SickGear/lib/hachoir/parser/misc/torrent.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

172 lines
5.6 KiB
Python

"""
.torrent metainfo file parser
http://wiki.theory.org/BitTorrentSpecification#Metainfo_File_Structure
Status: To statufy
Author: Christophe Gisquet <christophe.gisquet@free.fr>
"""
from hachoir.parser import Parser
from hachoir.field import (FieldSet, ParserError,
String, RawBytes)
from hachoir.core.endian import LITTLE_ENDIAN
from hachoir.core.tools import makePrintable, timestampUNIX, humanFilesize
# Maximum number of bytes for string length
MAX_STRING_LENGTH = 6 # length in 0..999999
# Maximum number of bytes for integer value
MAX_INTEGER_SIZE = 21 # 21 decimal digits (or "-" sign and 20 digits)
class Integer(FieldSet):
# i<integer encoded in base ten ASCII>e
def createFields(self):
yield String(self, "start", 1, "Integer start delimiter (i)", charset="ASCII")
# Find integer end
addr = self.absolute_address + self.current_size
len = self.stream.searchBytesLength('e', False, addr, addr + (MAX_INTEGER_SIZE + 1) * 8)
if len is None:
raise ParserError("Torrent: Unable to find integer end delimiter (e)!")
if not len:
raise ParserError("Torrent: error, empty integer!")
yield String(self, "value", len, "Integer value", charset="ASCII")
yield String(self, "end", 1, "Integer end delimiter")
def createValue(self):
"""Read integer value (may raise ValueError)"""
return int(self["value"].value)
class TorrentString(FieldSet):
# <string length encoded in base ten ASCII>:<string data>
def createFields(self):
addr = self.absolute_address
len = self.stream.searchBytesLength(':', False, addr, addr + (MAX_STRING_LENGTH + 1) * 8)
if len is None:
raise ParserError("Torrent: unable to find string separator (':')")
if not len:
raise ParserError("Torrent: error: no string length!")
val = String(self, "length", len, "String length")
yield val
try:
len = int(val.value)
except ValueError:
len = -1
if len < 0:
raise ParserError("Invalid string length (%s)" % makePrintable(val.value, "ASCII", to_unicode=True))
yield String(self, "separator", 1, "String length/value separator")
if not len:
self.info("Empty string: len=%i" % len)
return
if len < 512:
yield String(self, "value", len, "String value", charset="ISO-8859-1")
else:
# Probably raw data
yield RawBytes(self, "value", len, "Raw data")
def createValue(self):
if "value" in self:
field = self["value"]
if field.__class__ != RawBytes:
return field.value
else:
return None
else:
return None
class Dictionary(FieldSet):
# d<bencoded string><bencoded element>e
def createFields(self):
yield String(self, "start", 1, "Dictionary start delimiter (d)", charset="ASCII")
while self.stream.readBytes(self.absolute_address + self.current_size, 1) != "e":
yield DictionaryItem(self, "item[]")
yield String(self, "end", 1, "Dictionary end delimiter")
class List(FieldSet):
# l<bencoded values>e
def createFields(self):
yield String(self, "start", 1, "List start delimiter")
while self.stream.readBytes(self.absolute_address + self.current_size, 1) != "e":
yield Entry(self, "item[]")
yield String(self, "end", 1, "List end delimiter")
class DictionaryItem(FieldSet):
def __init__(self, *args):
FieldSet.__init__(self, *args)
# TODO: Remove this because it's not lazy?
key = self["key"]
if not key.hasValue():
return
key = key.value
self._name = str(key).replace(" ", "_")
def createDisplay(self):
if not self["value"].hasValue():
return None
if self._name in ("length", "piece_length"):
return humanFilesize(self.value)
return FieldSet.createDisplay(self)
def createValue(self):
if not self["value"].hasValue():
return None
if self._name == "creation_date":
return self.createTimestampValue()
else:
return self["value"].value
def createFields(self):
yield Entry(self, "key")
yield Entry(self, "value")
def createTimestampValue(self):
return timestampUNIX(self["value"].value)
# Map first chunk byte => type
TAGS = {'d': Dictionary, 'i': Integer, 'l': List}
for index in xrange(0, 9 + 1):
TAGS[str(index)] = TorrentString
# Create an entry
def Entry(parent, name):
addr = parent.absolute_address + parent.current_size
tag = parent.stream.readBytes(addr, 1)
if tag not in TAGS:
raise ParserError("Torrent: Entry of type %r not handled" % tag)
cls = TAGS[tag]
return cls(parent, name)
class TorrentFile(Parser):
endian = LITTLE_ENDIAN
MAGIC = "d8:announce"
MAGIC_EXTENSION = "d13:announce-list"
PARSER_TAGS = {
"id": "torrent",
"category": "misc",
"file_ext": ("torrent",),
"min_size": 50 * 8,
"mime": (u"application/x-bittorrent",),
"magic": ((MAGIC, 0),),
"description": "Torrent metainfo file"
}
def validate(self):
if self.stream.readBytes(0, len(self.MAGIC)) != self.MAGIC and \
self.stream.readBytes(0, len(self.MAGIC_EXTENSION)) != self.MAGIC_EXTENSION:
return "Invalid magic"
return True
def createFields(self):
yield Dictionary(self, "root", size=self.size)