1 # GNU MediaGoblin -- federated, autonomous media hosting
2 # Copyright (C) 2011, 2012 MediaGoblin contributors. See AUTHORS.
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.
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.
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/>.
25 from mediagoblin
import mg_globals
as mgg
26 from mediagoblin
.processing
import (
27 create_pub_filepath
, FilenameBuilder
,
28 MediaProcessor
, ProcessingManager
,
29 get_orig_filename
, copy_original
,
30 store_public
, request_from_args
)
31 from mediagoblin
.media_types
.ascii
import asciitoimage
33 _log
= logging
.getLogger(__name__
)
35 SUPPORTED_EXTENSIONS
= ['txt', 'asc', 'nfo']
36 MEDIA_TYPE
= 'mediagoblin.media_types.ascii'
39 def sniff_handler(media_file
, **kw
):
40 _log
.info('Sniffing {0}'.format(MEDIA_TYPE
))
41 if kw
.get('media') is not None:
42 name
, ext
= os
.path
.splitext(kw
['media'].filename
)
43 clean_ext
= ext
[1:].lower()
45 if clean_ext
in SUPPORTED_EXTENSIONS
:
51 class CommonAsciiProcessor(MediaProcessor
):
53 Provides a base for various ascii processing steps
55 def common_setup(self
):
56 self
.ascii_config
= mgg
.global_config
[
57 'media_type:mediagoblin.media_types.ascii']
59 # Conversions subdirectory to avoid collisions
60 self
.conversions_subdir
= os
.path
.join(
61 self
.workbench
.dir, 'convirsions')
62 os
.mkdir(self
.conversions_subdir
)
64 # Pull down and set up the original file
65 self
.orig_filename
= get_orig_filename(
66 self
.entry
, self
.workbench
)
67 self
.name_builder
= FilenameBuilder(self
.orig_filename
)
71 def copy_original(self
):
73 self
.entry
, self
.orig_filename
,
74 self
.name_builder
.fill('{basename}{ext}'))
76 def _detect_charset(self
, orig_file
):
77 d_charset
= chardet
.detect(orig_file
.read())
79 # Only select a non-utf-8 charset if chardet is *really* sure
80 # Tested with "Feli\x0109an superjaron", which was detected
81 if d_charset
['confidence'] < 0.9:
82 self
.charset
= 'utf-8'
84 self
.charset
= d_charset
['encoding']
86 _log
.info('Charset detected: {0}\nWill interpret as: {1}'.format(
93 def store_unicode_file(self
):
94 with
file(self
.orig_filename
, 'rb') as orig_file
:
95 self
._detect
_charset
(orig_file
)
96 unicode_filepath
= create_pub_filepath(self
.entry
,
99 with mgg
.public_store
.get_file(unicode_filepath
, 'wb') \
101 # Decode the original file from its detected charset (or UTF8)
102 # Encode the unicode instance to ASCII and replace any
103 # non-ASCII with an HTML entity (&#
105 unicode(orig_file
.read().decode(
106 self
.charset
)).encode(
108 'xmlcharrefreplace'))
110 self
.entry
.media_files
['unicode'] = unicode_filepath
112 def generate_thumb(self
, font
=None, thumb_size
=None):
113 with
file(self
.orig_filename
, 'rb') as orig_file
:
114 # If no font kwarg, check config
116 font
= self
.ascii_config
.get('thumbnail_font', None)
118 thumb_size
= (mgg
.global_config
['media:thumb']['max_width'],
119 mgg
.global_config
['media:thumb']['max_height'])
121 tmp_thumb
= os
.path
.join(
122 self
.conversions_subdir
,
123 self
.name_builder
.fill('{basename}.thumbnail.png'))
125 ascii_converter_args
= {}
127 # If there is a font from either the config or kwarg, update
128 # ascii_converter_args
130 ascii_converter_args
.update(
131 {'font': self
.ascii_config
['thumbnail_font']})
133 converter
= asciitoimage
.AsciiToImage(
134 **ascii_converter_args
)
136 thumb
= converter
._create
_image
(
139 with
file(tmp_thumb
, 'w') as thumb_file
:
143 thumb
.save(thumb_file
)
145 _log
.debug('Copying local file to public storage')
146 store_public(self
.entry
, 'thumb', tmp_thumb
,
147 self
.name_builder
.fill('{basename}.thumbnail.jpg'))
150 class InitialProcessor(CommonAsciiProcessor
):
152 Initial processing step for new ascii media
155 description
= "Initial processing"
158 def media_is_eligible(cls
, entry
=None, state
=None):
162 "unprocessed", "failed")
165 def generate_parser(cls
):
166 parser
= argparse
.ArgumentParser(
167 description
=cls
.description
,
173 metavar
=('max_width', 'max_width'),
178 help='the thumbnail font')
183 def args_to_request(cls
, args
):
184 return request_from_args(
185 args
, ['thumb_size', 'font'])
187 def process(self
, thumb_size
=None, font
=None):
189 self
.store_unicode_file()
190 self
.generate_thumb(thumb_size
=thumb_size
, font
=font
)
192 self
.delete_queue_file()
195 class Resizer(CommonAsciiProcessor
):
197 Resizing process steps for processed media
200 description
= 'Resize thumbnail'
203 def media_is_eligible(cls
, entry
=None, state
=None):
205 Determine if this media type is eligible for processing
209 return state
in 'processed'
212 def generate_parser(cls
):
213 parser
= argparse
.ArgumentParser(
214 description
=cls
.description
,
220 metavar
=('max_width', 'max_height'),
223 # Needed for gmg reprocess thumbs to work
233 def args_to_request(cls
, args
):
234 return request_from_args(
235 args
, ['thumb_size', 'file'])
237 def process(self
, thumb_size
=None, file=None):
239 self
.generate_thumb(thumb_size
=thumb_size
)
242 class AsciiProcessingManager(ProcessingManager
):
244 super(self
.__class
__, self
).__init
__()
245 self
.add_processor(InitialProcessor
)
246 self
.add_processor(Resizer
)