SickGear/lib/hachoir/parser/parser.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

161 lines
5.5 KiB
Python

import hachoir.core.config as config
from hachoir.field import Parser as GenericParser
from hachoir.core.error import error
from hachoir.core.tools import makeUnicode
from hachoir.core.i18n import _
from inspect import getmro
class ValidateError(Exception):
pass
class HachoirParser(object):
"""
A parser is the root of all other fields. It create first level of fields
and have special attributes and methods:
- tags: dictionnary with keys:
- "file_ext": classical file extensions (string or tuple of strings) ;
- "mime": MIME type(s) (string or tuple of strings) ;
- "description": String describing the parser.
- endian: Byte order (L{BIG_ENDIAN} or L{LITTLE_ENDIAN}) of input data ;
- stream: Data input stream (set in L{__init__()}).
Default values:
- size: Field set size will be size of input stream ;
- mime_type: First MIME type of tags["mime"] (if it does exist,
None otherwise).
"""
_autofix = False
def __init__(self, stream, **args):
validate = args.pop("validate", False)
self._mime_type = None
while validate:
nbits = self.getParserTags()["min_size"]
if stream.sizeGe(nbits):
res = self.validate()
if res is True:
break
res = makeUnicode(res)
else:
res = _("stream is smaller than %s.%s bytes" % divmod(nbits, 8))
raise ValidateError(res or _("no reason given"))
self._autofix = True
# --- Methods that can be overridden -------------------------------------
def createDescription(self):
"""
Create an Unicode description
"""
return self.PARSER_TAGS["description"]
def createMimeType(self):
"""
Create MIME type (string), eg. "image/png"
If it returns None, "application/octet-stream" is used.
"""
if "mime" in self.PARSER_TAGS:
return self.PARSER_TAGS["mime"][0]
return None
def validate(self):
"""
Check that the parser is able to parse the stream. Valid results:
- True: stream looks valid ;
- False: stream is invalid ;
- str: string describing the error.
"""
raise NotImplementedError()
# --- Getter methods -----------------------------------------------------
def _getDescription(self):
if self._description is None:
try:
self._description = self.createDescription()
if isinstance(self._description, str):
self._description = makeUnicode(self._description)
except Exception as err:
error("Error getting description of %s: %s" \
% (self.path, unicode(err)))
self._description = self.PARSER_TAGS["description"]
return self._description
description = property(_getDescription,
doc="Description of the parser")
def _getMimeType(self):
if not self._mime_type:
try:
self._mime_type = self.createMimeType()
except Exception as err:
self.error("Error when creating MIME type: %s" % unicode(err))
if not self._mime_type \
and self.createMimeType != Parser.createMimeType:
self._mime_type = Parser.createMimeType(self)
if not self._mime_type:
self._mime_type = u"application/octet-stream"
return self._mime_type
mime_type = property(_getMimeType)
def createContentSize(self):
return None
def _getContentSize(self):
if not hasattr(self, "_content_size"):
try:
self._content_size = self.createContentSize()
except Exception as err:
error("Unable to compute %s content size: %s" % (self.__class__.__name__, err))
self._content_size = None
return self._content_size
content_size = property(_getContentSize)
def createFilenameSuffix(self):
"""
Create filename suffix: "." + first value of self.PARSER_TAGS["file_ext"],
or None if self.PARSER_TAGS["file_ext"] doesn't exist.
"""
file_ext = self.getParserTags().get("file_ext")
if isinstance(file_ext, (tuple, list)):
file_ext = file_ext[0]
return file_ext and '.' + file_ext
def _getFilenameSuffix(self):
if not hasattr(self, "_filename_suffix"):
self._filename_extension = self.createFilenameSuffix()
return self._filename_extension
filename_suffix = property(_getFilenameSuffix)
@classmethod
def getParserTags(cls):
tags = {}
for cls in reversed(getmro(cls)):
if hasattr(cls, "PARSER_TAGS"):
tags.update(cls.PARSER_TAGS)
return tags
@classmethod
def print_(cls, out, verbose):
tags = cls.getParserTags()
print >> out, "- %s: %s" % (tags["id"], tags["description"])
if verbose:
if "mime" in tags:
print >> out, " MIME type: %s" % (", ".join(tags["mime"]))
if "file_ext" in tags:
file_ext = ", ".join(
".%s" % file_ext for file_ext in tags["file_ext"])
print >> out, " File extension: %s" % file_ext
autofix = property(lambda self: self._autofix and config.autofix)
class Parser(HachoirParser, GenericParser):
def __init__(self, stream, **args):
GenericParser.__init__(self, stream)
HachoirParser.__init__(self, stream, **args)