SickGear/lib/hachoir/metadata/riff.py
JackDandy 980e05cc99 Change Hachoir can't support PY2 so backport their PY3 to prevent a need for system dependant external binaries like mediainfo.
Backported 400 revisions from rev 1de4961-8897c5b (2018-2014).
Move core/benchmark, core/cmd_line, core/memory, core/profiler and core/timeout to core/optional/*
Remove metadata/qt*

PORT: Version 2.0a3 (inline with 3.0a3 @ f80c7d5).
Basic Support for XMP Packets.
tga: improvements to adhere more closely to the spec.
pdf: slightly improved parsing.
rar: fix TypeError on unknown block types.
Add MacRoman win32 codepage.
tiff/exif: support SubIFDs and tiled images.
Add method to export metadata in dictionary.
mpeg_video: don't attempt to parse Stream past length.
mpeg_video: parse ESCR correctly, add SCR value.
Change centralise CustomFragments.
field: don't set parser class if class is None, to enable autodetect.
field: add value/display for CustomFragment.
parser: inline warning to enable tracebacks in debug mode.
Fix empty bytestrings in makePrintable.
Fix contentSize in jpeg.py to account for image_data blocks.
Fix the ELF parser.
Enhance the AR archive parser.
elf parser: fix wrong wrong fields order in parsing little endian section flags.
elf parser: add s390 as a machine type.
Flesh out mp4 parser.

PORT: Version 2.0a1 (inline with 3.0a1).
Major refactoring and PEP8.
Fix ResourceWarning warnings on files. Add a close() method and support for the context manager protocol ("with obj: ...") to parsers, input and output streams.
metadata: get comment from ZIP.
Support for InputIOStream.read(0).
Fix sizeGe when size is None.
Remove unused new_seekable_field_set file.
Remove parser Mapsforge .map.
Remove parser Parallel Realities Starfighter .pak files.
sevenzip: fix for newer archives.
java: update access flags and modifiers for Java 1.7 and update description text for most recent Java.
Support ustar prefix field in tar archives.
Remove file_system* parsers.
Remove misc parsers 3d0, 3ds, gnome_keyring, msoffice*, mstask, ole*, word*.
Remove program parsers macho, nds, prc.
Support non-8bit Character subclasses.
Python parser supports Python 3.7.
Enhance mpeg_ts parser to support MTS/M2TS.
Support for creation date in tiff.
Change don't hardcode errno constant.

PORT: 1.9.1
Internal Only: The following are legacy reference to upstream commit messages.
Relevant changes up to b0a115f8.
Use integer division.
Replace HACHOIR_ERRORS with Exception.
Fix metadata.Data: make it sortable.
Import fixes from e7de492.
PORT: Version 2.0a1 (inline with 3.0a1 @ e9f8fad).
Replace hachoir.core.field with hachoir.field
Replace hachoir.core.stream with hachoir.stream
Remove the compatibility module for PY1.5 to PY2.5.
metadata: support TIFF picture.
metadata: fix string normalization.
metadata: fix datetime regex Fix hachoir bug #57.
FileFromInputStream: fix comparison between None and an int.
InputIOStream: open the file in binary mode.
2018-03-28 00:43:11 +01:00

203 lines
8 KiB
Python

"""
Extract metadata from RIFF file format: AVI video and WAV sound.
"""
from hachoir.metadata.metadata import Metadata, MultipleMetadata, registerExtractor
from hachoir.metadata.safe import fault_tolerant, getValue
from hachoir.parser.container.riff import RiffFile
from hachoir.parser.video.fourcc import UNCOMPRESSED_AUDIO
from hachoir.core.tools import humanFilesize, makeUnicode, timedelta2seconds
from hachoir.core.i18n import _
from hachoir.metadata.audio import computeComprRate as computeAudioComprRate
from datetime import timedelta
class RiffMetadata(MultipleMetadata):
TAG_TO_KEY = {
"INAM": "title",
"IART": "artist",
"ICMT": "comment",
"ICOP": "copyright",
"IENG": "author", # (engineer)
"ISFT": "producer",
"ICRD": "creation_date",
"IDIT": "creation_date",
}
def extract(self, riff, **kwargs):
type = riff["type"].value
if type == "WAVE":
self.extractWAVE(riff)
size = getValue(riff, "audio_data/size")
if size:
computeAudioComprRate(self, size * 8)
elif type == "AVI ":
if "headers" in riff:
if 'scan_index' in kwargs:
self.extractAVI(riff["headers"], scan_index=kwargs['scan_index'])
else:
self.extractAVI(riff["headers"])
self.extractInfo(riff["headers"])
elif type == "ACON":
self.extractAnim(riff)
if "info" in riff:
self.extractInfo(riff["info"])
def processChunk(self, chunk):
if "text" not in chunk:
return
value = chunk["text"].value
tag = chunk["tag"].value
if tag not in self.TAG_TO_KEY:
self.warning("Skip RIFF metadata %s: %s" % (tag, value))
return
key = self.TAG_TO_KEY[tag]
setattr(self, key, value)
@fault_tolerant
def extractWAVE(self, wav):
format = wav["format"]
# Number of channel, bits/sample, sample rate
self.nb_channel = format["nb_channel"].value
self.bits_per_sample = format["bit_per_sample"].value
self.sample_rate = format["sample_per_sec"].value
self.compression = format["codec"].display
if "nb_sample/nb_sample" in wav \
and 0 < format["sample_per_sec"].value:
self.duration = timedelta(seconds=float(
wav["nb_sample/nb_sample"].value) / format["sample_per_sec"].value)
if format["codec"].value in UNCOMPRESSED_AUDIO:
# Codec with fixed bit rate
self.bit_rate = format[
"nb_channel"].value * format["bit_per_sample"].value * format["sample_per_sec"].value
if not self.has("duration") \
and "audio_data/size" in wav \
and self.has("bit_rate"):
duration = float(wav["audio_data/size"].value) * \
8 / self.get('bit_rate')
self.duration = timedelta(seconds=duration)
def extractInfo(self, fieldset):
for field in fieldset:
if not field.is_field_set:
continue
if "tag" in field:
if field["tag"].value == "LIST":
self.extractInfo(field)
else:
self.processChunk(field)
@fault_tolerant
def extractAVIVideo(self, header, meta):
meta.compression = "%s (fourcc:\"%s\")" \
% (header["fourcc"].display, makeUnicode(header["fourcc"].value))
if header["rate"].value and header["scale"].value:
fps = float(header["rate"].value) / header["scale"].value
meta.frame_rate = fps
if 0 < fps:
self.duration = meta.duration = timedelta(
seconds=float(header["length"].value) / fps)
if "../stream_fmt/width" in header:
format = header["../stream_fmt"]
meta.width = format["width"].value
meta.height = format["height"].value
meta.bits_per_pixel = format["depth"].value
else:
meta.width = header["right"].value - header["left"].value
meta.height = header["bottom"].value - header["top"].value
@fault_tolerant
def extractAVIAudio(self, format, meta):
meta.nb_channel = format["channel"].value
meta.sample_rate = format["sample_rate"].value
meta.bit_rate = format["bit_rate"].value * 8
if format["bits_per_sample"].value:
meta.bits_per_sample = format["bits_per_sample"].value
if "../stream_hdr" in format:
header = format["../stream_hdr"]
if header["rate"].value and header["scale"].value:
frame_rate = float(
header["rate"].value) / header["scale"].value
meta.duration = timedelta(seconds=float(
header["length"].value) / frame_rate)
if header["fourcc"].value != "":
meta.compression = "%s (fourcc:\"%s\")" \
% (format["codec"].display, header["fourcc"].value)
if not meta.has("compression"):
meta.compression = format["codec"].display
self.computeAudioComprRate(meta)
@fault_tolerant
def computeAudioComprRate(self, meta):
uncompr = meta.get('bit_rate', 0)
if not uncompr:
return
compr = meta.get('nb_channel') * meta.get('sample_rate') * \
meta.get('bits_per_sample', default=16)
if not compr:
return
meta.compr_rate = float(compr) / uncompr
@fault_tolerant
def useAviHeader(self, header):
microsec = header["microsec_per_frame"].value
if microsec:
self.frame_rate = 1000000.0 / microsec
total_frame = getValue(header, "total_frame")
if total_frame and not self.has("duration"):
self.duration = timedelta(microseconds=total_frame * microsec)
self.width = header["width"].value
self.height = header["height"].value
def extractAVI(self, headers, **kwargs):
audio_index = 1
for stream in headers.array("stream"):
if "stream_hdr/stream_type" not in stream:
continue
stream_type = stream["stream_hdr/stream_type"].value
if stream_type == "vids":
if "stream_hdr" in stream:
meta = Metadata(self)
self.extractAVIVideo(stream["stream_hdr"], meta)
self.addGroup("video", meta, "Video stream")
elif stream_type == "auds":
if "stream_fmt" in stream:
meta = Metadata(self)
self.extractAVIAudio(stream["stream_fmt"], meta)
self.addGroup("audio[%u]" % audio_index, meta, "Audio stream")
audio_index += 1
if "avi_hdr" in headers:
self.useAviHeader(headers["avi_hdr"])
# Compute global bit rate
if self.has("duration") and "/movie/size" in headers:
self.bit_rate = float(
headers["/movie/size"].value) * 8 / timedelta2seconds(self.get('duration'))
# Video has index?
scan_index = (True, kwargs['scan_index'])['scan_index' in kwargs]
if scan_index and "/index" in headers:
self.comment = _("Has audio/video index (%s)") \
% humanFilesize(headers["/index"].size // 8)
@fault_tolerant
def extractAnim(self, riff):
if "anim_rate/rate[0]" in riff:
count = 0
total = 0
for rate in riff.array("anim_rate/rate"):
count += 1
if 100 < count:
break
total += rate.value / 60.0
if count and total:
self.frame_rate = count / total
if not self.has("frame_rate") and "anim_hdr/jiffie_rate" in riff:
self.frame_rate = 60.0 / riff["anim_hdr/jiffie_rate"].value
registerExtractor(RiffFile, RiffMetadata)