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
  23 from mediagoblin.media_types.ascii import asciitoimage
  24
  25 _log = logging.getLogger(__name__)
  26
  27 SUPPORTED_EXTENSIONS = ['txt', 'asc', 'nfo']
  28
  29
  30 def sniff_handler(media_file, **kw):
  31     if kw.get('media') is not None:
  32         name, ext = os.path.splitext(kw['media'].filename)
  33         clean_ext = ext[1:].lower()
  34
  35         if clean_ext in SUPPORTED_EXTENSIONS:
  36             return True
  37
  38     return False
  39
  40
  41 def process_ascii(entry):
  42     '''
  43     Code to process a txt file
  44     '''
  45     ascii_config = mgg.global_config['media_type:mediagoblin.media_types.ascii']
  46     workbench = mgg.workbench_manager.create_workbench()
  47     # Conversions subdirectory to avoid collisions
  48     conversions_subdir = os.path.join(
  49         workbench.dir, 'conversions')
  50     os.mkdir(conversions_subdir)
  51
  52     queued_filepath = entry.queued_media_file
  53     queued_filename = workbench.localized_file(
  54         mgg.queue_store, queued_filepath,
  55         'source')
  56
  57     queued_file = file(queued_filename, 'rb')
  58
  59     with queued_file:
  60         queued_file_charset = chardet.detect(queued_file.read())
  61
  62         # Only select a non-utf-8 charset if chardet is *really* sure
  63         # Tested with "Feli\x0109an superjaron", which was detecte
  64         if queued_file_charset['confidence'] < 0.9:
  65             interpreted_charset = 'utf-8'
  66         else:
  67             interpreted_charset = queued_file_charset['encoding']
  68
  69         _log.info('Charset detected: {0}\nWill interpret as: {1}'.format(
  70                 queued_file_charset,
  71                 interpreted_charset))
  72
  73         queued_file.seek(0)  # Rewind the queued file
  74
  75         thumb_filepath = create_pub_filepath(
  76             entry, 'thumbnail.png')
  77
  78         tmp_thumb_filename = os.path.join(
  79             conversions_subdir, thumb_filepath[-1])
  80
  81         ascii_converter_args = {}
  82
  83         if ascii_config['thumbnail_font']:
  84             ascii_converter_args.update(
  85                     {'font': ascii_config['thumbnail_font']})
  86
  87         converter = asciitoimage.AsciiToImage(
  88                **ascii_converter_args)
  89
  90         thumb = converter._create_image(
  91             queued_file.read())
  92
  93         with file(tmp_thumb_filename, 'w') as thumb_file:
  94             thumb.thumbnail(
  95                 (mgg.global_config['media:thumb']['max_width'],
  96                  mgg.global_config['media:thumb']['max_height']),
  97                 Image.ANTIALIAS)
  98             thumb.save(thumb_file)
  99
 100         _log.debug('Copying local file to public storage')
 101         mgg.public_store.copy_local_to_storage(
 102             tmp_thumb_filename, thumb_filepath)
 103
 104         queued_file.seek(0)
 105
 106         original_filepath = create_pub_filepath(entry, queued_filepath[-1])
 107
 108         with mgg.public_store.get_file(original_filepath, 'wb') \
 109             as original_file:
 110             original_file.write(queued_file.read())
 111
 112         queued_file.seek(0)  # Rewind *again*
 113
 114         unicode_filepath = create_pub_filepath(entry, 'ascii-portable.txt')
 115
 116         with mgg.public_store.get_file(unicode_filepath, 'wb') \
 117                 as unicode_file:
 118             # Decode the original file from its detected charset (or UTF8)
 119             # Encode the unicode instance to ASCII and replace any non-ASCII
 120             # with an HTML entity (&#
 121             unicode_file.write(
 122                 unicode(queued_file.read().decode(
 123                         interpreted_charset)).encode(
 124                     'ascii',
 125                     'xmlcharrefreplace'))
 126
 127     mgg.queue_store.delete_file(queued_filepath)
 128     entry.queued_media_file = []
 129     media_files_dict = entry.setdefault('media_files', {})
 130     media_files_dict['thumb'] = thumb_filepath
 131     media_files_dict['unicode'] = unicode_filepath
 132     media_files_dict['original'] = original_filepath
 133
 134     entry.save()