Turnign greek-iso filenames => utf-8 iso

Wed Jun 12 15:05:40 EDT 2013

On 12/6/2013 8:27 μμ, Νικόλαος Κούρας wrote:
> On 12/6/2013 3:42 μμ, Νικόλαος Κούρας wrote:
>
>>> =================================================================================================================
>>>
>>> # Convert wrongly encoded filenames to utf-8
>>> #
>>> =================================================================================================================
>>>
>>>
>>>
>>> path = b'/home/nikos/public_html/data/apps/'
>>> filenames = os.listdir( path )
>>>
>>> utf8_filenames = []
>>>
>>> for filename in filenames:
>>>      # Compute 'path/to/filename'
>>>      filename_bytes = path + filename
>>>      encoding = guess_encoding( filename_bytes )
>>>
>>>      if encoding == 'utf-8':
>>>          # File name is valid UTF-8, so we can skip to the next file.
>>>          utf8_filenames.append( filename_bytes )
>>>          continue
>>>      elif encoding is None:
>>>          # No idea what the encoding is. Hit it with a hammer until it
>>> stops moving.
>>>          filename = filename_bytes.decode( 'utf-8',
>>> 'xmlcharrefreplace' )
>>>      else:
>>>          filename = filename_bytes.decode( encoding )
>>>
>>>      # Rename the file to something which ought to be UTF-8 clean.
>>>      newname_bytes = filename.encode('utf-8')
>>>      os.rename( filename_bytes, newname_bytes )
>>>      utf8_filenames.append( newname_bytes )
>>>
>>>      # Once we get here, the file ought to be UTF-8 clean and the
>>> Unicode name ought to exist:
>>>      assert os.path.exists( newname_bytes.decode('utf-8') )
>>>
>>>
>>> # Switch filenames from utf8 bytestrings => unicode strings
>>> filenames = []
>>>
>>> for utf8_filename in utf8_filenames:
>>>      filenames.append( utf8_filename.decode('utf-8') )
>>>
>>> # Check the presence of a database file against the dir files and delete
>>> record if it doesn't exist
>>> cur.execute('''SELECT url FROM files''')
>>> data = cur.fetchall()
>>>
>>> for url in data:
>>>      if url not in filenames:
>>>          # Delete spurious
>>>          cur.execute('''DELETE FROM files WHERE url = %s''', url )
>>>
>>>
>>> #
>>> =================================================================================================================
>>>
>>>
>>>
>>> # Display ALL files, each with its own download button
>>> #
>>> =================================================================================================================
>>>
>>>
>>>
>>> print('''<body background='/data/images/star.jpg'>
>>>           <center><img src='/data/images/download.gif'><br><br>
>>>           <table border=5 cellpadding=5 bgcolor=green>
>>> ''')
>>>
>>> try:
>>>      cur.execute( '''SELECT * FROM files ORDER BY lastvisit DESC''' )
>>>      data = cur.fetchall()
>>>
>>>      for row in data:
>>>          (filename, hits, host, lastvisit) = row
>>>          lastvisit = lastvisit.strftime('%A %e %b, %H:%M')
>>>
>>>          print('''
>>>          <form method="get" action="/cgi-bin/files.py">
>>>              <tr>
>>>                  <td> <center> <input type="submit" name="filename"
>>> value="%s"> </td>
>>>                  <td> <center> <font color=yellow size=5> %s </td>
>>>                  <td> <center> <font color=orange size=4> %s </td>
>>>                  <td> <center> <font color=silver size=4> %s </td>
>>>              </tr>
>>>          </form>
>>>          ''' % (filename, hits, host, lastvisit) )
>>>      print( '''</table><br><br>''' )
>>> except pymysql.ProgrammingError as e:
>>>      print( repr(e) )
>>>
>>> sys.exit(0)
>>>
>>> ==========
>
> Please help, the script does not erring out, bu neither print the files
> along with download button for the users to download.
>
> What else do i need to try to find out, where the logical error(it it is
> one) might be?
>
> After correcting this issue, this gonna be my last question, every other
> script is fixed, its just this issues now almost 15 days.

Any ideas please on how to check this?