mediagoblin/media_types/ascii/processing.py

   1 # GNU MediaGoblin -- federated, autonomous media hosting
   2 # Copyright (C) 2011, 2012 MediaGoblin contributors.  See AUTHORS.
   3 #
   4 # This program is free software: you can redistribute it and/or modify
   5 # it under the terms of the GNU Affero General Public License as published by
   6 # the Free Software Foundation, either version 3 of the License, or
   7 # (at your option) any later version.
   8 #
   9 # This program is distributed in the hope that it will be useful,
  10 # but WITHOUT ANY WARRANTY; without even the implied warranty of
  11 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  12 # GNU Affero General Public License for more details.
  13 #
  14 # You should have received a copy of the GNU Affero General Public License
  15 # along with this program.  If not, see <http://www.gnu.org/licenses/>.
  16 import chardet
  17 import os
  18 import Image
  19 import logging
  20
  21 from mediagoblin import mg_globals as mgg
  22 from mediagoblin.processing import create_pub_filepath, THUMB_SIZE
  23 from mediagoblin.media_types.ascii import asciitoimage
  24
  25 _log = logging.getLogger(__name__)
  26
  27 def sniff_handler(media_file, **kw):
  28     return False
  29
  30 def process_ascii(entry):
  31     '''
  32     Code to process a txt file
  33     '''
  34     workbench = mgg.workbench_manager.create_workbench()
  35     # Conversions subdirectory to avoid collisions
  36     conversions_subdir = os.path.join(
  37         workbench.dir, 'conversions')
  38     os.mkdir(conversions_subdir)
  39
  40     queued_filepath = entry['queued_media_file']
  41     queued_filename = workbench.localized_file(
  42         mgg.queue_store, queued_filepath,
  43         'source')
  44
  45     queued_file = file(queued_filename, 'rb')
  46
  47     with queued_file:
  48         queued_file_charset = chardet.detect(queued_file.read())
  49
  50         # Only select a non-utf-8 charset if chardet is *really* sure
  51         # Tested with "Feli\x0109an superjaron", which was detecte
  52         if queued_file_charset['confidence'] < 0.9:
  53             interpreted_charset = 'utf-8'
  54         else:
  55             interpreted_charset = queued_file_charset['encoding']
  56
  57         _log.info('Charset detected: {0}\nWill interpret as: {1}'.format(
  58                 queued_file_charset,
  59                 interpreted_charset))
  60
  61         queued_file.seek(0)  # Rewind the queued file
  62
  63         thumb_filepath = create_pub_filepath(
  64             entry, 'thumbnail.png')
  65
  66         tmp_thumb_filename = os.path.join(
  67             conversions_subdir, thumb_filepath[-1])
  68
  69         converter = asciitoimage.AsciiToImage()
  70
  71         thumb = converter._create_image(
  72             queued_file.read())
  73
  74         with file(tmp_thumb_filename, 'w') as thumb_file:
  75             thumb.thumbnail(THUMB_SIZE, Image.ANTIALIAS)
  76             thumb.save(thumb_file)
  77
  78         _log.debug('Copying local file to public storage')
  79         mgg.public_store.copy_local_to_storage(
  80             tmp_thumb_filename, thumb_filepath)
  81
  82         queued_file.seek(0)
  83
  84         original_filepath = create_pub_filepath(entry, queued_filepath[-1])
  85
  86         with mgg.public_store.get_file(original_filepath, 'wb') \
  87             as original_file:
  88             original_file.write(queued_file.read())
  89
  90
  91         queued_file.seek(0)  # Rewind *again*
  92
  93         unicode_filepath = create_pub_filepath(entry, 'ascii-portable.txt')
  94
  95         with mgg.public_store.get_file(unicode_filepath, 'wb') \
  96                 as unicode_file:
  97             # Decode the original file from its detected charset (or UTF8)
  98             # Encode the unicode instance to ASCII and replace any non-ASCII
  99             # with an HTML entity (&#
 100             unicode_file.write(
 101                 unicode(queued_file.read().decode(
 102                         interpreted_charset)).encode(
 103                     'ascii',
 104                     'xmlcharrefreplace'))
 105
 106     mgg.queue_store.delete_file(queued_filepath)
 107     entry['queued_media_file'] = []
 108     media_files_dict = entry.setdefault('media_files', {})
 109     media_files_dict['thumb'] = thumb_filepath
 110     media_files_dict['unicode'] = unicode_filepath
 111     media_files_dict['original'] = original_filepath
 112
 113     entry.save()