1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
|
# GNU MediaGoblin -- federated, autonomous media hosting
# Copyright (C) 2011, 2012 MediaGoblin contributors. See AUTHORS.
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU Affero General Public License for more details.
#
# You should have received a copy of the GNU Affero General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
from collections import OrderedDict
import logging
import os
from mediagoblin import mg_globals as mgg
from mediagoblin.db.util import atomic_update
from mediagoblin.db.models import MediaEntry
from mediagoblin.tools.pluginapi import hook_handle
from mediagoblin.tools.translate import lazy_pass_to_ugettext as _
_log = logging.getLogger(__name__)
class ProgressCallback(object):
def __init__(self, entry):
self.entry = entry
def __call__(self, progress):
if progress:
self.entry.transcoding_progress = progress
self.entry.save()
def create_pub_filepath(entry, filename):
return mgg.public_store.get_unique_filepath(
['media_entries',
unicode(entry.id),
filename])
class FilenameBuilder(object):
"""Easily slice and dice filenames.
Initialize this class with an original file path, then use the fill()
method to create new filenames based on the original.
"""
MAX_FILENAME_LENGTH = 255 # VFAT's maximum filename length
def __init__(self, path):
"""Initialize a builder from an original file path."""
self.dirpath, self.basename = os.path.split(path)
self.basename, self.ext = os.path.splitext(self.basename)
self.ext = self.ext.lower()
def fill(self, fmtstr):
"""Build a new filename based on the original.
The fmtstr argument can include the following:
{basename} -- the original basename, with the extension removed
{ext} -- the original extension, always lowercase
If necessary, {basename} will be truncated so the filename does not
exceed this class' MAX_FILENAME_LENGTH in length.
"""
basename_len = (self.MAX_FILENAME_LENGTH -
len(fmtstr.format(basename='', ext=self.ext)))
return fmtstr.format(basename=self.basename[:basename_len],
ext=self.ext)
class MediaProcessor(object):
"""A particular processor for this media type.
While the ProcessingManager handles all types of MediaProcessing
possible for a particular media type, a MediaProcessor can be
thought of as a *particular* processing action for a media type.
For example, you may have separate MediaProcessors for:
- initial_processing: the intial processing of a media
- gen_thumb: generate a thumbnail
- resize: resize an image
- transcode: transcode a video
... etc.
Some information on producing a new MediaProcessor for your media type:
- You *must* supply a name attribute. This must be a class level
attribute, and a string. This will be used to determine the
subcommand of your process
- It's recommended that you supply a class level description
attribute.
- Supply a media_is_eligible classmethod. This will be used to
determine whether or not a media entry is eligible to use this
processor type. See the method documentation for details.
- To give "./bin/gmg reprocess run" abilities to this media type,
supply both gnerate_parser and parser_to_request classmethods.
- The process method will be what actually processes your media.
"""
# You MUST override this in the child MediaProcessor!
name = None
# Optional, but will be used in various places to describe the
# action this MediaProcessor provides
description = None
def __init__(self, manager, media_entry):
self.manager = manager
self.media_entry = media_entry
self.entry_orig_state = media_entry.state
# Should be initialized at time of processing, at least
self.workbench = None
def __enter__(self):
self.workbench = mgg.workbench_manager.create()
def __exit__(self, *args):
self.workbench.destroy()
self.workbench = None
# @with_workbench
def process(self, **kwargs):
"""
Actually process this media entry.
"""
raise NotImplementedError
@classmethod
def media_is_eligible(cls, media_entry):
raise NotImplementedError
###############################
# Command line interface things
###############################
@classmethod
def generate_parser(cls):
raise NotImplementedError
@classmethod
def args_to_request(cls, args):
raise NotImplementedError
##########################################
# THE FUTURE: web interface things here :)
##########################################
class ProcessingKeyError(Exception): pass
class ProcessorDoesNotExist(ProcessingKeyError): pass
class ProcessorNotEligible(ProcessingKeyError): pass
class ProcessingManager(object):
"""Manages all the processing actions available for a media type
Specific processing actions, MediaProcessor subclasses, are added
to the ProcessingManager.
"""
def __init__(self):
# Dict of all MediaProcessors of this media type
self.processors = OrderedDict()
def add_processor(self, processor):
"""
Add a processor class to this media type
"""
name = processor.name
if name is None:
raise AttributeError("Processor class's .name attribute not set")
self.processors[name] = processor
def list_eligible_processors(self, entry):
"""
List all processors that this media entry is eligible to be processed
for.
"""
return [
processor
for processor in self.processors.values()
if processor.media_is_eligible(entry)]
def list_all_processors(self):
return self.processors.values()
def gen_process_request_via_cli(self, subparser):
# Got to figure out what actually goes here before I can write this properly
pass
def get_processor(self, key, entry=None):
"""
Get the processor with this key.
If entry supplied, make sure this entry is actually compatible;
otherwise raise error.
"""
try:
processor = self.processors[key]
except KeyError:
raise ProcessorDoesNotExist(
"'%s' processor does not exist for this media type" % key)
if entry and not processor.media_is_eligible(entry):
raise ProcessorNotEligible(
"This entry is not eligible for processor with name '%s'" % key)
return processor
def process_from_args(self, entry, reprocess_command, request):
"""
Process a media entry.
"""
pass
def request_from_args(args, which_args):
"""
Generate a request from the values of some argparse parsed args
"""
request = {}
for arg in which_args:
request[arg] = getattr(args, arg)
return request
class MediaEntryNotFound(Exception): pass
def get_processing_manager_for_type(media_type):
"""
Get the appropriate media manager for this type
"""
manager_class = hook_handle(('reprocess_manager', media_type))
manager = manager_class()
return manager
def get_entry_and_processing_manager(media_id):
"""
Get a MediaEntry, its media type, and its manager all in one go.
Returns a tuple of: `(entry, media_type, media_manager)`
"""
entry = MediaEntry.query.filter_by(id=media_id).first()
if entry is None:
raise MediaEntryNotFound("Can't find media with id '%s'" % media_id)
manager = get_processing_manager_for_type(entry.media_type)
return entry, manager
################################################
# TODO: This ProcessingState is OUTDATED,
# and needs to be refactored into other tools!
################################################
class ProcessingState(object):
"""
The first and only argument to the "processor" of a media type
This could be thought of as a "request" to the processor
function. It has the main info for the request (media entry)
and a bunch of tools for the request on it.
It can get more fancy without impacting old media types.
"""
def __init__(self, entry):
self.entry = entry
self.workbench = None
self.orig_filename = None
def set_workbench(self, wb):
self.workbench = wb
def get_orig_filename(self):
"""
Get the a filename for the original, on local storage
If the media entry has a queued_media_file, use that, otherwise
use the original.
In the future, this will return the highest quality file available
if neither the original or queued file are available
"""
if self.orig_filename is not None:
return self.orig_filename
if self.entry.queued_media_file:
orig_filepath = self.entry.queued_media_file
storage = mgg.queue_store
else:
orig_filepath = self.entry.media_files['original']
storage = mgg.public_store
orig_filename = self.workbench.localized_file(
storage, orig_filepath,
'source')
self.orig_filename = orig_filename
return orig_filename
def copy_original(self, target_name, keyname=u"original"):
self.store_public(keyname, self.get_orig_filename(), target_name)
def store_public(self, keyname, local_file, target_name=None):
if target_name is None:
target_name = os.path.basename(local_file)
target_filepath = create_pub_filepath(self.entry, target_name)
if keyname in self.entry.media_files:
_log.warn("store_public: keyname %r already used for file %r, "
"replacing with %r", keyname,
self.entry.media_files[keyname], target_filepath)
mgg.public_store.copy_local_to_storage(local_file, target_filepath)
self.entry.media_files[keyname] = target_filepath
def delete_queue_file(self):
# Remove queued media file from storage and database.
# queued_filepath is in the task_id directory which should
# be removed too, but fail if the directory is not empty to be on
# the super-safe side.
queued_filepath = self.entry.queued_media_file
mgg.queue_store.delete_file(queued_filepath) # rm file
mgg.queue_store.delete_dir(queued_filepath[:-1]) # rm dir
self.entry.queued_media_file = []
def mark_entry_failed(entry_id, exc):
"""
Mark a media entry as having failed in its conversion.
Uses the exception that was raised to mark more information. If
the exception is a derivative of BaseProcessingFail then we can
store extra information that can be useful for users telling them
why their media failed to process.
Args:
- entry_id: The id of the media entry
"""
# Was this a BaseProcessingFail? In other words, was this a
# type of error that we know how to handle?
if isinstance(exc, BaseProcessingFail):
# Looks like yes, so record information about that failure and any
# metadata the user might have supplied.
atomic_update(mgg.database.MediaEntry,
{'id': entry_id},
{u'state': u'failed',
u'fail_error': unicode(exc.exception_path),
u'fail_metadata': exc.metadata})
else:
_log.warn("No idea what happened here, but it failed: %r", exc)
# Looks like no, so just mark it as failed and don't record a
# failure_error (we'll assume it wasn't handled) and don't record
# metadata (in fact overwrite it if somehow it had previous info
# here)
atomic_update(mgg.database.MediaEntry,
{'id': entry_id},
{u'state': u'failed',
u'fail_error': None,
u'fail_metadata': {}})
###############################################################################
# refactoring procstate stuff here
def get_orig_filename(entry, workbench):
"""
Get the a filename for the original, on local storage
If the media entry has a queued_media_file, use that, otherwise
use the original.
In the future, this will return the highest quality file available
if neither the original or queued file are available by checking
some ordered list of preferred keys.
"""
if entry.queued_media_file:
orig_filepath = entry.queued_media_file
storage = mgg.queue_store
else:
orig_filepath = entry.media_files['original']
storage = mgg.public_store
orig_filename = workbench.localized_file(
storage, orig_filepath,
'source')
return orig_filename
# end refactoring
###############################################################################
class BaseProcessingFail(Exception):
"""
Base exception that all other processing failure messages should
subclass from.
You shouldn't call this itself; instead you should subclass it
and provid the exception_path and general_message applicable to
this error.
"""
general_message = u''
@property
def exception_path(self):
return u"%s:%s" % (
self.__class__.__module__, self.__class__.__name__)
def __init__(self, **metadata):
self.metadata = metadata or {}
class BadMediaFail(BaseProcessingFail):
"""
Error that should be raised when an inappropriate file was given
for the media type specified.
"""
general_message = _(u'Invalid file given for media type.')
|