Merge branch 'master' into joar-skip_transcoding
[mediagoblin.git] / 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(proc_state):
42 """Code to process a txt file. Will be run by celery.
43
44 A Workbench() represents a local tempory dir. It is automatically
45 cleaned up when this function exits.
46 """
47 entry = proc_state.entry
48 workbench = proc_state.workbench
49 ascii_config = mgg.global_config['media_type:mediagoblin.media_types.ascii']
50 # Conversions subdirectory to avoid collisions
51 conversions_subdir = os.path.join(
52 workbench.dir, 'conversions')
53 os.mkdir(conversions_subdir)
54
55 queued_filepath = entry.queued_media_file
56 queued_filename = workbench.localized_file(
57 mgg.queue_store, queued_filepath,
58 'source')
59
60 queued_file = file(queued_filename, 'rb')
61
62 with queued_file:
63 queued_file_charset = chardet.detect(queued_file.read())
64
65 # Only select a non-utf-8 charset if chardet is *really* sure
66 # Tested with "Feli\x0109an superjaron", which was detecte
67 if queued_file_charset['confidence'] < 0.9:
68 interpreted_charset = 'utf-8'
69 else:
70 interpreted_charset = queued_file_charset['encoding']
71
72 _log.info('Charset detected: {0}\nWill interpret as: {1}'.format(
73 queued_file_charset,
74 interpreted_charset))
75
76 queued_file.seek(0) # Rewind the queued file
77
78 thumb_filepath = create_pub_filepath(
79 entry, 'thumbnail.png')
80
81 tmp_thumb_filename = os.path.join(
82 conversions_subdir, thumb_filepath[-1])
83
84 ascii_converter_args = {}
85
86 if ascii_config['thumbnail_font']:
87 ascii_converter_args.update(
88 {'font': ascii_config['thumbnail_font']})
89
90 converter = asciitoimage.AsciiToImage(
91 **ascii_converter_args)
92
93 thumb = converter._create_image(
94 queued_file.read())
95
96 with file(tmp_thumb_filename, 'w') as thumb_file:
97 thumb.thumbnail(
98 (mgg.global_config['media:thumb']['max_width'],
99 mgg.global_config['media:thumb']['max_height']),
100 Image.ANTIALIAS)
101 thumb.save(thumb_file)
102
103 _log.debug('Copying local file to public storage')
104 mgg.public_store.copy_local_to_storage(
105 tmp_thumb_filename, thumb_filepath)
106
107 queued_file.seek(0)
108
109 original_filepath = create_pub_filepath(entry, queued_filepath[-1])
110
111 with mgg.public_store.get_file(original_filepath, 'wb') \
112 as original_file:
113 original_file.write(queued_file.read())
114
115 queued_file.seek(0) # Rewind *again*
116
117 unicode_filepath = create_pub_filepath(entry, 'ascii-portable.txt')
118
119 with mgg.public_store.get_file(unicode_filepath, 'wb') \
120 as unicode_file:
121 # Decode the original file from its detected charset (or UTF8)
122 # Encode the unicode instance to ASCII and replace any non-ASCII
123 # with an HTML entity (&#
124 unicode_file.write(
125 unicode(queued_file.read().decode(
126 interpreted_charset)).encode(
127 'ascii',
128 'xmlcharrefreplace'))
129
130 mgg.queue_store.delete_file(queued_filepath)
131 entry.queued_media_file = []
132 media_files_dict = entry.setdefault('media_files', {})
133 media_files_dict['thumb'] = thumb_filepath
134 media_files_dict['unicode'] = unicode_filepath
135 media_files_dict['original'] = original_filepath
136
137 entry.save()