SickGear/lib/hachoir/metadata/archive.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

194 lines
7.1 KiB
Python

from hachoir.metadata.metadata_item import QUALITY_BEST, QUALITY_FASTEST
from hachoir.metadata.safe import fault_tolerant, getValue
from hachoir.metadata.metadata import (
RootMetadata, Metadata, MultipleMetadata, registerExtractor)
from hachoir.parser.archive import (Bzip2Parser, CabFile, GzipParser,
TarFile, ZipFile, MarFile)
from hachoir.core.tools import humanUnixAttributes
from hachoir.core.i18n import _
def maxNbFile(meta):
if meta.quality <= QUALITY_FASTEST:
return 0
if QUALITY_BEST <= meta.quality:
return None
return 1 + int(10 * meta.quality)
def computeCompressionRate(meta):
"""
Compute compression rate, sizes have to be in byte.
"""
if (not meta.has("file_size")
or not meta.get("compr_size", 0)):
return
file_size = meta.get("file_size")
if not file_size:
return
meta.compr_rate = float(file_size) / meta.get("compr_size")
class Bzip2Metadata(RootMetadata):
def extract(self, zip):
if "file" in zip:
self.compr_size = zip["file"].size // 8
class GzipMetadata(RootMetadata):
def extract(self, gzip):
self.useHeader(gzip)
computeCompressionRate(self)
@fault_tolerant
def useHeader(self, gzip):
self.compression = gzip["compression"].display
if gzip["mtime"]:
self.last_modification = gzip["mtime"].value
self.os = gzip["os"].display
if gzip["has_filename"].value:
self.filename = getValue(gzip, "filename")
if gzip["has_comment"].value:
self.comment = getValue(gzip, "comment")
self.compr_size = gzip["file"].size // 8
self.file_size = gzip["size"].value
class ZipMetadata(MultipleMetadata):
def extract(self, zip):
max_nb = maxNbFile(self)
for index, field in enumerate(zip.array("file")):
if max_nb is not None and max_nb <= index:
self.warning("ZIP archive contains many files, "
"but only first %s files are processed"
% max_nb)
break
self.processFile(field)
self.extract_end_central_directory(zip)
@fault_tolerant
def extract_end_central_directory(self, parser):
comment = parser['end_central_directory/comment'].value
if comment:
self.comment = comment
@fault_tolerant
def processFile(self, field):
meta = Metadata(self)
meta.filename = field["filename"].value
meta.creation_date = field["last_mod"].value
meta.compression = field["compression"].display
if "data_desc" in field:
meta.file_size = field["data_desc/file_uncompressed_size"].value
if field["data_desc/file_compressed_size"].value:
meta.compr_size = field["data_desc/file_compressed_size"].value
else:
meta.file_size = field["uncompressed_size"].value
if field["compressed_size"].value:
meta.compr_size = field["compressed_size"].value
computeCompressionRate(meta)
self.addGroup(field.name, meta, "File \"%s\"" % meta.get('filename'))
class TarMetadata(MultipleMetadata):
def extract(self, tar):
max_nb = maxNbFile(self)
for index, field in enumerate(tar.array("file")):
if max_nb is not None and max_nb <= index:
self.warning("TAR archive contains many files, "
"but only first %s files are processed"
% max_nb)
break
meta = Metadata(self)
self.extractFile(field, meta)
if meta.has("filename"):
title = _('File "%s"') % meta.getText('filename')
else:
title = _("File")
self.addGroup(field.name, meta, title)
@fault_tolerant
def extractFile(self, field, meta):
meta.filename = field["name"].value
meta.file_attr = humanUnixAttributes(field.getOctal("mode"))
meta.file_size = field.getOctal("size")
try:
if field.getOctal("mtime"):
meta.last_modification = field.getDatetime()
except ValueError:
pass
meta.file_type = field["type"].display
meta.author = "%s (uid=%s), group %s (gid=%s)" % \
(field["uname"].value, field.getOctal("uid"),
field["gname"].value, field.getOctal("gid"))
class CabMetadata(MultipleMetadata):
def extract(self, cab):
if "folder[0]" in cab:
self.useFolder(cab["folder[0]"])
self.format_version = "Microsoft Cabinet version %s.%s"\
% (cab["major_version"].display,
cab["minor_version"].display)
self.comment = "%s folders, %s files" % (
cab["nb_folder"].value, cab["nb_files"].value)
max_nb = maxNbFile(self)
for index, field in enumerate(cab.array("file")):
if max_nb is not None and max_nb <= index:
self.warning("CAB archive contains many files, "
"but only first %s files are processed"
% max_nb)
break
self.useFile(field)
@fault_tolerant
def useFolder(self, folder):
compr = folder["compr_method"].display
if folder["compr_method"].value != 0:
compr += " (level %u)" % folder["compr_level"].value
self.compression = compr
@fault_tolerant
def useFile(self, field):
meta = Metadata(self)
meta.filename = field["filename"].value
meta.file_size = field["filesize"].value
meta.creation_date = field["timestamp"].value
attr = field["attributes"].value
if attr != "(none)":
meta.file_attr = attr
if meta.has("filename"):
title = _("File \"%s\"") % meta.getText('filename')
else:
title = _("File")
self.addGroup(field.name, meta, title)
class MarMetadata(MultipleMetadata):
def extract(self, mar):
self.comment = "Contains %s files" % mar["nb_file"].value
self.format_version = "Microsoft Archive version %s"\
% mar["version"].value
max_nb = maxNbFile(self)
for index, field in enumerate(mar.array("file")):
if max_nb is not None and max_nb <= index:
self.warning("MAR archive contains many files, "
"but only first %s files are processed"
% max_nb)
break
meta = Metadata(self)
meta.filename = field["filename"].value
meta.compression = "None"
meta.file_size = field["filesize"].value
self.addGroup(field.name, meta,
"File \"%s\"" % meta.getText('filename'))
registerExtractor(CabFile, CabMetadata)
registerExtractor(GzipParser, GzipMetadata)
registerExtractor(Bzip2Parser, Bzip2Metadata)
registerExtractor(TarFile, TarMetadata)
registerExtractor(ZipFile, ZipMetadata)
registerExtractor(MarFile, MarMetadata)