[Spambayes-checkins] spambayes/spambayes storage.py,1.13,1.14

[Skip Montanaro]

Update of /cvsroot/spambayes/spambayes/spambayes
In directory sc8-pr-cvs1:/tmp/cvs-serv15492

Modified Files:
	storage.py 
Log Message:
Encode unicode objects as utf-8 before using as a key for DBDictClassifier
instances.



Index: storage.py
===================================================================
RCS file: /cvsroot/spambayes/spambayes/spambayes/storage.py,v
retrieving revision 1.13
retrieving revision 1.14
diff -C2 -d -r1.13 -r1.14
*** storage.py	27 Jun 2003 00:45:21 -0000	1.13
--- storage.py	1 Jul 2003 01:19:51 -0000	1.14
***************
*** 208,211 ****
--- 208,213 ----
  
      def _wordinfoget(self, word):
+         if isinstance(word, unicode):
+             word = word.encode("utf-8")
          try:
              return self.wordinfo[word]
***************
*** 230,233 ****
--- 232,237 ----
          # as much as 60%!!!  This also has the effect of reducing the time it
          # takes to store the database
+         if isinstance(word, unicode):
+             word = word.encode("utf-8")
          if record.spamcount + record.hamcount <= 1:
              self.db[word] = record.__getstate__()
***************
*** 243,246 ****
--- 247,252 ----
  
      def _wordinfodel(self, word):
+         if isinstance(word, unicode):
+             word = word.encode("utf-8")
          del self.wordinfo[word]
          self.changed_words[word] = WORD_DELETED