mirror of
https://github.com/SickGear/SickGear.git
synced 2024-12-11 21:53:37 +00:00
980e05cc99
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.
128 lines
4.6 KiB
Python
128 lines
4.6 KiB
Python
"""
|
|
GZIP archive parser.
|
|
|
|
Author: Victor Stinner
|
|
"""
|
|
|
|
from hachoir.parser import Parser
|
|
from hachoir.field import (
|
|
UInt8, UInt16, UInt32, Enum, TimestampUnix32,
|
|
Bit, CString, SubFile,
|
|
NullBits, Bytes, RawBytes)
|
|
from hachoir.core.text_handler import textHandler, hexadecimal, filesizeHandler
|
|
from hachoir.core.endian import LITTLE_ENDIAN
|
|
from hachoir.parser.common.deflate import Deflate
|
|
|
|
|
|
class GzipParser(Parser):
|
|
endian = LITTLE_ENDIAN
|
|
PARSER_TAGS = {
|
|
"id": "gzip",
|
|
"category": "archive",
|
|
"file_ext": ("gz",),
|
|
"mime": (u"application/x-gzip",),
|
|
"min_size": 18 * 8,
|
|
"magic_regex": (
|
|
# (magic, compression=deflate, <flags>, <mtime>, )
|
|
('\x1F\x8B\x08.{5}[\0\2\4\6][\x00-\x0D]', 0),
|
|
),
|
|
"description": u"gzip archive",
|
|
}
|
|
os_name = {
|
|
0: u"FAT filesystem",
|
|
1: u"Amiga",
|
|
2: u"VMS (or OpenVMS)",
|
|
3: u"Unix",
|
|
4: u"VM/CMS",
|
|
5: u"Atari TOS",
|
|
6: u"HPFS filesystem (OS/2, NT)",
|
|
7: u"Macintosh",
|
|
8: u"Z-System",
|
|
9: u"CP/M",
|
|
10: u"TOPS-20",
|
|
11: u"NTFS filesystem (NT)",
|
|
12: u"QDOS",
|
|
13: u"Acorn RISCOS",
|
|
}
|
|
COMPRESSION_NAME = {
|
|
8: u"deflate",
|
|
}
|
|
|
|
def validate(self):
|
|
if self["signature"].value != '\x1F\x8B':
|
|
return "Invalid signature"
|
|
if self["compression"].value not in self.COMPRESSION_NAME:
|
|
return "Unknown compression method (%u)" % self["compression"].value
|
|
if self["reserved[0]"].value != 0:
|
|
return "Invalid reserved[0] value"
|
|
if self["reserved[1]"].value != 0:
|
|
return "Invalid reserved[1] value"
|
|
if self["reserved[2]"].value != 0:
|
|
return "Invalid reserved[2] value"
|
|
return True
|
|
|
|
def createFields(self):
|
|
# Gzip header
|
|
yield Bytes(self, "signature", 2, r"GZip file signature (\x1F\x8B)")
|
|
yield Enum(UInt8(self, "compression", "Compression method"), self.COMPRESSION_NAME)
|
|
|
|
# Flags
|
|
yield Bit(self, "is_text", "File content is probably ASCII text")
|
|
yield Bit(self, "has_crc16", "Header CRC16")
|
|
yield Bit(self, "has_extra", "Extra informations (variable size)")
|
|
yield Bit(self, "has_filename", "Contains filename?")
|
|
yield Bit(self, "has_comment", "Contains comment?")
|
|
yield NullBits(self, "reserved[]", 3)
|
|
yield TimestampUnix32(self, "mtime", "Modification time")
|
|
|
|
# Extra flags
|
|
yield NullBits(self, "reserved[]", 1)
|
|
yield Bit(self, "slowest", "Compressor used maximum compression (slowest)")
|
|
yield Bit(self, "fastest", "Compressor used the fastest compression")
|
|
yield NullBits(self, "reserved[]", 5)
|
|
yield Enum(UInt8(self, "os", "Operating system"), self.os_name)
|
|
|
|
# Optional fields
|
|
if self["has_extra"].value:
|
|
yield UInt16(self, "extra_length", "Extra length")
|
|
yield RawBytes(self, "extra", self["extra_length"].value, "Extra")
|
|
if self["has_filename"].value:
|
|
yield CString(self, "filename", "Filename", charset="ISO-8859-1")
|
|
if self["has_comment"].value:
|
|
yield CString(self, "comment", "Comment")
|
|
if self["has_crc16"].value:
|
|
yield textHandler(UInt16(self, "hdr_crc16", "CRC16 of the header"),
|
|
hexadecimal)
|
|
|
|
if self._size is None: # TODO: is it possible to handle piped input?
|
|
raise NotImplementedError()
|
|
|
|
# Read file
|
|
size = (self._size - self.current_size) // 8 - 8 # -8: crc32+size
|
|
if 0 < size:
|
|
if self["has_filename"].value:
|
|
filename = self["filename"].value
|
|
else:
|
|
for tag, filename in self.stream.tags:
|
|
if tag == "filename" and filename.endswith(".gz"):
|
|
filename = filename[:-3]
|
|
break
|
|
else:
|
|
filename = None
|
|
yield Deflate(SubFile(self, "file", size, filename=filename))
|
|
|
|
# Footer
|
|
yield textHandler(UInt32(self, "crc32",
|
|
"Uncompressed data content CRC32"), hexadecimal)
|
|
yield filesizeHandler(UInt32(self, "size", "Uncompressed size"))
|
|
|
|
def createDescription(self):
|
|
desc = u"gzip archive"
|
|
info = []
|
|
if "filename" in self:
|
|
info.append('filename "%s"' % self["filename"].value)
|
|
if "size" in self:
|
|
info.append("was %s" % self["size"].display)
|
|
if self["mtime"].value:
|
|
info.append(self["mtime"].display)
|
|
return "%s: %s" % (desc, ", ".join(info))
|