2014-03-10 05:18:05 +00:00
|
|
|
"""
|
|
|
|
Microsoft Archive parser
|
|
|
|
|
|
|
|
Author: Victor Stinner
|
|
|
|
Creation date: 2007-03-04
|
|
|
|
"""
|
|
|
|
|
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.
2018-03-24 14:04:15 +00:00
|
|
|
from hachoir.parser import Parser
|
|
|
|
from hachoir.field import FieldSet, String, UInt32, SubFile
|
|
|
|
from hachoir.core.endian import LITTLE_ENDIAN
|
|
|
|
from hachoir.core.text_handler import textHandler, filesizeHandler, hexadecimal
|
|
|
|
|
2014-03-10 05:18:05 +00:00
|
|
|
MAX_NB_FILE = 100000
|
|
|
|
|
|
|
|
|
|
|
|
class FileIndex(FieldSet):
|
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.
2018-03-24 14:04:15 +00:00
|
|
|
static_size = 68 * 8
|
2014-03-10 05:18:05 +00:00
|
|
|
|
|
|
|
def createFields(self):
|
|
|
|
yield String(self, "filename", 56, truncate="\0", charset="ASCII")
|
|
|
|
yield filesizeHandler(UInt32(self, "filesize"))
|
|
|
|
yield textHandler(UInt32(self, "crc32"), hexadecimal)
|
|
|
|
yield UInt32(self, "offset")
|
|
|
|
|
|
|
|
def createDescription(self):
|
|
|
|
return "File %s (%s) at %s" % (
|
|
|
|
self["filename"].value, self["filesize"].display, self["offset"].value)
|
|
|
|
|
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.
2018-03-24 14:04:15 +00:00
|
|
|
|
2014-03-10 05:18:05 +00:00
|
|
|
class MarFile(Parser):
|
|
|
|
MAGIC = "MARC"
|
|
|
|
PARSER_TAGS = {
|
|
|
|
"id": "mar",
|
|
|
|
"category": "archive",
|
|
|
|
"file_ext": ("mar",),
|
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.
2018-03-24 14:04:15 +00:00
|
|
|
"min_size": 80 * 8, # At least one file index
|
2014-03-10 05:18:05 +00:00
|
|
|
"magic": ((MAGIC, 0),),
|
|
|
|
"description": "Microsoft Archive",
|
|
|
|
}
|
|
|
|
endian = LITTLE_ENDIAN
|
|
|
|
|
|
|
|
def validate(self):
|
|
|
|
if self.stream.readBytes(0, 4) != self.MAGIC:
|
|
|
|
return "Invalid magic"
|
|
|
|
if self["version"].value != 3:
|
|
|
|
return "Invalid version"
|
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.
2018-03-24 14:04:15 +00:00
|
|
|
if not (1 <= self["nb_file"].value <= MAX_NB_FILE):
|
2014-03-10 05:18:05 +00:00
|
|
|
return "Invalid number of file"
|
|
|
|
return True
|
|
|
|
|
|
|
|
def createFields(self):
|
|
|
|
yield String(self, "magic", 4, "File signature (MARC)", charset="ASCII")
|
|
|
|
yield UInt32(self, "version")
|
|
|
|
yield UInt32(self, "nb_file")
|
|
|
|
files = []
|
|
|
|
for index in xrange(self["nb_file"].value):
|
|
|
|
item = FileIndex(self, "file[]")
|
|
|
|
yield item
|
|
|
|
if item["filesize"].value:
|
|
|
|
files.append(item)
|
|
|
|
files.sort(key=lambda item: item["offset"].value)
|
|
|
|
for index in files:
|
|
|
|
padding = self.seekByte(index["offset"].value)
|
|
|
|
if padding:
|
|
|
|
yield padding
|
|
|
|
size = index["filesize"].value
|
|
|
|
desc = "File %s" % index["filename"].value
|
|
|
|
yield SubFile(self, "data[]", size, desc, filename=index["filename"].value)
|