/usr/share/pyshared/kaa/metadata/video/ogm.py is in python-kaa-metadata 0.7.7+svn4596-4.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | # -*- coding: iso-8859-1 -*-
# -----------------------------------------------------------------------------
# ogm.py - ogm/ogg file parser
# -----------------------------------------------------------------------------
# $Id: ogm.py 2818 2007-09-16 10:04:15Z dmeyer $
#
# -----------------------------------------------------------------------------
# kaa-Metadata - Media Metadata for Python
# Copyright (C) 2003-2006 Thomas Schueppel, Dirk Meyer
#
# First Edition: Thomas Schueppel <stain@acm.org>
# Maintainer: Dirk Meyer <dischi@freevo.org>
#
# Please see the file AUTHORS for a complete list of authors.
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 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 MER-
# CHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General
# Public License for more details.
#
# You should have received a copy of the GNU General Public License along
# with this program; if not, write to the Free Software Foundation, Inc.,
# 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
#
# -----------------------------------------------------------------------------
__all__ = ['Parser']
# python imports
import struct
import re
import stat
import os
import logging
# import kaa.metadata.video core
import core
# get logging object
log = logging.getLogger('metadata')
PACKET_TYPE_HEADER = 0x01
PACKED_TYPE_METADATA = 0x03
PACKED_TYPE_SETUP = 0x05
PACKET_TYPE_BITS = 0x07
PACKET_IS_SYNCPOINT = 0x08
#VORBIS_VIDEO_PACKET_INFO = 'video'
STREAM_HEADER_VIDEO = '<4sIQQIIHII'
STREAM_HEADER_AUDIO = '<4sIQQIIHHHI'
VORBISCOMMENT = { 'TITLE': 'title',
'ALBUM': 'album',
'ARTIST': 'artist',
'COMMENT': 'comment',
'ENCODER': 'encoder',
'TRACKNUMBER': 'trackno',
'LANGUAGE': 'language',
'GENRE': 'genre',
}
# FIXME: check VORBISCOMMENT date and convert to timestamp
# Deactived tag: 'DATE': 'date',
MAXITERATIONS = 30
class Ogm(core.AVContainer):
table_mapping = { 'VORBISCOMMENT' : VORBISCOMMENT }
def __init__(self, file):
core.AVContainer.__init__(self)
self.samplerate = 1
self.all_streams = [] # used to add meta data to streams
self.all_header = []
for i in range(MAXITERATIONS):
granule, nextlen = self._parseOGGS(file)
if granule == None:
if i == 0:
# oops, bad file
raise core.ParseError()
break
elif granule > 0:
# ok, file started
break
# seek to the end of the stream, to avoid scanning the whole file
if (os.stat(file.name)[stat.ST_SIZE] > 50000):
file.seek(os.stat(file.name)[stat.ST_SIZE]-49000)
# read the rest of the file into a buffer
h = file.read()
# find last OggS to get length info
if len(h) > 200:
idx = h.find('OggS')
pos = -49000 + idx
if idx:
file.seek(os.stat(file.name)[stat.ST_SIZE] + pos)
while 1:
granule, nextlen = self._parseOGGS(file)
if not nextlen:
break
# Copy metadata to the streams
if len(self.all_header) == len(self.all_streams):
for i in range(len(self.all_header)):
# get meta info
for key in self.all_streams[i].keys():
if self.all_header[i].has_key(key):
self.all_streams[i][key] = self.all_header[i][key]
del self.all_header[i][key]
if self.all_header[i].has_key(key.upper()):
asi = self.all_header[i][key.upper()]
self.all_streams[i][key] = asi
del self.all_header[i][key.upper()]
# Chapter parser
if self.all_header[i].has_key('CHAPTER01') and \
not self.chapters:
while 1:
s = 'CHAPTER%02d' % (len(self.chapters) + 1)
if self.all_header[i].has_key(s) and \
self.all_header[i].has_key(s + 'NAME'):
pos = self.all_header[i][s]
try:
pos = int(pos)
except ValueError:
new_pos = 0
for v in pos.split(':'):
new_pos = new_pos * 60 + float(v)
pos = int(new_pos)
c = self.all_header[i][s + 'NAME']
c = core.Chapter(c, pos)
del self.all_header[i][s + 'NAME']
del self.all_header[i][s]
self.chapters.append(c)
else:
break
# If there are no video streams in this ogg container, it
# must be an audio file. Raise an exception to cause the
# factory to fall back to audio.ogg.
if len(self.video) == 0:
raise core.ParseError
# Copy Metadata from tables into the main set of attributes
for header in self.all_header:
self._appendtable('VORBISCOMMENT', header)
def _parseOGGS(self,file):
h = file.read(27)
if len(h) == 0:
# Regular File end
return None, None
elif len(h) < 27:
log.debug("%d Bytes of Garbage found after End." % len(h))
return None, None
if h[:4] != "OggS":
log.debug("Invalid Ogg")
raise core.ParseError()
version = ord(h[4])
if version != 0:
log.debug("Unsupported OGG/OGM Version %d." % version)
return None, None
head = struct.unpack('<BQIIIB', h[5:])
headertype, granulepos, serial, pageseqno, checksum, \
pageSegCount = head
self.mime = 'application/ogm'
self.type = 'OGG Media'
tab = file.read(pageSegCount)
nextlen = 0
for i in range(len(tab)):
nextlen += ord(tab[i])
else:
h = file.read(1)
packettype = ord(h[0]) & PACKET_TYPE_BITS
if packettype == PACKET_TYPE_HEADER:
h += file.read(nextlen-1)
self._parseHeader(h, granulepos)
elif packettype == PACKED_TYPE_METADATA:
h += file.read(nextlen-1)
self._parseMeta(h)
else:
file.seek(nextlen-1,1)
if len(self.all_streams) > serial:
stream = self.all_streams[serial]
if hasattr(stream, 'samplerate') and \
stream.samplerate:
stream.length = granulepos / stream.samplerate
elif hasattr(stream, 'bitrate') and \
stream.bitrate:
stream.length = granulepos / stream.bitrate
return granulepos, nextlen + 27 + pageSegCount
def _parseMeta(self,h):
flags = ord(h[0])
headerlen = len(h)
if headerlen >= 7 and h[1:7] == 'vorbis':
header = {}
nextlen, self.encoder = self._extractHeaderString(h[7:])
numItems = struct.unpack('<I',h[7+nextlen:7+nextlen+4])[0]
start = 7+4+nextlen
for i in range(numItems):
(nextlen, s) = self._extractHeaderString(h[start:])
start += nextlen
if s:
a = re.split('=',s)
header[(a[0]).upper()]=a[1]
# Put Header fields into info fields
self.type = 'OGG Vorbis'
self.subtype = ''
self.all_header.append(header)
def _parseHeader(self,header,granule):
headerlen = len(header)
flags = ord(header[0])
if headerlen >= 30 and header[1:7] == 'vorbis':
ai = core.AudioStream()
ai.version, ai.channels, ai.samplerate, bitrate_max, ai.bitrate, \
bitrate_min, blocksize, framing = \
struct.unpack('<IBIiiiBB',header[7:7+23])
ai.codec = 'Vorbis'
#ai.granule = granule
#ai.length = granule / ai.samplerate
self.audio.append(ai)
self.all_streams.append(ai)
elif headerlen >= 7 and header[1:7] == 'theora':
# Theora Header
# XXX Finish Me
vi = core.VideoStream()
vi.codec = 'theora'
self.video.append(vi)
self.all_streams.append(vi)
elif headerlen >= 142 and \
header[1:36] == 'Direct Show Samples embedded in Ogg':
# Old Directshow format
# XXX Finish Me
vi = core.VideoStream()
vi.codec = 'dshow'
self.video.append(vi)
self.all_streams.append(vi)
elif flags & PACKET_TYPE_BITS == PACKET_TYPE_HEADER and \
headerlen >= struct.calcsize(STREAM_HEADER_VIDEO)+1:
# New Directshow Format
htype = header[1:9]
if htype[:5] == 'video':
sh = header[9:struct.calcsize(STREAM_HEADER_VIDEO)+9]
streamheader = struct.unpack( STREAM_HEADER_VIDEO, sh )
vi = core.VideoStream()
(type, ssize, timeunit, samplerate, vi.length, buffersize, \
vi.bitrate, vi.width, vi.height) = streamheader
vi.width /= 65536
vi.height /= 65536
# XXX length, bitrate are very wrong
vi.codec = type
vi.fps = 10000000 / timeunit
self.video.append(vi)
self.all_streams.append(vi)
elif htype[:5] == 'audio':
sha = header[9:struct.calcsize(STREAM_HEADER_AUDIO)+9]
streamheader = struct.unpack( STREAM_HEADER_AUDIO, sha )
ai = core.AudioStream()
(type, ssize, timeunit, ai.samplerate, ai.length, buffersize, \
ai.bitrate, ai.channels, bloc, ai.bitrate) = streamheader
self.samplerate = ai.samplerate
log.debug("Samplerate %d" % self.samplerate)
self.audio.append(ai)
self.all_streams.append(ai)
elif htype[:4] == 'text':
subtitle = core.Subtitle()
# FIXME: add more info
self.subtitles.append(subtitle)
self.all_streams.append(subtitle)
else:
log.debug("Unknown Header")
def _extractHeaderString(self,header):
len = struct.unpack( '<I', header[:4] )[0]
try:
return (len+4,unicode(header[4:4+len], 'utf-8'))
except (KeyError, IndexError, UnicodeDecodeError):
return (len+4,None)
Parser = Ogm
|