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 SUPPORTED_EXTENSIONS = ['txt', 'asc', 'nfo']
  28
  29 def sniff_handler(media_file, **kw):
  30     if not kw.get('media') == None:
  31         name, ext = os.path.splitext(kw['media'].filename)
  32         clean_ext = ext[1:].lower()
  33
  34         if clean_ext in SUPPORTED_EXTENSIONS:
  35             return True
  36
  37     return False
  38
  39 def process_ascii(entry):
  40     '''
  41     Code to process a txt file
  42     '''
  43     workbench = mgg.workbench_manager.create_workbench()
  44     # Conversions subdirectory to avoid collisions
  45     conversions_subdir = os.path.join(
  46         workbench.dir, 'conversions')
  47     os.mkdir(conversions_subdir)
  48
  49     queued_filepath = entry['queued_media_file']
  50     queued_filename = workbench.localized_file(
  51         mgg.queue_store, queued_filepath,
  52         'source')
  53
  54     queued_file = file(queued_filename, 'rb')
  55
  56     with queued_file:
  57         queued_file_charset = chardet.detect(queued_file.read())
  58
  59         # Only select a non-utf-8 charset if chardet is *really* sure
  60         # Tested with "Feli\x0109an superjaron", which was detecte
  61         if queued_file_charset['confidence'] < 0.9:
  62             interpreted_charset = 'utf-8'
  63         else:
  64             interpreted_charset = queued_file_charset['encoding']
  65
  66         _log.info('Charset detected: {0}\nWill interpret as: {1}'.format(
  67                 queued_file_charset,
  68                 interpreted_charset))
  69
  70         queued_file.seek(0)  # Rewind the queued file
  71
  72         thumb_filepath = create_pub_filepath(
  73             entry, 'thumbnail.png')
  74
  75         tmp_thumb_filename = os.path.join(
  76             conversions_subdir, thumb_filepath[-1])
  77
  78         converter = asciitoimage.AsciiToImage()
  79
  80         thumb = converter._create_image(
  81             queued_file.read())
  82
  83         with file(tmp_thumb_filename, 'w') as thumb_file:
  84             thumb.thumbnail(THUMB_SIZE, Image.ANTIALIAS)
  85             thumb.save(thumb_file)
  86
  87         _log.debug('Copying local file to public storage')
  88         mgg.public_store.copy_local_to_storage(
  89             tmp_thumb_filename, thumb_filepath)
  90
  91         queued_file.seek(0)
  92
  93         original_filepath = create_pub_filepath(entry, queued_filepath[-1])
  94
  95         with mgg.public_store.get_file(original_filepath, 'wb') \
  96             as original_file:
  97             original_file.write(queued_file.read())
  98
  99
 100         queued_file.seek(0)  # Rewind *again*
 101
 102         unicode_filepath = create_pub_filepath(entry, 'ascii-portable.txt')
 103
 104         with mgg.public_store.get_file(unicode_filepath, 'wb') \
 105                 as unicode_file:
 106             # Decode the original file from its detected charset (or UTF8)
 107             # Encode the unicode instance to ASCII and replace any non-ASCII
 108             # with an HTML entity (&#
 109             unicode_file.write(
 110                 unicode(queued_file.read().decode(
 111                         interpreted_charset)).encode(
 112                     'ascii',
 113                     'xmlcharrefreplace'))
 114
 115     mgg.queue_store.delete_file(queued_filepath)
 116     entry['queued_media_file'] = []
 117     media_files_dict = entry.setdefault('media_files', {})
 118     media_files_dict['thumb'] = thumb_filepath
 119     media_files_dict['unicode'] = unicode_filepath
 120     media_files_dict['original'] = original_filepath
 121
 122     entry.save()