAULTSECT, NoSectionError, NoOptionError
***************
*** 173,192 ****
          return existed
  
      def set(self, section, option, value):
          # c.f. ConfigParser.set()
-         print "setting", section, option, value
          ConfigParser.set(self, section, option, value)
          if self.record_original_values == False:
!             for file, sect in self._data.items():
!                 if sect == section:
!                     sectdict = {}
!                     optdict = {}
!                     if self._changed_options.has_key(file):
!                         sectdict = self._changed_options[file]
!                         if sectdict.has_key(section):
!                             optdict = sectdict[section]
!                     optdict[option] = value
!                     sectdict[section] = optdict
!                     self._changed_options[file] = sectdict
  
      def _read(self, fp, fpname):
--- 177,221 ----
          return existed
  
+     def add_section(self, section):
+         sect = {}
+         sect["__name__"] = section
+         self._sections[section] = sect
+ 
+     def add_option(self, section, option, value, original_file="<???>"):
+         if not self.has_section(section):
+             self.add_section(section)
+         if self.record_original_values == True:
+             self._updateDataIncludingOriginalValue(original_file, section,
+                                                    option, value)
+         else:
+             self._updateDataNoOriginalValue(original_file, section, option)
+             if original_file == "<???>":
+                 return
+             sectdict = {}
+             optdict = {}
+             if self._changed_options.has_key(original_file):
+                 sectdict = self._changed_options[original_file]
+                 if sectdict.has_key(section):
+                     optdict = sectdict[section]
+             optdict[option] = value
+             sectdict[section] = optdict
+             self._changed_options[original_file] = sectdict
+ 
      def set(self, section, option, value):
          # c.f. ConfigParser.set()
          ConfigParser.set(self, section, option, value)
          if self.record_original_values == False:
!             for (sect, opt), files in self._data.items():
!                 for file in files:
!                     if sect == section:
!                         sectdict = {}
!                         optdict = {}
!                         if self._changed_options.has_key(file):
!                             sectdict = self._changed_options[file]
!                             if sectdict.has_key(section):
!                                 optdict = sectdict[section]
!                         optdict[option] = value
!                         sectdict[section] = optdict
!                         self._changed_options[file] = sectdict
  
      def _read(self, fp, fpname):
***************
*** 287,291 ****
      def _updateDataNoOriginalValue(self, filename, sectname, optname):
          if self._data.has_key((sectname, optname)):
!             existing_data = self._data[(sectname, optname)]
              if filename not in existing_files:
                  existing_files += filename,
--- 316,320 ----
      def _updateDataNoOriginalValue(self, filename, sectname, optname):
          if self._data.has_key((sectname, optname)):
!             existing_files = self._data[(sectname, optname)]
              if filename not in existing_files:
                  existing_files += filename,



From timstone4 at users.sourceforge.net  Sat Apr 19 01:38:02 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Sat Apr 19 03:38:05 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.14,1.15
Message-ID: <E196mvC-0006kc-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv25915

Modified Files:
	message.py 
Log Message:
Little bit of code cleanup

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.14
retrieving revision 1.15
diff -C2 -d -r1.14 -r1.15
*** message.py	19 Apr 2003 04:13:44 -0000	1.14
--- message.py	19 Apr 2003 07:37:59 -0000	1.15
***************
*** 176,183 ****
          Nicked the regex from smtplib.quotedata.
          """
!         #XXX Tim doesn't like this regex.  He will study it to
!         #XXX see if he can learn to like it, or come up with
!         #XXX something he likes better.  - Tim
!         return re.sub(r'(?:\r\n|\n|\r(?!\n))', "\r\n", data)
  
      def as_string(self):
--- 176,180 ----
          Nicked the regex from smtplib.quotedata.
          """
!         return re.sub(r'(?:\r\n|\n|\r(?!\n))', '\r\n', data)
  
      def as_string(self):
***************
*** 276,285 ****
                                 
          if options['pop3proxy','include_evidence']:
!             evd = "; ".join(["%r: %.2f" % (word, score)
!              for word, score in clues
!              if (word[0] == '*' or
!                  score <= options['Hammie','clue_mailheader_cutoff'] or
!                  score >= 1.0 - options['Hammie','clue_mailheader_cutoff'])])
!             self[options['pop3proxy','evidence_header_name']] = evd
          
          if options['pop3proxy','add_mailid_to'].find("header") != -1:
--- 273,283 ----
                                 
          if options['pop3proxy','include_evidence']:
!             hco = options['Hammie','clue_mailheader_cutoff']
!             sco = 1 - hco
!             evd = []
!             for word, score in clues:
!                 if (word[0] == '*' or score <= hco or score >= sco):
!                     evd.append("%r: %.2f" % (word, score))
!             self[options['pop3proxy','evidence_header_name']] = "; ".join(evd)
          
          if options['pop3proxy','add_mailid_to'].find("header") != -1:



From timstone4 at users.sourceforge.net  Sat Apr 19 01:51:12 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Sat Apr 19 03:51:15 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.31,1.32
Message-ID: <E196n7w-0007cN-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv29258

Modified Files:
	Options.py 
Log Message:
Slight correction on smtpproxy servers validation regex

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.31
retrieving revision 1.32
diff -C2 -d -r1.31 -r1.32
*** Options.py	19 Apr 2003 05:19:50 -0000	1.31
--- Options.py	19 Apr 2003 07:51:09 -0000	1.32
***************
*** 766,770 ****
  address, you should now put the address of the machine running
  Spambayes.""",
! r"[\w\.\-]+(: [\d]+)?", True, False),
  
  ("ports", "Ports", "",
--- 766,770 ----
  address, you should now put the address of the machine running
  Spambayes.""",
! r"[\w\.\-]+(:[\d]+)?", True, False),
  
  ("ports", "Ports", "",



From anadelonbrin at users.sourceforge.net  Sat Apr 19 02:22:02 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sat Apr 19 04:22:07 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.26,1.27
Message-ID: <E196nbm-0001Bs-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv4533

Modified Files:
	imapfilter.py 
Log Message:
Fixed the long-standing problem with establishing the new
id for a message after it is saved.
Stopped filtering messages marked as /Deleted.
Fixed so that the flags of the original message are copied
along with the text.
Found a way to get the date of a message from a
(well-behaved) imap server, so switched to using that as
a default, and then falling back on the date header, and
then as a last resort the current time.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.26
retrieving revision 1.27
diff -C2 -d -r1.26 -r1.27
*** imapfilter.py	19 Apr 2003 01:45:20 -0000	1.26
--- imapfilter.py	19 Apr 2003 08:22:00 -0000	1.27
***************
*** 63,72 ****
        "OK", then the filter terminates.  Handling of these errors could be
        much nicer.
!     o The filter is currently designed to be periodically run (with cron,
!       for example).  It would probably be nicer if it was continually
!       running (like pop3proxy, for example) and periodically checked for
!       any new messages to process (with the RECENT command).  The period
!       could be an option.  This is partially done with the -l operand.
!     o Mail flagged with /Deleted shouldn't be filtered.
      o The flags should be copied along with the message (especially
        the /Seen flag, but all of them, really).
--- 63,67 ----
        "OK", then the filter terminates.  Handling of these errors could be
        much nicer.
!     o IMAP over SSL would be nice. (isbg has an example of how to do this)
      o The flags should be copied along with the message (especially
        the /Seen flag, but all of them, really).
***************
*** 197,205 ****
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
          response = imap.append(self.folder.name, None,
!                                self.extractTime(), self.as_string())
          self._check(response, 'append')
  
-         old_id = self.id
          if self.previous_folder is None:
              imap.SelectFolder(self.folder.name, False)
--- 192,216 ----
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
+         # we need to copy the flags as well
+         response = imap.uid("FETCH", self.id, "(FLAGS INTERNALDATE)")
+         self._check(response, 'fetch (flags internaldate)')
+         response_pattern = r"[\d]+ \(UID [\w]+ FLAGS (\([\\\w]+\)) "
+         response_pattern += r'INTERNALDATE ["]?([\w\-: ]+)["]?\)'
+         mo = re.match(response_pattern, response[1][0])
+         if mo is None:
+             msg_time = self.extractTime()
+             flags = None
+         else:
+             flags = mo.group(1)
+             msg_time = mo.group(2)
+ 
+         # See searching for new uid comments below
+         old_id = self.id
+         self["X-Spambayes-IMAP-OldID"] = old_id
+                     
          response = imap.append(self.folder.name, None,
!                                msg_time, self.as_string())
          self._check(response, 'append')
  
          if self.previous_folder is None:
              imap.SelectFolder(self.folder.name, False)
***************
*** 211,227 ****
  
          # We need to update the uid, as it will have changed
!         # XXX There will be problems here if the message *has not*
!         # XXX changed, as the message to be deleted will be found first
!         # XXX (if they are in the same folder)
!         imap.SelectFolder(self.folder.name, True)
!         #response = imap.uid("SEARCH", "TEXT", self.as_string())
!         #self._check(response, 'search')
!         #new_id = response[1][0]
!         new_id = ""
  
          #XXX This code to delete the old message id from the message
          #XXX info db and manipulate the message id, is a *serious* hack.
          #XXX There's gotta be a better way to do this.
- 
          message.msginfoDB._delState(self)
          self.id = new_id
--- 222,243 ----
  
          # We need to update the uid, as it will have changed
!         # Searching for the new message is full of problems.  Searching for
!         # the text sends far too much data through the connection, and
!         # doesn't work reliably anyway.  We instead search for a special
!         # header that we add for this explicit purpose.
!         imap.SelectFolder(self.folder.name, False)
!         response = imap.uid("SEARCH", "HEADER", "X-Spambayes-IMAP-OldID",
!                             old_id)
!         self._check(response, 'search')
!         new_id = response[1][0]
! 
!         # now that we know the new id, we need to correct the flags
!         if flags != None:
!             response = imap.uid("STORE", new_id, "+FLAGS.SILENT", flags)
!             self._check(response, "store flags")
  
          #XXX This code to delete the old message id from the message
          #XXX info db and manipulate the message id, is a *serious* hack.
          #XXX There's gotta be a better way to do this.
          message.msginfoDB._delState(self)
          self.id = new_id
***************
*** 250,253 ****
--- 266,277 ----
                  pass
  
+     def recent_keys(self):
+         '''Returns uids for all the messages in the folder that
+         are flagged as recent, but not flagged as deleted.'''
+         imap.SelectFolder(self.name, True)
+         response = imap.uid("SEARCH", "(RECENT UNDELETED)")
+         self._check(response, "SEARCH (RECENT UNDELETED)")
+         return response[1][0].split(' ')
+ 
      def keys(self):
          '''Returns uids for all the messages in the folder'''
***************
*** 257,267 ****
          if total_messages == '0':
              return []
!         response = imap.fetch("1:" + total_messages, "UID")
!         r = re.compile(r"[0-9]+ \(UID ([0-9]+)\)")
          uids = []
          for i in response[1]:
              mo = r.match(i)
              if mo is not None:
!                 uids.append(mo.group(1))
          return uids
  
--- 281,293 ----
          if total_messages == '0':
              return []
!         response = imap.fetch("1:" + total_messages, "(UID FLAGS)")
!         r = re.compile(r"[0-9]+ \(UID ([0-9]+) FLAGS \(([\\\w]*)\)\)")
          uids = []
          for i in response[1]:
              mo = r.match(i)
              if mo is not None:
!                 # We are not interested in messages marked as deleted
!                 if mo.group(2).lower() != "\\deleted":
!                     uids.append(mo.group(1))
          return uids
  
***************
*** 323,326 ****
--- 349,353 ----
  
                  msg.Save()
+ 
              
  class IMAPFilter(object):
***************
*** 328,332 ****
          self.spam_folder = IMAPFolder(options["imap", "spam_folder"])
          self.unsure_folder = IMAPFolder(options["imap", "unsure_folder"])
- 
          self.classifier = classifier
          
--- 355,358 ----
***************
*** 362,366 ****
          for filter_folder in options["imap", "filter_folders"].split():
              folder = IMAPFolder(filter_folder, False)
!             folder.Filter(self.classifier, self.spam_folder, self.unsure_folder)
   
          if options["globals", "verbose"]:
--- 388,393 ----
          for filter_folder in options["imap", "filter_folders"].split():
              folder = IMAPFolder(filter_folder, False)
!             folder.Filter(self.classifier, self.spam_folder,
!                           self.unsure_folder)
   
          if options["globals", "verbose"]:
***************
*** 455,458 ****
--- 482,486 ----
      # XXX using the same port by default.
      if launchUI:
+         imap.login(options["imap", "username"], pwd)
          httpServer = UserInterfaceServer(options["html_ui", "port"])
          httpServer.register(IMAPUserInterface(classifier, imap))



From anadelonbrin at users.sourceforge.net  Sat Apr 19 02:22:03 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sat Apr 19 04:22:10 2003
Subject: [Spambayes-checkins] spambayes/spambayes ImapUI.py, 1.3,
	1.4 UserInterface.py, 1.1, 1.2
Message-ID: <E196nbn-0001Bv-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv4533/spambayes

Modified Files:
	ImapUI.py UserInterface.py 
Log Message:
Fixed the long-standing problem with establishing the new
id for a message after it is saved.
Stopped filtering messages marked as /Deleted.
Fixed so that the flags of the original message are copied
along with the text.
Found a way to get the date of a message from a
(well-behaved) imap server, so switched to using that as
a default, and then falling back on the date header, and
then as a last resort the current time.

Index: ImapUI.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/ImapUI.py,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** ImapUI.py	19 Apr 2003 01:45:20 -0000	1.3
--- ImapUI.py	19 Apr 2003 08:22:01 -0000	1.4
***************
*** 57,61 ****
  
  import UserInterface
! from Options import options
  
  global classifier
--- 57,61 ----
  
  import UserInterface
! from Options import options, optionsPathname
  
  global classifier
***************
*** 131,140 ****
          from Options import options
  
      def _folder_list(self):
          '''Return a alphabetical list of all folders available
          on the server'''
!         response = imap.list()
          if response[0] != "OK":
!             return ()
          all_folders = response[1]
          folders = []
--- 131,191 ----
          from Options import options
  
+     def onSave(self, how):
+         self.imap.logout(False) # never expunge from the web ui
+         UserInterface.UserInterface.onSave(self, how)
+         
+     def onSelectfolders(self):
+         available_folders = self._folder_list()
+         content = self.html.configForm.clone()
+         content.configFormContent = ""
+         content.introduction = """This page allows you to change which
+         folders the filter works with."""
+         content.optionsPathname = optionsPathname
+ 
+         for opt in ("unsure_folder", "spam_folder",
+                     "filter_folders", "ham_train_folders",
+                     "spam_train_folders"):
+             folderBox = self._buildFolderBox("imap", opt, available_folders)
+             content.configFormContent += folderBox
+ 
+         self._writePreamble("Select Folders")
+         self.write(content)
+         self._writePostamble()
+ 
+     def _buildFolderBox(self, section, option, available_folders):
+         folderTable = self.html.configTable.clone()
+         del folderTable.configTextRow1
+         del folderTable.configCbRow1
+         del folderTable.configRow2
+         del folderTable.blankRow
+         del folderTable.folderRow
+         firstRow = True
+         for folder in available_folders:
+             folderRow = self.html.configTable.folderRow.clone()
+             if firstRow:
+                 folderRow.helpCell = options.doc(section, option)
+                 firstRow = False
+             else:
+                 del folderRow.helpCell
+             folderRow.folderBox.name = option
+             folderRow.folderBox.value = folder
+             folderRow.folderName = folder
+             if options.multiple_values_allowed(section, option):
+                 folderRow.folderBox.name += ',' + folder
+             else:
+                 folderRow.folderBox.type = "radio"
+             current_options = ',' + options[section, option] + ','
+             if current_options.find(',' + folder + ',') != -1:
+                 folderRow.folderBox.checked = "checked"
+             folderTable += folderRow
+         return self._buildBox(options.display_name(section, option),
+                               None, folderTable)
+ 
      def _folder_list(self):
          '''Return a alphabetical list of all folders available
          on the server'''
!         response = self.imap.list()
          if response[0] != "OK":
!             return []
          all_folders = response[1]
          folders = []

Index: UserInterface.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/UserInterface.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** UserInterface.py	18 Apr 2003 09:24:29 -0000	1.1
--- UserInterface.py	19 Apr 2003 08:22:01 -0000	1.2
***************
*** 398,401 ****
--- 398,402 ----
                  del configTable.configRow2
                  del configTable.blankRow
+                 del configTable.folderRow
                  section.heading = html_key
                  del section.iconCell
***************
*** 455,458 ****
--- 456,466 ----
                  elif str(currentValue) == '1':
                      currentValue = "True"
+             # XXX Something needs to be done here, otherwise really
+             # XXX long options squeeze the help text too far to the
+             # XXX right.  Browsers can't wrap the text (even if
+             # XXX no-wrap is False) unless there is whitespace to
+             # XXX wrap on - comma's don't count.  This works, but
+             # XXX it's a bit ugly.  Ideas?
+             # currentValue = str(currentValue).replace(',', '<br />')
              newConfigRow2.currentValue = currentValue
              configTable += newConfigRow1 + newConfigRow2 + blankRow



From anadelonbrin at users.sourceforge.net  Sat Apr 19 02:22:03 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sat Apr 19 04:22:14 2003
Subject: [Spambayes-checkins] spambayes/spambayes/resources ui.html, 1.8,
	1.9 ui_html.py, 1.8, 1.9
Message-ID: <E196nbn-0001C8-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes/resources
In directory sc8-pr-cvs1:/tmp/cvs-serv4533/spambayes/resources

Modified Files:
	ui.html ui_html.py 
Log Message:
Fixed the long-standing problem with establishing the new
id for a message after it is saved.
Stopped filtering messages marked as /Deleted.
Fixed so that the flags of the original message are copied
along with the text.
Found a way to get the date of a message from a
(well-behaved) imap server, so switched to using that as
a default, and then falling back on the date header, and
then as a last resort the current time.

Index: ui.html
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui.html,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** ui.html	19 Apr 2003 01:11:26 -0000	1.8
--- ui.html	19 Apr 2003 08:22:01 -0000	1.9
***************
*** 310,315 ****
      <FORM action="changeopts" method="POST">
  
!     <p>This page allows you to change the options that control how
!     Spambayes processes your email.  Your options are stored in
      <b><span id='optionsPathname'>/example/pathname</span></b>.</p>
  
--- 310,315 ----
      <FORM action="changeopts" method="POST">
  
!     <p><span id="introduction">This page allows you to change the options that control how
!     Spambayes processes your email.</span>  Your options are stored in
      <b><span id='optionsPathname'>/example/pathname</span></b>.</p>
  
***************
*** 345,351 ****
      <TR id="configRow2">
          <TD nowrap='1' align='right'>Current Value:</TD>
!         <TD nowrap='1'>&nbsp;<span id="currentValue">(value)</span></TD>
      </TR>
      <TR id="blankRow"><TD>&nbsp;</TD></TR>
      </TABLE>
      </span>
--- 345,361 ----
      <TR id="configRow2">
          <TD nowrap='1' align='right'>Current Value:</TD>
!         <TD nowrap='0' width='150'>&nbsp;<span id="currentValue">(value)</span></TD>
      </TR>
      <TR id="blankRow"><TD>&nbsp;</TD></TR>
+     <TR id="folderRow">
+         <TD width="25%">
+             <input type="checkbox" id="folderBox" value="value" name="folderName">
+             <span id="folderName">Folder name</span>
+             </input>
+         </TD>
+         <TD id='helpCell' valign='top' rowspan='1000'>
+             <p>(Help text goes here.)</p>
+         </TD>
+     </TR>
      </TABLE>
      </span>

Index: ui_html.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui_html.py,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** ui_html.py	19 Apr 2003 01:11:27 -0000	1.8
--- ui_html.py	19 Apr 2003 08:22:01 -0000	1.9
***************
*** 5,80 ****
  
  import zlib
! data = zlib.decompress("x��[�o۸\025����\037x\032Z%Xb;I��\034[X��a�5K|\033\016�CAY���$j\022\025�+���GR��$u\
! w�\006,-bK$\037\037\037���/df�\\��X�xsŮ\027�޲�\037޼��\005��㿝]�Ǘ�K��b49a��ge\
! �b��d<���\013��j�QiB��G��b�\010\026Gs��y�]�Ӑ�D�~(E���)Q��R���\001ǔjG_B\
! \031��'������O�1^�<9b�6.�#�\021ɃP񒟳�\027�8��\011���_)\036”{���+Y�зE��\
! �4��{x���,��7\023�YR#�>İj\021=Һ�\017�������d�¶�\022\030\022�b�0w�\025�z\003<�2���\
! C,�4s�K\006|�Ds7\012y��$!_ޯ\013Ye\021̴�\010���<��l=Y=N�\012h��<��+V����Dq\
! �d\016M�GV�$�X�\000͡~�TJ����7�61D<��?\004�;;{�Zv#哗Ԑ���k��K�@;����\
! \022\012-\007xGcK�Dͳ{�yt��ͷ\023�wζq�6�\007/��\003�c ۑ�j��br>��+��\012��=4hx�\015\
! WF���@r�4{^\010T\016-�\015*�T��sX_M�F㞠�tz�\030�C\025q.>�L�gK?�\022���U|\015H\
! q=�7��g�5�o�����fc\013\025��\001\034�JBD��/\036�C�Ϣ��-\023^�s_\033�\037��2�\031�\000hH��\
! Y��YY,�~3Z�+��$^gs��e\032GQ\"�q�<\013��\034�\000\012-jf\"�\013v��dy!�j���i\013\026�&B\
! \027\025���\031�5�2\025�%\036�\024b\005\023��\037\\��٘\017O\007���\\���U�\010���z�\001\004�%��C\022)��\013m�\
! �Y�g�[�y�y\021\000�za�ϰ-/�\015ȃ�&.�*N�\021�-e$��\013z:b�X�\031\010Am\004K��?�Yt�\022\"\
! �$�Z*�\034���}ۈ�N\024\000�#�\026��\001�_V�&�Ǡ�%� ?����%\024\002��`�*�\022\025\034&\006���\
! <�\022N/�&QT��S\000,ɢ\035\010\024\034I���MA�\020m��͗\036��c%~����1�2ba07�,�\007\014H�R\
! ²��.e��\014�]��\004ov�D\022�\005�4Bd�\026_\012� �\"\033��C\034Y\016,�\000��2�\005�\007V��\010�\011�Y�\
! 1)�\007�`m��\\�e\014`;�4��r��Y\013�FeBD%�&\024Z|Fz\033\\Tf\024���#˰��#�w(`�8)��\
! �\015���\016�\032��f��U��H\025v��yB�l�V��=9{��X��b\025ʏ�\020�F\023��]^��~eh�\000�\
! dlp\026gy��\034�.\036S�\\@�\003���%���=��6�N&�ؘV�g\0146�d;Y9�jT\010�m]�4�J+ٴ\
! �z�J�?����{5�5�� \006��\005e���\000���>�p�_��s�\020�b�\005�3\033c\013�\034�e����9\016�\
! �͙�Ev�\0310���W(�\020\034\031�\016\016��\024�%\020j\030\030!P\001^��\000��K&/\000W�ب�]����D�\017o��\
! O)�\030�w6�����p1\"j�F�b���,\013�%�A�z����$�6��6E8Q���k��@;:�\
! \022x\027e�\033�E���+\016a5\017%���R!za���\021~ �\004�?b��\023`+�o\020TS[\0252e��\012�,�l\001��\
! ΢�\017B\034AwW�$\001\036��\004\000���\012�@Z�Ch~̖('�\034����\033!�\021S�<��c\033,W\032��\\\003\010g�\
! \012\027\016�H�\010���m\003�\035!\035\023Jk/X��\033�\004�4�6;&x���\033�\000Zb\027��=��\010\013zH�\003�\023;�� \
! ���\014\030\012\024\010w��\006\012n��\005\024\030Eo\020]\035��@�4{V�t�o�*7���R$\011�\\b��7���`\006Q�%\007�\
! ^g�y�����s�\024b(��\021�\010�\010��(�1(�\005��EPX\010y�ߡ�\001��\023\020 =q�@m~\020eZb��\
! 7K�UU�x�\014|1���a�K�m���xȧ�h\026\015+�\004k-��\021\024���d���\012��R\015�\\���@{\032:`\
! �%L\007�\003KBS�:iB�f\014Xs����:��\010\035���\006cE�\000� ��EU��ą�Xdd!�n �B]1k6\
! Q{X����\036��w���Z7Q�q�Ϟ�\017�\036@���������V���]S�\036�$>�.!���V���7g\
! �\0321~�\020I@F�0�\014�\001�]�\021xz������c6\016�#w{�/��l\023�X��)\030/\002��\020\0329�7�ǟ�\
! ��\017Bs\013���h7�i�^�99\015�\023\020�BO/py\036u&�S�h]��OM����~���'��S�\020�E�*F�\
! ��Y�b�Й������a��Q��\016�!+�Bt�U����\005ʃ\011�2pb�>uV��O;s �m��1��!\
! ���@ Ÿ�tM����\033�twƸ8�NS�\002@�V��)h�\025\002,\033�.������$`��\003�\006D\
! �iA�d����C�ܕJ�\000�&\002�h\0017�\003=�\037\\��5�b腵��+'�\031ֈ�Y��\005�\005ď�\000���i\
! �ȵh��\032�J%�:\033��RW\016�i)0'Q\032l�\"$�����A\034�K�@�Lmdِ�#k\0215Rь��-}��\
! Q$$����\031񘅢Іc\036݁�Z;\004,��cԵ\011ct�f��J�+#\032�\0136e�z��x/6byOK�\034���\
! \015`�\031VJ�,V\020 \013L��Q]\037�\002V\014��\005R�!3�P\021���b%\012\037�V�`�4F0z(z�#��\033t@�c\
! ZK�\020�&2Ѓ.�rɋ��\031Q�O�\003��J�l\035\023h.i%M��G땔:��\017\024��\020d-�a/\025�9u��\
! \030�\000J\001��\037�\026��T��\037\023G\021�-\014Khs\037�(A\014\030���:1�'��?A \003�������:�0a\004��\
! �\006�܏|�H��AY�i�,\007k������\017\025���pw��\025$d\034��(.�? q�TB[዆�}�@)��\
! ����K\031x\014 ��s?T�$�H[qcc��\"���0=\036��\037�~�\007��웟.._/^�dR�*Ӛ)3�\011\007\
! 8��� �\\HS����\023��\001��U\012a�\010�(����f��l\015YY0g����Om)���;C:���׍\035\
! ��qr�b6�af\002x���\036���oU\011�8���\010��)�y�;=��\003�\037\016\034��B�vE�9;���\015�\
! /�D���a5�s�bɼ��Hɷr+�\013p\003\007���џ�&H�\003h\006�\027�\030X�?ۯ�G��|��?�ܤ\035�\
! ,{������\037ts\016�f�:�s\017��\005\014@\013�\003�U��Y��\022\002���u�NP�K�G�S��z�(�����#\
! ͖�֡\025���\026<G����q��X۴�)\037y��Si�\002��\005�;���G��\036��o��\022�6�\003���\012\
! �F\"�_�G>Z��`�@�.g8�~+�M�����Ûe�\003���P:XQ��\034My��\013�\006s+�N���]�\
! e�\\��طLJ����:\007��>x�m��Ă]�Y\004��u͂��\001�\016b�\014�Q]��Q1a�\022�\021�߫��\
! \\y��XZ\017f,a7%#��Տ�\016\0149��\032�*�o�k�����`\002��k�)=�wY���u����e��Q�\001\
! |��O�Z`���b��~\016���i\011�(Gx��„g�hrA\023��j�ӏ}J\024e�Ai\017��d�=i���\010M�\
! \006�����\001՗�ݪ<�<���(\004��՞������\017e\002\"1ZRZ%*�y����+nA�*�b�&͸�s\
! ��M\026\037R<*\011 jJ�^L�����PO�ﭲ��F� DG��\013:�\020��l72�s,��2P0:\0220��R\
! ��[��H\024�EnfR�_\024r\013�}�K�s\037O\006a_LOwv�|S��\007m,C��v\003\010��\007�\006�\\k���|!�\
! �'�5��y�\027�oC�*c�n\037`���9��\032\017h+,\035`p\034J<\000A��X&�l Du�c��\022gn��T�Y!\
! R�@�\011�C�ý�\010[�\005�R�b7l\007usc\012������\020�<+)��(�����$�?�twa\030\025 �\004}5\
! 's�(>\032\022�gW�\002_n\"���:\035����f�8֫�1{z�'�-�\012ᔪ\"qd\017N���%N��\010\002%x�\
! �*�+Gu�\015����\020\030\001\016�x��U�ĊmKY�坓ӳG*�\015���65�\027/_=B覐!\017c��v�P\
! �@�R\037��\022�Q\030<�B\006-�v\031\007�\012�`2�ݷ�d�/q.֊oE\011\036�\0211w:9E:�T��\002Q<�xž\
! CfI̘\006�A�8\004\016΁'�\020\030�D\017�O=�Z���#���B\013,D�\006�d��ݡ{e�9�\"\032\013���t*�\036\
! \024O��'\033qc\037�\026ٻ\0274��\\��8����L�Ԑ�z\003�`b(�p�\001��V��Ț:n�f\034�\010��\010�M\007\
! ����Н^�>��\014փ\030�`��p�\032�>�G5���#:W�������w\026�<�` d\016�h\001�C��z��\
! �f��S\010\004�|L\005U\034L(\005\024̹\030W��\003^�2w��r<8�R��t���#��\0275\015Nw�dA'�}��M�\033\
! �6\010�~06'��ܼjY�g�r�\\@�.��o�^9}�\017c\007\016_\027��(\000���V\015dqi\002g���s�\024\035�\
! �\031Mx(\022/x�\037�6g�\000qٞ�0�\\���sN_y4\013�\033o�\023b\010j�\017��\037R�{� �;\031m�F$9l\
! �I\007\036/�>J�#��\020����#�E4�c#�\001\036����\016]�����\007�''�[\035���ޓ!�sw��t\
! �\036�\036�M+��og����\037�\002�J\005Qw��ٵ�����,�*�]Ui�æä5~pQ\025\005��\002�l:�\002\
! G��*\033\\�ci(�\014ڽ�\032Ξb�)\011@7Gzn�1�[����X��׼��L\007�V�6X�3\012v�\037���L5\
! \021�\002�M��r>��0/V�\002��\007�\025l�j�x$��\017��b����l*\025�m6�`��N\017\017K�w�\035�&�G\
! )�p��J6S��#�ˏ�IW�TX{��J\011���)&\\�\0103�<\033��ϜJP4�w\015MI��3c\020�¢G\
! �쀻\027��0���\012��\027��\031lΒ�M�ɋ����씝N&�f\017F-\036̜J���x�ݎJ;�H\026��\
! \010>w�gM�J[hg���\"w���2���\015�bG��G�\016�\036�k�&�Csa�A\002��\016����\004�M��$y\
! �12��U�$�/0�_�")
  ### end
--- 5,81 ----
  
  import zlib
! data = zlib.decompress("x��[{oܸ\021����\016<\025�l�އ����Zhb���ŵ�Z\034\016��ZqwYK���7߽۠3CR�\036v6\
! �>�:�W+���p\036�\031��o.�_,~��b׋wo��\017o���y���_N/���ťnx1�L�\"�i!K\
! �R\036��W�{��_�7e\022ӧ�\021~���\005�ѹGO^p��$�;Q�\037\012��?���W|)�c�c�rG\017��\
! v�\023[�����N�1�K\036\037�b+��mD� J��g,��Z�36a������0�\036��J�\011�m\021��+>\
! �ez\017�*V���j\002?Kj�\007\011�\026�#�\033�\000�j�^M^LV+l\033-�!���\033掷B�7�c��z<H\
! ���{]R��ǚ�Q�Ӕ&\011��~��*�`��D�Lg,�Q$������8\026+�1}y��W��\011U\036���T\
! \0314e\037Y�b\031�0\006�C�BU�*�u%�q��!⹐\027����Ykٍ��/�!\021E��B�W�\002��+>6K�\
! �\034�\035�-�\0225����e�W�N��\031�ʨ܀\036�|�\016D��lG��Պ���\000\037�@>+\030;�Р�7\\\031\
! �7�\003�I���y.P9��\0136��\023R�^�a}5�\033�{����)b��2����R��-�\024K�g:V�\032<��\
! �ޜL���Կ%�g�b�������ÁG\022\"z\034|��\035\012~\036�\007��yQ��ڀ���\024\031Oi\004��D�^0�\
! ɚ\025����oFk��\031��:=�yX$2�bᏃ�iXdg�\007PhQ3\023�]�\023�'�r\025U��{����_D�z\
! E�<s�sͩJ\004n��6�X�D��\017���|̇�\003SKi����Ur����z�\013\010LK\024%�$\022.�\013m͞\
! Y�g�[�y�y\021\000�za�ϰ-/�\015Ȃ�F\026l%cq��K\025��悾\035�H�d\012B(7��J�\037�4:^\011\021k\
! \022jE-\025F\016ied�6\"�\02398�\021c\013x�\000�_U�&�I��\002GP\034��E\020\022r\001QB0���\022\025\034&\006��,\
! �bN/JM\"��R&�\024�v P\010$q�cz7\005qB��\015/�|��9V�G���\035C/#\026\006s����\001�(K\
! aY�c�*�T\012�.`qZ�7�w\"�ނQ\032!2�ŗ\000?�W�\015`�AF�\003�\"��c\025�\025\\\017�4��\035��g�\
! �$�\036���i�2U\024\022��HӸ�ˍ�f-L\032�\012\021\025(�Ph�\031�mpQ�Q\004�SF�ᒯ�Hޡ�\005��f\
! Wn��\030��h>�\\�z�Ta�x����Fm5�[��S��]��W$�P}��Pn4\001x��\005H�W�&\0140\
! M�\006�2ͪ�̡��r�\011�8�?\036h\\\\���c��ν��\033\033�j���&\027l�*GX�\012���s�$��J6\
! k�\036���\037��~�{5����@\014���mī\001Й\033}���~�O>���_L�\000~�cl\001�\003��Kga{�\
! C�g�Le\"=��3������!\0042\036\035\034�I)RK �00BG\005�J�\007Ht_2Y\016~\005���ݵ\033\037<�˳��\
! ���)E\030�㝏e���\034.FD\015��]lx�\026��?\\�e���1�Y/~\030[�S��ƴѦ�OT\022�y��\035�\
! �A�\000�E��������+\016���\012X�xQ��B�����\000�\004�?b*�\023`+�o<����UŠe�K�gR�\
! \005��u\032�c\020�\021\014w��c�\001\014M��\017w֫B3���7?fK�\023N������\020�\021+1y\002k�6X�2�\015�\
! \006'��+\\8xE2Ep���6�#�c��:\012\026��\006%�1\015�͎\011^����[b\027��{��\021\026�P�\007�\
! N�(�AO^�3 \024����3\013\024\\��\005\004��7�]\035�\034 f�=�M\032�\033X��-E\034��%&=~��<�\003\
! \012����7�}�\036���?\001\014ES3r�e\004V\004tz\024}\011�p\001��h\021\004\013!��;�\021��:\001\001�\023\027\006j�\003�\
! i��\032o\026%/�B�M3��ć0�ȗ�-�t0\036��|5��\025t�Z�/g\004�2\014��\021<X�;U�Ø��H\012�\
! ��\003�_�t =�$4\005��\006�5c��۽\035�թ�G訃w:�\025�\005�\007\005�.��\030�#.�b��uAv\003�\027�\
! �Y�A�a>�\002�=4W�PKm�n��u�\002�{&?<����*j��<\035��\025l\020�k��c����%$�2n��\
! ysʨ\021�S��\004d4\017���\033���\0359O/�N�\023#��8\014��텾��T�\010aټ�`�\010$��Ch�p�H\
! \036^�R>\010�-X\002���,f\035{q��4�N\000*��^��<�L��u�G?5M�J\036�7K+{\"����h-�\
! +�ak�Y�*���3!�����a��Q��\016�!-�\\t�U����\005ʃ\011�2\010b�>uV���:s �m��1\
! ��!����@t\006���+��7N���\031��qw��\024\000\012���\\��\020`��wy�O���#$\001K�\034\
! �4 zL\013�&{�,\037�Ů(E\002�� ��\026pS;�3����Y�R�^XK\030�rr�a�Q?�1uAj\001��\015@\
! h��F�\026�\\^���Ty��Bf�+�\020�J0'Q\030�bEHzI\035k�\003\034�\013�@�LmTѐ�#k\0215Rь��\
! -}��Q$$�:��x�BQhØGw ��\001\001K&\020\030um�\030\035��;�R����\005�2A�j\010�\027\033����A\
! ��+�\0060�\014��\004Y�\000 \013L��Q]\037�\002��a�\002)���\003T\004b��X�܇��?�2�\021�\036�\021�Ȥ��\
! ;��1�%^�h�\014��KY,y\036�1#��\011�\000~�\0220[�\004�KZI�u�h��B�\010��@\030�B��j�^*�s\
! �R�1�\001�\002���\026��T��\037#�\010`\013�\022ڹ\017RT \006\004o�Q'F�ĵ�'\010���z�~\032\034�q��\021\
! �ւ\015�{\037�:H��AQ��,-\007k������\017\025���pw��R\025$d\034pm$\013�\017HL�Jh\013�h׺\017\027(�\
! ���\036z~)\003�9�.r�CEL��\033\033�]�2����x�W���[?\030����tq�z��'�jV��L�j�\
! p�#�X\012�υ2%�O\015?r�\016 o�\022��#�`ϟ���Q,�5de�9;9l�~jK����3����g�n\
! �@B��\031�lN��\004��׿>lw��ߪ\002�8���\010��I�<\036QÁ?�\017\007�Ep��H���sv��\033\
! �_|�R���jb�4Œ�Z��R�U[�_@\03088<���4Ar>��`��\022\003k�G����<����矛�\
! ��eO�t��n�\007ݜ÷Y�N��C�}\035\006x\013'\002�U��Y��\022\000X��\006^\007����0Z/\025�Q��*\
! y�ٲ�:�\002砶9�аq�0n�\032k�56�#/�\021D*\035U@߼�<S�\036�k�(�\021-|�\005� �\021\035��\005\
! T06\022\031|h\037�h�\012��\002A�������6e\002{��\017o�=\017��;C�`Ee{s4�ao/�\033̭�98\017���\
! z�r�����o�\017;gY�u\016,�}��[��H��e\032�a`]3�7�\003\007�'�tTW+{T\014l_b5\"�{��\
! ^(�y$��`�\022v32�?^�8\034���H������{\035����\023L��zM<���]\0260�sC:|��2@��\
! \000~��O�Z`���b���\036����\022�Q��ͅ1O���\006��j��_��\010e�Ai\017��d�=i[�f��\
! S�������K�nU\026+\036��<\012A�yu�$����\025C�\000$FKJ���\031�K��8�%�N�JR1^�f��\
! 9N¦�\017\011\036�\004��\022�\027�j���>-ԓ�{����H\022����}N\007\032�җ�F�u�\005�,\005\005�#\001\023*\017)\
! 嚹�LD��/r3SI�E���Ou���ǓA�\027�ӝ�9����A\033�\020x�n�ö�\001���kM}z�/$\
! w�$��\036?O���m�Ye���\003�>�='�Z�\001m��\003\004ǡ�\003\020䌎e��\002!��\036;E\026���vS�f�\
! H�\003�'�\017�\017�.\"l!\027�S%�ݰ\035�͍)૿�+�/Bl��QH'���I�:��°W\000�\011�j\
! N��Q|4$�Ϯv\005�� ���:\035��`s�x\034��֘>���~��BwJU\021\031ك\023k�xd���+�@\011ޕ\
! �,�+Gu��Y�WI\010�\000\007h�u��SbŶ����������vCj�8�MM���W�\020��U�C\011��N\027j\
! \032���G��\004g\024\006ϣ�A�H���m�^0\031����>2�\004\027kŷ������;��\"\035U��f�(\036{�b�\
! !�$fL���O\034��s��?�t�\007�\036l����\021���\002\013Q��Y����н2֜O\021��[bl:�M\017\
! �\023}�d\0217��l��{A\023\"˕�����/ȴH\015\011�7�\001\023C��=\007Ȃ[QVy��q�7��F��G��t�\
! >\033�\017������`#��\015v/\016�����xTs�\016�=�su{�n߽�}g��G\027\014��@\035�����ynPk\
! �I�r����a-\033��\000\020��L�V$J�\013(��2^��\017x���es��\020�\012Q�S\013*'�, ��|^��t\025\
! I�t�۷n�����\006��\037�́�83�Z\006�\031�]4�\023������WN��ځ��ŭ;\012b\003\030ɴU\"Y\\\
! \032\\�-xn\025���5�1\017E�\005o��^���/.��<���=\035}{��g�\035�M���2`��\003��\017\011ϼ\
! 6��NF��\021q\006��l���k��\022�_��.\004\000�5td��Ƽ,@\032�\021\036o\007w�\"�\037�=\037�N��>�eZ\
! �'C���M*;�}�z�\007�j.b��~;�_\034\014�`\026�g����\034L�͝��7e\001U9�J�\0346[&��\
! *���\031Hd��\025ؑ���x�rR'ٍ��t�\014�\027���ڵ=ŴS=�n�$\007��T\014��\023�\033\025�N^>�\
! r'm\005���<��Ԭo�?fQn���9>��o��~\0327p\035\013�^��5�L&�^�\031S �G|}-��*5��\
! @u�`%����\021�\035\020^�^k\"�\005\006��k\013\006�BGT��\004M{X�\027�u�i��&>�b��/�Q���Hm\
! ӡTO_\022����P�μ#\024�~�T\024���fJ��\020{\015\025���Q�\022��6g,@����\000gkēɳ�\023��\
! S����¤)��zf��~\013�>�\007 ܽ��\\L��=������Jas��t¦/f�\027��\023v2���=\030�x\
! 0s�e6\033������\023�T�\036;���n%�)\035jg�Ynk�\010Y�Q�<�P��r���!�I�A\017�U\\�l��\
! �� �3f\007c!MskR�&Up�m�\030\025��_\015�?W�'\032��]")
  ### end



From anadelonbrin at users.sourceforge.net  Sat Apr 19 21:39:31 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:52:59 2003
Subject: [Spambayes-checkins] spambayes FAQ.txt,1.3,1.4
Message-ID: <E1975fv-0008SP-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv32478

Modified Files:
	FAQ.txt 
Log Message:
Update FAQ to cover configuration files for those that can't
or don't want to use the web (or otherwise) interface.
Also added/fxied a couple of Options functions to provide
information about the available options for these people.

Index: FAQ.txt
===================================================================
RCS file: /cvsroot/spambayes/spambayes/FAQ.txt,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** FAQ.txt	17 Apr 2003 23:49:40 -0000	1.3
--- FAQ.txt	20 Apr 2003 03:39:28 -0000	1.4
***************
*** 12,15 ****
--- 12,27 ----
     why you need to test your idea :)
  
+ Q: This software is great!  I want to implement it for all my users.
+    Are there plans to develop a server-side spambayes solution?
+ A: The problem with a server-side solution is that everyone has a
+    different idea of what is spam - that's the whole strength of the
+    bayesian-style filtering concept.  If you are certain that *all*
+    of your users would agree on what is spam and what is not, then
+    this might work for you, but otherwise you really have to have
+    individual databases for each user.  Either way, you should be
+    able to modify spambayes easily enough to fit into your setup.
+    Please let the list know if you do have success in this area, and
+    we'll update this answer.
+ 
  Q: I just got a spam, but the system said it was "unsure". Why
     couldn't it tell that it was spam - it's obvious?
***************
*** 41,53 ****
     bottom of the page.
  
! Q: This software is great!  I want to implement it for all my users.
!    Are there plans to develop a server-side spambayes solution?
! A: The problem with a server-side solution is that everyone has a
!    different idea of what is spam - that's the whole strength of the
!    bayesian-style filtering concept.  If you are certain that *all*
!    of your users would agree on what is spam and what is not, then
!    this might work for you, but otherwise you really have to have
!    individual databases for each user.  Either way, you should be
!    able to modify spambayes easily enough to fit into your setup.
!    Please let the list know if you do have success in this area, and
!    we'll update this answer.
--- 53,102 ----
     bottom of the page.
  
! Q: I can't use a web browser, so I can't configure pop3proxy/imapfilter.
!    Also: how do I configure hammiefilter and the other applications that
!    don't have a user interface?
! A: You need to create a configuration file.  This is in the 'standard'
!    ini file format (originally created for Windows 3.1, I believe).  You
!    can find documentation on this format in the Python ConfigParser doc,
!    <http://www.python.org/doc/current/lib/module-ConfigParser.html>, but
!    basically, it's just a text file: lines beginning with # are comments,
!    sections start with a line like "[Section Name]", and options are set
!    out within the appropriate section with lines like "opt = val" or
!    "opt: val" (either is ok).  Whitespace other than line endings is for
!    the most part ignored, so you can make it look like whatever you like.
!    You can see a list of what a configuration file of all the defaults
!    would like like if you execute the following Python commands:
!       >>> from spambayes.Options import options
!       >>> print options.display()
! 
! Q: That's great, now I know what the format looks like, but what options
!    do I need to set?
! A: This depends on exactly what you want to do, and which application you
!    are intending to use.  The easiest thing is to execute the following
!    Python commands:
!       >>> from spambayes.Options import options
!       >>> print options.display_full()
!    This will print out a complete list of the options, including a
!    description of the option, and its default value.  You can also look up
!    a single section, if you know its name:
!       >>> print options.display_full("section_name")
!    Or just a single option:
!       >>> print options.display_full("section_name", "option_name")
!    If you want a list of all the sections, you can use this command:
!       >>> print options.sections()
!    If you want a list of all the options, you can use this command:
!       >>> print options.options(prepend_section_name=False)
! 
! Q: I've made a configuration file, but spambayes is ignoring it. Now what?
! A: Spambayes looks for your configuration file in three places - if it
!    can't find it, then, obviously, your options will not be loaded.  The
!    first place that Spambayes checks is the environment variable
!    BAYESCUSTOMIZE.  You can set this to the path of your configuration file,
!    wherever it is, and it will be loaded.  You can also specify more than
!    one file, separated by the appropriate path separator for your platform.
!    This is the recommended method of specifying the location of the file,
!    unless you do so via a user interface (as provided by the POP3 proxy,
!    the Outlook plugin, and the IMAP filter). If Spambayes doesn't find
!    anything in the BAYESCUSTOMIZE variable, then it checks the current
!    working directory and your home directory for a bayescustomize.ini or
!    .spambayesrc file (respectively).



From anadelonbrin at users.sourceforge.net  Sat Apr 19 21:39:31 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:53:02 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.32,1.33
Message-ID: <E1975fv-0008SV-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv32478/spambayes

Modified Files:
	Options.py 
Log Message:
Update FAQ to cover configuration files for those that can't
or don't want to use the web (or otherwise) interface.
Also added/fxied a couple of Options functions to provide
information about the available options for these people.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.32
retrieving revision 1.33
diff -C2 -d -r1.32 -r1.33
*** Options.py	19 Apr 2003 07:51:09 -0000	1.32
--- Options.py	20 Apr 2003 03:39:29 -0000	1.33
***************
*** 1191,1197 ****
          '''Multiple values are allowed for this option.'''
          return self._options[sect, opt].multiple_values_allowed()
-     def as_nice_string(self, sect, opt):
-         '''Summarise the option in a user-readable format.'''
-         return self._options[sect, opt].as_nice_string(sect)
  
      def is_boolean(self, sect, opt):
--- 1191,1194 ----
***************
*** 1284,1287 ****
--- 1281,1305 ----
              raise ValueError("errors while parsing .ini file")
  
+     def sections(self):
+         '''Return an alphabetical list of all the sections.'''
+         all = []
+         for sect, opt in self._options.keys():
+             if sect not in all:
+                 all.append(sect)
+         all.sort()
+         return all
+ 
+     def options(self, prepend_section_name=False):
+         '''Return a alphabetical list of all the options, optionally
+         prefixed with [section_name]'''
+         all = []
+         for sect, opt in self._options.keys():
+             if prepend_section_name:
+                 all.append('[' + sect + ']' + opt)
+             else:
+                 all.append(opt)
+         all.sort()
+         return all
+ 
      def display(self):
          '''Display options in a config file form.'''
***************
*** 1301,1305 ****
          return output.getvalue()
  
!     def display_full(self):
         '''Display options including all information.'''
         # Given that the Options class is no longer as nice looking
--- 1319,1323 ----
          return output.getvalue()
  
!     def display_full(self, section=None, option=None):
         '''Display options including all information.'''
         # Given that the Options class is no longer as nice looking
***************
*** 1307,1313 ****
         # the doc, default values, and so on
         output = StringIO.StringIO()
!        for sect in self._config.sections():
!            for opt in self._config.options(sect):
!                output.write(self.as_nice_string(sect, opt))
         return output.getvalue()
  
--- 1325,1342 ----
         # the doc, default values, and so on
         output = StringIO.StringIO()
! 
!        # when section and option are both specified, this
!        # is nothing more than a call to as_nice_string
!        if section is not None and option is not None:
!            output.write(self._options[section,
!                                       option].as_nice_string(section))
!            return output.getvalue()
!        
!        all = self._options.keys()
!        all.sort()
!        for sect, opt in all:
!            if section is not None and sect != section:
!                continue
!            output.write(self._options[sect, opt].as_nice_string(sect))
         return output.getvalue()
  



From anadelonbrin at users.sourceforge.net  Sat Apr 19 22:11:04 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:53:05 2003
Subject: [Spambayes-checkins] website faq.ht,1.2,1.3
Message-ID: <E1976AS-00022U-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/website
In directory sc8-pr-cvs1:/tmp/cvs-serv7825

Modified Files:
	faq.ht 
Log Message:
Update FAQ to cover configuration files for those that can't
or don't want to use the web (or otherwise) interface.
(Also fixed whatever was wrong with the logo.png file when I uploaded these to the website).

Index: faq.ht
===================================================================
RCS file: /cvsroot/spambayes/website/faq.ht,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** faq.ht	17 Apr 2003 05:14:36 -0000	1.2
--- faq.ht	20 Apr 2003 04:11:02 -0000	1.3
***************
*** 15,18 ****
--- 15,26 ----
  <li><a href="#stillunsure">OK, I trained on that message. But I just got *another* one, and the stupid system still thinks it's unsure. Why did it ignore me???</a></li>
  <li><a href="#wipetraining">I've mucked up my training and I want to start all over again, but there isn't an option for this anywhere.  What do I do?</a></li>
+ <li><a href="#configfiles">I can't use a web browser, so I can't configure
+    pop3proxy/imapfilter.<br />
+    Also: how do I configure hammiefilter and the other applications that
+    don't have a user interface?</a></li>
+ <li><a href="#optionstoset">That's great, now I know what the format looks
+    like, but what options do I need to set?</a></li>
+ <li><a href="#configlocation">I've made a configuration file, but Spambayes is
+    ignoring it. Now what?</a></li>
  </ol>
  </ol>
***************
*** 78,79 ****
--- 86,151 ----
     you what this file is called (and where it is) down towards the
     bottom of the page.</p>
+ 
+ <h3><a name="#configfiles">I can't use a web browser, so I can't configure
+    pop3proxy/imapfilter.<br />
+    Also: how do I configure hammiefilter and the other applications that
+    don't have a user interface?</a></h3>
+ <p>You need to create a configuration file.  This is in the 'standard'
+    ini file format (originally created for Windows 3.1, I believe).  You
+    can find documentation on this format in the Python ConfigParser doc,
+    <a href="http://www.python.org/doc/current/lib/module-ConfigParser.html">
+    http://www.python.org/doc/current/lib/module-ConfigParser.html</a>, but
+    basically, it's just a text file: lines beginning with # are comments,
+    sections start with a line like "[Section Name]", and options are set
+    out within the appropriate section with lines like "opt = val" or
+    "opt: val" (either is ok).  Whitespace other than line endings is for
+    the most part ignored, so you can make it look like whatever you like.
+    You can see a list of what a configuration file of all the defaults
+    would like like if you execute the following Python commands:<br />
+    <pre>
+       >>> from spambayes.Options import options
+       >>> print options.display()
+    </pre></p>
+ 
+ <h3><a name="#optionstoset">That's great, now I know what the format looks
+    like, but what options do I need to set?</a></h3>
+ <p>This depends on exactly what you want to do, and which application you
+    are intending to use.  The easiest thing is to execute the following
+    Python commands:<br />
+    <pre>
+       >>> from spambayes.Options import options
+       >>> print options.display_full()
+    </pre>
+    This will print out a complete list of the options, including a
+    description of the option, and its default value.  You can also look up
+    a single section, if you know its name:<br />
+    <pre>
+       >>> print options.display_full("section_name")
+    </pre>
+    Or just a single option:<br />
+    <pre>
+       >>> print options.display_full("section_name", "option_name")
+    </pre>
+    If you want a list of all the sections, you can use this command:<br />
+    <pre>
+       >>> print options.sections()
+    </pre>
+    If you want a list of all the options, you can use this command:<br />
+    <pre>
+       >>> print options.options(prepend_section_name=False)
+    </pre></p>
+ 
+ <h3><a name="#configlocation">I've made a configuration file, but Spambayes is
+    ignoring it. Now what?</a></h3>
+ <p>Spambayes looks for your configuration file in three places - if it
+    can't find it, then, obviously, your options will not be loaded.  The
+    first place that Spambayes checks is the environment variable
+    BAYESCUSTOMIZE.  You can set this to the path of your configuration file,
+    wherever it is, and it will be loaded.  You can also specify more than
+    one file, separated by the appropriate path separator for your platform.
+    This is the recommended method of specifying the location of the file,
+    unless you do so via a user interface (as provided by the POP3 proxy,
+    the Outlook plugin, and the IMAP filter). If Spambayes doesn't find
+    anything in the BAYESCUSTOMIZE variable, then it checks the current
+    working directory and your home directory for a bayescustomize.ini or
+    .spambayesrc file (respectively).</p>



From anadelonbrin at users.sourceforge.net  Sat Apr 19 23:00:32 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:53:08 2003
Subject: [Spambayes-checkins] spambayes pop3proxy.py,1.74,1.75
Message-ID: <E1976wK-0004Wf-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv17377

Modified Files:
	pop3proxy.py 
Log Message:
Move the pop3proxy test code to a separate testing module.
If you used the -z or -t arguments, you should now execute
testtools/pop3proxytest.py -z or -t instead.

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.74
retrieving revision 1.75
diff -C2 -d -r1.74 -r1.75
*** pop3proxy.py	19 Apr 2003 02:11:54 -0000	1.74
--- pop3proxy.py	20 Apr 2003 05:00:27 -0000	1.75
***************
*** 13,20 ****
  
          options:
-             -z      : Runs a self-test and exits.
-             -t      : Runs a fake POP3 server on port 8110 (for testing).
              -h      : Displays this help message.
- 
              -d FILE : use the named DBM database file
              -D FILE : the the named Pickle database file
--- 13,17 ----
***************
*** 54,58 ****
  Web training interface:
  
-  o Functional tests.
   o Review already-trained messages, and purge them.
   o Include a Reply link that launches the registered email client, eg.
--- 51,54 ----
***************
*** 722,979 ****
  
  # ===================================================================
- # Test code.
- # ===================================================================
- 
- # One example of spam and one of ham - both are used to train, and are
- # then classified.  Not a good test of the classifier, but a perfectly
- # good test of the POP3 proxy.  The bodies of these came from the
- # spambayes project, and I added the headers myself because the
- # originals had no headers.
- 
- spam1 = """From: friend@public.com
- Subject: Make money fast
- 
- Hello tim_chandler , Want to save money ?
- Now is a good time to consider refinancing. Rates are low so you can cut
- your current payments and save money.
- 
- http://64.251.22.101/interest/index%38%30%300%2E%68t%6D
- 
- Take off list on site [s5]
- """
- 
- good1 = """From: chris@example.com
- Subject: ZPT and DTML
- 
- Jean Jordaan wrote:
- > 'Fraid so ;>  It contains a vintage dtml-calendar tag.
- >   http://www.zope.org/Members/teyc/CalendarTag
- >
- > Hmm I think I see what you mean: one needn't manually pass on the
- > namespace to a ZPT?
- 
- Yeah, Page Templates are a bit more clever, sadly, DTML methods aren't :-(
- 
- Chris
- """
- 
- class TestListener(Dibbler.Listener):
-     """Listener for TestPOP3Server.  Works on port 8110, to co-exist
-     with real POP3 servers."""
- 
-     def __init__(self, socketMap=asyncore.socket_map):
-         Dibbler.Listener.__init__(self, 8110, TestPOP3Server,
-                                   (socketMap,), socketMap=socketMap)
- 
- 
- class TestPOP3Server(Dibbler.BrighterAsyncChat):
-     """Minimal POP3 server, for testing purposes.  Doesn't support
-     UIDL.  USER, PASS, APOP, DELE and RSET simply return "+OK"
-     without doing anything.  Also understands the 'KILL' command, to
-     kill it.  The mail content is the example messages above.
-     """
- 
-     def __init__(self, clientSocket, socketMap):
-         # Grumble: asynchat.__init__ doesn't take a 'map' argument,
-         # hence the two-stage construction.
-         Dibbler.BrighterAsyncChat.__init__(self)
-         Dibbler.BrighterAsyncChat.set_socket(self, clientSocket, socketMap)
-         self.maildrop = [spam1, good1]
-         self.set_terminator('\r\n')
-         self.okCommands = ['USER', 'PASS', 'APOP', 'NOOP',
-                            'DELE', 'RSET', 'QUIT', 'KILL']
-         self.handlers = {'CAPA': self.onCapa,
-                          'STAT': self.onStat,
-                          'LIST': self.onList,
-                          'RETR': self.onRetr,
-                          'TOP': self.onTop}
-         self.push("+OK ready\r\n")
-         self.request = ''
- 
-     def collect_incoming_data(self, data):
-         """Asynchat override."""
-         self.request = self.request + data
- 
-     def found_terminator(self):
-         """Asynchat override."""
-         if ' ' in self.request:
-             command, args = self.request.split(None, 1)
-         else:
-             command, args = self.request, ''
-         command = command.upper()
-         if command in self.okCommands:
-             self.push("+OK (we hope)\r\n")
-             if command == 'QUIT':
-                 self.close_when_done()
-             if command == 'KILL':
-                 self.socket.shutdown(2)
-                 self.close()
-                 raise SystemExit
-         else:
-             handler = self.handlers.get(command, self.onUnknown)
-             self.push(handler(command, args))   # Or push_slowly for testing
-         self.request = ''
- 
-     def push_slowly(self, response):
-         """Useful for testing."""
-         for c in response:
-             self.push(c)
-             time.sleep(0.02)
- 
-     def onCapa(self, command, args):
-         """POP3 CAPA command.  This lies about supporting pipelining for
-         test purposes - the POP3 proxy *doesn't* support pipelining, and
-         we test that it correctly filters out that capability from the
-         proxied capability list."""
-         lines = ["+OK Capability list follows",
-                  "PIPELINING",
-                  "TOP",
-                  ".",
-                  ""]
-         return '\r\n'.join(lines)
- 
-     def onStat(self, command, args):
-         """POP3 STAT command."""
-         maildropSize = reduce(operator.add, map(len, self.maildrop))
-         maildropSize += len(self.maildrop) * len(HEADER_EXAMPLE)
-         return "+OK %d %d\r\n" % (len(self.maildrop), maildropSize)
- 
-     def onList(self, command, args):
-         """POP3 LIST command, with optional message number argument."""
-         if args:
-             try:
-                 number = int(args)
-             except ValueError:
-                 number = -1
-             if 0 < number <= len(self.maildrop):
-                 return "+OK %d\r\n" % len(self.maildrop[number-1])
-             else:
-                 return "-ERR no such message\r\n"
-         else:
-             returnLines = ["+OK"]
-             for messageIndex in range(len(self.maildrop)):
-                 size = len(self.maildrop[messageIndex])
-                 returnLines.append("%d %d" % (messageIndex + 1, size))
-             returnLines.append(".")
-             return '\r\n'.join(returnLines) + '\r\n'
- 
-     def _getMessage(self, number, maxLines):
-         """Implements the POP3 RETR and TOP commands."""
-         if 0 < number <= len(self.maildrop):
-             message = self.maildrop[number-1]
-             headers, body = message.split('\n\n', 1)
-             bodyLines = body.split('\n')[:maxLines]
-             message = headers + '\r\n\r\n' + '\n'.join(bodyLines)
-             return "+OK\r\n%s\r\n.\r\n" % message
-         else:
-             return "-ERR no such message\r\n"
- 
-     def onRetr(self, command, args):
-         """POP3 RETR command."""
-         try:
-             number = int(args)
-         except ValueError:
-             number = -1
-         return self._getMessage(number, 12345)
- 
-     def onTop(self, command, args):
-         """POP3 RETR command."""
-         try:
-             number, lines = map(int, args.split())
-         except ValueError:
-             number, lines = -1, -1
-         return self._getMessage(number, lines)
- 
-     def onUnknown(self, command, args):
-         """Unknown POP3 command."""
-         return "-ERR Unknown command: %s\r\n" % repr(command)
- 
- 
- def test():
-     """Runs a self-test using TestPOP3Server, a minimal POP3 server
-     that serves the example emails above.
-     """
-     # Run a proxy and a test server in separate threads with separate
-     # asyncore environments.
-     import threading
-     state.isTest = True
-     testServerReady = threading.Event()
-     def runTestServer():
-         testSocketMap = {}
-         TestListener(socketMap=testSocketMap)
-         testServerReady.set()
-         asyncore.loop(map=testSocketMap)
- 
-     proxyReady = threading.Event()
-     def runUIAndProxy():
-         httpServer = UserInterfaceServer(8881)
-         proxyUI = ProxyUserInterface(state)
-         httpServer.register(proxyUI)
-         BayesProxyListener('localhost', 8110, ('', 8111))
-         state.bayes.learn(tokenizer.tokenize(spam1), True)
-         state.bayes.learn(tokenizer.tokenize(good1), False)
-         proxyReady.set()
-         Dibbler.run()
- 
-     threading.Thread(target=runTestServer).start()
-     testServerReady.wait()
-     threading.Thread(target=runUIAndProxy).start()
-     proxyReady.wait()
- 
-     # Connect to the proxy and the test server.
-     proxy = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
-     proxy.connect(('localhost', 8111))
-     response = proxy.recv(100)
-     assert response == "+OK ready\r\n"
-     pop3Server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
-     pop3Server.connect(('localhost', 8110))
-     response = pop3Server.recv(100)
-     assert response == "+OK ready\r\n"
- 
-     # Verify that the test server claims to support pipelining.
-     pop3Server.send("capa\r\n")
-     response = pop3Server.recv(1000)
-     assert response.find("PIPELINING") >= 0
- 
-     # Ask for the capabilities via the proxy, and verify that the proxy
-     # is filtering out the PIPELINING capability.
-     proxy.send("capa\r\n")
-     response = proxy.recv(1000)
-     assert response.find("PIPELINING") == -1
- 
-     # Stat the mailbox to get the number of messages.
-     proxy.send("stat\r\n")
-     response = proxy.recv(100)
-     count, totalSize = map(int, response.split()[1:3])
-     assert count == 2
- 
-     # Loop through the messages ensuring that they have judgement
-     # headers.
-     for i in range(1, count+1):
-         response = ""
-         proxy.send("retr %d\r\n" % i)
-         while response.find('\n.\r\n') == -1:
-             response = response + proxy.recv(1000)
-         assert response.find(options["Hammie", "header_name"]) >= 0
- 
-     # Smoke-test the HTML UI.
-     httpServer = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
-     httpServer.connect(('localhost', 8881))
-     httpServer.sendall("get / HTTP/1.0\r\n\r\n")
-     response = ''
-     while 1:
-         packet = httpServer.recv(1000)
-         if not packet: break
-         response += packet
-     assert re.search(r"(?s)<html>.*Spambayes proxy.*</html>", response)
- 
-     # Kill the proxy and the test server.
-     proxy.sendall("kill\r\n")
-     proxy.recv(100)
-     pop3Server.sendall("kill\r\n")
-     pop3Server.recv(100)
- 
- 
- # ===================================================================
  # __main__ driver.
  # ===================================================================
--- 718,721 ----
***************
*** 982,986 ****
      # Read the arguments.
      try:
!         opts, args = getopt.getopt(sys.argv[1:], 'htbzpsd:D:l:u:')
      except getopt.error, msg:
          print >>sys.stderr, str(msg) + '\n\n' + __doc__
--- 724,728 ----
      # Read the arguments.
      try:
!         opts, args = getopt.getopt(sys.argv[1:], 'hbpsd:D:l:u:')
      except getopt.error, msg:
          print >>sys.stderr, str(msg) + '\n\n' + __doc__
***************
*** 992,998 ****
              print >>sys.stderr, __doc__
              sys.exit()
-         elif opt == '-t':
-             state.isTest = True
-             state.runTestServer = True
          elif opt == '-b':
              state.launchUI = True
--- 734,737 ----
***************
*** 1011,1017 ****
          elif opt == '-u':
              state.uiPort = int(arg)
-         elif opt == '-z':
-             state.isTest = True
-             runSelfTest = True
  
      # Do whatever we've been asked to do...
--- 750,753 ----
***************
*** 1027,1042 ****
      LoadServerInfo()
      
!     if runSelfTest:
!         print "\nRunning self-test...\n"
!         state.buildServerStrings()
!         test()
!         print "Self-test passed."   # ...else it would have asserted.
! 
!     elif state.runTestServer:
!         print "Running a test POP3 server on port 8110..."
!         TestListener()
!         asyncore.loop()
! 
!     elif 0 <= len(args) <= 2:
          # Normal usage, with optional server name and port number.
          if len(args) == 1:
--- 763,767 ----
      LoadServerInfo()
      
!     if 0 <= len(args) <= 2:
          # Normal usage, with optional server name and port number.
          if len(args) == 1:



From anadelonbrin at users.sourceforge.net  Sat Apr 19 23:00:32 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:53:11 2003
Subject: [Spambayes-checkins] spambayes/testtools pop3proxytest.py,NONE,1.1
Message-ID: <E1976wK-0004Wh-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/testtools
In directory sc8-pr-cvs1:/tmp/cvs-serv17377/testtools

Added Files:
	pop3proxytest.py 
Log Message:
Move the pop3proxy test code to a separate testing module.
If you used the -z or -t arguments, you should now execute
testtools/pop3proxytest.py -z or -t instead.

--- NEW FILE: pop3proxytest.py ---
#! /usr/bin/env python

"""Test the pop3proxy is working correctly.

When using the -z command line option, carries out a test that the
POP3 proxy can be connected to, that incoming mail is classified,
that pipelining is removed from the CAPA[bility] query, and that the
web ui is present.

The -t option runs a fake POP3 server on port 8810.  This is the
same server that the -z option uses, and may be separately run for
other testing purposes.

Usage:

    pop3proxytest.py [options]

        options:
            -z      : Runs a self-test and exits.
            -t      : Runs a fake POP3 server on port 8110 (for testing).
            -h      : Displays this help message.
"""

# This module is part of the spambayes project, which is Copyright 2002
# The Python Software Foundation and is covered by the Python Software
# Foundation license.

__author__ = "Richie Hindle <richie@entrian.com>"
__credits__ = "All the Spambayes folk."

try:
    True, False
except NameError:
    # Maintain compatibility with Python 2.2
    True, False = 1, 0

# This code originally formed a part of pop3proxy.py.  If you are examining
# the history of this file, you may need to go back to there.

todo = """
Web training interface:

 o Functional tests.
"""

# One example of spam and one of ham - both are used to train, and are
# then classified.  Not a good test of the classifier, but a perfectly
# good test of the POP3 proxy.  The bodies of these came from the
# spambayes project, and Richie added the headers because the
# originals had no headers.

spam1 = """From: friend@public.com
Subject: Make money fast

Hello tim_chandler , Want to save money ?
Now is a good time to consider refinancing. Rates are low so you can cut
your current payments and save money.

http://64.251.22.101/interest/index%38%30%300%2E%68t%6D

Take off list on site [s5]
"""

good1 = """From: chris@example.com
Subject: ZPT and DTML

Jean Jordaan wrote:
> 'Fraid so ;>  It contains a vintage dtml-calendar tag.
>   http://www.zope.org/Members/teyc/CalendarTag
>
> Hmm I think I see what you mean: one needn't manually pass on the
> namespace to a ZPT?

Yeah, Page Templates are a bit more clever, sadly, DTML methods aren't :-(

Chris
"""

import asyncore
import socket
import operator
import re
import getopt

# a bit of a hack to help those without spambayes on their
# Python path - stolen from timtest.py
import sys
import os
sys.path.insert(-1, os.getcwd())
sys.path.insert(-1, os.path.dirname(os.getcwd()))

from spambayes import Dibbler
from spambayes import tokenizer
from spambayes.UserInterface import UserInterfaceServer
from spambayes.ProxyUI import ProxyUserInterface
from pop3proxy import BayesProxyListener
from pop3proxy import state, _recreateState
from spambayes.Options import options

# HEADER_EXAMPLE is the longest possible header - the length of this one
# is added to the size of each message.
HEADER_EXAMPLE = '%s: xxxxxxxxxxxxxxxxxxxx\r\n' % \
                 options["Hammie", "header_name"]

class TestListener(Dibbler.Listener):
    """Listener for TestPOP3Server.  Works on port 8110, to co-exist
    with real POP3 servers."""

    def __init__(self, socketMap=asyncore.socket_map):
        Dibbler.Listener.__init__(self, 8110, TestPOP3Server,
                                  (socketMap,), socketMap=socketMap)


class TestPOP3Server(Dibbler.BrighterAsyncChat):
    """Minimal POP3 server, for testing purposes.  Doesn't support
    UIDL.  USER, PASS, APOP, DELE and RSET simply return "+OK"
    without doing anything.  Also understands the 'KILL' command, to
    kill it.  The mail content is the example messages above.
    """

    def __init__(self, clientSocket, socketMap):
        # Grumble: asynchat.__init__ doesn't take a 'map' argument,
        # hence the two-stage construction.
        Dibbler.BrighterAsyncChat.__init__(self)
        Dibbler.BrighterAsyncChat.set_socket(self, clientSocket, socketMap)
        self.maildrop = [spam1, good1]
        self.set_terminator('\r\n')
        self.okCommands = ['USER', 'PASS', 'APOP', 'NOOP',
                           'DELE', 'RSET', 'QUIT', 'KILL']
        self.handlers = {'CAPA': self.onCapa,
                         'STAT': self.onStat,
                         'LIST': self.onList,
                         'RETR': self.onRetr,
                         'TOP': self.onTop}
        self.push("+OK ready\r\n")
        self.request = ''

    def collect_incoming_data(self, data):
        """Asynchat override."""
        self.request = self.request + data

    def found_terminator(self):
        """Asynchat override."""
        if ' ' in self.request:
            command, args = self.request.split(None, 1)
        else:
            command, args = self.request, ''
        command = command.upper()
        if command in self.okCommands:
            self.push("+OK (we hope)\r\n")
            if command == 'QUIT':
                self.close_when_done()
            if command == 'KILL':
                self.socket.shutdown(2)
                self.close()
                raise SystemExit
        else:
            handler = self.handlers.get(command, self.onUnknown)
            self.push(handler(command, args))   # Or push_slowly for testing
        self.request = ''

    def push_slowly(self, response):
        """Useful for testing."""
        for c in response:
            self.push(c)
            time.sleep(0.02)

    def onCapa(self, command, args):
        """POP3 CAPA command.  This lies about supporting pipelining for
        test purposes - the POP3 proxy *doesn't* support pipelining, and
        we test that it correctly filters out that capability from the
        proxied capability list."""
        lines = ["+OK Capability list follows",
                 "PIPELINING",
                 "TOP",
                 ".",
                 ""]
        return '\r\n'.join(lines)

    def onStat(self, command, args):
        """POP3 STAT command."""
        maildropSize = reduce(operator.add, map(len, self.maildrop))
        maildropSize += len(self.maildrop) * len(HEADER_EXAMPLE)
        return "+OK %d %d\r\n" % (len(self.maildrop), maildropSize)

    def onList(self, command, args):
        """POP3 LIST command, with optional message number argument."""
        if args:
            try:
                number = int(args)
            except ValueError:
                number = -1
            if 0 < number <= len(self.maildrop):
                return "+OK %d\r\n" % len(self.maildrop[number-1])
            else:
                return "-ERR no such message\r\n"
        else:
            returnLines = ["+OK"]
            for messageIndex in range(len(self.maildrop)):
                size = len(self.maildrop[messageIndex])
                returnLines.append("%d %d" % (messageIndex + 1, size))
            returnLines.append(".")
            return '\r\n'.join(returnLines) + '\r\n'

    def _getMessage(self, number, maxLines):
        """Implements the POP3 RETR and TOP commands."""
        if 0 < number <= len(self.maildrop):
            message = self.maildrop[number-1]
            headers, body = message.split('\n\n', 1)
            bodyLines = body.split('\n')[:maxLines]
            message = headers + '\r\n\r\n' + '\n'.join(bodyLines)
            return "+OK\r\n%s\r\n.\r\n" % message
        else:
            return "-ERR no such message\r\n"

    def onRetr(self, command, args):
        """POP3 RETR command."""
        try:
            number = int(args)
        except ValueError:
            number = -1
        return self._getMessage(number, 12345)

    def onTop(self, command, args):
        """POP3 RETR command."""
        try:
            number, lines = map(int, args.split())
        except ValueError:
            number, lines = -1, -1
        return self._getMessage(number, lines)

    def onUnknown(self, command, args):
        """Unknown POP3 command."""
        return "-ERR Unknown command: %s\r\n" % repr(command)


def test():
    """Runs a self-test using TestPOP3Server, a minimal POP3 server
    that serves the example emails above.
    """
    # Run a proxy and a test server in separate threads with separate
    # asyncore environments.
    import threading
    state.isTest = True
    testServerReady = threading.Event()
    def runTestServer():
        testSocketMap = {}
        TestListener(socketMap=testSocketMap)
        testServerReady.set()
        asyncore.loop(map=testSocketMap)

    proxyReady = threading.Event()
    def runUIAndProxy():
        httpServer = UserInterfaceServer(8881)
        proxyUI = ProxyUserInterface(state, _recreateState)
        httpServer.register(proxyUI)
        BayesProxyListener('localhost', 8110, ('', 8111))
        state.bayes.learn(tokenizer.tokenize(spam1), True)
        state.bayes.learn(tokenizer.tokenize(good1), False)
        proxyReady.set()
        Dibbler.run()

    threading.Thread(target=runTestServer).start()
    testServerReady.wait()
    threading.Thread(target=runUIAndProxy).start()
    proxyReady.wait()

    # Connect to the proxy and the test server.
    proxy = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    proxy.connect(('localhost', 8111))
    response = proxy.recv(100)
    assert response == "+OK ready\r\n"
    pop3Server = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    pop3Server.connect(('localhost', 8110))
    response = pop3Server.recv(100)
    assert response == "+OK ready\r\n"

    # Verify that the test server claims to support pipelining.
    pop3Server.send("capa\r\n")
    response = pop3Server.recv(1000)
    assert response.find("PIPELINING") >= 0

    # Ask for the capabilities via the proxy, and verify that the proxy
    # is filtering out the PIPELINING capability.
    proxy.send("capa\r\n")
    response = proxy.recv(1000)
    assert response.find("PIPELINING") == -1

    # Stat the mailbox to get the number of messages.
    proxy.send("stat\r\n")
    response = proxy.recv(100)
    count, totalSize = map(int, response.split()[1:3])
    assert count == 2

    # Loop through the messages ensuring that they have judgement
    # headers.
    for i in range(1, count+1):
        response = ""
        proxy.send("retr %d\r\n" % i)
        while response.find('\n.\r\n') == -1:
            response = response + proxy.recv(1000)
        assert response.find(options["Hammie", "header_name"]) >= 0

    # Smoke-test the HTML UI.
    httpServer = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
    httpServer.connect(('localhost', 8881))
    httpServer.sendall("get / HTTP/1.0\r\n\r\n")
    response = ''
    while 1:
        packet = httpServer.recv(1000)
        if not packet: break
        response += packet
    assert re.search(r"(?s)<html>.*Spambayes proxy.*</html>", response)

    # Kill the proxy and the test server.
    proxy.sendall("kill\r\n")
    proxy.recv(100)
    pop3Server.sendall("kill\r\n")
    pop3Server.recv(100)

def run():
    # Read the arguments.
    try:
        opts, args = getopt.getopt(sys.argv[1:], 'htz')
    except getopt.error, msg:
        print >>sys.stderr, str(msg) + '\n\n' + __doc__
        sys.exit()

    runSelfTest = False
    for opt, arg in opts:
        if opt == '-h':
            print >>sys.stderr, __doc__
            sys.exit()
        elif opt == '-t':
            state.isTest = True
            state.runTestServer = True
        elif opt == '-z':
            state.isTest = True
            runSelfTest = True

    state.createWorkers()

    if runSelfTest:
        print "\nRunning self-test...\n"
        state.buildServerStrings()
        test()
        print "Self-test passed."   # ...else it would have asserted.

    elif state.runTestServer:
        print "Running a test POP3 server on port 8110..."
        TestListener()
        asyncore.loop()

    else:
        print >>sys.stderr, __doc__

if __name__ == '__main__':
    run()



From anadelonbrin at users.sourceforge.net  Sun Apr 20 00:13:19 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:53:13 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.33,1.34
Message-ID: <E19784l-0008IP-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv31884/spambayes

Modified Files:
	Options.py 
Log Message:
Changes to make the default options more easily read (by
humans).  Well, hopefully.  No changes to the actual code.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.33
retrieving revision 1.34
diff -C2 -d -r1.33 -r1.34
*** Options.py	20 Apr 2003 03:39:29 -0000	1.33
--- Options.py	20 Apr 2003 06:13:16 -0000	1.34
***************
*** 101,104 ****
--- 101,139 ----
  import re
  
+ # These are handy references to commonly used regex/tuples defining
+ # permitted values. Although the majority of options use one of these,
+ # you may use any regex or tuple you wish.
+ HEADER_NAME = r"[\w\.-\*]+"
+ HEADER_VALUE = r"[\w\.-\*]+"
+ INTEGER = r"[\d]+"              # actually, a *positive* integer
+ REAL = r"[\d]+[\.]?[\d]*"       # likewise, a *positive* real
[...1600 lines suppressed...]
!     ("filter_folders", "Folders to filter", "INBOX",
!      """Comma delimited list of folders to be filtered""",
!      IMAP_FOLDER, MULTIPLE_ALLOWED, DO_NOT_RESTORE),
! 
!     ("unsure_folder", "Folder for unsure messages", "",
!      """""", IMAP_FOLDER, SINGLE_VALUE, DO_NOT_RESTORE),
!     
!     ("spam_folder", "Folder for suspected spam", "",
!      """""", IMAP_FOLDER, SINGLE_VALUE, DO_NOT_RESTORE),
  
+     ("ham_train_folders", "Folders with mail to be trained as ham", "",
+      """Comma delimited list of folders that will be examined for messages
+      to train as ham.""", IMAP_FOLDER, MULTIPLE_ALLOWED, DO_NOT_RESTORE),
+ 
+     ("spam_train_folders", "Folders with mail to be trained as spam", "",
+      """Comma delimited list of folders that will be examined for messages
+      to train as spam.""", IMAP_FOLDER, MULTIPLE_ALLOWED, DO_NOT_RESTORE),
+   ),
  }
  



From anadelonbrin at users.sourceforge.net  Sun Apr 20 00:26:17 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:53:16 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.34,1.35
Message-ID: <E1978HJ-0000Ub-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv1856/spambayes

Modified Files:
	Options.py 
Log Message:
Allow "" as a valid option iff the valid option is defined as a
regex and multiple values is set.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.34
retrieving revision 1.35
diff -C2 -d -r1.34 -r1.35
*** Options.py	20 Apr 2003 06:13:16 -0000	1.34
--- Options.py	20 Apr 2003 06:26:14 -0000	1.35
***************
*** 134,138 ****
  # Again, for ease of reading, we define these here:
  RESTORE = True
! DO_NO_RESTORE = False
  
  __all__ = ['options']
--- 134,138 ----
  # Again, for ease of reading, we define these here:
  RESTORE = True
! DO_NOT_RESTORE = False
  
  __all__ = ['options']
***************
*** 427,436 ****
       """default locations for timcv and timtest - these get the set number
       interpolated.""",
!      VARIABLE_PATH, MULTIPLE_ALLOWED, RESTORE),
  
      ("ham_directories", "Ham directories", "Data/Ham/Set%d",
       """default locations for timcv and timtest - these get the set number
       interpolated.""",
!      VARIABLE_PATH, MULTIPLE_ALLOWED, RESTORE),
    ),
  
--- 427,436 ----
       """default locations for timcv and timtest - these get the set number
       interpolated.""",
!      VARIABLE_PATH, SINGLE_VALUE, RESTORE),
  
      ("ham_directories", "Ham directories", "Data/Ham/Set%d",
       """default locations for timcv and timtest - these get the set number
       interpolated.""",
!      VARIABLE_PATH, SINGLE_VALUE, RESTORE),
    ),
  
***************
*** 1138,1143 ****
--- 1138,1147 ----
                 return False
          elif type(self.allowed_values) == type(""):
+             if self.multiple and value == "":
+                 return True
              vals = self._split_values(value)
              if len(vals) == 0:
+                 return False
+             elif len(vals) > 1 and not self.multiple:
                  return False
              return True



From anadelonbrin at users.sourceforge.net  Sun Apr 20 00:58:54 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:53:19 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.27,1.28
Message-ID: <E1978ms-00028q-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv8188

Modified Files:
	imapfilter.py 
Log Message:
Change imap filter to specify servers in the pop3proxy style,
i.e. server[:port] rather than have two options.  If you were
previously specifying a port, you will need to change your
configuration file, otherwise no change is necessary.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.27
retrieving revision 1.28
diff -C2 -d -r1.27 -r1.28
*** imapfilter.py	19 Apr 2003 08:22:00 -0000	1.27
--- imapfilter.py	20 Apr 2003 06:58:52 -0000	1.28
***************
*** 454,457 ****
--- 454,463 ----
  or training will be performed."""
  
+     server = options["imap", "server"]
+     username = options["imap", "username"]
+     if server == "" or username == "":
+         print "You need to specify both a server and a username."
+         sys.exit()
+ 
      if promptForPass:
          pwd = getpass()
***************
*** 472,477 ****
          print "Done."            
                  
!     imap = IMAPSession(options["imap", "server"],
!                        options["imap", "port"], imapDebug)
  
      imap_filter = IMAPFilter(classifier)
--- 478,490 ----
          print "Done."            
                  
!     if server.find(':') > -1:
!         server, port = server.split(':', 1)
!         port = int(port)
!     else:
!         if options["imap", "use_ssl"]:
!             port = 993
!         else:
!             port = 143
!     imap = IMAPSession(server, port, imapDebug)
  
      imap_filter = IMAPFilter(classifier)
***************
*** 482,486 ****
      # XXX using the same port by default.
      if launchUI:
!         imap.login(options["imap", "username"], pwd)
          httpServer = UserInterfaceServer(options["html_ui", "port"])
          httpServer.register(IMAPUserInterface(classifier, imap))
--- 495,499 ----
      # XXX using the same port by default.
      if launchUI:
!         imap.login(username, pwd)
          httpServer = UserInterfaceServer(options["html_ui", "port"])
          httpServer.register(IMAPUserInterface(classifier, imap))
***************
*** 488,492 ****
      else:
          while True:
!             imap.login(options["imap", "username"], pwd)
  
              if doTrain:
--- 501,505 ----
      else:
          while True:
!             imap.login(username, pwd)
  
              if doTrain:



From anadelonbrin at users.sourceforge.net  Sun Apr 20 00:58:55 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:53:22 2003
Subject: [Spambayes-checkins] spambayes/spambayes ImapUI.py, 1.4,
	1.5 Options.py, 1.35, 1.36
Message-ID: <E1978mt-00028t-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv8188/spambayes

Modified Files:
	ImapUI.py Options.py 
Log Message:
Change imap filter to specify servers in the pop3proxy style,
i.e. server[:port] rather than have two options.  If you were
previously specifying a port, you will need to change your
configuration file, otherwise no change is necessary.

Index: ImapUI.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/ImapUI.py,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -d -r1.4 -r1.5
*** ImapUI.py	19 Apr 2003 08:22:01 -0000	1.4
--- ImapUI.py	20 Apr 2003 06:58:52 -0000	1.5
***************
*** 73,76 ****
--- 73,77 ----
      'imapusername': ('imap',            'username'),
      'imappassword': ('imap',            'password'),
+     'imapssl':      ('imap',            'use_ssl'),
      'p3notateto':   ('pop3proxy',       'notate_to'),
      'p3notatesub':  ('pop3proxy',       'notate_subject'),
***************
*** 88,92 ****
             # localhost, it's available for the world to see)
             # on the other hand, we have to be able to enter it somehow...
!            'imappassword',
             'Header Options', 'p3notateto', 'p3notatesub', 
             'p3prob', 'p3thermostat', 'p3evidence', 
--- 89,93 ----
             # localhost, it's available for the world to see)
             # on the other hand, we have to be able to enter it somehow...
!            'imappassword', 'imapssl',
             'Header Options', 'p3notateto', 'p3notatesub', 
             'p3prob', 'p3thermostat', 'p3evidence', 

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.35
retrieving revision 1.36
diff -C2 -d -r1.35 -r1.36
*** Options.py	20 Apr 2003 06:26:14 -0000	1.35
--- Options.py	20 Apr 2003 06:58:52 -0000	1.36
***************
*** 881,887 ****
    "imap" : (
      ("server", "Server", "",
!      """This is the name of the imap server that stores your mail, and
!      which the imap filter will connect to - for example: mail.example.com
!      or imap.example.com.  If you use more than one server, then things are
       a bit more complicated for you at the moment, sorry.  You will need to
       have multiple instances of the imap filter running, each with a
--- 881,889 ----
    "imap" : (
      ("server", "Server", "",
!      """This is the name and port of the imap server that stores your mail,
!      and which the imap filter will connect to - for example:
!      mail.example.com or imap.example.com:143.  The default IMAP port is
!      143, or 993 if using SSL; if you connect via one of those ports, you
!      can leave this blank. If you use more than one server, then things are
       a bit more complicated for you at the moment, sorry.  You will need to
       have multiple instances of the imap filter running, each with a
***************
*** 891,903 ****
       mailing list know if you are in this situation so that we can consider
       coming up with a better solution.""",
!      SERVER, SINGLE_VALUE, DO_NOT_RESTORE),
! 
!     ("port", "Port", 143,
!      """This is the port of the imap server that stores your mail, and
!      which the imap filter will connect to.  The default IMAP port is 143,
!      or 993 if using SSL; you will probably have one of those values here.
!      If you are using multiple imap servers, please see the comments
!      regarding the server value.""",
!      PORT, SINGLE_VALUE, DO_NOT_RESTORE),
  
      ("username", "Username", "",
--- 893,897 ----
       mailing list know if you are in this situation so that we can consider
       coming up with a better solution.""",
!      SERVER, MULTIPLE_ALLOWED, DO_NOT_RESTORE),
  
      ("username", "Username", "",
***************
*** 907,911 ****
       on the same server, please see the comments regarding the server
       value.""",
!      PORT, SINGLE_VALUE, DO_NOT_RESTORE),
  
      ("password", "Password", "",
--- 901,905 ----
       on the same server, please see the comments regarding the server
       value.""",
!      r"[\w]+", MULTIPLE_ALLOWED, DO_NOT_RESTORE),
  
      ("password", "Password", "",
***************
*** 917,921 ****
       blank and use the -p command line option to imapfilter.py and you will
       be prompted for your password.""",
!      r"[\w]+", SINGLE_VALUE, DO_NOT_RESTORE),
  
      ("expunge", "Purge//Expunge", False,
--- 911,915 ----
       blank and use the -p command line option to imapfilter.py and you will
       be prompted for your password.""",
!      r"[\w]+", MULTIPLE_ALLOWED, DO_NOT_RESTORE),
  
      ("expunge", "Purge//Expunge", False,
***************
*** 925,928 ****
--- 919,926 ----
       BOOLEAN, SINGLE_VALUE, RESTORE),
  
+     ("use_ssl", "Connect via a secure socket layer", False,
+      """NOT YET IMPLEMENTED""",
+      BOOLEAN, SINGLE_VALUE, DO_NOT_RESTORE),
+ 
      ("filter_folders", "Folders to filter", "INBOX",
       """Comma delimited list of folders to be filtered""",
***************
*** 1051,1055 ****
                    },
      'imap': {'server' : string_cracker,
-              'port' : int_cracker,
               'username' : string_cracker,
               'password' : string_cracker,
--- 1049,1052 ----
***************
*** 1059,1063 ****
               'ham_train_folders' : string_cracker,
               'spam_train_folders' : string_cracker,
!              'expunge' : boolean_cracker, 
              },
      'html_ui': {'port': int_cracker,
--- 1056,1061 ----
               'ham_train_folders' : string_cracker,
               'spam_train_folders' : string_cracker,
!              'expunge' : boolean_cracker,
!              'use_ssl' : boolean_cracker,
              },
      'html_ui': {'port': int_cracker,



From anadelonbrin at users.sourceforge.net  Sun Apr 20 03:41:18 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:53:41 2003
Subject: [Spambayes-checkins] spambayes/spambayes ImapUI.py, 1.5,
	1.6 ProxyUI.py, 1.2, 1.3 UserInterface.py, 1.2, 1.3
Message-ID: <E197BK2-0005eS-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv21696/spambayes

Modified Files:
	ImapUI.py ProxyUI.py UserInterface.py 
Log Message:
Set the user interface web pages to no cache as this is bad for the
configuration pages.
Fixed the checking of entered parameters so that both imapfilter
and pop3proxy work (in my testing, at least).
Changed parm_ini_map to a simpler version with just option and
section names (html keys are auto generated).
Move the select folder config for imap into two pages rather than
one - one for folder to train, one for filtering folders.  If this still
results in pages that are too long for people with lots of folders,
then this can be further split into one page per option.
Fixed the folder selector config so that it actually works.
Now that it works, made the folder selector config accessible.
Added a check to see if parsedate works so that we handle
things gracefully if it does not.
Fixed the re that got the internal date so that it can handle the
other half of the world.
Added in a fallback option in case imap can't find the uid of the
replacement message, although I'm not convinced this is a good
fallback (better than nothing, though).
Happy Easter, all ;)

Index: ImapUI.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/ImapUI.py,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** ImapUI.py	20 Apr 2003 06:58:52 -0000	1.5
--- ImapUI.py	20 Apr 2003 09:41:15 -0000	1.6
***************
*** 61,97 ****
  global classifier
  
! # This control dictionary maps http request parameters and template fields
! # to ConfigParser sections and options.  The key matches both the input
! # field that corresponds to a section/option, and also the HTML template
! # variable that is used to display the value of that section/option.
! parm_map = \
!    {'hamcutoff':    ('Categorization',  'ham_cutoff'),
!     'spamcutoff':   ('Categorization',  'spam_cutoff'),
!     'dbname':       ('pop3proxy',       'persistent_storage_file'),
!     'imapserver':   ('imap',            'server'),
!     'imapport':     ('imap',            'port'),
!     'imapusername': ('imap',            'username'),
!     'imappassword': ('imap',            'password'),
!     'imapssl':      ('imap',            'use_ssl'),
!     'p3notateto':   ('pop3proxy',       'notate_to'),
!     'p3notatesub':  ('pop3proxy',       'notate_subject'),
!     'p3addid':      ('pop3proxy',       'add_mailid_to'),
!     'p3stripid':    ('pop3proxy',       'strip_incoming_mailids'),
!     'p3prob':       ('pop3proxy',       'include_prob'),
!     'p3thermostat': ('pop3proxy',       'include_thermostat'),
!     'p3evidence':   ('pop3proxy',       'include_evidence'),
!    }
! 
! display = ('IMAP Options', 'imapserver', 'imapport', 'imapusername',
!            # to display, or not to display; that is the question
!            # if we show this here, it's in plain text for everyone to
!            # see (and worse - if we don't restrict connections to
!            # localhost, it's available for the world to see)
!            # on the other hand, we have to be able to enter it somehow...
!            'imappassword', 'imapssl',
!            'Header Options', 'p3notateto', 'p3notatesub', 
!            'p3prob', 'p3thermostat', 'p3evidence', 
!            'p3addid', 'p3stripid',
!            'Statistics Options', 'dbname', 'hamcutoff', 'spamcutoff')
  
  class IMAPUserInterface(UserInterface.UserInterface):
--- 61,93 ----
  global classifier
  
! # These are the options that will be offered on the configuration page.
! # If the option is None, then the entry is a header and the following
! # options will appear in a new box on the configuration page.
! # These are also used to generate http request parameters and template
! # fields/variables.
! parm_map = (
!     ('IMAP Options',          None),
!     ('imap',                  'server'),
!     ('imap',                  'username'),
!     # to display, or not to display; that is the question!
!     # if we show this here, it's in plain text for everyone to
!     # see (and worse - if we don't restrict connections to
!     # localhost, it's available for the world to see)
!     # on the other hand, we have to be able to enter it somehow...
!     ('imap',                  'password'),
!     ('imap',                  'use_ssl'),
!     ('Header Options',        None),
!     ('pop3proxy',             'notate_to'),
!     ('pop3proxy',             'notate_subject'),
!     ('pop3proxy',             'include_prob'),
!     ('pop3proxy',             'include_thermostat'),
!     ('pop3proxy',             'include_evidence'),
!     ('pop3proxy',             'add_mailid_to'),
!     ('pop3proxy',             'strip_incoming_mailids'),
!     ('Statistics Options',    None),
!     ('pop3proxy',             'persistent_storage_file'),
!     ('Categorization',        'ham_cutoff'),
!     ('Categorization',        'spam_cutoff'),
! )
  
  class IMAPUserInterface(UserInterface.UserInterface):
***************
*** 100,104 ****
      def __init__(self, cls, imap):
          global classifier
!         UserInterface.UserInterface.__init__(self, cls, parm_map, display)
          classifier = cls
          self.imap = imap
--- 96,100 ----
      def __init__(self, cls, imap):
          global classifier
!         UserInterface.UserInterface.__init__(self, cls, parm_map)
          classifier = cls
          self.imap = imap
***************
*** 110,113 ****
--- 106,113 ----
          statusTable = self.html.statusTable.clone()
          del statusTable.proxyDetails
+         # This could be a bit more modular
+         statusTable.configurationLink += """You can also <a href=
+         'filterfolders'>configure folders to filter</a> and <a href=
+         'trainingfolders'>Configure folders to train</a>"""
          content = (self._buildBox('Status and Configuration',
                                    'status.gif', statusTable % stateDict)+
***************
*** 135,157 ****
          self.imap.logout(False) # never expunge from the web ui
          UserInterface.UserInterface.onSave(self, how)
!         
!     def onSelectfolders(self):
          available_folders = self._folder_list()
          content = self.html.configForm.clone()
          content.configFormContent = ""
          content.introduction = """This page allows you to change which
!         folders the filter works with."""
          content.optionsPathname = optionsPathname
  
          for opt in ("unsure_folder", "spam_folder",
!                     "filter_folders", "ham_train_folders",
                      "spam_train_folders"):
              folderBox = self._buildFolderBox("imap", opt, available_folders)
              content.configFormContent += folderBox
  
!         self._writePreamble("Select Folders")
          self.write(content)
          self._writePostamble()
  
      def _buildFolderBox(self, section, option, available_folders):
          folderTable = self.html.configTable.clone()
--- 135,200 ----
          self.imap.logout(False) # never expunge from the web ui
          UserInterface.UserInterface.onSave(self, how)
! 
!     def onFilterfolders(self):
          available_folders = self._folder_list()
          content = self.html.configForm.clone()
          content.configFormContent = ""
          content.introduction = """This page allows you to change which
!         folders are filtered, and where filtered mail ends up."""
!         content.config_submit.value = "Save Filter Folders"
          content.optionsPathname = optionsPathname
  
          for opt in ("unsure_folder", "spam_folder",
!                     "filter_folders"):
!             folderBox = self._buildFolderBox("imap", opt, available_folders)
!             content.configFormContent += folderBox
! 
!         self._writePreamble("Select Filter Folders")
!         self.write(content)
!         self._writePostamble()
! 
!     def onTrainingfolders(self):
!         available_folders = self._folder_list()
!         content = self.html.configForm.clone()
!         content.configFormContent = ""
!         content.introduction = """This page allows you to change which
!         folders contain mail to train Spambayes."""
!         content.config_submit.value = "Save Training Folders"
!         content.optionsPathname = optionsPathname
! 
!         for opt in ("ham_train_folders",
                      "spam_train_folders"):
              folderBox = self._buildFolderBox("imap", opt, available_folders)
              content.configFormContent += folderBox
  
!         self._writePreamble("Select Training Folders")
          self.write(content)
          self._writePostamble()
  
+     def onChangeopts(self, **parms):
+         backup = self.parm_ini_map
+         print parms
+         if parms["how"] == "Save Training Folders" or \
+            parms["how"] == "Save Filter Folders":
+             del parms["how"]
+             self.parm_ini_map = ()
+             for opt, value in parms.items():
+                 del parms[opt]
+                 # Under strange circumstances this could break,
+                 # so if we can think of a better way to do this,
+                 # that would be nice.
+                 if opt[-len(value):] == value:
+                     opt = opt[:-len(value)]
+                 self.parm_ini_map += ("imap", opt),
+                 key = "imap_" + opt
+                 if parms.has_key(key):
+                     parms[key] += ',' + value
+                 else:
+                     parms[key] = value
+         print self.parm_ini_map
+         print parms
+         UserInterface.UserInterface.onChangeopts(self, **parms)
+         self.parm_ini_map = backup
+         
      def _buildFolderBox(self, section, option, available_folders):
          folderTable = self.html.configTable.clone()
***************
*** 173,177 ****
              folderRow.folderName = folder
              if options.multiple_values_allowed(section, option):
!                 folderRow.folderBox.name += ',' + folder
              else:
                  folderRow.folderBox.type = "radio"
--- 216,220 ----
              folderRow.folderName = folder
              if options.multiple_values_allowed(section, option):
!                 folderRow.folderBox.name += folder
              else:
                  folderRow.folderBox.type = "radio"
***************
*** 195,202 ****
              m = r.search(fol)
              name_attributes = fol[:m.end()-1]
!             folder_delimiter = fol[m.end()+1:m.end()+2]
              # a bit of a hack, but we really need to know if this is
              # the case
!             if folder_delimiter == ',':
                  print """WARNING: Your imap server uses commas as the folder
                  delimiter.  This may cause unpredictable errors."""
--- 238,245 ----
              m = r.search(fol)
              name_attributes = fol[:m.end()-1]
!             self.folder_delimiter = fol[m.end()+1:m.end()+2]
              # a bit of a hack, but we really need to know if this is
              # the case
!             if self.folder_delimiter == ',':
                  print """WARNING: Your imap server uses commas as the folder
                  delimiter.  This may cause unpredictable errors."""

Index: ProxyUI.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/ProxyUI.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** ProxyUI.py	19 Apr 2003 02:09:49 -0000	1.2
--- ProxyUI.py	20 Apr 2003 09:41:15 -0000	1.3
***************
*** 72,106 ****
  global state
  
! # This control dictionary maps http request parameters and template fields
! # to ConfigParser sections and options.  The key matches both the input
! # field that corresponds to a section/option, and also the HTML template
! # variable that is used to display the value of that section/option.
! parm_ini_map = \
!    {'hamcutoff':    ('Categorization',  'ham_cutoff'),
!     'spamcutoff':   ('Categorization',  'spam_cutoff'),
!     'dbname':       ('pop3proxy',       'persistent_storage_file'),
!     'p3servers':    ('pop3proxy',       'servers'),
!     'p3ports':      ('pop3proxy',       'ports'),
!     'p3notateto':   ('pop3proxy',       'notate_to'),
!     'p3notatesub':  ('pop3proxy',       'notate_subject'),
!     'p3cachemsg':   ('pop3proxy',       'cache_messages'),
!     'p3addid':      ('pop3proxy',       'add_mailid_to'),
!     'p3stripid':    ('pop3proxy',       'strip_incoming_mailids'),
!     'p3prob':       ('pop3proxy',       'include_prob'),
!     'p3thermostat': ('pop3proxy',       'include_thermostat'),
!     'p3evidence':   ('pop3proxy',       'include_evidence'),
!     'smtpservers':  ('smtpproxy',       'servers'),
!     'smtpports':    ('smtpproxy',       'ports'),
!     'smtpham':      ('smtpproxy',       'ham_address'),
!     'smtpspam':     ('smtpproxy',       'spam_address'),
!    }
! 
! display = ('POP3 Proxy Options', 'p3servers', 'p3ports', 'p3cachemsg',
!            'Header Options', 'p3notateto', 'p3notatesub', 
!            'p3prob', 'p3thermostat', 'p3evidence', 
!            'p3addid', 'p3stripid',
!            'SMTP Proxy Options', 'smtpservers', 'smtpports', 'smtpham',
!            'smtpspam',
!            'Statistics Options', 'dbname', 'hamcutoff', 'spamcutoff')
  
  
--- 72,103 ----
  global state
  
! # These are the options that will be offered on the configuration page.
! # If the option is None, then the entry is a header and the following
! # options will appear in a new box on the configuration page.
! # These are also used to generate http request parameters and template
! # fields/variables.
! parm_ini_map = (
!     ('POP3 Proxy Options',  None),
!     ('pop3proxy',           'servers'),
!     ('pop3proxy',           'ports'),
!     ('pop3proxy',           'cache_messages'),
!     ('Header Options',      None),
!     ('pop3proxy',           'notate_to'),
!     ('pop3proxy',           'notate_subject'),
!     ('pop3proxy',           'include_prob'),
!     ('pop3proxy',           'include_thermostat'),
!     ('pop3proxy',           'include_evidence'),
!     ('pop3proxy',           'add_mailid_to'),
!     ('pop3proxy',           'strip_incoming_mailids'),
!     ('SMTP Proxy Options',  None),
!     ('smtpproxy',           'servers'),
!     ('smtpproxy',           'ports'),
!     ('smtpproxy',           'ham_address'),
!     ('smtpproxy',           'spam_address'),
!     ('Statistics Options',  None),
!     ('pop3proxy',           'persistent_storage_file'),
!     ('Categorization',      'ham_cutoff'),
!     ('Categorization',      'spam_cutoff'),
! )
  
  
***************
*** 111,115 ****
          global state
          UserInterface.UserInterface.__init__(self, proxy_state.bayes,
!                                              parm_ini_map, display)
          state = proxy_state
          self.state_recreator = state_recreator # ugly
--- 108,112 ----
          global state
          UserInterface.UserInterface.__init__(self, proxy_state.bayes,
!                                              parm_ini_map)
          state = proxy_state
          self.state_recreator = state_recreator # ugly
***************
*** 464,465 ****
--- 461,504 ----
          # Recreate the state.
          self.state_recreator()
+ 
+     def verifyInput(self, parms):
+         '''Check that the given input is valid.'''
+         # Most of the work here is done by the parent class, but
+         # we have a few extra checks
+         errmsg = UserInterface.UserInterface.verifyInput(self, parms)
+         
+         # check for equal number of pop3servers and ports
+         slist = parms['pop3proxy_servers'].split(',')
+         plist = parms['pop3proxy_ports'].split(',')
+         if len(slist) != len(plist):
+             errmsg += '<li>The number of POP3 proxy ports specified ' + \
+                       'must match the number of servers specified</li>\n'
+ 
+         # check for duplicate ports
+         plist.sort()
+         for p in range(len(plist)-1):
+             try:
+                 if plist[p] == plist[p+1]:
+                     errmsg += '<li>All POP3 port numbers must be unique</li>'
+                     break
+             except IndexError:
+                 pass
+ 
+         # check for equal number of smtpservers and ports
+         slist = parms['smtpproxy_servers'].split(',')
+         plist = parms['smtpproxy_ports'].split(',')
+         if len(slist) != len(plist):
+             errmsg += '<li>The number of SMTP proxy ports specified ' + \
+                       'must match the number of servers specified</li>\n'
+ 
+         # check for duplicate ports
+         plist.sort()
+         for p in range(len(plist)-1):
+             try:
+                 if plist[p] == plist[p+1]:
+                     errmsg += '<li>All SMTP port numbers must be unique</li>'
+                     break
+             except IndexError:
+                 pass
+ 
+         return errmsg

Index: UserInterface.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/UserInterface.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** UserInterface.py	19 Apr 2003 08:22:01 -0000	1.2
--- UserInterface.py	20 Apr 2003 09:41:15 -0000	1.3
***************
*** 204,208 ****
      """Serves the HTML user interface."""
  
!     def __init__(self, bayes, config_parms=[], config_display=[]):
          """Load up the necessary resources: ui.html and helmet.gif."""
          global classifier
--- 204,208 ----
      """Serves the HTML user interface."""
  
!     def __init__(self, bayes, config_parms=()):
          """Load up the necessary resources: ui.html and helmet.gif."""
          global classifier
***************
*** 210,214 ****
          classifier = bayes
          self.parm_ini_map = config_parms
-         self.display = config_display
  
      def onClassify(self, file, text, which):
--- 210,213 ----
***************
*** 377,382 ****
  
          # Loop though the sections.
!         for html_key in self.display:
!             if not self.parm_ini_map.has_key(html_key):
                  if configTable is not None and section is not None:
                      # Finish off the box for this section and add it
--- 376,384 ----
  
          # Loop though the sections.
!         for sect, opt in self.parm_ini_map:
!             # We need a string to use as the html key that we can change to
!             # and from the sect, opt pair.  We like irony, so we use '_' as
!             # the delimiter <wink>
!             if opt is None:
                  if configTable is not None and section is not None:
                      # Finish off the box for this section and add it
***************
*** 399,406 ****
                  del configTable.blankRow
                  del configTable.folderRow
!                 section.heading = html_key
                  del section.iconCell
                  continue
!             (sect, opt) = self.parm_ini_map[html_key]
  
              # Populate the rows with the details and add them to the table.
--- 401,408 ----
                  del configTable.blankRow
                  del configTable.folderRow
!                 section.heading = sect
                  del section.iconCell
                  continue
!             html_key = sect + '_' + opt
  
              # Populate the rows with the details and add them to the table.
***************
*** 476,479 ****
--- 478,483 ----
  
      def onChangeopts(self, **parms):
+         if parms.has_key("how"):
+             del parms["how"]
          html = self.html.clone()
          html.shutdownTableCell = "&nbsp;"
***************
*** 490,496 ****
  
          for name, value in parms.items():
!            if self.parm_ini_map.has_key(name):
!                sect, opt = self.parm_ini_map[name]
!                options.set(sect, opt, value)
  
          op = open(optionsPathname, "r")
--- 494,501 ----
  
          for name, value in parms.items():
!             print name, value
!             sect, opt = name.split('_', 1)
!             if (sect, opt) in self.parm_ini_map:
!                 options.set(sect, opt, value)
  
          op = open(optionsPathname, "r")
***************
*** 525,529 ****
          '''Check that the given input is valid.'''
          # Most of the work here is done by the options class, but
!         # we have a few extra checks that are beyond its capabilities
          errmsg = ''
  
--- 530,534 ----
          '''Check that the given input is valid.'''
          # Most of the work here is done by the options class, but
!         # we may have a few extra checks that are beyond its capabilities
          errmsg = ''
  
***************
*** 539,547 ****
                  del parms[name]
  
!         for html_key in self.display:
!             if not self.parm_ini_map.has_key(html_key):
!                 nice_section_name = html_key
                  continue
!             sect, opt = self.parm_ini_map[html_key]
              if not parms.has_key(html_key):
                  # This is a set of checkboxes where none are selected
--- 544,552 ----
                  del parms[name]
  
!         for sect, opt in self.parm_ini_map:
!             if opt is None:
!                 nice_section_name = sect
                  continue
!             html_key = sect + '_' + opt
              if not parms.has_key(html_key):
                  # This is a set of checkboxes where none are selected
***************
*** 555,559 ****
                          value_string += val
                          value_string += ','
!                     value = value_string[:-1]
                  value = options.convert(sect, opt, value)
              if not options.is_valid(sect, opt, value):
--- 560,564 ----
                          value_string += val
                          value_string += ','
!                     value = value_string[:-1]   # remove trailing comma
                  value = options.convert(sect, opt, value)
              if not options.is_valid(sect, opt, value):
***************
*** 569,606 ****
              parms[html_key] = value
  
-         # check for equal number of pop3servers and ports
-         slist = parms['p3servers'].split(',')
-         plist = parms['p3ports'].split(',')
-         if len(slist) != len(plist):
-             errmsg += '<li>The number of POP3 proxy ports specified ' + \
-                       'must match the number of servers specified</li>\n'
- 
-         # check for duplicate ports
-         plist.sort()
-         for p in range(len(plist)-1):
-             try:
-                 if plist[p] == plist[p+1]:
-                     errmsg += '<li>All POP3 port numbers must be unique</li>'
-                     break
-             except IndexError:
-                 pass
- 
-         # check for equal number of smtpservers and ports
-         slist = parms['smtpservers'].split(',')
-         plist = parms['smtpports'].split(',')
-         if len(slist) != len(plist):
-             errmsg += '<li>The number of SMTP proxy ports specified ' + \
-                       'must match the number of servers specified</li>\n'
- 
-         # check for duplicate ports
-         plist.sort()
-         for p in range(len(plist)-1):
-             try:
-                 if plist[p] == plist[p+1]:
-                     errmsg += '<li>All SMTP port numbers must be unique</li>'
-                     break
-             except IndexError:
-                 pass
- 
          return errmsg
  
--- 574,577 ----
***************
*** 615,621 ****
  
          # Only restore the settings that appear on the form.
!         for section, option in self.parm_ini_map.values():
!             if not options.no_restore(section, option):
!                 options.set(section, option, c.get(section,option))
  
          op = open(optionsPathname, "r")
--- 586,593 ----
  
          # Only restore the settings that appear on the form.
!         for section, option in self.parm_ini_map:
!             if option is not None:
!                 if not options.no_restore(section, option):
!                     options.set(section, option, c.get(section,option))
  
          op = open(optionsPathname, "r")



From anadelonbrin at users.sourceforge.net  Sun Apr 20 03:41:17 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:53:59 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.28,1.29
Message-ID: <E197BK1-0005eP-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv21696

Modified Files:
	imapfilter.py 
Log Message:
Set the user interface web pages to no cache as this is bad for the
configuration pages.
Fixed the checking of entered parameters so that both imapfilter
and pop3proxy work (in my testing, at least).
Changed parm_ini_map to a simpler version with just option and
section names (html keys are auto generated).
Move the select folder config for imap into two pages rather than
one - one for folder to train, one for filtering folders.  If this still
results in pages that are too long for people with lots of folders,
then this can be further split into one page per option.
Fixed the folder selector config so that it actually works.
Now that it works, made the folder selector config accessible.
Added a check to see if parsedate works so that we handle
things gracefully if it does not.
Fixed the re that got the internal date so that it can handle the
other half of the world.
Added in a fallback option in case imap can't find the uid of the
replacement message, although I'm not convinced this is a good
fallback (better than nothing, though).
Happy Easter, all ;)

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.28
retrieving revision 1.29
diff -C2 -d -r1.28 -r1.29
*** imapfilter.py	20 Apr 2003 06:58:52 -0000	1.28
--- imapfilter.py	20 Apr 2003 09:41:15 -0000	1.29
***************
*** 176,181 ****
          message_date = self["Date"]
          if message_date is not None:
!             return imaplib.Time2Internaldate(\
!                        time.mktime(parsedate(message_date)))
          else:
              return imaplib.Time2Internaldate(time.time())
--- 176,182 ----
          message_date = self["Date"]
          if message_date is not None:
!             parsed_date = parsedate(message_date)
!             if parsed_date is not None:
!                 return imaplib.Time2Internaldate(time.mktime(parsed_date))
          else:
              return imaplib.Time2Internaldate(time.time())
***************
*** 195,204 ****
          response = imap.uid("FETCH", self.id, "(FLAGS INTERNALDATE)")
          self._check(response, 'fetch (flags internaldate)')
!         response_pattern = r"[\d]+ \(UID [\w]+ FLAGS (\([\\\w]+\)) "
!         response_pattern += r'INTERNALDATE ["]?([\w\-: ]+)["]?\)'
          mo = re.match(response_pattern, response[1][0])
          if mo is None:
              msg_time = self.extractTime()
!             flags = None
          else:
              flags = mo.group(1)
--- 196,205 ----
          response = imap.uid("FETCH", self.id, "(FLAGS INTERNALDATE)")
          self._check(response, 'fetch (flags internaldate)')
!         response_pattern = r"[\d]+ \(UID [\w]+ FLAGS (\([\\\w]*\)) "
!         response_pattern += r'INTERNALDATE ["]?([\w\-\+: ]+)["]?\)'
          mo = re.match(response_pattern, response[1][0])
          if mo is None:
              msg_time = self.extractTime()
!             flags = ""
          else:
              flags = mo.group(1)
***************
*** 227,237 ****
          # header that we add for this explicit purpose.
          imap.SelectFolder(self.folder.name, False)
!         response = imap.uid("SEARCH", "HEADER", "X-Spambayes-IMAP-OldID",
                              old_id)
          self._check(response, 'search')
          new_id = response[1][0]
  
          # now that we know the new id, we need to correct the flags
!         if flags != None:
              response = imap.uid("STORE", new_id, "+FLAGS.SILENT", flags)
              self._check(response, "store flags")
--- 228,248 ----
          # header that we add for this explicit purpose.
          imap.SelectFolder(self.folder.name, False)
!         response = imap.uid("SEARCH", "(HEADER)", "X-Spambayes-IMAP-OldID",
                              old_id)
          self._check(response, 'search')
          new_id = response[1][0]
+         # This works with NetMail, but not with Courier.  Very strange,
+         # and needs more examination.  For the moment, if the search
+         # turns up empty, we make the very big assumption that the new
+         # message is the last one with a recent flag
+         if new_id == "":
+             response = imap.uid("SEARCH", "(RECENT)")
+             new_id = response[1][0]
+             if new_id.find(' ') > -1:
+                 ids = new_id.split(' ')
+                 new_id = ids[-1]
  
          # now that we know the new id, we need to correct the flags
!         if flags != "":
              response = imap.uid("STORE", new_id, "+FLAGS.SILENT", flags)
              self._check(response, "store flags")



From anadelonbrin at users.sourceforge.net  Sun Apr 20 03:41:18 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 20 22:54:03 2003
Subject: [Spambayes-checkins] spambayes/spambayes/resources ui.html, 1.9,
	1.10 ui_html.py, 1.9, 1.10
Message-ID: <E197BK2-0005ea-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes/resources
In directory sc8-pr-cvs1:/tmp/cvs-serv21696/spambayes/resources

Modified Files:
	ui.html ui_html.py 
Log Message:
Set the user interface web pages to no cache as this is bad for the
configuration pages.
Fixed the checking of entered parameters so that both imapfilter
and pop3proxy work (in my testing, at least).
Changed parm_ini_map to a simpler version with just option and
section names (html keys are auto generated).
Move the select folder config for imap into two pages rather than
one - one for folder to train, one for filtering folders.  If this still
results in pages that are too long for people with lots of folders,
then this can be further split into one page per option.
Fixed the folder selector config so that it actually works.
Now that it works, made the folder selector config accessible.
Added a check to see if parsedate works so that we handle
things gracefully if it does not.
Fixed the re that got the internal date so that it can handle the
other half of the world.
Added in a fallback option in case imap can't find the uid of the
replacement message, although I'm not convinced this is a good
fallback (better than nothing, though).
Happy Easter, all ;)

Index: ui.html
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui.html,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** ui.html	19 Apr 2003 08:22:01 -0000	1.9
--- ui.html	20 Apr 2003 09:41:15 -0000	1.10
***************
*** 3,6 ****
--- 3,8 ----
  <head>
  <title id="title">Spambayes User Interface</title>
+ <meta http-equiv="Pragma" content="no-cache" />
+ <meta http-equiv="Expires" content="-1" />
  <style>
  body { font: 90% arial, swiss, helvetica; margin: 0 }
***************
*** 136,142 ****
      <td valign='top'>
          <img src='config.gif' width='40' height='40' align='left'/>
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;You can configure your Spambayes<br/>
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;system using the
!             <a href='config'>Configuration page</a>.</td>
      </tr>
      </table>
--- 138,146 ----
      <td valign='top'>
          <img src='config.gif' width='40' height='40' align='left'/>
+         <span id="configurationLink">
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;You can configure your Spambayes<br/>
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;system using the
!             <a href='config'>Configuration page</a>.
!         </span></td>
      </tr>
      </table>
***************
*** 362,366 ****
  
      <center>
!       <input type="submit" name="how" value="Save"/>
      </center>
  
--- 366,370 ----
  
      <center>
!       <input id="config_submit" type="submit" name="how" value="Save"/>
      </center>
  

Index: ui_html.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui_html.py,v
retrieving revision 1.9
retrieving revision 1.10
diff -C2 -d -r1.9 -r1.10
*** ui_html.py	19 Apr 2003 08:22:01 -0000	1.9
--- ui_html.py	20 Apr 2003 09:41:16 -0000	1.10
***************
*** 5,81 ****
  
  import zlib
! data = zlib.decompress("x��[{oܸ\021����\016<\025�l�އ����Zhb���ŵ�Z\034\016��ZqwYK���7߽۠3CR�\036v6\
! �>�:�W+���p\036�\031��o.�_,~��b׋wo��\017o���y���_N/���ťnx1�L�\"�i!K\
! �R\036��W�{��_�7e\022ӧ�\021~���\005�ѹGO^p��$�;Q�\037\012��?���W|)�c�c�rG\017��\
! v�\023[�����N�1�K\036\037�b+��mD� J��g,��Z�36a������0�\036��J�\011�m\021��+>\
! �ez\017�*V���j\002?Kj�\007\011�\026�#�\033�\000�j�^M^LV+l\033-�!���\033掷B�7�c��z<H\
! ���{]R��ǚ�Q�Ӕ&\011��~��*�`��D�Lg,�Q$������8\026+�1}y��W��\011U\036���T\
! \0314e\037Y�b\031�0\006�C�BU�*�u%�q��!⹐\027����Ykٍ��/�!\021E��B�W�\002��+>6K�\
! �\034�\035�-�\0225����e�W�N��\031�ʨ܀\036�|�\016D��lG��Պ���\000\037�@>+\030;�Р�7\\\031\
! �7�\003�I���y.P9��\0136��\023R�^�a}5�\033�{����)b��2����R��-�\024K�g:V�\032<��\
! �ޜL���Կ%�g�b�������ÁG\022\"z\034|��\035\012~\036�\007��yQ��ڀ���\024\031Oi\004��D�^0�\
! ɚ\025����oFk��\031��:=�yX$2�bᏃ�iXdg�\007PhQ3\023�]�\023�'�r\025U��{����_D�z\
! E�<s�sͩJ\004n��6�X�D��\017���|̇�\003SKi����Ur����z�\013\010LK\024%�$\022.�\013m͞\
! Y�g�[�y�y\021\000�za�ϰ-/�\015Ȃ�F\026l%cq��K\025��悾\035�H�d\012B(7��J�\037�4:^\011\021k\
! \022jE-\025F\016ied�6\"�\02398�\021c\013x�\000�_U�&�I��\002GP\034��E\020\022r\001QB0���\022\025\034&\006��,\
! �bN/JM\"��R&�\024�v P\010$q�cz7\005qB��\015/�|��9V�G���\035C/#\026\006s����\001�(K\
! aY�c�*�T\012�.`qZ�7�w\"�ނQ\032!2�ŗ\000?�W�\015`�AF�\003�\"��c\025�\025\\\017�4��\035��g�\
! �$�\036���i�2U\024\022��HӸ�ˍ�f-L\032�\012\021\025(�Ph�\031�mpQ�Q\004�SF�ᒯ�Hޡ�\005��f\
! Wn��\030��h>�\\�z�Ta�x����Fm5�[��S��]��W$�P}��Pn4\001x��\005H�W�&\0140\
! M�\006�2ͪ�̡��r�\011�8�?\036h\\\\���c��ν��\033\033�j���&\027l�*GX�\012���s�$��J6\
! k�\036���\037��~�{5����@\014���mī\001Й\033}���~�O>���_L�\000~�cl\001�\003��Kga{�\
! C�g�Le\"=��3������!\0042\036\035\034�I)RK �00BG\005�J�\007Ht_2Y\016~\005���ݵ\033\037<�˳��\
! ���)E\030�㝏e���\034.FD\015��]lx�\026��?\\�e���1�Y/~\030[�S��ƴѦ�OT\022�y��\035�\
! �A�\000�E��������+\016���\012X�xQ��B�����\000�\004�?b*�\023`+�o<����UŠe�K�gR�\
! \005��u\032�c\020�\021\014w��c�\001\014M��\017w֫B3���7?fK�\023N������\020�\021+1y\002k�6X�2�\015�\
! \006'��+\\8xE2Ep���6�#�c��:\012\026��\006%�1\015�͎\011^����[b\027��{��\021\026�P�\007�\
! N�(�AO^�3 \024����3\013\024\\��\005\004��7�]\035�\034 f�=�M\032�\033X��-E\034��%&=~��<�\003\
! \012����7�}�\036���?\001\014ES3r�e\004V\004tz\024}\011�p\001��h\021\004\013!��;�\021��:\001\001�\023\027\006j�\003�\
! i��\032o\026%/�B�M3��ć0�ȗ�-�t0\036��|5��\025t�Z�/g\004�2\014��\021<X�;U�Ø��H\012�\
! ��\003�_�t =�$4\005��\006�5c��۽\035�թ�G訃w:�\025�\005�\007\005�.��\030�#.�b��uAv\003�\027�\
! �Y�A�a>�\002�=4W�PKm�n��u�\002�{&?<����*j��<\035��\025l\020�k��c����%$�2n��\
! ysʨ\021�S��\004d4\017���\033���\0359O/�N�\023#��8\014��텾��T�\010aټ�`�\010$��Ch�p�H\
! \036^�R>\010�-X\002���,f\035{q��4�N\000*��^��<�L��u�G?5M�J\036�7K+{\"����h-�\
! +�ak�Y�*���3!�����a��Q��\016�!-�\\t�U����\005ʃ\011�2\010b�>uV���:s �m��1\
! ��!����@t\006���+��7N���\031��qw��\024\000\012���\\��\020`��wy�O���#$\001K�\034\
! �4 zL\013�&{�,\037�Ů(E\002�� ��\026pS;�3����Y�R�^XK\030�rr�a�Q?�1uAj\001��\015@\
! h��F�\026�\\^���Ty��Bf�+�\020�J0'Q\030�bEHzI\035k�\003\034�\013�@�LmTѐ�#k\0215Rь��\
! -}��Q$$�:��x�BQhØGw ��\001\001K&\020\030um�\030\035��;�R����\005�2A�j\010�\027\033����A\
! ��+�\0060�\014��\004Y�\000 \013L��Q]\037�\002��a�\002)���\003T\004b��X�܇��?�2�\021�\036�\021�Ȥ��\
! ;��1�%^�h�\014��KY,y\036�1#��\011�\000~�\0220[�\004�KZI�u�h��B�\010��@\030�B��j�^*�s\
! �R�1�\001�\002���\026��T��\037#�\010`\013�\022ڹ\017RT \006\004o�Q'F�ĵ�'\010���z�~\032\034�q��\021\
! �ւ\015�{\037�:H��AQ��,-\007k������\017\025���pw��R\025$d\034pm$\013�\017HL�Jh\013�h׺\017\027(�\
! ���\036z~)\003�9�.r�CEL��\033\033�]�2����x�W���[?\030����tq�z��'�jV��L�j�\
! p�#�X\012�υ2%�O\015?r�\016 o�\022��#�`ϟ���Q,�5de�9;9l�~jK����3����g�n\
! �@B��\031�lN��\004��׿>lw��ߪ\002�8���\010��I�<\036QÁ?�\017\007�Ep��H���sv��\033\
! �_|�R���jb�4Œ�Z��R�U[�_@\03088<���4Ar>��`��\022\003k�G����<����矛�\
! ��eO�t��n�\007ݜ÷Y�N��C�}\035\006x\013'\002�U��Y��\022\000X��\006^\007����0Z/\025�Q��*\
! y�ٲ�:�\002砶9�аq�0n�\032k�56�#/�\021D*\035U@߼�<S�\036�k�(�\021-|�\005� �\021\035��\005\
! T06\022\031|h\037�h�\012��\002A�������6e\002{��\017o�=\017��;C�`Ee{s4�ao/�\033̭�98\017���\
! z�r�����o�\017;gY�u\016,�}��[��H��e\032�a`]3�7�\003\007�'�tTW+{T\014l_b5\"�{��\
! ^(�y$��`�\022v32�?^�8\034���H������{\035����\023L��zM<���]\0260�sC:|��2@��\
! \000~��O�Z`���b���\036����\022�Q��ͅ1O���\006��j��_��\010e�Ai\017��d�=i[�f��\
! S�������K�nU\026+\036��<\012A�yu�$����\025C�\000$FKJ���\031�K��8�%�N�JR1^�f��\
! 9N¦�\017\011\036�\004��\022�\027�j���>-ԓ�{����H\022����}N\007\032�җ�F�u�\005�,\005\005�#\001\023*\017)\
! 嚹�LD��/r3SI�E���Ou���ǓA�\027�ӝ�9����A\033�\020x�n�ö�\001���kM}z�/$\
! w�$��\036?O���m�Ye���\003�>�='�Z�\001m��\003\004ǡ�\003\020䌎e��\002!��\036;E\026���vS�f�\
! H�\003�'�\017�\017�.\"l!\027�S%�ݰ\035�͍)૿�+�/Bl��QH'���I�:��°W\000�\011�j\
! N��Q|4$�Ϯv\005�� ���:\035��`s�x\034��֘>���~��BwJU\021\031ك\023k�xd���+�@\011ޕ\
! �,�+Gu��Y�WI\010�\000\007h�u��SbŶ����������vCj�8�MM���W�\020��U�C\011��N\027j\
! \032���G��\004g\024\006ϣ�A�H���m�^0\031����>2�\004\027kŷ������;��\"\035U��f�(\036{�b�\
! !�$fL���O\034��s��?�t�\007�\036l����\021���\002\013Q��Y����н2֜O\021��[bl:�M\017\
! �\023}�d\0217��l��{A\023\"˕�����/ȴH\015\011�7�\001\023C��=\007Ȃ[QVy��q�7��F��G��t�\
! >\033�\017������`#��\015v/\016�����xTs�\016�=�su{�n߽�}g��G\027\014��@\035�����ynPk\
! �I�r����a-\033��\000\020��L�V$J�\013(��2^��\017x���es��\020�\012Q�S\013*'�, ��|^��t\025\
! I�t�۷n�����\006��\037�́�83�Z\006�\031�]4�\023������WN��ځ��ŭ;\012b\003\030ɴU\"Y\\\
! \032\\�-xn\025���5�1\017E�\005o��^���/.��<���=\035}{��g�\035�M���2`��\003��\017\011ϼ\
! 6��NF��\021q\006��l���k��\022�_��.\004\000�5td��Ƽ,@\032�\021\036o\007w�\"�\037�=\037�N��>�eZ\
! �'C���M*;�}�z�\007�j.b��~;�_\034\014�`\026�g����\034L�͝��7e\001U9�J�\0346[&��\
! *���\031Hd��\025ؑ���x�rR'ٍ��t�\014�\027���ڵ=ŴS=�n�$\007��T\014��\023�\033\025�N^>�\
! r'm\005���<��Ԭo�?fQn���9>��o��~\0327p\035\013�^��5�L&�^�\031S �G|}-��*5��\
! @u�`%����\021�\035\020^�^k\"�\005\006��k\013\006�BGT��\004M{X�\027�u�i��&>�b��/�Q���Hm\
! ӡTO_\022����P�μ#\024�~�T\024���fJ��\020{\015\025���Q�\022��6g,@����\000gkēɳ�\023��\
! S����¤)��zf��~\013�>�\007 ܽ��\\L��=������Jas��t¦/f�\027��\023v2���=\030�x\
! 0s�e6\033������\023�T�\036;���n%�)\035jg�Ynk�\010Y�Q�<�P��r���!�I�A\017�U\\�l��\
! �� �3f\007c!MskR�&Up�m�\030\025��_\015�?W�'\032��]")
  ### end
--- 5,82 ----
  
  import zlib
! data = zlib.decompress("x��[{o\033�\021����\016�-��Q[\017;I���hb���ŵu-\016��Ai)����v\037�ՠ߽3Cr����\
! �\011�\011,�\034\016���͐�~s��|���%��xϮx��\017��;\036\016�rz>\034^�/të�h��\031OrYH\
! ��h8���\013��j�)�>\005\017�E$�\014g\036}�۔�\013�\0239�!\027\031�CR�lŗb:�\0168&\026\005g��H\
! ��_K�0�3���ǖ\012z'��K��/7�c��\001����D�8\036��y��Y\026*ܱOl\005\035&췣\027�g\
! �GG,��<?b\033\021=�B.�\031�y��Ʉ��߿���\013X�\036��Je1�m\020��+>�dr\017�*Rل�j\004\
! ?Kj�\007\011\"\025�\023�\033�\0002��ތ^�V+l\033��2n�;�\012��\000�\013\025���A�-���\000�<��\015\026<Ih\
! �\005_ޯ3U&!̴\034\011�錥<\014e�����\036Gb\0054ƯϾ��U?\013��\";.T\012M�#�U$C���f_��\
! *\012\025w�\022ߨJ�\020�˿\011�wz����Z����\020�<�k���@���\025��\0222-\007xGcs�D��{�yt�\
! �շ#�wƶ2,6�\007�_�\003�c ے�j��bt�Ç+��\012���7��\015WF���@r�>�=�\004*�\026t\
! �z\025tD*��ٯ��s�q�Pt:=G\014�Qd2\025w*����O���c)��\015]������YE�[�~�/��\
! ��x3�JBDw�_<z�����-#��3_\033�\037��<�\011�\000�\000��\013�2^�<[�|�f��+��H�\
! ���\027y,�0\022�0x�,��\014�\000\012\015jf\"�\013v��di��rY|�����X�.�(O��\\s�b�[�M&\
! V0\021<��\025��\016y�t`j\011��r]��R\0160\0204Yo>���DQrH\"�29���\025zƺ����W\001�\027\006�\
! \014��ހ4�od�V2\022Gl�T�\010*.�鈅b%\023\020B�\021,R���'��J�H�P+j)1,I+#��\026��\
! �\011\017\030���\007����5�T�\016�8����.���\011�\022���\"�KTp�\030�U\"Ө�8�(4��L\012\031��R,�\
! �@!�Dю��\024�\011�.6�h��k�X�\0379+Sv\014��X\030�\015&\013��\007D�(�eU�]�8U\011�;��i\011^\
! �>�(|\017Fi�Ȥ\026_\014��_E6��\007\031Z\016,������\027p=��4Ew\030\001��\036\023�{�\017֦�KU�Kp�\003\
! M�\022b��f%L\032�\010\021�(����3���\022�\010ħ\014-�\005_\037��\027\002\026����]�\001'b�\003�F��0u\025�\
! -R�]�q\032\021'\033���nUvO�\036vU�^�,\026�\021\002B��\004�e�\027 �_\031�0�4\031\033��$-\0132���NJ]*\
! \000@��x�qQ)�f��_�y�74�U�\031�M��N���j\025�m[g<�y��l�X=Z%�?�g���f��*\
! \027��\030lg�)ۈW\001�37�T���j�<��㟏�\000~�Cl\001�\003��\012ga{�C�g3�R�\034x�\031xG��\012\
! �\020\002\031\017\017\016��\024�%\020�\031\030��\002%�\003$�/�4\003���\006��ڍ\017^F�Y��W[��\"\014��N�2�I\016\027\
! \003�\006k��7<Y���\037.ɲ�^�\020��\023?���*�lc�hS�'J\011��R��kǠ�\003�\"O|�����\025\007\
! X�\027\012XOy^��B�����\000�\004�?b*�\023`+ѯ=����T��e�\013�gR�\005��m\022vc\020�\021\014w��\"�\
! \001\014M��_�W�f ��!o~̖('�\034����\033!�#V`f\006֎m�\\e�\033r\015N8Y��p��d��\020\023��\
! �mKH��u\024�E�\015J\002c\032D�\035\023<ߵ��;\021���.��w\002k-,血\017t��Qf��<�f@(�Q2�Z\
! ��\">/ `\024�C����\0001��Ym�H��*\027��l)�\010F.1��k�Ud�\024P�%\007�^k�y�����3�\004\
! 0\024M���\027!X\021��P�%(�9��E\020,�<�o�G\000��\004\004H�\\\030��\017P�%�k��\027�(s�7��W#\037\
! �\030\"_�nA���O��,\032V�\002k\015��\021\004�0H2G�`\005\037T^�c��\")О�\016\030\016Ӂ����\024�N\032(\
! V�\001kn�vTW�V��Q\007�\027+�\013�\017\012B]X�\021�G\\��\"\003��\006�/�\025�f��\027ٰ\015|��\\�C\015�\
! պ�2׍s|�L~8����*j�m�\016�M\005��T&񸻀DZF�\036�\037�O\0315\"~JГ�����5�\
! \032bw~K��\013�����c:\\\004G��B_rf�I��lVQ0Q\004\022��!4p8�%�?oA)\037��\026,\001I�n擖\
! ��sr\032t+\000�BO/py\036�&�R��:ף���P\005�����=\021F�qC�\026ɕİ��I\031c�К�����\
! �aW�Q��\016�!��L�������9ʃ\011�2\010b�>�V��OZs �M��1W�!�������@t\006��\
! �\033��\033���n�q��;MU\012\000\005Z��s��V\010�l�\017{MU\023)3R����;ݺ<v�\010��\022\013\014����!\
! ��̖��!���B���\015Pi)\0137%\006=�\037��K ��%�Agg\\�:A��ğ����5\007��\004.$Ⱥ�Jp\
! ި\001h��\027*��X�Hu�\021�]\001f(rô�)�3u�l\026�#��r���QyMB��dV�I3�\0077�Y�G\031�\
! ��ش'R2\013E��c%݁�Z\005\022,�@@�5\015c�����J!��\027�\026l�\013ժ!`�o���S\020&d\021��\
! .ʢ\000Y�\000X\013,\001\020񣪮��/\011��9R�!�\007�\011��\013�\022�\017�.0�\035#\030=\024#��)\033\030��\"�t�x\
! !�5�Ѓ.d��YȆ���'�\021��J�l�\023h.i%5F֣�Jr\015>8�\003a#\013]֪\011�頀S�j�a\015�\
! \024\000�~9w|�)\021P��od\030\002�aXz�� E\005b@�g���\037���\031\002\011(�\036���\016�x��\017hk�\015��\
! E�\016\002ip���X\026���r�GB��\012��c��Fy�\022\0229\016x8�9�\007$�N\005�\001{�Kއ\013��~L|\017=�\
! ���<f\033qw!&&�Y�����.3��eaZ=��?p��\017���7?�_����ɤ�e�5S%�'\034�H:΂\
! �u�Li�S͏\\�\003���\030��\000���˗��f\020�d\015�\\0c'���OM)���ZC\032�|���\016$t\034�1\
! ɦ4�L\000/~���f�Oݭ�\001�S)\034�����\003��\0015\034�\023���8\005\027Z��+���)��j\000~�%J\015�\
! �����\024Yf�t\007�z��\";�0ppx�\035��y��|����Y)z����+��|5\037���?��\012)˞���\
! ���\017ڹ�o�g�\032��q�:\014�\026N\004�-\0276f5�Q\000n�\007\033x\0350�s���\023�v�\024\026G}����f�v�\
! \013���f<E����@ƫ�mR۔���G\020�tT\001}�\002�b��Fq�h��\022�6�\003��\002\025��D\006�\
! 4���f-���B�\014�������\005{���o�=G��;CidI�~s��ao/�\032̍�88\017�\015t՗ejy�\
! \015c�\036\037�����#X���\033��H��d\022�a`=4�7�\003\007�'�4VW9;T\014�_b\025#�;u�N(�x(�\
! �`�\022v\0232�?^��\037���P������\012^���\011&P�:����\005L\011ݐ\016��]\006(�u\030��f���\
! Ǵr�Y�vW��-�Y-�\036�\010���\"��=�\\P�\023]�z��K�P�\036����V�ّ�EnFh:5\030~��<\
! \015���^W���a\027ˣ\020t�WEN\022Jc�\0331�\011@b����\012�� ��C^p��.%\025�5i�m��$l*��\
! �%\000�\024S��VCg\006�SF=\031��ʪ�\033I�\020\035��� DP��ݨ�ʱ\000�%�`t�`B�!�\\\023�\006�H\
! \024�Enf*(���\026\034��.��|<Q�}1=�ٝsQ��w�X���v\003\036��\017�\006n]k���|!��g����\
! y��oM�*c�n\037`���9��\032\017vK,\035 8^(<8A��8'\011-\020�z�Su���n�\025s��X=�=��\
! 0�p�\"�\026r�?�\"���A�\\�\002��+��\"�6�J\012��\012�$5�>A�OG�]��\012�0A_͉�=�\017�\
! D��ծ �\033�ٿ^���\037l�\027�c��\032��\027?�o��N�*\"C{�bm\027�:q�F\020(�ۂ\027y�j\
! �0��2^\000#�\001\032oU�j�f�m�J��3>9}�\"^��<MiS\021z���\023��3��\013\011��N\027jj���G�\
! �\004g\024\006ϱ�A�Hی�m-�`4�ͷ�}b�/\011.֊oD\016\021�\0111�:9E:�T��\002Q<�XƾCfI̘\006\
! �A�8\000\007�\024�\031�D\017�O=�Z�\003�#\026�{�\005�@�\006gɪc�C��Y}�E4�n����=\010OtѓE\
! ��dz����N�,��\036\017�c� � �'��\000\007L�\001\012�� \015nDQfI]�mިÛ\004v\037��A��?t�\
! ����#�� &6ؽ8�~���Q\021�;����U핺}���uv\036]L\020*\005u�\016�C��A�&'�K}�\
! �Ƈ�l,�\002@��2\025Z�(y/�l��xa/M��,s\007�-�C��E��1��<��\010\013�YE��\025&�сq�\
! �}��\027\033��~04\007��Լj\030�g�v^�k�.���_:}��x{�t�7�(�\015`$�F�d~ap�G��\
! �U��BW�F|!\"/x�\037��h�^���9�3(���ѷ~N�xfۡ�\004;�/\003������<��\030�=\031m\
! �FD)����\026���>I�{Ѣ�\020\000`WБ�\"j�\000��G�zӻC�����s��{Y�^��{��\032�\
! ݤ�#����ѣ��E\037��lwq0��,��T/u�ٛ|��`�o�\002�r�V�Z9l�LZ�\007�e���A�\
! �&=+�#G������J�k\037��\020\031\010/����k{�i�z\000�\034I��]�\010\034[+��*ꝼ~�=�N�\012��\
! �{R\001�Y߄ʢ�>��w�����\021+�i\\�5.�z�>�x4\032�{�gH��\033��u:��TD��C�۝�\
! \033�L�����J���-\020^\015h+��\005b����\0142���XqB�\035x�\014��c�F���ZM���\006�_|9k\
! S\026��&}ٟ�7����9��yG���^�p�����)�L�V�^�J\025X\030�id\016��&�\006K[�\036�^\
! �\035�L�2]���*u���3#B�\033��ɿ%��m.玓���\000��\005\037T\002��d�#6~5\031���������\
! �������(��p��n\007��x����a\004���ͺ���ck���\"��v�pF}\0115�Ŏ2��&W\007=�\026v\
! M����^�\004Θ\035��5ͭ�\"�����AcT�������\037����")
  ### end



From timstone4 at users.sourceforge.net  Sun Apr 20 18:36:26 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Sun Apr 20 22:54:41 2003
Subject: [Spambayes-checkins] spambayes pop3proxy.py,1.75,1.76
Message-ID: <E197PII-0007Ct-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv27694a

Modified Files:
	pop3proxy.py 
Log Message:
Useless imports and comments removed.  Changes onStat to add a fixed
fudge factor to message sizes, rather than try to make some half-baked
attempt at guessing how much will be added.  Stat is used by MUAs to
determine if a message is too large to download (today), and to display its
size on the user interface... that's about all, so a ballpark guess is not
particularly dangerous.

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.75
retrieving revision 1.76
diff -C2 -d -r1.75 -r1.76
*** pop3proxy.py	20 Apr 2003 05:00:27 -0000	1.75
--- pop3proxy.py	21 Apr 2003 00:36:23 -0000	1.76
***************
*** 51,64 ****
  Web training interface:
  
-  o Review already-trained messages, and purge them.
-  o Include a Reply link that launches the registered email client, eg.
-    mailto:tim@fourstonesExpressions.com?subject=Re:%20pop3proxy&body=Hi%21%0D
-  o Keyboard navigation (David Ascher).  But aren't Tab and left/right
-    arrow enough?
-  o [Francois Granger] Show the raw spambrob number close to the buttons
-    (this would mean using the extra X-Hammie header by default).
-  o Add Today and Refresh buttons on the Review page.
- 
- 
  User interface improvements:
  
--- 51,54 ----
***************
*** 66,71 ****
   o Deployment: Windows executable?  atlaxwin and ctypes?  Or just
     webbrowser?
-  o Can it cleanly dynamically update its status display while having a
-    POP3 conversation?  Hammering reload sucks.
   o Save the stats (num classified, etc.) between sessions.
   o "Reload database" button.
--- 56,59 ----
***************
*** 74,82 ****
  New features:
  
-  o "Send me an email every [...] to remind me to train on new
-    messages."
-  o "Send me a status email every [...] telling how many mails have been
-    classified, etc."
-  o Whitelist.
   o Online manual.
   o Links to project homepage, mailing list, etc.
--- 62,65 ----
***************
*** 105,140 ****
   o NNTP proxy.
   o Zoe...!
- 
- Notes, for the sake of somewhere better to put them:
- 
- Don't proxy spams at all?  This would mean writing a full POP3 client
- and server - it would download all your mail on a timer and serve to you
- all the non-spams.  It could be 'safe' in that it leaves the messages in
- the real POP3 account until you collect them from it (or in the case of
- spams, until you collect contemporaneous hams).  The web interface would
- then present all the spams so that you could correct any FPs and mark
- them for collection.  The thing is no longer a proxy (because the first
- POP3 command in a conversion is STAT or LIST, which tells you how many
- mails there are - it wouldn't know the answer, and finding out could
- take weeks over a modem - I've already had problems with clients timing
- out while the proxy was downloading stuff from the server).
- 
- Adam's idea: add checkboxes to a Google results list for "Relevant" /
- "Irrelevant", then submit that to build a search including the
- highest-scoring tokens and excluding the lowest-scoring ones.
  """
  
! try:
!     import cStringIO as StringIO
! except ImportError:
!     import StringIO
! 
! import os, sys, re, operator, errno, getopt, time, bisect, binascii
! import socket, asyncore, asynchat, cgi
! import mailbox, email.Header
  from thread import start_new_thread
! from email.Iterators import typed_subpart_iterator
! import spambayes
! from spambayes import storage, tokenizer, mboxutils, Dibbler
  from spambayes.FileCorpus import FileCorpus, ExpiryFileCorpus
  from spambayes.FileCorpus import FileMessageFactory, GzipFileMessageFactory
--- 88,100 ----
   o NNTP proxy.
   o Zoe...!
  """
  
! import os, sys, re, errno, getopt, time
! import socket
  from thread import start_new_thread
! 
! import spambayes.message
! from spambayes import Dibbler
! from spambayes import storage
  from spambayes.FileCorpus import FileCorpus, ExpiryFileCorpus
  from spambayes.FileCorpus import FileMessageFactory, GzipFileMessageFactory
***************
*** 142,146 ****
  from spambayes.UserInterface import UserInterfaceServer
  from spambayes.ProxyUI import ProxyUserInterface
- import spambayes.message
  
  # Increase the stack size on MacOS X.  Stolen from Lib/test/regrtest.py
--- 102,105 ----
***************
*** 155,164 ****
          resource.setrlimit(resource.RLIMIT_STACK, (newsoft, hard))
  
! 
! # HEADER_EXAMPLE is the longest possible header - the length of this one
! # is added to the size of each message.
! HEADER_EXAMPLE = '%s: xxxxxxxxxxxxxxxxxxxx\r\n' % \
!                  options["Hammie", "header_name"]
! 
  
  class ServerLineReader(Dibbler.BrighterAsyncChat):
--- 114,119 ----
          resource.setrlimit(resource.RLIMIT_STACK, (newsoft, hard))
  
! # number to add to STAT length for each msg to fudge for spambayes headers
! HEADER_SIZE_FUDGE_FACTOR = 512
  
  class ServerLineReader(Dibbler.BrighterAsyncChat):
***************
*** 440,444 ****
          if match:
              count = int(match.group(1))
!             size = int(match.group(2)) + len(HEADER_EXAMPLE) * count
              return '+OK %d %d%s\r\n' % (count, size, match.group(3))
          else:
--- 395,399 ----
          if match:
              count = int(match.group(1))
!             size = int(match.group(2)) + HEADER_SIZE_FUDGE_FACTOR * count
              return '+OK %d %d%s\r\n' % (count, size, match.group(3))
          else:
***************
*** 496,500 ****
                      state.numUnsure += 1
  
!             # Cache the message; don't pollute the cache with test messages.
                  if not state.isTest \
                      and options["pop3proxy", "cache_messages"]:
--- 451,455 ----
                      state.numUnsure += 1
  
!                 # Cache the message; don't pollute the cache with test messages.
                  if not state.isTest \
                      and options["pop3proxy", "cache_messages"]:
***************
*** 643,647 ****
              # where they do not need to do any more regular training to
              # be satisfied with spambayes' performance, we expire old
!             # messages from not only the trained corpii, but the unknown
              # as well.
              self.spamCorpus.removeExpiredMessages()
--- 598,602 ----
              # where they do not need to do any more regular training to
              # be satisfied with spambayes' performance, we expire old
!             # messages from not only the trained corpora, but the unknown
              # as well.
              self.spamCorpus.removeExpiredMessages()



From timstone4 at users.sourceforge.net  Mon Apr 21 06:18:49 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 21 08:18:52 2003
Subject: [Spambayes-checkins] spambayes pop3proxy.py,1.76,1.77
Message-ID: <E197aG1-0005MV-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv20566

Modified Files:
	pop3proxy.py 
Log Message:
Didn't catch all uses of HEADER_EXAMPLE, which was removed

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.76
retrieving revision 1.77
diff -C2 -d -r1.76 -r1.77
*** pop3proxy.py	21 Apr 2003 00:36:23 -0000	1.76
--- pop3proxy.py	21 Apr 2003 12:18:45 -0000	1.77
***************
*** 411,415 ****
                  if match:
                      number = int(match.group(1))
!                     size = int(match.group(2)) + len(HEADER_EXAMPLE)
                      line = "%d %d" % (number, size)
                  outputLines.append(line)
--- 411,415 ----
                  if match:
                      number = int(match.group(1))
!                     size = int(match.group(2)) + HEADER_SIZE_FUDGE_FACTOR
                      line = "%d %d" % (number, size)
                  outputLines.append(line)
***************
*** 419,423 ****
              match = re.search('^\+OK\s+(\d+)(.*)\r\n', response)
              if match:
!                 size = int(match.group(1)) + len(HEADER_EXAMPLE)
                  return "+OK %d%s\r\n" % (size, match.group(2))
              else:
--- 419,423 ----
              match = re.search('^\+OK\s+(\d+)(.*)\r\n', response)
              if match:
!                 size = int(match.group(1)) + HEADER_SIZE_FUDGE_FACTOR
                  return "+OK %d%s\r\n" % (size, match.group(2))
              else:



From timstone4 at users.sourceforge.net  Mon Apr 21 15:15:40 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 21 17:15:50 2003
Subject: [Spambayes-checkins] 
	spambayes/spambayes/resources ui_html.py, 1.10,
	1.11 ui.html, 1.10, 1.11
Message-ID: <E197idY-0003ra-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes/resources
In directory sc8-pr-cvs1:/tmp/cvs-serv14745

Modified Files:
	ui_html.py ui.html 
Log Message:
Cosmetic changes to configuration page

Index: ui_html.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui_html.py,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** ui_html.py	20 Apr 2003 09:41:16 -0000	1.10
--- ui_html.py	21 Apr 2003 21:15:36 -0000	1.11
***************
*** 5,82 ****
  
  import zlib
! data = zlib.decompress("x��[{o\033�\021����\016�-��Q[\017;I���hb���ŵu-\016��Ai)����v\037�ՠ߽3Cr����\
! �\011�\011,�\034\016���͐�~s��|���%��xϮx��\017��;\036\016�rz>\034^�/të�h��\031OrYH\
! ��h8���\013��j�)�>\005\017�E$�\014g\036}�۔�\013�\0239�!\027\031�CR�lŗb:�\0168&\026\005g��H\
! ��_K�0�3���ǖ\012z'��K��/7�c��\001����D�8\036��y��Y\026*ܱOl\005\035&췣\027�g\
! �GG,��<?b\033\021=�B.�\031�y��Ʉ��߿���\013X�\036��Je1�m\020��+>�dr\017�*Rل�j\004\
! ?Kj�\007\011\"\025�\023�\033�\0002��ތ^�V+l\033��2n�;�\012��\000�\013\025���A�-���\000�<��\015\026<Ih\
! �\005_ޯ3U&!̴\034\011�錥<\014e�����\036Gb\0054ƯϾ��U?\013��\";.T\012M�#�U$C���f_��\
! *\012\025w�\022ߨJ�\020�˿\011�wz����Z����\020�<�k���@���\025��\0222-\007xGcs�D��{�yt�\
! �շ#�wƶ2,6�\007�_�\003�c ے�j��bt�Ç+��\012���7��\015WF���@r�>�=�\004*�\026t\
! �z\025tD*��ٯ��s�q�Pt:=G\014�Qd2\025w*����O���c)��\015]������YE�[�~�/��\
! ��x3�JBDw�_<z�����-#��3_\033�\037��<�\011�\000�\000��\013�2^�<[�|�f��+��H�\
! ���\027y,�0\022�0x�,��\014�\000\012\015jf\"�\013v��di��rY|�����X�.�(O��\\s�b�[�M&\
! V0\021<��\025��\016y�t`j\011��r]��R\0160\0204Yo>���DQrH\"�29���\025zƺ����W\001�\027\006�\
! \014��ހ4�od�V2\022Gl�T�\010*.�鈅b%\023\020B�\021,R���'��J�H�P+j)1,I+#��\026��\
! �\011\017\030���\007����5�T�\016�8����.���\011�\022���\"�KTp�\030�U\"Ө�8�(4��L\012\031��R,�\
! �@!�Dю��\024�\011�.6�h��k�X�\0379+Sv\014��X\030�\015&\013��\007D�(�eU�]�8U\011�;��i\011^\
! �>�(|\017Fi�Ȥ\026_\014��_E6��\007\031Z\016,������\027p=��4Ew\030\001��\036\023�{�\017֦�KU�Kp�\003\
! M�\022b��f%L\032�\010\021�(����3���\022�\010ħ\014-�\005_\037��\027\002\026����]�\001'b�\003�F��0u\025�\
! -R�]�q\032\021'\033���nUvO�\036vU�^�,\026�\021\002B��\004�e�\027 �_\031�0�4\031\033��$-\0132���NJ]*\
! \000@��x�qQ)�f��_�y�74�U�\031�M��N���j\025�m[g<�y��l�X=Z%�?�g���f��*\
! \027��\030lg�)ۈW\001�37�T���j�<��㟏�\000~�Cl\001�\003��\012ga{�C�g3�R�\034x�\031xG��\012\
! �\020\002\031\017\017\016��\024�%\020�\031\030��\002%�\003$�/�4\003���\006��ڍ\017^F�Y��W[��\"\014��N�2�I\016\027\
! \003�\006k��7<Y���\037.ɲ�^�\020��\023?���*�lc�hS�'J\011��R��kǠ�\003�\"O|�����\025\007\
! X�\027\012XOy^��B�����\000�\004�?b*�\023`+ѯ=����T��e�\013�gR�\005��m\022vc\020�\021\014w��\"�\
! \001\014M��_�W�f ��!o~̖('�\034����\033!�#V`f\006֎m�\\e�\033r\015N8Y��p��d��\020\023��\
! �mKH��u\024�E�\015J\002c\032D�\035\023<ߵ��;\021���.��w\002k-,血\017t��Qf��<�f@(�Q2�Z\
! ��\">/ `\024�C����\0001��Ym�H��*\027��l)�\010F.1��k�Ud�\024P�%\007�^k�y�����3�\004\
! 0\024M���\027!X\021��P�%(�9��E\020,�<�o�G\000��\004\004H�\\\030��\017P�%�k��\027�(s�7��W#\037\
! �\030\"_�nA���O��,\032V�\002k\015��\021\004�0H2G�`\005\037T^�c��\")О�\016\030\016Ӂ����\024�N\032(\
! V�\001kn�vTW�V��Q\007�\027+�\013�\017\012B]X�\021�G\\��\"\003��\006�/�\025�f��\027ٰ\015|��\\�C\015�\
! պ�2׍s|�L~8����*j�m�\016�M\005��T&񸻀DZF�\036�\037�O\0315\"~JГ�����5�\
! \032bw~K��\013�����c:\\\004G��B_rf�I��lVQ0Q\004\022��!4p8�%�?oA)\037��\026,\001I�n擖\
! ��sr\032t+\000�BO/py\036�&�R��:ף���P\005�����=\021F�qC�\026ɕİ��I\031c�К�����\
! �aW�Q��\016�!��L�������9ʃ\011�2\010b�>�V��OZs �M��1W�!�������@t\006��\
! �\033��\033���n�q��;MU\012\000\005Z��s��V\010�l�\017{MU\023)3R����;ݺ<v�\010��\022\013\014����!\
! ��̖��!���B���\015Pi)\0137%\006=�\037��K ��%�Agg\\�:A��ğ����5\007��\004.$Ⱥ�Jp\
! ި\001h��\027*��X�Hu�\021�]\001f(rô�)�3u�l\026�#��r���QyMB��dV�I3�\0077�Y�G\031�\
! ��ش'R2\013E��c%݁�Z\005\022,�@@�5\015c�����J!��\027�\026l�\013ժ!`�o���S\020&d\021��\
! .ʢ\000Y�\000X\013,\001\020񣪮��/\011��9R�!�\007�\011��\013�\022�\017�.0�\035#\030=\024#��)\033\030��\"�t�x\
! !�5�Ѓ.d��YȆ���'�\021��J�l�\023h.i%5F֣�Jr\015>8�\003a#\013]֪\011�頀S�j�a\015�\
! \024\000�~9w|�)\021P��od\030\002�aXz�� E\005b@�g���\037���\031\002\011(�\036���\016�x��\017hk�\015��\
! E�\016\002ip���X\026���r�GB��\012��c��Fy�\022\0229\016x8�9�\007$�N\005�\001{�Kއ\013��~L|\017=�\
! ���<f\033qw!&&�Y�����.3��eaZ=��?p��\017���7?�_����ɤ�e�5S%�'\034�H:΂\
! �u�Li�S͏\\�\003���\030��\000���˗��f\020�d\015�\\0c'���OM)���ZC\032�|���\016$t\034�1\
! ɦ4�L\000/~���f�Oݭ�\001�S)\034�����\003��\0015\034�\023���8\005\027Z��+���)��j\000~�%J\015�\
! �����\024Yf�t\007�z��\";�0ppx�\035��y��|����Y)z����+��|5\037���?��\012)˞���\
! ���\017ڹ�o�g�\032��q�:\014�\026N\004�-\0276f5�Q\000n�\007\033x\0350�s���\023�v�\024\026G}����f�v�\
! \013���f<E����@ƫ�mR۔���G\020�tT\001}�\002�b��Fq�h��\022�6�\003��\002\025��D\006�\
! 4���f-���B�\014�������\005{���o�=G��;CidI�~s��ao/�\032̍�88\017�\015t՗ejy�\
! \015c�\036\037�����#X���\033��H��d\022�a`=4�7�\003\007�'�4VW9;T\014�_b\025#�;u�N(�x(�\
! �`�\022v\0232�?^��\037���P������\012^���\011&P�:����\005L\011ݐ\016��]\006(�u\030��f���\
! Ǵr�Y�vW��-�Y-�\036�\010���\"��=�\\P�\023]�z��K�P�\036����V�ّ�EnFh:5\030~��<\
! \015���^W���a\027ˣ\020t�WEN\022Jc�\0331�\011@b����\012�� ��C^p��.%\025�5i�m��$l*��\
! �%\000�\024S��VCg\006�SF=\031��ʪ�\033I�\020\035��� DP��ݨ�ʱ\000�%�`t�`B�!�\\\023�\006�H\
! \024�Enf*(���\026\034��.��|<Q�}1=�ٝsQ��w�X���v\003\036��\017�\006n]k���|!��g����\
! y��oM�*c�n\037`���9��\032\017vK,\035 8^(<8A��8'\011-\020�z�Su���n�\025s��X=�=��\
! 0�p�\"�\026r�?�\"���A�\\�\002��+��\"�6�J\012��\012�$5�>A�OG�]��\012�0A_͉�=�\017�\
! D��ծ �\033�ٿ^���\037l�\027�c��\032��\027?�o��N�*\"C{�bm\027�:q�F\020(�ۂ\027y�j\
! �0��2^\000#�\001\032oU�j�f�m�J��3>9}�\"^��<MiS\021z���\023��3��\013\011��N\027jj���G�\
! �\004g\024\006ϱ�A�Hی�m-�`4�ͷ�}b�/\011.֊oD\016\021�\0111�:9E:�T��\002Q<�XƾCfI̘\006\
! �A�8\000\007�\024�\031�D\017�O=�Z�\003�#\026�{�\005�@�\006gɪc�C��Y}�E4�n����=\010OtѓE\
! ��dz����N�,��\036\017�c� � �'��\000\007L�\001\012�� \015nDQfI]�mިÛ\004v\037��A��?t�\
! ����#�� &6ؽ8�~���Q\021�;����U핺}���uv\036]L\020*\005u�\016�C��A�&'�K}�\
! �Ƈ�l,�\002@��2\025Z�(y/�l��xa/M��,s\007�-�C��E��1��<��\010\013�YE��\025&�сq�\
! �}��\027\033��~04\007��Լj\030�g�v^�k�.���_:}��x{�t�7�(�\015`$�F�d~ap�G��\
! �U��BW�F|!\"/x�\037��h�^���9�3(���ѷ~N�xfۡ�\004;�/\003������<��\030�=\031m\
! �FD)����\026���>I�{Ѣ�\020\000`WБ�\"j�\000��G�zӻC�����s��{Y�^��{��\032�\
! ݤ�#����ѣ��E\037��lwq0��,��T/u�ٛ|��`�o�\002�r�V�Z9l�LZ�\007�e���A�\
! �&=+�#G������J�k\037��\020\031\010/����k{�i�z\000�\034I��]�\010\034[+��*ꝼ~�=�N�\012��\
! �{R\001�Y߄ʢ�>��w�����\021+�i\\�5.�z�>�x4\032�{�gH��\033��u:��TD��C�۝�\
! \033�L�����J���-\020^\015h+��\005b����\0142���XqB�\035x�\014��c�F���ZM���\006�_|9k\
! S\026��&}ٟ�7����9��yG���^�p�����)�L�V�^�J\025X\030�id\016��&�\006K[�\036�^\
! �\035�L�2]���*u���3#B�\033��ɿ%��m.玓���\000��\005\037T\002��d�#6~5\031���������\
! �������(��p��n\007��x����a\004���ͺ���ck���\"��v�pF}\0115�Ŏ2��&W\007=�\026v\
! M����^�\004Θ\035��5ͭ�\"�����AcT�������\037����")
  ### end
--- 5,175 ----
  
  import zlib
! data = zlib.decompress('x\xda\xdd[\xffo\xdb8\xb2\xff}\x81\xfd\x1f\xb8:\xb4J\xb0\x89\xed$mo\xcf\xb1\
! \x85k\x93\xec\xe5p\xed6\x97x\xdfa\xb1X\x14\x94E\xdb\xbaH\xa2\x9eD\xc5\xf5+\
! \xf6\x7f\xbf\x99!)Q_\x92\xba\xb7o\xef\x01/-bK$\x87\xc3\xe1|\xf9\xcc\x90\x99}\
! s\xf9\xfeb\xf1\xd3\xcd\x15\xbb^\xbc{\xcbn~|\xf3\xf6\xaf\x17\xcc;\x1e\x8f\xff\
! qv1\x1e_..u\xc3\x8b\xd1\xe4\x84-\n\x9e\x95\xb1\x8ae\xc6\x93\xf1\xf8\xea\x07/\
! \xf8\xfa\xab\xd9F\xa5\t}\n\x1e\xe1\xa7\x8aU"X\x1c\xcd=\xfa\xe6\x05w9OC\xbe\
! \x13%\xfb\xb1\x14\x05\xfbk\xa6D\xb1\xe2K1\x1bS\x07\x1cS\xaa\x1d}\te\xb4c\x9f\
! \xd8Jfj\xca\xfe4y\xc6x\x11\xf3\xe4\x88\x95\xdb\xb8,\x8f\xd8F$\x0fB\xc5K~\xce\
! R^\xac\xe3l\xca&\xec\xd7\xaf\xbfR<\x84)\xf7\x18\x87\x9dW\xb2H\xa1o\x8b\xc0\
! \xd7_\xf1i\x12g\xf7\xf0~)\x13YL\xd9\x1f&\xf0\xb3\xa4F>}\x88a\xd5"z\xa4u#\x1f\
! `YM\xdb\xab\xc9\x8b\xc9j\x85m\xa3%0$2\xc5\xb8a\xeex+\xe2\xf5\x06x\x0ce\x12Q\
! \x8f\x87Xli\xe6^\x97\x0c\xf8\xe4\x89\xe6n\x14\xf2,\xa3IB\xbe\xbc_\x17\xb2\
! \xca"\x98i9\x110\xd39\xcby\x14\xc5\xd9z\xfe\xb2\xfez\x9c\x88\x15\xd08yy\xfe\
! \xf5W\xac\xfe\te\x11\x89\xe2X\xc9\x1c\x9a\xf2\x8f\xac\x94I\x1c\xb10\x01\x9aC\
! \xfdB\xa9\x94L{]\x89o\xdcmb\x88x.\xe3\xff\x11\xd0\xef\xec\xecYk\xd9\x8d\x94O\
! ^RC*\xca\x92\xaf\x85\xde/\x85\x02\xed\xf0+>6K(\xb4\x1c\xe0\x1d\x8d-\xc5\x125\
! \xcf\xee\xb5\xe6\xd1e\xee\x0f\xdfM\xf0\xdf9\xdb\xc6\x91\xda\x80\x1e\xbc|\xe6\
! \x0eD\x8e\x81lG\x86\xab\xd5\x8a\x8b\xc9\xf9\x00\x1f\xae@>+\x18;\xf7\xd0\xa0\
! \xe1\x8d7\\\x19\x8d7\xd3\x03\xc9I\xfe\xd1\xecy!P9\xb4\xa0K6\xa8\xa0\x13R\xc1\
! ^\xcfa}5\x9d\x1b\x8d{\x82\xa2\xd3\xe9)b\xb8\x0eU\xc4\xb9\xf8 3\xbd\x9f-\xfd\
! \x14K\xfcg:V\xf15x\x8a\xeb!\xbd9\x9d<;\xaf\xa9\x7fG\xd4\xcf\x87\xc56\x1b[W1\
! \x1b\x1b\x87\x03_I\x88\xe8q\xf0\x8bG\xefP\xf0\xb3(~`\xcb\x84\x97\xe5\xdc\xd7\
! \x06\xe4\x07\xa6\xa5\xccyF#\xc05\xa4By\xc1,N\xd7\xac,\x96s_\xbf\x19\xad\xe3\
! \x95\xcfx\x12\xaf\xb3\xb9\xcf\xc32\x8d\xa3(\x11\xfe8x\x9e\x85e~\x0e|\x00\x85\
! \x1653\x91\xde\x05;Q{\xb2\xbc\x90Q\xb5T?\xf0\xb4\xe5\x16\xff!B\xd7+\x12\xe5\
! \xa93\x9ekNe*pK<\xb6)\xc4\n&\x82g?\xb8\x86\xdf\xb31\x1f\x9e\x0eL-\xa3\xb9\
! \x9e\xaf\xd59\xab\xe2\x11\xfa\xea6\xeb\xed\x07\x10\x98\x96(J\x0eI\xa4<\xce.\
! \xb45{f\x85\x9e\xb1n-\xe7\xd9\xe6E\x00\xbc\xeb\x85\x81>\xc3\xb6\xbch6 \x0f\
! \x16\x9b\xb8d\xab8\x11Gl\xb6\x94\x91\x08j.\xe8\xe9\x88Eb\x15g \x04\xb5\x11,\
! \x91\xf2\xfe\x98g\xd1\xf1J\x88D\x93\x90+j\xa90r\xc4VF\xf6m#\xc2;Q\x80\x13\
! \x1e1\xb6\x80\xd7\x0f\xe0\xfdeUj\x02y\x0c:X\xe2\x08\x8acz\xba\x08BB! J\x08&>\
! \xaa\x82/Q\xc1ab\xf0WY\x9c\'U\xc2\xe9\x85\xd2$\x8a*Sq\n\x0eK\xb2h\x07\x02\
! \x85@\x92$;\xa6wS\x10\'D[m\xb8j\xf3\xa5\xc7k\xe6X\x89\x1f%\xabrv\x0c\xbd\x8c\
! X\x18\xcc\r&\x0b\xff\xc1\x07$B)aY\xd5c\x972\xcde\x06\xe2.aqZ\x827\xbbw"\x89\
! \xde\x82Q\x1a!\xb2X\x8b/\x05~\xd0\xaf"\x1b\xc0\xdcC\x1cY\x0e,\x8b\xe0\xfa\
! \x8fe\xf8Op=\xb0\xd2<Gw\x98\x00\x9f\x85\x1e\x93\xf2{\xe0\x0f\xd6\xa6\xd9\xcb\
! eY\xc6\xe0lG\x9a\xc6\x15_n\xb44ka\xd2\xa8L\x88\xa8D\xd9\x84B\x8b\xcfHo\x83\
! \x8b\xca\x8c"\x10\x9fqd\x19V|}D\xf2\x0e\x05,\x10\'e7;\xb5\x01\'b\xb8\x03\xba\
! F\xea\xa3\xd98w\x15\xea5R\x85]\xe3i\x9e\x10\'\x1b\xb9\xd5\xfcneqO\xc1\x1ev5\
! \xd6\xbd\xa2X\x85\xf2#\x04\x04\xb5\xd1\x04\xe0e\x97\x17 \xa1_\x19\x9a0\xc04\
! \x19\x1b\x9c\xc5Y^)2\x87\xa6\x8b\xc7\xd4.\x17\x80q@\x7f<\xd0\xb8\xa4\x12u\
! \xb3\xc7\xd0\xaf\xcd\xbd\x93\x8976\xa6\xd5\xec\x19\x83M.\xd9NV\x8e\xb0\x1a\
! \x15\x82m[\x17<M\xb9\xd2J6m\xad\x1e\xad\x92\xfc\x1f\xf8\xb3~\xf8{5\xc1\x7f\
! \xb5\x8b\xcbA\x0c\xb6\xb3\xeb\x94m\xc4\xab\x01\xd0\xb9\x1b}\xea\xe1\xe8~\xb5\
! O\x9e{\xe4\xf1/&^\x00?\xb31\xb6\x80\xce\x81^\x16\xcaY\xd8\x9e\xe3\xd0\xf8\
! \xd9\x9c\xc9\\d\x07\x9eq\x06\xde\x11\xf3\n\xe5\x1dB \xe3\xd1\xc1\xe1\x9e\x94\
! "\xb9\x04B\r\x03#tT\xe0\xafDq\x80D\xf7%\x93\x17\xe0W\x90\xd8\xa8\xd9]\xbb\
! \xf1\xc1\xf3D\x9d\x0fo\x7f\xbd\xc5O)\xc2\x18\x1d\xefl\x1c\x07\xfb/\xc9\xe1bD\
! \xd4`\x8d\xde\xc5\x86gk\x11y\xff\x87K\xb2,t\x974\x06=\xeb\xc5\x0fc\xabw\x924\
! \xdb\x986\xda\x14\xf9\x89*\x86`^\xab|\xc7\xb5c\xd0*\x81wQf\xbe\xf1\xbf\xe8ap\
! \xe0\x8a\x03\xac\xe6\xa1\x04\xd6s^*\xf4^\x88>\xb25\xba\x1f@\x95`\xf9GL\x16z\
! \x02l%\xfa\x8d\x07\xd5\xd4V\x85LY\xb9,\xb8\x02\x7f\x16k\xb6\xc0\xb7\xbe\xce\
! \xa2~\x0cB?\x82\xe1\xae\x90I\x02<\x80\xa1\tp\xfc\xe1\xcezUh\x06\xd2z\x1e\xf2\
! \xe6\xc7l\x89r\xc2\xc9\x91\x18\xd9_\xb9\x11B\x1d1\x85\xc9\x13X;\xb6\xc1r\xa5\
! \x89o\xc858\xe1l]\xe1\xc2\xc1+\x92)\x82C\xcc\xc4\xb6q\xb7\x1d!\x1d\x93\x97\
! \xd6Q\xb0\x1457(\t\x8ci\x10mvL\xf0r\xd7u\x9eoD\x02\xde\x12\xbbh/\xdf\x0b\xac\
! \x8d\xb0\xa0\x87\x04>\xd0ub\xc7\xb8\x18\xf4\xe4e=\x03B\x81\x02\xdd\xdd,\xb7@\
! \xc1E|^@\xc0(z\x83\xde\xd5\xe1\xc9\x01b\xa6\xd9\xb3\xda\xa4\x91\xbe\x81U.\
! \xfa\xf7\xd9R$\t\x8c\\b\xd2\xe37>K\x15\xc1\x0cP\xa8%\x07\xad^g\xbcy\xed\xa3\
! \xf5\xe0\xd4s\xff\x140\x14M\xcd\xc8\xf1\xab\x08\xac\x08\xe8\xf4(\xfa1(\xc2\
! \x05\xcc\xeb\xa3E\x10,\x84<\xca\xef\xd0G\x00\xea\xeb\x04\x04HO\\\x18\xa8\xcd\
! \x0fP\xa6%\xe6k\xbcY*\xae\xaaR\xe3M3\xf0\xc5\xc4\x870\x86\xc8\x97\xbe[\xd0\
! \xe9`<\xe4\xd3y4\x8b\x86\x15t\xc0Z\x8b/g\x04\xc12\x0c\x92\xcc\x11<X\xc1;Y\
! \xaaa\xccUZ$\x05\xda\xd3\xd0\x01\xe3/a:\x90\x1eX\x12\x9a\x82\xd5I\x03\xc5\
! \x9a1`\xcd\xed\xde\x8e\xea\xea\xd4\xea#t\xd4\xc1;\x1b\xc4\x8a\xe8\x02\xf8\
! \x83\x84P\x17Uy\x02\xf1\x11\x17f\xb1\xc8\xc8\xba \xbb\x81\xf0\x0bu\xc5\xac\
! \xd9\xa0\xf6\xb0\x18w\x81\xef\x1e\x9a\xabw\xa8\xa5\xb6Z7Q\xe6\xbaq\x81\xcf\
! \x9e\xc9\x0f\xe7\x1e\xb8PWE\xed\xb3\xcd\xd3\xe1\xb9\xad`\x83\xf0]S\xf6\x1e\
! \xcb$>\xee.!\x91\x8e\x93V\x8f\x9b\xf77g\x8c\x1a\x11?e\xe8I@F\xb30\xe8\x0c\
! \xbd\x81\xd8]\xde\x91\xf3\xf4\x82\x93\x93\x93\x89\x91\xc7l\x1c\x06G\xee\xf6B\
! _rf\xb2M\x84\xb0lQS0Q\x04\x12\xff\xd4!4r8o$\x8f?\xafA)\x1f\x84\xe6\x16,\x01I\
! \xd1n\x96\xd3\x8e\xbd\xb8sr\x1at\'\x00\x95BO/py\x1eu&\xe8S\xd6\xde\xba\xd4\
! \xa3\x9f\x9aFI\xc5\x93\xfdfieO\x84\x91S\xdc\x10\xadE\xf1*\xc6\xb0\xb5\xe7\
! \xacY\x95b\xd6\xd0\x99\x90\xc1\xb7\xf4\xe8\xe9a\xd7\xfdQ\x9b\xcf\x0e\xfa1+\
! \xabBt\x86U\xf4\xb2\xbb\xc8\x05\xca\x83\t\xbd2\x08b\x98>uV\x82\x9cO;s \xe7m\
! \xfa\xed1\xd7\xfd!\x9b\xee\x88\xa7\xc4\xed\xb8@t\x7f\x06\xe9\x9a\xd2\xcf+\
! \xf1\xd17N\xd3\xfd\xdd\x19\xe3\xfaqw\x9a\xba\x14\x00\n\xb4\x8a\xd7O\xb9f[!\
! \xc0\xb2\x91\xef\xf2\xda\x9f\xbc\xff\xfb\'H\x02\x96X9\xa0i@\xf4\x98\x16\x14M\
! \xf6\xd8Y\xfe>$\xcb]\xa9D\n\xae\xdb \x90\x8e\x16pS;\xd03\xfa\xc1\x85\x99Y\
! \xbbR\x84^XK\x18\xb9rr\x82a\xedQ?\xeb1uAj\x01\xf8\xb1\r@h\x9f\x9bF\xeb\xb9\
! \x16\xad\\^\xbb\xafR\xc9\xa2\xceF!\xb3\xd4\x95C\x08Z\n\xccI\x94\xc6\xb7X\x11\
! \x92^R\xc7\xda\xf6\x00\x07\xf2\x12,\x10+S\x1bY6$\xf4\xc8ZD\x8dT4c~pK\x9fu\
! \x7f\x14\t\xc9\xa6\x8e1{"\x1e\xb3P\x14\xda0\xe6\xd1\x1dH\xaau@\xc0\x92\t\x04\
! F]\x9b0F\x87i\xf6\xce\xac\x14\xa22z\xe3z\xc1\xa6LP\xaf\x1a\x02\xef\xc5F,\xef\
! ii\x90\xe3\x17\x12\xb2\x01\xcc1\xc3J)\x90\xc5\n\x00\xb2\xc0T\x9e\x88\x1f\xd5\
! \xf5\x01,`\xc50\xcc_ e\x1f2s\x80\x8a@\xcc\xbf\x14+Q\xf8\x90\xb6\xf2\x07S\xa6\
! 1\x82\xd1C1b\x1f\x99\xf4\xdfx\x07\x149\xa6\xb5\xc4\x0b\x11m\x90\x81\x1et\x19\
! \x97K^Dl\xcc\x88:|\x82;\x80\xdf\xa8\x04\xcc\xd61\x81\xe6\x92V\xd2`]=Z\xaf\
! \xa4\xd4 \x82\xa3>\x10\xc6\xb1\x10d-\xdb\xb0\x97\n\xfe\x9c\xba\xd4{\x0ck\x00\
! \xa5\x00 \xf6\x97\xab\x85c\xfb&\xd5\xa7\xf4\xc7\xdf\xc4Q\x04\xb0\x85a\tm\xee\
! \x83\x14%\x88\x01\xc1\x9b\xf9\xaa\x13#\x7f\xe2\xda\xfd\x13\x042Px=^\x7f\x1b\
! \x1c\xaeq\x85\x81\x11\xd0\xd6\x82\r\xf6\xb9\x8f|\x1d$\xd1\xe2\xa0\xac\xc24V\
! \x96\x83\xb5t\xf8\x7fCB\xf4\x87\n\xd6\xf8c\xb8\xbbAy\xc9\n\x122\x0e\xb86\x8a\
! K\xe4\x0fH\x9c8\x95\xd0\x16|\xd1\xaeu\x1f.P\n\xfb1\xf1\x03\xf4\xfcR\x06\x1es\
! \x90]\xe4\xdc\x87\x8a\x98D\x17i\x0b76\x96\xbb,\xe2\xdc.\x0b\xd3\xe3\xf1?\xf9\
! \x03\xd7o\xfd`<\x9e}\xf3\xf3\xc5\xe5\xeb\xc5\xeb\x9fM\xaaYeZ3e\xa6}\xc2\x01\
! \x8e\xa4c)H>\x17\xd2\x94(>5\xfc\xc4+v\x00y{\x95\x02L\x1e!\x1f%{\xfe\x9c\xb5\
! \xdf\x8c\x12\x91\xad!+\x0b\xe6\xec\xf4\xb0\x19\xfa\xa9-E\xd2\xfayg\xe8\xcf\'\
! \xbf\x9c\xf7\xba\xb1\x83\x18:N\xceY\xccf4\xccL\x00/\xbe\xfd\xf6\xb0\xdd\xfdS\
! \x7f\xabJ\xc0\xe2T\xd2\x06"8\xfa\xe7\xf8\x97\x11\xee\xf4\x88\x1a\x0e\xfc\xa9\
! \x7f8p,\x82\x0b\xadG\xda\x15\xcd\xe7\xec\x0c\xd7[7\x00\xbf\xf8\x12\xa5\x06\
! \xef\x87\xd5\xc4\xcei\x8a%\xf3Z\xba#%\xdf\xca\xad(. \x0c\x1c\x1c\x1e\xf6G\
! \x7fz\x9a 9\x1f\xf0f0\x7fQ\x89\x815\xfc\xda~\xe5<\x9a\xaf\xe6c<\xfe\xe5\x97&\
! \xed e\xd9\xd3;\xdd\xbc\xbf[\xf8A7\xe7\xf0m\x16\xacS<\xf7Pm_\x87\x01\xde\xc2\
! \x89@wUhcV+\xa9\x04\x00\x16\xbc\xb3\x81\xd7\x01\xb5\xbcdxd<%\x8c\xd6KEq\xd4\
! \xf7\x85L\x1fi\xb6l\xb7\x0e\xad\xc09\xc8m\xc1s4l\x1c?\x8c[\xbc\xc6\xda\xa6\
! \x8dM\xf9\xc8\x8b\x7f\x04\x91JG\x15\xd07/0\xdf)v\x8f\xff=j\x14\xf7\x88\x16~\
! \xfb\r\x94 \xb6\x11\x1d\xf8\xfc\rT06\x12\x19\xfc\xd2>\xf2\xd1\x9a\x15\x06\
! \x83\x05\x82v9\xc3\xd9\xf5[\xb9m\xca\x04\xf6\x14\xcf\x1f\xde,{\x1e\xe8\xf7w\
! \x86\xd2\xc1\x8a\xca\xf6\xe6h\xca\xc3\xde^\xd07\x98[1up\x1e\xd6\xffu\xf5\x96\
! \x15ry\xff\rc\xdf\x1d\x1fv\xce\xb2\x86\xeb\x1cX\xc2\xfb\xe0\x05\xb7\xf1r\x13\
! \x0bv\x1dg\x11\x18\x06\xd65\x0bz\xf3g\xf0w\x80y2LGu\xb5\xb2G\xc5\xc0\xf6%V#\
! \n\xbfW_\xe9\x85\xf2\x82G\xb1\xb4\x11\xccX\xc2nJF\xf0\xb7\xab\x9f\x86\x03\
! \x18r\x1ai5\xb4UT\xdf<\xd7\xc1\xab\xff\xfb\xf7`\x02\xf5\xd7k\xe2)=\xffgY\xc0\
! \xd4\xce\r\xe9\xf0\xfc\x9fe\x80\xd2Q\x87\x01|\xf6\xc7O\xaaZ`\x94\xdb\xceb\
! \xb5\xbb~\x0e\xee\xf0\xeci\t\xf4(Gx\xda\xe6\xc2\x84g\xf7hrA\x03Ot\xb5\xea\
! \xe9\xc7>%B\xd9{P\xdaC\xe3;\x19fO\xda\x16\xb9\x19\xa1\xe9\xd4`\xfcy?\xf38\
! \xa0\xfa\x92\xba[\x95\'\x92G},\x8fB\xd0m^\x1d9I(\xad\xedo\xc5P&\x00\x89\xd1\
! \x92\xd2*Qq\xce\x0bE\\\x1dG\\q\xeb\xd4\xaeb*\xc6k\xd2\x8c\xdb<\xc7I\xd8d\xf1\
! !\xc5\xa3\x92\x00PSJ\xf5bZ\r\xd5\xfe\xdb\xa7\x85z2|o\x95U\x7f7\x92\x04!:\xb2\
! \x7f_\xd0\x81\x86\xa0\xf4e\xbb\x91I\x9dc\x016\xcb@\xc1\xe8H\xc0\x84\xcaCJ\
! \xb9\xa6n-\x13\x91(\xe4\x8b\xdc\xcc\xa4(\xbf(\xe4\x16\x1c\xf7\x99.u\xcf}<\
! \x19\x84}1=\xdd\xd9\x9d\xf3M\xbd\xdf\x1f\xb4\xb1\x0c\x81\xf7\xed\x06<l[\x1f\
! \x10\r\xdc\xb9\xd6\xd4\xa7\xb7\xf9Br\xd7ORk\xec\xf1\xf3$/L\xdf\x86\x9cU\xc6:\
! \xdd>\xc0\xea\x83\xd9sR\xaf5\x1e\xd0VX:@p\x1cJ<\x00A\xce\xe8X&\x8b,\x10\xa2\
! \xba\xe8\xb1Sd\x8937\xddn*\xdf\xac\x10\xa9|\xa0\xfb\x04\xf5\xa1\xf6\xe1\xdeE\
! \x84-\xe4\x82\x7f\xafD\xb1\x1b\xb6\x83\xba\xb91\x05|\xf5\xdf\xf8\xca\xef\x8b\
! \x10\xdb<+)\xf8\xde(\xa4\x93\xd4\xf8\xfa$\xd0?\x9btwa\xd8+\x00\xc2\x04}5\'s\
! \xf6(>\x1a\x12\xf9gW\xbb\x82Xn\x10\xe7\xf0z\x9d\x0e\xde~\xb0\xb9Y<\x8e\xf5jk\
! \xcc\x9e^\xfc\xc9~\x8b\xbfBwJU\x918\xb2\x07\'\xd6v\xf1\xc8\x12\xa7\xf9w\x04\
! \x81\x12\xbcS\\\x95\xc3\x95\xa3\xba\xd9\xc2\xac\x1f\xaa4\x04F\x80\x034\xde\
! \xbav\xd5)\xb1b\xdbRVxy\xe7\xe4\xf4\xec\x91\xcavCj\xf38\xa5MM\xe8\xc5\xcbW\
! \x8f\x10\xba)d\xc8\xc3\x18r\xb9\x9d.\xd44.u\xa9\x8f\xeau\t\xce(\x0c\x9eG!\
! \x83\xd6\x91v\x19\x07\xdb\n\xbd`2\xfa\xe3w\x7fzd\xc2/\t.\xd6\x8aoE\t\x11\xe1\
! \x111w:9E:\xaaT\xe5\xcd\x02Q<\xf6x\xc5\xbeCfI\xcc\x98\x06\xe5A\x9f8\x00\x07\
! \xe7\xc0\x13\x7f\xc8\x19\xe9D\x0f\xe4O=\xd8Z\x9a\x83\xb1#\x96\xc4\xf7B\x0b,D\
! \x9d\x06g\xc9\xea\xe3\xbbC\xf7\xcaXs>E4\x16n\x89\xb1\xe9T4=\x08O\xf4\xd1\x93\
! E\xdc\xd8\xc7\xb3E\xf6\xee\x05M\x88,W\xe6>\x0e\xeec\xbf \xd3"5$\xa0\xde\x00\
! \x07L\x0c\x01\n\xf7\x1c \x0fn\x85\xaa\x8a\xac\xa9\xe3\xb6o\xc6\xe1\x8d\x00\
! \xbb\x8f\xe0\xbf\xe9\xc0}:\xbc\x1f\xba\xd3k\xdd\xc7\xd3\x91\xc1F\x10\x13\x1b\
! \xec^\x1c\x0e_\xa3\xdbG\xf1\xa8\xe6\xfe=P{D\xe7\xea\xf6Z\xdd\xbe\x7f\x7f\xfb\
! \xce:;\x8f.\x18\x08\x99\x83:Z\x87\xe7\xa1\xc3\xf3z\xd7\xee\xb0f\x8d\xc5S\x00\
! \x02T>\xa6\x82*\x0e&/\x05\x14\xcc\xb9\x18W\xf6\x92\x03^\xa62w\xd6\xdcr<\x04\
! \xb2R\x94\xfat\x82\xca\xc6#\xaa\xbc\x175\rNw\x8ddA\'\xbb}\xf3\xf5M\xbf\x1b\
! \xae6\xe8~\xfd`lN\x0c\xc7\xb9y\xd5\xb2\xe8\xcf\xc8\xe5\xa2\xb9\x80H]\x16\xaf\
! \xdf\xbc\xbdr\xfa\x0c\x1f\xc6\x0e\x1c\xbe.n\xddQ\xe0\xfc\xc1\nNZ5\x90\xc5\
! \xa5\x01\xce\x1e)\xbb\xe7\x96):\x1a[3\x9a\xf0P$^\xf0\x16?\xecm\xce\xfe\x01\
! \xfe\xe2\xb2=O\xdfb\xdc\xb0c\xee\xe2\xe8\x1b:\xa7\xaf<\x9a\x88\xdaM@\xd391\
! \xe0\xda\xf4\x03\xb8\xd5\x0f)\xcf\xbd6N\xef\xceG\xfb\xb2\x11I\x0e;\xbdl2\x82\
! \xc7\xeb\xa6\x8f\x12\x18\xb8\x14\x81\xd8\xd3\xde\xae\xe8\x88\t\x00\xd75\x0cb\
! \xb8\xa0\xc6\x9c, \x1a\xe0\x17\xbe\xde\x0en\xd8E\xf8%\xdb\xf5\xd8i\xdf\xff\
! \xc6\xde\xed;\x8d\xbdU\xab7n\xc8G\xba[N\xf5G\xba\x98U\x8f\xf9@\x8f\xe6F\x16}\
! \xec\xb7\xfd\xfd\x85\xc2\xe0\x0ff\xb1\xffE\x85Sw\xc9\x83Y\xb8\xb9\xdc\xf5\
! \xffY\xa3@\x9fN\xbd\xc7\xb7\xd6\xf0C\xaa\xd5\xd9\xe8\x8b\xaa(\xf0/\x1eH\x96\
! \xd3/\xd0\x10#\x8b\xc6\xcbiBD\x07"\x10\xed\xf1a\xed\x1c?\xbf\x04\xe3\xc5~\
! \xafe\xfcN\xbc;\xc5\x11\xe8\xe6\xe8\x87\xdbwL~\xbe\x1fq\xf5\xb54\xaak\xd4\
! \xdc\xb6\x0cICvk)\x1b,{\x1a\x13\xba\xe3\x0f\xc2k\xd0cM\xc4\xbe\xc0\xc0\xdb<\
! \xb6\xc2p!t\xc0\x13+N\xd0\xb0\x17\x8b\x7f\x03[\xb7\x9a6\x1e\x8ej\xe2\x03,\
! \xb6\x18\xfc\xe2\x1bM\x9bJEr\x9b\r\xa5Z\xfa\x90\xbe\xd3\xc3\xc3\xa2\xfc\x9dy\
! GA\x9a\xfdE\xca(\xdc5\xf7\xb3\xcd\x94\xf8\x97\x19\xf6\x1a(|o\x127)\x15V!m\
! \xceV\x82\xe8\xfb\x19\x9b\x01\xae\xe6\xb2\xc5\xc9d\xf2l\xe8\x04c\xe6\xd4\xc4\
! \xa2\xe1\xbf\xf0h\x8a\xd3\xbe\x9e\x19\xe1\xa0\xdf\x02\x88\x8f\xfe\x01\x06w\
! \xaf@9\x17\x83 q/\x15\xc0\x16/x\'3\xd8\x9c%;\x9b\xb0\x93\x17\xd3\xc9\x8b\xe9\
! \xd9);\x9dLN\xcd\x1e\x8cZ<\x989\x95\xca\xa7\xe3\xf1v\xbb\x1d\x95v\xe2\x91,\
! \xd6c\x87\x11|\xeeV\x12\x9b\xd2\x9d1\xd8\xf6r[\x9bE\xc0\x07\x9dg\xcb\xfa\x87\
! \xb2W\x94\x8b\x1de\x0eaMb\x0cz\xd8\xaf\xa2\x9ad\x17\xcd\x85=\x07\t\x9c3;\x18\
! \x0bY\x9a[\x03\xd9\x1b\xa8\xee\xa4\xbb\xa012\xda\xe9\xbf\xda\xd1\x7f.\xf8/\
! \xb3M\xb1\x95' )
  ### end

Index: ui.html
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui.html,v
retrieving revision 1.10
retrieving revision 1.11
diff -C2 -d -r1.10 -r1.11
*** ui.html	20 Apr 2003 09:41:15 -0000	1.10
--- ui.html	21 Apr 2003 21:15:36 -0000	1.11
***************
*** 3,8 ****
  <head>
  <title id="title">Spambayes User Interface</title>
- <meta http-equiv="Pragma" content="no-cache" />
- <meta http-equiv="Expires" content="-1" />
  <style>
  body { font: 90% arial, swiss, helvetica; margin: 0 }
--- 3,6 ----
***************
*** 138,146 ****
      <td valign='top'>
          <img src='config.gif' width='40' height='40' align='left'/>
-         <span id="configurationLink">
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;You can configure your Spambayes<br/>
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;system using the
!             <a href='config'>Configuration page</a>.
!         </span></td>
      </tr>
      </table>
--- 136,142 ----
      <td valign='top'>
          <img src='config.gif' width='40' height='40' align='left'/>
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;You can configure your Spambayes<br/>
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;system using the
!             <a href='config'>Configuration page</a>.</td>
      </tr>
      </table>
***************
*** 314,319 ****
      <FORM action="changeopts" method="POST">
  
!     <p><span id="introduction">This page allows you to change the options that control how
!     Spambayes processes your email.</span>  Your options are stored in
      <b><span id='optionsPathname'>/example/pathname</span></b>.</p>
  
--- 310,315 ----
      <FORM action="changeopts" method="POST">
  
!     <p>This page allows you to change the options that control how
!     Spambayes processes your email.  Your options are stored in
      <b><span id='optionsPathname'>/example/pathname</span></b>.</p>
  
***************
*** 325,340 ****
          </TD>
          <TD>
!             <input type="text" size="26" id="input" name="from_parm_ini_map"/>
          </TD>
          <TD id='helpSpacer'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
!         <TD id='helpCell' valign='top'>
              <p>(Help text goes here.)</p>
          </TD>
      </TR>
      <TR id="configCbRow1">
!         <TD align="right" nowrap='1'>
              <span id="label">Label</span>:&nbsp;
          </TD>
!         <TD width='110'>
              <div id="input">
                  <input type="checkbox" id="input_box" value="value" name="from_parm_ini_map"/>
--- 321,336 ----
          </TD>
          <TD>
!                <input type="text" size="26" id="input" name="from_parm_ini_map"/>
          </TD>
          <TD id='helpSpacer'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
!         <TD id='helpCell' valign='top' rowspan='2'>
              <p>(Help text goes here.)</p>
          </TD>
      </TR>
      <TR id="configCbRow1">
!         <TD align="right" nowrap='1' valign='top'>
              <span id="label">Label</span>:&nbsp;
          </TD>
!         <TD nowrap='1' valign='top'>
              <div id="input">
                  <input type="checkbox" id="input_box" value="value" name="from_parm_ini_map"/>
***************
*** 343,370 ****
          </TD>
          <TD id='helpSpacer'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
!         <TD id='helpCell' valign='top'>
              <p>(Help text goes here.)</p>
          </TD>
      </TR>
      <TR id="configRow2">
!         <TD nowrap='1' align='right'>Current Value:</TD>
!         <TD nowrap='0' width='150'>&nbsp;<span id="currentValue">(value)</span></TD>
      </TR>
!     <TR id="blankRow"><TD>&nbsp;</TD></TR>
!     <TR id="folderRow">
!         <TD width="25%">
!             <input type="checkbox" id="folderBox" value="value" name="folderName">
!             <span id="folderName">Folder name</span>
!             </input>
!         </TD>
!         <TD id='helpCell' valign='top' rowspan='1000'>
!             <p>(Help text goes here.)</p>
!         </TD>
      </TR>
      </TABLE>
      </span>
  
      <center>
!       <input id="config_submit" type="submit" name="how" value="Save"/>
      </center>
  
--- 339,360 ----
          </TD>
          <TD id='helpSpacer'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
!         <TD id='helpCell' valign='top' rowspan='2'>
              <p>(Help text goes here.)</p>
          </TD>
      </TR>
      <TR id="configRow2">
!         <TD nowrap='1' align='right' valign='top'>Current Value:</TD>
!         <TD nowrap='1' valign='top'>&nbsp;<span id="currentValue">(value)</span></TD>
      </TR>
!     <TR id="configTextRow2">
!         <TD nowrap='1' align='right' valign='top'>Current Value:</TD>
!         <TD valign='top'>&nbsp;<span id="currentValue">(value)</span></TD>
      </TR>
+     <TR id="blankRow"><TD>&nbsp;</TD></TR>
      </TABLE>
      </span>
  
      <center>
!       <input type="submit" name="how" value="Save"/>
      </center>
  



From timstone4 at users.sourceforge.net  Mon Apr 21 15:15:55 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 21 17:15:59 2003
Subject: [Spambayes-checkins] spambayes/spambayes UserInterface.py,1.3,1.4
Message-ID: <E197idn-0003x7-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv15117

Modified Files:
	UserInterface.py 
Log Message:
Cosmetic changes to configuration page

Index: UserInterface.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/UserInterface.py,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** UserInterface.py	20 Apr 2003 09:41:15 -0000	1.3
--- UserInterface.py	21 Apr 2003 21:15:52 -0000	1.4
***************
*** 73,76 ****
--- 73,77 ----
  import cgi
  import mailbox
+ import types
  
  import PyMeldLite
***************
*** 204,208 ****
      """Serves the HTML user interface."""
  
!     def __init__(self, bayes, config_parms=()):
          """Load up the necessary resources: ui.html and helmet.gif."""
          global classifier
--- 205,209 ----
      """Serves the HTML user interface."""
  
!     def __init__(self, bayes, config_parms=[], config_display=[]):
          """Load up the necessary resources: ui.html and helmet.gif."""
          global classifier
***************
*** 210,213 ****
--- 211,215 ----
          classifier = bayes
          self.parm_ini_map = config_parms
+         self.display = config_display
  
      def onClassify(self, file, text, which):
***************
*** 376,384 ****
  
          # Loop though the sections.
!         for sect, opt in self.parm_ini_map:
!             # We need a string to use as the html key that we can change to
!             # and from the sect, opt pair.  We like irony, so we use '_' as
!             # the delimiter <wink>
!             if opt is None:
                  if configTable is not None and section is not None:
                      # Finish off the box for this section and add it
--- 378,383 ----
  
          # Loop though the sections.
!         for html_key in self.display:
!             if not self.parm_ini_map.has_key(html_key):
                  if configTable is not None and section is not None:
                      # Finish off the box for this section and add it
***************
*** 395,398 ****
--- 394,398 ----
                  configCbRow1 = configTable.configCbRow1.clone()
                  configRow2 = configTable.configRow2.clone()
+                 configTextRow2 = configTable.configTextRow2.clone()
                  blankRow = configTable.blankRow.clone()
                  del configTable.configTextRow1
***************
*** 400,408 ****
                  del configTable.configRow2
                  del configTable.blankRow
!                 del configTable.folderRow
!                 section.heading = sect
                  del section.iconCell
                  continue
!             html_key = sect + '_' + opt
  
              # Populate the rows with the details and add them to the table.
--- 400,407 ----
                  del configTable.configRow2
                  del configTable.blankRow
!                 section.heading = html_key
                  del section.iconCell
                  continue
!             (sect, opt) = self.parm_ini_map[html_key]
  
              # Populate the rows with the details and add them to the table.
***************
*** 427,433 ****
                      if options.is_boolean(sect, opt):
                          if str(val) == "0":
!                             val = "False"
                          elif str(val) == "1":
!                             val = "True"
                      newOption.val_label = str(val)
                      if options.multiple_values_allowed(sect, opt):
--- 426,432 ----
                      if options.is_boolean(sect, opt):
                          if str(val) == "0":
!                             val = "Yes"
                          elif str(val) == "1":
!                             val = "No"
                      newOption.val_label = str(val)
                      if options.multiple_values_allowed(sect, opt):
***************
*** 450,468 ****
                                       cgi.escape(options.doc(sect, opt))
  
-             newConfigRow2 = configRow2.clone()
              currentValue = options[sect, opt]
              # for Python 2.2
              if options.is_boolean(sect, opt):
                  if str(currentValue) == '0':
!                     currentValue = "False"
                  elif str(currentValue) == '1':
!                     currentValue = "True"
!             # XXX Something needs to be done here, otherwise really
!             # XXX long options squeeze the help text too far to the
!             # XXX right.  Browsers can't wrap the text (even if
!             # XXX no-wrap is False) unless there is whitespace to
!             # XXX wrap on - comma's don't count.  This works, but
!             # XXX it's a bit ugly.  Ideas?
!             # currentValue = str(currentValue).replace(',', '<br />')
              newConfigRow2.currentValue = currentValue
              configTable += newConfigRow1 + newConfigRow2 + blankRow
--- 449,466 ----
                                       cgi.escape(options.doc(sect, opt))
  
              currentValue = options[sect, opt]
+ 
+             if type(currentValue) in types.StringTypes and \
+                 str(currentValue) not in (0,1):
+                 currentValue = currentValue.replace(',', ', ')
+                 newConfigRow2 = configTextRow2.clone()
+             else:
+                 newConfigRow2 = configRow2.clone()
              # for Python 2.2
              if options.is_boolean(sect, opt):
                  if str(currentValue) == '0':
!                     currentValue = "Yes"
                  elif str(currentValue) == '1':
!                     currentValue = "No"
              newConfigRow2.currentValue = currentValue
              configTable += newConfigRow1 + newConfigRow2 + blankRow
***************
*** 478,483 ****
  
      def onChangeopts(self, **parms):
-         if parms.has_key("how"):
-             del parms["how"]
          html = self.html.clone()
          html.shutdownTableCell = "&nbsp;"
--- 476,479 ----
***************
*** 494,501 ****
  
          for name, value in parms.items():
!             print name, value
!             sect, opt = name.split('_', 1)
!             if (sect, opt) in self.parm_ini_map:
!                 options.set(sect, opt, value)
  
          op = open(optionsPathname, "r")
--- 490,496 ----
  
          for name, value in parms.items():
!            if self.parm_ini_map.has_key(name):
!                sect, opt = self.parm_ini_map[name]
!                options.set(sect, opt, value)
  
          op = open(optionsPathname, "r")
***************
*** 530,534 ****
          '''Check that the given input is valid.'''
          # Most of the work here is done by the options class, but
!         # we may have a few extra checks that are beyond its capabilities
          errmsg = ''
  
--- 525,529 ----
          '''Check that the given input is valid.'''
          # Most of the work here is done by the options class, but
!         # we have a few extra checks that are beyond its capabilities
          errmsg = ''
  
***************
*** 544,552 ****
                  del parms[name]
  
!         for sect, opt in self.parm_ini_map:
!             if opt is None:
!                 nice_section_name = sect
                  continue
!             html_key = sect + '_' + opt
              if not parms.has_key(html_key):
                  # This is a set of checkboxes where none are selected
--- 539,547 ----
                  del parms[name]
  
!         for html_key in self.display:
!             if not self.parm_ini_map.has_key(html_key):
!                 nice_section_name = html_key
                  continue
!             sect, opt = self.parm_ini_map[html_key]
              if not parms.has_key(html_key):
                  # This is a set of checkboxes where none are selected
***************
*** 560,564 ****
                          value_string += val
                          value_string += ','
!                     value = value_string[:-1]   # remove trailing comma
                  value = options.convert(sect, opt, value)
              if not options.is_valid(sect, opt, value):
--- 555,559 ----
                          value_string += val
                          value_string += ','
!                     value = value_string[:-1]
                  value = options.convert(sect, opt, value)
              if not options.is_valid(sect, opt, value):
***************
*** 574,577 ****
--- 569,606 ----
              parms[html_key] = value
  
+         # check for equal number of pop3servers and ports
+         slist = parms['p3servers'].split(',')
+         plist = parms['p3ports'].split(',')
+         if len(slist) != len(plist):
+             errmsg += '<li>The number of POP3 proxy ports specified ' + \
+                       'must match the number of servers specified</li>\n'
+ 
+         # check for duplicate ports
+         plist.sort()
+         for p in range(len(plist)-1):
+             try:
+                 if plist[p] == plist[p+1]:
+                     errmsg += '<li>All POP3 port numbers must be unique</li>'
+                     break
+             except IndexError:
+                 pass
+ 
+         # check for equal number of smtpservers and ports
+         slist = parms['smtpservers'].split(',')
+         plist = parms['smtpports'].split(',')
+         if len(slist) != len(plist):
+             errmsg += '<li>The number of SMTP proxy ports specified ' + \
+                       'must match the number of servers specified</li>\n'
+ 
+         # check for duplicate ports
+         plist.sort()
+         for p in range(len(plist)-1):
+             try:
+                 if plist[p] == plist[p+1]:
+                     errmsg += '<li>All SMTP port numbers must be unique</li>'
+                     break
+             except IndexError:
+                 pass
+ 
          return errmsg
  
***************
*** 586,593 ****
  
          # Only restore the settings that appear on the form.
!         for section, option in self.parm_ini_map:
!             if option is not None:
!                 if not options.no_restore(section, option):
!                     options.set(section, option, c.get(section,option))
  
          op = open(optionsPathname, "r")
--- 615,621 ----
  
          # Only restore the settings that appear on the form.
!         for section, option in self.parm_ini_map.values():
!             if not options.no_restore(section, option):
!                 options.set(section, option, c.get(section,option))
  
          op = open(optionsPathname, "r")



From montanaro at users.sourceforge.net  Mon Apr 21 15:16:39 2003
From: montanaro at users.sourceforge.net (Skip Montanaro)
Date: Mon Apr 21 17:16:43 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.15,1.16
Message-ID: <E197ieV-0004DQ-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv16117

Modified Files:
	message.py 
Log Message:
Confirmed on c.l.py with Tim Peters that the original re was more complex
than necessary.  This should be a more readable regex.



Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.15
retrieving revision 1.16
diff -C2 -d -r1.15 -r1.16
*** message.py	19 Apr 2003 07:37:59 -0000	1.15
--- message.py	21 Apr 2003 21:16:35 -0000	1.16
***************
*** 173,180 ****
      def _force_CRLF(self, data):
          """Make sure data uses CRLF for line termination.
- 
-         Nicked the regex from smtplib.quotedata.
          """
!         return re.sub(r'(?:\r\n|\n|\r(?!\n))', '\r\n', data)
  
      def as_string(self):
--- 173,178 ----
      def _force_CRLF(self, data):
          """Make sure data uses CRLF for line termination.
          """
!         return re.sub(r'\r\n|\r|\n', '\r\n', data)
  
      def as_string(self):



From tim at fourstonesExpressions.com  Mon Apr 21 17:19:24 2003
From: tim at fourstonesExpressions.com (Tim Stone - Four Stones Expressions)
Date: Mon Apr 21 17:19:29 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.15,1.16
In-Reply-To: <E197ieV-0004DQ-00@sc8-pr-cvs1.sourceforge.net>
Message-ID: <E621X31USA0IEIH1ZVR21NMKE1XFAON.3ea4605c@myst>

4/21/2003 4:16:39 PM, "Skip Montanaro" <montanaro@users.sourceforge.net> 
wrote:

>Update of /cvsroot/spambayes/spambayes/spambayes
>In directory sc8-pr-cvs1:/tmp/cvs-serv16117
>
>Modified Files:
>	message.py 
>Log Message:
>Confirmed on c.l.py with Tim Peters that the original re was more complex
>than necessary.  This should be a more readable regex.

>          """
>!         return re.sub(r'\r\n|\r|\n', '\r\n', data)

I think this one is even too complex.  '\r\n?|\n' does the same thing... ;)

c'est moi - TimS
http://www.fourstonesExpressions.com
http://wecanstopspam.org

There are 10 kinds of people in the world:
  those who understand binary,
  and those who don't.



From anadelonbrin at users.sourceforge.net  Mon Apr 21 16:37:52 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Mon Apr 21 18:37:55 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.36,1.37
Message-ID: <E197jv6-0000Bf-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv645/spambayes

Modified Files:
	Options.py 
Log Message:
Fix for [ spambayes-Bugs-725307 ].
This is not a nice fix, it's a quick hack that solves the problem.
However, those options that become sets no longer have
their values checked for validity.  This didn't happen before the
option changeover, so nothing is really lost, but a better fix
needs to be done.  I don't have time right now, but I'll do this
RSN.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.36
retrieving revision 1.37
diff -C2 -d -r1.36 -r1.37
*** Options.py	20 Apr 2003 06:58:52 -0000	1.36
--- Options.py	21 Apr 2003 22:37:49 -0000	1.37
***************
*** 1136,1139 ****
--- 1136,1144 ----
                 return False
          elif type(self.allowed_values) == type(""):
+             # this is a complete hack - something better needs to
+             # be worked out for sets, but I don't have time just now.
+             import types
+             if type(value) == type(Set()):
+                 return True
              if self.multiple and value == "":
                  return True
***************
*** 1259,1262 ****
--- 1264,1270 ----
          '''Convert option from a string to the appropriate type.'''
          fetcher, converter = all_options[sect][opt]
+         # if it is already the correct type, we're done
+         if type(value) == type(converter("1")):
+             return value
          return converter(value)
  



From tim.one at comcast.net  Mon Apr 21 19:30:34 2003
From: tim.one at comcast.net (Tim Peters)
Date: Mon Apr 21 18:54:15 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.15,1.16
In-Reply-To: <E621X31USA0IEIH1ZVR21NMKE1XFAON.3ea4605c@myst>
Message-ID: <LNBBLJKPBEHFEDALKOLCAENHEDAB.tim.one@comcast.net>

>>          """
>>!         return re.sub(r'\r\n|\r|\n', '\r\n', data)

[Tim Stone]
> I think this one is even too complex.  '\r\n?|\n' does the same
> thing... ;)

That's one I suggested.  Another was

    \r\n|[\r\n]

which also only needs to process two alternatives to find the lone-\n case
(character classes are faster than alternation in Python regexps).


From tim at fourstonesExpressions.com  Mon Apr 21 19:24:22 2003
From: tim at fourstonesExpressions.com (Tim Stone - Four Stones Expressions)
Date: Mon Apr 21 19:24:30 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py, 1.15,
	1.16
In-Reply-To: <LNBBLJKPBEHFEDALKOLCAENHEDAB.tim.one@comcast.net>
Message-ID: <OK8QO744YICUPVQTRMWSHGLIXRUTNI.3ea47da6@myst>

4/21/2003 5:30:34 PM, Tim Peters <tim.one@comcast.net> wrote:

>>>          """
>>>!         return re.sub(r'\r\n|\r|\n', '\r\n', data)
>
>[Tim Stone]
>> I think this one is even too complex.  '\r\n?|\n' does the same
>> thing... ;)
>
>That's one I suggested.  Another was
>
>    \r\n|[\r\n]

Surprisingly, my cursory benchmark scores this one about 20% slower than the 
others that we've bandied about...

>
>which also only needs to process two alternatives to find the lone-\n case
>(character classes are faster than alternation in Python regexps).

Yes, and the first alternative is still a useless match... can't we get rid of 
that somehow?

>
>
>


c'est moi - TimS
http://www.fourstonesExpressions.com
http://wecanstopspam.org

There are 10 kinds of people in the world:
  those who understand binary,
  and those who don't.



From tim.one at comcast.net  Mon Apr 21 20:44:06 2003
From: tim.one at comcast.net (Tim Peters)
Date: Mon Apr 21 19:58:49 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py, 1.15,
	1.16
In-Reply-To: <OK8QO744YICUPVQTRMWSHGLIXRUTNI.3ea47da6@myst>
Message-ID: <LNBBLJKPBEHFEDALKOLCGENLEDAB.tim.one@comcast.net>

>> That's one I suggested.  Another was
>>
>>    \r\n|[\r\n]

[Tim Stone]
> Surprisingly, my cursory benchmark scores this one about 20%
> slower than the others that we've bandied about...

I don't want to bother learning exactly which data you benchmarked or how
you timed it.  Both topics have consumed megabytes on c.l.py <wink>.

>>(character classes are faster than alternation in Python regexps).

> Yes, and the first alternative is still a useless match... can't
> we get rid of that somehow?

The match prevents re.sub from seeing the sequence \r\n as individual
characters, which is important to stop just one of them from getting
replaced by \r\n.  A look*behind* assertion could prevent \n from getting
replaced when it's preceded by \r, but Skip was after readability here.
This stuff doesn't cost enough to worry about.


From anadelonbrin at users.sourceforge.net  Mon Apr 21 20:25:06 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Mon Apr 21 22:25:10 2003
Subject: [Spambayes-checkins] spambayes/spambayes UserInterface.py,1.4,1.5
Message-ID: <E197nT0-0003oL-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv14578/spambayes

Modified Files:
	UserInterface.py 
Log Message:
Re-commit of some changes that were accidentily removed :)

Index: UserInterface.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/UserInterface.py,v
retrieving revision 1.4
retrieving revision 1.5
diff -C2 -d -r1.4 -r1.5
*** UserInterface.py	21 Apr 2003 21:15:52 -0000	1.4
--- UserInterface.py	22 Apr 2003 02:25:03 -0000	1.5
***************
*** 205,209 ****
      """Serves the HTML user interface."""
  
!     def __init__(self, bayes, config_parms=[], config_display=[]):
          """Load up the necessary resources: ui.html and helmet.gif."""
          global classifier
--- 205,209 ----
      """Serves the HTML user interface."""
  
!     def __init__(self, bayes, config_parms=()):
          """Load up the necessary resources: ui.html and helmet.gif."""
          global classifier
***************
*** 211,215 ****
          classifier = bayes
          self.parm_ini_map = config_parms
-         self.display = config_display
  
      def onClassify(self, file, text, which):
--- 211,214 ----
***************
*** 378,383 ****
  
          # Loop though the sections.
!         for html_key in self.display:
!             if not self.parm_ini_map.has_key(html_key):
                  if configTable is not None and section is not None:
                      # Finish off the box for this section and add it
--- 377,385 ----
  
          # Loop though the sections.
!         for sect, opt in self.parm_ini_map:
!             # We need a string to use as the html key that we can change to
!             # and from the sect, opt pair.  We like irony, so we use '_' as
!             # the delimiter <wink>
!             if opt is None:
                  if configTable is not None and section is not None:
                      # Finish off the box for this section and add it
***************
*** 392,407 ****
                  configTable = self.html.configTable.clone()
                  configTextRow1 = configTable.configTextRow1.clone()
                  configCbRow1 = configTable.configCbRow1.clone()
                  configRow2 = configTable.configRow2.clone()
-                 configTextRow2 = configTable.configTextRow2.clone()
                  blankRow = configTable.blankRow.clone()
                  del configTable.configTextRow1
                  del configTable.configCbRow1
                  del configTable.configRow2
                  del configTable.blankRow
!                 section.heading = html_key
                  del section.iconCell
                  continue
!             (sect, opt) = self.parm_ini_map[html_key]
  
              # Populate the rows with the details and add them to the table.
--- 394,411 ----
                  configTable = self.html.configTable.clone()
                  configTextRow1 = configTable.configTextRow1.clone()
+                 configTextRow2 = configTable.configTextRow2.clone()
                  configCbRow1 = configTable.configCbRow1.clone()
                  configRow2 = configTable.configRow2.clone()
                  blankRow = configTable.blankRow.clone()
                  del configTable.configTextRow1
+                 del configTable.configTextRow2
                  del configTable.configCbRow1
                  del configTable.configRow2
                  del configTable.blankRow
!                 del configTable.folderRow
!                 section.heading = sect
                  del section.iconCell
                  continue
!             html_key = sect + '_' + opt
  
              # Populate the rows with the details and add them to the table.
***************
*** 426,432 ****
                      if options.is_boolean(sect, opt):
                          if str(val) == "0":
-                             val = "Yes"
-                         elif str(val) == "1":
                              val = "No"
                      newOption.val_label = str(val)
                      if options.multiple_values_allowed(sect, opt):
--- 430,436 ----
                      if options.is_boolean(sect, opt):
                          if str(val) == "0":
                              val = "No"
+                         elif str(val) == "1":
+                             val = "Yes"
                      newOption.val_label = str(val)
                      if options.multiple_values_allowed(sect, opt):
***************
*** 449,454 ****
                                       cgi.escape(options.doc(sect, opt))
  
              currentValue = options[sect, opt]
! 
              if type(currentValue) in types.StringTypes and \
                  str(currentValue) not in (0,1):
--- 453,459 ----
                                       cgi.escape(options.doc(sect, opt))
  
+             newConfigRow2 = configRow2.clone()
              currentValue = options[sect, opt]
!  
              if type(currentValue) in types.StringTypes and \
                  str(currentValue) not in (0,1):
***************
*** 457,466 ****
              else:
                  newConfigRow2 = configRow2.clone()
              # for Python 2.2
              if options.is_boolean(sect, opt):
                  if str(currentValue) == '0':
-                     currentValue = "Yes"
-                 elif str(currentValue) == '1':
                      currentValue = "No"
              newConfigRow2.currentValue = currentValue
              configTable += newConfigRow1 + newConfigRow2 + blankRow
--- 462,479 ----
              else:
                  newConfigRow2 = configRow2.clone()
+             
              # for Python 2.2
              if options.is_boolean(sect, opt):
                  if str(currentValue) == '0':
                      currentValue = "No"
+                 elif str(currentValue) == '1':
+                     currentValue = "Yes"
+             # XXX Something needs to be done here, otherwise really
+             # XXX long options squeeze the help text too far to the
+             # XXX right.  Browsers can't wrap the text (even if
+             # XXX no-wrap is False) unless there is whitespace to
+             # XXX wrap on - comma's don't count.  This works, but
+             # XXX it's a bit ugly.  Ideas?
+             # currentValue = str(currentValue).replace(',', '<br />')
              newConfigRow2.currentValue = currentValue
              configTable += newConfigRow1 + newConfigRow2 + blankRow
***************
*** 476,479 ****
--- 489,494 ----
  
      def onChangeopts(self, **parms):
+         if parms.has_key("how"):
+             del parms["how"]
          html = self.html.clone()
          html.shutdownTableCell = "&nbsp;"
***************
*** 490,496 ****
  
          for name, value in parms.items():
!            if self.parm_ini_map.has_key(name):
!                sect, opt = self.parm_ini_map[name]
!                options.set(sect, opt, value)
  
          op = open(optionsPathname, "r")
--- 505,511 ----
  
          for name, value in parms.items():
!             sect, opt = name.split('_', 1)
!             if (sect, opt) in self.parm_ini_map:
!                 options.set(sect, opt, value)
  
          op = open(optionsPathname, "r")
***************
*** 525,529 ****
          '''Check that the given input is valid.'''
          # Most of the work here is done by the options class, but
!         # we have a few extra checks that are beyond its capabilities
          errmsg = ''
  
--- 540,544 ----
          '''Check that the given input is valid.'''
          # Most of the work here is done by the options class, but
!         # we may have a few extra checks that are beyond its capabilities
          errmsg = ''
  
***************
*** 539,547 ****
                  del parms[name]
  
!         for html_key in self.display:
!             if not self.parm_ini_map.has_key(html_key):
!                 nice_section_name = html_key
                  continue
!             sect, opt = self.parm_ini_map[html_key]
              if not parms.has_key(html_key):
                  # This is a set of checkboxes where none are selected
--- 554,562 ----
                  del parms[name]
  
!         for sect, opt in self.parm_ini_map:
!             if opt is None:
!                 nice_section_name = sect
                  continue
!             html_key = sect + '_' + opt
              if not parms.has_key(html_key):
                  # This is a set of checkboxes where none are selected
***************
*** 555,559 ****
                          value_string += val
                          value_string += ','
!                     value = value_string[:-1]
                  value = options.convert(sect, opt, value)
              if not options.is_valid(sect, opt, value):
--- 570,574 ----
                          value_string += val
                          value_string += ','
!                     value = value_string[:-1]   # remove trailing comma
                  value = options.convert(sect, opt, value)
              if not options.is_valid(sect, opt, value):
***************
*** 569,606 ****
              parms[html_key] = value
  
-         # check for equal number of pop3servers and ports
-         slist = parms['p3servers'].split(',')
-         plist = parms['p3ports'].split(',')
-         if len(slist) != len(plist):
-             errmsg += '<li>The number of POP3 proxy ports specified ' + \
-                       'must match the number of servers specified</li>\n'
- 
-         # check for duplicate ports
-         plist.sort()
-         for p in range(len(plist)-1):
-             try:
-                 if plist[p] == plist[p+1]:
-                     errmsg += '<li>All POP3 port numbers must be unique</li>'
-                     break
-             except IndexError:
-                 pass
- 
-         # check for equal number of smtpservers and ports
-         slist = parms['smtpservers'].split(',')
-         plist = parms['smtpports'].split(',')
-         if len(slist) != len(plist):
-             errmsg += '<li>The number of SMTP proxy ports specified ' + \
-                       'must match the number of servers specified</li>\n'
- 
-         # check for duplicate ports
-         plist.sort()
-         for p in range(len(plist)-1):
-             try:
-                 if plist[p] == plist[p+1]:
-                     errmsg += '<li>All SMTP port numbers must be unique</li>'
-                     break
-             except IndexError:
-                 pass
- 
          return errmsg
  
--- 584,587 ----
***************
*** 615,621 ****
  
          # Only restore the settings that appear on the form.
!         for section, option in self.parm_ini_map.values():
!             if not options.no_restore(section, option):
!                 options.set(section, option, c.get(section,option))
  
          op = open(optionsPathname, "r")
--- 596,603 ----
  
          # Only restore the settings that appear on the form.
!         for section, option in self.parm_ini_map:
!             if option is not None:
!                 if not options.no_restore(section, option):
!                     options.set(section, option, c.get(section,option))
  
          op = open(optionsPathname, "r")



From anadelonbrin at users.sourceforge.net  Mon Apr 21 20:25:09 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Mon Apr 21 22:25:16 2003
Subject: [Spambayes-checkins] spambayes/spambayes/resources ui.html, 1.11,
	1.12 ui_html.py, 1.11, 1.12
Message-ID: <E197nT3-0003oY-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes/resources
In directory sc8-pr-cvs1:/tmp/cvs-serv14578/spambayes/resources

Modified Files:
	ui.html ui_html.py 
Log Message:
Re-commit of some changes that were accidentily removed :)

Index: ui.html
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui.html,v
retrieving revision 1.11
retrieving revision 1.12
diff -C2 -d -r1.11 -r1.12
*** ui.html	21 Apr 2003 21:15:36 -0000	1.11
--- ui.html	22 Apr 2003 02:25:04 -0000	1.12
***************
*** 3,6 ****
--- 3,8 ----
  <head>
  <title id="title">Spambayes User Interface</title>
+ <meta http-equiv="Pragma" content="no-cache" />
+ <meta http-equiv="Expires" content="-1" />
  <style>
  body { font: 90% arial, swiss, helvetica; margin: 0 }
***************
*** 136,142 ****
      <td valign='top'>
          <img src='config.gif' width='40' height='40' align='left'/>
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;You can configure your Spambayes<br/>
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;system using the
!             <a href='config'>Configuration page</a>.</td>
      </tr>
      </table>
--- 138,146 ----
      <td valign='top'>
          <img src='config.gif' width='40' height='40' align='left'/>
+         <span id="configurationLink">
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;You can configure your Spambayes<br/>
          &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;system using the
!             <a href='config'>Configuration page</a>.
!         </span></td>
      </tr>
      </table>
***************
*** 310,315 ****
      <FORM action="changeopts" method="POST">
  
!     <p>This page allows you to change the options that control how
!     Spambayes processes your email.  Your options are stored in
      <b><span id='optionsPathname'>/example/pathname</span></b>.</p>
  
--- 314,319 ----
      <FORM action="changeopts" method="POST">
  
!     <p><span id="introduction">This page allows you to change the options that control how
!     Spambayes processes your email.</span>  Your options are stored in
      <b><span id='optionsPathname'>/example/pathname</span></b>.</p>
  
***************
*** 321,325 ****
          </TD>
          <TD>
!                <input type="text" size="26" id="input" name="from_parm_ini_map"/>
          </TD>
          <TD id='helpSpacer'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
--- 325,329 ----
          </TD>
          <TD>
!             <input type="text" size="26" id="input" name="from_parm_ini_map"/>
          </TD>
          <TD id='helpSpacer'>&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;</TD>
***************
*** 332,336 ****
              <span id="label">Label</span>:&nbsp;
          </TD>
!         <TD nowrap='1' valign='top'>
              <div id="input">
                  <input type="checkbox" id="input_box" value="value" name="from_parm_ini_map"/>
--- 336,340 ----
              <span id="label">Label</span>:&nbsp;
          </TD>
!         <TD width='110' nowrap='1' valign='top'>
              <div id="input">
                  <input type="checkbox" id="input_box" value="value" name="from_parm_ini_map"/>
***************
*** 345,349 ****
      <TR id="configRow2">
          <TD nowrap='1' align='right' valign='top'>Current Value:</TD>
!         <TD nowrap='1' valign='top'>&nbsp;<span id="currentValue">(value)</span></TD>
      </TR>
      <TR id="configTextRow2">
--- 349,353 ----
      <TR id="configRow2">
          <TD nowrap='1' align='right' valign='top'>Current Value:</TD>
!         <TD nowrap='0' width='150' valign='top'>&nbsp;<span id="currentValue">(value)</span></TD>
      </TR>
      <TR id="configTextRow2">
***************
*** 352,360 ****
      </TR>
      <TR id="blankRow"><TD>&nbsp;</TD></TR>
      </TABLE>
      </span>
  
      <center>
!       <input type="submit" name="how" value="Save"/>
      </center>
  
--- 356,374 ----
      </TR>
      <TR id="blankRow"><TD>&nbsp;</TD></TR>
+     <TR id="folderRow">
+         <TD width="25%">
+             <input type="checkbox" id="folderBox" value="value" name="folderName">
+             <span id="folderName">Folder name</span>
+             </input>
+         </TD>
+         <TD id='helpCell' valign='top' rowspan='1000'>
+             <p>(Help text goes here.)</p>
+         </TD>
+     </TR>
      </TABLE>
      </span>
  
      <center>
!       <input id="config_submit" type="submit" name="how" value="Save"/>
      </center>
  

Index: ui_html.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/resources/ui_html.py,v
retrieving revision 1.11
retrieving revision 1.12
diff -C2 -d -r1.11 -r1.12
*** ui_html.py	21 Apr 2003 21:15:36 -0000	1.11
--- ui_html.py	22 Apr 2003 02:25:04 -0000	1.12
***************
*** 5,175 ****
  
  import zlib
! data = zlib.decompress('x\xda\xdd[\xffo\xdb8\xb2\xff}\x81\xfd\x1f\xb8:\xb4J\xb0\x89\xed$mo\xcf\xb1\
! \x85k\x93\xec\xe5p\xed6\x97x\xdfa\xb1X\x14\x94E\xdb\xbaH\xa2\x9eD\xc5\xf5+\
! \xf6\x7f\xbf\x99!)Q_\x92\xba\xb7o\xef\x01/-bK$\x87\xc3\xe1|\xf9\xcc\x90\x99}\
! s\xf9\xfeb\xf1\xd3\xcd\x15\xbb^\xbc{\xcbn~|\xf3\xf6\xaf\x17\xcc;\x1e\x8f\xff\
! qv1\x1e_..u\xc3\x8b\xd1\xe4\x84-\n\x9e\x95\xb1\x8ae\xc6\x93\xf1\xf8\xea\x07/\
! \xf8\xfa\xab\xd9F\xa5\t}\n\x1e\xe1\xa7\x8aU"X\x1c\xcd=\xfa\xe6\x05w9OC\xbe\
! \x13%\xfb\xb1\x14\x05\xfbk\xa6D\xb1\xe2K1\x1bS\x07\x1cS\xaa\x1d}\te\xb4c\x9f\
! \xd8Jfj\xca\xfe4y\xc6x\x11\xf3\xe4\x88\x95\xdb\xb8,\x8f\xd8F$\x0fB\xc5K~\xce\
! R^\xac\xe3l\xca&\xec\xd7\xaf\xbfR<\x84)\xf7\x18\x87\x9dW\xb2H\xa1o\x8b\xc0\
! \xd7_\xf1i\x12g\xf7\xf0~)\x13YL\xd9\x1f&\xf0\xb3\xa4F>}\x88a\xd5"z\xa4u#\x1f\
! `YM\xdb\xab\xc9\x8b\xc9j\x85m\xa3%0$2\xc5\xb8a\xeex+\xe2\xf5\x06x\x0ce\x12Q\
! \x8f\x87Xli\xe6^\x97\x0c\xf8\xe4\x89\xe6n\x14\xf2,\xa3IB\xbe\xbc_\x17\xb2\
! \xca"\x98i9\x110\xd39\xcby\x14\xc5\xd9z\xfe\xb2\xfez\x9c\x88\x15\xd08yy\xfe\
! \xf5W\xac\xfe\te\x11\x89\xe2X\xc9\x1c\x9a\xf2\x8f\xac\x94I\x1c\xb10\x01\x9aC\
! \xfdB\xa9\x94L{]\x89o\xdcmb\x88x.\xe3\xff\x11\xd0\xef\xec\xecYk\xd9\x8d\x94O\
! ^RC*\xca\x92\xaf\x85\xde/\x85\x02\xed\xf0+>6K(\xb4\x1c\xe0\x1d\x8d-\xc5\x125\
! \xcf\xee\xb5\xe6\xd1e\xee\x0f\xdfM\xf0\xdf9\xdb\xc6\x91\xda\x80\x1e\xbc|\xe6\
! \x0eD\x8e\x81lG\x86\xab\xd5\x8a\x8b\xc9\xf9\x00\x1f\xae@>+\x18;\xf7\xd0\xa0\
! \xe1\x8d7\\\x19\x8d7\xd3\x03\xc9I\xfe\xd1\xecy!P9\xb4\xa0K6\xa8\xa0\x13R\xc1\
! ^\xcfa}5\x9d\x1b\x8d{\x82\xa2\xd3\xe9)b\xb8\x0eU\xc4\xb9\xf8 3\xbd\x9f-\xfd\
! \x14K\xfcg:V\xf15x\x8a\xeb!\xbd9\x9d<;\xaf\xa9\x7fG\xd4\xcf\x87\xc56\x1b[W1\
! \x1b\x1b\x87\x03_I\x88\xe8q\xf0\x8bG\xefP\xf0\xb3(~`\xcb\x84\x97\xe5\xdc\xd7\
! \x06\xe4\x07\xa6\xa5\xccyF#\xc05\xa4By\xc1,N\xd7\xac,\x96s_\xbf\x19\xad\xe3\
! \x95\xcfx\x12\xaf\xb3\xb9\xcf\xc32\x8d\xa3(\x11\xfe8x\x9e\x85e~\x0e|\x00\x85\
! \x1653\x91\xde\x05;Q{\xb2\xbc\x90Q\xb5T?\xf0\xb4\xe5\x16\xff!B\xd7+\x12\xe5\
! \xa93\x9ekNe*pK<\xb6)\xc4\n&\x82g?\xb8\x86\xdf\xb31\x1f\x9e\x0eL-\xa3\xb9\
! \x9e\xaf\xd59\xab\xe2\x11\xfa\xea6\xeb\xed\x07\x10\x98\x96(J\x0eI\xa4<\xce.\
! \xb45{f\x85\x9e\xb1n-\xe7\xd9\xe6E\x00\xbc\xeb\x85\x81>\xc3\xb6\xbch6 \x0f\
! \x16\x9b\xb8d\xab8\x11Gl\xb6\x94\x91\x08j.\xe8\xe9\x88Eb\x15g \x04\xb5\x11,\
! \x91\xf2\xfe\x98g\xd1\xf1J\x88D\x93\x90+j\xa90r\xc4VF\xf6m#\xc2;Q\x80\x13\
! \x1e1\xb6\x80\xd7\x0f\xe0\xfdeUj\x02y\x0c:X\xe2\x08\x8acz\xba\x08BB! J\x08&>\
! \xaa\x82/Q\xc1ab\xf0WY\x9c\'U\xc2\xe9\x85\xd2$\x8a*Sq\n\x0eK\xb2h\x07\x02\
! \x85@\x92$;\xa6wS\x10\'D[m\xb8j\xf3\xa5\xc7k\xe6X\x89\x1f%\xabrv\x0c\xbd\x8c\
! X\x18\xcc\r&\x0b\xff\xc1\x07$B)aY\xd5c\x972\xcde\x06\xe2.aqZ\x827\xbbw"\x89\
! \xde\x82Q\x1a!\xb2X\x8b/\x05~\xd0\xaf"\x1b\xc0\xdcC\x1cY\x0e,\x8b\xe0\xfa\
! \x8fe\xf8Op=\xb0\xd2<Gw\x98\x00\x9f\x85\x1e\x93\xf2{\xe0\x0f\xd6\xa6\xd9\xcb\
! eY\xc6\xe0lG\x9a\xc6\x15_n\xb44ka\xd2\xa8L\x88\xa8D\xd9\x84B\x8b\xcfHo\x83\
! \x8b\xca\x8c"\x10\x9fqd\x19V|}D\xf2\x0e\x05,\x10\'e7;\xb5\x01\'b\xb8\x03\xba\
! F\xea\xa3\xd98w\x15\xea5R\x85]\xe3i\x9e\x10\'\x1b\xb9\xd5\xfcneqO\xc1\x1ev5\
! \xd6\xbd\xa2X\x85\xf2#\x04\x04\xb5\xd1\x04\xe0e\x97\x17 \xa1_\x19\x9a0\xc04\
! \x19\x1b\x9c\xc5Y^)2\x87\xa6\x8b\xc7\xd4.\x17\x80q@\x7f<\xd0\xb8\xa4\x12u\
! \xb3\xc7\xd0\xaf\xcd\xbd\x93\x8976\xa6\xd5\xec\x19\x83M.\xd9NV\x8e\xb0\x1a\
! \x15\x82m[\x17<M\xb9\xd2J6m\xad\x1e\xad\x92\xfc\x1f\xf8\xb3~\xf8{5\xc1\x7f\
! \xb5\x8b\xcbA\x0c\xb6\xb3\xeb\x94m\xc4\xab\x01\xd0\xb9\x1b}\xea\xe1\xe8~\xb5\
! O\x9e{\xe4\xf1/&^\x00?\xb31\xb6\x80\xce\x81^\x16\xcaY\xd8\x9e\xe3\xd0\xf8\
! \xd9\x9c\xc9\\d\x07\x9eq\x06\xde\x11\xf3\n\xe5\x1dB \xe3\xd1\xc1\xe1\x9e\x94\
! "\xb9\x04B\r\x03#tT\xe0\xafDq\x80D\xf7%\x93\x17\xe0W\x90\xd8\xa8\xd9]\xbb\
! \xf1\xc1\xf3D\x9d\x0fo\x7f\xbd\xc5O)\xc2\x18\x1d\xefl\x1c\x07\xfb/\xc9\xe1bD\
! \xd4`\x8d\xde\xc5\x86gk\x11y\xff\x87K\xb2,t\x974\x06=\xeb\xc5\x0fc\xabw\x924\
! \xdb\x986\xda\x14\xf9\x89*\x86`^\xab|\xc7\xb5c\xd0*\x81wQf\xbe\xf1\xbf\xe8ap\
! \xe0\x8a\x03\xac\xe6\xa1\x04\xd6s^*\xf4^\x88>\xb25\xba\x1f@\x95`\xf9GL\x16z\
! \x02l%\xfa\x8d\x07\xd5\xd4V\x85LY\xb9,\xb8\x02\x7f\x16k\xb6\xc0\xb7\xbe\xce\
! \xa2~\x0cB?\x82\xe1\xae\x90I\x02<\x80\xa1\tp\xfc\xe1\xcezUh\x06\xd2z\x1e\xf2\
! \xe6\xc7l\x89r\xc2\xc9\x91\x18\xd9_\xb9\x11B\x1d1\x85\xc9\x13X;\xb6\xc1r\xa5\
! \x89o\xc858\xe1l]\xe1\xc2\xc1+\x92)\x82C\xcc\xc4\xb6q\xb7\x1d!\x1d\x93\x97\
! \xd6Q\xb0\x1457(\t\x8ci\x10mvL\xf0r\xd7u\x9eoD\x02\xde\x12\xbbh/\xdf\x0b\xac\
! \x8d\xb0\xa0\x87\x04>\xd0ub\xc7\xb8\x18\xf4\xe4e=\x03B\x81\x02\xdd\xdd,\xb7@\
! \xc1E|^@\xc0(z\x83\xde\xd5\xe1\xc9\x01b\xa6\xd9\xb3\xda\xa4\x91\xbe\x81U.\
! \xfa\xf7\xd9R$\t\x8c\\b\xd2\xe37>K\x15\xc1\x0cP\xa8%\x07\xad^g\xbcy\xed\xa3\
! \xf5\xe0\xd4s\xff\x140\x14M\xcd\xc8\xf1\xab\x08\xac\x08\xe8\xf4(\xfa1(\xc2\
! \x05\xcc\xeb\xa3E\x10,\x84<\xca\xef\xd0G\x00\xea\xeb\x04\x04HO\\\x18\xa8\xcd\
! \x0fP\xa6%\xe6k\xbcY*\xae\xaaR\xe3M3\xf0\xc5\xc4\x870\x86\xc8\x97\xbe[\xd0\
! \xe9`<\xe4\xd3y4\x8b\x86\x15t\xc0Z\x8b/g\x04\xc12\x0c\x92\xcc\x11<X\xc1;Y\
! \xaaa\xccUZ$\x05\xda\xd3\xd0\x01\xe3/a:\x90\x1eX\x12\x9a\x82\xd5I\x03\xc5\
! \x9a1`\xcd\xed\xde\x8e\xea\xea\xd4\xea#t\xd4\xc1;\x1b\xc4\x8a\xe8\x02\xf8\
! \x83\x84P\x17Uy\x02\xf1\x11\x17f\xb1\xc8\xc8\xba \xbb\x81\xf0\x0bu\xc5\xac\
! \xd9\xa0\xf6\xb0\x18w\x81\xef\x1e\x9a\xabw\xa8\xa5\xb6Z7Q\xe6\xbaq\x81\xcf\
! \x9e\xc9\x0f\xe7\x1e\xb8PWE\xed\xb3\xcd\xd3\xe1\xb9\xad`\x83\xf0]S\xf6\x1e\
! \xcb$>\xee.!\x91\x8e\x93V\x8f\x9b\xf77g\x8c\x1a\x11?e\xe8I@F\xb30\xe8\x0c\
! \xbd\x81\xd8]\xde\x91\xf3\xf4\x82\x93\x93\x93\x89\x91\xc7l\x1c\x06G\xee\xf6B\
! _rf\xb2M\x84\xb0lQS0Q\x04\x12\xff\xd4!4r8o$\x8f?\xafA)\x1f\x84\xe6\x16,\x01I\
! \xd1n\x96\xd3\x8e\xbd\xb8sr\x1at\'\x00\x95BO/py\x1eu&\xe8S\xd6\xde\xba\xd4\
! \xa3\x9f\x9aFI\xc5\x93\xfdfieO\x84\x91S\xdc\x10\xadE\xf1*\xc6\xb0\xb5\xe7\
! \xacY\x95b\xd6\xd0\x99\x90\xc1\xb7\xf4\xe8\xe9a\xd7\xfdQ\x9b\xcf\x0e\xfa1+\
! \xabBt\x86U\xf4\xb2\xbb\xc8\x05\xca\x83\t\xbd2\x08b\x98>uV\x82\x9cO;s \xe7m\
! \xfa\xed1\xd7\xfd!\x9b\xee\x88\xa7\xc4\xed\xb8@t\x7f\x06\xe9\x9a\xd2\xcf+\
! \xf1\xd17N\xd3\xfd\xdd\x19\xe3\xfaqw\x9a\xba\x14\x00\n\xb4\x8a\xd7O\xb9f[!\
! \xc0\xb2\x91\xef\xf2\xda\x9f\xbc\xff\xfb\'H\x02\x96X9\xa0i@\xf4\x98\x16\x14M\
! \xf6\xd8Y\xfe>$\xcb]\xa9D\n\xae\xdb \x90\x8e\x16pS;\xd03\xfa\xc1\x85\x99Y\
! \xbbR\x84^XK\x18\xb9rr\x82a\xedQ?\xeb1uAj\x01\xf8\xb1\r@h\x9f\x9bF\xeb\xb9\
! \x16\xad\\^\xbb\xafR\xc9\xa2\xceF!\xb3\xd4\x95C\x08Z\n\xccI\x94\xc6\xb7X\x11\
! \x92^R\xc7\xda\xf6\x00\x07\xf2\x12,\x10+S\x1bY6$\xf4\xc8ZD\x8dT4c~pK\x9fu\
! \x7f\x14\t\xc9\xa6\x8e1{"\x1e\xb3P\x14\xda0\xe6\xd1\x1dH\xaau@\xc0\x92\t\x04\
! F]\x9b0F\x87i\xf6\xce\xac\x14\xa22z\xe3z\xc1\xa6LP\xaf\x1a\x02\xef\xc5F,\xef\
! ii\x90\xe3\x17\x12\xb2\x01\xcc1\xc3J)\x90\xc5\n\x00\xb2\xc0T\x9e\x88\x1f\xd5\
! \xf5\x01,`\xc50\xcc_ e\x1f2s\x80\x8a@\xcc\xbf\x14+Q\xf8\x90\xb6\xf2\x07S\xa6\
! 1\x82\xd1C1b\x1f\x99\xf4\xdfx\x07\x149\xa6\xb5\xc4\x0b\x11m\x90\x81\x1et\x19\
! \x97K^Dl\xcc\x88:|\x82;\x80\xdf\xa8\x04\xcc\xd61\x81\xe6\x92V\xd2`]=Z\xaf\
! \xa4\xd4 \x82\xa3>\x10\xc6\xb1\x10d-\xdb\xb0\x97\n\xfe\x9c\xba\xd4{\x0ck\x00\
! \xa5\x00 \xf6\x97\xab\x85c\xfb&\xd5\xa7\xf4\xc7\xdf\xc4Q\x04\xb0\x85a\tm\xee\
! \x83\x14%\x88\x01\xc1\x9b\xf9\xaa\x13#\x7f\xe2\xda\xfd\x13\x042Px=^\x7f\x1b\
! \x1c\xaeq\x85\x81\x11\xd0\xd6\x82\r\xf6\xb9\x8f|\x1d$\xd1\xe2\xa0\xac\xc24V\
! \x96\x83\xb5t\xf8\x7fCB\xf4\x87\n\xd6\xf8c\xb8\xbbAy\xc9\n\x122\x0e\xb86\x8a\
! K\xe4\x0fH\x9c8\x95\xd0\x16|\xd1\xaeu\x1f.P\n\xfb1\xf1\x03\xf4\xfcR\x06\x1es\
! \x90]\xe4\xdc\x87\x8a\x98D\x17i\x0b76\x96\xbb,\xe2\xdc.\x0b\xd3\xe3\xf1?\xf9\
! \x03\xd7o\xfd`<\x9e}\xf3\xf3\xc5\xe5\xeb\xc5\xeb\x9fM\xaaYeZ3e\xa6}\xc2\x01\
! \x8e\xa4c)H>\x17\xd2\x94(>5\xfc\xc4+v\x00y{\x95\x02L\x1e!\x1f%{\xfe\x9c\xb5\
! \xdf\x8c\x12\x91\xad!+\x0b\xe6\xec\xf4\xb0\x19\xfa\xa9-E\xd2\xfayg\xe8\xcf\'\
! \xbf\x9c\xf7\xba\xb1\x83\x18:N\xceY\xccf4\xccL\x00/\xbe\xfd\xf6\xb0\xdd\xfdS\
! \x7f\xabJ\xc0\xe2T\xd2\x06"8\xfa\xe7\xf8\x97\x11\xee\xf4\x88\x1a\x0e\xfc\xa9\
! \x7f8p,\x82\x0b\xadG\xda\x15\xcd\xe7\xec\x0c\xd7[7\x00\xbf\xf8\x12\xa5\x06\
! \xef\x87\xd5\xc4\xcei\x8a%\xf3Z\xba#%\xdf\xca\xad(. \x0c\x1c\x1c\x1e\xf6G\
! \x7fz\x9a 9\x1f\xf0f0\x7fQ\x89\x815\xfc\xda~\xe5<\x9a\xaf\xe6c<\xfe\xe5\x97&\
! \xed e\xd9\xd3;\xdd\xbc\xbf[\xf8A7\xe7\xf0m\x16\xacS<\xf7Pm_\x87\x01\xde\xc2\
! \x89@wUhcV+\xa9\x04\x00\x16\xbc\xb3\x81\xd7\x01\xb5\xbcdxd<%\x8c\xd6KEq\xd4\
! \xf7\x85L\x1fi\xb6l\xb7\x0e\xad\xc09\xc8m\xc1s4l\x1c?\x8c[\xbc\xc6\xda\xa6\
! \x8dM\xf9\xc8\x8b\x7f\x04\x91JG\x15\xd07/0\xdf)v\x8f\xff=j\x14\xf7\x88\x16~\
! \xfb\r\x94 \xb6\x11\x1d\xf8\xfc\rT06\x12\x19\xfc\xd2>\xf2\xd1\x9a\x15\x06\
! \x83\x05\x82v9\xc3\xd9\xf5[\xb9m\xca\x04\xf6\x14\xcf\x1f\xde,{\x1e\xe8\xf7w\
! \x86\xd2\xc1\x8a\xca\xf6\xe6h\xca\xc3\xde^\xd07\x98[1up\x1e\xd6\xffu\xf5\x96\
! \x15ry\xff\rc\xdf\x1d\x1fv\xce\xb2\x86\xeb\x1cX\xc2\xfb\xe0\x05\xb7\xf1r\x13\
! \x0bv\x1dg\x11\x18\x06\xd65\x0bz\xf3g\xf0w\x80y2LGu\xb5\xb2G\xc5\xc0\xf6%V#\
! \n\xbfW_\xe9\x85\xf2\x82G\xb1\xb4\x11\xccX\xc2nJF\xf0\xb7\xab\x9f\x86\x03\
! \x18r\x1ai5\xb4UT\xdf<\xd7\xc1\xab\xff\xfb\xf7`\x02\xf5\xd7k\xe2)=\xffgY\xc0\
! \xd4\xce\r\xe9\xf0\xfc\x9fe\x80\xd2Q\x87\x01|\xf6\xc7O\xaaZ`\x94\xdb\xceb\
! \xb5\xbb~\x0e\xee\xf0\xeci\t\xf4(Gx\xda\xe6\xc2\x84g\xf7hrA\x03Ot\xb5\xea\
! \xe9\xc7>%B\xd9{P\xdaC\xe3;\x19fO\xda\x16\xb9\x19\xa1\xe9\xd4`\xfcy?\xf38\
! \xa0\xfa\x92\xba[\x95\'\x92G},\x8fB\xd0m^\x1d9I(\xad\xedo\xc5P&\x00\x89\xd1\
! \x92\xd2*Qq\xce\x0bE\\\x1dG\\q\xeb\xd4\xaeb*\xc6k\xd2\x8c\xdb<\xc7I\xd8d\xf1\
! !\xc5\xa3\x92\x00PSJ\xf5bZ\r\xd5\xfe\xdb\xa7\x85z2|o\x95U\x7f7\x92\x04!:\xb2\
! \x7f_\xd0\x81\x86\xa0\xf4e\xbb\x91I\x9dc\x016\xcb@\xc1\xe8H\xc0\x84\xcaCJ\
! \xb9\xa6n-\x13\x91(\xe4\x8b\xdc\xcc\xa4(\xbf(\xe4\x16\x1c\xf7\x99.u\xcf}<\
! \x19\x84}1=\xdd\xd9\x9d\xf3M\xbd\xdf\x1f\xb4\xb1\x0c\x81\xf7\xed\x06<l[\x1f\
! \x10\r\xdc\xb9\xd6\xd4\xa7\xb7\xf9Br\xd7ORk\xec\xf1\xf3$/L\xdf\x86\x9cU\xc6:\
! \xdd>\xc0\xea\x83\xd9sR\xaf5\x1e\xd0VX:@p\x1cJ<\x00A\xce\xe8X&\x8b,\x10\xa2\
! \xba\xe8\xb1Sd\x8937\xddn*\xdf\xac\x10\xa9|\xa0\xfb\x04\xf5\xa1\xf6\xe1\xdeE\
! \x84-\xe4\x82\x7f\xafD\xb1\x1b\xb6\x83\xba\xb91\x05|\xf5\xdf\xf8\xca\xef\x8b\
! \x10\xdb<+)\xf8\xde(\xa4\x93\xd4\xf8\xfa$\xd0?\x9btwa\xd8+\x00\xc2\x04}5\'s\
! \xf6(>\x1a\x12\xf9gW\xbb\x82Xn\x10\xe7\xf0z\x9d\x0e\xde~\xb0\xb9Y<\x8e\xf5jk\
! \xcc\x9e^\xfc\xc9~\x8b\xbfBwJU\x918\xb2\x07\'\xd6v\xf1\xc8\x12\xa7\xf9w\x04\
! \x81\x12\xbcS\\\x95\xc3\x95\xa3\xba\xd9\xc2\xac\x1f\xaa4\x04F\x80\x034\xde\
! \xbav\xd5)\xb1b\xdbRVxy\xe7\xe4\xf4\xec\x91\xcavCj\xf38\xa5MM\xe8\xc5\xcbW\
! \x8f\x10\xba)d\xc8\xc3\x18r\xb9\x9d.\xd44.u\xa9\x8f\xeau\t\xce(\x0c\x9eG!\
! \x83\xd6\x91v\x19\x07\xdb\n\xbd`2\xfa\xe3w\x7fzd\xc2/\t.\xd6\x8aoE\t\x11\xe1\
! \x111w:9E:\xaaT\xe5\xcd\x02Q<\xf6x\xc5\xbeCfI\xcc\x98\x06\xe5A\x9f8\x00\x07\
! \xe7\xc0\x13\x7f\xc8\x19\xe9D\x0f\xe4O=\xd8Z\x9a\x83\xb1#\x96\xc4\xf7B\x0b,D\
! \x9d\x06g\xc9\xea\xe3\xbbC\xf7\xcaXs>E4\x16n\x89\xb1\xe9T4=\x08O\xf4\xd1\x93\
! E\xdc\xd8\xc7\xb3E\xf6\xee\x05M\x88,W\xe6>\x0e\xeec\xbf \xd3"5$\xa0\xde\x00\
! \x07L\x0c\x01\n\xf7\x1c \x0fn\x85\xaa\x8a\xac\xa9\xe3\xb6o\xc6\xe1\x8d\x00\
! \xbb\x8f\xe0\xbf\xe9\xc0}:\xbc\x1f\xba\xd3k\xdd\xc7\xd3\x91\xc1F\x10\x13\x1b\
! \xec^\x1c\x0e_\xa3\xdbG\xf1\xa8\xe6\xfe=P{D\xe7\xea\xf6Z\xdd\xbe\x7f\x7f\xfb\
! \xce:;\x8f.\x18\x08\x99\x83:Z\x87\xe7\xa1\xc3\xf3z\xd7\xee\xb0f\x8d\xc5S\x00\
! \x02T>\xa6\x82*\x0e&/\x05\x14\xcc\xb9\x18W\xf6\x92\x03^\xa62w\xd6\xdcr<\x04\
! \xb2R\x94\xfat\x82\xca\xc6#\xaa\xbc\x175\rNw\x8ddA\'\xbb}\xf3\xf5M\xbf\x1b\
! \xae6\xe8~\xfd`lN\x0c\xc7\xb9y\xd5\xb2\xe8\xcf\xc8\xe5\xa2\xb9\x80H]\x16\xaf\
! \xdf\xbc\xbdr\xfa\x0c\x1f\xc6\x0e\x1c\xbe.n\xddQ\xe0\xfc\xc1\nNZ5\x90\xc5\
! \xa5\x01\xce\x1e)\xbb\xe7\x96):\x1a[3\x9a\xf0P$^\xf0\x16?\xecm\xce\xfe\x01\
! \xfe\xe2\xb2=O\xdfb\xdc\xb0c\xee\xe2\xe8\x1b:\xa7\xaf<\x9a\x88\xdaM@\xd391\
! \xe0\xda\xf4\x03\xb8\xd5\x0f)\xcf\xbd6N\xef\xceG\xfb\xb2\x11I\x0e;\xbdl2\x82\
! \xc7\xeb\xa6\x8f\x12\x18\xb8\x14\x81\xd8\xd3\xde\xae\xe8\x88\t\x00\xd75\x0cb\
! \xb8\xa0\xc6\x9c, \x1a\xe0\x17\xbe\xde\x0en\xd8E\xf8%\xdb\xf5\xd8i\xdf\xff\
! \xc6\xde\xed;\x8d\xbdU\xab7n\xc8G\xba[N\xf5G\xba\x98U\x8f\xf9@\x8f\xe6F\x16}\
! \xec\xb7\xfd\xfd\x85\xc2\xe0\x0ff\xb1\xffE\x85Sw\xc9\x83Y\xb8\xb9\xdc\xf5\
! \xffY\xa3@\x9fN\xbd\xc7\xb7\xd6\xf0C\xaa\xd5\xd9\xe8\x8b\xaa(\xf0/\x1eH\x96\
! \xd3/\xd0\x10#\x8b\xc6\xcbiBD\x07"\x10\xed\xf1a\xed\x1c?\xbf\x04\xe3\xc5~\
! \xafe\xfcN\xbc;\xc5\x11\xe8\xe6\xe8\x87\xdbwL~\xbe\x1fq\xf5\xb54\xaak\xd4\
! \xdc\xb6\x0cICvk)\x1b,{\x1a\x13\xba\xe3\x0f\xc2k\xd0cM\xc4\xbe\xc0\xc0\xdb<\
! \xb6\xc2p!t\xc0\x13+N\xd0\xb0\x17\x8b\x7f\x03[\xb7\x9a6\x1e\x8ej\xe2\x03,\
! \xb6\x18\xfc\xe2\x1bM\x9bJEr\x9b\r\xa5Z\xfa\x90\xbe\xd3\xc3\xc3\xa2\xfc\x9dy\
! GA\x9a\xfdE\xca(\xdc5\xf7\xb3\xcd\x94\xf8\x97\x19\xf6\x1a(|o\x127)\x15V!m\
! \xceV\x82\xe8\xfb\x19\x9b\x01\xae\xe6\xb2\xc5\xc9d\xf2l\xe8\x04c\xe6\xd4\xc4\
! \xa2\xe1\xbf\xf0h\x8a\xd3\xbe\x9e\x19\xe1\xa0\xdf\x02\x88\x8f\xfe\x01\x06w\
! \xaf@9\x17\x83 q/\x15\xc0\x16/x\'3\xd8\x9c%;\x9b\xb0\x93\x17\xd3\xc9\x8b\xe9\
! \xd9);\x9dLN\xcd\x1e\x8cZ<\x989\x95\xca\xa7\xe3\xf1v\xbb\x1d\x95v\xe2\x91,\
! \xd6c\x87\x11|\xeeV\x12\x9b\xd2\x9d1\xd8\xf6r[\x9bE\xc0\x07\x9dg\xcb\xfa\x87\
! \xb2W\x94\x8b\x1de\x0eaMb\x0cz\xd8\xaf\xa2\x9ad\x17\xcd\x85=\x07\t\x9c3;\x18\
! \x0bY\x9a[\x03\xd9\x1b\xa8\xee\xa4\xbb\xa012\xda\xe9\xbf\xda\xd1\x7f.\xf8/\
! \xb3M\xb1\x95' )
  ### end
--- 5,83 ----
  
  import zlib
! data = zlib.decompress("x��[{o\0339����\016�^$mcmI��ܬ,56�=��%\023����`00(5%q����e]�����d7�\
! aY���\003�\011,u�,\026���U��|w��b���\025��}��n~����\027�;\036\016�rv1\034^�.u���2\
! �䲐*��px��\027|��d]�\021}\012\036�g!�H0\031N=��\005w)��|+r�S.2��\020ْ/�dH\035pL,\012\
! ��E�\036����q��d|\025s�-\024�N�����\005_��dž�\003��R���\031q|b��Ŗf��p˾�%t\030�?\
! �^1�I\036\035�|#����E�(\012���,��J&c6b�����a={���K��зA��o�8��\003�_�He\
! c��\021�,���\037%�T�ϴ��#Ȭn{7z3Z.�m`Vʸa�x#�j\015<�U\024R�G)64s�K\002|�Hs7\
! ��$�I�|��T��0�b$`�s��0��j���z\034�%�8y{��7����,\024�q�RhJ�X�\"\031�y\004\
! 4���UQ��ӕ�FU\"���\\���~gg�\032ˮ�|�\032b��|%�~\025(�\026��^B��\000�hl.\026��v\
! �5�.s��~����F��\032���+w r\014d[2\\.�\\��{�p\005�`��}��7�pe4�L\017$G���L\
! �rhA�WAG������j:�\032����i\0271\\G��TܫD�gC?�\002�����\0067tݧ7��W�\025���\
! y��&C�*&C���+\011\021�\031~��\035\012~\022�G��x�O}m@~`Z�'4\002\\\0038*/��x��l1����J.\
! }�#�J�>��\014�H���u2��s�\003(4����.؉����\012�E�#�\033>�/b�\\�<v�sͩ�\005n\
! ��֙X�D��\007��{2��Ӂ�%4��Uq�J9�@�d��\000\002�\022E�!����B[�gV�\031��r���\004�\
! �^\030�3l˛z\003�`��9[�H\034��B�\"����#\026��L@\010�Z�H��c���K!\"MB-��İ$����\
! Z�w\"\003'<`l\006�\037���2�\004R\011:��\010\012�z�\020BB& J\010&���/P�ab�W�L�2����$�2)d\014\
! \016K�p\013\002�@\022E[�wS\020'D�X�ɗ\036��c9~�L�1�2ba07�,�\007\037\020��\020�U=v��T% �\034\
! \026�%x��$��#\030�\021\"�Z|1��~\025�\000�\036eh9�,��?V�끕�)��\010�����?\000�6�^��\
! \\��\035h\032W\020۵4+aҨD�0G�̅\026���\032\027�\030E >eh\031.���=\027�@���l�58\021�\035�5R\037L\
! ���P�*�\032�ӈ8Y���w��\007\012���R�\012e1WO\020\020��&\000/ۼ\000\011��Є\001����D&iY�9�]\
! <VlS\001\000\012��\003��JQ5{\014���;\031yCcZ��1��mU�\010�V!ضU��\027Z�ƍգU��\003�\015\
! �F��rq)��vv���x\025\000:w�O5\034ݯ��S�<���\013�g2�\026�9�ˬp\026��84~6e*\025Ɂg��\
! wļ��\016!����pOJ�Z\000���\001:*�W\";@���I3�+HlP����uT��o�Ż\024a��w2��\
! �Kr�\030\0205X�w���J����,\013�%\015A�:����\"�6��6E~��\020�+�o�v\014Z9�.��7�\027=\
! \014\016\\r��|�����\005z/D\037�\012�\017�J��#�2=\001�\022�ڃjj�L�,_d�\000&5[�[�'a7\006�\037�p\
! ��(\002\036��\0048���zUh\006�z\036���l�r�ɑ\030�_�\026�8b\005ff`��\006�U&�!����U�\013\007�H�\010\
! \0161\021��ݶ�tL^ZG�\\Tܠ$0�A��2��m�y~\020\021xK좽|'��‚\036\012�@׉\035e����j\006�\002\
! \031%s�\005\012.��\002\002F�\007��\016O\016\0203͞�&��\015�rѿ�\026\"�`�\002�\036��YE\026L\000�Zr��ƛ�>Z\017\
! N=�O\001C�Ԍ\034\021�\025\001�\016E_�\"\\��>Z\004�Bȣ�\026}\004��N@��ȅ���\000eZb�ƛy��2�x�\
! \014|3�!�!��\026t:\030\017�t\036͢a\005-����\031A�\014�$s\004\017V�I�E?��-�\002�����0\035H\017,\011M\
! �꤁b�\030��foGuuj�\004\035u�Nz�\"�\000�� ԅe\032A|ąY,2�.�n �B]1k6�}�\015��w\017�\
! �;�P[��(s�8�g��S\017\\���������T�^��){�e\022O�KH�e��q���Q#�\004=\011�h\
! 2\017ZCo v�w�<����dd�1\031΃#w{�/93�$BX6�(�(\002��\020\0328�גǟ����Bs\013���\
! h7�q�^�99\015�\023�J��\027�<\017Z\023t)ko��ѻ�)T���fidO��c�\020�Er)1l�9kRƘ5�&\
! d�->�=�;j�⠟���DkXI/ۋ��<��+� ��Sk%���5\007rޤ�\034s�\035�n��%n�\005��\
! 3Hה~މ'�8M�wk����i�R\000(�R�v�f[!���?�5UM��H\015?b\002�t�����3�\012\013,0\030\
! B\002���N2[Rڇd��\013\021��7@��,ܔ\030�~p�.�\020\032�\034\006��q��\004��\023��iu!k\006��\011\\H�\
! u���Q\003�n//TVe����#\004�\002�P�i+S�g�X�,�G���bEk��\036Yɬ\026�f�\017n�\
! �2\"aU�iO�d\026�B��J�\003I�\012$Xj���k\032�X1=ߚ�B4G/^-ؔ\027�UC��X��\003-�� L\
! �\"07��E\001�X\002�\026X\002 �GU]\001\013_\022��3��CF\017\020\023���b)2\037�]�h�;F0z(F�#S60^\005E\
! ��0�BDkD�\007]�|���\015\031Q�Op#�\033����'�\\�Jj��G��\032|p�\007�F\026��T\023.�A\001�.�\
! \036�\032@)\000���j��\014S\"���_�0\004�ð�6�A�\012Ā��|�\011�?r��\016\002\011(�\036���\016�x��\017hk\
! �\015��E�\016\002ip���X\026���r��@B��\012��c��Ay�\022\0229\016x8�9�\007$N�\012j\003�h��\017\027(���\
! �\021z~-\003�y�6��BLL����7k�]d2��´z�W���[?\030\016'��rq�~��\027�����L�h�p�\
! #�8\013�֙2��/5?r�\016 �/c��\003�#g�_��A$�\025ds���\036�C�4�HZ?m\015�����N7v \
! ���I6�af\002x���\0376��nU\016\030�J�@\004G�\"\035�N\017���\037��=�)��j�]�t��p�U\003��\
! /Qj�_M윦�2��;(�G�\021�\005�������/�\011��\001o\006�g��Y�ߛ��G��|\014���Z�+�,\
! {z���w3?h�*�͞uj�\036���0�[8\021讜ۘ�HF\001�\005�l�u�0�\031�c�\011�uRX\034�C��g�\
! -ۍ�.p\016j��\024\015\033��\003\031���qmS>��\037A��Q\005��\013�w����\032�=����\011J\020ۈ\016|�\023T0\
! 6\022\031��<*Қ5\017z\013\013�2���jS�\027��߿Y�\034���\014��%��͑�����k0�b��<<7�U_\
! ����w�}|�:\003믏`���\013n�b-\005��I\010���Ќ��\021�\035`�\004�X]��P1p�U����e:�\
! <�T6�\031K؎�\010�����\000���Z\015m��7�U����-�@���xJ��^\0260%tC:<�{\031�4�a\000�\
! ��^�\037��mg��]=\007wxf�\000z�#춹yē\0074���'�ʵ��K�P�\036����V�ّ�EnFh:5\030\
! ��g�\007T_S�+�H��Q\010�ͫ\"'\011����\030�\004 1ZR\\F�LyV\020W�!/�ujW����4�6�q\022\
! 6���x�\022\000j���L��3��)��\014�[e�ߍ$A���?gt\020\"(}٬UT�X��\022P0:J0��R��\
! [\003E$\012�\"73\025�_dj\003��L�ȧ>�(¾����ι���{m,}�}�\006\017��\007D\003w�5u魿���N\
! j�=�L�����Ye���\003�>�='�Z��n��\003\004�s�\007'�\031\035�$�\005BTO=v�.2q���b�2\021�G\
! ��P\035�\037�]D�@.�_�ȶ�vP5צ�������\010�ͳ���B:I��O\020��Q{\027��\002 L�Ws�g\
! ���>����%�r�8���t������q�WYc�{�'�-�\012�)UEdh\017\\���Q'N�\010\002%xW�\"�\
! �\034U�\026f�X�s`\0048@�jW��,�-T��~NNϞ��פ��SZW�޼}�\014��L��\\B.�Յ�ڥ\
! .�\021�.�\031��s,d�:�6�`[s/\030\015���?<3��\004\027kŷ\"�����[��\"\035U��z�(\036{,c�!�\
! $fL�ҠK\034��sP�?�t�\007�\036l�́�\021���\002��N��dձߡ{լ>�\"\0323��Xw��\036�'\
! ���\"n����|�b'D�+s�\007��[�i��\023Pg�\003&�\000�{~�\006��(����6o��M\002����~�\
! �\037��{��ӑ�F\020\023\033�^\034�_��G�\010�\003P{F��J�~�|��:;�.&\010��:Z����ܠV��\
! Υ>O_��Z6\026U\001 PY�\012�H��\027P6�l���&�r��\003��!��\"��\030TN\036X@����\"��\012��\
! ���kݾ�wË5zg?\030���aj^5\014�\005�]��\032������WN��3ޞ3�٭;\012b\003\030�I�D2�4�\
! �#[��*FK�+F#>\027�\027|�\017{I�{/`vٜg\007J7�{����w��vh7�N�ˀy�{p��1O�&�\
! oOF��\026Q\012������k��\022�h�����h-\012��5\014b����,X��\027�������k��\023����\
! \003�\023p��Nio��M����S��.~Uc��������T��h\030|o\026��T`u�ߛ���c���\013t봭\
! [��\032~H�Z\033}Qf\031�E\005�rܳ4KfT�T��\035��\030�ԮO\023%�\020�h�\017+���r�k����\033��\024T\
! ���+=}�*\002_��8�qz�o_y�<l��4�\017Ϛ\0305�?\016xΗ�}~���\011sm�\"V���]&q2\032��\
! �V1���\005A��!��*\"N\"���^�R���}�B\\cq�H��?\012���\025]�\002�Q��\000K�иC,9\001�\016\
! b���Kl�j�x������`�﫭�\"T��/!�W)Z=<<:�3�\010+�?)\025η��{3%�ݍ��\013�\
! ��Z�\002k�6��A�ݼڤ\027�A�F��Ι&N�2�����\010��3#h�\0330��?���\0057�ڗ�\034�\000��\
! \005�T\002��`g#v�f<z3>;e��ѩكA�\0073gQ���p��\014r;�@e���\010>��u�ո��r\033�E\
! �\023����j\014(\027;�\034���\005�a��mJ\022h.�5H����Xn�ܚĪN���\004h�\012��o��_��/EH\
! SM")
  ### end



From timstone4 at users.sourceforge.net  Mon Apr 21 20:35:27 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 21 22:35:30 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.37,1.38
Message-ID: <E197nd1-0004ZO-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv17549

Modified Files:
	Options.py 
Log Message:
Altered (rewrote) is_valid method to correctly handle multiple value options
that are being set to Set or tuple values.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.37
retrieving revision 1.38
diff -C2 -d -r1.37 -r1.38
*** Options.py	21 Apr 2003 22:37:49 -0000	1.37
--- Options.py	22 Apr 2003 02:35:24 -0000	1.38
***************
*** 100,103 ****
--- 100,104 ----
  
  import re
+ import types
  
  # These are handy references to commonly used regex/tuples defining
***************
*** 1119,1156 ****
      def is_valid(self, value):
          '''Check if this is a valid value for this option.'''
!         if self.allowed_values is None:
              return False
!         if type(self.allowed_values) == type((0,1)):
!             if self.multiple and value is None:
                  return True
!             if type(value) == type((0,1)):
!                 if self.multiple:
!                     for v in value:
!                         if not v in self.allowed_values:
!                             return False
!                     return True
                  return False
              else:
!                if value in self.allowed_values:
!                    return True
!                return False
!         elif type(self.allowed_values) == type(""):
              # this is a complete hack - something better needs to
              # be worked out for sets, but I don't have time just now.
!             import types
!             if type(value) == type(Set()):
!                 return True
!             if self.multiple and value == "":
!                 return True
!             vals = self._split_values(value)
!             if len(vals) == 0:
!                 return False
!             elif len(vals) > 1 and not self.multiple:
!                 return False
!             return True
  
      def _split_values(self, value):
          # do the regex mojo here
!         r = re.compile(self.allowed_values)
          s = str(value)
          i = 0
--- 1120,1243 ----
      def is_valid(self, value):
          '''Check if this is a valid value for this option.'''
!         
! # XXX This test is in the original code, but makes no sense....
! #        if self.allowed_values is None:
! #            return False
! 
!         if self.multiple:
!             return self.is_valid_multiple(value)
!         else:
!             return self.is_valid_single(value)
! 
!     def is_valid_multiple(self, value):
! 
!         if value is None or value == "":
!             # always allow a multiple value option to be set to nothing
!             return True
! 
!         tv = type(value)
!         
!         if tv in types.StringTypes:
!             if type(self.allowed_values) in types.StringTypes:
!                 # allowed value is a regex, use it to make value into a tuple
!                 vals = self._split_values(value)
!             else:
!                 # allowed value is a tuple, make vals a tuple
!                 vals = (value,)
!         elif tv == types.TupleType or tv == type(Set()):
!             # value is being passed in as a tuple or a Set.  In this case,
!             # allowed values *must* be a tuple, because a regex can only
!             # execute against a string.  This condition indicates a
!             # programming error.
!             if not type(self.allowed_values) == types.TupleType:
!                 raise TypeError, \
! """Attempt to set multiple value option %s with an allowed_values regex
! to a tuple or Set value.""" % (self.name)
!             else:
!                 vals = values
!         else:
!             # here we're setting a multiple value option to a value
!             # that is contained in other than a string, a tuple, or a set.
!             raise TypeError, \
! """Attempt to set multiple value option %s to a value that is not a string,
! tuple, or Set.""" % (self.name)
!         
!         # at this point, vals is a tuple or a Set.  If length is zero,
!         # then it's likely that the allowed_values regex did not find
!         # any matches.  At any rate, this is not an allowed value, but
!         # it is not an exception.
! 
!         if len(vals) == 0:
              return False
! 
!         if type(self.allowed_values) == types.TupleType:
!             # if self.allowed_values is not a tuple, then it is
!             # a regex, and if there are no matches, the length
!             # check above will catch the error
!             for v in vals:
!                 if not v in self.allowed_values:
!                     return False
!             # here, all elements of the vals tuple are in allowed_values
!             return True
! 
!         # if we've made it this far, then the allowed_values is a regex
!         # that matched value at least once
!         return True
! 
! 
!     def is_valid_single(self, value):
!         if type(self.allowed_values) == types.TupleType:
!             if value in self.allowed_values:
                  return True
!             else:
                  return False
+         else:
+             avals = self._split_values(value)
+             # in this case, allowed_values must be a regex, and
+             # _split_values must match once and only once
+             if len(avals) == 1:
+                 return True
              else:
!                 # either no match or too many matches
!                 return False
!             
! # ****** replaced code, temporarily retained for reference
! #        if type(self.allowed_values) == type((0,1)):
! #            if self.multiple and value is None:
! #                return True
! #            if type(value) == type((0,1)):
! #                if self.multiple:
! #                    for v in value:
! #                        if not v in self.allowed_values:
! #                            return False
! #                    return True
! #                return False
! #            else:
! #               if value in self.allowed_values:
! #                   return True
! #               return False
!             
! #        elif type(self.allowed_values) == type(""):
              # this is a complete hack - something better needs to
              # be worked out for sets, but I don't have time just now.
! #            import types
! #            if type(value) == type(Set()):
! #                return True
! #            if self.multiple and value == "":
! #                return True
! #            vals = self._split_values(value)
! #            if len(vals) == 0:
! #                return False
! #            elif len(vals) > 1 and not self.multiple:
! #                return False
! #            return True
  
      def _split_values(self, value):
          # do the regex mojo here
!         try:
!             r = re.compile(self.allowed_values)
!         except:
!             print self.allowed_values
!             raise
          s = str(value)
          i = 0



From anadelonbrin at users.sourceforge.net  Tue Apr 22 01:12:26 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Tue Apr 22 08:16:17 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.38,1.39
Message-ID: <E197rx4-00049M-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv15891/spambayes

Modified Files:
	Options.py 
Log Message:
Tim's code is much nicer, but still doesn't work 100% with sets.  So once again for us Outlook people we check in a temporary fix.
(We are working on something more permanent, honest!).

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.38
retrieving revision 1.39
diff -C2 -d -r1.38 -r1.39
*** Options.py	22 Apr 2003 02:35:24 -0000	1.38
--- Options.py	22 Apr 2003 07:12:23 -0000	1.39
***************
*** 1131,1142 ****
  
      def is_valid_multiple(self, value):
! 
!         if value is None or value == "":
              # always allow a multiple value option to be set to nothing
              return True
- 
-         tv = type(value)
          
          if tv in types.StringTypes:
              if type(self.allowed_values) in types.StringTypes:
                  # allowed value is a regex, use it to make value into a tuple
--- 1131,1144 ----
  
      def is_valid_multiple(self, value):
!         if value is None:
              # always allow a multiple value option to be set to nothing
              return True
          
+         tv = type(value)
          if tv in types.StringTypes:
+             if value == "":
+                 # always allow a multiple value option to be set to ""
+                 return True
+ 
              if type(self.allowed_values) in types.StringTypes:
                  # allowed value is a regex, use it to make value into a tuple
***************
*** 1147,1153 ****
          elif tv == types.TupleType or tv == type(Set()):
              # value is being passed in as a tuple or a Set.  In this case,
!             # allowed values *must* be a tuple, because a regex can only
!             # execute against a string.  This condition indicates a
!             # programming error.
              if not type(self.allowed_values) == types.TupleType:
                  raise TypeError, \
--- 1149,1162 ----
          elif tv == types.TupleType or tv == type(Set()):
              # value is being passed in as a tuple or a Set.  In this case,
!             # allowed values *must* be a tuple, because a regex
!             # can only execute against a string.  This condition indicates
!             # a programming error.
!             # XXX This is not true, sadly.  For example the safe_headers
!             # XXX options (in Tokenizer) is a set, but has a regex that
!             # XXX describes the individual (string) elements of the set
!             # XXX This whole things needs work, so for the moment, fake
!             # XXX it.
!             if tv == type(Set()):
!                 return True
              if not type(self.allowed_values) == types.TupleType:
                  raise TypeError, \
***************
*** 1167,1171 ****
          # any matches.  At any rate, this is not an allowed value, but
          # it is not an exception.
! 
          if len(vals) == 0:
              return False
--- 1176,1180 ----
          # any matches.  At any rate, this is not an allowed value, but
          # it is not an exception.
!         # XXX This is not true, as a Set can be empty...
          if len(vals) == 0:
              return False



From timstone4 at users.sourceforge.net  Tue Apr 22 07:14:23 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Tue Apr 22 09:14:27 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.29,1.30
Message-ID: <E197xbL-0004xD-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv19013

Modified Files:
	imapfilter.py 
Log Message:
Added more output for verbose in training, corrected a counting error for
number of msgs trained.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.29
retrieving revision 1.30
diff -C2 -d -r1.29 -r1.30
*** imapfilter.py	20 Apr 2003 09:41:15 -0000	1.29
--- imapfilter.py	22 Apr 2003 13:14:20 -0000	1.30
***************
*** 371,374 ****
--- 371,377 ----
          if options["globals", "verbose"]:
              t = time.time()
+             
+         total_ham_trained = 0
+         total_spam_trained = 0
  
          if options["imap", "ham_train_folders"] != "":
***************
*** 376,381 ****
--- 379,389 ----
                                   options["imap", "ham_train_folders"].split()
              for fol in ham_training_folders:
+                 if options['globals', 'verbose']:
+                     print "   Training ham folder %s" % (fol)
                  folder = IMAPFolder(fol)
                  num_ham_trained = folder.Train(self.classifier, False)
+                 total_ham_trained += num_ham_trained
+                 if options['globals', 'verbose']:
+                     print "       %s trained." % (num_ham_trained)
  
          if options["imap", "spam_train_folders"] != "":
***************
*** 383,395 ****
                                    options["imap", "spam_train_folders"].split()
              for fol in spam_training_folders:
                  folder = IMAPFolder(fol)
                  num_spam_trained = folder.Train(self.classifier, True)
  
!         if num_ham_trained or num_spam_trained:
              self.classifier.store()
          
          if options["globals", "verbose"]:
              print "Training took %s seconds, %s messages were trained" \
!                   % (time.time() - t, num_ham_trained + num_spam_trained)
  
      def Filter(self):
--- 391,408 ----
                                    options["imap", "spam_train_folders"].split()
              for fol in spam_training_folders:
+                 if options['globals', 'verbose']:
+                     print "   Training spam folder %s" % (fol)
                  folder = IMAPFolder(fol)
                  num_spam_trained = folder.Train(self.classifier, True)
+                 total_spam_trained += num_spam_trained
+                 if options['globals', 'verbose']:
+                     print "       %s trained." % (num_spam_trained)
  
!         if total_ham_trained or total_spam_trained:
              self.classifier.store()
          
          if options["globals", "verbose"]:
              print "Training took %s seconds, %s messages were trained" \
!                   % (time.time() - t, total_ham_trained + total_spam_trained)
  
      def Filter(self):



From montanaro at users.sourceforge.net  Tue Apr 22 09:08:00 2003
From: montanaro at users.sourceforge.net (Skip Montanaro)
Date: Tue Apr 22 11:08:03 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.16,1.17
Message-ID: <E197zNI-0001v0-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv7327

Modified Files:
	message.py 
Log Message:
triple-" makes python-mode happier


Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.16
retrieving revision 1.17
diff -C2 -d -r1.16 -r1.17
*** message.py	21 Apr 2003 21:16:35 -0000	1.16
--- message.py	22 Apr 2003 15:07:55 -0000	1.17
***************
*** 1,5 ****
  #! /usr/bin/env python
  
! '''message.py - Core Spambayes classes.
  
  Classes:
--- 1,5 ----
  #! /usr/bin/env python
  
! """message.py - Core Spambayes classes.
  
  Classes:
***************
*** 67,71 ****
      o Suggestions?
  
!     '''
  
  # This module is part of the spambayes project, which is Copyright 2002
--- 67,71 ----
      o Suggestions?
  
!     """
  
  # This module is part of the spambayes project, which is Copyright 2002



From timstone4 at users.sourceforge.net  Tue Apr 22 12:59:51 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Tue Apr 22 14:59:55 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.17,1.18
Message-ID: <E1982zf-0004Gm-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv16379

Modified Files:
	message.py 
Log Message:
Compiled the crlf regex, and added a couple comments

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.17
retrieving revision 1.18
diff -C2 -d -r1.17 -r1.18
*** message.py	22 Apr 2003 15:07:55 -0000	1.17
--- message.py	22 Apr 2003 18:59:48 -0000	1.18
***************
*** 64,68 ****
  
  To Do:
!     o Master DB module
      o Suggestions?
  
--- 64,70 ----
  
  To Do:
!     o Master DB module, or at least make the msginfodb name an options parm
!     o Figure out how to safely add message id to body (or if it can be done
!       at all...)
      o Suggestions?
  
***************
*** 101,104 ****
--- 103,107 ----
  import shelve
  
+ CRLFRE = re.compile(r'\r\n|\r|\n')
  
  class MessageInfoDB:
***************
*** 174,178 ****
          """Make sure data uses CRLF for line termination.
          """
!         return re.sub(r'\r\n|\r|\n', '\r\n', data)
  
      def as_string(self):
--- 177,181 ----
          """Make sure data uses CRLF for line termination.
          """
!         return CRLFRE.sub('\r\n', data)
  
      def as_string(self):



From skip at pobox.com  Tue Apr 22 15:20:11 2003
From: skip at pobox.com (Skip Montanaro)
Date: Tue Apr 22 15:20:30 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.17,1.18
In-Reply-To: <E1982zf-0004Gm-00@sc8-pr-cvs1.sourceforge.net>
References: <E1982zf-0004Gm-00@sc8-pr-cvs1.sourceforge.net>
Message-ID: <16037.38379.566210.678501@montanaro.dyndns.org>


    Tim> Compiled the crlf regex, and added a couple comments

Tim,

I doubt compiling the regex helps.  Running timeit.py suggests this is the
case:

    % timeit.py -s "data = 'line 0\r\nline 1\nline 2\rline 3\r\r\nline 4\n' ; import re ; CRLF='\r\n'" "re.sub(r'\r\n|\n|\r', CRLF, data)"
    10000 loops, best of 3: 38.4 usec per loop
    % timeit.py -s "data = 'line 0\r\nline 1\nline 2\rline 3\r\r\nline 4\n' ; import re ; CRLF='\r\n' ; CRLFRE = re.compile(r'\r\n|\n|\r')" "re.sub(CRLFRE, CRLF, data)"
    10000 loops, best of 3: 38.5 usec per loop

I ran both several times.  The above times are the best I came up with.

In fact, looking at the code for sre.sub and sre._compile suggests that
using strings should be slightly faster than using compiled regular
expressions, because strings are cached with their compiled re's, whereas
compiled re's aren't.

Skip

From tim at fourstonesExpressions.com  Tue Apr 22 15:45:30 2003
From: tim at fourstonesExpressions.com (Tim Stone - Four Stones Expressions)
Date: Tue Apr 22 15:45:41 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.17,1.18
In-Reply-To: <16037.38379.566210.678501@montanaro.dyndns.org>
Message-ID: <KG85475QNJFXVB0NJNHB8YVWS716384.3ea59bda@myst>

Interesting... my little test, which didn't use timeit, showed a 20%-30% 
improvement... we can revert the change if you think it's not worth it.

4/22/2003 2:20:11 PM, Skip Montanaro <skip@pobox.com> wrote:

>
>    Tim> Compiled the crlf regex, and added a couple comments
>
>Tim,
>
>I doubt compiling the regex helps.  Running timeit.py suggests this is the
>case:
>
>    % timeit.py -s "data = 'line 0\r\nline 1\nline 2\rline 3\r\r\nline 4\n' ; 
import re ; CRLF='\r\n'" "re.sub(r'\r\n|\n|\r', CRLF, data)"
>    10000 loops, best of 3: 38.4 usec per loop
>    % timeit.py -s "data = 'line 0\r\nline 1\nline 2\rline 3\r\r\nline 4\n' ; 
import re ; CRLF='\r\n' ; CRLFRE = re.compile(r'\r\n|\n|\r')" "re.sub(CRLFRE, 
CRLF, data)"
>    10000 loops, best of 3: 38.5 usec per loop
>
>I ran both several times.  The above times are the best I came up with.
>
>In fact, looking at the code for sre.sub and sre._compile suggests that
>using strings should be slightly faster than using compiled regular
>expressions, because strings are cached with their compiled re's, whereas
>compiled re's aren't.
>
>Skip
>
>


c'est moi - TimS
http://www.fourstonesExpressions.com
http://wecanstopspam.org

There are 10 kinds of people in the world:
  those who understand binary,
  and those who don't.



From skip at pobox.com  Tue Apr 22 16:10:34 2003
From: skip at pobox.com (Skip Montanaro)
Date: Tue Apr 22 16:27:52 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.17,1.18
In-Reply-To: <KG85475QNJFXVB0NJNHB8YVWS716384.3ea59bda@myst>
References: <16037.38379.566210.678501@montanaro.dyndns.org>
	<KG85475QNJFXVB0NJNHB8YVWS716384.3ea59bda@myst>
Message-ID: <16037.41402.336849.375188@montanaro.dyndns.org>


    Tim> Interesting... my little test, which didn't use timeit, showed a
    Tim> 20%-30% improvement... we can revert the change if you think it's
    Tim> not worth it.

It's okay to leave it in.

Skip

From anadelonbrin at users.sourceforge.net  Tue Apr 22 16:19:51 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Tue Apr 22 18:20:19 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.39,1.40
Message-ID: <E19867D-0003Ct-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv12253/spambayes

Modified Files:
	Options.py 
Log Message:
Fix for SF[ 725616 ] provided by Sjoerd Mullender.

(Didn't escape - in three regexs).  Who knows why this
sometimes worked...

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.39
retrieving revision 1.40
diff -C2 -d -r1.39 -r1.40
*** Options.py	22 Apr 2003 07:12:23 -0000	1.39
--- Options.py	22 Apr 2003 22:19:48 -0000	1.40
***************
*** 11,15 ****
  BAYESCUSTOMIZE is checked for a list of names, if nothing is found
  then the local directory and the home directory are checked for a
! file caleld bayescustomize.ini and the initial values are loaded from
  this.
  
--- 11,15 ----
  BAYESCUSTOMIZE is checked for a list of names, if nothing is found
  then the local directory and the home directory are checked for a
! file called bayescustomize.ini and the initial values are loaded from
  this.
  
***************
*** 105,110 ****
  # permitted values. Although the majority of options use one of these,
  # you may use any regex or tuple you wish.
! HEADER_NAME = r"[\w\.-\*]+"
! HEADER_VALUE = r"[\w\.-\*]+"
  INTEGER = r"[\d]+"              # actually, a *positive* integer
  REAL = r"[\d]+[\.]?[\d]*"       # likewise, a *positive* real
--- 105,110 ----
  # permitted values. Although the majority of options use one of these,
  # you may use any regex or tuple you wish.
! HEADER_NAME = r"[\w\.\-\*]+"
! HEADER_VALUE = r"[\w\.\-\*]+"
  INTEGER = r"[\d]+"              # actually, a *positive* integer
  REAL = r"[\d]+[\.]?[\d]*"       # likewise, a *positive* real
***************
*** 113,117 ****
  PORT = r"[\d]+"
  EMAIL_ADDRESS = r"[\w\-\.]+@[\w\-\.]+"
! PATH = r"[\w\.-~:\\/\*]+"
  VARIABLE_PATH = PATH + r"%"
  FILE = r"[\S]+"
--- 113,117 ----
  PORT = r"[\d]+"
  EMAIL_ADDRESS = r"[\w\-\.]+@[\w\-\.]+"
! PATH = r"[\w\.\-~:\\/\*]+"
  VARIABLE_PATH = PATH + r"%"
  FILE = r"[\S]+"



From anadelonbrin at users.sourceforge.net  Tue Apr 22 16:47:16 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Tue Apr 22 18:47:20 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.30,1.31
Message-ID: <E1986Xk-0005xV-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv22874

Modified Files:
	imapfilter.py 
Log Message:
Made the processing of the fetch response in keys()
more robust.  It should now handle the response in any
(valid) order.  Works for me, but the old one did too :)
Testers take your places... :)

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.30
retrieving revision 1.31
diff -C2 -d -r1.30 -r1.31
*** imapfilter.py	22 Apr 2003 13:14:20 -0000	1.30
--- imapfilter.py	22 Apr 2003 22:47:13 -0000	1.31
***************
*** 295,305 ****
          r = re.compile(r"[0-9]+ \(UID ([0-9]+) FLAGS \(([\\\w]*)\)\)")
          uids = []
!         for i in response[1]:
!             mo = r.match(i)
!             if mo is not None:
!                 # We are not interested in messages marked as deleted
!                 if mo.group(2).lower() != "\\deleted":
!                     uids.append(mo.group(1))
          return uids
  
      def __getitem__(self, key):
--- 295,324 ----
          r = re.compile(r"[0-9]+ \(UID ([0-9]+) FLAGS \(([\\\w]*)\)\)")
          uids = []
!         for resp in response[1]:
!             data = self._extract_fetch_data(resp)
!             if data.has_key("FLAGS"):
!                 if data["FLAGS"].lower().find("\\deleted") == -1:
!                     # We are interested in messages not marked as deleted
!                     uids.append(data["UID"])
!             else:
!                 uids.append(data["UID"])
          return uids
+ 
+     def _extract_fetch_data(self, response):
+         '''Extract data from the response given to an IMAP FETCH command.'''
+         data = {}
+         # the first item will always be the message number
+         mo = re.match(r"([0-9]+) \(?([\w\\\(\) ]*)\)?", response)
+         if mo is None:
+             print """IMAP server gave strange fetch response.  Please
+             report this as a bug."""
+         else:
+             data["message_number"] = mo.group(1)
+             response = mo.group(2)
+         mo = re.findall(r"([\w]+) \(?([\w\\]+)\)?", response)
+         for key, val in mo:
+             data[key] = val
+         return data
+         
  
      def __getitem__(self, key):



From anadelonbrin at users.sourceforge.net  Thu Apr 24 01:43:55 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 24 03:44:00 2003
Subject: [Spambayes-checkins] spambayes/spambayes ImapUI.py, 1.6,
	1.7 Options.py, 1.40, 1.41 ProxyUI.py, 1.3,
	1.4 UserInterface.py, 1.5, 1.6 message.py, 1.18,
	1.19 tokenizer.py, 1.8, 1.9
Message-ID: <E198bOd-0000JE-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv1065/spambayes

Modified Files:
	ImapUI.py Options.py ProxyUI.py UserInterface.py message.py 
	tokenizer.py 
Log Message:
Fix for:
[ 725307 ] Outlook plugin won't load (anymore)
[ 725466 ] Include a proper locale fix in Options.py
[ 726255 ] Problem if bayescustomize.ini not there

Moved the line endings fix from message.py to imapmessage,
which is more appropriate.

Removed all reliance on UpdateableConfigParser from Options.

Removed the ConfigParser object from Options.

Removed the all_options dict from Options.

Changed multiple options to tuples (this required one very small
change in tokenizer).

Fixed the user interface for these changes, and for Tim's
change from True/False to Yes/No.

Removed some debugging statements that had been committed
by mistake at some point.

Fixed a potential problem with the imap ui trying to display a folder
list before a server/username had been entered.

Index: ImapUI.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/ImapUI.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** ImapUI.py	20 Apr 2003 09:41:15 -0000	1.6
--- ImapUI.py	24 Apr 2003 07:43:46 -0000	1.7
***************
*** 93,102 ****
  class IMAPUserInterface(UserInterface.UserInterface):
      """Serves the HTML user interface for the proxies."""
! 
!     def __init__(self, cls, imap):
          global classifier
          UserInterface.UserInterface.__init__(self, cls, parm_map)
          classifier = cls
          self.imap = imap
  
      def onHome(self):
--- 93,103 ----
  class IMAPUserInterface(UserInterface.UserInterface):
      """Serves the HTML user interface for the proxies."""
!     def __init__(self, cls, imap, pwd):
          global classifier
          UserInterface.UserInterface.__init__(self, cls, parm_map)
          classifier = cls
          self.imap = imap
+         self.imap_pwd = pwd
+         self.imap_logged_in = False
  
      def onHome(self):
***************
*** 107,113 ****
          del statusTable.proxyDetails
          # This could be a bit more modular
!         statusTable.configurationLink += """You can also <a href=
!         'filterfolders'>configure folders to filter</a> and <a href=
!         'trainingfolders'>Configure folders to train</a>"""
          content = (self._buildBox('Status and Configuration',
                                    'status.gif', statusTable % stateDict)+
--- 108,115 ----
          del statusTable.proxyDetails
          # This could be a bit more modular
!         statusTable.configurationLink += """<br />&nbsp;&nbsp;&nbsp;&nbsp;
!         &nbsp;You can also <a href='filterfolders'>configure folders to
!         filter</a><br />and <a
!         href='trainingfolders'>Configure folders to train</a>"""
          content = (self._buildBox('Status and Configuration',
                                    'status.gif', statusTable % stateDict)+
***************
*** 133,140 ****
  
      def onSave(self, how):
!         self.imap.logout(False) # never expunge from the web ui
          UserInterface.UserInterface.onSave(self, how)
  
      def onFilterfolders(self):
          available_folders = self._folder_list()
          content = self.html.configForm.clone()
--- 135,145 ----
  
      def onSave(self, how):
!         if self.imap is not None:
!             self.imap.logout()
          UserInterface.UserInterface.onSave(self, how)
  
      def onFilterfolders(self):
+         self._writePreamble("Select Filter Folders")
+         self._login_to_imap()
          available_folders = self._folder_list()
          content = self.html.configForm.clone()
***************
*** 150,158 ****
              content.configFormContent += folderBox
  
-         self._writePreamble("Select Filter Folders")
          self.write(content)
          self._writePostamble()
  
      def onTrainingfolders(self):
          available_folders = self._folder_list()
          content = self.html.configForm.clone()
--- 155,194 ----
              content.configFormContent += folderBox
  
          self.write(content)
          self._writePostamble()
  
+     def _login_to_imap(self):
+         if self.imap_logged_in:
+             return
+         if self.imap is None:
+             server = options["imap", "server"][0]
+             if server.find(':') > -1:
+                 server, port = server.split(':', 1)
+                 port = int(port)
+             else:
+                 if options["imap", "use_ssl"]:
+                     port = 993
+                 else:
+                     port = 143
+             imap = IMAPSession(server, port)
+         if self.imap is None:
+             content = self._buildBox("Error", None,
+                                      """Must specify server details first.""")
+             self.write(content)
+             self._writePostamble()
+             return
+         username = options["imap", "username"][0]
+         if username == "":
+             content = self._buildBox("Error", None,
+                                      """Must specify username first.""")
+             self.write(content)
+             self._writePostamble()
+             return
+         self.imap.login(username, self.imap_pwd)
+         self.imap_logged_in = True
+ 
      def onTrainingfolders(self):
+         self._writePreamble("Select Training Folders")
+         self._login_to_imap()
          available_folders = self._folder_list()
          content = self.html.configForm.clone()
***************
*** 168,172 ****
              content.configFormContent += folderBox
  
-         self._writePreamble("Select Training Folders")
          self.write(content)
          self._writePostamble()
--- 204,207 ----
***************
*** 174,178 ****
      def onChangeopts(self, **parms):
          backup = self.parm_ini_map
-         print parms
          if parms["how"] == "Save Training Folders" or \
             parms["how"] == "Save Filter Folders":
--- 209,212 ----
***************
*** 192,197 ****
                  else:
                      parms[key] = value
-         print self.parm_ini_map
-         print parms
          UserInterface.UserInterface.onChangeopts(self, **parms)
          self.parm_ini_map = backup
--- 226,229 ----
***************
*** 200,203 ****
--- 232,236 ----
          folderTable = self.html.configTable.clone()
          del folderTable.configTextRow1
+         del folderTable.configTextRow2
          del folderTable.configCbRow1
          del folderTable.configRow2
***************
*** 216,225 ****
              folderRow.folderName = folder
              if options.multiple_values_allowed(section, option):
                  folderRow.folderBox.name += folder
              else:
                  folderRow.folderBox.type = "radio"
-             current_options = ',' + options[section, option] + ','
-             if current_options.find(',' + folder + ',') != -1:
-                 folderRow.folderBox.checked = "checked"
              folderTable += folderRow
          return self._buildBox(options.display_name(section, option),
--- 249,259 ----
              folderRow.folderName = folder
              if options.multiple_values_allowed(section, option):
+                 if folder in options[section, option]:
+                     folderRow.folderBox.checked = "checked"
                  folderRow.folderBox.name += folder
              else:
+                 if folder == options[section, option]:
+                     folderRow.folderBox.checked = "checked"
                  folderRow.folderBox.type = "radio"
              folderTable += folderRow
          return self._buildBox(options.display_name(section, option),
***************
*** 238,241 ****
--- 272,278 ----
              m = r.search(fol)
              name_attributes = fol[:m.end()-1]
+             # IMAP is a truly odd protocol.  The delimiter is
+             # only the delimiter for this particular folder - each
+             # folder *may* have a different delimiter
              self.folder_delimiter = fol[m.end()+1:m.end()+2]
              # a bit of a hack, but we really need to know if this is

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.40
retrieving revision 1.41
diff -C2 -d -r1.40 -r1.41
*** Options.py	22 Apr 2003 22:19:48 -0000	1.40
--- Options.py	24 Apr 2003 07:43:46 -0000	1.41
***************
*** 11,16 ****
  BAYESCUSTOMIZE is checked for a list of names, if nothing is found
  then the local directory and the home directory are checked for a
! file called bayescustomize.ini and the initial values are loaded from
! this.
  
  The Option class holds information about an option - the name of the
--- 11,16 ----
  BAYESCUSTOMIZE is checked for a list of names, if nothing is found
  then the local directory and the home directory are checked for a
! file called bayescustomize.ini or .spambayesrc (respectively) and
[...2134 lines suppressed...]
  else:
--- 1430,1434 ----
  if alternate:
      filenames = alternate.split(os.pathsep)
!     options.merge_files(filenames)
      optionsPathname = os.path.abspath(filenames[-1])
  else:
***************
*** 1522,1526 ****
              alts.append(epath)
      if alts:
!         options.mergefiles(alts)
          optionsPathname = os.path.abspath(alts[-1])
  
--- 1439,1443 ----
              alts.append(epath)
      if alts:
!         options.merge_files(alts)
          optionsPathname = os.path.abspath(alts[-1])
  

Index: ProxyUI.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/ProxyUI.py,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** ProxyUI.py	20 Apr 2003 09:41:15 -0000	1.3
--- ProxyUI.py	24 Apr 2003 07:43:47 -0000	1.4
***************
*** 39,42 ****
--- 39,44 ----
   o Can it cleanly dynamically update its status display while having a POP3
     conversation?  Hammering reload sucks.
+  o Have both the trained evidence (if present) and current evidence on the
+    show clues page.
  
   o Suggestions?
***************
*** 469,474 ****
          
          # check for equal number of pop3servers and ports
!         slist = parms['pop3proxy_servers'].split(',')
!         plist = parms['pop3proxy_ports'].split(',')
          if len(slist) != len(plist):
              errmsg += '<li>The number of POP3 proxy ports specified ' + \
--- 471,476 ----
          
          # check for equal number of pop3servers and ports
!         slist = list(parms['pop3proxy_servers'])
!         plist = list(parms['pop3proxy_ports'])
          if len(slist) != len(plist):
              errmsg += '<li>The number of POP3 proxy ports specified ' + \
***************
*** 486,491 ****
  
          # check for equal number of smtpservers and ports
!         slist = parms['smtpproxy_servers'].split(',')
!         plist = parms['smtpproxy_ports'].split(',')
          if len(slist) != len(plist):
              errmsg += '<li>The number of SMTP proxy ports specified ' + \
--- 488,493 ----
  
          # check for equal number of smtpservers and ports
!         slist = list(parms['smtpproxy_servers'])
!         plist = list(parms['smtpproxy_ports'])
          if len(slist) != len(plist):
              errmsg += '<li>The number of SMTP proxy ports specified ' + \

Index: UserInterface.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/UserInterface.py,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** UserInterface.py	22 Apr 2003 02:25:03 -0000	1.5
--- UserInterface.py	24 Apr 2003 07:43:48 -0000	1.6
***************
*** 410,419 ****
  
              # Populate the rows with the details and add them to the table.
!             if type(options.valid_input(sect, opt)) == type(""):
                  # we provide a text input
                  newConfigRow1 = configTextRow1.clone()
                  newConfigRow1.label = options.display_name(sect, opt)
                  newConfigRow1.input.name = html_key
!                 newConfigRow1.input.value = options.get(sect, opt)
              else:
                  # we provide checkboxes/radio buttons
--- 410,419 ----
  
              # Populate the rows with the details and add them to the table.
!             if type(options.valid_input(sect, opt)) in types.StringTypes:
                  # we provide a text input
                  newConfigRow1 = configTextRow1.clone()
                  newConfigRow1.label = options.display_name(sect, opt)
                  newConfigRow1.input.name = html_key
!                 newConfigRow1.input.value = options.unconvert(sect, opt)
              else:
                  # we provide checkboxes/radio buttons
***************
*** 425,444 ****
                  for val in options.valid_input(sect, opt):
                      newOption = blankOption.clone()
-                     if str(val) in str(options[sect, opt]).split():
-                         newOption.input_box.checked = "checked" 
-                     # help for Python 2.2
-                     if options.is_boolean(sect, opt):
-                         if str(val) == "0":
-                             val = "No"
-                         elif str(val) == "1":
-                             val = "Yes"
-                     newOption.val_label = str(val)
                      if options.multiple_values_allowed(sect, opt):
                          newOption.input_box.type = "checkbox"
                          newOption.input_box.name = html_key + '-' + str(i)
                          i += 1
                      else:
                          newOption.input_box.type = "radio"
                          newOption.input_box.name = html_key
                      newOption.input_box.value = str(val)
                      if firstOpt: 
--- 425,446 ----
                  for val in options.valid_input(sect, opt):
                      newOption = blankOption.clone()
                      if options.multiple_values_allowed(sect, opt):
+                         if val in options[sect, opt]:
+                             newOption.input_box.checked = "checked" 
                          newOption.input_box.type = "checkbox"
                          newOption.input_box.name = html_key + '-' + str(i)
                          i += 1
                      else:
+                         if val == options[sect, opt]:
+                             newOption.input_box.checked = "checked"
                          newOption.input_box.type = "radio"
                          newOption.input_box.name = html_key
+                     # Tim thinks that Yes/No makes more sense than True/False
+                     if options.is_boolean(sect, opt):
+                         if val == False:
+                             val = "No"
+                         elif val == True:
+                             val = "Yes"
+                     newOption.val_label = str(val)
                      newOption.input_box.value = str(val)
                      if firstOpt: 
***************
*** 456,471 ****
              currentValue = options[sect, opt]
   
!             if type(currentValue) in types.StringTypes and \
!                 str(currentValue) not in (0,1):
                  currentValue = currentValue.replace(',', ', ')
                  newConfigRow2 = configTextRow2.clone()
              else:
                  newConfigRow2 = configRow2.clone()
              
!             # for Python 2.2
              if options.is_boolean(sect, opt):
!                 if str(currentValue) == '0':
                      currentValue = "No"
!                 elif str(currentValue) == '1':
                      currentValue = "Yes"
              # XXX Something needs to be done here, otherwise really
--- 458,473 ----
              currentValue = options[sect, opt]
   
!             if type(currentValue) in types.StringTypes:
                  currentValue = currentValue.replace(',', ', ')
                  newConfigRow2 = configTextRow2.clone()
              else:
+                 currentValue = options.unconvert(sect, opt)
                  newConfigRow2 = configRow2.clone()
              
!             # Tim thinks that Yes/No makes more sense than True/False
              if options.is_boolean(sect, opt):
!                 if currentValue == "False":
                      currentValue = "No"
!                 elif currentValue == "True":
                      currentValue = "Yes"
              # XXX Something needs to be done here, otherwise really
***************
*** 495,498 ****
--- 497,501 ----
          html.mainContent = self.html.headedBox.clone()
          errmsg = self.verifyInput(parms)
+ 
          if errmsg != '':
              html.mainContent.heading = "Errors Detected"
***************
*** 509,515 ****
                  options.set(sect, opt, value)
  
!         op = open(optionsPathname, "r")
!         options.update_file(op)
!         op.close()
          self.reReadOptions()
  
--- 512,516 ----
                  options.set(sect, opt, value)
  
!         options.update_file(optionsPathname)
          self.reReadOptions()
  
***************
*** 561,578 ****
              if not parms.has_key(html_key):
                  # This is a set of checkboxes where none are selected
!                 value = None
              else:
                  value = parms[html_key]
!             if value is not None:
!                 if type(value) == type((0,1)):
!                     value_string = ""
!                     for val in value:
!                         value_string += val
!                         value_string += ','
!                     value = value_string[:-1]   # remove trailing comma
                  value = options.convert(sect, opt, value)
              if not options.is_valid(sect, opt, value):
                  errmsg += '<li>\'%s\' is not a value valid for [%s] %s' % \
!                           (value, nice_section_name,
                             options.display_name(sect, opt))
                  if type(options.valid_input(sect, opt)) == type((0,1)):
--- 562,586 ----
              if not parms.has_key(html_key):
                  # This is a set of checkboxes where none are selected
!                 value = ()
!                 entered_value = "None"
              else:
                  value = parms[html_key]
!                 entered_value = value
!                 # Tim thinks that Yes/No makes more sense than True/False
!                 if options.is_boolean(sect, opt):
!                     if value == "No":
!                         value = False
!                     elif value == "Yes":
!                         value = True
!                 if options.multiple_values_allowed(sect, opt):
!                     if value == "":
!                         value = ()
!                     else:
!                         if type(value) != types.TupleType:
!                             value = (value,)
                  value = options.convert(sect, opt, value)
              if not options.is_valid(sect, opt, value):
                  errmsg += '<li>\'%s\' is not a value valid for [%s] %s' % \
!                           (entered_value, nice_section_name,
                             options.display_name(sect, opt))
                  if type(options.valid_input(sect, opt)) == type((0,1)):

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.18
retrieving revision 1.19
diff -C2 -d -r1.18 -r1.19
*** message.py	22 Apr 2003 18:59:48 -0000	1.18
--- message.py	24 Apr 2003 07:43:49 -0000	1.19
***************
*** 103,108 ****
  import shelve
  
- CRLFRE = re.compile(r'\r\n|\r|\n')
- 
  class MessageInfoDB:
      def __init__(self, db_name, mode='c'):
--- 103,106 ----
***************
*** 174,192 ****
          return tokenize(self.as_string())
  
-     def _force_CRLF(self, data):
-         """Make sure data uses CRLF for line termination.
-         """
-         return CRLFRE.sub('\r\n', data)
- 
-     def as_string(self):
-         # The email package stores line endings in the "internal" Python
-         # format ('\n').  According to that package, it is up to the
-         # server of that information to convert to appropriate line
-         # endings (according to RFC822, that is \r\n *only*).
-         # We, however, always want to return correct endings from
-         # as_string(), so we make the change here, rather than having
-         # the same code in imapfilter, pop3proxy, and so on.
-         return self._force_CRLF(email.Message.Message.as_string(self))
-         
      def modified(self):
          if self.id:    # only persist if key is present
--- 172,175 ----
***************
*** 282,286 ****
              self[options['pop3proxy','evidence_header_name']] = "; ".join(evd)
          
!         if options['pop3proxy','add_mailid_to'].find("header") != -1:
              self[options['pop3proxy','mailid_header_name']] = self.id
  
--- 265,269 ----
              self[options['pop3proxy','evidence_header_name']] = "; ".join(evd)
          
!         if "header" in options['pop3proxy','add_mailid_to']:
              self[options['pop3proxy','mailid_header_name']] = self.id
  

Index: tokenizer.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/tokenizer.py,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** tokenizer.py	18 Apr 2003 09:24:29 -0000	1.8
--- tokenizer.py	24 Apr 2003 07:43:50 -0000	1.9
***************
*** 1305,1309 ****
              # lines can be a too strong a discriminator for accidental
              # reasons.
!             safe_headers = options.safe_headers
              for x in msg.keys():
                  if x.lower() in safe_headers:
--- 1305,1309 ----
              # lines can be a too strong a discriminator for accidental
              # reasons.
!             safe_headers = options["Tokenizer", "safe_headers"]
              for x in msg.keys():
                  if x.lower() in safe_headers:
***************
*** 1311,1317 ****
          for x in x2n.items():
              yield "header:%s:%d" % x
!         if options.record_header_absence:
!             for x in options.safe_headers - Set([k.lower() for k in x2n]):
!                 yield "noheader:" + x
  
      def tokenize_body(self, msg, maxword=options.skip_max_word_size):
--- 1311,1318 ----
          for x in x2n.items():
              yield "header:%s:%d" % x
!         if options["Tokenizer", "record_header_absence"]:
!             for k in x2n:
!                 if not k.lower() in options["Tokenizer", "safe_headers"]:
!                     yield "noheader:" + k
  
      def tokenize_body(self, msg, maxword=options.skip_max_word_size):



From anadelonbrin at users.sourceforge.net  Thu Apr 24 01:44:19 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 24 03:44:23 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py, 1.31,
	1.32 pop3proxy.py, 1.77, 1.78 smtpproxy.py, 1.5, 1.6
Message-ID: <E198bP1-0000Ik-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv1065

Modified Files:
	imapfilter.py pop3proxy.py smtpproxy.py 
Log Message:
Fix for:
[ 725307 ] Outlook plugin won't load (anymore)
[ 725466 ] Include a proper locale fix in Options.py
[ 726255 ] Problem if bayescustomize.ini not there

Moved the line endings fix from message.py to imapmessage,
which is more appropriate.

Removed all reliance on UpdateableConfigParser from Options.

Removed the ConfigParser object from Options.

Removed the all_options dict from Options.

Changed multiple options to tuples (this required one very small
change in tokenizer).

Fixed the user interface for these changes, and for Tim's
change from True/False to Yes/No.

Removed some debugging statements that had been committed
by mistake at some point.

Fixed a potential problem with the imap ui trying to display a folder
list before a server/username had been entered.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.31
retrieving revision 1.32
diff -C2 -d -r1.31 -r1.32
*** imapfilter.py	22 Apr 2003 22:47:13 -0000	1.31
--- imapfilter.py	24 Apr 2003 07:43:44 -0000	1.32
***************
*** 63,73 ****
        "OK", then the filter terminates.  Handling of these errors could be
        much nicer.
      o IMAP over SSL would be nice. (isbg has an example of how to do this)
!     o The flags should be copied along with the message (especially
!       the /Seen flag, but all of them, really).
!     o Should the imap options server and port be combined?  i.e. instead
!       of having server=imap.example.com and port=143, have
!       server=imap.example.com:143?  This would be more consistent with
!       pop3proxy and would get rid of one option at no real cost.
      o Suggestions?
  """
--- 63,72 ----
        "OK", then the filter terminates.  Handling of these errors could be
        much nicer.
+     o We should check if the spam and unsure folders exist before filtering.
      o IMAP over SSL would be nice. (isbg has an example of how to do this)
!     o Develop a test script, like testtools/pop3proxytest.py that runs
!       through some tests (perhaps with a *real* imap server, rather than
!       a dummy one).  This would make it easier to carry out the tests
!       against each server whenever a change is made.
      o Suggestions?
  """
***************
*** 95,98 ****
--- 94,98 ----
  import sys
  import getopt
+ import types
  from getpass import getpass
  import email.Parser
***************
*** 108,120 ****
  imap = None
  
! # global rfc822 fetch command
! rfc822_command = "(RFC822.PEEK)"
  
  class IMAPSession(imaplib.IMAP4):
      '''A class extending the IMAP4 class, with a few optimizations'''
      
!     def __init__(self, server, port, debug):
          imaplib.Debug = debug  # this is a global in the imaplib module
          imaplib.IMAP4.__init__(self, server, port)
          # For efficiency, we remember which folder we are currently
          # in, and only send a select command to the IMAP server if
--- 108,172 ----
  imap = None
  
! CRLF_RE = re.compile(r'\r\n|\r|\n')
! 
! # A flag can have any character in the ascii range 32-127
! # except for (){ %*"\
! FLAG_CHARS = ""
! for i in range(32, 127):
!     if not chr(i) in ['(', ')', '{', ' ', '%', '*', '"', '\\']:
!         FLAG_CHARS += chr(i)
! FLAG = r"\\?[" + re.escape(FLAG_CHARS) + r"]+"
! # The empty flag set "()" doesn't match, so that extract returns
! # data["FLAGS"] == None
! FLAGS_RE = re.compile(r"(FLAGS) (\((" + FLAG + r" )*(" + FLAG + r")\))")
! INTERNALDATE_RE = re.compile(r"(INTERNALDATE) (\"\d{1,2}\-[A-Za-z]{3,3}\-" +
!                              r"\d{2,4} \d{2,2}\:\d{2,2}\:\d{2,2} " +
!                              r"[\+\-]\d{4,4}\")")
! RFC822_RE = re.compile(r"(RFC822) (\{[\d]+\})")
! UID_RE = re.compile(r"(UID) ([\d]+)")
! FETCH_RESPONSE_RE = re.compile(r"([0-9]+) \(([" + \
!                                re.escape(FLAG_CHARS) + r"\"\{\}\(\)\\ ]*)\)?")
! LITERAL_RE = re.compile(r"^\{[\d]+\}$")
! 
! def _extract_fetch_data(response):
!     '''Extract data from the response given to an IMAP FETCH command.'''
!     # response might be a tuple containing literal data
!     if type(response) == types.TupleType:
!         literal = response[1]
!         response = response[0]
!     else:
!         literal = None
!     # the first item will always be the message number
!     mo = FETCH_RESPONSE_RE.match(response)
!     data = {}
!     if mo is None:
!         print """IMAP server gave strange fetch response.  Please
!         report this as a bug."""
!         print response
!     else:
!         data["message_number"] = mo.group(1)
!         response = mo.group(2)
!     # We support the following FETCH items:
!     #  FLAGS
!     #  INTERNALDATE
!     #  RFC822
!     #  UID
!     # All others are ignored.
!     for r in [FLAGS_RE, INTERNALDATE_RE, RFC822_RE, UID_RE]:
!         mo = r.search(response)
!         if mo is not None:
!             if LITERAL_RE.match(mo.group(2)):
!                 data[mo.group(1)] = literal
!             else:
!                 data[mo.group(1)] = mo.group(2)
!     return data
  
  class IMAPSession(imaplib.IMAP4):
      '''A class extending the IMAP4 class, with a few optimizations'''
      
!     def __init__(self, server, port, debug=0, do_expunge=False):
          imaplib.Debug = debug  # this is a global in the imaplib module
          imaplib.IMAP4.__init__(self, server, port)
+         # XXX We should check here to see if the server/port were valid
          # For efficiency, we remember which folder we are currently
          # in, and only send a select command to the IMAP server if
***************
*** 122,126 ****
          # both IMAPMessage and IMAPFolder.
          self.current_folder = None
!         self.current_folder_readonly = None
  
      def login(self, uid, pw):
--- 174,178 ----
          # both IMAPMessage and IMAPFolder.
          self.current_folder = None
!         self.do_expunge = do_expunge
  
      def login(self, uid, pw):
***************
*** 135,158 ****
                  raise
      
!     def logout(self, expunge):
          # sign off
!         if expunge:
              self.expunge()
          imaplib.IMAP4.logout(self)  # superclass logout
          
!     def SelectFolder(self, folder, readOnly=True, force=False):
          '''A method to point ensuing imap operations at a target folder'''
!         
!         if self.current_folder != folder or \
!            self.current_folder_readonly != readOnly or force:
!             # Occasionally, we need to force a command, because we
!             # are interested in the response.  Things would be much
!             # nicer if we cached this information somewhere.
!             response = self.select(folder, readOnly)
              if response[0] != "OK":
!                 print "Invalid response to %s:\n%s" % (command, response)
                  sys.exit(-1)
              self.current_folder = folder
-             self.current_folder_readonly = readOnly
              return response
  
--- 187,214 ----
                  raise
      
!     def logout(self):
          # sign off
!         if self.do_expunge:
              self.expunge()
          imaplib.IMAP4.logout(self)  # superclass logout
          
!     def SelectFolder(self, folder):
          '''A method to point ensuing imap operations at a target folder'''
!         if self.current_folder != folder:
!             if self.current_folder != None:
!                 if self.do_expunge:
!                     # It is faster to do close() than a single
!                     # expunge when we log out (because expunge returns
!                     # a list of all the deleted messages, that we don't do
!                     # anything with)
!                     imap.close()
!             # We *always* use SELECT and not EXAMINE, because this
!             # speeds things up considerably.
!             response = self.select(folder, False)
              if response[0] != "OK":
!                 print "Invalid response to select %s:\n%s" % (folder,
!                                                               response)
                  sys.exit(-1)
              self.current_folder = folder
              return response
  
***************
*** 160,165 ****
      def __init__(self, folder, id):
          message.Message.__init__(self)
- 
          self.id = id
          self.folder = folder
          self.previous_folder = None
--- 216,221 ----
      def __init__(self, folder, id):
          message.Message.__init__(self)
          self.id = id
+         message.msginfoDB._getState(self)
          self.folder = folder
          self.previous_folder = None
***************
*** 170,173 ****
--- 226,242 ----
              sys.exit(-1)
  
+     def _force_CRLF(self, data):
+         """Make sure data uses CRLF for line termination.
+         """
+         return CRLF_RE.sub('\r\n', data)
+ 
+     def as_string(self):
+         # The email package stores line endings in the "internal" Python
+         # format ('\n').  It is up to whoever transmits that information to
+         # convert to appropriate line endings (according to RFC822, that is
+         # \r\n *only*).  imaplib *should* take care of this for us (in the
+         # append function), but does not, so we do it here
+         return self._force_CRLF(message.SBHeaderMessage.as_string(self))
+         
      def extractTime(self):
          # When we create a new copy of a message, we need to specify
***************
*** 189,192 ****
--- 258,262 ----
              self.previous_folder = self.folder
              self.folder = dest
+         self.modified()
  
      def Save(self):
***************
*** 196,208 ****
          response = imap.uid("FETCH", self.id, "(FLAGS INTERNALDATE)")
          self._check(response, 'fetch (flags internaldate)')
!         response_pattern = r"[\d]+ \(UID [\w]+ FLAGS (\([\\\w]*\)) "
!         response_pattern += r'INTERNALDATE ["]?([\w\-\+: ]+)["]?\)'
!         mo = re.match(response_pattern, response[1][0])
!         if mo is None:
              msg_time = self.extractTime()
!             flags = ""
          else:
!             flags = mo.group(1)
!             msg_time = mo.group(2)
  
          # See searching for new uid comments below
--- 266,281 ----
          response = imap.uid("FETCH", self.id, "(FLAGS INTERNALDATE)")
          self._check(response, 'fetch (flags internaldate)')
!         data = _extract_fetch_data(response[1][0])
!         if data.has_key("INTERNALDATE"):
!             msg_time = data["INTERNALDATE"]
!         else:
              msg_time = self.extractTime()
!         if data.has_key("FLAGS"):
!             flags = data["FLAGS"]
!             # The \Recent flag can be fetched, but cannot be stored
!             # We must remove it from the list if it is there.
!             flags = re.sub(r"\\Recent ?|\\ ?Recent", "", flags)
          else:
!             flags = None
  
          # See searching for new uid comments below
***************
*** 210,221 ****
          self["X-Spambayes-IMAP-OldID"] = old_id
                      
!         response = imap.append(self.folder.name, None,
                                 msg_time, self.as_string())
          self._check(response, 'append')
  
          if self.previous_folder is None:
!             imap.SelectFolder(self.folder.name, False)
          else:
!             imap.SelectFolder(self.previous_folder.name, False)
              self.previous_folder = None
          response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
--- 283,294 ----
          self["X-Spambayes-IMAP-OldID"] = old_id
                      
!         response = imap.append(self.folder.name, flags,
                                 msg_time, self.as_string())
          self._check(response, 'append')
  
          if self.previous_folder is None:
!             imap.SelectFolder(self.folder.name)
          else:
!             imap.SelectFolder(self.previous_folder.name)
              self.previous_folder = None
          response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
***************
*** 227,232 ****
          # doesn't work reliably anyway.  We instead search for a special
          # header that we add for this explicit purpose.
!         imap.SelectFolder(self.folder.name, False)
!         response = imap.uid("SEARCH", "(HEADER)", "X-Spambayes-IMAP-OldID",
                              old_id)
          self._check(response, 'search')
--- 300,305 ----
          # doesn't work reliably anyway.  We instead search for a special
          # header that we add for this explicit purpose.
!         imap.SelectFolder(self.folder.name)
!         response = imap.uid("SEARCH", "HEADER", "X-Spambayes-IMAP-OldID",
                              old_id)
          self._check(response, 'search')
***************
*** 237,241 ****
          # message is the last one with a recent flag
          if new_id == "":
!             response = imap.uid("SEARCH", "(RECENT)")
              new_id = response[1][0]
              if new_id.find(' ') > -1:
--- 310,314 ----
          # message is the last one with a recent flag
          if new_id == "":
!             response = imap.uid("SEARCH", "RECENT")
              new_id = response[1][0]
              if new_id.find(' ') > -1:
***************
*** 243,251 ****
                  new_id = ids[-1]
  
-         # now that we know the new id, we need to correct the flags
-         if flags != "":
-             response = imap.uid("STORE", new_id, "+FLAGS.SILENT", flags)
-             self._check(response, "store flags")
- 
          #XXX This code to delete the old message id from the message
          #XXX info db and manipulate the message id, is a *serious* hack.
--- 316,319 ----
***************
*** 259,262 ****
--- 327,331 ----
      def __init__(self, folder_name, readOnly=True):
          self.name = folder_name
+         self.rfc822_command = "RFC822.PEEK"
  
      def __cmp__(self, obj):
***************
*** 281,341 ****
          are flagged as recent, but not flagged as deleted.'''
          imap.SelectFolder(self.name, True)
!         response = imap.uid("SEARCH", "(RECENT UNDELETED)")
!         self._check(response, "SEARCH (RECENT UNDELETED)")
          return response[1][0].split(' ')
  
      def keys(self):
!         '''Returns uids for all the messages in the folder'''
          # request message range
!         response = imap.SelectFolder(self.name, True, True)
!         total_messages = response[1][0]
!         if total_messages == '0':
              return []
!         response = imap.fetch("1:" + total_messages, "(UID FLAGS)")
!         r = re.compile(r"[0-9]+ \(UID ([0-9]+) FLAGS \(([\\\w]*)\)\)")
!         uids = []
!         for resp in response[1]:
!             data = self._extract_fetch_data(resp)
!             if data.has_key("FLAGS"):
!                 if data["FLAGS"].lower().find("\\deleted") == -1:
!                     # We are interested in messages not marked as deleted
!                     uids.append(data["UID"])
!             else:
!                 uids.append(data["UID"])
!         return uids
! 
!     def _extract_fetch_data(self, response):
!         '''Extract data from the response given to an IMAP FETCH command.'''
!         data = {}
!         # the first item will always be the message number
!         mo = re.match(r"([0-9]+) \(?([\w\\\(\) ]*)\)?", response)
!         if mo is None:
!             print """IMAP server gave strange fetch response.  Please
!             report this as a bug."""
!         else:
!             data["message_number"] = mo.group(1)
!             response = mo.group(2)
!         mo = re.findall(r"([\w]+) \(?([\w\\]+)\)?", response)
!         for key, val in mo:
!             data[key] = val
!         return data
!         
  
      def __getitem__(self, key):
          '''Return message matching the given uid'''
!         global rfc822_command
!         imap.SelectFolder(self.name, True)
          # We really want to use RFC822.PEEK here, as that doesn't effect
          # the status of the message.  Unfortunately, it appears that not
          # all IMAP servers support this, even though it is in RFC1730
!         response = imap.uid("FETCH", key, rfc822_command)
          if response[0] != "OK":
!             rfc822_command = "(RFC822)"
!             response = imap.uid("FETCH", key, rfc822_command)
          self._check(response, "uid fetch")
!         messageText = response[1][0][1]
          # we return an instance of *our* message class, not the
          # raw rfc822 message
- 
          msg = IMAPMessage(self, key)
          msg.setPayload(messageText)
--- 350,384 ----
          are flagged as recent, but not flagged as deleted.'''
          imap.SelectFolder(self.name, True)
!         response = imap.uid("SEARCH", "RECENT UNDELETED")
!         self._check(response, "SEARCH RECENT UNDELETED")
          return response[1][0].split(' ')
  
      def keys(self):
!         '''Returns uids for all the messages in the folder not
!         marked as deleted.'''
          # request message range
!         imap.SelectFolder(self.name)
!         response = imap.uid("SEARCH", "UNDELETED")
!         self._check(response, "SEARCH UNDELETED")
!         if response[1][0] == "":
              return []
!         return response[1][0].split(' ')
  
      def __getitem__(self, key):
          '''Return message matching the given uid'''
!         imap.SelectFolder(self.name)
          # We really want to use RFC822.PEEK here, as that doesn't effect
          # the status of the message.  Unfortunately, it appears that not
          # all IMAP servers support this, even though it is in RFC1730
!         response = imap.uid("FETCH", key, self.rfc822_command)
          if response[0] != "OK":
!             self.rfc822_command = "RFC822"
!             response = imap.uid("FETCH", key, self.rfc822_command)
          self._check(response, "uid fetch")
!         data = _extract_fetch_data(response[1][0])
!         messageText = data["RFC822"]
! 
          # we return an instance of *our* message class, not the
          # raw rfc822 message
          msg = IMAPMessage(self, key)
          msg.setPayload(messageText)
***************
*** 365,369 ****
          for msg in self:
              if msg.GetClassification() is None:
!                 (prob, clues) = classifier.spamprob(msg.asTokens(), evidence=True)
                  # add headers and remember classification
                  msg.addSBHeaders(prob, clues)
--- 408,413 ----
          for msg in self:
              if msg.GetClassification() is None:
!                 (prob, clues) = classifier.spamprob(msg.asTokens(),
!                                                     evidence=True)
                  # add headers and remember classification
                  msg.addSBHeaders(prob, clues)
***************
*** 395,400 ****
  
          if options["imap", "ham_train_folders"] != "":
!             ham_training_folders = \
!                                  options["imap", "ham_train_folders"].split()
              for fol in ham_training_folders:
                  if options['globals', 'verbose']:
--- 439,443 ----
  
          if options["imap", "ham_train_folders"] != "":
!             ham_training_folders = options["imap", "ham_train_folders"]
              for fol in ham_training_folders:
                  if options['globals', 'verbose']:
***************
*** 407,412 ****
  
          if options["imap", "spam_train_folders"] != "":
!             spam_training_folders = \
!                                   options["imap", "spam_train_folders"].split()
              for fol in spam_training_folders:
                  if options['globals', 'verbose']:
--- 450,454 ----
  
          if options["imap", "spam_train_folders"] != "":
!             spam_training_folders = options["imap", "spam_train_folders"]
              for fol in spam_training_folders:
                  if options['globals', 'verbose']:
***************
*** 429,433 ****
              t = time.time()
              
!         for filter_folder in options["imap", "filter_folders"].split():
              folder = IMAPFolder(filter_folder, False)
              folder.Filter(self.classifier, self.spam_folder,
--- 471,475 ----
              t = time.time()
              
!         for filter_folder in options["imap", "filter_folders"]:
              folder = IMAPFolder(filter_folder, False)
              folder.Filter(self.classifier, self.spam_folder,
***************
*** 455,458 ****
--- 497,502 ----
      promptForPass = False
      launchUI = False
+     server = ""
+     username = ""
  
      for opt, arg in opts:
***************
*** 497,511 ****
  or training will be performed."""
  
-     server = options["imap", "server"]
-     username = options["imap", "username"]
-     if server == "" or username == "":
-         print "You need to specify both a server and a username."
-         sys.exit()
- 
-     if promptForPass:
-         pwd = getpass()
-     else:
-         pwd = options["imap", "password"]
- 
      bdbname = os.path.expanduser(bdbname)
      
--- 541,544 ----
***************
*** 520,524 ****
      if options["globals", "verbose"]:
          print "Done."            
!                 
      if server.find(':') > -1:
          server, port = server.split(':', 1)
--- 553,572 ----
      if options["globals", "verbose"]:
          print "Done."            
! 
!     if options["imap", "server"]:
!         # The options class is ahead of us here:
!         #   it knows that imap:server will eventually be able to have
!         #   multiple values, but for the moment, we just use the first one
!         server = options["imap", "server"][0]
!         username = options["imap", "username"][0]
!         pwd = options["imap", "password"][0]
!     else:
!         if not launchUI:
!             print "You need to specify both a server and a username."
!             sys.exit()
! 
!     if promptForPass:
!         pwd = getpass()
! 
      if server.find(':') > -1:
          server, port = server.split(':', 1)
***************
*** 529,546 ****
          else:
              port = 143
-     imap = IMAPSession(server, port, imapDebug)
  
      imap_filter = IMAPFilter(classifier)
  
      # Web interface
-     # XXX If someone is running *both* pop3proxy and imapfilter
-     # XXX then there will be trouble since both interfaces are
-     # XXX using the same port by default.
      if launchUI:
!         imap.login(username, pwd)
          httpServer = UserInterfaceServer(options["html_ui", "port"])
!         httpServer.register(IMAPUserInterface(classifier, imap))
          Dibbler.run(launchBrowser=launchUI)
      else:
          while True:
              imap.login(username, pwd)
--- 577,592 ----
          else:
              port = 143
  
      imap_filter = IMAPFilter(classifier)
  
      # Web interface
      if launchUI:
!         if server != "":
!             imap = IMAPSession(server, port, imapDebug, doExpunge)
          httpServer = UserInterfaceServer(options["html_ui", "port"])
!         httpServer.register(IMAPUserInterface(classifier, imap, pwd))
          Dibbler.run(launchBrowser=launchUI)
      else:
+         imap = IMAPSession(server, port, imapDebug, doExpunge)
          while True:
              imap.login(username, pwd)
***************
*** 555,559 ****
                  imap_filter.Filter()
  
!             imap.logout(doExpunge)
              
              if sleepTime:
--- 601,605 ----
                  imap_filter.Filter()
  
!             imap.logout()
              
              if sleepTime:

Index: pop3proxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/pop3proxy.py,v
retrieving revision 1.77
retrieving revision 1.78
diff -C2 -d -r1.77 -r1.78
*** pop3proxy.py	21 Apr 2003 12:18:45 -0000	1.77
--- pop3proxy.py	24 Apr 2003 07:43:44 -0000	1.78
***************
*** 502,506 ****
          self.proxyPorts = []
          if options["pop3proxy", "servers"]:
!             for server in options["pop3proxy", "servers"].split(','):
                  server = server.strip()
                  if server.find(':') > -1:
--- 502,506 ----
          self.proxyPorts = []
          if options["pop3proxy", "servers"]:
!             for server in options["pop3proxy", "servers"]:
                  server = server.strip()
                  if server.find(':') > -1:
***************
*** 511,515 ****
  
          if options["pop3proxy", "ports"]:
!             splitPorts = options["pop3proxy", "ports"].split(',')
              self.proxyPorts = map(_addressAndPort, splitPorts)
  
--- 511,515 ----
  
          if options["pop3proxy", "ports"]:
!             splitPorts = options["pop3proxy", "ports"]
              self.proxyPorts = map(_addressAndPort, splitPorts)
  

Index: smtpproxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/smtpproxy.py,v
retrieving revision 1.5
retrieving revision 1.6
diff -C2 -d -r1.5 -r1.6
*** smtpproxy.py	18 Apr 2003 05:52:13 -0000	1.5
--- smtpproxy.py	24 Apr 2003 07:43:45 -0000	1.6
***************
*** 473,477 ****
      proxyPorts = []
      if options.smtpproxy_servers:
!         for server in options.smtpproxy_servers.split(','):
              server = server.strip()
              if server.find(':') > -1:
--- 473,477 ----
      proxyPorts = []
      if options.smtpproxy_servers:
!         for server in options.smtpproxy_servers:
              server = server.strip()
              if server.find(':') > -1:
***************
*** 481,485 ****
              servers.append((server, int(port)))
      if options.smtpproxy_ports:
!         splitPorts = options.smtpproxy_ports.split(',')
          proxyPorts = map(_addressAndPort, splitPorts)
      if len(servers) != len(proxyPorts):
--- 481,485 ----
              servers.append((server, int(port)))
      if options.smtpproxy_ports:
!         splitPorts = options.smtpproxy_ports
          proxyPorts = map(_addressAndPort, splitPorts)
      if len(servers) != len(proxyPorts):



From anadelonbrin at users.sourceforge.net  Thu Apr 24 01:46:03 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 24 03:46:05 2003
Subject: [Spambayes-checkins] spambayes/utilities convert_config_file.py,
	NONE, 1.1
Message-ID: <E198bQh-0000Z8-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/utilities
In directory sc8-pr-cvs1:/tmp/cvs-serv2086/utilities

Added Files:
	convert_config_file.py 
Log Message:
A script that will convert configuration files over to the new format.

Any comments and whitespace (other than in the lines of options that change) are retained, and a backup of the file is saved.

Please let me know of any problems so that I can fix them.

--- NEW FILE: convert_config_file.py ---
#! /usr/bin/env python

"""Convert configuration files

This script will convert configuration files to the new format.
It works by reading in the old configuration file and updating it -
this means that as soon as the Options module stops accepting the old
style input, this script will also stop working, and need to be replaced
with a new, much more complicated one.

By default, the script looks for a file called "bayescustomize.ini" in
the current working directory.  You may override this with the "-f" option.

The "-v" option produces verbose output, and "-h" produces this text.

For safety, a backup of the old configuration file is saved with a ".bak"
suffix - note that if a file by this name already exists, it is replaced.

Note that around options that change blank lines might move - there isn't
really an easy way around this, but it's easily fixed by hand, and if you
don't look at the config file, you'll never know <wink>.
"""

# This module is part of the spambayes project, which is Copyright 2002-3
# The Python Software Foundation and is covered by the Python Software
# Foundation license.

__author__ = "Tony Meyer, <ta-meyer@ihug.co.nz>"
__credits__ = "All the Spambayes folk."

import getopt
import sys
import shutil
import os

# a bit of a hack to help those without spambayes on their
# Python path - stolen from timtest.py
sys.path.insert(-1, os.getcwd())
sys.path.insert(-1, os.path.dirname(os.getcwd()))

from spambayes import Options

def run():
    try:
        opts, args = getopt.getopt(sys.argv[1:], 'vhf:')
    except getopt.error, msg:
        print >>sys.stderr, str(msg) + '\n\n' + __doc__
        sys.exit()

    filename = "bayescustomize.ini"
    verbose = False

    for opt, arg in opts:
        if opt == '-h':
            print >>sys.stderr, __doc__
            sys.exit()
        elif opt == '-f':
            filename = arg
        elif opt == '-v':
            verbose = True

    o = Options.OptionsClass()
    if verbose:
        print "Loading defaults"
    o.load_defaults()
    alts = []
    if verbose:
        print "Updating file:", filename
    if os.path.exists(filename):
        if verbose:
            print "Merging..."
        o.merge_file(filename)
    else:
        print filename, "does not exist; exiting."
        sys.exit(-1)
    if verbose:
        print "Copying file", filename, "to", filename + ".bak"
    shutil.copyfile(filename, filename + ".bak")
    if verbose:
        print "Updating..."
    o.update_file(filename)
    if verbose:
        print "Done."

if __name__ == '__main__':
    run()



From timstone4 at users.sourceforge.net  Thu Apr 24 16:50:54 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Thu Apr 24 18:50:57 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.19,1.20
Message-ID: <E198pYM-0002NK-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv9065

Modified Files:
	message.py 
Log Message:
Correct _get_state and _set_state methods to correctly persist and restore
message persistent state

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.19
retrieving revision 1.20
diff -C2 -d -r1.19 -r1.20
*** message.py	24 Apr 2003 07:43:49 -0000	1.19
--- message.py	24 Apr 2003 22:50:47 -0000	1.20
***************
*** 115,124 ****
      def _getState(self, msg):
          try:
!             return self.db[msg.getId()]
          except KeyError:
!             return None
  
      def _setState(self, msg):
!         self.db[msg.getId()] = msg
  
      def _delState(self, msg):
--- 115,124 ----
      def _getState(self, msg):
          try:
!             (msg.c, msg.t) = self.db[msg.getId()]
          except KeyError:
!             pass
  
      def _setState(self, msg):
!         self.db[msg.getId()] = (msg.c, msg.t)
  
      def _delState(self, msg):
***************
*** 164,168 ****
          self.id = id
          msginfoDB._getState(self)
-         self.modified()   # id has changed, force storage
          
      def getId(self):
--- 164,167 ----



From anadelonbrin at users.sourceforge.net  Thu Apr 24 20:29:18 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 24 22:29:22 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.32,1.33
Message-ID: <E198sxi-0003n6-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv14539

Modified Files:
	imapfilter.py 
Log Message:
Fix Options convert and unconvert functions.

Fix valid characters for imap username and password.

Improve behaviour of convert_config_file script.

A few extra comments here and there.

Check that spam/unsure/filter folders exist in imap before filtering,
likewise with training.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.32
retrieving revision 1.33
diff -C2 -d -r1.32 -r1.33
*** imapfilter.py	24 Apr 2003 07:43:44 -0000	1.32
--- imapfilter.py	25 Apr 2003 02:29:15 -0000	1.33
***************
*** 48,52 ****
      o By default, the filter does *not* delete, modify or move any of your
        mail.  Due to quirks in how imap works, new versions of your mail are
!       modified and placed in new folders, but there originals are still
        available.  These are flagged with the /Deleted flag so that you know
        that they can be removed.  Your mailer may not show these messages
--- 48,52 ----
      o By default, the filter does *not* delete, modify or move any of your
        mail.  Due to quirks in how imap works, new versions of your mail are
!       modified and placed in new folders, but the originals are still
        available.  These are flagged with the /Deleted flag so that you know
        that they can be removed.  Your mailer may not show these messages
***************
*** 63,72 ****
        "OK", then the filter terminates.  Handling of these errors could be
        much nicer.
!     o We should check if the spam and unsure folders exist before filtering.
!     o IMAP over SSL would be nice. (isbg has an example of how to do this)
      o Develop a test script, like testtools/pop3proxytest.py that runs
        through some tests (perhaps with a *real* imap server, rather than
        a dummy one).  This would make it easier to carry out the tests
        against each server whenever a change is made.
      o Suggestions?
  """
--- 63,89 ----
        "OK", then the filter terminates.  Handling of these errors could be
        much nicer.
!     o IMAP over SSL would be nice.  imaplib in Python 2.3 has an SSL class
!       that we could inherit from
      o Develop a test script, like testtools/pop3proxytest.py that runs
        through some tests (perhaps with a *real* imap server, rather than
        a dummy one).  This would make it easier to carry out the tests
        against each server whenever a change is made.
+     o The RFC says that "unique identifiers persist across sessions", but
+       also that "[i]f unique identifiers from an earlier session fail to
+       persist to this session...".  This strikes me as fairly inconsistent.
+       If the uid does not persist, then we will end up re-training/filtering
+       the message, but I'm not sure what can be done about that.  There is
+       mention of the UID validity value, which each folder has.  If the uids
+       fail to persist, then this value will increase.  The RFC doesn't say
+       if this is the *only* time it will increase, though.  I'm not sure
+       if this value is of any use to us or not; it's worth keeping in mind,
+       though.
+     o IMAP supports authentication via other methods than the plain-text
+       password method that we are using at the moment.  Neither of the
+       servers I have access to offer any alternative method, however.  If
+       someone's does, then it would be nice to offer this.
+     o Usernames should be able to be literals as well as quoted strings.
+       This might help if the username/password has special characters like
+       accented characters.
      o Suggestions?
  """
***************
*** 110,114 ****
  CRLF_RE = re.compile(r'\r\n|\r|\n')
  
! # A flag can have any character in the ascii range 32-127
  # except for (){ %*"\
  FLAG_CHARS = ""
--- 127,131 ----
  CRLF_RE = re.compile(r'\r\n|\r|\n')
  
! # A flag can have any character in the ascii range 32-126
  # except for (){ %*"\
  FLAG_CHARS = ""
***************
*** 258,262 ****
              self.previous_folder = self.folder
              self.folder = dest
-         self.modified()
  
      def Save(self):
--- 275,278 ----
***************
*** 441,444 ****
--- 457,462 ----
              ham_training_folders = options["imap", "ham_train_folders"]
              for fol in ham_training_folders:
+                 # Select the folder to make sure it exists
+                 imap.SelectFolder(fol)
                  if options['globals', 'verbose']:
                      print "   Training ham folder %s" % (fol)
***************
*** 452,455 ****
--- 470,475 ----
              spam_training_folders = options["imap", "spam_train_folders"]
              for fol in spam_training_folders:
+                 # Select the folder to make sure it exists
+                 imap.SelectFolder(fol)
                  if options['globals', 'verbose']:
                      print "   Training spam folder %s" % (fol)
***************
*** 470,475 ****
--- 490,501 ----
          if options["globals", "verbose"]:
              t = time.time()
+ 
+         # Select the spam folder and unsure folder to make sure they exist
+         imap.SelectFolder(self.spam_folder)
+         imap.SelectFolder(self.unsure_folder)
              
          for filter_folder in options["imap", "filter_folders"]:
+             # Select the folder to make sure it exists
+             imap.SelectFolder(filter_folder)
              folder = IMAPFolder(filter_folder, False)
              folder.Filter(self.classifier, self.spam_folder,



From anadelonbrin at users.sourceforge.net  Thu Apr 24 20:29:19 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 24 22:29:26 2003
Subject: [Spambayes-checkins] 
	spambayes/utilities convert_config_file.py, 1.1, 1.2
Message-ID: <E198sxj-0003nD-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/utilities
In directory sc8-pr-cvs1:/tmp/cvs-serv14539/utilities

Modified Files:
	convert_config_file.py 
Log Message:
Fix Options convert and unconvert functions.

Fix valid characters for imap username and password.

Improve behaviour of convert_config_file script.

A few extra comments here and there.

Check that spam/unsure/filter folders exist in imap before filtering,
likewise with training.

Index: convert_config_file.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/utilities/convert_config_file.py,v
retrieving revision 1.1
retrieving revision 1.2
diff -C2 -d -r1.1 -r1.2
*** convert_config_file.py	24 Apr 2003 07:45:55 -0000	1.1
--- convert_config_file.py	25 Apr 2003 02:29:16 -0000	1.2
***************
*** 14,19 ****
  The "-v" option produces verbose output, and "-h" produces this text.
  
! For safety, a backup of the old configuration file is saved with a ".bak"
! suffix - note that if a file by this name already exists, it is replaced.
  
  Note that around options that change blank lines might move - there isn't
--- 14,20 ----
  The "-v" option produces verbose output, and "-h" produces this text.
  
! For safety, a backup of the old configuration file is saved with a
! ".backup" suffix - note that if a file by this name already exists, this
! does not occur.
  
  Note that around options that change blank lines might move - there isn't
***************
*** 74,80 ****
          print filename, "does not exist; exiting."
          sys.exit(-1)
!     if verbose:
!         print "Copying file", filename, "to", filename + ".bak"
!     shutil.copyfile(filename, filename + ".bak")
      if verbose:
          print "Updating..."
--- 75,83 ----
          print filename, "does not exist; exiting."
          sys.exit(-1)
!     backup_name = filename + ".backup"
!     if not os.path.exists(backup_name):
!         if verbose:
!             print "Copying file", filename, "to", backup_name
!         shutil.copyfile(filename, backup_name)
      if verbose:
          print "Updating..."



From anadelonbrin at users.sourceforge.net  Thu Apr 24 20:29:18 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 24 22:29:30 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py, 1.41,
	1.42 UserInterface.py, 1.6, 1.7
Message-ID: <E198sxi-0003nA-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv14539/spambayes

Modified Files:
	Options.py UserInterface.py 
Log Message:
Fix Options convert and unconvert functions.

Fix valid characters for imap username and password.

Improve behaviour of convert_config_file script.

A few extra comments here and there.

Check that spam/unsure/filter folders exist in imap before filtering,
likewise with training.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.41
retrieving revision 1.42
diff -C2 -d -r1.41 -r1.42
*** Options.py	24 Apr 2003 07:43:46 -0000	1.41
--- Options.py	25 Apr 2003 02:29:16 -0000	1.42
***************
*** 32,35 ****
--- 32,37 ----
   o Find a regex expert to come up with *good* patterns for domains,
     email addresses, and so forth.
+  o str(Option) should really call Option.unconvert since this is what
+    it does.  Try putting that in and running all the tests.
   o [See also the __issues__ string.]
   o Suggestions?
***************
*** 112,115 ****
--- 114,127 ----
  IMAP_FOLDER = r"[^,]+"
  
+ # IMAP's astring should also be valid in the form:
+ #   "{" number "}" CRLF *CHAR8
+ #   where number represents the number of CHAR8 octets
+ # but this is too complex for us at the moment.
+ IMAP_ASTRING = ""
+ for i in range(1, 128):
+     if not chr(i) in ['"', '\\', '\n', '\r']:
+         IMAP_ASTRING += chr(i)
+ IMAP_ASTRING = r"\"?\\?[" + re.escape(IMAP_ASTRING) + r"]+\"?"
+ 
  # Similarly, each option must specify whether it should be reset to
  # this value on a "reset to defaults" command.  Most should, but with some
***************
*** 886,890 ****
       on the same server, please see the comments regarding the server
       value.""",
!      r"[\w]+", DO_NOT_RESTORE),
  
      ("password", "Password", (),
--- 898,902 ----
       on the same server, please see the comments regarding the server
       value.""",
!      IMAP_ASTRING, DO_NOT_RESTORE),
  
      ("password", "Password", (),
***************
*** 896,900 ****
       blank and use the -p command line option to imapfilter.py and you will
       be prompted for your password.""",
!      r"[\w]+", DO_NOT_RESTORE),
  
      ("expunge", "Purge//Expunge", False,
--- 908,912 ----
       blank and use the -p command line option to imapfilter.py and you will
       be prompted for your password.""",
!      IMAP_ASTRING, DO_NOT_RESTORE),
  
      ("expunge", "Purge//Expunge", False,
***************
*** 938,941 ****
--- 950,954 ----
          self.restore = restore
          self.value = None
+         self.delimiter = None
  
      def display_name(self):
***************
*** 1061,1064 ****
--- 1074,1081 ----
      def convert(self, value):
          '''Convert value from a string to the appropriate type.'''
+         svt = type(self.value)
+         if svt == type(value):
+             # already the correct type
+             return value
          if self.is_boolean():
              if str(value) == "True" or value == 1:
***************
*** 1067,1081 ****
                  return False
              raise TypeError, self.name + " must be True or False"
!         svt = type(self.value)
!         if svt == type(value):
              # already the correct type
              return value
!         if svt == types.IntType:
              return locale.atoi(value)
!         if svt == types.FloatType:
              return locale.atof(value)
!         if svt in types.StringTypes and svt in types.StringTypes:
!             return value
!         raise TypeError, self.name + " has an invalid type."
  
      def unconvert(self):
--- 1084,1117 ----
                  return False
              raise TypeError, self.name + " must be True or False"
!         if self.multiple_values_allowed():
!             # This will fall apart if the allowed_value is a tuple,
!             # but not a homogenous one...
!             if type(self.allowed_values) in types.StringTypes:
!                 vals = list(self._split_values(value))
!             else:
!                 vals = value.split()
!             if len(self.default_value) > 0:
!                 to_type = type(self.default_value[0])
!             else:
!                 to_type = types.StringType
!             for i in range(0, len(vals)):
!                 vals[i] = self._convert(vals[i], to_type)
!             return tuple(vals)
!         else:
!             return self._convert(value, svt)
!         raise TypeError, self.name + " has an invalid type."
! 
!     def _convert(self, value, to_type):
!         '''Convert an int, float or string to the specified type.'''
!         if to_type == type(value):
              # already the correct type
              return value
!         if to_type == types.IntType:
              return locale.atoi(value)
!         if to_type == types.FloatType:
              return locale.atof(value)
!         if to_type in types.StringTypes:
!             return str(value)
!         raise TypeError, "Invalid type."
  
      def unconvert(self):
***************
*** 1091,1102 ****
                  return "False"
          if type(self.value) == types.TupleType:
              # We need to separate out the items
-             # We use a character that is invalid as the separator
-             # so that it will reparse correctly
              strval = ""
!             # XXX fix this
!             sep = ' '
              for v in self.value:
!                 strval += v + sep
              strval = strval[:-1] # trailing seperator
          else:
--- 1127,1171 ----
                  return "False"
          if type(self.value) == types.TupleType:
+             if len(self.value) == 0:
+                 return ""
+             if len(self.value) == 1:
+                 v = self.value[0]
+                 if type(v) == types.FloatType:
+                     return locale.str(self.value[0])
+                 return str(v)
              # We need to separate out the items
              strval = ""
!             # We use a character that is invalid as the separator
!             # so that it will reparse correctly.  We could try all
!             # characters, but we make do with this set of commonly
!             # used ones - note that the first one that works will
!             # be used.  Perhaps a nicer solution than this would be
!             # to specifiy a valid delimiter for all options that
!             # can have multiple values.  Note that we have None at
!             # the end so that this will crash and die if none of
!             # the separators works <wink>
!             if self.delimiter is None:
!                 if type(self.allowed_values) == types.TupleType:
!                     self.delimiter = ' '
!                 else:
!                     v0 = self.value[0]
!                     v1 = self.value[1]
!                     for sep in [' ', ',', ':', ';', '/', '\\', None]:
!                         # we know at this point that len(self.value) is at
!                         # least two, because len==0 and len==1 were dealt
!                         # with as special cases
!                         test_str = v0 + sep + v1
!                         test_tuple = self._split_values(test_str)
!                         if test_tuple[0] == v0 and test_tuple[1] == v1 and \
!                            len(test_tuple) == 2:
!                             break
!                     # cache this so we don't always need to do the above
!                     self.delimiter = sep
              for v in self.value:
!                 if type(v) == types.FloatType:
!                     v = locale.str(v)
!                 else:
!                     v = str(v)
!                 strval += v + self.delimiter
              strval = strval[:-1] # trailing seperator
          else:

Index: UserInterface.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/UserInterface.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** UserInterface.py	24 Apr 2003 07:43:48 -0000	1.6
--- UserInterface.py	25 Apr 2003 02:29:16 -0000	1.7
***************
*** 38,46 ****
   o Save the stats (num classified, etc.) between sessions.
   o "Reload database" button.
!  o Checkboxes need a default value (i.e. what to set the option as
!    when no boxes are checked).  This needs to be thought about and
!    then implemented.  add_id is an example of what it does at the
!    moment.
! 
   o Suggestions?
  
--- 38,43 ----
   o Save the stats (num classified, etc.) between sessions.
   o "Reload database" button.
!  o Displaying options should be done with the locale format function
!    rather than str().
   o Suggestions?
  



From anadelonbrin at users.sourceforge.net  Thu Apr 24 20:31:49 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Thu Apr 24 22:31:53 2003
Subject: [Spambayes-checkins] 
	spambayes/spambayes CompatConfigParser.py, 1.1,
	NONE UpdatableConfigParser.py, 1.3, NONE
Message-ID: <E198t09-0003zJ-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv15310/spambayes

Removed Files:
	CompatConfigParser.py UpdatableConfigParser.py 
Log Message:
Options.py has been reworked to no longer need these files.

--- CompatConfigParser.py DELETED ---

--- UpdatableConfigParser.py DELETED ---



From anadelonbrin at users.sourceforge.net  Thu Apr 24 22:12:04 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 25 00:12:11 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.33,1.34
Message-ID: <E198uZA-0001hP-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv6476

Modified Files:
	imapfilter.py 
Log Message:
Added message_from_string functions (for Message,
SBHeaderMessage and IMAPMessage) like those in email.
This provides a nicer method of creating a message than using the
setPayload function.  Switched imapfilter over to using this.

Plus various documentation fixes and a couple of extra checks.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.33
retrieving revision 1.34
diff -C2 -d -r1.33 -r1.34
*** imapfilter.py	25 Apr 2003 02:29:15 -0000	1.33
--- imapfilter.py	25 Apr 2003 04:12:00 -0000	1.34
***************
*** 112,117 ****
  import getopt
  import types
  from getpass import getpass
- import email.Parser
  from email.Utils import parsedate
  
--- 112,117 ----
  import getopt
  import types
+ import email
  from getpass import getpass
  from email.Utils import parsedate
  
***************
*** 231,241 ****
  
  class IMAPMessage(message.SBHeaderMessage):
!     def __init__(self, folder, id):
          message.Message.__init__(self)
!         self.id = id
!         message.msginfoDB._getState(self)
!         self.folder = folder
          self.previous_folder = None
  
      def _check(self, response, command):
          if response[0] != "OK":
--- 231,242 ----
  
  class IMAPMessage(message.SBHeaderMessage):
!     def __init__(self):
          message.Message.__init__(self)
!         self.folder = None
          self.previous_folder = None
  
+     def setFolder(self, folder):
+         self.folder = folder
+ 
      def _check(self, response, command):
          if response[0] != "OK":
***************
*** 269,272 ****
--- 270,275 ----
  
      def MoveTo(self, dest):
+         '''Note that message should move to another folder.  No move is
+         carried out until Save() is called.'''
          # This move operation just changes where we think we are,
          # and we do an actual move on save (to avoid doing
***************
*** 277,283 ****
--- 280,293 ----
  
      def Save(self):
+         '''Save message to imap server.'''
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
          # we need to copy the flags as well
+         if self.folder is None:
+             raise RuntimeError, """Can't save a message that doesn't
+             have a folder."""
+         if self.id is None:
+             raise RuntimeError, """Can't save a message that doesn't have
+             an id."""
          response = imap.uid("FETCH", self.id, "(FLAGS INTERNALDATE)")
          self._check(response, 'fetch (flags internaldate)')
***************
*** 298,302 ****
          old_id = self.id
          self["X-Spambayes-IMAP-OldID"] = old_id
!                     
          response = imap.append(self.folder.name, flags,
                                 msg_time, self.as_string())
--- 308,312 ----
          old_id = self.id
          self["X-Spambayes-IMAP-OldID"] = old_id
! 
          response = imap.append(self.folder.name, flags,
                                 msg_time, self.as_string())
***************
*** 339,342 ****
--- 349,356 ----
          self.modified()
  
+ # This performs a similar function to email.message_from_string()
+ def imapmessage_from_string(s, _class=IMAPMessage, strict=False):
+     return email.message_from_string(s, _class, strict)
+ 
  
  class IMAPFolder(object):
***************
*** 347,350 ****
--- 361,366 ----
      def __cmp__(self, obj):
          '''Two folders are equal if their names are equal'''
+         if obj is None:
+             return False
          return cmp(self.name, obj.name)
  
***************
*** 397,402 ****
          # we return an instance of *our* message class, not the
          # raw rfc822 message
!         msg = IMAPMessage(self, key)
!         msg.setPayload(messageText)
          
          return msg
--- 413,419 ----
          # we return an instance of *our* message class, not the
          # raw rfc822 message
!         msg = imapmessage_from_string(messageText)
!         msg.setId(key)
!         msg.setFolder(self)
          
          return msg
***************
*** 406,410 ****
          num_trained = 0
          for msg in self:
!             if msg.GetTrained() == isSpam:
                  classifier.unlearn(msg.asTokens(), not isSpam)
                  # Once the message has been untrained, it's training memory
--- 423,427 ----
          num_trained = 0
          for msg in self:
!             if msg.GetTrained() == (not isSpam):
                  classifier.unlearn(msg.asTokens(), not isSpam)
                  # Once the message has been untrained, it's training memory



From anadelonbrin at users.sourceforge.net  Thu Apr 24 22:12:04 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Fri Apr 25 00:12:20 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.20,1.21
Message-ID: <E198uZA-0001hW-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv6476/spambayes

Modified Files:
	message.py 
Log Message:
Added message_from_string functions (for Message,
SBHeaderMessage and IMAPMessage) like those in email.
This provides a nicer method of creating a message than using the
setPayload function.  Switched imapfilter over to using this.

Plus various documentation fixes and a couple of extra checks.

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.20
retrieving revision 1.21
diff -C2 -d -r1.20 -r1.21
*** message.py	24 Apr 2003 22:50:47 -0000	1.20
--- message.py	25 Apr 2003 04:12:02 -0000	1.21
***************
*** 33,64 ****
      A typical classification usage pattern would be something like:
      
!     >>>msg = spambayes.message.SBHeaderMessage()
!     >>>msg.setPayload(substance) # substance comes from somewhere else
!     >>>id = msg.setIdFromPayload()
      
!     >>>if id is None:
!     >>>    msg.setId(time())   # or some unique identifier
       
!     >>>msg.delSBHeaders()      # never include sb headers in a classification
      
!     >>># bayes object is your responsibility   
!     >>>(prob, clues) = bayes.spamprob(msg.asTokens(), evidence=True)
  
!     >>>msg.addSBHeaders(prob, clues)
      
      
      A typical usage pattern to train as spam would be something like:
      
!     >>>msg = spambayes.message.SBHeaderMessage()
!     >>>msg.setPayload(substance) # substance comes from somewhere else
!     >>>id = msg.setId(msgid)     # id is a fname, outlook msg id, something...
  
!     >>>msg.delSBHeaders()        # never include sb headers in a train
      
!     >>>if msg.getTraining() == False:   # could be None, can't do boolean test
!     >>>    bayes.unlearn(msg.asTokens(), False)  # untrain the ham
      
!     >>>bayes.learn(msg.asTokens(), True) # train as spam
!     >>>msg.rememberTraining(True)
      
  
--- 33,64 ----
      A typical classification usage pattern would be something like:
      
!     >>> msg = spambayes.message.SBHeaderMessage()
!     >>> msg.setPayload(substance) # substance comes from somewhere else
!     >>> id = msg.setIdFromPayload()
      
!     >>> if id is None:
!     >>>     msg.setId(time())   # or some unique identifier
       
!     >>> msg.delSBHeaders()      # never include sb headers in a classification
      
!     >>> # bayes object is your responsibility   
!     >>> (prob, clues) = bayes.spamprob(msg.asTokens(), evidence=True)
  
!     >>> msg.addSBHeaders(prob, clues)
      
      
      A typical usage pattern to train as spam would be something like:
      
!     >>> msg = spambayes.message.SBHeaderMessage()
!     >>> msg.setPayload(substance) # substance comes from somewhere else
!     >>> id = msg.setId(msgid)     # id is a fname, outlook msg id, something...
  
!     >>> msg.delSBHeaders()        # never include sb headers in a train
      
!     >>> if msg.getTraining() == False:   # could be None, can't do boolean test
!     >>>     bayes.unlearn(msg.asTokens(), False)  # untrain the ham
      
!     >>> bayes.learn(msg.asTokens(), True) # train as spam
!     >>> msg.rememberTraining(True)
      
  
***************
*** 92,95 ****
--- 92,96 ----
  import re
  
+ import email            # for message_from_string
  import email.Message
  import email.Parser
***************
*** 141,145 ****
          # non-persistent state includes all of email.Message.Message state
  
!         
      def setPayload(self, payload):
          prs = email.Parser.Parser()
--- 142,153 ----
          # non-persistent state includes all of email.Message.Message state
  
!     # This function (and it's hackishness) can be avoided by using the
!     # message_from_string and sbheadermessage_from_string functions
!     # at the end of the module.  i.e. instead of doing this:
!     #   >>> msg = spambayes.message.SBHeaderMessage()
!     #   >>> msg.setPayload(substance)
!     # you do this:
!     #   >>> msg = sbheadermessage_from_string(substance)
!     # imapfilter has an example of this in action
      def setPayload(self, payload):
          prs = email.Parser.Parser()
***************
*** 281,282 ****
--- 289,297 ----
          del self[options['pop3proxy','thermostat_header_name']]
          del self[options['pop3proxy','evidence_header_name']]
+ 
+ # These perform similar functions to email.message_from_string()
+ def message_from_string(s, _class=Message, strict=False):
+     return email.message_from_string(s, _class, strict)
+ 
+ def sbheadermessage_from_string(s, _class=SBHeaderMessage, strict=False):
+     return email.message_from_string(s, _class, strict)



From anadelonbrin at users.sourceforge.net  Sat Apr 26 23:11:44 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 27 01:11:48 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.42,1.43
Message-ID: <E199eS0-00078U-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv27377/spambayes

Modified Files:
	Options.py 
Log Message:
Couple of small bugs still in Options.py

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.42
retrieving revision 1.43
diff -C2 -d -r1.42 -r1.43
*** Options.py	25 Apr 2003 02:29:16 -0000	1.42
--- Options.py	27 Apr 2003 05:11:40 -0000	1.43
***************
*** 191,195 ****
       BOOLEAN, RESTORE),
  
!     ("safe_headers", "Safe headers", ("abuse-reports-to", "date errors-to",
                                        "from", "importance", "in-reply-to",
                                        "message-id", "mime-version",
--- 191,195 ----
       BOOLEAN, RESTORE),
  
!     ("safe_headers", "Safe headers", ("abuse-reports-to", "date", "errors-to",
                                        "from", "importance", "in-reply-to",
                                        "message-id", "mime-version",
***************
*** 1155,1161 ****
                          # least two, because len==0 and len==1 were dealt
                          # with as special cases
!                         test_str = v0 + sep + v1
                          test_tuple = self._split_values(test_str)
!                         if test_tuple[0] == v0 and test_tuple[1] == v1 and \
                             len(test_tuple) == 2:
                              break
--- 1155,1163 ----
                          # least two, because len==0 and len==1 were dealt
                          # with as special cases
!                         test_str = str(v0) + sep + str(v1)
                          test_tuple = self._split_values(test_str)
!                         print test_tuple, v0, v1
!                         if test_tuple[0] == str(v0) and \
!                            test_tuple[1] == str(v1) and \
                             len(test_tuple) == 2:
                              break



From anadelonbrin at users.sourceforge.net  Sun Apr 27 16:07:19 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 27 18:07:22 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.43,1.44
Message-ID: <E199uIp-0008O1-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv32172/spambayes

Modified Files:
	Options.py 
Log Message:
Removed a debugging line left in Options.py

Fixed the bug that meant that 'tuple' options had to be separated
with a single space instead of an arbitary amount of whitespace,
as reported by Sjoerd Mullender.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.43
retrieving revision 1.44
diff -C2 -d -r1.43 -r1.44
*** Options.py	27 Apr 2003 05:11:40 -0000	1.43
--- Options.py	27 Apr 2003 22:07:16 -0000	1.44
***************
*** 1157,1161 ****
                          test_str = str(v0) + sep + str(v1)
                          test_tuple = self._split_values(test_str)
-                         print test_tuple, v0, v1
                          if test_tuple[0] == str(v0) and \
                             test_tuple[1] == str(v1) and \
--- 1157,1160 ----
***************
*** 1355,1359 ****
                  else:
                      if self.multiple_values_allowed(sect, opt):
!                         value = tuple(value.split(' '))
                      self.set(sect, opt, self.convert(sect, opt, value))
  
--- 1354,1358 ----
                  else:
                      if self.multiple_values_allowed(sect, opt):
!                         value = tuple(value.split())
                      self.set(sect, opt, self.convert(sect, opt, value))
  



From anadelonbrin at users.sourceforge.net  Sun Apr 27 16:33:18 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 27 18:33:23 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.44,1.45
Message-ID: <E199uhy-0002d4-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv10042/spambayes

Modified Files:
	Options.py 
Log Message:
Finished a comment in imapfilter.

Fixed a bug in Options.py that stopped Tim's config file
converting correctly.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.44
retrieving revision 1.45
diff -C2 -d -r1.44 -r1.45
*** Options.py	27 Apr 2003 22:07:16 -0000	1.44
--- Options.py	27 Apr 2003 22:33:13 -0000	1.45
***************
*** 1354,1358 ****
                  else:
                      if self.multiple_values_allowed(sect, opt):
!                         value = tuple(value.split())
                      self.set(sect, opt, self.convert(sect, opt, value))
  
--- 1354,1358 ----
                  else:
                      if self.multiple_values_allowed(sect, opt):
!                         value = self.convert(sect, opt, value)
                      self.set(sect, opt, self.convert(sect, opt, value))
  



From anadelonbrin at users.sourceforge.net  Sun Apr 27 16:33:45 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 27 18:33:48 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.34,1.35
Message-ID: <E199uiP-0002cm-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv10042

Modified Files:
	imapfilter.py 
Log Message:
Finished a comment in imapfilter.

Fixed a bug in Options.py that stopped Tim's config file
converting correctly.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.34
retrieving revision 1.35
diff -C2 -d -r1.34 -r1.35
*** imapfilter.py	25 Apr 2003 04:12:00 -0000	1.34
--- imapfilter.py	27 Apr 2003 22:33:13 -0000	1.35
***************
*** 64,68 ****
        much nicer.
      o IMAP over SSL would be nice.  imaplib in Python 2.3 has an SSL class
!       that we could inherit from
      o Develop a test script, like testtools/pop3proxytest.py that runs
        through some tests (perhaps with a *real* imap server, rather than
--- 64,75 ----
        much nicer.
      o IMAP over SSL would be nice.  imaplib in Python 2.3 has an SSL class
!       that we could inherit from.  This idea would be that SSL is available
!       if the SSL class is available (so those using Python 2.2 can't use
!       imapfilter with SSL, but 2.3ers can).  It's easy enough to do the
!       enabling/disabling of the options (don't forget to wipe it from the
!       UI list), but I'm not quite sure how to handle the inheritance.  We
!       don't actually use the IMAP4 class, we use our own class that inherits
!       from that.  How can we dynamically select which class to inherit from?
!       (This is probably where my lack of Python expertise shows up...)
      o Develop a test script, like testtools/pop3proxytest.py that runs
        through some tests (perhaps with a *real* imap server, rather than



From anadelonbrin at users.sourceforge.net  Sun Apr 27 18:36:06 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 27 20:36:09 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py,1.45,1.46
Message-ID: <E199wco-0005x4-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv22797/spambayes

Modified Files:
	Options.py 
Log Message:
Added a comment to Options.py

Added imapfilter.py to setup.py

Changed smtpproxy, proxytee, notesfilter, hammiefilter and
dbExpImp to use the new Options style.

Fix bug in hammiefilter calling OptionClass.mergefiles instead of
the new (better) name merge_files.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.45
retrieving revision 1.46
diff -C2 -d -r1.45 -r1.46
*** Options.py	27 Apr 2003 22:33:13 -0000	1.45
--- Options.py	28 Apr 2003 00:36:03 -0000	1.46
***************
*** 34,37 ****
--- 34,43 ----
   o str(Option) should really call Option.unconvert since this is what
     it does.  Try putting that in and running all the tests.
+  o Each Option object has a delimiter attribute - this separates out
+    values when the Object can have multiple values and is in string
+    form.  At the moment the only place this is set is in unconvert()
+    where it is set to the first valid character out of a list.  It
+    would be nice if convert() set the delimiter (if it wasn't already)
+    so that Options would keep the one they start with.
   o [See also the __issues__ string.]
   o Suggestions?



From anadelonbrin at users.sourceforge.net  Sun Apr 27 18:36:05 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Sun Apr 27 20:36:14 2003
Subject: [Spambayes-checkins] 
	spambayes dbExpImp.py, 1.6, 1.7 hammiefilter.py,
	1.15, 1.16 notesfilter.py, 1.2, 1.3 proxytee.py, 1.3,
	1.4 setup.py, 1.17, 1.18 smtpproxy.py, 1.6, 1.7
Message-ID: <E199wcn-0005ws-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv22797

Modified Files:
	dbExpImp.py hammiefilter.py notesfilter.py proxytee.py 
	setup.py smtpproxy.py 
Log Message:
Added a comment to Options.py

Added imapfilter.py to setup.py

Changed smtpproxy, proxytee, notesfilter, hammiefilter and
dbExpImp to use the new Options style.

Fix bug in hammiefilter calling OptionClass.mergefiles instead of
the new (better) name merge_files.

Index: dbExpImp.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/dbExpImp.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** dbExpImp.py	11 Mar 2003 13:40:14 -0000	1.6
--- dbExpImp.py	28 Apr 2003 00:36:03 -0000	1.7
***************
*** 256,260 ****
              newDBM = False
          elif opt == '-v':
!             options.verbose = True
  
      if (dbFN and flatFN):
--- 256,260 ----
              newDBM = False
          elif opt == '-v':
!             options["globals", "verbose"] = True
  
      if (dbFN and flatFN):

Index: hammiefilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/hammiefilter.py,v
retrieving revision 1.15
retrieving revision 1.16
diff -C2 -d -r1.15 -r1.16
*** hammiefilter.py	4 Feb 2003 15:57:20 -0000	1.15
--- hammiefilter.py	28 Apr 2003 00:36:03 -0000	1.16
***************
*** 97,105 ****
      def __init__(self):
          options = Options.options
!         options.mergefiles(['/etc/hammierc',
                              os.path.expanduser('~/.hammierc')])
!         self.dbname = options.hammiefilter_persistent_storage_file
          self.dbname = os.path.expanduser(self.dbname)
!         self.usedb = options.hammiefilter_persistent_use_database
  
      def newdb(self):
--- 97,105 ----
      def __init__(self):
          options = Options.options
!         options.merge_files(['/etc/hammierc',
                              os.path.expanduser('~/.hammierc')])
!         self.dbname = options["hammiefilter", "persistent_storage_file"]
          self.dbname = os.path.expanduser(self.dbname)
!         self.usedb = options["hammiefilter", "persistent_use_database"]
  
      def newdb(self):

Index: notesfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/notesfilter.py,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** notesfilter.py	28 Mar 2003 13:57:52 -0000	1.2
--- notesfilter.py	28 Apr 2003 00:36:03 -0000	1.3
***************
*** 197,213 ****
                  # generate_long_skips = True blows up on occasion,
                  # probably due to this unicode problem.
!                 options.generate_long_skips = False
                  tokens = tokenizer.tokenize(message)
                  prob, clues = bayes.spamprob(tokens, evidence=True)
  
!                 if prob < options.ham_cutoff:
!                     disposition = options.header_ham_string
                      numham += 1
!                 elif prob > options.spam_cutoff:
!                     disposition = options.header_spam_string
                      docstomove += [doc]
                      numspam += 1
                  else:
!                     disposition = options.header_unsure_string
                      numuns += 1
  
--- 197,213 ----
                  # generate_long_skips = True blows up on occasion,
                  # probably due to this unicode problem.
!                 options["Tokenizer", "generate_long_skips"] = False
                  tokens = tokenizer.tokenize(message)
                  prob, clues = bayes.spamprob(tokens, evidence=True)
  
!                 if prob < options["Categorization", "ham_cutoff"]:
!                     disposition = options["Hammie", "header_ham_string"]
                      numham += 1
!                 elif prob > options["Categorization", "spam_cutoff"]:
!                     disposition = options["Hammie", "header_spam_string"]
                      docstomove += [doc]
                      numspam += 1
                  else:
!                     disposition = options["Hammie", "header_unsure_string"]
                      numuns += 1
  
***************
*** 235,241 ****
  
      if is_spam:
!         str = options.header_spam_string
      else:
!         str = options.header_ham_string
  
      print "Training %s" % (str)
--- 235,241 ----
  
      if is_spam:
!         str = options["Hammie", "header_spam_string"]
      else:
!         str = options["Hammie", "header_ham_string"]
  
      print "Training %s" % (str)
***************
*** 256,260 ****
          message = "Subject: %s\r\n%s" % (subj, body)
  
!         options.generate_long_skips = False
          tokens = tokenizer.tokenize(message)
  
--- 256,260 ----
          message = "Subject: %s\r\n%s" % (subj, body)
  
!         options["Tokenizer", "generate_long_skips"] = False
          tokens = tokenizer.tokenize(message)
  
***************
*** 262,269 ****
          if notesindex.has_key(nid):
              trainedas = notesindex[nid]
!             if trainedas == options.header_spam_string and not is_spam:
                  # msg is trained as spam, is to be retrained as ham
                  bayes.unlearn(tokens, True)
!             elif trainedas == options.header_ham_string and is_spam:
                  # msg is trained as ham, is to be retrained as spam
                  bayes.unlearn(tokens, False)
--- 262,271 ----
          if notesindex.has_key(nid):
              trainedas = notesindex[nid]
!             if trainedas == options["Hammie", "header_spam_string"] and \
!                not is_spam:
                  # msg is trained as spam, is to be retrained as ham
                  bayes.unlearn(tokens, True)
!             elif trainedas == options["Hammie", "header_ham_string"] and \
!                  is_spam:
                  # msg is trained as ham, is to be retrained as spam
                  bayes.unlearn(tokens, False)

Index: proxytee.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/proxytee.py,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** proxytee.py	20 Jan 2003 20:46:18 -0000	1.3
--- proxytee.py	28 Apr 2003 00:36:03 -0000	1.4
***************
*** 92,96 ****
      null = False
      server = "localhost"
!     port = options.html_ui_port
      prob = 1.0
  
--- 92,96 ----
      null = False
      server = "localhost"
!     port = options["html_ui", "port"]
      prob = 1.0
  

Index: setup.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/setup.py,v
retrieving revision 1.17
retrieving revision 1.18
diff -C2 -d -r1.17 -r1.18
*** setup.py	28 Feb 2003 18:08:51 -0000	1.17
--- setup.py	28 Apr 2003 00:36:03 -0000	1.18
***************
*** 42,45 ****
--- 42,46 ----
             'dbExpImp.py',
             'mboxtrain.py',
+            'imapfilter.py',
            ],
          packages = [

Index: smtpproxy.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/smtpproxy.py,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** smtpproxy.py	24 Apr 2003 07:43:45 -0000	1.6
--- smtpproxy.py	28 Apr 2003 00:36:03 -0000	1.7
***************
*** 335,350 ****
      def onRcptTo(self, command, args):
          toHost, toFull = self.splitTo(args[0])
!         if toFull == options.smtpproxy_shutdown_address:
!             self.push("421 Closing on user request\r\n")
!             self.socket.shutdown(2)
!             self.close()
!             raise SystemExit
!             return None
!         elif toFull == options.smtpproxy_spam_address:
              self.train_as_spam = True
              self.blockData = True
              self.push("250 OK\r\n")
              return None
!         elif toFull == options.smtpproxy_ham_address:
              self.train_as_ham = True
              self.blockData = True
--- 335,344 ----
      def onRcptTo(self, command, args):
          toHost, toFull = self.splitTo(args[0])
!         if toFull == options["smtpproxy", "spam_address"]:
              self.train_as_spam = True
              self.blockData = True
              self.push("250 OK\r\n")
              return None
!         elif toFull == options["smtpproxy", "ham_address"]:
              self.train_as_ham = True
              self.blockData = True
***************
*** 391,395 ****
  
          # the nicest MUA is one that forwards the header intact
!         id = msg.get(options.pop3proxy_mailid_header_name)
          if id is not None:
              return id
--- 385,389 ----
  
          # the nicest MUA is one that forwards the header intact
!         id = msg.get(options["pop3proxy", "mailid_header_name"])
          if id is not None:
              return id
***************
*** 416,420 ****
  
      def _find_id_in_text(self, text):
!         id_location = text.find(options.pop3proxy_mailid_header_name)
          if id_location == -1:
              return None
--- 410,414 ----
  
      def _find_id_in_text(self, text):
!         id_location = text.find(options["pop3proxy", "mailid_header_name"])
          if id_location == -1:
              return None
***************
*** 422,426 ****
              # A MUA might enclose the id in a table
              # (Mozilla Mail does this with inline html)
!             s = re.compile(options.pop3proxy_mailid_header_name + \
                             ':[\s]*</th>[\s]*<td>[\s]*')
              if s.search(text[id_location:]) is not None:
--- 416,420 ----
              # A MUA might enclose the id in a table
              # (Mozilla Mail does this with inline html)
!             s = re.compile(options["pop3proxy", "mailid_header_name"] + \
                             ':[\s]*</th>[\s]*<td>[\s]*')
              if s.search(text[id_location:]) is not None:
***************
*** 429,433 ****
                  id_end = s.search(text[id_location:]).end() + id_location
              else:
!                 id_location += len(options.pop3proxy_mailid_header_name) + 2
                  s = re.compile('[\w -]+[\\r]?\\n')
                  id_end = s.search(text[id_location:]).end() + id_location
--- 423,428 ----
                  id_end = s.search(text[id_location:]).end() + id_location
              else:
!                 id_location += len(options["pop3proxy",
!                                            "mailid_header_name"]) + 2
                  s = re.compile('[\w -]+[\\r]?\\n')
                  id_end = s.search(text[id_location:]).end() + id_location
***************
*** 446,450 ****
              print "Could not extract id"
              return
!         if options.verbose:
              if isSpam == True:
                  print "Training %s as spam" % id
--- 441,445 ----
              print "Could not extract id"
              return
!         if options["globals", "verbose"]:
              if isSpam == True:
                  print "Training %s as spam" % id
***************
*** 472,477 ****
      servers = []
      proxyPorts = []
!     if options.smtpproxy_servers:
!         for server in options.smtpproxy_servers:
              server = server.strip()
              if server.find(':') > -1:
--- 467,472 ----
      servers = []
      proxyPorts = []
!     if options["smtpproxy", "servers"]:
!         for server in options["smtpproxy", "servers"]:
              server = server.strip()
              if server.find(':') > -1:
***************
*** 480,485 ****
                  port = '25'
              servers.append((server, int(port)))
!     if options.smtpproxy_ports:
!         splitPorts = options.smtpproxy_ports
          proxyPorts = map(_addressAndPort, splitPorts)
      if len(servers) != len(proxyPorts):
--- 475,480 ----
                  port = '25'
              servers.append((server, int(port)))
!     if options["smtpproxy", "ports"]:
!         splitPorts = options["smtpproxy", "ports"]
          proxyPorts = map(_addressAndPort, splitPorts)
      if len(servers) != len(proxyPorts):



From anadelonbrin at users.sourceforge.net  Sun Apr 27 23:20:50 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Mon Apr 28 01:20:53 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.35,1.36
Message-ID: <E19A14M-0003Ik-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv12655

Modified Files:
	imapfilter.py 
Log Message:
Fix for SelectFolder bug reported by David Abrahams
(str object has no attribute 'name')

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.35
retrieving revision 1.36
diff -C2 -d -r1.35 -r1.36
*** imapfilter.py	27 Apr 2003 22:33:13 -0000	1.35
--- imapfilter.py	28 Apr 2003 05:20:46 -0000	1.36
***************
*** 219,224 ****
      def SelectFolder(self, folder):
          '''A method to point ensuing imap operations at a target folder'''
!         if self.current_folder != folder:
!             if self.current_folder != None:
                  if self.do_expunge:
                      # It is faster to do close() than a single
--- 219,224 ----
      def SelectFolder(self, folder):
          '''A method to point ensuing imap operations at a target folder'''
!         if self.current_folder != None:
!             if self.current_folder != folder:
                  if self.do_expunge:
                      # It is faster to do close() than a single
***************
*** 516,521 ****
  
          # Select the spam folder and unsure folder to make sure they exist
!         imap.SelectFolder(self.spam_folder)
!         imap.SelectFolder(self.unsure_folder)
              
          for filter_folder in options["imap", "filter_folders"]:
--- 516,521 ----
  
          # Select the spam folder and unsure folder to make sure they exist
!         imap.SelectFolder(self.spam_folder.name)
!         imap.SelectFolder(self.unsure_folder.name)
              
          for filter_folder in options["imap", "filter_folders"]:



From anadelonbrin at users.sourceforge.net  Mon Apr 28 01:01:29 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Mon Apr 28 03:01:33 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.21,1.22
Message-ID: <E19A2dl-0002w5-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv11246/spambayes

Modified Files:
	message.py 
Log Message:
Switch from imapfilter using IMAP uids as persistent ids for
messages to our own generated ids.  This code runs on one
server I have, but I don't have time for more testing at the moment.
I'm checking it in since the old code is Bad and this should be
ok....

WARNING: You will need to disguard any hammie.db that you
have trained with imapfilter.py, and also any spambayes.messageinfo.db
files as well.

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.21
retrieving revision 1.22
diff -C2 -d -r1.21 -r1.22
*** message.py	25 Apr 2003 04:12:02 -0000	1.21
--- message.py	28 Apr 2003 07:01:21 -0000	1.22
***************
*** 237,241 ****
          try:
              self.setId(self[options['pop3proxy','mailid_header_name']])
!         except KeyError:
              return None
  
--- 237,241 ----
          try:
              self.setId(self[options['pop3proxy','mailid_header_name']])
!         except ValueError:
              return None
  



From anadelonbrin at users.sourceforge.net  Mon Apr 28 01:01:29 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Mon Apr 28 03:01:37 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.36,1.37
Message-ID: <E19A2dl-0002w4-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv11246

Modified Files:
	imapfilter.py 
Log Message:
Switch from imapfilter using IMAP uids as persistent ids for
messages to our own generated ids.  This code runs on one
server I have, but I don't have time for more testing at the moment.
I'm checking it in since the old code is Bad and this should be
ok....

WARNING: You will need to disguard any hammie.db that you
have trained with imapfilter.py, and also any spambayes.messageinfo.db
files as well.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.36
retrieving revision 1.37
diff -C2 -d -r1.36 -r1.37
*** imapfilter.py	28 Apr 2003 05:20:46 -0000	1.36
--- imapfilter.py	28 Apr 2003 07:01:20 -0000	1.37
***************
*** 93,96 ****
--- 93,101 ----
        This might help if the username/password has special characters like
        accented characters.
+     o The code currently FETCHes the whole RFC822 message in training, even
+       if it will subsequently decide that the message has already been
+       trained (it won't then train on it, it just throws the message away).
+       This is really inefficient, and a better solution needs to be
+       developed.
      o Suggestions?
  """
***************
*** 191,196 ****
      def __init__(self, server, port, debug=0, do_expunge=False):
          imaplib.Debug = debug  # this is a global in the imaplib module
!         imaplib.IMAP4.__init__(self, server, port)
!         # XXX We should check here to see if the server/port were valid
          # For efficiency, we remember which folder we are currently
          # in, and only send a select command to the IMAP server if
--- 196,208 ----
      def __init__(self, server, port, debug=0, do_expunge=False):
          imaplib.Debug = debug  # this is a global in the imaplib module
!         try:
!             imaplib.IMAP4.__init__(self, server, port)
!         except:
!             # A more specific except would be good here, but I get
!             # (in Python 2.2) a generic 'error' and a 'gaierror'
!             # if I pass a valid domain that isn't an IMAP server
!             # or invalid domain (respectively)
!             print "Invalid server or port, please check these settings."
!             sys.exit(-1)
          # For efficiency, we remember which folder we are currently
          # in, and only send a select command to the IMAP server if
***************
*** 200,206 ****
          self.do_expunge = do_expunge
  
!     def login(self, uid, pw):
          try:
!             imaplib.IMAP4.login(self, uid, pw)  # superclass login
          except imaplib.IMAP4.error, e:
              if str(e) == "permission denied":
--- 212,218 ----
          self.do_expunge = do_expunge
  
!     def login(self, username, pwd):
          try:
!             imaplib.IMAP4.login(self, username, pwd)  # superclass login
          except imaplib.IMAP4.error, e:
              if str(e) == "permission denied":
***************
*** 219,224 ****
      def SelectFolder(self, folder):
          '''A method to point ensuing imap operations at a target folder'''
!         if self.current_folder != None:
!             if self.current_folder != folder:
                  if self.do_expunge:
                      # It is faster to do close() than a single
--- 231,236 ----
      def SelectFolder(self, folder):
          '''A method to point ensuing imap operations at a target folder'''
!         if self.current_folder != folder:
!             if self.current_folder != None:
                  if self.do_expunge:
                      # It is faster to do close() than a single
***************
*** 252,257 ****
  
      def _force_CRLF(self, data):
!         """Make sure data uses CRLF for line termination.
!         """
          return CRLF_RE.sub('\r\n', data)
  
--- 264,268 ----
  
      def _force_CRLF(self, data):
!         """Make sure data uses CRLF for line termination."""
          return CRLF_RE.sub('\r\n', data)
  
***************
*** 266,271 ****
      def extractTime(self):
          # When we create a new copy of a message, we need to specify
!         # a timestamp for the message.  If the message has a date header
!         # we use that.  Otherwise, we use the current time.
          message_date = self["Date"]
          if message_date is not None:
--- 277,282 ----
      def extractTime(self):
          # When we create a new copy of a message, we need to specify
!         # a timestamp for the message.  If the message has a valid date
!         # header we use that.  Otherwise, we use the current time.
          message_date = self["Date"]
          if message_date is not None:
***************
*** 278,288 ****
      def MoveTo(self, dest):
          '''Note that message should move to another folder.  No move is
!         carried out until Save() is called.'''
!         # This move operation just changes where we think we are,
!         # and we do an actual move on save (to avoid doing
!         # this more than once)
          if self.previous_folder is None:
              self.previous_folder = self.folder
!             self.folder = dest
  
      def Save(self):
--- 289,296 ----
      def MoveTo(self, dest):
          '''Note that message should move to another folder.  No move is
!         carried out until Save() is called, for efficiency.'''
          if self.previous_folder is None:
              self.previous_folder = self.folder
!         self.folder = dest
  
      def Save(self):
***************
*** 290,294 ****
          # we can't actually update the message with IMAP
          # so what we do is create a new message and delete the old one
-         # we need to copy the flags as well
          if self.folder is None:
              raise RuntimeError, """Can't save a message that doesn't
--- 298,301 ----
***************
*** 297,301 ****
              raise RuntimeError, """Can't save a message that doesn't have
              an id."""
!         response = imap.uid("FETCH", self.id, "(FLAGS INTERNALDATE)")
          self._check(response, 'fetch (flags internaldate)')
          data = _extract_fetch_data(response[1][0])
--- 304,308 ----
              raise RuntimeError, """Can't save a message that doesn't have
              an id."""
!         response = imap.uid("FETCH", self.uid, "(FLAGS INTERNALDATE)")
          self._check(response, 'fetch (flags internaldate)')
          data = _extract_fetch_data(response[1][0])
***************
*** 312,318 ****
              flags = None
  
!         # See searching for new uid comments below
!         old_id = self.id
!         self["X-Spambayes-IMAP-OldID"] = old_id
  
          response = imap.append(self.folder.name, flags,
--- 319,328 ----
              flags = None
  
!         # Once, we used the IMAP uid to keep track of messages.
!         # This fails miserably because it's only guarenteed to be unique
!         # within a particular folder.  Folders have a UID validity value,
!         # but this can change from session to session.  So we forget this
!         # imap rubbish and use our own id.
!         self[options["pop3proxy", "mailid_header_name"]] = self.id
  
          response = imap.append(self.folder.name, flags,
***************
*** 325,344 ****
              imap.SelectFolder(self.previous_folder.name)
              self.previous_folder = None
!         response = imap.uid("STORE", old_id, "+FLAGS.SILENT", "(\\Deleted)")
          self._check(response, 'store')
  
!         # We need to update the uid, as it will have changed
!         # Searching for the new message is full of problems.  Searching for
!         # the text sends far too much data through the connection, and
!         # doesn't work reliably anyway.  We instead search for a special
!         # header that we add for this explicit purpose.
          imap.SelectFolder(self.folder.name)
!         response = imap.uid("SEARCH", "HEADER", "X-Spambayes-IMAP-OldID",
!                             old_id)
          self._check(response, 'search')
          new_id = response[1][0]
!         # This works with NetMail, but not with Courier.  Very strange,
!         # and needs more examination.  For the moment, if the search
!         # turns up empty, we make the very big assumption that the new
          # message is the last one with a recent flag
          if new_id == "":
--- 335,352 ----
              imap.SelectFolder(self.previous_folder.name)
              self.previous_folder = None
!         response = imap.uid("STORE", self.uid, "+FLAGS.SILENT", "(\\Deleted)")
          self._check(response, 'store')
  
!         # We need to update the uid, as it will have changed.
!         # Although we don't use the UID to keep track of messages, we do
!         # have to use it for IMAP operations.
          imap.SelectFolder(self.folder.name)
!         response = imap.uid("SEARCH", "HEADER",
!                             options["pop3proxy", "mailid_header_name"],
!                             self.id)
          self._check(response, 'search')
          new_id = response[1][0]
!         # Let's hope it doesn't, but, just in case, if the search
!         # turns up empty, we make the assumption that the new
          # message is the last one with a recent flag
          if new_id == "":
***************
*** 348,358 ****
                  ids = new_id.split(' ')
                  new_id = ids[-1]
! 
!         #XXX This code to delete the old message id from the message
!         #XXX info db and manipulate the message id, is a *serious* hack.
!         #XXX There's gotta be a better way to do this.
!         message.msginfoDB._delState(self)
!         self.id = new_id
!         self.modified()
  
  # This performs a similar function to email.message_from_string()
--- 356,360 ----
                  ids = new_id.split(' ')
                  new_id = ids[-1]
!         self.uid = new_id
  
  # This performs a similar function to email.message_from_string()
***************
*** 362,368 ****
  
  class IMAPFolder(object):
!     def __init__(self, folder_name, readOnly=True):
          self.name = folder_name
          self.rfc822_command = "RFC822.PEEK"
  
      def __cmp__(self, obj):
--- 364,373 ----
  
  class IMAPFolder(object):
!     def __init__(self, folder_name):
          self.name = folder_name
          self.rfc822_command = "RFC822.PEEK"
+         # Unique names for cached messages - see _generate_id below.
+         self.lastBaseMessageName = ''
+         self.uniquifier = 2
  
      def __cmp__(self, obj):
***************
*** 385,389 ****
                  pass
  
!     def recent_keys(self):
          '''Returns uids for all the messages in the folder that
          are flagged as recent, but not flagged as deleted.'''
--- 390,394 ----
                  pass
  
!     def recent_uids(self):
          '''Returns uids for all the messages in the folder that
          are flagged as recent, but not flagged as deleted.'''
***************
*** 394,400 ****
  
      def keys(self):
!         '''Returns uids for all the messages in the folder not
          marked as deleted.'''
-         # request message range
          imap.SelectFolder(self.name)
          response = imap.uid("SEARCH", "UNDELETED")
--- 399,404 ----
  
      def keys(self):
!         '''Returns *uids* for all the messages in the folder not
          marked as deleted.'''
          imap.SelectFolder(self.name)
          response = imap.uid("SEARCH", "UNDELETED")
***************
*** 421,429 ****
          # raw rfc822 message
          msg = imapmessage_from_string(messageText)
-         msg.setId(key)
          msg.setFolder(self)
          
          return msg
!    
      def Train(self, classifier, isSpam):
          '''Train folder as spam/ham'''
--- 425,453 ----
          # raw rfc822 message
          msg = imapmessage_from_string(messageText)
          msg.setFolder(self)
+         msg.uid = data["UID"]
+         if msg.setIdFromPayload() is None:
+             msg.setId(self._generate_id())
+             # Unfortunately, we now have to re-save this message, so that
+             # our id is stored on the IMAP server.  Before anyone suggests
+             # it, we can't store it as a flag, because user-defined flags
+             # aren't supported by all IMAP servers.
+             msg.Save()
          
          return msg
! 
!     # Lifted straight from pop3proxy.py (under the name getNewMessageName)
!     def _generate_id(self):
!         # The message id is the time it arrived, with a uniquifier
!         # appended if two arrive within one clock tick of each other.
!         messageName = "%10.10d" % long(time.time())
!         if messageName == self.lastBaseMessageName:
!             messageName = "%s-%d" % (messageName, self.uniquifier)
!             self.uniquifier += 1
!         else:
!             self.lastBaseMessageName = messageName
!             self.uniquifier = 2
!         return messageName
! 
      def Train(self, classifier, isSpam):
          '''Train folder as spam/ham'''
***************
*** 522,526 ****
              # Select the folder to make sure it exists
              imap.SelectFolder(filter_folder)
!             folder = IMAPFolder(filter_folder, False)
              folder.Filter(self.classifier, self.spam_folder,
                            self.unsure_folder)
--- 546,550 ----
              # Select the folder to make sure it exists
              imap.SelectFolder(filter_folder)
!             folder = IMAPFolder(filter_folder)
              folder.Filter(self.classifier, self.spam_folder,
                            self.unsure_folder)



From timstone4 at users.sourceforge.net  Mon Apr 28 08:07:22 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 28 10:07:25 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.37,1.38
Message-ID: <E19A9Hu-0007uI-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv30301

Modified Files:
	imapfilter.py 
Log Message:
Create imap session object each time a login occurs, because of an apparent
bug that disallows login on a logged out session.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.37
retrieving revision 1.38
diff -C2 -d -r1.37 -r1.38
*** imapfilter.py	28 Apr 2003 07:01:20 -0000	1.37
--- imapfilter.py	28 Apr 2003 14:07:18 -0000	1.38
***************
*** 662,667 ****
          Dibbler.run(launchBrowser=launchUI)
      else:
-         imap = IMAPSession(server, port, imapDebug, doExpunge)
          while True:
              imap.login(username, pwd)
  
--- 662,667 ----
          Dibbler.run(launchBrowser=launchUI)
      else:
          while True:
+             imap = IMAPSession(server, port, imapDebug, doExpunge)
              imap.login(username, pwd)
  



From anadelonbrin at users.sourceforge.net  Mon Apr 28 17:36:27 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Mon Apr 28 19:36:29 2003
Subject: [Spambayes-checkins] spambayes/spambayes Options.py, 1.46,
	1.47 UserInterface.py, 1.7, 1.8
Message-ID: <E19AIAd-0005Bm-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv19897/spambayes

Modified Files:
	Options.py UserInterface.py 
Log Message:
Fix for [ spambayes-Bugs-728886 ] In the pop3 UI not able
to pass more than 1 server

Fix for incorrect is_boolean code for Python 2.3 as reported by
Sjoerd Mullender.

Index: Options.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/Options.py,v
retrieving revision 1.46
retrieving revision 1.47
diff -C2 -d -r1.46 -r1.47
*** Options.py	28 Apr 2003 00:36:03 -0000	1.46
--- Options.py	28 Apr 2003 23:36:24 -0000	1.47
***************
*** 1189,1193 ****
          # So, just for the 2.2 people, we have this helper function
          try:
!             if type(self.allowed_values) == types.BooleanType:
                  return True
              return False
--- 1189,1195 ----
          # So, just for the 2.2 people, we have this helper function
          try:
!             if type(self.allowed_values) == types.TupleType and \
!                len(self.allowed_values) > 0 and \
!                type(self.allowed_values[0]) == types.BooleanType:
                  return True
              return False

Index: UserInterface.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/UserInterface.py,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** UserInterface.py	25 Apr 2003 02:29:16 -0000	1.7
--- UserInterface.py	28 Apr 2003 23:36:24 -0000	1.8
***************
*** 570,579 ****
                      elif value == "Yes":
                          value = True
!                 if options.multiple_values_allowed(sect, opt):
!                     if value == "":
                          value = ()
-                     else:
-                         if type(value) != types.TupleType:
-                             value = (value,)
                  value = options.convert(sect, opt, value)
              if not options.is_valid(sect, opt, value):
--- 570,576 ----
                      elif value == "Yes":
                          value = True
!                 if options.multiple_values_allowed(sect, opt) and \
!                    value == "":
                          value = ()
                  value = options.convert(sect, opt, value)
              if not options.is_valid(sect, opt, value):



From anadelonbrin at users.sourceforge.net  Mon Apr 28 19:01:50 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Mon Apr 28 21:01:56 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.38,1.39
Message-ID: <E19AJVG-00047P-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv15780

Modified Files:
	imapfilter.py 
Log Message:
Instead of retrieving the whole RFC822 message when we
iterate through a folder, just get the RFC822 headers, which
we can use to determine whether the message has been
trained or not.  This *might* fix the problem where messages
are being ignored on filtering.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.38
retrieving revision 1.39
diff -C2 -d -r1.38 -r1.39
*** imapfilter.py	28 Apr 2003 14:07:18 -0000	1.38
--- imapfilter.py	29 Apr 2003 01:01:42 -0000	1.39
***************
*** 76,89 ****
        a dummy one).  This would make it easier to carry out the tests
        against each server whenever a change is made.
-     o The RFC says that "unique identifiers persist across sessions", but
-       also that "[i]f unique identifiers from an earlier session fail to
-       persist to this session...".  This strikes me as fairly inconsistent.
-       If the uid does not persist, then we will end up re-training/filtering
-       the message, but I'm not sure what can be done about that.  There is
-       mention of the UID validity value, which each folder has.  If the uids
-       fail to persist, then this value will increase.  The RFC doesn't say
-       if this is the *only* time it will increase, though.  I'm not sure
-       if this value is of any use to us or not; it's worth keeping in mind,
-       though.
      o IMAP supports authentication via other methods than the plain-text
        password method that we are using at the moment.  Neither of the
--- 76,79 ----
***************
*** 93,101 ****
        This might help if the username/password has special characters like
        accented characters.
-     o The code currently FETCHes the whole RFC822 message in training, even
-       if it will subsequently decide that the message has already been
-       trained (it won't then train on it, it just throws the message away).
-       This is really inefficient, and a better solution needs to be
-       developed.
      o Suggestions?
  """
--- 83,86 ----
***************
*** 125,128 ****
--- 110,114 ----
  import types
  import email
+ import email.Parser
  from getpass import getpass
  from email.Utils import parsedate
***************
*** 153,156 ****
--- 139,143 ----
                               r"[\+\-]\d{4,4}\")")
  RFC822_RE = re.compile(r"(RFC822) (\{[\d]+\})")
+ RFC822_HEADER_RE = re.compile(r"(RFC822.HEADER) (\{[\d]+\})")
  UID_RE = re.compile(r"(UID) ([\d]+)")
  FETCH_RESPONSE_RE = re.compile(r"([0-9]+) \(([" + \
***************
*** 160,164 ****
  def _extract_fetch_data(response):
      '''Extract data from the response given to an IMAP FETCH command.'''
!     # response might be a tuple containing literal data
      if type(response) == types.TupleType:
          literal = response[1]
--- 147,154 ----
  def _extract_fetch_data(response):
      '''Extract data from the response given to an IMAP FETCH command.'''
!     # Response might be a tuple containing literal data
!     # At the moment, we only handle one literal per response.  This
!     # may need to be improved if our code ever asks for something
!     # more complicated (like RFC822.Header and RFC822.Body)
      if type(response) == types.TupleType:
          literal = response[1]
***************
*** 181,186 ****
      #  RFC822
      #  UID
      # All others are ignored.
!     for r in [FLAGS_RE, INTERNALDATE_RE, RFC822_RE, UID_RE]:
          mo = r.search(response)
          if mo is not None:
--- 171,178 ----
      #  RFC822
      #  UID
+     #  RFC822.HEADER
      # All others are ignored.
!     for r in [FLAGS_RE, INTERNALDATE_RE, RFC822_RE, UID_RE,
!               RFC822_HEADER_RE]:
          mo = r.search(response)
          if mo is not None:
***************
*** 254,257 ****
--- 246,251 ----
          self.folder = None
          self.previous_folder = None
+         self.rfc822_command = "RFC822.PEEK"
+         self.got_substance = False
  
      def setFolder(self, folder):
***************
*** 287,290 ****
--- 281,318 ----
              return imaplib.Time2Internaldate(time.time())
  
+     def get_substance(self):
+         '''Retrieve the RFC822 message from the IMAP server and set as the
+         substance of this message.'''
+         if self.got_substance:
+             return
+         if self.uid is None or self.id is None:
+             print "Cannot get substance of message without an id and an UID"
+             return
+         imap.SelectFolder(self.folder.name)
+         # We really want to use RFC822.PEEK here, as that doesn't effect
+         # the status of the message.  Unfortunately, it appears that not
+         # all IMAP servers support this, even though it is in RFC1730
+         response = imap.uid("FETCH", self.uid, self.rfc822_command)
+         if response[0] != "OK":
+             self.rfc822_command = "RFC822"
+             response = imap.uid("FETCH", self.uid, self.rfc822_command)
+         self._check(response, "uid fetch")
+         data = _extract_fetch_data(response[1][0])
+         # Annoyingly, we can't just pass over the RFC822 message to an
+         # existing message object (like self) and have it parse it. So
+         # we go through the hoops of creating a new message, and then
+         # copying over all its internals.
+         new_msg = email.Parser.Parser().parsestr(data["RFC822"])
+         self._headers = new_msg._headers
+         self._unixfrom = new_msg._unixfrom
+         self._payload = new_msg._payload
+         self._charset = new_msg._charset
+         self.preamble = new_msg.preamble
+         self.epilogue = new_msg.epilogue
+         self._default_type = new_msg._default_type
+         if not self.has_key(options["pop3proxy", "mailid_header_name"]):
+             self[options["pop3proxy", "mailid_header_name"]] = self.id
+         self.got_substance = True
+ 
      def MoveTo(self, dest):
          '''Note that message should move to another folder.  No move is
***************
*** 319,329 ****
              flags = None
  
-         # Once, we used the IMAP uid to keep track of messages.
-         # This fails miserably because it's only guarenteed to be unique
-         # within a particular folder.  Folders have a UID validity value,
-         # but this can change from session to session.  So we forget this
-         # imap rubbish and use our own id.
-         self[options["pop3proxy", "mailid_header_name"]] = self.id
- 
          response = imap.append(self.folder.name, flags,
                                 msg_time, self.as_string())
--- 347,350 ----
***************
*** 342,348 ****
          # have to use it for IMAP operations.
          imap.SelectFolder(self.folder.name)
!         response = imap.uid("SEARCH", "HEADER",
!                             options["pop3proxy", "mailid_header_name"],
!                             self.id)
          self._check(response, 'search')
          new_id = response[1][0]
--- 363,369 ----
          # have to use it for IMAP operations.
          imap.SelectFolder(self.folder.name)
!         response = imap.uid("SEARCH", "(UNDELETED HEADER " + \
!                             options["pop3proxy", "mailid_header_name"] + \
!                             " " + self.id + ")")
          self._check(response, 'search')
          new_id = response[1][0]
***************
*** 366,370 ****
      def __init__(self, folder_name):
          self.name = folder_name
-         self.rfc822_command = "RFC822.PEEK"
          # Unique names for cached messages - see _generate_id below.
          self.lastBaseMessageName = ''
--- 387,390 ----
***************
*** 409,431 ****
  
      def __getitem__(self, key):
!         '''Return message matching the given uid'''
          imap.SelectFolder(self.name)
!         # We really want to use RFC822.PEEK here, as that doesn't effect
!         # the status of the message.  Unfortunately, it appears that not
!         # all IMAP servers support this, even though it is in RFC1730
!         response = imap.uid("FETCH", key, self.rfc822_command)
!         if response[0] != "OK":
!             self.rfc822_command = "RFC822"
!             response = imap.uid("FETCH", key, self.rfc822_command)
!         self._check(response, "uid fetch")
          data = _extract_fetch_data(response[1][0])
-         messageText = data["RFC822"]
  
!         # we return an instance of *our* message class, not the
!         # raw rfc822 message
!         msg = imapmessage_from_string(messageText)
          msg.setFolder(self)
!         msg.uid = data["UID"]
!         if msg.setIdFromPayload() is None:
              msg.setId(self._generate_id())
              # Unfortunately, we now have to re-save this message, so that
--- 429,450 ----
  
      def __getitem__(self, key):
!         '''Return message (no substance) matching the given uid.'''
!         # We don't retrieve the substances of the message here - you need
!         # to call msg.get_substance() to do that.
          imap.SelectFolder(self.name)
!         # Using RFC822.HEADER.LINES would be better here, but it seems
!         # that not all servers accept it, even though it is in the RFC
!         response = imap.uid("FETCH", key, "RFC822.HEADER")
!         self._check(response, "uid fetch header lines")
          data = _extract_fetch_data(response[1][0])
  
!         msg = IMAPMessage()
          msg.setFolder(self)
!         msg.uid = key
!         r = re.compile(re.escape(options["pop3proxy",
!                                          "mailid_header_name"]) + \
!                        "\:\s*(\d+(\-\d)?)")
!         mo = r.search(data["RFC822.HEADER"])
!         if mo is None:
              msg.setId(self._generate_id())
              # Unfortunately, we now have to re-save this message, so that
***************
*** 433,437 ****
--- 452,460 ----
              # it, we can't store it as a flag, because user-defined flags
              # aren't supported by all IMAP servers.
+             # This will need to be done once per message.
+             msg.get_substance()
              msg.Save()
+         else:
+             msg.setId(mo.group(1))
          
          return msg
***************
*** 455,458 ****
--- 478,482 ----
          for msg in self:
              if msg.GetTrained() == (not isSpam):
+                 msg.get_substance()
                  classifier.unlearn(msg.asTokens(), not isSpam)
                  # Once the message has been untrained, it's training memory
***************
*** 463,466 ****
--- 487,491 ----
  
              if msg.GetTrained() is None:
+                 msg.get_substance()
                  classifier.learn(msg.asTokens(), isSpam)
                  num_trained += 1
***************
*** 472,475 ****
--- 497,501 ----
          for msg in self:
              if msg.GetClassification() is None:
+                 msg.get_substance()
                  (prob, clues) = classifier.spamprob(msg.asTokens(),
                                                      evidence=True)



From timstone4 at users.sourceforge.net  Mon Apr 28 21:56:46 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 28 23:56:56 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.22,1.23
Message-ID: <E19AMEY-0000wW-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv3577

Modified Files:
	message.py 
Log Message:
moved force_crlf for rfc822 compliance back into message class, because
it is needed for pop3proxy, and presumably any other proxy or filter that uses
the message class.

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.22
retrieving revision 1.23
diff -C2 -d -r1.22 -r1.23
*** message.py	28 Apr 2003 07:01:21 -0000	1.22
--- message.py	29 Apr 2003 03:56:43 -0000	1.23
***************
*** 179,182 ****
--- 179,194 ----
          return tokenize(self.as_string())
  
+     def _force_CRLF(self, data):
+         """Make sure data uses CRLF for line termination."""
+         return CRLF_RE.sub('\r\n', data)
+ 
+     def as_string(self):
+         # The email package stores line endings in the "internal" Python
+         # format ('\n').  It is up to whoever transmits that information to
+         # convert to appropriate line endings (according to RFC822, that is
+         # \r\n *only*).  imaplib *should* take care of this for us (in the
+         # append function), but does not, so we do it here
+         return self._force_CRLF(message.SBHeaderMessage.as_string(self))
+         
      def modified(self):
          if self.id:    # only persist if key is present



From timstone4 at users.sourceforge.net  Mon Apr 28 21:57:28 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 28 23:57:38 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.39,1.40
Message-ID: <E19AMFE-00016P-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv4197

Modified Files:
	imapfilter.py 
Log Message:
removed force_crlf from imapmessage class, moved to message base class
for rfc822 compliance back into message class, because it is needed for
pop3proxy, and presumably any other proxy or filter that uses the message 
class.

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.39
retrieving revision 1.40
diff -C2 -d -r1.39 -r1.40
*** imapfilter.py	29 Apr 2003 01:01:42 -0000	1.39
--- imapfilter.py	29 Apr 2003 03:57:25 -0000	1.40
***************
*** 257,272 ****
              sys.exit(-1)
  
-     def _force_CRLF(self, data):
-         """Make sure data uses CRLF for line termination."""
-         return CRLF_RE.sub('\r\n', data)
- 
-     def as_string(self):
-         # The email package stores line endings in the "internal" Python
-         # format ('\n').  It is up to whoever transmits that information to
-         # convert to appropriate line endings (according to RFC822, that is
-         # \r\n *only*).  imaplib *should* take care of this for us (in the
-         # append function), but does not, so we do it here
-         return self._force_CRLF(message.SBHeaderMessage.as_string(self))
-         
      def extractTime(self):
          # When we create a new copy of a message, we need to specify
--- 257,260 ----



From timstone4 at users.sourceforge.net  Mon Apr 28 21:58:54 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 28 23:59:01 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.23,1.24
Message-ID: <E19AMGc-0001MY-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv5206

Modified Files:
	message.py 
Log Message:
oops... forgot to move the regex

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.23
retrieving revision 1.24
diff -C2 -d -r1.23 -r1.24
*** message.py	29 Apr 2003 03:56:43 -0000	1.23
--- message.py	29 Apr 2003 03:58:51 -0000	1.24
***************
*** 104,107 ****
--- 104,109 ----
  import shelve
  
+ CRLF_RE = re.compile(r'\r\n|\r|\n')
+ 
  class MessageInfoDB:
      def __init__(self, db_name, mode='c'):



From timstone4 at users.sourceforge.net  Mon Apr 28 21:59:06 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Mon Apr 28 23:59:10 2003
Subject: [Spambayes-checkins] spambayes imapfilter.py,1.40,1.41
Message-ID: <E19AMGo-0001PI-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv5374

Modified Files:
	imapfilter.py 
Log Message:
oops... forgot to move the regex

Index: imapfilter.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/imapfilter.py,v
retrieving revision 1.40
retrieving revision 1.41
diff -C2 -d -r1.40 -r1.41
*** imapfilter.py	29 Apr 2003 03:57:25 -0000	1.40
--- imapfilter.py	29 Apr 2003 03:59:04 -0000	1.41
***************
*** 123,128 ****
  imap = None
  
- CRLF_RE = re.compile(r'\r\n|\r|\n')
- 
  # A flag can have any character in the ascii range 32-126
  # except for (){ %*"\
--- 123,126 ----



From timstone4 at users.sourceforge.net  Tue Apr 29 07:46:21 2003
From: timstone4 at users.sourceforge.net (Tim Stone)
Date: Tue Apr 29 09:46:25 2003
Subject: [Spambayes-checkins] spambayes/spambayes message.py,1.24,1.25
Message-ID: <E19AVR7-0003Zm-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv13721

Modified Files:
	message.py 
Log Message:
corrected module path error

Index: message.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/message.py,v
retrieving revision 1.24
retrieving revision 1.25
diff -C2 -d -r1.24 -r1.25
*** message.py	29 Apr 2003 03:58:51 -0000	1.24
--- message.py	29 Apr 2003 13:46:18 -0000	1.25
***************
*** 191,195 ****
          # \r\n *only*).  imaplib *should* take care of this for us (in the
          # append function), but does not, so we do it here
!         return self._force_CRLF(message.SBHeaderMessage.as_string(self))
          
      def modified(self):
--- 191,195 ----
          # \r\n *only*).  imaplib *should* take care of this for us (in the
          # append function), but does not, so we do it here
!         return self._force_CRLF(email.Message.Message.as_string(self))
          
      def modified(self):



From anadelonbrin at users.sourceforge.net  Wed Apr 30 00:43:31 2003
From: anadelonbrin at users.sourceforge.net (Tony Meyer)
Date: Wed Apr 30 02:44:17 2003
Subject: [Spambayes-checkins] spambayes/testtools urlslurper.py, NONE,
	1.1 timtest.py, 1.3, 1.4
Message-ID: <E19AlJT-0006rX-00@sc8-pr-cvs1.sourceforge.net>

Update of /cvsroot/spambayes/spambayes/testtools
In directory sc8-pr-cvs1:/tmp/cvs-serv26353/testtools

Modified Files:
	timtest.py 
Added Files:
	urlslurper.py 
Log Message:
Fix a comment typo in timtest.py

Add urlslurper.py.  This is a version of timtest.py that will retrieve
text from (http) urls included in messages, if the message doesn't
have enough clues to classify it as ham/spam.  This is a standalone
module and does not require modification of any other modules.

To test, run urlsluper.py and compare the output to output from timtest.py.
The docstring has more information.

--- NEW FILE: urlslurper.py ---
#!/usr/bin/env python

"""Concept based on Richard Jowsey's URLSlurper.java

SlurpingClassifier is a class that extends Classifier to (in some cases)
also retrieve text from (http) urls contained in messages and use that
to augment the probability calculation.

*** At the moment, this script is designed as a special instance of timtest.
(Command line arguments (like -n) are passed through to timtest).
Executing the script has the same effect as executing timtest, except that
the SlurpingClassifier class is used instead of Classifier.  This should
make testing this concept reasonably easy, without modifying the tokeniser,
classifier, or anything else.  To actually integrate this code, you would
need to replace use of the Classifier class with the SlurpingClassifier
class, and also call urlslurper.setup() if you need to set up caching or
a proxy.  If this was to be permanently added as an option, then this
information could be stored in Options.py, and this step would be
unnecessary.***

We retrieve as many urls from the message as we can find, subject to a
user-defined time limit.  Note that this time limit doesn't get checked
in the middle of retrieving a URL, so if one take a long time to get
(perhaps it times out), we might go well over the time limit.

We only slurp if:
  o The original probability is in our unsure range.
  o There were less than 'max_discriminators' clues in the original.
  o We can get some text back from the link (it hasn't timed out, for
    example).
  o The score of the retrieved text is outside our unsure range.

If the global only_slurp_base is True, then each url gets converted to its
'base' form - i.e. as simple a version as possible.  All directory
information is removed, and the domain is reduced to the two (three for
those with a country TLD) top-most elements.  This should have two
beneficial effects:
  o It's unlikely that any information could be contained in this 'base'
    url that could identify the user (unless they have a *lot* of domains).
  o Many urls (both spam and ham) will strip down into the same 'base' url.
    Since we have a limited form of caching, this means that a lot fewer
    urls will have to be retrieved.
However, this does mean that if the 'base' url is hammy and the full is
spammy, or vice-versa, that the slurp will give back the wrong information.
Whether or not this is the case would have to be determined by testing.
This defaults to False; you can set it to true with via the command line:
        -b                      Reduce URLs to simple ('base') form.

If you need to connect via an [authenicating] proxy, you can pass values
via the command line:
        -u username             Proxy username
        -p password             Proxy password
        -a host                 Address for proxy (e.g. proxy.example.com)
        -o proxy port           Port for proxy (probably 8080 or 80)

To speed things up, the result from slurping a url is cached in a pickle,
and referred to where possible.  This defaults to the file "url.pck" in
the local directory, but you can specify your own file via the command line:
        -f filename             URL cache filename

Notes:
 o There are lots of ways to get around this working.  If the site has a
   robots.txt file that excludes all robots, or all urllib robots, then
   this will fail.  If the page is just an html frame with no content,
   then this will fail.  And so on...
 o Training is only carried out on the message itself - no slurping is
   done.  This is probably as it should be.
 o At the moment, the score from classifying the webpage is averaged
   with the score from classifying the message.  It would be interesting
   to see if:
     (a) Replacing the message score with the webpage score, or
     (b) Rescoring with the message tokens and the webpage tokens
   would give better results.  (Note that with (b), the caching would not
   work, unless we cached all the tokens, not just the probs).
"""

# This module is part of the spambayes project, which is Copyright 2002-3
# The Python Software Foundation and is covered by the Python Software
# Foundation license.

__author__ = "Tony Meyer <ta-meyer@ihug.co.nz>"
__credits__ = "Richard Jowsey, all the Spambayes folk."

from __future__ import generators

import urllib2
import sys
import re
import pickle
import os
import time

sys.path.insert(-1, os.getcwd())
sys.path.insert(-1, os.path.dirname(os.getcwd()))

from email import message_from_string
from spambayes.tokenizer import Tokenizer
from spambayes import storage
from spambayes.Options import options
from spambayes.classifier import Classifier, Bayes
from testtools import timtest
import spambayes

global cache_filename
cache_filename = "url.pck"

global proxy_info
proxy_info = {}
# Fill in the details here (and uncomment these lines) if you connect via
# a proxy and don't want to enter the details via the command line.
#proxy_info = {
#    'user' : 'username',
#    'pass' : 'password',
#    'host' : "domain name",
#    'port' : 8080  # 8080 or 80, probably
#}

global only_slurp_base
only_slurp_base = False
global url_dict
url_dict = {}

def body_tokens(msg):
    tokens = Tokenizer().tokenize_body(msg)
    for tok in tokens:
        yield tok

HTTP_RE = re.compile(r"http\://[\@\w.:~\\/\-\?\+\=]+[\w]")

class SlurpingClassifier(Classifier):
    def __init__(self):
        Classifier.__init__(self)

    def spamprob(self, wordstream, evidence=False, time_limit=None):
        global url_dict
        start_time = time.time()
        prob, clues = Classifier.spamprob(self, wordstream, True)
        if len(clues) < options["Classifier", "max_discriminators"] and \
           prob > options["Categorization", "ham_cutoff"] and \
           prob < options["Categorization", "spam_cutoff"] and \
           (time_limit is None or time.time() - start_time < time_limit):
            urls = HTTP_RE.findall(wordstream.guts)
            urlprob = 0.0
            urlclues = []
            number_urls = 0
            for url in urls:
                if only_slurp_base:
                    # to try and speed things up, and to avoid following
                    # unique URLS, we convert the url to as basic a form
                    # as we can - so http://www.massey.ac.nz/~tameyer/index.html
                    # would become http://massey.ac.nz and http://id.example.com
                    # would become http://example.com
                    url = url + '/'
                    scheme, empty, domain, garbage = url.split('/', 3)
                    parts = domain.split('.')
                    if len(parts) > 2:
                        base_domain = parts[-2] + '.' + parts[-1]
                        if len(parts[-1]) < 3:
                            base_domain = parts[-3] + '.' + base_domain
                    else:
                        base_domain = domain
                    url = scheme + "//" + base_domain
                tokens = None
                if url_dict.has_key(url):
                    urlprob += url_dict[url]
                    number_urls += 1
                else:
                    if options["globals", "verbose"]:
                        print "Slurping:", url, "..."
                    try:
                        f = urllib2.urlopen(url)
                        page = f.read()
                        f.close()
                        headers = str(f.headers)
                        page = headers + "\r\n" + page
                        if options["globals", "verbose"]:
                            print "Slurped."
                    except IOError:
                        url_dict[url] = 0.5
                        print "Couldn't get", url
                    if not url_dict.has_key(url) or url_dict[url] != 0.5:
                        # Create a fake Message object since Tokenizer is
                        # designed to deal with them.
                        msg = message_from_string(page)
                        # Although we have a message object with headers
                        # (kindly provided by urllib2), the headers won't
                        # match those that we have trained against (unless
                        # we start training with slurping as well), so
                        # we only tokenise the *body*.
                        uprob = Classifier.spamprob(self, body_tokens(msg))
                        urlprob += uprob
                        number_urls += 1
                        url_dict[url] = uprob
            if number_urls > 0 and \
               (urlprob < options["Categorization", "ham_cutoff"] or \
                urlprob > options["Categorization", "spam_cutoff"]):
                prob = (prob + (urlprob / number_urls)) / 2
        # Save the url dict so we don't continually slurp the same urls
        # The problem here, of course, is that we save the probability that
        # the current database gives us.  If we do more/different training
        # later, this probability might not still be accurate.  We should
        # either:
        #   (a) Not do any caching,
        #   (b) Cache the tokens (needs lots of space!) not the prob, or
        #   (c) Tag the probability with a date, and after x time has
        #       passed, expire old probabilities.
        f = file(cache_filename, "w")
        pickle.dump(url_dict, f)
        f.close()
        if evidence:
            return prob, clues
        return prob

def setup(proxy={}, filename=None):
    if len(proxy) > 0:
        # build a new opener that uses a proxy requiring authorization
        proxy_support = urllib2.ProxyHandler({"http" :
                        "http://%(user)s:%(pass)s@%(host)s:%(port)d" % proxy})
        opener = urllib2.build_opener(proxy_support, urllib2.HTTPHandler)
    else:
        # Build a new opener without any proxy information.
        opener = urllib2.build_opener(urllib2.HTTPHandler)
     
    # install it
    urllib2.install_opener(opener)

    # read any url cache    
    if os.path.exists(filename):
        f = file(filename, "r")
        url_dict = pickle.load(f)
        f.close()

 
if __name__ == "__main__":
    import getopt
    from spambayes import msgs

    try:
        opts, args = getopt.getopt(sys.argv[1:], 'hbu:p:a:o:f:n:s:',
                                   ['ham-keep=', 'spam-keep='])
    except getopt.error, msg:
        print >>sys.stderr, __doc__
        sys.exit()

    nsets = seed = hamkeep = spamkeep = None
    for opt, arg in opts:
        if opt == '-h':
            print >>sys.stderr, __doc__
            sys.exit()
        elif opt == '-u':
            global proxy_info
            proxy_info["user"] = arg
        elif opt == '-p':
            global proxy_info
            proxy_info["pass"] = arg
        elif opt == '-a':
            global proxy_info
            proxy_info["host"] = arg
        elif opt == '-o':
            global proxy_info
            proxy_info["port"] = int(arg)
        elif opt == '-f':
            global cache_filename
            cache_filename = arg
        elif opt == '-b':
            global only_slurp_base
            only_slurp_base = True
        # from timtest.py
        elif opt == '-n':
            nsets = int(arg)
        elif opt == '-s':
            seed = int(arg)
        elif opt == '--ham-keep':
            hamkeep = int(arg)
        elif opt == '--spam-keep':
            spamkeep = int(arg)

    setup(proxy_info, cache_filename)
    spambayes.classifier.Bayes = SlurpingClassifier

    if nsets is None:
        timtest.usage(1, "-n is required")

    msgs.setparms(hamkeep, spamkeep, seed=seed)
    timtest.drive(nsets)

Index: timtest.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/testtools/timtest.py,v
retrieving revision 1.3
retrieving revision 1.4
diff -C2 -d -r1.3 -r1.4
*** timtest.py	10 Mar 2003 00:51:55 -0000	1.3
--- timtest.py	30 Apr 2003 06:43:28 -0000	1.4
***************
*** 26,30 ****
      -s int
          A seed for the random number generator.  Has no effect unless
!         at least on of {--ham-keep, --spam-keep} is specified.  If -s
          isn't specifed, the seed is taken from current time.
  
--- 26,30 ----
      -s int
          A seed for the random number generator.  Has no effect unless
!         at least one of {--ham-keep, --spam-keep} is specified.  If -s
          isn't specifed, the seed is taken from current time.