stevazi/addon
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 3 Wiki Activity

rimesso guessit con le modifiche per gli import

Browse Source
This commit is contained in:
marco
2020-05-03 15:51:27 +02:00
parent 99c9f5f134
commit 8cd92ee71f
139 changed files with 37742 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
core/support.py
View File

@@ -7,6 +7,8 @@ import os
import re import re
import sys import sys
from lib.guessit import guessit
PY3 = False PY3 = False
if sys.version_info[0] >= 3: PY3 = True; unicode = str; unichr = chr; long = int if sys.version_info[0] >= 3: PY3 = True; unicode = str; unichr = chr; long = int
if PY3: if PY3:
@@ -271,14 +273,13 @@ def scrapeBlock(item, args, block, patron, headers, action, pagination, debug, t
longtitle = title + (s if title and title2 else '') + title2 + '\n' longtitle = title + (s if title and title2 else '') + title2 + '\n'
if sceneTitle: if sceneTitle:
import lib.PTN.parse as parse parsedTitle = guessit(title)
parsedTitle = parse(title)
title = longtitle = parsedTitle.get('title', '') title = longtitle = parsedTitle.get('title', '')
log('TITOLO',title) log('TITOLO',title)
if parsedTitle.get('quality'): if parsedTitle.get('source'):
quality = str(parsedTitle.get('quality')) quality = str(parsedTitle.get('source'))
if parsedTitle.get('resolution'): if parsedTitle.get('screen_size'):
quality += ' ' + str(parsedTitle.get('resolution', '')) quality += ' ' + str(parsedTitle.get('screen_size', ''))
if not scraped['year']: if not scraped['year']:
infolabels['year'] = parsedTitle.get('year', '') infolabels['year'] = parsedTitle.get('year', '')
if parsedTitle.get('episode') and parsedTitle.get('season'): if parsedTitle.get('episode') and parsedTitle.get('season'):
@@ -297,8 +298,8 @@ def scrapeBlock(item, args, block, patron, headers, action, pagination, debug, t
longtitle += s + config.get_localized_string(30140) + " " +str(parsedTitle.get('season')[0]) + '-' + str(parsedTitle.get('season')[-1]) longtitle += s + config.get_localized_string(30140) + " " +str(parsedTitle.get('season')[0]) + '-' + str(parsedTitle.get('season')[-1])
elif parsedTitle.get('season'): elif parsedTitle.get('season'):
longtitle += s + config.get_localized_string(60027) % str(parsedTitle.get('season')) longtitle += s + config.get_localized_string(60027) % str(parsedTitle.get('season'))
if parsedTitle.get('episodeName'): if parsedTitle.get('episode_title'):
longtitle += s + parsedTitle.get('episodeName') longtitle += s + parsedTitle.get('episode_title')
longtitle = typo(longtitle, 'bold') longtitle = typo(longtitle, 'bold')
lang1, longtitle = scrapeLang(scraped, lang, longtitle) lang1, longtitle = scrapeLang(scraped, lang, longtitle)
@@ -871,7 +872,7 @@ def match(item_url_string, **args):
string = args.get('string', False) string = args.get('string', False)
# remove scrape arguments # remove scrape arguments
args = dict([(key, val) for key, val in args.items() if key not in ['patron', 'patronBlock', 'patronBlocks', 'debug', 'debugBlock', 'string']]) args = dict([(key, val) for key, val in args.items() if key not in ['patron', 'patronBlock', 'patronBlocks', 'debug', 'debugBlock', 'string']])
# check type of item_url_string # check type of item_url_string
if string: if string:

25
lib/babelfish/__init__.py Executable file
View File

@@ -0,0 +1,25 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
__title__ = 'babelfish'
__version__ = '0.5.5-dev'
__author__ = 'Antoine Bertin'
__license__ = 'BSD'
__copyright__ = 'Copyright 2015 the BabelFish authors'
import sys
if sys.version_info[0] >= 3:
basestr = str
else:
basestr = basestring
from .converters import (LanguageConverter, LanguageReverseConverter, LanguageEquivalenceConverter, CountryConverter,
CountryReverseConverter)
from .country import country_converters, COUNTRIES, COUNTRY_MATRIX, Country
from .exceptions import Error, LanguageConvertError, LanguageReverseError, CountryConvertError, CountryReverseError
from .language import language_converters, LANGUAGES, LANGUAGE_MATRIX, Language
from .script import SCRIPTS, SCRIPT_MATRIX, Script

289
lib/babelfish/converters/__init__.py Executable file
View File

@@ -0,0 +1,289 @@
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
import collections
import functools
from importlib import import_module
# from pkg_resources import iter_entry_points, EntryPoint
from ..exceptions import LanguageConvertError, LanguageReverseError
# from https://github.com/kennethreitz/requests/blob/master/requests/structures.py
class CaseInsensitiveDict(collections.MutableMapping):
"""A case-insensitive ``dict``-like object.
Implements all methods and operations of
``collections.MutableMapping`` as well as dict's ``copy``. Also
provides ``lower_items``.
All keys are expected to be strings. The structure remembers the
case of the last key to be set, and ``iter(instance)``,
``keys()``, ``items()``, ``iterkeys()``, and ``iteritems()``
will contain case-sensitive keys. However, querying and contains
testing is case insensitive:
cid = CaseInsensitiveDict()
cid['English'] = 'eng'
cid['ENGLISH'] == 'eng' # True
list(cid) == ['English'] # True
If the constructor, ``.update``, or equality comparison
operations are given keys that have equal ``.lower()``s, the
behavior is undefined.
"""
def __init__(self, data=None, **kwargs):
self._store = dict()
if data is None:
data = {}
self.update(data, **kwargs)
def __setitem__(self, key, value):
# Use the lowercased key for lookups, but store the actual
# key alongside the value.
self._store[key.lower()] = (key, value)
def __getitem__(self, key):
return self._store[key.lower()][1]
def __delitem__(self, key):
del self._store[key.lower()]
def __iter__(self):
return (casedkey for casedkey, mappedvalue in self._store.values())
def __len__(self):
return len(self._store)
def lower_items(self):
"""Like iteritems(), but with all lowercase keys."""
return (
(lowerkey, keyval[1])
for (lowerkey, keyval)
in self._store.items()
)
def __eq__(self, other):
if isinstance(other, collections.Mapping):
other = CaseInsensitiveDict(other)
else:
return NotImplemented
# Compare insensitively
return dict(self.lower_items()) == dict(other.lower_items())
# Copy is required
def copy(self):
return CaseInsensitiveDict(self._store.values())
def __repr__(self):
return '%s(%r)' % (self.__class__.__name__, dict(self.items()))
class LanguageConverter(object):
"""A :class:`LanguageConverter` supports converting an alpha3 language code with an
alpha2 country code and a script code into a custom code
.. attribute:: codes
Set of possible custom codes
"""
def convert(self, alpha3, country=None, script=None):
"""Convert an alpha3 language code with an alpha2 country code and a script code
into a custom code
:param string alpha3: ISO-639-3 language code
:param country: ISO-3166 country code, if any
:type country: string or None
:param script: ISO-15924 script code, if any
:type script: string or None
:return: the corresponding custom code
:rtype: string
:raise: :class:`~babelfish.exceptions.LanguageConvertError`
"""
raise NotImplementedError
class LanguageReverseConverter(LanguageConverter):
"""A :class:`LanguageConverter` able to reverse a custom code into a alpha3
ISO-639-3 language code, alpha2 ISO-3166-1 country code and ISO-15924 script code
"""
def reverse(self, code):
"""Reverse a custom code into alpha3, country and script code
:param string code: custom code to reverse
:return: the corresponding alpha3 ISO-639-3 language code, alpha2 ISO-3166-1 country code and ISO-15924 script code
:rtype: tuple
:raise: :class:`~babelfish.exceptions.LanguageReverseError`
"""
raise NotImplementedError
class LanguageEquivalenceConverter(LanguageReverseConverter):
"""A :class:`LanguageEquivalenceConverter` is a utility class that allows you to easily define a
:class:`LanguageReverseConverter` by only specifying the dict from alpha3 to their corresponding symbols.
You must specify the dict of equivalence as a class variable named SYMBOLS.
If you also set the class variable CASE_SENSITIVE to ``True`` then the reverse conversion function will be
case-sensitive (it is case-insensitive by default).
Example::
class MyCodeConverter(babelfish.LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {'fra': 'mycode1', 'eng': 'mycode2'}
"""
CASE_SENSITIVE = False
def __init__(self):
self.codes = set()
self.to_symbol = {}
if self.CASE_SENSITIVE:
self.from_symbol = {}
else:
self.from_symbol = CaseInsensitiveDict()
for alpha3, symbol in self.SYMBOLS.items():
self.to_symbol[alpha3] = symbol
self.from_symbol[symbol] = (alpha3, None, None)
self.codes.add(symbol)
def convert(self, alpha3, country=None, script=None):
try:
return self.to_symbol[alpha3]
except KeyError:
raise LanguageConvertError(alpha3, country, script)
def reverse(self, code):
try:
return self.from_symbol[code]
except KeyError:
raise LanguageReverseError(code)
class CountryConverter(object):
"""A :class:`CountryConverter` supports converting an alpha2 country code
into a custom code
.. attribute:: codes
Set of possible custom codes
"""
def convert(self, alpha2):
"""Convert an alpha2 country code into a custom code
:param string alpha2: ISO-3166-1 language code
:return: the corresponding custom code
:rtype: string
:raise: :class:`~babelfish.exceptions.CountryConvertError`
"""
raise NotImplementedError
class CountryReverseConverter(CountryConverter):
"""A :class:`CountryConverter` able to reverse a custom code into a alpha2
ISO-3166-1 country code
"""
def reverse(self, code):
"""Reverse a custom code into alpha2 code
:param string code: custom code to reverse
:return: the corresponding alpha2 ISO-3166-1 country code
:rtype: string
:raise: :class:`~babelfish.exceptions.CountryReverseError`
"""
raise NotImplementedError
class ConverterManager(object):
"""Manager for babelfish converters behaving like a dict with lazy loading
Loading is done in this order:
* Entry point converters
* Registered converters
* Internal converters
.. attribute:: entry_point
The entry point where to look for converters
.. attribute:: internal_converters
Internal converters with entry point syntax
"""
entry_point = ''
internal_converters = []
def __init__(self):
#: Registered converters with entry point syntax
self.registered_converters = []
#: Loaded converters
self.converters = {}
def __getitem__(self, name):
"""Get a converter, lazy loading it if necessary"""
if name in self.converters:
return self.converters[name]
# for ep in iter_entry_points(self.entry_point):
# if ep.name == name:
# self.converters[ep.name] = ep.load()()
# return self.converters[ep.name]
def parse(str):
import re
match = re.match('(?P<name>\w+) = (?P<module>[a-z0-9.]+):(?P<class>\w+)', str)
print match.groupdict()
return match.groupdict()
for ep in (parse(c) for c in self.registered_converters + self.internal_converters):
if ep.get('name') == name:
cl = getattr(import_module(ep.get('module')), ep.get('class'))
self.converters[ep.get('name')] = cl()
return self.converters[ep.get('name')]
raise KeyError(name)
def __setitem__(self, name, converter):
"""Load a converter"""
self.converters[name] = converter
def __delitem__(self, name):
"""Unload a converter"""
del self.converters[name]
def __iter__(self):
"""Iterator over loaded converters"""
return iter(self.converters)
def register(self, entry_point):
"""Register a converter
:param string entry_point: converter to register (entry point syntax)
:raise: ValueError if already registered
"""
if entry_point in self.registered_converters:
raise ValueError('Already registered')
self.registered_converters.insert(0, entry_point)
def unregister(self, entry_point):
"""Unregister a converter
:param string entry_point: converter to unregister (entry point syntax)
"""
self.registered_converters.remove(entry_point)
def __contains__(self, name):
return name in self.converters

17
lib/babelfish/converters/alpha2.py Executable file
View File

@@ -0,0 +1,17 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class Alpha2Converter(LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.alpha2:
SYMBOLS[iso_language.alpha3] = iso_language.alpha2

17
lib/babelfish/converters/alpha3b.py Executable file
View File

@@ -0,0 +1,17 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class Alpha3BConverter(LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.alpha3b:
SYMBOLS[iso_language.alpha3] = iso_language.alpha3b

17
lib/babelfish/converters/alpha3t.py Executable file
View File

@@ -0,0 +1,17 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class Alpha3TConverter(LanguageEquivalenceConverter):
CASE_SENSITIVE = True
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.alpha3t:
SYMBOLS[iso_language.alpha3] = iso_language.alpha3t

31
lib/babelfish/converters/countryname.py Executable file
View File

@@ -0,0 +1,31 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import CountryReverseConverter, CaseInsensitiveDict
from ..country import COUNTRY_MATRIX
from ..exceptions import CountryConvertError, CountryReverseError
class CountryNameConverter(CountryReverseConverter):
def __init__(self):
self.codes = set()
self.to_name = {}
self.from_name = CaseInsensitiveDict()
for country in COUNTRY_MATRIX:
self.codes.add(country.name)
self.to_name[country.alpha2] = country.name
self.from_name[country.name] = country.alpha2
def convert(self, alpha2):
if alpha2 not in self.to_name:
raise CountryConvertError(alpha2)
return self.to_name[alpha2]
def reverse(self, name):
if name not in self.from_name:
raise CountryReverseError(name)
return self.from_name[name]

17
lib/babelfish/converters/name.py Executable file
View File

@@ -0,0 +1,17 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageEquivalenceConverter
from ..language import LANGUAGE_MATRIX
class NameConverter(LanguageEquivalenceConverter):
CASE_SENSITIVE = False
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
if iso_language.name:
SYMBOLS[iso_language.alpha3] = iso_language.name

36
lib/babelfish/converters/opensubtitles.py Executable file
View File

@@ -0,0 +1,36 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageReverseConverter, CaseInsensitiveDict
from ..exceptions import LanguageReverseError
from ..language import language_converters
class OpenSubtitlesConverter(LanguageReverseConverter):
def __init__(self):
self.alpha3b_converter = language_converters['alpha3b']
self.alpha2_converter = language_converters['alpha2']
self.to_opensubtitles = {('por', 'BR'): 'pob', ('gre', None): 'ell', ('srp', None): 'scc', ('srp', 'ME'): 'mne'}
self.from_opensubtitles = CaseInsensitiveDict({'pob': ('por', 'BR'), 'pb': ('por', 'BR'), 'ell': ('ell', None),
'scc': ('srp', None), 'mne': ('srp', 'ME')})
self.codes = (self.alpha2_converter.codes | self.alpha3b_converter.codes | set(['pob', 'pb', 'scc', 'mne']))
def convert(self, alpha3, country=None, script=None):
alpha3b = self.alpha3b_converter.convert(alpha3, country, script)
if (alpha3b, country) in self.to_opensubtitles:
return self.to_opensubtitles[(alpha3b, country)]
return alpha3b
def reverse(self, opensubtitles):
if opensubtitles in self.from_opensubtitles:
return self.from_opensubtitles[opensubtitles]
for conv in [self.alpha3b_converter, self.alpha2_converter]:
try:
return conv.reverse(opensubtitles)
except LanguageReverseError:
pass
raise LanguageReverseError(opensubtitles)

23
lib/babelfish/converters/scope.py Executable file
View File

@@ -0,0 +1,23 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageConverter
from ..exceptions import LanguageConvertError
from ..language import LANGUAGE_MATRIX
class ScopeConverter(LanguageConverter):
FULLNAME = {'I': 'individual', 'M': 'macrolanguage', 'S': 'special'}
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
SYMBOLS[iso_language.alpha3] = iso_language.scope
codes = set(SYMBOLS.values())
def convert(self, alpha3, country=None, script=None):
if self.SYMBOLS[alpha3] in self.FULLNAME:
return self.FULLNAME[self.SYMBOLS[alpha3]]
raise LanguageConvertError(alpha3, country, script)

23
lib/babelfish/converters/type.py Executable file
View File

@@ -0,0 +1,23 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from . import LanguageConverter
from ..exceptions import LanguageConvertError
from ..language import LANGUAGE_MATRIX
class LanguageTypeConverter(LanguageConverter):
FULLNAME = {'A': 'ancient', 'C': 'constructed', 'E': 'extinct', 'H': 'historical', 'L': 'living', 'S': 'special'}
SYMBOLS = {}
for iso_language in LANGUAGE_MATRIX:
SYMBOLS[iso_language.alpha3] = iso_language.type
codes = set(SYMBOLS.values())
def convert(self, alpha3, country=None, script=None):
if self.SYMBOLS[alpha3] in self.FULLNAME:
return self.FULLNAME[self.SYMBOLS[alpha3]]
raise LanguageConvertError(alpha3, country, script)

108
lib/babelfish/country.py Executable file
View File

@@ -0,0 +1,108 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from collections import namedtuple
from functools import partial
# from pkg_resources import resource_stream # @UnresolvedImport
import os
from .converters import ConverterManager
from . import basestr
COUNTRIES = {}
COUNTRY_MATRIX = []
#: The namedtuple used in the :data:`COUNTRY_MATRIX`
IsoCountry = namedtuple('IsoCountry', ['name', 'alpha2'])
f = open(os.path.join(os.path.dirname(__file__), 'data/iso-3166-1.txt'))
f.readline()
for l in f:
iso_country = IsoCountry(*l.decode('utf-8').strip().split(';'))
COUNTRIES[iso_country.alpha2] = iso_country.name
COUNTRY_MATRIX.append(iso_country)
f.close()
class CountryConverterManager(ConverterManager):
""":class:`~babelfish.converters.ConverterManager` for country converters"""
entry_point = 'babelfish.country_converters'
internal_converters = ['name = babelfish.converters.countryname:CountryNameConverter']
country_converters = CountryConverterManager()
class CountryMeta(type):
"""The :class:`Country` metaclass
Dynamically redirect :meth:`Country.frommycode` to :meth:`Country.fromcode` with the ``mycode`` `converter`
"""
def __getattr__(cls, name):
if name.startswith('from'):
return partial(cls.fromcode, converter=name[4:])
return type.__getattribute__(cls, name)
class Country(CountryMeta(str('CountryBase'), (object,), {})):
"""A country on Earth
A country is represented by a 2-letter code from the ISO-3166 standard
:param string country: 2-letter ISO-3166 country code
"""
def __init__(self, country):
if country not in COUNTRIES:
raise ValueError('%r is not a valid country' % country)
#: ISO-3166 2-letter country code
self.alpha2 = country
@classmethod
def fromcode(cls, code, converter):
"""Create a :class:`Country` by its `code` using `converter` to
:meth:`~babelfish.converters.CountryReverseConverter.reverse` it
:param string code: the code to reverse
:param string converter: name of the :class:`~babelfish.converters.CountryReverseConverter` to use
:return: the corresponding :class:`Country` instance
:rtype: :class:`Country`
"""
return cls(country_converters[converter].reverse(code))
def __getstate__(self):
return self.alpha2
def __setstate__(self, state):
self.alpha2 = state
def __getattr__(self, name):
try:
return country_converters[name].convert(self.alpha2)
except KeyError:
raise AttributeError(name)
def __hash__(self):
return hash(self.alpha2)
def __eq__(self, other):
if isinstance(other, basestr):
return str(self) == other
if not isinstance(other, Country):
return False
return self.alpha2 == other.alpha2
def __ne__(self, other):
return not self == other
def __repr__(self):
return '<Country [%s]>' % self
def __str__(self):
return self.alpha2

250
lib/babelfish/data/iso-3166-1.txt Executable file
View File

@@ -0,0 +1,250 @@
Country Name;ISO 3166-1-alpha-2 code
AFGHANISTAN;AF
ÅLAND ISLANDS;AX
ALBANIA;AL
ALGERIA;DZ
AMERICAN SAMOA;AS
ANDORRA;AD
ANGOLA;AO
ANGUILLA;AI
ANTARCTICA;AQ
ANTIGUA AND BARBUDA;AG
ARGENTINA;AR
ARMENIA;AM
ARUBA;AW
AUSTRALIA;AU
AUSTRIA;AT
AZERBAIJAN;AZ
BAHAMAS;BS
BAHRAIN;BH
BANGLADESH;BD
BARBADOS;BB
BELARUS;BY
BELGIUM;BE
BELIZE;BZ
BENIN;BJ
BERMUDA;BM
BHUTAN;BT
BOLIVIA, PLURINATIONAL STATE OF;BO
BONAIRE, SINT EUSTATIUS AND SABA;BQ
BOSNIA AND HERZEGOVINA;BA
BOTSWANA;BW
BOUVET ISLAND;BV
BRAZIL;BR
BRITISH INDIAN OCEAN TERRITORY;IO
BRUNEI DARUSSALAM;BN
BULGARIA;BG
BURKINA FASO;BF
BURUNDI;BI
CAMBODIA;KH
CAMEROON;CM
CANADA;CA
CAPE VERDE;CV
CAYMAN ISLANDS;KY
CENTRAL AFRICAN REPUBLIC;CF
CHAD;TD
CHILE;CL
CHINA;CN
CHRISTMAS ISLAND;CX
COCOS (KEELING) ISLANDS;CC
COLOMBIA;CO
COMOROS;KM
CONGO;CG
CONGO, THE DEMOCRATIC REPUBLIC OF THE;CD
COOK ISLANDS;CK
COSTA RICA;CR
CÔTE D'IVOIRE;CI
CROATIA;HR
CUBA;CU
CURAÇAO;CW
CYPRUS;CY
CZECH REPUBLIC;CZ
DENMARK;DK
DJIBOUTI;DJ
DOMINICA;DM
DOMINICAN REPUBLIC;DO
ECUADOR;EC
EGYPT;EG
EL SALVADOR;SV
EQUATORIAL GUINEA;GQ
ERITREA;ER
ESTONIA;EE
ETHIOPIA;ET
FALKLAND ISLANDS (MALVINAS);FK
FAROE ISLANDS;FO
FIJI;FJ
FINLAND;FI
FRANCE;FR
FRENCH GUIANA;GF
FRENCH POLYNESIA;PF
FRENCH SOUTHERN TERRITORIES;TF
GABON;GA
GAMBIA;GM
GEORGIA;GE
GERMANY;DE
GHANA;GH
GIBRALTAR;GI
GREECE;GR
GREENLAND;GL
GRENADA;GD
GUADELOUPE;GP
GUAM;GU
GUATEMALA;GT
GUERNSEY;GG
GUINEA;GN
GUINEA-BISSAU;GW
GUYANA;GY
HAITI;HT
HEARD ISLAND AND MCDONALD ISLANDS;HM
HOLY SEE (VATICAN CITY STATE);VA
HONDURAS;HN
HONG KONG;HK
HUNGARY;HU
ICELAND;IS
INDIA;IN
INDONESIA;ID
IRAN, ISLAMIC REPUBLIC OF;IR
IRAQ;IQ
IRELAND;IE
ISLE OF MAN;IM
ISRAEL;IL
ITALY;IT
JAMAICA;JM
JAPAN;JP
JERSEY;JE
JORDAN;JO
KAZAKHSTAN;KZ
KENYA;KE
KIRIBATI;KI
KOREA, DEMOCRATIC PEOPLE'S REPUBLIC OF;KP
KOREA, REPUBLIC OF;KR
KUWAIT;KW
KYRGYZSTAN;KG
LAO PEOPLE'S DEMOCRATIC REPUBLIC;LA
LATVIA;LV
LEBANON;LB
LESOTHO;LS
LIBERIA;LR
LIBYA;LY
LIECHTENSTEIN;LI
LITHUANIA;LT
LUXEMBOURG;LU
MACAO;MO
MACEDONIA, THE FORMER YUGOSLAV REPUBLIC OF;MK
MADAGASCAR;MG
MALAWI;MW
MALAYSIA;MY
MALDIVES;MV
MALI;ML
MALTA;MT
MARSHALL ISLANDS;MH
MARTINIQUE;MQ
MAURITANIA;MR
MAURITIUS;MU
MAYOTTE;YT
MEXICO;MX
MICRONESIA, FEDERATED STATES OF;FM
MOLDOVA, REPUBLIC OF;MD
MONACO;MC
MONGOLIA;MN
MONTENEGRO;ME
MONTSERRAT;MS
MOROCCO;MA
MOZAMBIQUE;MZ
MYANMAR;MM
NAMIBIA;NA
NAURU;NR
NEPAL;NP
NETHERLANDS;NL
NEW CALEDONIA;NC
NEW ZEALAND;NZ
NICARAGUA;NI
NIGER;NE
NIGERIA;NG
NIUE;NU
NORFOLK ISLAND;NF
NORTHERN MARIANA ISLANDS;MP
NORWAY;NO
OMAN;OM
PAKISTAN;PK
PALAU;PW
PALESTINE, STATE OF;PS
PANAMA;PA
PAPUA NEW GUINEA;PG
PARAGUAY;PY
PERU;PE
PHILIPPINES;PH
PITCAIRN;PN
POLAND;PL
PORTUGAL;PT
PUERTO RICO;PR
QATAR;QA
RÉUNION;RE
ROMANIA;RO
RUSSIAN FEDERATION;RU
RWANDA;RW
SAINT BARTHÉLEMY;BL
SAINT HELENA, ASCENSION AND TRISTAN DA CUNHA;SH
SAINT KITTS AND NEVIS;KN
SAINT LUCIA;LC
SAINT MARTIN (FRENCH PART);MF
SAINT PIERRE AND MIQUELON;PM
SAINT VINCENT AND THE GRENADINES;VC
SAMOA;WS
SAN MARINO;SM
SAO TOME AND PRINCIPE;ST
SAUDI ARABIA;SA
SENEGAL;SN
SERBIA;RS
SEYCHELLES;SC
SIERRA LEONE;SL
SINGAPORE;SG
SINT MAARTEN (DUTCH PART);SX
SLOVAKIA;SK
SLOVENIA;SI
SOLOMON ISLANDS;SB
SOMALIA;SO
SOUTH AFRICA;ZA
SOUTH GEORGIA AND THE SOUTH SANDWICH ISLANDS;GS
SOUTH SUDAN;SS
SPAIN;ES
SRI LANKA;LK
SUDAN;SD
SURINAME;SR
SVALBARD AND JAN MAYEN;SJ
SWAZILAND;SZ
SWEDEN;SE
SWITZERLAND;CH
SYRIAN ARAB REPUBLIC;SY
TAIWAN, PROVINCE OF CHINA;TW
TAJIKISTAN;TJ
TANZANIA, UNITED REPUBLIC OF;TZ
THAILAND;TH
TIMOR-LESTE;TL
TOGO;TG
TOKELAU;TK
TONGA;TO
TRINIDAD AND TOBAGO;TT
TUNISIA;TN
TURKEY;TR
TURKMENISTAN;TM
TURKS AND CAICOS ISLANDS;TC
TUVALU;TV
UGANDA;UG
UKRAINE;UA
UNITED ARAB EMIRATES;AE
UNITED KINGDOM;GB
UNITED STATES;US
UNITED STATES MINOR OUTLYING ISLANDS;UM
URUGUAY;UY
UZBEKISTAN;UZ
VANUATU;VU
VENEZUELA, BOLIVARIAN REPUBLIC OF;VE
VIET NAM;VN
VIRGIN ISLANDS, BRITISH;VG
VIRGIN ISLANDS, U.S.;VI
WALLIS AND FUTUNA;WF
WESTERN SAHARA;EH
YEMEN;YE
ZAMBIA;ZM
ZIMBABWE;ZW

7875
lib/babelfish/data/iso-639-3.tab Executable file
View File

File diff suppressed because it is too large Load Diff

176
lib/babelfish/data/iso15924-utf8-20131012.txt Executable file
View File

@@ -0,0 +1,176 @@
#
# ISO 15924 - Codes for the representation of names of scripts
# Codes pour la représentation des noms d’écritures
# Format:
# Code;N°;English Name;Nom français;PVA;Date
#
Afak;439;Afaka;afaka;;2010-12-21
Aghb;239;Caucasian Albanian;aghbanien;;2012-10-16
Ahom;338;Ahom, Tai Ahom;âhom;;2012-11-01
Arab;160;Arabic;arabe;Arabic;2004-05-01
Armi;124;Imperial Aramaic;araméen impérial;Imperial_Aramaic;2009-06-01
Armn;230;Armenian;arménien;Armenian;2004-05-01
Avst;134;Avestan;avestique;Avestan;2009-06-01
Bali;360;Balinese;balinais;Balinese;2006-10-10
Bamu;435;Bamum;bamoum;Bamum;2009-06-01
Bass;259;Bassa Vah;bassa;;2010-03-26
Batk;365;Batak;batik;Batak;2010-07-23
Beng;325;Bengali;bengalî;Bengali;2004-05-01
Blis;550;Blissymbols;symboles Bliss;;2004-05-01
Bopo;285;Bopomofo;bopomofo;Bopomofo;2004-05-01
Brah;300;Brahmi;brahma;Brahmi;2010-07-23
Brai;570;Braille;braille;Braille;2004-05-01
Bugi;367;Buginese;bouguis;Buginese;2006-06-21
Buhd;372;Buhid;bouhide;Buhid;2004-05-01
Cakm;349;Chakma;chakma;Chakma;2012-02-06
Cans;440;Unified Canadian Aboriginal Syllabics;syllabaire autochtone canadien unifié;Canadian_Aboriginal;2004-05-29
Cari;201;Carian;carien;Carian;2007-07-02
Cham;358;Cham;cham (čam, tcham);Cham;2009-11-11
Cher;445;Cherokee;tchérokî;Cherokee;2004-05-01
Cirt;291;Cirth;cirth;;2004-05-01
Copt;204;Coptic;copte;Coptic;2006-06-21
Cprt;403;Cypriot;syllabaire chypriote;Cypriot;2004-05-01
Cyrl;220;Cyrillic;cyrillique;Cyrillic;2004-05-01
Cyrs;221;Cyrillic (Old Church Slavonic variant);cyrillique (variante slavonne);;2004-05-01
Deva;315;Devanagari (Nagari);dévanâgarî;Devanagari;2004-05-01
Dsrt;250;Deseret (Mormon);déseret (mormon);Deseret;2004-05-01
Dupl;755;Duployan shorthand, Duployan stenography;sténographie Duployé;;2010-07-18
Egyd;070;Egyptian demotic;démotique égyptien;;2004-05-01
Egyh;060;Egyptian hieratic;hiératique égyptien;;2004-05-01
Egyp;050;Egyptian hieroglyphs;hiéroglyphes égyptiens;Egyptian_Hieroglyphs;2009-06-01
Elba;226;Elbasan;elbasan;;2010-07-18
Ethi;430;Ethiopic (Geʻez);éthiopien (geʻez, guèze);Ethiopic;2004-10-25
Geor;240;Georgian (Mkhedruli);géorgien (mkhédrouli);Georgian;2004-05-29
Geok;241;Khutsuri (Asomtavruli and Nuskhuri);khoutsouri (assomtavrouli et nouskhouri);Georgian;2012-10-16
Glag;225;Glagolitic;glagolitique;Glagolitic;2006-06-21
Goth;206;Gothic;gotique;Gothic;2004-05-01
Gran;343;Grantha;grantha;;2009-11-11
Grek;200;Greek;grec;Greek;2004-05-01
Gujr;320;Gujarati;goudjarâtî (gujrâtî);Gujarati;2004-05-01
Guru;310;Gurmukhi;gourmoukhî;Gurmukhi;2004-05-01
Hang;286;Hangul (Hangŭl, Hangeul);hangûl (hangŭl, hangeul);Hangul;2004-05-29
Hani;500;Han (Hanzi, Kanji, Hanja);idéogrammes han (sinogrammes);Han;2009-02-23
Hano;371;Hanunoo (Hanunóo);hanounóo;Hanunoo;2004-05-29
Hans;501;Han (Simplified variant);idéogrammes han (variante simplifiée);;2004-05-29
Hant;502;Han (Traditional variant);idéogrammes han (variante traditionnelle);;2004-05-29
Hatr;127;Hatran;hatrénien;;2012-11-01
Hebr;125;Hebrew;hébreu;Hebrew;2004-05-01
Hira;410;Hiragana;hiragana;Hiragana;2004-05-01
Hluw;080;Anatolian Hieroglyphs (Luwian Hieroglyphs, Hittite Hieroglyphs);hiéroglyphes anatoliens (hiéroglyphes louvites, hiéroglyphes hittites);;2011-12-09
Hmng;450;Pahawh Hmong;pahawh hmong;;2004-05-01
Hrkt;412;Japanese syllabaries (alias for Hiragana + Katakana);syllabaires japonais (alias pour hiragana + katakana);Katakana_Or_Hiragana;2011-06-21
Hung;176;Old Hungarian (Hungarian Runic);runes hongroises (ancien hongrois);;2012-10-16
Inds;610;Indus (Harappan);indus;;2004-05-01
Ital;210;Old Italic (Etruscan, Oscan, etc.);ancien italique (étrusque, osque, etc.);Old_Italic;2004-05-29
Java;361;Javanese;javanais;Javanese;2009-06-01
Jpan;413;Japanese (alias for Han + Hiragana + Katakana);japonais (alias pour han + hiragana + katakana);;2006-06-21
Jurc;510;Jurchen;jurchen;;2010-12-21
Kali;357;Kayah Li;kayah li;Kayah_Li;2007-07-02
Kana;411;Katakana;katakana;Katakana;2004-05-01
Khar;305;Kharoshthi;kharochthî;Kharoshthi;2006-06-21
Khmr;355;Khmer;khmer;Khmer;2004-05-29
Khoj;322;Khojki;khojkî;;2011-06-21
Knda;345;Kannada;kannara (canara);Kannada;2004-05-29
Kore;287;Korean (alias for Hangul + Han);coréen (alias pour hangûl + han);;2007-06-13
Kpel;436;Kpelle;kpèllé;;2010-03-26
Kthi;317;Kaithi;kaithî;Kaithi;2009-06-01
Lana;351;Tai Tham (Lanna);taï tham (lanna);Tai_Tham;2009-06-01
Laoo;356;Lao;laotien;Lao;2004-05-01
Latf;217;Latin (Fraktur variant);latin (variante brisée);;2004-05-01
Latg;216;Latin (Gaelic variant);latin (variante gaélique);;2004-05-01
Latn;215;Latin;latin;Latin;2004-05-01
Lepc;335;Lepcha (Róng);lepcha (róng);Lepcha;2007-07-02
Limb;336;Limbu;limbou;Limbu;2004-05-29
Lina;400;Linear A;linéaire A;;2004-05-01
Linb;401;Linear B;linéaire B;Linear_B;2004-05-29
Lisu;399;Lisu (Fraser);lisu (Fraser);Lisu;2009-06-01
Loma;437;Loma;loma;;2010-03-26
Lyci;202;Lycian;lycien;Lycian;2007-07-02
Lydi;116;Lydian;lydien;Lydian;2007-07-02
Mahj;314;Mahajani;mahâjanî;;2012-10-16
Mand;140;Mandaic, Mandaean;mandéen;Mandaic;2010-07-23
Mani;139;Manichaean;manichéen;;2007-07-15
Maya;090;Mayan hieroglyphs;hiéroglyphes mayas;;2004-05-01
Mend;438;Mende Kikakui;mendé kikakui;;2013-10-12
Merc;101;Meroitic Cursive;cursif méroïtique;Meroitic_Cursive;2012-02-06
Mero;100;Meroitic Hieroglyphs;hiéroglyphes méroïtiques;Meroitic_Hieroglyphs;2012-02-06
Mlym;347;Malayalam;malayâlam;Malayalam;2004-05-01
Modi;323;Modi, Moḍī;modî;;2013-10-12
Moon;218;Moon (Moon code, Moon script, Moon type);écriture Moon;;2006-12-11
Mong;145;Mongolian;mongol;Mongolian;2004-05-01
Mroo;199;Mro, Mru;mro;;2010-12-21
Mtei;337;Meitei Mayek (Meithei, Meetei);meitei mayek;Meetei_Mayek;2009-06-01
Mult;323; Multani;multanî;;2012-11-01
Mymr;350;Myanmar (Burmese);birman;Myanmar;2004-05-01
Narb;106;Old North Arabian (Ancient North Arabian);nord-arabique;;2010-03-26
Nbat;159;Nabataean;nabatéen;;2010-03-26
Nkgb;420;Nakhi Geba ('Na-'Khi ²Ggŏ-¹baw, Naxi Geba);nakhi géba;;2009-02-23
Nkoo;165;N’Ko;n’ko;Nko;2006-10-10
Nshu;499;Nüshu;nüshu;;2010-12-21
Ogam;212;Ogham;ogam;Ogham;2004-05-01
Olck;261;Ol Chiki (Ol Cemet’, Ol, Santali);ol tchiki;Ol_Chiki;2007-07-02
Orkh;175;Old Turkic, Orkhon Runic;orkhon;Old_Turkic;2009-06-01
Orya;327;Oriya;oriyâ;Oriya;2004-05-01
Osma;260;Osmanya;osmanais;Osmanya;2004-05-01
Palm;126;Palmyrene;palmyrénien;;2010-03-26
Pauc;263;Pau Cin Hau;paou chin haou;;2013-10-12
Perm;227;Old Permic;ancien permien;;2004-05-01
Phag;331;Phags-pa;’phags pa;Phags_Pa;2006-10-10
Phli;131;Inscriptional Pahlavi;pehlevi des inscriptions;Inscriptional_Pahlavi;2009-06-01
Phlp;132;Psalter Pahlavi;pehlevi des psautiers;;2007-11-26
Phlv;133;Book Pahlavi;pehlevi des livres;;2007-07-15
Phnx;115;Phoenician;phénicien;Phoenician;2006-10-10
Plrd;282;Miao (Pollard);miao (Pollard);Miao;2012-02-06
Prti;130;Inscriptional Parthian;parthe des inscriptions;Inscriptional_Parthian;2009-06-01
Qaaa;900;Reserved for private use (start);réservé à l’usage privé (début);;2004-05-29
Qabx;949;Reserved for private use (end);réservé à l’usage privé (fin);;2004-05-29
Rjng;363;Rejang (Redjang, Kaganga);redjang (kaganga);Rejang;2009-02-23
Roro;620;Rongorongo;rongorongo;;2004-05-01
Runr;211;Runic;runique;Runic;2004-05-01
Samr;123;Samaritan;samaritain;Samaritan;2009-06-01
Sara;292;Sarati;sarati;;2004-05-29
Sarb;105;Old South Arabian;sud-arabique, himyarite;Old_South_Arabian;2009-06-01
Saur;344;Saurashtra;saurachtra;Saurashtra;2007-07-02
Sgnw;095;SignWriting;SignÉcriture, SignWriting;;2006-10-10
Shaw;281;Shavian (Shaw);shavien (Shaw);Shavian;2004-05-01
Shrd;319;Sharada, Śāradā;charada, shard;Sharada;2012-02-06
Sidd;302;Siddham, Siddhaṃ, Siddhamātṛkā;siddham;;2013-10-12
Sind;318;Khudawadi, Sindhi;khoudawadî, sindhî;;2010-12-21
Sinh;348;Sinhala;singhalais;Sinhala;2004-05-01
Sora;398;Sora Sompeng;sora sompeng;Sora_Sompeng;2012-02-06
Sund;362;Sundanese;sundanais;Sundanese;2007-07-02
Sylo;316;Syloti Nagri;sylotî nâgrî;Syloti_Nagri;2006-06-21
Syrc;135;Syriac;syriaque;Syriac;2004-05-01
Syre;138;Syriac (Estrangelo variant);syriaque (variante estranghélo);;2004-05-01
Syrj;137;Syriac (Western variant);syriaque (variante occidentale);;2004-05-01
Syrn;136;Syriac (Eastern variant);syriaque (variante orientale);;2004-05-01
Tagb;373;Tagbanwa;tagbanoua;Tagbanwa;2004-05-01
Takr;321;Takri, Ṭākrī, Ṭāṅkrī;tâkrî;Takri;2012-02-06
Tale;353;Tai Le;taï-le;Tai_Le;2004-10-25
Talu;354;New Tai Lue;nouveau taï-lue;New_Tai_Lue;2006-06-21
Taml;346;Tamil;tamoul;Tamil;2004-05-01
Tang;520;Tangut;tangoute;;2010-12-21
Tavt;359;Tai Viet;taï viêt;Tai_Viet;2009-06-01
Telu;340;Telugu;télougou;Telugu;2004-05-01
Teng;290;Tengwar;tengwar;;2004-05-01
Tfng;120;Tifinagh (Berber);tifinagh (berbère);Tifinagh;2006-06-21
Tglg;370;Tagalog (Baybayin, Alibata);tagal (baybayin, alibata);Tagalog;2009-02-23
Thaa;170;Thaana;thâna;Thaana;2004-05-01
Thai;352;Thai;thaï;Thai;2004-05-01
Tibt;330;Tibetan;tibétain;Tibetan;2004-05-01
Tirh;326;Tirhuta;tirhouta;;2011-12-09
Ugar;040;Ugaritic;ougaritique;Ugaritic;2004-05-01
Vaii;470;Vai;vaï;Vai;2007-07-02
Visp;280;Visible Speech;parole visible;;2004-05-01
Wara;262;Warang Citi (Varang Kshiti);warang citi;;2009-11-11
Wole;480;Woleai;woléaï;;2010-12-21
Xpeo;030;Old Persian;cunéiforme persépolitain;Old_Persian;2006-06-21
Xsux;020;Cuneiform, Sumero-Akkadian;cunéiforme suméro-akkadien;Cuneiform;2006-10-10
Yiii;460;Yi;yi;Yi;2004-05-01
Zinh;994;Code for inherited script;codet pour écriture héritée;Inherited;2009-02-23
Zmth;995;Mathematical notation;notation mathématique;;2007-11-26
Zsym;996;Symbols;symboles;;2007-11-26
Zxxx;997;Code for unwritten documents;codet pour les documents non écrits;;2011-06-21
Zyyy;998;Code for undetermined script;codet pour écriture indéterminée;Common;2004-05-29
Zzzz;999;Code for uncoded script;codet pour écriture non codée;Unknown;2006-10-10

474
lib/babelfish/data/opensubtitles_languages.txt Executable file
View File

@@ -0,0 +1,474 @@
IdSubLanguage ISO639 LanguageName UploadEnabled WebEnabled
aar aa Afar, afar 0 0
abk ab Abkhazian 0 0
ace Achinese 0 0
ach Acoli 0 0
ada Adangme 0 0
ady adyghé 0 0
afa Afro-Asiatic (Other) 0 0
afh Afrihili 0 0
afr af Afrikaans 1 0
ain Ainu 0 0
aka ak Akan 0 0
akk Akkadian 0 0
alb sq Albanian 1 1
ale Aleut 0 0
alg Algonquian languages 0 0
alt Southern Altai 0 0
amh am Amharic 0 0
ang English, Old (ca.450-1100) 0 0
apa Apache languages 0 0
ara ar Arabic 1 1
arc Aramaic 0 0
arg an Aragonese 0 0
arm hy Armenian 1 0
arn Araucanian 0 0
arp Arapaho 0 0
art Artificial (Other) 0 0
arw Arawak 0 0
asm as Assamese 0 0
ast Asturian, Bable 0 0
ath Athapascan languages 0 0
aus Australian languages 0 0
ava av Avaric 0 0
ave ae Avestan 0 0
awa Awadhi 0 0
aym ay Aymara 0 0
aze az Azerbaijani 0 0
bad Banda 0 0
bai Bamileke languages 0 0
bak ba Bashkir 0 0
bal Baluchi 0 0
bam bm Bambara 0 0
ban Balinese 0 0
baq eu Basque 1 1
bas Basa 0 0
bat Baltic (Other) 0 0
bej Beja 0 0
bel be Belarusian 0 0
bem Bemba 0 0
ben bn Bengali 1 0
ber Berber (Other) 0 0
bho Bhojpuri 0 0
bih bh Bihari 0 0
bik Bikol 0 0
bin Bini 0 0
bis bi Bislama 0 0
bla Siksika 0 0
bnt Bantu (Other) 0 0
bos bs Bosnian 1 0
bra Braj 0 0
bre br Breton 1 0
btk Batak (Indonesia) 0 0
bua Buriat 0 0
bug Buginese 0 0
bul bg Bulgarian 1 1
bur my Burmese 1 0
byn Blin 0 0
cad Caddo 0 0
cai Central American Indian (Other) 0 0
car Carib 0 0
cat ca Catalan 1 1
cau Caucasian (Other) 0 0
ceb Cebuano 0 0
cel Celtic (Other) 0 0
cha ch Chamorro 0 0
chb Chibcha 0 0
che ce Chechen 0 0
chg Chagatai 0 0
chi zh Chinese 1 1
chk Chuukese 0 0
chm Mari 0 0
chn Chinook jargon 0 0
cho Choctaw 0 0
chp Chipewyan 0 0
chr Cherokee 0 0
chu cu Church Slavic 0 0
chv cv Chuvash 0 0
chy Cheyenne 0 0
cmc Chamic languages 0 0
cop Coptic 0 0
cor kw Cornish 0 0
cos co Corsican 0 0
cpe Creoles and pidgins, English based (Other) 0 0
cpf Creoles and pidgins, French-based (Other) 0 0
cpp Creoles and pidgins, Portuguese-based (Other) 0 0
cre cr Cree 0 0
crh Crimean Tatar 0 0
crp Creoles and pidgins (Other) 0 0
csb Kashubian 0 0
cus Cushitic (Other)' couchitiques, autres langues 0 0
cze cs Czech 1 1
dak Dakota 0 0
dan da Danish 1 1
dar Dargwa 0 0
day Dayak 0 0
del Delaware 0 0
den Slave (Athapascan) 0 0
dgr Dogrib 0 0
din Dinka 0 0
div dv Divehi 0 0
doi Dogri 0 0
dra Dravidian (Other) 0 0
dua Duala 0 0
dum Dutch, Middle (ca.1050-1350) 0 0
dut nl Dutch 1 1
dyu Dyula 0 0
dzo dz Dzongkha 0 0
efi Efik 0 0
egy Egyptian (Ancient) 0 0
eka Ekajuk 0 0
elx Elamite 0 0
eng en English 1 1
enm English, Middle (1100-1500) 0 0
epo eo Esperanto 1 0
est et Estonian 1 1
ewe ee Ewe 0 0
ewo Ewondo 0 0
fan Fang 0 0
fao fo Faroese 0 0
fat Fanti 0 0
fij fj Fijian 0 0
fil Filipino 0 0
fin fi Finnish 1 1
fiu Finno-Ugrian (Other) 0 0
fon Fon 0 0
fre fr French 1 1
frm French, Middle (ca.1400-1600) 0 0
fro French, Old (842-ca.1400) 0 0
fry fy Frisian 0 0
ful ff Fulah 0 0
fur Friulian 0 0
gaa Ga 0 0
gay Gayo 0 0
gba Gbaya 0 0
gem Germanic (Other) 0 0
geo ka Georgian 1 1
ger de German 1 1
gez Geez 0 0
gil Gilbertese 0 0
gla gd Gaelic 0 0
gle ga Irish 0 0
glg gl Galician 1 1
glv gv Manx 0 0
gmh German, Middle High (ca.1050-1500) 0 0
goh German, Old High (ca.750-1050) 0 0
gon Gondi 0 0
gor Gorontalo 0 0
got Gothic 0 0
grb Grebo 0 0
grc Greek, Ancient (to 1453) 0 0
ell el Greek 1 1
grn gn Guarani 0 0
guj gu Gujarati 0 0
gwi Gwich´in 0 0
hai Haida 0 0
hat ht Haitian 0 0
hau ha Hausa 0 0
haw Hawaiian 0 0
heb he Hebrew 1 1
her hz Herero 0 0
hil Hiligaynon 0 0
him Himachali 0 0
hin hi Hindi 1 1
hit Hittite 0 0
hmn Hmong 0 0
hmo ho Hiri Motu 0 0
hrv hr Croatian 1 1
hun hu Hungarian 1 1
hup Hupa 0 0
iba Iban 0 0
ibo ig Igbo 0 0
ice is Icelandic 1 1
ido io Ido 0 0
iii ii Sichuan Yi 0 0
ijo Ijo 0 0
iku iu Inuktitut 0 0
ile ie Interlingue 0 0
ilo Iloko 0 0
ina ia Interlingua (International Auxiliary Language Asso 0 0
inc Indic (Other) 0 0
ind id Indonesian 1 1
ine Indo-European (Other) 0 0
inh Ingush 0 0
ipk ik Inupiaq 0 0
ira Iranian (Other) 0 0
iro Iroquoian languages 0 0
ita it Italian 1 1
jav jv Javanese 0 0
jpn ja Japanese 1 1
jpr Judeo-Persian 0 0
jrb Judeo-Arabic 0 0
kaa Kara-Kalpak 0 0
kab Kabyle 0 0
kac Kachin 0 0
kal kl Kalaallisut 0 0
kam Kamba 0 0
kan kn Kannada 0 0
kar Karen 0 0
kas ks Kashmiri 0 0
kau kr Kanuri 0 0
kaw Kawi 0 0
kaz kk Kazakh 1 0
kbd Kabardian 0 0
kha Khasi 0 0
khi Khoisan (Other) 0 0
khm km Khmer 1 1
kho Khotanese 0 0
kik ki Kikuyu 0 0
kin rw Kinyarwanda 0 0
kir ky Kirghiz 0 0
kmb Kimbundu 0 0
kok Konkani 0 0
kom kv Komi 0 0
kon kg Kongo 0 0
kor ko Korean 1 1
kos Kosraean 0 0
kpe Kpelle 0 0
krc Karachay-Balkar 0 0
kro Kru 0 0
kru Kurukh 0 0
kua kj Kuanyama 0 0
kum Kumyk 0 0
kur ku Kurdish 0 0
kut Kutenai 0 0
lad Ladino 0 0
lah Lahnda 0 0
lam Lamba 0 0
lao lo Lao 0 0
lat la Latin 0 0
lav lv Latvian 1 0
lez Lezghian 0 0
lim li Limburgan 0 0
lin ln Lingala 0 0
lit lt Lithuanian 1 0
lol Mongo 0 0
loz Lozi 0 0
ltz lb Luxembourgish 1 0
lua Luba-Lulua 0 0
lub lu Luba-Katanga 0 0
lug lg Ganda 0 0
lui Luiseno 0 0
lun Lunda 0 0
luo Luo (Kenya and Tanzania) 0 0
lus lushai 0 0
mac mk Macedonian 1 1
mad Madurese 0 0
mag Magahi 0 0
mah mh Marshallese 0 0
mai Maithili 0 0
mak Makasar 0 0
mal ml Malayalam 1 0
man Mandingo 0 0
mao mi Maori 0 0
map Austronesian (Other) 0 0
mar mr Marathi 0 0
mas Masai 0 0
may ms Malay 1 1
mdf Moksha 0 0
mdr Mandar 0 0
men Mende 0 0
mga Irish, Middle (900-1200) 0 0
mic Mi'kmaq 0 0
min Minangkabau 0 0
mis Miscellaneous languages 0 0
mkh Mon-Khmer (Other) 0 0
mlg mg Malagasy 0 0
mlt mt Maltese 0 0
mnc Manchu 0 0
mni Manipuri 0 0
mno Manobo languages 0 0
moh Mohawk 0 0
mol mo Moldavian 0 0
mon mn Mongolian 1 0
mos Mossi 0 0
mwl Mirandese 0 0
mul Multiple languages 0 0
mun Munda languages 0 0
mus Creek 0 0
mwr Marwari 0 0
myn Mayan languages 0 0
myv Erzya 0 0
nah Nahuatl 0 0
nai North American Indian 0 0
nap Neapolitan 0 0
nau na Nauru 0 0
nav nv Navajo 0 0
nbl nr Ndebele, South 0 0
nde nd Ndebele, North 0 0
ndo ng Ndonga 0 0
nds Low German 0 0
nep ne Nepali 0 0
new Nepal Bhasa 0 0
nia Nias 0 0
nic Niger-Kordofanian (Other) 0 0
niu Niuean 0 0
nno nn Norwegian Nynorsk 0 0
nob nb Norwegian Bokmal 0 0
nog Nogai 0 0
non Norse, Old 0 0
nor no Norwegian 1 1
nso Northern Sotho 0 0
nub Nubian languages 0 0
nwc Classical Newari 0 0
nya ny Chichewa 0 0
nym Nyamwezi 0 0
nyn Nyankole 0 0
nyo Nyoro 0 0
nzi Nzima 0 0
oci oc Occitan 1 1
oji oj Ojibwa 0 0
ori or Oriya 0 0
orm om Oromo 0 0
osa Osage 0 0
oss os Ossetian 0 0
ota Turkish, Ottoman (1500-1928) 0 0
oto Otomian languages 0 0
paa Papuan (Other) 0 0
pag Pangasinan 0 0
pal Pahlavi 0 0
pam Pampanga 0 0
pan pa Panjabi 0 0
pap Papiamento 0 0
pau Palauan 0 0
peo Persian, Old (ca.600-400 B.C.) 0 0
per fa Persian 1 1
phi Philippine (Other) 0 0
phn Phoenician 0 0
pli pi Pali 0 0
pol pl Polish 1 1
pon Pohnpeian 0 0
por pt Portuguese 1 1
pra Prakrit languages 0 0
pro Provençal, Old (to 1500) 0 0
pus ps Pushto 0 0
que qu Quechua 0 0
raj Rajasthani 0 0
rap Rapanui 0 0
rar Rarotongan 0 0
roa Romance (Other) 0 0
roh rm Raeto-Romance 0 0
rom Romany 0 0
run rn Rundi 0 0
rup Aromanian 0 0
rus ru Russian 1 1
sad Sandawe 0 0
sag sg Sango 0 0
sah Yakut 0 0
sai South American Indian (Other) 0 0
sal Salishan languages 0 0
sam Samaritan Aramaic 0 0
san sa Sanskrit 0 0
sas Sasak 0 0
sat Santali 0 0
scc sr Serbian 1 1
scn Sicilian 0 0
sco Scots 0 0
sel Selkup 0 0
sem Semitic (Other) 0 0
sga Irish, Old (to 900) 0 0
sgn Sign Languages 0 0
shn Shan 0 0
sid Sidamo 0 0
sin si Sinhalese 1 1
sio Siouan languages 0 0
sit Sino-Tibetan (Other) 0 0
sla Slavic (Other) 0 0
slo sk Slovak 1 1
slv sl Slovenian 1 1
sma Southern Sami 0 0
sme se Northern Sami 0 0
smi Sami languages (Other) 0 0
smj Lule Sami 0 0
smn Inari Sami 0 0
smo sm Samoan 0 0
sms Skolt Sami 0 0
sna sn Shona 0 0
snd sd Sindhi 0 0
snk Soninke 0 0
sog Sogdian 0 0
som so Somali 0 0
son Songhai 0 0
sot st Sotho, Southern 0 0
spa es Spanish 1 1
srd sc Sardinian 0 0
srr Serer 0 0
ssa Nilo-Saharan (Other) 0 0
ssw ss Swati 0 0
suk Sukuma 0 0
sun su Sundanese 0 0
sus Susu 0 0
sux Sumerian 0 0
swa sw Swahili 1 0
swe sv Swedish 1 1
syr Syriac 1 0
tah ty Tahitian 0 0
tai Tai (Other) 0 0
tam ta Tamil 1 0
tat tt Tatar 0 0
tel te Telugu 1 0
tem Timne 0 0
ter Tereno 0 0
tet Tetum 0 0
tgk tg Tajik 0 0
tgl tl Tagalog 1 1
tha th Thai 1 1
tib bo Tibetan 0 0
tig Tigre 0 0
tir ti Tigrinya 0 0
tiv Tiv 0 0
tkl Tokelau 0 0
tlh Klingon 0 0
tli Tlingit 0 0
tmh Tamashek 0 0
tog Tonga (Nyasa) 0 0
ton to Tonga (Tonga Islands) 0 0
tpi Tok Pisin 0 0
tsi Tsimshian 0 0
tsn tn Tswana 0 0
tso ts Tsonga 0 0
tuk tk Turkmen 0 0
tum Tumbuka 0 0
tup Tupi languages 0 0
tur tr Turkish 1 1
tut Altaic (Other) 0 0
tvl Tuvalu 0 0
twi tw Twi 0 0
tyv Tuvinian 0 0
udm Udmurt 0 0
uga Ugaritic 0 0
uig ug Uighur 0 0
ukr uk Ukrainian 1 1
umb Umbundu 0 0
und Undetermined 0 0
urd ur Urdu 1 0
uzb uz Uzbek 0 0
vai Vai 0 0
ven ve Venda 0 0
vie vi Vietnamese 1 1
vol vo Volapük 0 0
vot Votic 0 0
wak Wakashan languages 0 0
wal Walamo 0 0
war Waray 0 0
was Washo 0 0
wel cy Welsh 0 0
wen Sorbian languages 0 0
wln wa Walloon 0 0
wol wo Wolof 0 0
xal Kalmyk 0 0
xho xh Xhosa 0 0
yao Yao 0 0
yap Yapese 0 0
yid yi Yiddish 0 0
yor yo Yoruba 0 0
ypk Yupik languages 0 0
zap Zapotec 0 0
zen Zenaga 0 0
zha za Zhuang 0 0
znd Zande 0 0
zul zu Zulu 0 0
zun Zuni 0 0
rum ro Romanian 1 1
pob pb Brazilian 1 1
mne Montenegrin 1 0

85
lib/babelfish/exceptions.py Executable file
View File

@@ -0,0 +1,85 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
class Error(Exception):
"""Base class for all exceptions in babelfish"""
pass
class LanguageError(Error, AttributeError):
"""Base class for all language exceptions in babelfish"""
pass
class LanguageConvertError(LanguageError):
"""Exception raised by converters when :meth:`~babelfish.converters.LanguageConverter.convert` fails
:param string alpha3: alpha3 code that failed conversion
:param country: country code that failed conversion, if any
:type country: string or None
:param script: script code that failed conversion, if any
:type script: string or None
"""
def __init__(self, alpha3, country=None, script=None):
self.alpha3 = alpha3
self.country = country
self.script = script
def __str__(self):
s = self.alpha3
if self.country is not None:
s += '-' + self.country
if self.script is not None:
s += '-' + self.script
return s
class LanguageReverseError(LanguageError):
"""Exception raised by converters when :meth:`~babelfish.converters.LanguageReverseConverter.reverse` fails
:param string code: code that failed reverse conversion
"""
def __init__(self, code):
self.code = code
def __str__(self):
return repr(self.code)
class CountryError(Error, AttributeError):
"""Base class for all country exceptions in babelfish"""
pass
class CountryConvertError(CountryError):
"""Exception raised by converters when :meth:`~babelfish.converters.CountryConverter.convert` fails
:param string alpha2: alpha2 code that failed conversion
"""
def __init__(self, alpha2):
self.alpha2 = alpha2
def __str__(self):
return self.alpha2
class CountryReverseError(CountryError):
"""Exception raised by converters when :meth:`~babelfish.converters.CountryReverseConverter.reverse` fails
:param string code: code that failed reverse conversion
"""
def __init__(self, code):
self.code = code
def __str__(self):
return repr(self.code)

186
lib/babelfish/language.py Executable file
View File

@@ -0,0 +1,186 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
from collections import namedtuple
from functools import partial
import os
# from pkg_resources import resource_stream # @UnresolvedImport
from .converters import ConverterManager
from .country import Country
from .exceptions import LanguageConvertError
from .script import Script
from . import basestr
LANGUAGES = set()
LANGUAGE_MATRIX = []
#: The namedtuple used in the :data:`LANGUAGE_MATRIX`
IsoLanguage = namedtuple('IsoLanguage', ['alpha3', 'alpha3b', 'alpha3t', 'alpha2', 'scope', 'type', 'name', 'comment'])
f = open(os.path.join(os.path.dirname(__file__), 'data/iso-639-3.tab'))
f.readline()
for l in f:
iso_language = IsoLanguage(*l.decode('utf-8').split('\t'))
LANGUAGES.add(iso_language.alpha3)
LANGUAGE_MATRIX.append(iso_language)
f.close()
class LanguageConverterManager(ConverterManager):
""":class:`~babelfish.converters.ConverterManager` for language converters"""
entry_point = 'babelfish.language_converters'
internal_converters = ['alpha2 = babelfish.converters.alpha2:Alpha2Converter',
'alpha3b = babelfish.converters.alpha3b:Alpha3BConverter',
'alpha3t = babelfish.converters.alpha3t:Alpha3TConverter',
'name = babelfish.converters.name:NameConverter',
'scope = babelfish.converters.scope:ScopeConverter',
'type = babelfish.converters.type:LanguageTypeConverter',
'opensubtitles = babelfish.converters.opensubtitles:OpenSubtitlesConverter']
language_converters = LanguageConverterManager()
class LanguageMeta(type):
"""The :class:`Language` metaclass
Dynamically redirect :meth:`Language.frommycode` to :meth:`Language.fromcode` with the ``mycode`` `converter`
"""
def __getattr__(cls, name):
if name.startswith('from'):
return partial(cls.fromcode, converter=name[4:])
return type.__getattribute__(cls, name)
class Language(LanguageMeta(str('LanguageBase'), (object,), {})):
"""A human language
A human language is composed of a language part following the ISO-639
standard and can be country-specific when a :class:`~babelfish.country.Country`
is specified.
The :class:`Language` is extensible with custom converters (see :ref:`custom_converters`)
:param string language: the language as a 3-letter ISO-639-3 code
:param country: the country (if any) as a 2-letter ISO-3166 code or :class:`~babelfish.country.Country` instance
:type country: string or :class:`~babelfish.country.Country` or None
:param script: the script (if any) as a 4-letter ISO-15924 code or :class:`~babelfish.script.Script` instance
:type script: string or :class:`~babelfish.script.Script` or None
:param unknown: the unknown language as a three-letters ISO-639-3 code to use as fallback
:type unknown: string or None
:raise: ValueError if the language could not be recognized and `unknown` is ``None``
"""
def __init__(self, language, country=None, script=None, unknown=None):
if unknown is not None and language not in LANGUAGES:
language = unknown
if language not in LANGUAGES:
raise ValueError('%r is not a valid language' % language)
self.alpha3 = language
self.country = None
if isinstance(country, Country):
self.country = country
elif country is None:
self.country = None
else:
self.country = Country(country)
self.script = None
if isinstance(script, Script):
self.script = script
elif script is None:
self.script = None
else:
self.script = Script(script)
@classmethod
def fromcode(cls, code, converter):
"""Create a :class:`Language` by its `code` using `converter` to
:meth:`~babelfish.converters.LanguageReverseConverter.reverse` it
:param string code: the code to reverse
:param string converter: name of the :class:`~babelfish.converters.LanguageReverseConverter` to use
:return: the corresponding :class:`Language` instance
:rtype: :class:`Language`
"""
return cls(*language_converters[converter].reverse(code))
@classmethod
def fromietf(cls, ietf):
"""Create a :class:`Language` by from an IETF language code
:param string ietf: the ietf code
:return: the corresponding :class:`Language` instance
:rtype: :class:`Language`
"""
subtags = ietf.split('-')
language_subtag = subtags.pop(0).lower()
if len(language_subtag) == 2:
language = cls.fromalpha2(language_subtag)
else:
language = cls(language_subtag)
while subtags:
subtag = subtags.pop(0)
if len(subtag) == 2:
language.country = Country(subtag.upper())
else:
language.script = Script(subtag.capitalize())
if language.script is not None:
if subtags:
raise ValueError('Wrong IETF format. Unmatched subtags: %r' % subtags)
break
return language
def __getstate__(self):
return self.alpha3, self.country, self.script
def __setstate__(self, state):
self.alpha3, self.country, self.script = state
def __getattr__(self, name):
alpha3 = self.alpha3
country = self.country.alpha2 if self.country is not None else None
script = self.script.code if self.script is not None else None
try:
return language_converters[name].convert(alpha3, country, script)
except KeyError:
raise AttributeError(name)
def __hash__(self):
return hash(str(self))
def __eq__(self, other):
if isinstance(other, basestr):
return str(self) == other
if not isinstance(other, Language):
return False
return (self.alpha3 == other.alpha3 and
self.country == other.country and
self.script == other.script)
def __ne__(self, other):
return not self == other
def __bool__(self):
return self.alpha3 != 'und'
__nonzero__ = __bool__
def __repr__(self):
return '<Language [%s]>' % self
def __str__(self):
try:
s = self.alpha2
except LanguageConvertError:
s = self.alpha3
if self.country is not None:
s += '-' + str(self.country)
if self.script is not None:
s += '-' + str(self.script)
return s

78
lib/babelfish/script.py Executable file
View File

@@ -0,0 +1,78 @@
# -*- coding: utf-8 -*-
#
# Copyright (c) 2013 the BabelFish authors. All rights reserved.
# Use of this source code is governed by the 3-clause BSD license
# that can be found in the LICENSE file.
#
from __future__ import unicode_literals
import os
from collections import namedtuple
# from pkg_resources import resource_stream # @UnresolvedImport
from . import basestr
#: Script code to script name mapping
SCRIPTS = {}
#: List of countries in the ISO-15924 as namedtuple of code, number, name, french_name, pva and date
SCRIPT_MATRIX = []
#: The namedtuple used in the :data:`SCRIPT_MATRIX`
IsoScript = namedtuple('IsoScript', ['code', 'number', 'name', 'french_name', 'pva', 'date'])
f = open(os.path.join(os.path.dirname(__file__), 'data/iso15924-utf8-20131012.txt'))
f.readline()
for l in f:
l = l.decode('utf-8').strip()
if not l or l.startswith('#'):
continue
script = IsoScript._make(l.split(';'))
SCRIPT_MATRIX.append(script)
SCRIPTS[script.code] = script.name
f.close()
class Script(object):
"""A human writing system
A script is represented by a 4-letter code from the ISO-15924 standard
:param string script: 4-letter ISO-15924 script code
"""
def __init__(self, script):
if script not in SCRIPTS:
raise ValueError('%r is not a valid script' % script)
#: ISO-15924 4-letter script code
self.code = script
@property
def name(self):
"""English name of the script"""
return SCRIPTS[self.code]
def __getstate__(self):
return self.code
def __setstate__(self, state):
self.code = state
def __hash__(self):
return hash(self.code)
def __eq__(self, other):
if isinstance(other, basestr):
return self.code == other
if not isinstance(other, Script):
return False
return self.code == other.code
def __ne__(self, other):
return not self == other
def __repr__(self):
return '<Script [%s]>' % self
def __str__(self):
return self.code

9
lib/dateutil/__init__.py Normal file
View File

@@ -0,0 +1,9 @@
"""
Copyright (c) 2003-2010 Gustavo Niemeyer <gustavo@niemeyer.net>
This module offers extensions to the standard python 2.3+
datetime module.
"""
__author__ = "Gustavo Niemeyer <gustavo@niemeyer.net>"
__license__ = "PSF License"
__version__ = "1.5.0.1"

92
lib/dateutil/easter.py Normal file
View File

@@ -0,0 +1,92 @@
"""
Copyright (c) 2003-2007 Gustavo Niemeyer <gustavo@niemeyer.net>
This module offers extensions to the standard python 2.3+
datetime module.
"""
__author__ = "Gustavo Niemeyer <gustavo@niemeyer.net>"
__license__ = "PSF License"
import datetime
__all__ = ["easter", "EASTER_JULIAN", "EASTER_ORTHODOX", "EASTER_WESTERN"]
EASTER_JULIAN = 1
EASTER_ORTHODOX = 2
EASTER_WESTERN = 3
def easter(year, method=EASTER_WESTERN):
"""
This method was ported from the work done by GM Arts,
on top of the algorithm by Claus Tondering, which was
based in part on the algorithm of Ouding (1940), as
quoted in "Explanatory Supplement to the Astronomical
Almanac", P. Kenneth Seidelmann, editor.
This algorithm implements three different easter
calculation methods:
1 - Original calculation in Julian calendar, valid in
dates after 326 AD
2 - Original method, with date converted to Gregorian
calendar, valid in years 1583 to 4099
3 - Revised method, in Gregorian calendar, valid in
years 1583 to 4099 as well
These methods are represented by the constants:
EASTER_JULIAN = 1
EASTER_ORTHODOX = 2
EASTER_WESTERN = 3
The default method is method 3.
More about the algorithm may be found at:
http://users.chariot.net.au/~gmarts/eastalg.htm
and
http://www.tondering.dk/claus/calendar.html
"""
if not (1 <= method <= 3):
raise ValueError, "invalid method"
# g - Golden year - 1
# c - Century
# h - (23 - Epact) mod 30
# i - Number of days from March 21 to Paschal Full Moon
# j - Weekday for PFM (0=Sunday, etc)
# p - Number of days from March 21 to Sunday on or before PFM
# (-6 to 28 methods 1 & 3, to 56 for method 2)
# e - Extra days to add for method 2 (converting Julian
# date to Gregorian date)
y = year
g = y % 19
e = 0
if method < 3:
# Old method
i = (19*g+15)%30
j = (y+y//4+i)%7
if method == 2:
# Extra dates to convert Julian to Gregorian date
e = 10
if y > 1600:
e = e+y//100-16-(y//100-16)//4
else:
# New method
c = y//100
h = (c-c//4-(8*c+13)//25+19*g+15)%30
i = h-(h//28)*(1-(h//28)*(29//(h+1))*((21-g)//11))
j = (y+y//4+i+2-c+c//4)%7
# p can be from -6 to 56 corresponding to dates 22 March to 23 May
# (later dates apply to method 2, although 23 May never actually occurs)
p = i-j+e
d = 1+(p+27+(p+6)//40)%31
m = 3+(p+26)//30
return datetime.date(int(y),int(m),int(d))

886
lib/dateutil/parser.py Normal file
View File

@@ -0,0 +1,886 @@
# -*- coding:iso-8859-1 -*-
"""
Copyright (c) 2003-2007 Gustavo Niemeyer <gustavo@niemeyer.net>
This module offers extensions to the standard python 2.3+
datetime module.
"""
__author__ = "Gustavo Niemeyer <gustavo@niemeyer.net>"
__license__ = "PSF License"
import datetime
import string
import time
import sys
import os
try:
from cStringIO import StringIO
except ImportError:
from StringIO import StringIO
import relativedelta
import tz
__all__ = ["parse", "parserinfo"]
# Some pointers:
#
# http://www.cl.cam.ac.uk/~mgk25/iso-time.html
# http://www.iso.ch/iso/en/prods-services/popstds/datesandtime.html
# http://www.w3.org/TR/NOTE-datetime
# http://ringmaster.arc.nasa.gov/tools/time_formats.html
# http://search.cpan.org/author/MUIR/Time-modules-2003.0211/lib/Time/ParseDate.pm
# http://stein.cshl.org/jade/distrib/docs/java.text.SimpleDateFormat.html
class _timelex(object):
def __init__(self, instream):
if isinstance(instream, basestring):
instream = StringIO(instream)
self.instream = instream
self.wordchars = ('abcdfeghijklmnopqrstuvwxyz'
'ABCDEFGHIJKLMNOPQRSTUVWXYZ_'
'<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>'
'<EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD><EFBFBD>')
self.numchars = '0123456789'
self.whitespace = ' \t\r\n'
self.charstack = []
self.tokenstack = []
self.eof = False
def get_token(self):
if self.tokenstack:
return self.tokenstack.pop(0)
seenletters = False
token = None
state = None
wordchars = self.wordchars
numchars = self.numchars
whitespace = self.whitespace
while not self.eof:
if self.charstack:
nextchar = self.charstack.pop(0)
else:
nextchar = self.instream.read(1)
while nextchar == '\x00':
nextchar = self.instream.read(1)
if not nextchar:
self.eof = True
break
elif not state:
token = nextchar
if nextchar in wordchars:
state = 'a'
elif nextchar in numchars:
state = '0'
elif nextchar in whitespace:
token = ' '
break # emit token
else:
break # emit token
elif state == 'a':
seenletters = True
if nextchar in wordchars:
token += nextchar
elif nextchar == '.':
token += nextchar
state = 'a.'
else:
self.charstack.append(nextchar)
break # emit token
elif state == '0':
if nextchar in numchars:
token += nextchar
elif nextchar == '.':
token += nextchar
state = '0.'
else:
self.charstack.append(nextchar)
break # emit token
elif state == 'a.':
seenletters = True
if nextchar == '.' or nextchar in wordchars:
token += nextchar
elif nextchar in numchars and token[-1] == '.':
token += nextchar
state = '0.'
else:
self.charstack.append(nextchar)
break # emit token
elif state == '0.':
if nextchar == '.' or nextchar in numchars:
token += nextchar
elif nextchar in wordchars and token[-1] == '.':
token += nextchar
state = 'a.'
else:
self.charstack.append(nextchar)
break # emit token
if (state in ('a.', '0.') and
(seenletters or token.count('.') > 1 or token[-1] == '.')):
l = token.split('.')
token = l[0]
for tok in l[1:]:
self.tokenstack.append('.')
if tok:
self.tokenstack.append(tok)
return token
def __iter__(self):
return self
def next(self):
token = self.get_token()
if token is None:
raise StopIteration
return token
def split(cls, s):
return list(cls(s))
split = classmethod(split)
class _resultbase(object):
def __init__(self):
for attr in self.__slots__:
setattr(self, attr, None)
def _repr(self, classname):
l = []
for attr in self.__slots__:
value = getattr(self, attr)
if value is not None:
l.append("%s=%s" % (attr, `value`))
return "%s(%s)" % (classname, ", ".join(l))
def __repr__(self):
return self._repr(self.__class__.__name__)
class parserinfo(object):
# m from a.m/p.m, t from ISO T separator
JUMP = [" ", ".", ",", ";", "-", "/", "'",
"at", "on", "and", "ad", "m", "t", "of",
"st", "nd", "rd", "th"]
WEEKDAYS = [("Mon", "Monday"),
("Tue", "Tuesday"),
("Wed", "Wednesday"),
("Thu", "Thursday"),
("Fri", "Friday"),
("Sat", "Saturday"),
("Sun", "Sunday")]
MONTHS = [("Jan", "January"),
("Feb", "February"),
("Mar", "March"),
("Apr", "April"),
("May", "May"),
("Jun", "June"),
("Jul", "July"),
("Aug", "August"),
("Sep", "September"),
("Oct", "October"),
("Nov", "November"),
("Dec", "December")]
HMS = [("h", "hour", "hours"),
("m", "minute", "minutes"),
("s", "second", "seconds")]
AMPM = [("am", "a"),
("pm", "p")]
UTCZONE = ["UTC", "GMT", "Z"]
PERTAIN = ["of"]
TZOFFSET = {}
def __init__(self, dayfirst=False, yearfirst=False):
self._jump = self._convert(self.JUMP)
self._weekdays = self._convert(self.WEEKDAYS)
self._months = self._convert(self.MONTHS)
self._hms = self._convert(self.HMS)
self._ampm = self._convert(self.AMPM)
self._utczone = self._convert(self.UTCZONE)
self._pertain = self._convert(self.PERTAIN)
self.dayfirst = dayfirst
self.yearfirst = yearfirst
self._year = time.localtime().tm_year
self._century = self._year//100*100
def _convert(self, lst):
dct = {}
for i in range(len(lst)):
v = lst[i]
if isinstance(v, tuple):
for v in v:
dct[v.lower()] = i
else:
dct[v.lower()] = i
return dct
def jump(self, name):
return name.lower() in self._jump
def weekday(self, name):
if len(name) >= 3:
try:
return self._weekdays[name.lower()]
except KeyError:
pass
return None
def month(self, name):
if len(name) >= 3:
try:
return self._months[name.lower()]+1
except KeyError:
pass
return None
def hms(self, name):
try:
return self._hms[name.lower()]
except KeyError:
return None
def ampm(self, name):
try:
return self._ampm[name.lower()]
except KeyError:
return None
def pertain(self, name):
return name.lower() in self._pertain
def utczone(self, name):
return name.lower() in self._utczone
def tzoffset(self, name):
if name in self._utczone:
return 0
return self.TZOFFSET.get(name)
def convertyear(self, year):
if year < 100:
year += self._century
if abs(year-self._year) >= 50:
if year < self._year:
year += 100
else:
year -= 100
return year
def validate(self, res):
# move to info
if res.year is not None:
res.year = self.convertyear(res.year)
if res.tzoffset == 0 and not res.tzname or res.tzname == 'Z':
res.tzname = "UTC"
res.tzoffset = 0
elif res.tzoffset != 0 and res.tzname and self.utczone(res.tzname):
res.tzoffset = 0
return True
class parser(object):
def __init__(self, info=None):
self.info = info or parserinfo()
def parse(self, timestr, default=None,
ignoretz=False, tzinfos=None,
**kwargs):
if not default:
default = datetime.datetime.now().replace(hour=0, minute=0,
second=0, microsecond=0)
res = self._parse(timestr, **kwargs)
if res is None:
raise ValueError, "unknown string format"
repl = {}
for attr in ["year", "month", "day", "hour",
"minute", "second", "microsecond"]:
value = getattr(res, attr)
if value is not None:
repl[attr] = value
ret = default.replace(**repl)
if res.weekday is not None and not res.day:
ret = ret+relativedelta.relativedelta(weekday=res.weekday)
if not ignoretz:
if callable(tzinfos) or tzinfos and res.tzname in tzinfos:
if callable(tzinfos):
tzdata = tzinfos(res.tzname, res.tzoffset)
else:
tzdata = tzinfos.get(res.tzname)
if isinstance(tzdata, datetime.tzinfo):
tzinfo = tzdata
elif isinstance(tzdata, basestring):
tzinfo = tz.tzstr(tzdata)
elif isinstance(tzdata, int):
tzinfo = tz.tzoffset(res.tzname, tzdata)
else:
raise ValueError, "offset must be tzinfo subclass, " \
"tz string, or int offset"
ret = ret.replace(tzinfo=tzinfo)
elif res.tzname and res.tzname in time.tzname:
ret = ret.replace(tzinfo=tz.tzlocal())
elif res.tzoffset == 0:
ret = ret.replace(tzinfo=tz.tzutc())
elif res.tzoffset:
ret = ret.replace(tzinfo=tz.tzoffset(res.tzname, res.tzoffset))
return ret
class _result(_resultbase):
__slots__ = ["year", "month", "day", "weekday",
"hour", "minute", "second", "microsecond",
"tzname", "tzoffset"]
def _parse(self, timestr, dayfirst=None, yearfirst=None, fuzzy=False):
info = self.info
if dayfirst is None:
dayfirst = info.dayfirst
if yearfirst is None:
yearfirst = info.yearfirst
res = self._result()
l = _timelex.split(timestr)
try:
# year/month/day list
ymd = []
# Index of the month string in ymd
mstridx = -1
len_l = len(l)
i = 0
while i < len_l:
# Check if it's a number
try:
value_repr = l[i]
value = float(value_repr)
except ValueError:
value = None
if value is not None:
# Token is a number
len_li = len(l[i])
i += 1
if (len(ymd) == 3 and len_li in (2, 4)
and (i >= len_l or (l[i] != ':' and
info.hms(l[i]) is None))):
# 19990101T23[59]
s = l[i-1]
res.hour = int(s[:2])
if len_li == 4:
res.minute = int(s[2:])
elif len_li == 6 or (len_li > 6 and l[i-1].find('.') == 6):
# YYMMDD or HHMMSS[.ss]
s = l[i-1]
if not ymd and l[i-1].find('.') == -1:
ymd.append(info.convertyear(int(s[:2])))
ymd.append(int(s[2:4]))
ymd.append(int(s[4:]))
else:
# 19990101T235959[.59]
res.hour = int(s[:2])
res.minute = int(s[2:4])
res.second, res.microsecond = _parsems(s[4:])
elif len_li == 8:
# YYYYMMDD
s = l[i-1]
ymd.append(int(s[:4]))
ymd.append(int(s[4:6]))
ymd.append(int(s[6:]))
elif len_li in (12, 14):
# YYYYMMDDhhmm[ss]
s = l[i-1]
ymd.append(int(s[:4]))
ymd.append(int(s[4:6]))
ymd.append(int(s[6:8]))
res.hour = int(s[8:10])
res.minute = int(s[10:12])
if len_li == 14:
res.second = int(s[12:])
elif ((i < len_l and info.hms(l[i]) is not None) or
(i+1 < len_l and l[i] == ' ' and
info.hms(l[i+1]) is not None)):
# HH[ ]h or MM[ ]m or SS[.ss][ ]s
if l[i] == ' ':
i += 1
idx = info.hms(l[i])
while True:
if idx == 0:
res.hour = int(value)
if value%1:
res.minute = int(60*(value%1))
elif idx == 1:
res.minute = int(value)
if value%1:
res.second = int(60*(value%1))
elif idx == 2:
res.second, res.microsecond = \
_parsems(value_repr)
i += 1
if i >= len_l or idx == 2:
break
# 12h00
try:
value_repr = l[i]
value = float(value_repr)
except ValueError:
break
else:
i += 1
idx += 1
if i < len_l:
newidx = info.hms(l[i])
if newidx is not None:
idx = newidx
elif i+1 < len_l and l[i] == ':':
# HH:MM[:SS[.ss]]
res.hour = int(value)
i += 1
value = float(l[i])
res.minute = int(value)
if value%1:
res.second = int(60*(value%1))
i += 1
if i < len_l and l[i] == ':':
res.second, res.microsecond = _parsems(l[i+1])
i += 2
elif i < len_l and l[i] in ('-', '/', '.'):
sep = l[i]
ymd.append(int(value))
i += 1
if i < len_l and not info.jump(l[i]):
try:
# 01-01[-01]
ymd.append(int(l[i]))
except ValueError:
# 01-Jan[-01]
value = info.month(l[i])
if value is not None:
ymd.append(value)
assert mstridx == -1
mstridx = len(ymd)-1
else:
return None
i += 1
if i < len_l and l[i] == sep:
# We have three members
i += 1
value = info.month(l[i])
if value is not None:
ymd.append(value)
mstridx = len(ymd)-1
assert mstridx == -1
else:
ymd.append(int(l[i]))
i += 1
elif i >= len_l or info.jump(l[i]):
if i+1 < len_l and info.ampm(l[i+1]) is not None:
# 12 am
res.hour = int(value)
if res.hour < 12 and info.ampm(l[i+1]) == 1:
res.hour += 12
elif res.hour == 12 and info.ampm(l[i+1]) == 0:
res.hour = 0
i += 1
else:
# Year, month or day
ymd.append(int(value))
i += 1
elif info.ampm(l[i]) is not None:
# 12am
res.hour = int(value)
if res.hour < 12 and info.ampm(l[i]) == 1:
res.hour += 12
elif res.hour == 12 and info.ampm(l[i]) == 0:
res.hour = 0
i += 1
elif not fuzzy:
return None
else:
i += 1
continue
# Check weekday
value = info.weekday(l[i])
if value is not None:
res.weekday = value
i += 1
continue
# Check month name
value = info.month(l[i])
if value is not None:
ymd.append(value)
assert mstridx == -1
mstridx = len(ymd)-1
i += 1
if i < len_l:
if l[i] in ('-', '/'):
# Jan-01[-99]
sep = l[i]
i += 1
ymd.append(int(l[i]))
i += 1
if i < len_l and l[i] == sep:
# Jan-01-99
i += 1
ymd.append(int(l[i]))
i += 1
elif (i+3 < len_l and l[i] == l[i+2] == ' '
and info.pertain(l[i+1])):
# Jan of 01
# In this case, 01 is clearly year
try:
value = int(l[i+3])
except ValueError:
# Wrong guess
pass
else:
# Convert it here to become unambiguous
ymd.append(info.convertyear(value))
i += 4
continue
# Check am/pm
value = info.ampm(l[i])
if value is not None:
if value == 1 and res.hour < 12:
res.hour += 12
elif value == 0 and res.hour == 12:
res.hour = 0
i += 1
continue
# Check for a timezone name
if (res.hour is not None and len(l[i]) <= 5 and
res.tzname is None and res.tzoffset is None and
not [x for x in l[i] if x not in string.ascii_uppercase]):
res.tzname = l[i]
res.tzoffset = info.tzoffset(res.tzname)
i += 1
# Check for something like GMT+3, or BRST+3. Notice
# that it doesn't mean "I am 3 hours after GMT", but
# "my time +3 is GMT". If found, we reverse the
# logic so that timezone parsing code will get it
# right.
if i < len_l and l[i] in ('+', '-'):
l[i] = ('+', '-')[l[i] == '+']
res.tzoffset = None
if info.utczone(res.tzname):
# With something like GMT+3, the timezone
# is *not* GMT.
res.tzname = None
continue
# Check for a numbered timezone
if res.hour is not None and l[i] in ('+', '-'):
signal = (-1,1)[l[i] == '+']
i += 1
len_li = len(l[i])
if len_li == 4:
# -0300
res.tzoffset = int(l[i][:2])*3600+int(l[i][2:])*60
elif i+1 < len_l and l[i+1] == ':':
# -03:00
res.tzoffset = int(l[i])*3600+int(l[i+2])*60
i += 2
elif len_li <= 2:
# -[0]3
res.tzoffset = int(l[i][:2])*3600
else:
return None
i += 1
res.tzoffset *= signal
# Look for a timezone name between parenthesis
if (i+3 < len_l and
info.jump(l[i]) and l[i+1] == '(' and l[i+3] == ')' and
3 <= len(l[i+2]) <= 5 and
not [x for x in l[i+2]
if x not in string.ascii_uppercase]):
# -0300 (BRST)
res.tzname = l[i+2]
i += 4
continue
# Check jumps
if not (info.jump(l[i]) or fuzzy):
return None
i += 1
# Process year/month/day
len_ymd = len(ymd)
if len_ymd > 3:
# More than three members!?
return None
elif len_ymd == 1 or (mstridx != -1 and len_ymd == 2):
# One member, or two members with a month string
if mstridx != -1:
res.month = ymd[mstridx]
del ymd[mstridx]
if len_ymd > 1 or mstridx == -1:
if ymd[0] > 31:
res.year = ymd[0]
else:
res.day = ymd[0]
elif len_ymd == 2:
# Two members with numbers
if ymd[0] > 31:
# 99-01
res.year, res.month = ymd
elif ymd[1] > 31:
# 01-99
res.month, res.year = ymd
elif dayfirst and ymd[1] <= 12:
# 13-01
res.day, res.month = ymd
else:
# 01-13
res.month, res.day = ymd
if len_ymd == 3:
# Three members
if mstridx == 0:
res.month, res.day, res.year = ymd
elif mstridx == 1:
if ymd[0] > 31 or (yearfirst and ymd[2] <= 31):
# 99-Jan-01
res.year, res.month, res.day = ymd
else:
# 01-Jan-01
# Give precendence to day-first, since
# two-digit years is usually hand-written.
res.day, res.month, res.year = ymd
elif mstridx == 2:
# WTF!?
if ymd[1] > 31:
# 01-99-Jan
res.day, res.year, res.month = ymd
else:
# 99-01-Jan
res.year, res.day, res.month = ymd
else:
if ymd[0] > 31 or \
(yearfirst and ymd[1] <= 12 and ymd[2] <= 31):
# 99-01-01
res.year, res.month, res.day = ymd
elif ymd[0] > 12 or (dayfirst and ymd[1] <= 12):
# 13-01-01
res.day, res.month, res.year = ymd
else:
# 01-13-01
res.month, res.day, res.year = ymd
except (IndexError, ValueError, AssertionError):
return None
if not info.validate(res):
return None
return res
DEFAULTPARSER = parser()
def parse(timestr, parserinfo=None, **kwargs):
if parserinfo:
return parser(parserinfo).parse(timestr, **kwargs)
else:
return DEFAULTPARSER.parse(timestr, **kwargs)
class _tzparser(object):
class _result(_resultbase):
__slots__ = ["stdabbr", "stdoffset", "dstabbr", "dstoffset",
"start", "end"]
class _attr(_resultbase):
__slots__ = ["month", "week", "weekday",
"yday", "jyday", "day", "time"]
def __repr__(self):
return self._repr("")
def __init__(self):
_resultbase.__init__(self)
self.start = self._attr()
self.end = self._attr()
def parse(self, tzstr):
res = self._result()
l = _timelex.split(tzstr)
try:
len_l = len(l)
i = 0
while i < len_l:
# BRST+3[BRDT[+2]]
j = i
while j < len_l and not [x for x in l[j]
if x in "0123456789:,-+"]:
j += 1
if j != i:
if not res.stdabbr:
offattr = "stdoffset"
res.stdabbr = "".join(l[i:j])
else:
offattr = "dstoffset"
res.dstabbr = "".join(l[i:j])
i = j
if (i < len_l and
(l[i] in ('+', '-') or l[i][0] in "0123456789")):
if l[i] in ('+', '-'):
# Yes, that's right. See the TZ variable
# documentation.
signal = (1,-1)[l[i] == '+']
i += 1
else:
signal = -1
len_li = len(l[i])
if len_li == 4:
# -0300
setattr(res, offattr,
(int(l[i][:2])*3600+int(l[i][2:])*60)*signal)
elif i+1 < len_l and l[i+1] == ':':
# -03:00
setattr(res, offattr,
(int(l[i])*3600+int(l[i+2])*60)*signal)
i += 2
elif len_li <= 2:
# -[0]3
setattr(res, offattr,
int(l[i][:2])*3600*signal)
else:
return None
i += 1
if res.dstabbr:
break
else:
break
if i < len_l:
for j in range(i, len_l):
if l[j] == ';': l[j] = ','
assert l[i] == ','
i += 1
if i >= len_l:
pass
elif (8 <= l.count(',') <= 9 and
not [y for x in l[i:] if x != ','
for y in x if y not in "0123456789"]):
# GMT0BST,3,0,30,3600,10,0,26,7200[,3600]
for x in (res.start, res.end):
x.month = int(l[i])
i += 2
if l[i] == '-':
value = int(l[i+1])*-1
i += 1
else:
value = int(l[i])
i += 2
if value:
x.week = value
x.weekday = (int(l[i])-1)%7
else:
x.day = int(l[i])
i += 2
x.time = int(l[i])
i += 2
if i < len_l:
if l[i] in ('-','+'):
signal = (-1,1)[l[i] == "+"]
i += 1
else:
signal = 1
res.dstoffset = (res.stdoffset+int(l[i]))*signal
elif (l.count(',') == 2 and l[i:].count('/') <= 2 and
not [y for x in l[i:] if x not in (',','/','J','M',
'.','-',':')
for y in x if y not in "0123456789"]):
for x in (res.start, res.end):
if l[i] == 'J':
# non-leap year day (1 based)
i += 1
x.jyday = int(l[i])
elif l[i] == 'M':
# month[-.]week[-.]weekday
i += 1
x.month = int(l[i])
i += 1
assert l[i] in ('-', '.')
i += 1
x.week = int(l[i])
if x.week == 5:
x.week = -1
i += 1
assert l[i] in ('-', '.')
i += 1
x.weekday = (int(l[i])-1)%7
else:
# year day (zero based)
x.yday = int(l[i])+1
i += 1
if i < len_l and l[i] == '/':
i += 1
# start time
len_li = len(l[i])
if len_li == 4:
# -0300
x.time = (int(l[i][:2])*3600+int(l[i][2:])*60)
elif i+1 < len_l and l[i+1] == ':':
# -03:00
x.time = int(l[i])*3600+int(l[i+2])*60
i += 2
if i+1 < len_l and l[i+1] == ':':
i += 2
x.time += int(l[i])
elif len_li <= 2:
# -[0]3
x.time = (int(l[i][:2])*3600)
else:
return None
i += 1
assert i == len_l or l[i] == ','
i += 1
assert i >= len_l
except (IndexError, ValueError, AssertionError):
return None
return res
DEFAULTTZPARSER = _tzparser()
def _parsetz(tzstr):
return DEFAULTTZPARSER.parse(tzstr)
def _parsems(value):
"""Parse a I[.F] seconds value into (seconds, microseconds)."""
if "." not in value:
return int(value), 0
else:
i, f = value.split(".")
return int(i), int(f.ljust(6, "0")[:6])
# vim:ts=4:sw=4:et

432
lib/dateutil/relativedelta.py Normal file
View File

@@ -0,0 +1,432 @@
"""
Copyright (c) 2003-2010 Gustavo Niemeyer <gustavo@niemeyer.net>
This module offers extensions to the standard python 2.3+
datetime module.
"""
__author__ = "Gustavo Niemeyer <gustavo@niemeyer.net>"
__license__ = "PSF License"
import datetime
import calendar
__all__ = ["relativedelta", "MO", "TU", "WE", "TH", "FR", "SA", "SU"]
class weekday(object):
__slots__ = ["weekday", "n"]
def __init__(self, weekday, n=None):
self.weekday = weekday
self.n = n
def __call__(self, n):
if n == self.n:
return self
else:
return self.__class__(self.weekday, n)
def __eq__(self, other):
try:
if self.weekday != other.weekday or self.n != other.n:
return False
except AttributeError:
return False
return True
def __repr__(self):
s = ("MO", "TU", "WE", "TH", "FR", "SA", "SU")[self.weekday]
if not self.n:
return s
else:
return "%s(%+d)" % (s, self.n)
MO, TU, WE, TH, FR, SA, SU = weekdays = tuple([weekday(x) for x in range(7)])
class relativedelta:
"""
The relativedelta type is based on the specification of the excelent
work done by M.-A. Lemburg in his mx.DateTime extension. However,
notice that this type does *NOT* implement the same algorithm as
his work. Do *NOT* expect it to behave like mx.DateTime's counterpart.
There's two different ways to build a relativedelta instance. The
first one is passing it two date/datetime classes:
relativedelta(datetime1, datetime2)
And the other way is to use the following keyword arguments:
year, month, day, hour, minute, second, microsecond:
Absolute information.
years, months, weeks, days, hours, minutes, seconds, microseconds:
Relative information, may be negative.
weekday:
One of the weekday instances (MO, TU, etc). These instances may
receive a parameter N, specifying the Nth weekday, which could
be positive or negative (like MO(+1) or MO(-2). Not specifying
it is the same as specifying +1. You can also use an integer,
where 0=MO.
leapdays:
Will add given days to the date found, if year is a leap
year, and the date found is post 28 of february.
yearday, nlyearday:
Set the yearday or the non-leap year day (jump leap days).
These are converted to day/month/leapdays information.
Here is the behavior of operations with relativedelta:
1) Calculate the absolute year, using the 'year' argument, or the
original datetime year, if the argument is not present.
2) Add the relative 'years' argument to the absolute year.
3) Do steps 1 and 2 for month/months.
4) Calculate the absolute day, using the 'day' argument, or the
original datetime day, if the argument is not present. Then,
subtract from the day until it fits in the year and month
found after their operations.
5) Add the relative 'days' argument to the absolute day. Notice
that the 'weeks' argument is multiplied by 7 and added to
'days'.
6) Do steps 1 and 2 for hour/hours, minute/minutes, second/seconds,
microsecond/microseconds.
7) If the 'weekday' argument is present, calculate the weekday,
with the given (wday, nth) tuple. wday is the index of the
weekday (0-6, 0=Mon), and nth is the number of weeks to add
forward or backward, depending on its signal. Notice that if
the calculated date is already Monday, for example, using
(0, 1) or (0, -1) won't change the day.
"""
def __init__(self, dt1=None, dt2=None,
years=0, months=0, days=0, leapdays=0, weeks=0,
hours=0, minutes=0, seconds=0, microseconds=0,
year=None, month=None, day=None, weekday=None,
yearday=None, nlyearday=None,
hour=None, minute=None, second=None, microsecond=None):
if dt1 and dt2:
if not isinstance(dt1, datetime.date) or \
not isinstance(dt2, datetime.date):
raise TypeError, "relativedelta only diffs datetime/date"
if type(dt1) is not type(dt2):
if not isinstance(dt1, datetime.datetime):
dt1 = datetime.datetime.fromordinal(dt1.toordinal())
elif not isinstance(dt2, datetime.datetime):
dt2 = datetime.datetime.fromordinal(dt2.toordinal())
self.years = 0
self.months = 0
self.days = 0
self.leapdays = 0
self.hours = 0
self.minutes = 0
self.seconds = 0
self.microseconds = 0
self.year = None
self.month = None
self.day = None
self.weekday = None
self.hour = None
self.minute = None
self.second = None
self.microsecond = None
self._has_time = 0
months = (dt1.year*12+dt1.month)-(dt2.year*12+dt2.month)
self._set_months(months)
dtm = self.__radd__(dt2)
if dt1 < dt2:
while dt1 > dtm:
months += 1
self._set_months(months)
dtm = self.__radd__(dt2)
else:
while dt1 < dtm:
months -= 1
self._set_months(months)
dtm = self.__radd__(dt2)
delta = dt1 - dtm
self.seconds = delta.seconds+delta.days*86400
self.microseconds = delta.microseconds
else:
self.years = years
self.months = months
self.days = days+weeks*7
self.leapdays = leapdays
self.hours = hours
self.minutes = minutes
self.seconds = seconds
self.microseconds = microseconds
self.year = year
self.month = month
self.day = day
self.hour = hour
self.minute = minute
self.second = second
self.microsecond = microsecond
if type(weekday) is int:
self.weekday = weekdays[weekday]
else:
self.weekday = weekday
yday = 0
if nlyearday:
yday = nlyearday
elif yearday:
yday = yearday
if yearday > 59:
self.leapdays = -1
if yday:
ydayidx = [31,59,90,120,151,181,212,243,273,304,334,366]
for idx, ydays in enumerate(ydayidx):
if yday <= ydays:
self.month = idx+1
if idx == 0:
self.day = yday
else:
self.day = yday-ydayidx[idx-1]
break
else:
raise ValueError, "invalid year day (%d)" % yday
self._fix()
def _fix(self):
if abs(self.microseconds) > 999999:
s = self.microseconds//abs(self.microseconds)
div, mod = divmod(self.microseconds*s, 1000000)
self.microseconds = mod*s
self.seconds += div*s
if abs(self.seconds) > 59:
s = self.seconds//abs(self.seconds)
div, mod = divmod(self.seconds*s, 60)
self.seconds = mod*s
self.minutes += div*s
if abs(self.minutes) > 59:
s = self.minutes//abs(self.minutes)
div, mod = divmod(self.minutes*s, 60)
self.minutes = mod*s
self.hours += div*s
if abs(self.hours) > 23:
s = self.hours//abs(self.hours)
div, mod = divmod(self.hours*s, 24)
self.hours = mod*s
self.days += div*s
if abs(self.months) > 11:
s = self.months//abs(self.months)
div, mod = divmod(self.months*s, 12)
self.months = mod*s
self.years += div*s
if (self.hours or self.minutes or self.seconds or self.microseconds or
self.hour is not None or self.minute is not None or
self.second is not None or self.microsecond is not None):
self._has_time = 1
else:
self._has_time = 0
def _set_months(self, months):
self.months = months
if abs(self.months) > 11:
s = self.months//abs(self.months)
div, mod = divmod(self.months*s, 12)
self.months = mod*s
self.years = div*s
else:
self.years = 0
def __radd__(self, other):
if not isinstance(other, datetime.date):
raise TypeError, "unsupported type for add operation"
elif self._has_time and not isinstance(other, datetime.datetime):
other = datetime.datetime.fromordinal(other.toordinal())
year = (self.year or other.year)+self.years
month = self.month or other.month
if self.months:
assert 1 <= abs(self.months) <= 12
month += self.months
if month > 12:
year += 1
month -= 12
elif month < 1:
year -= 1
month += 12
day = min(calendar.monthrange(year, month)[1],
self.day or other.day)
repl = {"year": year, "month": month, "day": day}
for attr in ["hour", "minute", "second", "microsecond"]:
value = getattr(self, attr)
if value is not None:
repl[attr] = value
days = self.days
if self.leapdays and month > 2 and calendar.isleap(year):
days += self.leapdays
ret = (other.replace(**repl)
+ datetime.timedelta(days=days,
hours=self.hours,
minutes=self.minutes,
seconds=self.seconds,
microseconds=self.microseconds))
if self.weekday:
weekday, nth = self.weekday.weekday, self.weekday.n or 1
jumpdays = (abs(nth)-1)*7
if nth > 0:
jumpdays += (7-ret.weekday()+weekday)%7
else:
jumpdays += (ret.weekday()-weekday)%7
jumpdays *= -1
ret += datetime.timedelta(days=jumpdays)
return ret
def __rsub__(self, other):
return self.__neg__().__radd__(other)
def __add__(self, other):
if not isinstance(other, relativedelta):
raise TypeError, "unsupported type for add operation"
return relativedelta(years=other.years+self.years,
months=other.months+self.months,
days=other.days+self.days,
hours=other.hours+self.hours,
minutes=other.minutes+self.minutes,
seconds=other.seconds+self.seconds,
microseconds=other.microseconds+self.microseconds,
leapdays=other.leapdays or self.leapdays,
year=other.year or self.year,
month=other.month or self.month,
day=other.day or self.day,
weekday=other.weekday or self.weekday,
hour=other.hour or self.hour,
minute=other.minute or self.minute,
second=other.second or self.second,
microsecond=other.second or self.microsecond)
def __sub__(self, other):
if not isinstance(other, relativedelta):
raise TypeError, "unsupported type for sub operation"
return relativedelta(years=other.years-self.years,
months=other.months-self.months,
days=other.days-self.days,
hours=other.hours-self.hours,
minutes=other.minutes-self.minutes,
seconds=other.seconds-self.seconds,
microseconds=other.microseconds-self.microseconds,
leapdays=other.leapdays or self.leapdays,
year=other.year or self.year,
month=other.month or self.month,
day=other.day or self.day,
weekday=other.weekday or self.weekday,
hour=other.hour or self.hour,
minute=other.minute or self.minute,
second=other.second or self.second,
microsecond=other.second or self.microsecond)
def __neg__(self):
return relativedelta(years=-self.years,
months=-self.months,
days=-self.days,
hours=-self.hours,
minutes=-self.minutes,
seconds=-self.seconds,
microseconds=-self.microseconds,
leapdays=self.leapdays,
year=self.year,
month=self.month,
day=self.day,
weekday=self.weekday,
hour=self.hour,
minute=self.minute,
second=self.second,
microsecond=self.microsecond)
def __nonzero__(self):
return not (not self.years and
not self.months and
not self.days and
not self.hours and
not self.minutes and
not self.seconds and
not self.microseconds and
not self.leapdays and
self.year is None and
self.month is None and
self.day is None and
self.weekday is None and
self.hour is None and
self.minute is None and
self.second is None and
self.microsecond is None)
def __mul__(self, other):
f = float(other)
return relativedelta(years = int(round(self.years*f)),
months = int(round(self.months*f)),
days = int(round(self.days*f)),
hours = int(round(self.hours*f)),
minutes = int(round(self.minutes*f)),
seconds = int(round(self.seconds*f)),
microseconds = self.microseconds*f,
leapdays = self.leapdays,
year = self.year,
month = self.month,
day = self.day,
weekday = self.weekday,
hour = self.hour,
minute = self.minute,
second = self.second,
microsecond = self.microsecond)
def __eq__(self, other):
if not isinstance(other, relativedelta):
return False
if self.weekday or other.weekday:
if not self.weekday or not other.weekday:
return False
if self.weekday.weekday != other.weekday.weekday:
return False
n1, n2 = self.weekday.n, other.weekday.n
if n1 != n2 and not ((not n1 or n1 == 1) and (not n2 or n2 == 1)):
return False
return (self.years == other.years and
self.months == other.months and
self.days == other.days and
self.hours == other.hours and
self.minutes == other.minutes and
self.seconds == other.seconds and
self.leapdays == other.leapdays and
self.year == other.year and
self.month == other.month and
self.day == other.day and
self.hour == other.hour and
self.minute == other.minute and
self.second == other.second and
self.microsecond == other.microsecond)
def __ne__(self, other):
return not self.__eq__(other)
def __div__(self, other):
return self.__mul__(1/float(other))
def __repr__(self):
l = []
for attr in ["years", "months", "days", "leapdays",
"hours", "minutes", "seconds", "microseconds"]:
value = getattr(self, attr)
if value:
l.append("%s=%+d" % (attr, value))
for attr in ["year", "month", "day", "weekday",
"hour", "minute", "second", "microsecond"]:
value = getattr(self, attr)
if value is not None:
l.append("%s=%s" % (attr, `value`))
return "%s(%s)" % (self.__class__.__name__, ", ".join(l))
# vim:ts=4:sw=4:et

1108
lib/dateutil/rrule.py Normal file
View File

File diff suppressed because it is too large Load Diff

958
lib/dateutil/tz.py Normal file
View File

@@ -0,0 +1,958 @@
"""
Copyright (c) 2003-2007 Gustavo Niemeyer <gustavo@niemeyer.net>
This module offers extensions to the standard python 2.3+
datetime module.
"""
__author__ = "Gustavo Niemeyer <gustavo@niemeyer.net>"
__license__ = "PSF License"
import datetime
import struct
import time
import sys
import os
relativedelta = None
parser = None
rrule = None
__all__ = ["tzutc", "tzoffset", "tzlocal", "tzfile", "tzrange",
"tzstr", "tzical", "tzwin", "tzwinlocal", "gettz"]
try:
from dateutil.tzwin import tzwin, tzwinlocal
except (ImportError, OSError):
tzwin, tzwinlocal = None, None
ZERO = datetime.timedelta(0)
EPOCHORDINAL = datetime.datetime.utcfromtimestamp(0).toordinal()
class tzutc(datetime.tzinfo):
def utcoffset(self, dt):
return ZERO
def dst(self, dt):
return ZERO
def tzname(self, dt):
return "UTC"
def __eq__(self, other):
return (isinstance(other, tzutc) or
(isinstance(other, tzoffset) and other._offset == ZERO))
def __ne__(self, other):
return not self.__eq__(other)
def __repr__(self):
return "%s()" % self.__class__.__name__
__reduce__ = object.__reduce__
class tzoffset(datetime.tzinfo):
def __init__(self, name, offset):
self._name = name
self._offset = datetime.timedelta(seconds=offset)
def utcoffset(self, dt):
return self._offset
def dst(self, dt):
return ZERO
def tzname(self, dt):
return self._name
def __eq__(self, other):
return (isinstance(other, tzoffset) and
self._offset == other._offset)
def __ne__(self, other):
return not self.__eq__(other)
def __repr__(self):
return "%s(%s, %s)" % (self.__class__.__name__,
`self._name`,
self._offset.days*86400+self._offset.seconds)
__reduce__ = object.__reduce__
class tzlocal(datetime.tzinfo):
_std_offset = datetime.timedelta(seconds=-time.timezone)
if time.daylight:
_dst_offset = datetime.timedelta(seconds=-time.altzone)
else:
_dst_offset = _std_offset
def utcoffset(self, dt):
if self._isdst(dt):
return self._dst_offset
else:
return self._std_offset
def dst(self, dt):
if self._isdst(dt):
return self._dst_offset-self._std_offset
else:
return ZERO
def tzname(self, dt):
return time.tzname[self._isdst(dt)]
def _isdst(self, dt):
# We can't use mktime here. It is unstable when deciding if
# the hour near to a change is DST or not.
#
# timestamp = time.mktime((dt.year, dt.month, dt.day, dt.hour,
# dt.minute, dt.second, dt.weekday(), 0, -1))
# return time.localtime(timestamp).tm_isdst
#
# The code above yields the following result:
#
#>>> import tz, datetime
#>>> t = tz.tzlocal()
#>>> datetime.datetime(2003,2,15,23,tzinfo=t).tzname()
#'BRDT'
#>>> datetime.datetime(2003,2,16,0,tzinfo=t).tzname()
#'BRST'
#>>> datetime.datetime(2003,2,15,23,tzinfo=t).tzname()
#'BRST'
#>>> datetime.datetime(2003,2,15,22,tzinfo=t).tzname()
#'BRDT'
#>>> datetime.datetime(2003,2,15,23,tzinfo=t).tzname()
#'BRDT'
#
# Here is a more stable implementation:
#
timestamp = ((dt.toordinal() - EPOCHORDINAL) * 86400
+ dt.hour * 3600
+ dt.minute * 60
+ dt.second)
return time.localtime(timestamp+time.timezone).tm_isdst
def __eq__(self, other):
if not isinstance(other, tzlocal):
return False
return (self._std_offset == other._std_offset and
self._dst_offset == other._dst_offset)
return True
def __ne__(self, other):
return not self.__eq__(other)
def __repr__(self):
return "%s()" % self.__class__.__name__
__reduce__ = object.__reduce__
class _ttinfo(object):
__slots__ = ["offset", "delta", "isdst", "abbr", "isstd", "isgmt"]
def __init__(self):
for attr in self.__slots__:
setattr(self, attr, None)
def __repr__(self):
l = []
for attr in self.__slots__:
value = getattr(self, attr)
if value is not None:
l.append("%s=%s" % (attr, `value`))
return "%s(%s)" % (self.__class__.__name__, ", ".join(l))
def __eq__(self, other):
if not isinstance(other, _ttinfo):
return False
return (self.offset == other.offset and
self.delta == other.delta and
self.isdst == other.isdst and
self.abbr == other.abbr and
self.isstd == other.isstd and
self.isgmt == other.isgmt)
def __ne__(self, other):
return not self.__eq__(other)
def __getstate__(self):
state = {}
for name in self.__slots__:
state[name] = getattr(self, name, None)
return state
def __setstate__(self, state):
for name in self.__slots__:
if name in state:
setattr(self, name, state[name])
class tzfile(datetime.tzinfo):
# http://www.twinsun.com/tz/tz-link.htm
# ftp://elsie.nci.nih.gov/pub/tz*.tar.gz
def __init__(self, fileobj):
if isinstance(fileobj, basestring):
self._filename = fileobj
fileobj = open(fileobj)
elif hasattr(fileobj, "name"):
self._filename = fileobj.name
else:
self._filename = `fileobj`
# From tzfile(5):
#
# The time zone information files used by tzset(3)
# begin with the magic characters "TZif" to identify
# them as time zone information files, followed by
# sixteen bytes reserved for future use, followed by
# six four-byte values of type long, written in a
# ``standard'' byte order (the high-order byte
# of the value is written first).
if fileobj.read(4) != "TZif":
raise ValueError, "magic not found"
fileobj.read(16)
(
# The number of UTC/local indicators stored in the file.
ttisgmtcnt,
# The number of standard/wall indicators stored in the file.
ttisstdcnt,
# The number of leap seconds for which data is
# stored in the file.
leapcnt,
# The number of "transition times" for which data
# is stored in the file.
timecnt,
# The number of "local time types" for which data
# is stored in the file (must not be zero).
typecnt,
# The number of characters of "time zone
# abbreviation strings" stored in the file.
charcnt,
) = struct.unpack(">6l", fileobj.read(24))
# The above header is followed by tzh_timecnt four-byte
# values of type long, sorted in ascending order.
# These values are written in ``standard'' byte order.
# Each is used as a transition time (as returned by
# time(2)) at which the rules for computing local time
# change.
if timecnt:
self._trans_list = struct.unpack(">%dl" % timecnt,
fileobj.read(timecnt*4))
else:
self._trans_list = []
# Next come tzh_timecnt one-byte values of type unsigned
# char; each one tells which of the different types of
# ``local time'' types described in the file is associated
# with the same-indexed transition time. These values
# serve as indices into an array of ttinfo structures that
# appears next in the file.
if timecnt:
self._trans_idx = struct.unpack(">%dB" % timecnt,
fileobj.read(timecnt))
else:
self._trans_idx = []
# Each ttinfo structure is written as a four-byte value
# for tt_gmtoff of type long, in a standard byte
# order, followed by a one-byte value for tt_isdst
# and a one-byte value for tt_abbrind. In each
# structure, tt_gmtoff gives the number of
# seconds to be added to UTC, tt_isdst tells whether
# tm_isdst should be set by localtime(3), and
# tt_abbrind serves as an index into the array of
# time zone abbreviation characters that follow the
# ttinfo structure(s) in the file.
ttinfo = []
for i in range(typecnt):
ttinfo.append(struct.unpack(">lbb", fileobj.read(6)))
abbr = fileobj.read(charcnt)
# Then there are tzh_leapcnt pairs of four-byte
# values, written in standard byte order; the
# first value of each pair gives the time (as
# returned by time(2)) at which a leap second
# occurs; the second gives the total number of
# leap seconds to be applied after the given time.
# The pairs of values are sorted in ascending order
# by time.
# Not used, for now
if leapcnt:
leap = struct.unpack(">%dl" % (leapcnt*2),
fileobj.read(leapcnt*8))
# Then there are tzh_ttisstdcnt standard/wall
# indicators, each stored as a one-byte value;
# they tell whether the transition times associated
# with local time types were specified as standard
# time or wall clock time, and are used when
# a time zone file is used in handling POSIX-style
# time zone environment variables.
if ttisstdcnt:
isstd = struct.unpack(">%db" % ttisstdcnt,
fileobj.read(ttisstdcnt))
# Finally, there are tzh_ttisgmtcnt UTC/local
# indicators, each stored as a one-byte value;
# they tell whether the transition times associated
# with local time types were specified as UTC or
# local time, and are used when a time zone file
# is used in handling POSIX-style time zone envi-
# ronment variables.
if ttisgmtcnt:
isgmt = struct.unpack(">%db" % ttisgmtcnt,
fileobj.read(ttisgmtcnt))
# ** Everything has been read **
# Build ttinfo list
self._ttinfo_list = []
for i in range(typecnt):
gmtoff, isdst, abbrind = ttinfo[i]
# Round to full-minutes if that's not the case. Python's
# datetime doesn't accept sub-minute timezones. Check
# http://python.org/sf/1447945 for some information.
gmtoff = (gmtoff+30)//60*60
tti = _ttinfo()
tti.offset = gmtoff
tti.delta = datetime.timedelta(seconds=gmtoff)
tti.isdst = isdst
tti.abbr = abbr[abbrind:abbr.find('\x00', abbrind)]
tti.isstd = (ttisstdcnt > i and isstd[i] != 0)
tti.isgmt = (ttisgmtcnt > i and isgmt[i] != 0)
self._ttinfo_list.append(tti)
# Replace ttinfo indexes for ttinfo objects.
trans_idx = []
for idx in self._trans_idx:
trans_idx.append(self._ttinfo_list[idx])
self._trans_idx = tuple(trans_idx)
# Set standard, dst, and before ttinfos. before will be
# used when a given time is before any transitions,
# and will be set to the first non-dst ttinfo, or to
# the first dst, if all of them are dst.
self._ttinfo_std = None
self._ttinfo_dst = None
self._ttinfo_before = None
if self._ttinfo_list:
if not self._trans_list:
self._ttinfo_std = self._ttinfo_first = self._ttinfo_list[0]
else:
for i in range(timecnt-1,-1,-1):
tti = self._trans_idx[i]
if not self._ttinfo_std and not tti.isdst:
self._ttinfo_std = tti
elif not self._ttinfo_dst and tti.isdst:
self._ttinfo_dst = tti
if self._ttinfo_std and self._ttinfo_dst:
break
else:
if self._ttinfo_dst and not self._ttinfo_std:
self._ttinfo_std = self._ttinfo_dst
for tti in self._ttinfo_list:
if not tti.isdst:
self._ttinfo_before = tti
break
else:
self._ttinfo_before = self._ttinfo_list[0]
# Now fix transition times to become relative to wall time.
#
# I'm not sure about this. In my tests, the tz source file
# is setup to wall time, and in the binary file isstd and
# isgmt are off, so it should be in wall time. OTOH, it's
# always in gmt time. Let me know if you have comments
# about this.
laststdoffset = 0
self._trans_list = list(self._trans_list)
for i in range(len(self._trans_list)):
tti = self._trans_idx[i]
if not tti.isdst:
# This is std time.
self._trans_list[i] += tti.offset
laststdoffset = tti.offset
else:
# This is dst time. Convert to std.
self._trans_list[i] += laststdoffset
self._trans_list = tuple(self._trans_list)
def _find_ttinfo(self, dt, laststd=0):
timestamp = ((dt.toordinal() - EPOCHORDINAL) * 86400
+ dt.hour * 3600
+ dt.minute * 60
+ dt.second)
idx = 0
for trans in self._trans_list:
if timestamp < trans:
break
idx += 1
else:
return self._ttinfo_std
if idx == 0:
return self._ttinfo_before
if laststd:
while idx > 0:
tti = self._trans_idx[idx-1]
if not tti.isdst:
return tti
idx -= 1
else:
return self._ttinfo_std
else:
return self._trans_idx[idx-1]
def utcoffset(self, dt):
if not self._ttinfo_std:
return ZERO
return self._find_ttinfo(dt).delta
def dst(self, dt):
if not self._ttinfo_dst:
return ZERO
tti = self._find_ttinfo(dt)
if not tti.isdst:
return ZERO
# The documentation says that utcoffset()-dst() must
# be constant for every dt.
return tti.delta-self._find_ttinfo(dt, laststd=1).delta
# An alternative for that would be:
#
# return self._ttinfo_dst.offset-self._ttinfo_std.offset
#
# However, this class stores historical changes in the
# dst offset, so I belive that this wouldn't be the right
# way to implement this.
def tzname(self, dt):
if not self._ttinfo_std:
return None
return self._find_ttinfo(dt).abbr
def __eq__(self, other):
if not isinstance(other, tzfile):
return False
return (self._trans_list == other._trans_list and
self._trans_idx == other._trans_idx and
self._ttinfo_list == other._ttinfo_list)
def __ne__(self, other):
return not self.__eq__(other)
def __repr__(self):
return "%s(%s)" % (self.__class__.__name__, `self._filename`)
def __reduce__(self):
if not os.path.isfile(self._filename):
raise ValueError, "Unpickable %s class" % self.__class__.__name__
return (self.__class__, (self._filename,))
class tzrange(datetime.tzinfo):
def __init__(self, stdabbr, stdoffset=None,
dstabbr=None, dstoffset=None,
start=None, end=None):
global relativedelta
if not relativedelta:
from dateutil import relativedelta
self._std_abbr = stdabbr
self._dst_abbr = dstabbr
if stdoffset is not None:
self._std_offset = datetime.timedelta(seconds=stdoffset)
else:
self._std_offset = ZERO
if dstoffset is not None:
self._dst_offset = datetime.timedelta(seconds=dstoffset)
elif dstabbr and stdoffset is not None:
self._dst_offset = self._std_offset+datetime.timedelta(hours=+1)
else:
self._dst_offset = ZERO
if dstabbr and start is None:
self._start_delta = relativedelta.relativedelta(
hours=+2, month=4, day=1, weekday=relativedelta.SU(+1))
else:
self._start_delta = start
if dstabbr and end is None:
self._end_delta = relativedelta.relativedelta(
hours=+1, month=10, day=31, weekday=relativedelta.SU(-1))
else:
self._end_delta = end
def utcoffset(self, dt):
if self._isdst(dt):
return self._dst_offset
else:
return self._std_offset
def dst(self, dt):
if self._isdst(dt):
return self._dst_offset-self._std_offset
else:
return ZERO
def tzname(self, dt):
if self._isdst(dt):
return self._dst_abbr
else:
return self._std_abbr
def _isdst(self, dt):
if not self._start_delta:
return False
year = datetime.datetime(dt.year,1,1)
start = year+self._start_delta
end = year+self._end_delta
dt = dt.replace(tzinfo=None)
if start < end:
return dt >= start and dt < end
else:
return dt >= start or dt < end
def __eq__(self, other):
if not isinstance(other, tzrange):
return False
return (self._std_abbr == other._std_abbr and
self._dst_abbr == other._dst_abbr and
self._std_offset == other._std_offset and
self._dst_offset == other._dst_offset and
self._start_delta == other._start_delta and
self._end_delta == other._end_delta)
def __ne__(self, other):
return not self.__eq__(other)
def __repr__(self):
return "%s(...)" % self.__class__.__name__
__reduce__ = object.__reduce__
class tzstr(tzrange):
def __init__(self, s):
global parser
if not parser:
from dateutil import parser
self._s = s
res = parser._parsetz(s)
if res is None:
raise ValueError, "unknown string format"
# Here we break the compatibility with the TZ variable handling.
# GMT-3 actually *means* the timezone -3.
if res.stdabbr in ("GMT", "UTC"):
res.stdoffset *= -1
# We must initialize it first, since _delta() needs
# _std_offset and _dst_offset set. Use False in start/end
# to avoid building it two times.
tzrange.__init__(self, res.stdabbr, res.stdoffset,
res.dstabbr, res.dstoffset,
start=False, end=False)
if not res.dstabbr:
self._start_delta = None
self._end_delta = None
else:
self._start_delta = self._delta(res.start)
if self._start_delta:
self._end_delta = self._delta(res.end, isend=1)
def _delta(self, x, isend=0):
kwargs = {}
if x.month is not None:
kwargs["month"] = x.month
if x.weekday is not None:
kwargs["weekday"] = relativedelta.weekday(x.weekday, x.week)
if x.week > 0:
kwargs["day"] = 1
else:
kwargs["day"] = 31
elif x.day:
kwargs["day"] = x.day
elif x.yday is not None:
kwargs["yearday"] = x.yday
elif x.jyday is not None:
kwargs["nlyearday"] = x.jyday
if not kwargs:
# Default is to start on first sunday of april, and end
# on last sunday of october.
if not isend:
kwargs["month"] = 4
kwargs["day"] = 1
kwargs["weekday"] = relativedelta.SU(+1)
else:
kwargs["month"] = 10
kwargs["day"] = 31
kwargs["weekday"] = relativedelta.SU(-1)
if x.time is not None:
kwargs["seconds"] = x.time
else:
# Default is 2AM.
kwargs["seconds"] = 7200
if isend:
# Convert to standard time, to follow the documented way
# of working with the extra hour. See the documentation
# of the tzinfo class.
delta = self._dst_offset-self._std_offset
kwargs["seconds"] -= delta.seconds+delta.days*86400
return relativedelta.relativedelta(**kwargs)
def __repr__(self):
return "%s(%s)" % (self.__class__.__name__, `self._s`)
class _tzicalvtzcomp:
def __init__(self, tzoffsetfrom, tzoffsetto, isdst,
tzname=None, rrule=None):
self.tzoffsetfrom = datetime.timedelta(seconds=tzoffsetfrom)
self.tzoffsetto = datetime.timedelta(seconds=tzoffsetto)
self.tzoffsetdiff = self.tzoffsetto-self.tzoffsetfrom
self.isdst = isdst
self.tzname = tzname
self.rrule = rrule
class _tzicalvtz(datetime.tzinfo):
def __init__(self, tzid, comps=[]):
self._tzid = tzid
self._comps = comps
self._cachedate = []
self._cachecomp = []
def _find_comp(self, dt):
if len(self._comps) == 1:
return self._comps[0]
dt = dt.replace(tzinfo=None)
try:
return self._cachecomp[self._cachedate.index(dt)]
except ValueError:
pass
lastcomp = None
lastcompdt = None
for comp in self._comps:
if not comp.isdst:
# Handle the extra hour in DST -> STD
compdt = comp.rrule.before(dt-comp.tzoffsetdiff, inc=True)
else:
compdt = comp.rrule.before(dt, inc=True)
if compdt and (not lastcompdt or lastcompdt < compdt):
lastcompdt = compdt
lastcomp = comp
if not lastcomp:
# RFC says nothing about what to do when a given
# time is before the first onset date. We'll look for the
# first standard component, or the first component, if
# none is found.
for comp in self._comps:
if not comp.isdst:
lastcomp = comp
break
else:
lastcomp = comp[0]
self._cachedate.insert(0, dt)
self._cachecomp.insert(0, lastcomp)
if len(self._cachedate) > 10:
self._cachedate.pop()
self._cachecomp.pop()
return lastcomp
def utcoffset(self, dt):
return self._find_comp(dt).tzoffsetto
def dst(self, dt):
comp = self._find_comp(dt)
if comp.isdst:
return comp.tzoffsetdiff
else:
return ZERO
def tzname(self, dt):
return self._find_comp(dt).tzname
def __repr__(self):
return "<tzicalvtz %s>" % `self._tzid`
__reduce__ = object.__reduce__
class tzical:
def __init__(self, fileobj):
global rrule
if not rrule:
from dateutil import rrule
if isinstance(fileobj, basestring):
self._s = fileobj
fileobj = open(fileobj)
elif hasattr(fileobj, "name"):
self._s = fileobj.name
else:
self._s = `fileobj`
self._vtz = {}
self._parse_rfc(fileobj.read())
def keys(self):
return self._vtz.keys()
def get(self, tzid=None):
if tzid is None:
keys = self._vtz.keys()
if len(keys) == 0:
raise ValueError, "no timezones defined"
elif len(keys) > 1:
raise ValueError, "more than one timezone available"
tzid = keys[0]
return self._vtz.get(tzid)
def _parse_offset(self, s):
s = s.strip()
if not s:
raise ValueError, "empty offset"
if s[0] in ('+', '-'):
signal = (-1,+1)[s[0]=='+']
s = s[1:]
else:
signal = +1
if len(s) == 4:
return (int(s[:2])*3600+int(s[2:])*60)*signal
elif len(s) == 6:
return (int(s[:2])*3600+int(s[2:4])*60+int(s[4:]))*signal
else:
raise ValueError, "invalid offset: "+s
def _parse_rfc(self, s):
lines = s.splitlines()
if not lines:
raise ValueError, "empty string"
# Unfold
i = 0
while i < len(lines):
line = lines[i].rstrip()
if not line:
del lines[i]
elif i > 0 and line[0] in (" ", "\t"):
lines[i-1] += line[1:]
del lines[i]
else:
i += 1
tzid = None
comps = []
invtz = False
comptype = None
for line in lines:
if not line:
continue
name, value = line.split(':', 1)
parms = name.split(';')
if not parms:
raise ValueError, "empty property name"
name = parms[0].upper()
parms = parms[1:]
if invtz:
if name == "BEGIN":
if value in ("STANDARD", "DAYLIGHT"):
# Process component
pass
else:
raise ValueError, "unknown component: "+value
comptype = value
founddtstart = False
tzoffsetfrom = None
tzoffsetto = None
rrulelines = []
tzname = None
elif name == "END":
if value == "VTIMEZONE":
if comptype:
raise ValueError, \
"component not closed: "+comptype
if not tzid:
raise ValueError, \
"mandatory TZID not found"
if not comps:
raise ValueError, \
"at least one component is needed"
# Process vtimezone
self._vtz[tzid] = _tzicalvtz(tzid, comps)
invtz = False
elif value == comptype:
if not founddtstart:
raise ValueError, \
"mandatory DTSTART not found"
if tzoffsetfrom is None:
raise ValueError, \
"mandatory TZOFFSETFROM not found"
if tzoffsetto is None:
raise ValueError, \
"mandatory TZOFFSETFROM not found"
# Process component
rr = None
if rrulelines:
rr = rrule.rrulestr("\n".join(rrulelines),
compatible=True,
ignoretz=True,
cache=True)
comp = _tzicalvtzcomp(tzoffsetfrom, tzoffsetto,
(comptype == "DAYLIGHT"),
tzname, rr)
comps.append(comp)
comptype = None
else:
raise ValueError, \
"invalid component end: "+value
elif comptype:
if name == "DTSTART":
rrulelines.append(line)
founddtstart = True
elif name in ("RRULE", "RDATE", "EXRULE", "EXDATE"):
rrulelines.append(line)
elif name == "TZOFFSETFROM":
if parms:
raise ValueError, \
"unsupported %s parm: %s "%(name, parms[0])
tzoffsetfrom = self._parse_offset(value)
elif name == "TZOFFSETTO":
if parms:
raise ValueError, \
"unsupported TZOFFSETTO parm: "+parms[0]
tzoffsetto = self._parse_offset(value)
elif name == "TZNAME":
if parms:
raise ValueError, \
"unsupported TZNAME parm: "+parms[0]
tzname = value
elif name == "COMMENT":
pass
elif name.upper().startswith('X-'):
# Ignore experimental properties.
pass
else:
raise ValueError, "unsupported property: "+name
else:
if name == "TZID":
for p in parms:
if not p.upper().startswith('X-'):
raise ValueError, \
"unsupported TZID parm: "+p
tzid = value
elif name in ("TZURL", "LAST-MODIFIED", "COMMENT"):
pass
elif name.upper().startswith('X-'):
# Ignore experimental properties.
pass
else:
raise ValueError, "unsupported property: "+name
elif name == "BEGIN" and value == "VTIMEZONE":
tzid = None
comps = []
invtz = True
def __repr__(self):
return "%s(%s)" % (self.__class__.__name__, `self._s`)
if sys.platform != "win32":
TZFILES = ["/etc/localtime", "localtime"]
TZPATHS = ["/usr/share/zoneinfo", "/usr/lib/zoneinfo", "/etc/zoneinfo"]
else:
TZFILES = []
TZPATHS = []
def gettz(name=None):
tz = None
if not name:
try:
name = os.environ["TZ"]
except KeyError:
pass
if name is None or name == ":":
for filepath in TZFILES:
if not os.path.isabs(filepath):
filename = filepath
for path in TZPATHS:
filepath = os.path.join(path, filename)
if os.path.isfile(filepath):
break
else:
continue
if os.path.isfile(filepath):
try:
tz = tzfile(filepath)
break
except (IOError, OSError, ValueError):
pass
else:
tz = tzlocal()
else:
if name.startswith(":"):
name = name[:-1]
if os.path.isabs(name):
if os.path.isfile(name):
tz = tzfile(name)
else:
tz = None
else:
for path in TZPATHS:
filepath = os.path.join(path, name)
if not os.path.isfile(filepath):
filepath = filepath.replace(' ','_')
if not os.path.isfile(filepath):
continue
try:
tz = tzfile(filepath)
break
except (IOError, OSError, ValueError):
pass
else:
tz = None
if tzwin:
try:
tz = tzwin(name)
except OSError:
pass
if not tz:
from dateutil.zoneinfo import gettz
tz = gettz(name)
if not tz:
for c in name:
# name must have at least one offset to be a tzstr
if c in "0123456789":
try:
tz = tzstr(name)
except ValueError:
pass
break
else:
if name in ("GMT", "UTC"):
tz = tzutc()
elif name in time.tzname:
tz = tzlocal()
return tz
# vim:ts=4:sw=4:et

180
lib/dateutil/tzwin.py Normal file
View File

@@ -0,0 +1,180 @@
# This code was originally contributed by Jeffrey Harris.
import datetime
import struct
import _winreg
__author__ = "Jeffrey Harris & Gustavo Niemeyer <gustavo@niemeyer.net>"
__all__ = ["tzwin", "tzwinlocal"]
ONEWEEK = datetime.timedelta(7)
TZKEYNAMENT = r"SOFTWARE\Microsoft\Windows NT\CurrentVersion\Time Zones"
TZKEYNAME9X = r"SOFTWARE\Microsoft\Windows\CurrentVersion\Time Zones"
TZLOCALKEYNAME = r"SYSTEM\CurrentControlSet\Control\TimeZoneInformation"
def _settzkeyname():
global TZKEYNAME
handle = _winreg.ConnectRegistry(None, _winreg.HKEY_LOCAL_MACHINE)
try:
_winreg.OpenKey(handle, TZKEYNAMENT).Close()
TZKEYNAME = TZKEYNAMENT
except WindowsError:
TZKEYNAME = TZKEYNAME9X
handle.Close()
_settzkeyname()
class tzwinbase(datetime.tzinfo):
"""tzinfo class based on win32's timezones available in the registry."""
def utcoffset(self, dt):
if self._isdst(dt):
return datetime.timedelta(minutes=self._dstoffset)
else:
return datetime.timedelta(minutes=self._stdoffset)
def dst(self, dt):
if self._isdst(dt):
minutes = self._dstoffset - self._stdoffset
return datetime.timedelta(minutes=minutes)
else:
return datetime.timedelta(0)
def tzname(self, dt):
if self._isdst(dt):
return self._dstname
else:
return self._stdname
def list():
"""Return a list of all time zones known to the system."""
handle = _winreg.ConnectRegistry(None, _winreg.HKEY_LOCAL_MACHINE)
tzkey = _winreg.OpenKey(handle, TZKEYNAME)
result = [_winreg.EnumKey(tzkey, i)
for i in range(_winreg.QueryInfoKey(tzkey)[0])]
tzkey.Close()
handle.Close()
return result
list = staticmethod(list)
def display(self):
return self._display
def _isdst(self, dt):
dston = picknthweekday(dt.year, self._dstmonth, self._dstdayofweek,
self._dsthour, self._dstminute,
self._dstweeknumber)
dstoff = picknthweekday(dt.year, self._stdmonth, self._stddayofweek,
self._stdhour, self._stdminute,
self._stdweeknumber)
if dston < dstoff:
return dston <= dt.replace(tzinfo=None) < dstoff
else:
return not dstoff <= dt.replace(tzinfo=None) < dston
class tzwin(tzwinbase):
def __init__(self, name):
self._name = name
handle = _winreg.ConnectRegistry(None, _winreg.HKEY_LOCAL_MACHINE)
tzkey = _winreg.OpenKey(handle, "%s\%s" % (TZKEYNAME, name))
keydict = valuestodict(tzkey)
tzkey.Close()
handle.Close()
self._stdname = keydict["Std"].encode("iso-8859-1")
self._dstname = keydict["Dlt"].encode("iso-8859-1")
self._display = keydict["Display"]
# See http://ww_winreg.jsiinc.com/SUBA/tip0300/rh0398.htm
tup = struct.unpack("=3l16h", keydict["TZI"])
self._stdoffset = -tup[0]-tup[1] # Bias + StandardBias * -1
self._dstoffset = self._stdoffset-tup[2] # + DaylightBias * -1
(self._stdmonth,
self._stddayofweek, # Sunday = 0
self._stdweeknumber, # Last = 5
self._stdhour,
self._stdminute) = tup[4:9]
(self._dstmonth,
self._dstdayofweek, # Sunday = 0
self._dstweeknumber, # Last = 5
self._dsthour,
self._dstminute) = tup[12:17]
def __repr__(self):
return "tzwin(%s)" % repr(self._name)
def __reduce__(self):
return (self.__class__, (self._name,))
class tzwinlocal(tzwinbase):
def __init__(self):
handle = _winreg.ConnectRegistry(None, _winreg.HKEY_LOCAL_MACHINE)
tzlocalkey = _winreg.OpenKey(handle, TZLOCALKEYNAME)
keydict = valuestodict(tzlocalkey)
tzlocalkey.Close()
self._stdname = keydict["StandardName"].encode("iso-8859-1")
self._dstname = keydict["DaylightName"].encode("iso-8859-1")
try:
tzkey = _winreg.OpenKey(handle, "%s\%s"%(TZKEYNAME, self._stdname))
_keydict = valuestodict(tzkey)
self._display = _keydict["Display"]
tzkey.Close()
except OSError:
self._display = None
handle.Close()
self._stdoffset = -keydict["Bias"]-keydict["StandardBias"]
self._dstoffset = self._stdoffset-keydict["DaylightBias"]
# See http://ww_winreg.jsiinc.com/SUBA/tip0300/rh0398.htm
tup = struct.unpack("=8h", keydict["StandardStart"])
(self._stdmonth,
self._stddayofweek, # Sunday = 0
self._stdweeknumber, # Last = 5
self._stdhour,
self._stdminute) = tup[1:6]
tup = struct.unpack("=8h", keydict["DaylightStart"])
(self._dstmonth,
self._dstdayofweek, # Sunday = 0
self._dstweeknumber, # Last = 5
self._dsthour,
self._dstminute) = tup[1:6]
def __reduce__(self):
return (self.__class__, ())
def picknthweekday(year, month, dayofweek, hour, minute, whichweek):
"""dayofweek == 0 means Sunday, whichweek 5 means last instance"""
first = datetime.datetime(year, month, 1, hour, minute)
weekdayone = first.replace(day=((dayofweek-first.isoweekday())%7+1))
for n in xrange(whichweek):
dt = weekdayone+(whichweek-n)*ONEWEEK
if dt.month == month:
return dt
def valuestodict(key):
"""Convert a registry key's values to a dictionary."""
dict = {}
size = _winreg.QueryInfoKey(key)[1]
for i in range(size):
data = _winreg.EnumValue(key, i)
dict[data[0]] = data[1]
return dict

85
lib/dateutil/zoneinfo/__init__.py Normal file
View File

@@ -0,0 +1,85 @@
"""
Copyright (c) 2003-2005 Gustavo Niemeyer <gustavo@niemeyer.net>
This module offers extensions to the standard python 2.3+
datetime module.
"""
from dateutil.tz import tzfile
from tarfile import TarFile
import os
__author__ = "Gustavo Niemeyer <gustavo@niemeyer.net>"
__license__ = "PSF License"
__all__ = ["setcachesize", "gettz", "rebuild"]
CACHE = {}
class tzfile(tzfile):
def __reduce__(self):
return (gettz, (self._filename,))
def getzoneinfofile():
filenames = os.listdir(os.path.join(os.path.dirname(__file__)))
filenames.sort()
filenames.reverse()
for entry in filenames:
if entry.startswith("zoneinfo") and ".tar." in entry:
return os.path.join(os.path.dirname(__file__), entry)
return None
def buildcache():
global CACHE
zoneinfofile = getzoneinfofile()
if zoneinfofile:
tf = TarFile.open(zoneinfofile)
try:
for tarinfo in tf.getmembers():
if tarinfo.islnk() or tarinfo.isfile():
zonefile = tf.extractfile(tarinfo)
CACHE[tarinfo.name] = tzfile(zonefile)
finally:
tf.close()
buildcache()
del getzoneinfofile
del buildcache
def setcachesize(_):
# Since the cache now eagerly initialized at
# import time, there's no point in controlling
# its size.
pass
def gettz(name):
return CACHE.get(name)
def rebuild(filename, tag=None, format="gz"):
import tempfile, shutil
tmpdir = tempfile.mkdtemp()
zonedir = os.path.join(tmpdir, "zoneinfo")
moduledir = os.path.dirname(__file__)
if tag: tag = "-"+tag
targetname = "zoneinfo%s.tar.%s" % (tag, format)
try:
tf = TarFile.open(filename)
for name in tf.getnames():
if not (name.endswith(".sh") or
name.endswith(".tab") or
name == "leapseconds"):
tf.extract(name, tmpdir)
filepath = os.path.join(tmpdir, name)
os.system("zic -d %s %s" % (zonedir, filepath))
tf.close()
target = os.path.join(moduledir, targetname)
for entry in os.listdir(moduledir):
if entry.startswith("zoneinfo") and ".tar." in entry:
os.unlink(os.path.join(moduledir, entry))
tf = TarFile.open(target, "w:%s" % format)
for entry in os.listdir(zonedir):
entrypath = os.path.join(zonedir, entry)
tf.add(entrypath, entry)
tf.close()
finally:
shutil.rmtree(tmpdir)

BIN
lib/dateutil/zoneinfo/zoneinfo-2012c.tar.gz Normal file
View File

Binary file not shown.

14
lib/guessit/__init__.py Normal file
View File

@@ -0,0 +1,14 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Extracts as much information as possible from a video file.
"""
from . import monkeypatch as _monkeypatch
from .api import guessit, GuessItApi
from .options import ConfigurationException
from .rules.common.quantity import Size
from .__version__ import __version__
_monkeypatch.monkeypatch_rebulk()

180
lib/guessit/__main__.py Normal file
View File

@@ -0,0 +1,180 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Entry point module
"""
# pragma: no cover
from __future__ import print_function
import json
import logging
import os
import sys
import six
from rebulk.__version__ import __version__ as __rebulk_version__
from guessit import api
from guessit.__version__ import __version__
from guessit.jsonutils import GuessitEncoder
from guessit.options import argument_parser, parse_options, load_config, merge_options
try:
from collections import OrderedDict
except ImportError: # pragma: no-cover
from ordereddict import OrderedDict # pylint:disable=import-error
def guess_filename(filename, options):
"""
Guess a single filename using given options
:param filename: filename to parse
:type filename: str
:param options:
:type options: dict
:return:
:rtype:
"""
if not options.get('yaml') and not options.get('json') and not options.get('show_property'):
print('For:', filename)
guess = api.guessit(filename, options)
if options.get('show_property'):
print(guess.get(options.get('show_property'), ''))
return
if options.get('json'):
print(json.dumps(guess, cls=GuessitEncoder, ensure_ascii=False))
elif options.get('yaml'):
import yaml
from guessit import yamlutils
ystr = yaml.dump({filename: OrderedDict(guess)}, Dumper=yamlutils.CustomDumper, default_flow_style=False,
allow_unicode=True)
i = 0
for yline in ystr.splitlines():
if i == 0:
print("? " + yline[:-1])
elif i == 1:
print(":" + yline[1:])
else:
print(yline)
i += 1
else:
print('GuessIt found:', json.dumps(guess, cls=GuessitEncoder, indent=4, ensure_ascii=False))
def display_properties(options):
"""
Display properties
"""
properties = api.properties(options)
if options.get('json'):
if options.get('values'):
print(json.dumps(properties, cls=GuessitEncoder, ensure_ascii=False))
else:
print(json.dumps(list(properties.keys()), cls=GuessitEncoder, ensure_ascii=False))
elif options.get('yaml'):
import yaml
from guessit import yamlutils
if options.get('values'):
print(yaml.dump(properties, Dumper=yamlutils.CustomDumper, default_flow_style=False, allow_unicode=True))
else:
print(yaml.dump(list(properties.keys()), Dumper=yamlutils.CustomDumper, default_flow_style=False,
allow_unicode=True))
else:
print('GuessIt properties:')
properties_list = list(sorted(properties.keys()))
for property_name in properties_list:
property_values = properties.get(property_name)
print(2 * ' ' + '[+] %s' % (property_name,))
if property_values and options.get('values'):
for property_value in property_values:
print(4 * ' ' + '[!] %s' % (property_value,))
def fix_argv_encoding():
"""
Fix encoding of sys.argv on windows Python 2
"""
if six.PY2 and os.name == 'nt': # pragma: no cover
# see http://bugs.python.org/issue2128
import locale
for i, j in enumerate(sys.argv):
sys.argv[i] = j.decode(locale.getpreferredencoding())
def main(args=None): # pylint:disable=too-many-branches
"""
Main function for entry point
"""
fix_argv_encoding()
if args is None: # pragma: no cover
options = parse_options()
else:
options = parse_options(args)
config = load_config(options)
options = merge_options(config, options)
if options.get('verbose'):
logging.basicConfig(stream=sys.stdout, format='%(message)s')
logging.getLogger().setLevel(logging.DEBUG)
help_required = True
if options.get('version'):
print('+-------------------------------------------------------+')
print('+ GuessIt ' + __version__ + (28 - len(__version__)) * ' ' + '+')
print('+-------------------------------------------------------+')
print('+ Rebulk ' + __rebulk_version__ + (29 - len(__rebulk_version__)) * ' ' + '+')
print('+-------------------------------------------------------+')
print('| Please report any bug or feature request at |')
print('| https://github.com/guessit-io/guessit/issues. |')
print('+-------------------------------------------------------+')
help_required = False
if options.get('yaml'):
try:
import yaml # pylint:disable=unused-variable,unused-import
except ImportError: # pragma: no cover
del options['yaml']
print('PyYAML is not installed. \'--yaml\' option will be ignored ...', file=sys.stderr)
if options.get('properties') or options.get('values'):
display_properties(options)
help_required = False
filenames = []
if options.get('filename'):
for filename in options.get('filename'):
filenames.append(filename)
if options.get('input_file'):
if six.PY2:
input_file = open(options.get('input_file'), 'r')
else:
input_file = open(options.get('input_file'), 'r', encoding='utf-8')
try:
filenames.extend([line.strip() for line in input_file.readlines()])
finally:
input_file.close()
filenames = list(filter(lambda f: f, filenames))
if filenames:
for filename in filenames:
help_required = False
guess_filename(filename, options)
if help_required: # pragma: no cover
argument_parser.print_help()
if __name__ == '__main__': # pragma: no cover
main()

7
lib/guessit/__version__.py Normal file
View File

@@ -0,0 +1,7 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Version module
"""
# pragma: no cover
__version__ = '3.1.2.dev0'

263
lib/guessit/api.py Normal file
View File

@@ -0,0 +1,263 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
API functions that can be used by external software
"""
try:
from collections import OrderedDict
except ImportError: # pragma: no-cover
from ordereddict import OrderedDict # pylint:disable=import-error
import os
import traceback
import six
from rebulk.introspector import introspect
from .__version__ import __version__
from .options import parse_options, load_config, merge_options
from .rules import rebulk_builder
class GuessitException(Exception):
"""
Exception raised when guessit fails to perform a guess because of an internal error.
"""
def __init__(self, string, options):
super(GuessitException, self).__init__("An internal error has occured in guessit.\n"
"===================== Guessit Exception Report =====================\n"
"version=%s\n"
"string=%s\n"
"options=%s\n"
"--------------------------------------------------------------------\n"
"%s"
"--------------------------------------------------------------------\n"
"Please report at "
"https://github.com/guessit-io/guessit/issues.\n"
"====================================================================" %
(__version__, str(string), str(options), traceback.format_exc()))
self.string = string
self.options = options
def configure(options=None, rules_builder=rebulk_builder, force=False):
"""
Load configuration files and initialize rebulk rules if required.
:param options:
:type options: dict
:param rules_builder:
:type rules_builder:
:param force:
:type force: bool
:return:
"""
default_api.configure(options, rules_builder=rules_builder, force=force)
def guessit(string, options=None):
"""
Retrieves all matches from string as a dict
:param string: the filename or release name
:type string: str
:param options:
:type options: str|dict
:return:
:rtype:
"""
return default_api.guessit(string, options)
def properties(options=None):
"""
Retrieves all properties with possible values that can be guessed
:param options:
:type options: str|dict
:return:
:rtype:
"""
return default_api.properties(options)
def suggested_expected(titles, options=None):
"""
Return a list of suggested titles to be used as `expected_title` based on the list of titles
:param titles: the filename or release name
:type titles: list|set|dict
:param options:
:type options: str|dict
:return:
:rtype: list of str
"""
return default_api.suggested_expected(titles, options)
class GuessItApi(object):
"""
An api class that can be configured with custom Rebulk configuration.
"""
def __init__(self):
"""Default constructor."""
self.rebulk = None
self.config = None
self.load_config_options = None
self.advanced_config = None
@classmethod
def _fix_encoding(cls, value):
if isinstance(value, list):
return [cls._fix_encoding(item) for item in value]
if isinstance(value, dict):
return {cls._fix_encoding(k): cls._fix_encoding(v) for k, v in value.items()}
if six.PY2 and isinstance(value, six.text_type):
return value.encode('utf-8')
if six.PY3 and isinstance(value, six.binary_type):
return value.decode('ascii')
return value
@classmethod
def _has_same_properties(cls, dic1, dic2, values):
for value in values:
if dic1.get(value) != dic2.get(value):
return False
return True
def configure(self, options=None, rules_builder=rebulk_builder, force=False, sanitize_options=True):
"""
Load configuration files and initialize rebulk rules if required.
:param options:
:type options: str|dict
:param rules_builder:
:type rules_builder:
:param force:
:type force: bool
:return:
:rtype: dict
"""
if sanitize_options:
options = parse_options(options, True)
options = self._fix_encoding(options)
if self.config is None or self.load_config_options is None or force or \
not self._has_same_properties(self.load_config_options,
options,
['config', 'no_user_config', 'no_default_config']):
config = load_config(options)
config = self._fix_encoding(config)
self.load_config_options = options
else:
config = self.config
advanced_config = merge_options(config.get('advanced_config'), options.get('advanced_config'))
should_build_rebulk = force or not self.rebulk or not self.advanced_config or \
self.advanced_config != advanced_config
if should_build_rebulk:
self.advanced_config = advanced_config
self.rebulk = rules_builder(advanced_config)
self.config = config
return self.config
def guessit(self, string, options=None): # pylint: disable=too-many-branches
"""
Retrieves all matches from string as a dict
:param string: the filename or release name
:type string: str|Path
:param options:
:type options: str|dict
:return:
:rtype:
"""
try:
from pathlib import Path
if isinstance(string, Path):
try:
# Handle path-like object
string = os.fspath(string)
except AttributeError:
string = str(string)
except ImportError:
pass
try:
options = parse_options(options, True)
options = self._fix_encoding(options)
config = self.configure(options, sanitize_options=False)
options = merge_options(config, options)
result_decode = False
result_encode = False
if six.PY2:
if isinstance(string, six.text_type):
string = string.encode("utf-8")
result_decode = True
elif isinstance(string, six.binary_type):
string = six.binary_type(string)
if six.PY3:
if isinstance(string, six.binary_type):
string = string.decode('ascii')
result_encode = True
elif isinstance(string, six.text_type):
string = six.text_type(string)
matches = self.rebulk.matches(string, options)
if result_decode:
for match in matches:
if isinstance(match.value, six.binary_type):
match.value = match.value.decode("utf-8")
if result_encode:
for match in matches:
if isinstance(match.value, six.text_type):
match.value = match.value.encode("ascii")
return matches.to_dict(options.get('advanced', False), options.get('single_value', False),
options.get('enforce_list', False))
except:
raise GuessitException(string, options)
def properties(self, options=None):
"""
Grab properties and values that can be generated.
:param options:
:type options:
:return:
:rtype:
"""
options = parse_options(options, True)
options = self._fix_encoding(options)
config = self.configure(options, sanitize_options=False)
options = merge_options(config, options)
unordered = introspect(self.rebulk, options).properties
ordered = OrderedDict()
for k in sorted(unordered.keys(), key=six.text_type):
ordered[k] = list(sorted(unordered[k], key=six.text_type))
if hasattr(self.rebulk, 'customize_properties'):
ordered = self.rebulk.customize_properties(ordered)
return ordered
def suggested_expected(self, titles, options=None):
"""
Return a list of suggested titles to be used as `expected_title` based on the list of titles
:param titles: the filename or release name
:type titles: list|set|dict
:param options:
:type options: str|dict
:return:
:rtype: list of str
"""
suggested = []
for title in titles:
guess = self.guessit(title, options)
if len(guess) != 2 or 'title' not in guess:
suggested.append(title)
return suggested
default_api = GuessItApi()

27
lib/guessit/backports.py Normal file
View File

@@ -0,0 +1,27 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Backports
"""
# pragma: no-cover
# pylint: skip-file
def cmp_to_key(mycmp):
"""functools.cmp_to_key backport"""
class KeyClass(object):
"""Key class"""
def __init__(self, obj, *args): # pylint: disable=unused-argument
self.obj = obj
def __lt__(self, other):
return mycmp(self.obj, other.obj) < 0
def __gt__(self, other):
return mycmp(self.obj, other.obj) > 0
def __eq__(self, other):
return mycmp(self.obj, other.obj) == 0
def __le__(self, other):
return mycmp(self.obj, other.obj) <= 0
def __ge__(self, other):
return mycmp(self.obj, other.obj) >= 0
def __ne__(self, other):
return mycmp(self.obj, other.obj) != 0
return KeyClass

586
lib/guessit/config/options.json Normal file
View File

@@ -0,0 +1,586 @@
{
"expected_title": [
"OSS 117",
"This is Us"
],
"allowed_countries": [
"au",
"gb",
"us"
],
"allowed_languages": [
"ca",
"cs",
"de",
"en",
"es",
"fr",
"he",
"hi",
"hu",
"it",
"ja",
"ko",
"mul",
"nl",
"no",
"pl",
"pt",
"ro",
"ru",
"sv",
"te",
"uk",
"und"
],
"advanced_config": {
"common_words": [
"ca",
"cat",
"de",
"he",
"it",
"no",
"por",
"rum",
"se",
"st",
"sub"
],
"groups": {
"starting": "([{",
"ending": ")]}"
},
"audio_codec": {
"audio_channels": {
"1.0": [
"1ch",
"mono"
],
"2.0": [
"2ch",
"stereo",
"re:(2[\\W_]0(?:ch)?)(?=[^\\d]|$)"
],
"5.1": [
"5ch",
"6ch",
"re:(5[\\W_][01](?:ch)?)(?=[^\\d]|$)",
"re:(6[\\W_]0(?:ch)?)(?=[^\\d]|$)"
],
"7.1": [
"7ch",
"8ch",
"re:(7[\\W_][01](?:ch)?)(?=[^\\d]|$)"
]
}
},
"container": {
"subtitles": [
"srt",
"idx",
"sub",
"ssa",
"ass"
],
"info": [
"nfo"
],
"videos": [
"3g2",
"3gp",
"3gp2",
"asf",
"avi",
"divx",
"flv",
"iso",
"m4v",
"mk2",
"mk3d",
"mka",
"mkv",
"mov",
"mp4",
"mp4a",
"mpeg",
"mpg",
"ogg",
"ogm",
"ogv",
"qt",
"ra",
"ram",
"rm",
"ts",
"vob",
"wav",
"webm",
"wma",
"wmv"
],
"torrent": [
"torrent"
],
"nzb": [
"nzb"
]
},
"country": {
"synonyms": {
"ES": [
"españa"
],
"GB": [
"UK"
],
"BR": [
"brazilian",
"bra"
],
"CA": [
"québec",
"quebec",
"qc"
],
"MX": [
"Latinoamérica",
"latin america"
]
}
},
"episodes": {
"season_max_range": 100,
"episode_max_range": 100,
"max_range_gap": 1,
"season_markers": [
"s"
],
"season_ep_markers": [
"x"
],
"disc_markers": [
"d"
],
"episode_markers": [
"xe",
"ex",
"ep",
"e",
"x"
],
"range_separators": [
"-",
"~",
"to",
"a"
],
"discrete_separators": [
"+",
"&",
"and",
"et"
],
"season_words": [
"season",
"saison",
"seizoen",
"seasons",
"saisons",
"tem",
"temp",
"temporada",
"temporadas",
"stagione"
],
"episode_words": [
"episode",
"episodes",
"eps",
"ep",
"episodio",
"episodios",
"capitulo",
"capitulos"
],
"of_words": [
"of",
"sur"
],
"all_words": [
"All"
]
},
"language": {
"synonyms": {
"ell": [
"gr",
"greek"
],
"spa": [
"esp",
"español",
"espanol"
],
"fra": [
"français",
"vf",
"vff",
"vfi",
"vfq"
],
"swe": [
"se"
],
"por_BR": [
"po",
"pb",
"pob",
"ptbr",
"br",
"brazilian"
],
"deu_CH": [
"swissgerman",
"swiss german"
],
"nld_BE": [
"flemish"
],
"cat": [
"català",
"castellano",
"espanol castellano",
"español castellano"
],
"ces": [
"cz"
],
"ukr": [
"ua"
],
"zho": [
"cn"
],
"jpn": [
"jp"
],
"hrv": [
"scr"
],
"mul": [
"multi",
"dl"
]
},
"subtitle_affixes": [
"sub",
"subs",
"esub",
"esubs",
"subbed",
"custom subbed",
"custom subs",
"custom sub",
"customsubbed",
"customsubs",
"customsub",
"soft subtitles",
"soft subs"
],
"subtitle_prefixes": [
"st",
"vost",
"subforced",
"fansub",
"hardsub",
"legenda",
"legendas",
"legendado",
"subtitulado",
"soft",
"subtitles"
],
"subtitle_suffixes": [
"subforced",
"fansub",
"hardsub"
],
"language_affixes": [
"dublado",
"dubbed",
"dub"
],
"language_prefixes": [
"true"
],
"language_suffixes": [
"audio"
],
"weak_affixes": [
"v",
"audio",
"true"
]
},
"part": {
"prefixes": [
"pt",
"part"
]
},
"release_group": {
"forbidden_names": [
"bonus",
"by",
"for",
"par",
"pour",
"rip"
],
"ignored_seps": "[]{}()"
},
"screen_size": {
"frame_rates": [
"23.976",
"24",
"25",
"29.970",
"30",
"48",
"50",
"60",
"120"
],
"min_ar": 1.333,
"max_ar": 1.898,
"interlaced": [
"360",
"480",
"576",
"900",
"1080"
],
"progressive": [
"360",
"480",
"540",
"576",
"900",
"1080",
"368",
"720",
"1440",
"2160",
"4320"
]
},
"website": {
"safe_tlds": [
"com",
"net",
"org"
],
"safe_subdomains": [
"www"
],
"safe_prefixes": [
"co",
"com",
"net",
"org"
],
"prefixes": [
"from"
]
},
"streaming_service": {
"A&E": [
"AE",
"A&E"
],
"ABC": "AMBC",
"ABC Australia": "AUBC",
"Al Jazeera English": "AJAZ",
"AMC": "AMC",
"Amazon Prime": [
"AMZN",
"Amazon",
"re:Amazon-?Prime"
],
"Adult Swim": [
"AS",
"re:Adult-?Swim"
],
"America's Test Kitchen": "ATK",
"Animal Planet": "ANPL",
"AnimeLab": "ANLB",
"AOL": "AOL",
"ARD": "ARD",
"BBC iPlayer": [
"iP",
"re:BBC-?iPlayer"
],
"BravoTV": "BRAV",
"Canal+": "CNLP",
"Cartoon Network": "CN",
"CBC": "CBC",
"CBS": "CBS",
"CNBC": "CNBC",
"Comedy Central": [
"CC",
"re:Comedy-?Central"
],
"Channel 4": "4OD",
"CHRGD": "CHGD",
"Cinemax": "CMAX",
"Country Music Television": "CMT",
"Comedians in Cars Getting Coffee": "CCGC",
"Crunchy Roll": [
"CR",
"re:Crunchy-?Roll"
],
"Crackle": "CRKL",
"CSpan": "CSPN",
"CTV": "CTV",
"CuriosityStream": "CUR",
"CWSeed": "CWS",
"Daisuki": "DSKI",
"DC Universe": "DCU",
"Deadhouse Films": "DHF",
"DramaFever": [
"DF",
"DramaFever"
],
"Digiturk Diledigin Yerde": "DDY",
"Discovery": [
"DISC",
"Discovery"
],
"Disney": [
"DSNY",
"Disney"
],
"DIY Network": "DIY",
"Doc Club": "DOCC",
"DPlay": "DPLY",
"E!": "ETV",
"ePix": "EPIX",
"El Trece": "ETTV",
"ESPN": "ESPN",
"Esquire": "ESQ",
"Family": "FAM",
"Family Jr": "FJR",
"Food Network": "FOOD",
"Fox": "FOX",
"Freeform": "FREE",
"FYI Network": "FYI",
"Global": "GLBL",
"GloboSat Play": "GLOB",
"Hallmark": "HLMK",
"HBO Go": [
"HBO",
"re:HBO-?Go"
],
"HGTV": "HGTV",
"History": [
"HIST",
"History"
],
"Hulu": "HULU",
"Investigation Discovery": "ID",
"IFC": "IFC",
"iTunes": "iTunes",
"ITV": "ITV",
"Knowledge Network": "KNOW",
"Lifetime": "LIFE",
"Motor Trend OnDemand": "MTOD",
"MBC": [
"MBC",
"MBCVOD"
],
"MSNBC": "MNBC",
"MTV": "MTV",
"National Geographic": [
"NATG",
"re:National-?Geographic"
],
"NBA TV": [
"NBA",
"re:NBA-?TV"
],
"NBC": "NBC",
"Netflix": [
"NF",
"Netflix"
],
"NFL": "NFL",
"NFL Now": "NFLN",
"NHL GameCenter": "GC",
"Nickelodeon": [
"NICK",
"Nickelodeon"
],
"Norsk Rikskringkasting": "NRK",
"OnDemandKorea": [
"ODK",
"OnDemandKorea"
],
"PBS": "PBS",
"PBS Kids": "PBSK",
"Playstation Network": "PSN",
"Pluzz": "PLUZ",
"RTE One": "RTE",
"SBS (AU)": "SBS",
"SeeSo": [
"SESO",
"SeeSo"
],
"Shomi": "SHMI",
"Spike": "SPIK",
"Spike TV": [
"SPKE",
"re:Spike-?TV"
],
"Sportsnet": "SNET",
"Sprout": "SPRT",
"Stan": "STAN",
"Starz": "STZ",
"Sveriges Television": "SVT",
"SwearNet": "SWER",
"Syfy": "SYFY",
"TBS": "TBS",
"TFou": "TFOU",
"The CW": [
"CW",
"re:The-?CW"
],
"TLC": "TLC",
"TubiTV": "TUBI",
"TV3 Ireland": "TV3",
"TV4 Sweeden": "TV4",
"TVING": "TVING",
"TV Land": [
"TVL",
"re:TV-?Land"
],
"UFC": "UFC",
"UKTV": "UKTV",
"Univision": "UNIV",
"USA Network": "USAN",
"Velocity": "VLCT",
"VH1": "VH1",
"Viceland": "VICE",
"Viki": "VIKI",
"Vimeo": "VMEO",
"VRV": "VRV",
"W Network": "WNET",
"WatchMe": "WME",
"WWE Network": "WWEN",
"Xbox Video": "XBOX",
"Yahoo": "YHOO",
"YouTube Red": "RED",
"ZDF": "ZDF"
}
}
}

22
lib/guessit/jsonutils.py Normal file
View File

@@ -0,0 +1,22 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
JSON Utils
"""
import json
from six import text_type
from rebulk.match import Match
class GuessitEncoder(json.JSONEncoder):
"""
JSON Encoder for guessit response
"""
def default(self, o): # pylint:disable=method-hidden
if isinstance(o, Match):
return o.advanced
if hasattr(o, 'name'): # Babelfish languages/countries long name
return text_type(o.name)
# pragma: no cover
return text_type(o)

34
lib/guessit/monkeypatch.py Normal file
View File

@@ -0,0 +1,34 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Monkeypatch initialisation functions
"""
try:
from collections import OrderedDict
except ImportError: # pragma: no-cover
from ordereddict import OrderedDict # pylint:disable=import-error
from rebulk.match import Match
def monkeypatch_rebulk():
"""Monkeypatch rebulk classes"""
@property
def match_advanced(self):
"""
Build advanced dict from match
:param self:
:return:
"""
ret = OrderedDict()
ret['value'] = self.value
if self.raw:
ret['raw'] = self.raw
ret['start'] = self.start
ret['end'] = self.end
return ret
Match.advanced = match_advanced

295
lib/guessit/options.py Normal file
View File

@@ -0,0 +1,295 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Options
"""
import copy
import json
import os
import pkgutil
import shlex
from argparse import ArgumentParser
import six
def build_argument_parser():
"""
Builds the argument parser
:return: the argument parser
:rtype: ArgumentParser
"""
opts = ArgumentParser()
opts.add_argument(dest='filename', help='Filename or release name to guess', nargs='*')
naming_opts = opts.add_argument_group("Naming")
naming_opts.add_argument('-t', '--type', dest='type', default=None,
help='The suggested file type: movie, episode. If undefined, type will be guessed.')
naming_opts.add_argument('-n', '--name-only', dest='name_only', action='store_true', default=None,
help='Parse files as name only, considering "/" and "\\" like other separators.')
naming_opts.add_argument('-Y', '--date-year-first', action='store_true', dest='date_year_first', default=None,
help='If short date is found, consider the first digits as the year.')
naming_opts.add_argument('-D', '--date-day-first', action='store_true', dest='date_day_first', default=None,
help='If short date is found, consider the second digits as the day.')
naming_opts.add_argument('-L', '--allowed-languages', action='append', dest='allowed_languages', default=None,
help='Allowed language (can be used multiple times)')
naming_opts.add_argument('-C', '--allowed-countries', action='append', dest='allowed_countries', default=None,
help='Allowed country (can be used multiple times)')
naming_opts.add_argument('-E', '--episode-prefer-number', action='store_true', dest='episode_prefer_number',
default=None,
help='Guess "serie.213.avi" as the episode 213. Without this option, '
'it will be guessed as season 2, episode 13')
naming_opts.add_argument('-T', '--expected-title', action='append', dest='expected_title', default=None,
help='Expected title to parse (can be used multiple times)')
naming_opts.add_argument('-G', '--expected-group', action='append', dest='expected_group', default=None,
help='Expected release group (can be used multiple times)')
naming_opts.add_argument('--includes', action='append', dest='includes', default=None,
help='List of properties to be detected')
naming_opts.add_argument('--excludes', action='append', dest='excludes', default=None,
help='List of properties to be ignored')
input_opts = opts.add_argument_group("Input")
input_opts.add_argument('-f', '--input-file', dest='input_file', default=None,
help='Read filenames from an input text file. File should use UTF-8 charset.')
output_opts = opts.add_argument_group("Output")
output_opts.add_argument('-v', '--verbose', action='store_true', dest='verbose', default=None,
help='Display debug output')
output_opts.add_argument('-P', '--show-property', dest='show_property', default=None,
help='Display the value of a single property (title, series, video_codec, year, ...)')
output_opts.add_argument('-a', '--advanced', dest='advanced', action='store_true', default=None,
help='Display advanced information for filename guesses, as json output')
output_opts.add_argument('-s', '--single-value', dest='single_value', action='store_true', default=None,
help='Keep only first value found for each property')
output_opts.add_argument('-l', '--enforce-list', dest='enforce_list', action='store_true', default=None,
help='Wrap each found value in a list even when property has a single value')
output_opts.add_argument('-j', '--json', dest='json', action='store_true', default=None,
help='Display information for filename guesses as json output')
output_opts.add_argument('-y', '--yaml', dest='yaml', action='store_true', default=None,
help='Display information for filename guesses as yaml output')
conf_opts = opts.add_argument_group("Configuration")
conf_opts.add_argument('-c', '--config', dest='config', action='append', default=None,
help='Filepath to configuration file. Configuration file contains the same '
'options as those from command line options, but option names have "-" characters '
'replaced with "_". This configuration will be merged with default and user '
'configuration files.')
conf_opts.add_argument('--no-user-config', dest='no_user_config', action='store_true',
default=None,
help='Disable user configuration. If not defined, guessit tries to read configuration files '
'at ~/.guessit/options.(json|yml|yaml) and ~/.config/guessit/options.(json|yml|yaml)')
conf_opts.add_argument('--no-default-config', dest='no_default_config', action='store_true',
default=None,
help='Disable default configuration. This should be done only if you are providing a full '
'configuration through user configuration or --config option. If no "advanced_config" '
'is provided by another configuration file, it will still be loaded from default '
'configuration.')
information_opts = opts.add_argument_group("Information")
information_opts.add_argument('-p', '--properties', dest='properties', action='store_true', default=None,
help='Display properties that can be guessed.')
information_opts.add_argument('-V', '--values', dest='values', action='store_true', default=None,
help='Display property values that can be guessed.')
information_opts.add_argument('--version', dest='version', action='store_true', default=None,
help='Display the guessit version.')
return opts
def parse_options(options=None, api=False):
"""
Parse given option string
:param options:
:type options:
:param api
:type api: boolean
:return:
:rtype:
"""
if isinstance(options, six.string_types):
args = shlex.split(options)
options = vars(argument_parser.parse_args(args))
elif options is None:
if api:
options = {}
else:
options = vars(argument_parser.parse_args())
elif not isinstance(options, dict):
options = vars(argument_parser.parse_args(options))
return options
argument_parser = build_argument_parser()
class ConfigurationException(Exception):
"""
Exception related to configuration file.
"""
pass # pylint:disable=unnecessary-pass
def load_config(options):
"""
Load options from configuration files, if defined and present.
:param options:
:type options:
:return:
:rtype:
"""
configurations = []
if not options.get('no_default_config'):
default_options_data = pkgutil.get_data('guessit', 'config/options.json').decode('utf-8')
default_options = json.loads(default_options_data)
configurations.append(default_options)
config_files = []
if not options.get('no_user_config'):
home_directory = os.path.expanduser("~")
cwd = os.getcwd()
yaml_supported = False
try:
import yaml # pylint:disable=unused-variable,unused-import
yaml_supported = True
except ImportError:
pass
config_file_locations = get_options_file_locations(home_directory, cwd, yaml_supported)
config_files = [f for f in config_file_locations if os.path.exists(f)]
custom_config_files = options.get('config')
if custom_config_files:
config_files = config_files + custom_config_files
for config_file in config_files:
config_file_options = load_config_file(config_file)
if config_file_options:
configurations.append(config_file_options)
config = {}
if configurations:
config = merge_options(*configurations)
if 'advanced_config' not in config:
# Guessit doesn't work without advanced_config, so we use default if no configuration files provides it.
default_options_data = pkgutil.get_data('guessit', 'config/options.json').decode('utf-8')
default_options = json.loads(default_options_data)
config['advanced_config'] = default_options['advanced_config']
return config
def merge_options(*options):
"""
Merge options into a single options dict.
:param options:
:type options:
:return:
:rtype:
"""
merged = {}
if options:
if options[0]:
merged.update(copy.deepcopy(options[0]))
for options in options[1:]:
if options:
pristine = options.get('pristine')
if pristine is True:
merged = {}
elif pristine:
for to_reset in pristine:
if to_reset in merged:
del merged[to_reset]
for (option, value) in options.items():
merge_option_value(option, value, merged)
return merged
def merge_option_value(option, value, merged):
"""
Merge option value
:param option:
:param value:
:param merged:
:return:
"""
if value is not None and option != 'pristine':
if option in merged.keys() and isinstance(merged[option], list):
for val in value:
if val not in merged[option]:
merged[option].append(val)
elif option in merged.keys() and isinstance(merged[option], dict):
merged[option] = merge_options(merged[option], value)
elif isinstance(value, list):
merged[option] = list(value)
else:
merged[option] = value
def load_config_file(filepath):
"""
Load a configuration as an options dict.
Format of the file is given with filepath extension.
:param filepath:
:type filepath:
:return:
:rtype:
"""
if filepath.endswith('.json'):
with open(filepath) as config_file_data:
return json.load(config_file_data)
if filepath.endswith('.yaml') or filepath.endswith('.yml'):
try:
import yaml
with open(filepath) as config_file_data:
return yaml.load(config_file_data, yaml.SafeLoader)
except ImportError: # pragma: no cover
raise ConfigurationException('Configuration file extension is not supported. '
'PyYAML should be installed to support "%s" file' % (
filepath,))
try:
# Try to load input as JSON
return json.loads(filepath)
except: # pylint: disable=bare-except
pass
raise ConfigurationException('Configuration file extension is not supported for "%s" file.' % (filepath,))
def get_options_file_locations(homedir, cwd, yaml_supported=False):
"""
Get all possible locations for options file.
:param homedir: user home directory
:type homedir: basestring
:param cwd: current working directory
:type homedir: basestring
:return:
:rtype: list
"""
locations = []
configdirs = [(os.path.join(homedir, '.guessit'), 'options'),
(os.path.join(homedir, '.config', 'guessit'), 'options'),
(cwd, 'guessit.options')]
configexts = ['json']
if yaml_supported:
configexts.append('yaml')
configexts.append('yml')
for configdir in configdirs:
for configext in configexts:
locations.append(os.path.join(configdir[0], configdir[1] + '.' + configext))
return locations

35
lib/guessit/reutils.py Normal file
View File

@@ -0,0 +1,35 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Utils for re module
"""
from rebulk.remodule import re
def build_or_pattern(patterns, name=None, escape=False):
"""
Build a or pattern string from a list of possible patterns
:param patterns:
:type patterns:
:param name:
:type name:
:param escape:
:type escape:
:return:
:rtype:
"""
or_pattern = []
for pattern in patterns:
if not or_pattern:
or_pattern.append('(?')
if name:
or_pattern.append('P<' + name + '>')
else:
or_pattern.append(':')
else:
or_pattern.append('|')
or_pattern.append('(?:%s)' % re.escape(pattern) if escape else pattern)
or_pattern.append(')')
return ''.join(or_pattern)

99
lib/guessit/rules/__init__.py Normal file
View File

@@ -0,0 +1,99 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Rebulk object default builder
"""
from rebulk import Rebulk
from .markers.path import path
from .markers.groups import groups
from .properties.episodes import episodes
from .properties.container import container
from .properties.source import source
from .properties.video_codec import video_codec
from .properties.audio_codec import audio_codec
from .properties.screen_size import screen_size
from .properties.website import website
from .properties.date import date
from .properties.title import title
from .properties.episode_title import episode_title
from .properties.language import language
from .properties.country import country
from .properties.release_group import release_group
from .properties.streaming_service import streaming_service
from .properties.other import other
from .properties.size import size
from .properties.bit_rate import bit_rate
from .properties.edition import edition
from .properties.cds import cds
from .properties.bonus import bonus
from .properties.film import film
from .properties.part import part
from .properties.crc import crc
from .properties.mimetype import mimetype
from .properties.type import type_
from .processors import processors
def rebulk_builder(config):
"""
Default builder for main Rebulk object used by api.
:return: Main Rebulk object
:rtype: Rebulk
"""
def _config(name):
return config.get(name, {})
rebulk = Rebulk()
common_words = frozenset(_config('common_words'))
rebulk.rebulk(path(_config('path')))
rebulk.rebulk(groups(_config('groups')))
rebulk.rebulk(episodes(_config('episodes')))
rebulk.rebulk(container(_config('container')))
rebulk.rebulk(source(_config('source')))
rebulk.rebulk(video_codec(_config('video_codec')))
rebulk.rebulk(audio_codec(_config('audio_codec')))
rebulk.rebulk(screen_size(_config('screen_size')))
rebulk.rebulk(website(_config('website')))
rebulk.rebulk(date(_config('date')))
rebulk.rebulk(title(_config('title')))
rebulk.rebulk(episode_title(_config('episode_title')))
rebulk.rebulk(language(_config('language'), common_words))
rebulk.rebulk(country(_config('country'), common_words))
rebulk.rebulk(release_group(_config('release_group')))
rebulk.rebulk(streaming_service(_config('streaming_service')))
rebulk.rebulk(other(_config('other')))
rebulk.rebulk(size(_config('size')))
rebulk.rebulk(bit_rate(_config('bit_rate')))
rebulk.rebulk(edition(_config('edition')))
rebulk.rebulk(cds(_config('cds')))
rebulk.rebulk(bonus(_config('bonus')))
rebulk.rebulk(film(_config('film')))
rebulk.rebulk(part(_config('part')))
rebulk.rebulk(crc(_config('crc')))
rebulk.rebulk(processors(_config('processors')))
rebulk.rebulk(mimetype(_config('mimetype')))
rebulk.rebulk(type_(_config('type')))
def customize_properties(properties):
"""
Customize default rebulk properties
"""
count = properties['count']
del properties['count']
properties['season_count'] = count
properties['episode_count'] = count
return properties
rebulk.customize_properties = customize_properties
return rebulk

15
lib/guessit/rules/common/__init__.py Normal file
View File

@@ -0,0 +1,15 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Common module
"""
import re
seps = r' [](){}+*|=-_~#/\\.,;:' # list of tags/words separators
seps_no_groups = seps.replace('[](){}', '')
seps_no_fs = seps.replace('/', '').replace('\\', '')
title_seps = r'-+/\|' # separators for title
dash = (r'-', r'['+re.escape(seps_no_fs)+']') # abbreviation used by many rebulk objects.
alt_dash = (r'@', r'['+re.escape(seps_no_fs)+']') # abbreviation used by many rebulk objects.

75
lib/guessit/rules/common/comparators.py Normal file
View File

@@ -0,0 +1,75 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Comparators
"""
try:
from functools import cmp_to_key
except ImportError:
from ...backports import cmp_to_key
def marker_comparator_predicate(match):
"""
Match predicate used in comparator
"""
return (
not match.private
and match.name not in ('proper_count', 'title')
and not (match.name == 'container' and 'extension' in match.tags)
and not (match.name == 'other' and match.value == 'Rip')
)
def marker_weight(matches, marker, predicate):
"""
Compute the comparator weight of a marker
:param matches:
:param marker:
:param predicate:
:return:
"""
return len(set(match.name for match in matches.range(*marker.span, predicate=predicate)))
def marker_comparator(matches, markers, predicate):
"""
Builds a comparator that returns markers sorted from the most valuable to the less.
Take the parts where matches count is higher, then when length is higher, then when position is at left.
:param matches:
:type matches:
:param markers:
:param predicate:
:return:
:rtype:
"""
def comparator(marker1, marker2):
"""
The actual comparator function.
"""
matches_count = marker_weight(matches, marker2, predicate) - marker_weight(matches, marker1, predicate)
if matches_count:
return matches_count
# give preference to rightmost path
return markers.index(marker2) - markers.index(marker1)
return comparator
def marker_sorted(markers, matches, predicate=marker_comparator_predicate):
"""
Sort markers from matches, from the most valuable to the less.
:param markers:
:type markers:
:param matches:
:type matches:
:param predicate:
:return:
:rtype:
"""
return sorted(markers, key=cmp_to_key(marker_comparator(matches, markers, predicate=predicate)))

125
lib/guessit/rules/common/date.py Normal file
View File

@@ -0,0 +1,125 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Date
"""
from dateutil import parser
from rebulk.remodule import re
_dsep = r'[-/ \.]'
_dsep_bis = r'[-/ \.x]'
date_regexps = [
re.compile(r'%s((\d{8}))%s' % (_dsep, _dsep), re.IGNORECASE),
re.compile(r'%s((\d{6}))%s' % (_dsep, _dsep), re.IGNORECASE),
re.compile(r'(?:^|[^\d])((\d{2})%s(\d{1,2})%s(\d{1,2}))(?:$|[^\d])' % (_dsep, _dsep), re.IGNORECASE),
re.compile(r'(?:^|[^\d])((\d{1,2})%s(\d{1,2})%s(\d{2}))(?:$|[^\d])' % (_dsep, _dsep), re.IGNORECASE),
re.compile(r'(?:^|[^\d])((\d{4})%s(\d{1,2})%s(\d{1,2}))(?:$|[^\d])' % (_dsep_bis, _dsep), re.IGNORECASE),
re.compile(r'(?:^|[^\d])((\d{1,2})%s(\d{1,2})%s(\d{4}))(?:$|[^\d])' % (_dsep, _dsep_bis), re.IGNORECASE),
re.compile(r'(?:^|[^\d])((\d{1,2}(?:st|nd|rd|th)?%s(?:[a-z]{3,10})%s\d{4}))(?:$|[^\d])' % (_dsep, _dsep),
re.IGNORECASE)]
def valid_year(year):
"""Check if number is a valid year"""
return 1920 <= year < 2030
def _is_int(string):
"""
Check if the input string is an integer
:param string:
:type string:
:return:
:rtype:
"""
try:
int(string)
return True
except ValueError:
return False
def _guess_day_first_parameter(groups): # pylint:disable=inconsistent-return-statements
"""
If day_first is not defined, use some heuristic to fix it.
It helps to solve issues with python dateutils 2.5.3 parser changes.
:param groups: match groups found for the date
:type groups: list of match objects
:return: day_first option guessed value
:rtype: bool
"""
# If match starts with a long year, then day_first is force to false.
if _is_int(groups[0]) and valid_year(int(groups[0][:4])):
return False
# If match ends with a long year, the day_first is forced to true.
if _is_int(groups[-1]) and valid_year(int(groups[-1][-4:])):
return True
# If match starts with a short year, then day_first is force to false.
if _is_int(groups[0]) and int(groups[0][:2]) > 31:
return False
# If match ends with a short year, then day_first is force to true.
if _is_int(groups[-1]) and int(groups[-1][-2:]) > 31:
return True
def search_date(string, year_first=None, day_first=None): # pylint:disable=inconsistent-return-statements
"""Looks for date patterns, and if found return the date and group span.
Assumes there are sentinels at the beginning and end of the string that
always allow matching a non-digit delimiting the date.
Year can be defined on two digit only. It will return the nearest possible
date from today.
>>> search_date(' This happened on 2002-04-22. ')
(18, 28, datetime.date(2002, 4, 22))
>>> search_date(' And this on 17-06-1998. ')
(13, 23, datetime.date(1998, 6, 17))
>>> search_date(' no date in here ')
"""
for date_re in date_regexps:
search_match = date_re.search(string)
if not search_match:
continue
start, end = search_match.start(1), search_match.end(1)
groups = search_match.groups()[1:]
match = '-'.join(groups)
if match is None:
continue
if year_first and day_first is None:
day_first = False
if day_first is None:
day_first = _guess_day_first_parameter(groups)
# If day_first/year_first is undefined, parse is made using both possible values.
yearfirst_opts = [False, True]
if year_first is not None:
yearfirst_opts = [year_first]
dayfirst_opts = [True, False]
if day_first is not None:
dayfirst_opts = [day_first]
kwargs_list = ({'dayfirst': d, 'yearfirst': y}
for d in dayfirst_opts for y in yearfirst_opts)
for kwargs in kwargs_list:
try:
date = parser.parse(match, **kwargs)
except (ValueError, TypeError): # pragma: no cover
# see https://bugs.launchpad.net/dateutil/+bug/1247643
date = None
# check date plausibility
if date and valid_year(date.year): # pylint:disable=no-member
return start, end, date.date() # pylint:disable=no-member

53
lib/guessit/rules/common/expected.py Normal file
View File

@@ -0,0 +1,53 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Expected property factory
"""
import re
from rebulk import Rebulk
from rebulk.utils import find_all
from . import dash, seps
def build_expected_function(context_key):
"""
Creates a expected property function
:param context_key:
:type context_key:
:param cleanup:
:type cleanup:
:return:
:rtype:
"""
def expected(input_string, context):
"""
Expected property functional pattern.
:param input_string:
:type input_string:
:param context:
:type context:
:return:
:rtype:
"""
ret = []
for search in context.get(context_key):
if search.startswith('re:'):
search = search[3:]
search = search.replace(' ', '-')
matches = Rebulk().regex(search, abbreviations=[dash], flags=re.IGNORECASE) \
.matches(input_string, context)
for match in matches:
ret.append(match.span)
else:
value = search
for sep in seps:
input_string = input_string.replace(sep, ' ')
search = search.replace(sep, ' ')
for start in find_all(input_string, search, ignore_case=True):
ret.append({'start': start, 'end': start + len(search), 'value': value})
return ret
return expected

136
lib/guessit/rules/common/formatters.py Normal file
View File

@@ -0,0 +1,136 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Formatters
"""
from rebulk.formatters import formatters
from rebulk.remodule import re
from . import seps
_excluded_clean_chars = ',:;-/\\'
clean_chars = ""
for sep in seps:
if sep not in _excluded_clean_chars:
clean_chars += sep
def _potential_before(i, input_string):
"""
Check if the character at position i can be a potential single char separator considering what's before it.
:param i:
:type i: int
:param input_string:
:type input_string: str
:return:
:rtype: bool
"""
return i - 1 >= 0 and input_string[i] in seps and input_string[i - 2] in seps and input_string[i - 1] not in seps
def _potential_after(i, input_string):
"""
Check if the character at position i can be a potential single char separator considering what's after it.
:param i:
:type i: int
:param input_string:
:type input_string: str
:return:
:rtype: bool
"""
return i + 2 >= len(input_string) or \
input_string[i + 2] == input_string[i] and input_string[i + 1] not in seps
def cleanup(input_string):
"""
Removes and strip separators from input_string (but keep ',;' characters)
It also keep separators for single characters (Mavels Agents of S.H.I.E.L.D.)
:param input_string:
:type input_string: str
:return:
:rtype:
"""
clean_string = input_string
for char in clean_chars:
clean_string = clean_string.replace(char, ' ')
# Restore input separator if they separate single characters.
# Useful for Mavels Agents of S.H.I.E.L.D.
# https://github.com/guessit-io/guessit/issues/278
indices = [i for i, letter in enumerate(clean_string) if letter in seps]
dots = set()
if indices:
clean_list = list(clean_string)
potential_indices = []
for i in indices:
if _potential_before(i, input_string) and _potential_after(i, input_string):
potential_indices.append(i)
replace_indices = []
for potential_index in potential_indices:
if potential_index - 2 in potential_indices or potential_index + 2 in potential_indices:
replace_indices.append(potential_index)
if replace_indices:
for replace_index in replace_indices:
dots.add(input_string[replace_index])
clean_list[replace_index] = input_string[replace_index]
clean_string = ''.join(clean_list)
clean_string = strip(clean_string, ''.join([c for c in seps if c not in dots]))
clean_string = re.sub(' +', ' ', clean_string)
return clean_string
def strip(input_string, chars=seps):
"""
Strip separators from input_string
:param input_string:
:param chars:
:type input_string:
:return:
:rtype:
"""
return input_string.strip(chars)
def raw_cleanup(raw):
"""
Cleanup a raw value to perform raw comparison
:param raw:
:type raw:
:return:
:rtype:
"""
return formatters(cleanup, strip)(raw.lower())
def reorder_title(title, articles=('the',), separators=(',', ', ')):
"""
Reorder the title
:param title:
:type title:
:param articles:
:type articles:
:param separators:
:type separators:
:return:
:rtype:
"""
ltitle = title.lower()
for article in articles:
for separator in separators:
suffix = separator + article
if ltitle[-len(suffix):] == suffix:
return title[-len(suffix) + len(separator):] + ' ' + title[:-len(suffix)]
return title

165
lib/guessit/rules/common/numeral.py Normal file
View File

@@ -0,0 +1,165 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
parse numeral from various formats
"""
from rebulk.remodule import re
digital_numeral = r'\d{1,4}'
roman_numeral = r'(?=[MCDLXVI]+)M{0,4}(?:CM|CD|D?C{0,3})(?:XC|XL|L?X{0,3})(?:IX|IV|V?I{0,3})'
english_word_numeral_list = [
'zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight', 'nine', 'ten',
'eleven', 'twelve', 'thirteen', 'fourteen', 'fifteen', 'sixteen', 'seventeen', 'eighteen', 'nineteen', 'twenty'
]
french_word_numeral_list = [
'zéro', 'un', 'deux', 'trois', 'quatre', 'cinq', 'six', 'sept', 'huit', 'neuf', 'dix',
'onze', 'douze', 'treize', 'quatorze', 'quinze', 'seize', 'dix-sept', 'dix-huit', 'dix-neuf', 'vingt'
]
french_alt_word_numeral_list = [
'zero', 'une', 'deux', 'trois', 'quatre', 'cinq', 'six', 'sept', 'huit', 'neuf', 'dix',
'onze', 'douze', 'treize', 'quatorze', 'quinze', 'seize', 'dixsept', 'dixhuit', 'dixneuf', 'vingt'
]
def __build_word_numeral(*args):
"""
Build word numeral regexp from list.
:param args:
:type args:
:param kwargs:
:type kwargs:
:return:
:rtype:
"""
re_ = None
for word_list in args:
for word in word_list:
if not re_:
re_ = r'(?:(?=\w+)'
else:
re_ += '|'
re_ += word
re_ += ')'
return re_
word_numeral = __build_word_numeral(english_word_numeral_list, french_word_numeral_list, french_alt_word_numeral_list)
numeral = '(?:' + digital_numeral + '|' + roman_numeral + '|' + word_numeral + ')'
__romanNumeralMap = (
('M', 1000),
('CM', 900),
('D', 500),
('CD', 400),
('C', 100),
('XC', 90),
('L', 50),
('XL', 40),
('X', 10),
('IX', 9),
('V', 5),
('IV', 4),
('I', 1)
)
__romanNumeralPattern = re.compile('^' + roman_numeral + '$')
def __parse_roman(value):
"""
convert Roman numeral to integer
:param value: Value to parse
:type value: string
:return:
:rtype:
"""
if not __romanNumeralPattern.search(value):
raise ValueError('Invalid Roman numeral: %s' % value)
result = 0
index = 0
for num, integer in __romanNumeralMap:
while value[index:index + len(num)] == num:
result += integer
index += len(num)
return result
def __parse_word(value):
"""
Convert Word numeral to integer
:param value: Value to parse
:type value: string
:return:
:rtype:
"""
for word_list in [english_word_numeral_list, french_word_numeral_list, french_alt_word_numeral_list]:
try:
return word_list.index(value.lower())
except ValueError:
pass
raise ValueError # pragma: no cover
_clean_re = re.compile(r'[^\d]*(\d+)[^\d]*')
def parse_numeral(value, int_enabled=True, roman_enabled=True, word_enabled=True, clean=True):
"""
Parse a numeric value into integer.
:param value: Value to parse. Can be an integer, roman numeral or word.
:type value: string
:param int_enabled:
:type int_enabled:
:param roman_enabled:
:type roman_enabled:
:param word_enabled:
:type word_enabled:
:param clean:
:type clean:
:return: Numeric value, or None if value can't be parsed
:rtype: int
"""
# pylint: disable=too-many-branches
if int_enabled:
try:
if clean:
match = _clean_re.match(value)
if match:
clean_value = match.group(1)
return int(clean_value)
return int(value)
except ValueError:
pass
if roman_enabled:
try:
if clean:
for word in value.split():
try:
return __parse_roman(word.upper())
except ValueError:
pass
return __parse_roman(value)
except ValueError:
pass
if word_enabled:
try:
if clean:
for word in value.split():
try:
return __parse_word(word)
except ValueError: # pragma: no cover
pass
return __parse_word(value) # pragma: no cover
except ValueError: # pragma: no cover
pass
raise ValueError('Invalid numeral: ' + value) # pragma: no cover

27
lib/guessit/rules/common/pattern.py Normal file
View File

@@ -0,0 +1,27 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Pattern utility functions
"""
def is_disabled(context, name):
"""Whether a specific pattern is disabled.
The context object might define an inclusion list (includes) or an exclusion list (excludes)
A pattern is considered disabled if it's found in the exclusion list or
it's not found in the inclusion list and the inclusion list is not empty or not defined.
:param context:
:param name:
:return:
"""
if not context:
return False
excludes = context.get('excludes')
if excludes and name in excludes:
return True
includes = context.get('includes')
return includes and name not in includes

106
lib/guessit/rules/common/quantity.py Normal file
View File

@@ -0,0 +1,106 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Quantities: Size
"""
import re
from abc import abstractmethod
import six
from ..common import seps
class Quantity(object):
"""
Represent a quantity object with magnitude and units.
"""
parser_re = re.compile(r'(?P<magnitude>\d+(?:[.]\d+)?)(?P<units>[^\d]+)?')
def __init__(self, magnitude, units):
self.magnitude = magnitude
self.units = units
@classmethod
@abstractmethod
def parse_units(cls, value):
"""
Parse a string to a proper unit notation.
"""
raise NotImplementedError
@classmethod
def fromstring(cls, string):
"""
Parse the string into a quantity object.
:param string:
:return:
"""
values = cls.parser_re.match(string).groupdict()
try:
magnitude = int(values['magnitude'])
except ValueError:
magnitude = float(values['magnitude'])
units = cls.parse_units(values['units'])
return cls(magnitude, units)
def __hash__(self):
return hash(str(self))
def __eq__(self, other):
if isinstance(other, six.string_types):
return str(self) == other
if not isinstance(other, self.__class__):
return NotImplemented
return self.magnitude == other.magnitude and self.units == other.units
def __ne__(self, other):
return not self == other
def __repr__(self):
return '<{0} [{1}]>'.format(self.__class__.__name__, self)
def __str__(self):
return '{0}{1}'.format(self.magnitude, self.units)
class Size(Quantity):
"""
Represent size.
e.g.: 1.1GB, 300MB
"""
@classmethod
def parse_units(cls, value):
return value.strip(seps).upper()
class BitRate(Quantity):
"""
Represent bit rate.
e.g.: 320Kbps, 1.5Mbps
"""
@classmethod
def parse_units(cls, value):
value = value.strip(seps).capitalize()
for token in ('bits', 'bit'):
value = value.replace(token, 'bps')
return value
class FrameRate(Quantity):
"""
Represent frame rate.
e.g.: 24fps, 60fps
"""
@classmethod
def parse_units(cls, value):
return 'fps'

74
lib/guessit/rules/common/validators.py Normal file
View File

@@ -0,0 +1,74 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Validators
"""
from functools import partial
from rebulk.validators import chars_before, chars_after, chars_surround
from . import seps
seps_before = partial(chars_before, seps)
seps_after = partial(chars_after, seps)
seps_surround = partial(chars_surround, seps)
def int_coercable(string):
"""
Check if string can be coerced to int
:param string:
:type string:
:return:
:rtype:
"""
try:
int(string)
return True
except ValueError:
return False
def and_(*validators):
"""
Compose validators functions
:param validators:
:type validators:
:return:
:rtype:
"""
def composed(string):
"""
Composed validators function
:param string:
:type string:
:return:
:rtype:
"""
for validator in validators:
if not validator(string):
return False
return True
return composed
def or_(*validators):
"""
Compose validators functions
:param validators:
:type validators:
:return:
:rtype:
"""
def composed(string):
"""
Composed validators function
:param string:
:type string:
:return:
:rtype:
"""
for validator in validators:
if validator(string):
return True
return False
return composed

34
lib/guessit/rules/common/words.py Normal file
View File

@@ -0,0 +1,34 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Words utils
"""
from collections import namedtuple
from . import seps
_Word = namedtuple('_Word', ['span', 'value'])
def iter_words(string):
"""
Iterate on all words in a string
:param string:
:type string:
:return:
:rtype: iterable[str]
"""
i = 0
last_sep_index = -1
inside_word = False
for char in string:
if ord(char) < 128 and char in seps: # Make sure we don't exclude unicode characters.
if inside_word:
yield _Word(span=(last_sep_index+1, i), value=string[last_sep_index+1:i])
inside_word = False
last_sep_index = i
else:
inside_word = True
i += 1
if inside_word:
yield _Word(span=(last_sep_index+1, i), value=string[last_sep_index+1:i])

5
lib/guessit/rules/markers/__init__.py Normal file
View File

@@ -0,0 +1,5 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Markers
"""

52
lib/guessit/rules/markers/groups.py Normal file
View File

@@ -0,0 +1,52 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Groups markers (...), [...] and {...}
"""
from rebulk import Rebulk
def groups(config):
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk()
rebulk.defaults(name="group", marker=True)
starting = config['starting']
ending = config['ending']
def mark_groups(input_string):
"""
Functional pattern to mark groups (...), [...] and {...}.
:param input_string:
:return:
"""
openings = ([], [], [])
i = 0
ret = []
for char in input_string:
start_type = starting.find(char)
if start_type > -1:
openings[start_type].append(i)
i += 1
end_type = ending.find(char)
if end_type > -1:
try:
start_index = openings[end_type].pop()
ret.append((start_index, i))
except IndexError:
pass
return ret
rebulk.functional(mark_groups)
return rebulk

47
lib/guessit/rules/markers/path.py Normal file
View File

@@ -0,0 +1,47 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Path markers
"""
from rebulk import Rebulk
from rebulk.utils import find_all
def path(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk()
rebulk.defaults(name="path", marker=True)
def mark_path(input_string, context):
"""
Functional pattern to mark path elements.
:param input_string:
:param context:
:return:
"""
ret = []
if context.get('name_only', False):
ret.append((0, len(input_string)))
else:
indices = list(find_all(input_string, '/'))
indices += list(find_all(input_string, '\\'))
indices += [-1, len(input_string)]
indices.sort()
for i in range(0, len(indices) - 1):
ret.append((indices[i] + 1, indices[i + 1]))
return ret
rebulk.functional(mark_path)
return rebulk

20
lib/guessit/rules/match_processors.py Normal file
View File

@@ -0,0 +1,20 @@
"""
Match processors
"""
from guessit.rules.common import seps
def strip(match, chars=seps):
"""
Strip given characters from match.
:param chars:
:param match:
:return:
"""
while match.input_string[match.start] in chars:
match.start += 1
while match.input_string[match.end - 1] in chars:
match.end -= 1
if not match:
return False

259
lib/guessit/rules/processors.py Normal file
View File

@@ -0,0 +1,259 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Processors
"""
from collections import defaultdict
import copy
import six
from rebulk import Rebulk, Rule, CustomRule, POST_PROCESS, PRE_PROCESS, AppendMatch, RemoveMatch
from .common import seps_no_groups
from .common.formatters import cleanup
from .common.comparators import marker_sorted
from .common.date import valid_year
from .common.words import iter_words
class EnlargeGroupMatches(CustomRule):
"""
Enlarge matches that are starting and/or ending group to include brackets in their span.
"""
priority = PRE_PROCESS
def when(self, matches, context):
starting = []
ending = []
for group in matches.markers.named('group'):
for match in matches.starting(group.start + 1):
starting.append(match)
for match in matches.ending(group.end - 1):
ending.append(match)
if starting or ending:
return starting, ending
return False
def then(self, matches, when_response, context):
starting, ending = when_response
for match in starting:
matches.remove(match)
match.start -= 1
match.raw_start += 1
matches.append(match)
for match in ending:
matches.remove(match)
match.end += 1
match.raw_end -= 1
matches.append(match)
class EquivalentHoles(Rule):
"""
Creates equivalent matches for holes that have same values than existing (case insensitive)
"""
priority = POST_PROCESS
consequence = AppendMatch
def when(self, matches, context):
new_matches = []
for filepath in marker_sorted(matches.markers.named('path'), matches):
holes = matches.holes(start=filepath.start, end=filepath.end, formatter=cleanup)
for name in matches.names:
for hole in list(holes):
for current_match in matches.named(name):
if isinstance(current_match.value, six.string_types) and \
hole.value.lower() == current_match.value.lower():
if 'equivalent-ignore' in current_match.tags:
continue
new_value = _preferred_string(hole.value, current_match.value)
if hole.value != new_value:
hole.value = new_value
if current_match.value != new_value:
current_match.value = new_value
hole.name = name
hole.tags = ['equivalent']
new_matches.append(hole)
if hole in holes:
holes.remove(hole)
return new_matches
class RemoveAmbiguous(Rule):
"""
If multiple matches are found with same name and different values, keep the one in the most valuable filepart.
Also keep others match with same name and values than those kept ones.
"""
priority = POST_PROCESS
consequence = RemoveMatch
def __init__(self, sort_function=marker_sorted, predicate=None):
super(RemoveAmbiguous, self).__init__()
self.sort_function = sort_function
self.predicate = predicate
def when(self, matches, context):
fileparts = self.sort_function(matches.markers.named('path'), matches)
previous_fileparts_names = set()
values = defaultdict(list)
to_remove = []
for filepart in fileparts:
filepart_matches = matches.range(filepart.start, filepart.end, predicate=self.predicate)
filepart_names = set()
for match in filepart_matches:
filepart_names.add(match.name)
if match.name in previous_fileparts_names:
if match.value not in values[match.name]:
to_remove.append(match)
else:
if match.value not in values[match.name]:
values[match.name].append(match.value)
previous_fileparts_names.update(filepart_names)
return to_remove
class RemoveLessSpecificSeasonEpisode(RemoveAmbiguous):
"""
If multiple season/episodes matches are found with different values,
keep the one tagged as 'SxxExx' or in the rightmost filepart.
"""
def __init__(self, name):
super(RemoveLessSpecificSeasonEpisode, self).__init__(
sort_function=(lambda markers, matches:
marker_sorted(list(reversed(markers)), matches,
lambda match: match.name == name and 'SxxExx' in match.tags)),
predicate=lambda match: match.name == name)
def _preferred_string(value1, value2): # pylint:disable=too-many-return-statements
"""
Retrieves preferred title from both values.
:param value1:
:type value1: str
:param value2:
:type value2: str
:return: The preferred title
:rtype: str
"""
if value1 == value2:
return value1
if value1.istitle() and not value2.istitle():
return value1
if not value1.isupper() and value2.isupper():
return value1
if not value1.isupper() and value1[0].isupper() and not value2[0].isupper():
return value1
if _count_title_words(value1) > _count_title_words(value2):
return value1
return value2
def _count_title_words(value):
"""
Count only many words are titles in value.
:param value:
:type value:
:return:
:rtype:
"""
ret = 0
for word in iter_words(value):
if word.value.istitle():
ret += 1
return ret
class SeasonYear(Rule):
"""
If a season is a valid year and no year was found, create an match with year.
"""
priority = POST_PROCESS
consequence = AppendMatch
def when(self, matches, context):
ret = []
if not matches.named('year'):
for season in matches.named('season'):
if valid_year(season.value):
year = copy.copy(season)
year.name = 'year'
ret.append(year)
return ret
class YearSeason(Rule):
"""
If a year is found, no season found, and episode is found, create an match with season.
"""
priority = POST_PROCESS
consequence = AppendMatch
def when(self, matches, context):
ret = []
if not matches.named('season') and matches.named('episode'):
for year in matches.named('year'):
season = copy.copy(year)
season.name = 'season'
ret.append(season)
return ret
class Processors(CustomRule):
"""
Empty rule for ordering post_processing properly.
"""
priority = POST_PROCESS
def when(self, matches, context):
pass
def then(self, matches, when_response, context): # pragma: no cover
pass
class StripSeparators(CustomRule):
"""
Strip separators from matches. Keep separators if they are from acronyms, like in ".S.H.I.E.L.D."
"""
priority = POST_PROCESS
def when(self, matches, context):
return matches
def then(self, matches, when_response, context): # pragma: no cover
for match in matches:
for _ in range(0, len(match.span)):
if match.raw[0] in seps_no_groups and (len(match.raw) < 3 or match.raw[2] not in seps_no_groups):
match.raw_start += 1
for _ in reversed(range(0, len(match.span))):
if match.raw[-1] in seps_no_groups and (len(match.raw) < 3 or match.raw[-3] not in seps_no_groups):
match.raw_end -= 1
def processors(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
return Rebulk().rules(EnlargeGroupMatches, EquivalentHoles,
RemoveLessSpecificSeasonEpisode('season'),
RemoveLessSpecificSeasonEpisode('episode'),
RemoveAmbiguous, SeasonYear, YearSeason, Processors, StripSeparators)

5
lib/guessit/rules/properties/__init__.py Normal file
View File

@@ -0,0 +1,5 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Properties
"""

235
lib/guessit/rules/properties/audio_codec.py Normal file
View File

@@ -0,0 +1,235 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
audio_codec, audio_profile and audio_channels property
"""
from rebulk import Rebulk, Rule, RemoveMatch
from rebulk.remodule import re
from ..common import dash
from ..common.pattern import is_disabled
from ..common.validators import seps_before, seps_after
audio_properties = ['audio_codec', 'audio_profile', 'audio_channels']
def audio_codec(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk()\
.regex_defaults(flags=re.IGNORECASE, abbreviations=[dash])\
.string_defaults(ignore_case=True)
def audio_codec_priority(match1, match2):
"""
Gives priority to audio_codec
:param match1:
:type match1:
:param match2:
:type match2:
:return:
:rtype:
"""
if match1.name == 'audio_codec' and match2.name in ['audio_profile', 'audio_channels']:
return match2
if match1.name in ['audio_profile', 'audio_channels'] and match2.name == 'audio_codec':
return match1
return '__default__'
rebulk.defaults(name='audio_codec',
conflict_solver=audio_codec_priority,
disabled=lambda context: is_disabled(context, 'audio_codec'))
rebulk.regex("MP3", "LAME", r"LAME(?:\d)+-?(?:\d)+", value="MP3")
rebulk.string("MP2", value="MP2")
rebulk.regex('Dolby', 'DolbyDigital', 'Dolby-Digital', 'DD', 'AC3D?', value='Dolby Digital')
rebulk.regex('Dolby-?Atmos', 'Atmos', value='Dolby Atmos')
rebulk.string("AAC", value="AAC")
rebulk.string('EAC3', 'DDP', 'DD+', value='Dolby Digital Plus')
rebulk.string("Flac", value="FLAC")
rebulk.string("DTS", value="DTS")
rebulk.regex('DTS-?HD', 'DTS(?=-?MA)', value='DTS-HD',
conflict_solver=lambda match, other: other if other.name == 'audio_codec' else '__default__')
rebulk.regex('True-?HD', value='Dolby TrueHD')
rebulk.string('Opus', value='Opus')
rebulk.string('Vorbis', value='Vorbis')
rebulk.string('PCM', value='PCM')
rebulk.string('LPCM', value='LPCM')
rebulk.defaults(clear=True,
name='audio_profile',
disabled=lambda context: is_disabled(context, 'audio_profile'))
rebulk.string('MA', value='Master Audio', tags=['audio_profile.rule', 'DTS-HD'])
rebulk.string('HR', 'HRA', value='High Resolution Audio', tags=['audio_profile.rule', 'DTS-HD'])
rebulk.string('ES', value='Extended Surround', tags=['audio_profile.rule', 'DTS'])
rebulk.string('HE', value='High Efficiency', tags=['audio_profile.rule', 'AAC'])
rebulk.string('LC', value='Low Complexity', tags=['audio_profile.rule', 'AAC'])
rebulk.string('HQ', value='High Quality', tags=['audio_profile.rule', 'Dolby Digital'])
rebulk.string('EX', value='EX', tags=['audio_profile.rule', 'Dolby Digital'])
rebulk.defaults(clear=True,
name="audio_channels",
disabled=lambda context: is_disabled(context, 'audio_channels'))
rebulk.regex('7[01]', value='7.1', validator=seps_after, tags='weak-audio_channels')
rebulk.regex('5[01]', value='5.1', validator=seps_after, tags='weak-audio_channels')
rebulk.string('20', value='2.0', validator=seps_after, tags='weak-audio_channels')
for value, items in config.get('audio_channels').items():
for item in items:
if item.startswith('re:'):
rebulk.regex(item[3:], value=value, children=True)
else:
rebulk.string(item, value=value)
rebulk.rules(DtsHDRule, DtsRule, AacRule, DolbyDigitalRule, AudioValidatorRule, HqConflictRule,
AudioChannelsValidatorRule)
return rebulk
class AudioValidatorRule(Rule):
"""
Remove audio properties if not surrounded by separators and not next each others
"""
priority = 64
consequence = RemoveMatch
def when(self, matches, context):
ret = []
audio_list = matches.range(predicate=lambda match: match.name in audio_properties)
for audio in audio_list:
if not seps_before(audio):
valid_before = matches.range(audio.start - 1, audio.start,
lambda match: match.name in audio_properties)
if not valid_before:
ret.append(audio)
continue
if not seps_after(audio):
valid_after = matches.range(audio.end, audio.end + 1,
lambda match: match.name in audio_properties)
if not valid_after:
ret.append(audio)
continue
return ret
class AudioProfileRule(Rule):
"""
Abstract rule to validate audio profiles
"""
priority = 64
dependency = AudioValidatorRule
consequence = RemoveMatch
def __init__(self, codec):
super(AudioProfileRule, self).__init__()
self.codec = codec
def enabled(self, context):
return not is_disabled(context, 'audio_profile')
def when(self, matches, context):
profile_list = matches.named('audio_profile',
lambda match: 'audio_profile.rule' in match.tags and
self.codec in match.tags)
ret = []
for profile in profile_list:
codec = matches.at_span(profile.span,
lambda match: match.name == 'audio_codec' and
match.value == self.codec, 0)
if not codec:
codec = matches.previous(profile,
lambda match: match.name == 'audio_codec' and
match.value == self.codec)
if not codec:
codec = matches.next(profile,
lambda match: match.name == 'audio_codec' and
match.value == self.codec)
if not codec:
ret.append(profile)
if codec:
ret.extend(matches.conflicting(profile))
return ret
class DtsHDRule(AudioProfileRule):
"""
Rule to validate DTS-HD profile
"""
def __init__(self):
super(DtsHDRule, self).__init__('DTS-HD')
class DtsRule(AudioProfileRule):
"""
Rule to validate DTS profile
"""
def __init__(self):
super(DtsRule, self).__init__('DTS')
class AacRule(AudioProfileRule):
"""
Rule to validate AAC profile
"""
def __init__(self):
super(AacRule, self).__init__('AAC')
class DolbyDigitalRule(AudioProfileRule):
"""
Rule to validate Dolby Digital profile
"""
def __init__(self):
super(DolbyDigitalRule, self).__init__('Dolby Digital')
class HqConflictRule(Rule):
"""
Solve conflict between HQ from other property and from audio_profile.
"""
dependency = [DtsHDRule, DtsRule, AacRule, DolbyDigitalRule]
consequence = RemoveMatch
def enabled(self, context):
return not is_disabled(context, 'audio_profile')
def when(self, matches, context):
hq_audio = matches.named('audio_profile', lambda m: m.value == 'High Quality')
hq_audio_spans = [match.span for match in hq_audio]
return matches.named('other', lambda m: m.span in hq_audio_spans)
class AudioChannelsValidatorRule(Rule):
"""
Remove audio_channel if no audio codec as previous match.
"""
priority = 128
consequence = RemoveMatch
def enabled(self, context):
return not is_disabled(context, 'audio_channels')
def when(self, matches, context):
ret = []
for audio_channel in matches.tagged('weak-audio_channels'):
valid_before = matches.range(audio_channel.start - 1, audio_channel.start,
lambda match: match.name == 'audio_codec')
if not valid_before:
ret.append(audio_channel)
return ret

74
lib/guessit/rules/properties/bit_rate.py Normal file
View File

@@ -0,0 +1,74 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
video_bit_rate and audio_bit_rate properties
"""
import re
from rebulk import Rebulk
from rebulk.rules import Rule, RemoveMatch, RenameMatch
from ..common import dash, seps
from ..common.pattern import is_disabled
from ..common.quantity import BitRate
from ..common.validators import seps_surround
def bit_rate(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: (is_disabled(context, 'audio_bit_rate')
and is_disabled(context, 'video_bit_rate')))
rebulk = rebulk.regex_defaults(flags=re.IGNORECASE, abbreviations=[dash])
rebulk.defaults(name='audio_bit_rate', validator=seps_surround)
rebulk.regex(r'\d+-?[kmg]b(ps|its?)', r'\d+\.\d+-?[kmg]b(ps|its?)',
conflict_solver=(
lambda match, other: match
if other.name == 'audio_channels' and 'weak-audio_channels' not in other.tags
else other
),
formatter=BitRate.fromstring, tags=['release-group-prefix'])
rebulk.rules(BitRateTypeRule)
return rebulk
class BitRateTypeRule(Rule):
"""
Convert audio bit rate guess into video bit rate.
"""
consequence = [RenameMatch('video_bit_rate'), RemoveMatch]
def when(self, matches, context):
to_rename = []
to_remove = []
if is_disabled(context, 'audio_bit_rate'):
to_remove.extend(matches.named('audio_bit_rate'))
else:
video_bit_rate_disabled = is_disabled(context, 'video_bit_rate')
for match in matches.named('audio_bit_rate'):
previous = matches.previous(match, index=0,
predicate=lambda m: m.name in ('source', 'screen_size', 'video_codec'))
if previous and not matches.holes(previous.end, match.start, predicate=lambda m: m.value.strip(seps)):
after = matches.next(match, index=0, predicate=lambda m: m.name == 'audio_codec')
if after and not matches.holes(match.end, after.start, predicate=lambda m: m.value.strip(seps)):
bitrate = match.value
if bitrate.units == 'Kbps' or (bitrate.units == 'Mbps' and bitrate.magnitude < 10):
continue
if video_bit_rate_disabled:
to_remove.append(match)
else:
to_rename.append(match)
if to_rename or to_remove:
return to_rename, to_remove
return False

56
lib/guessit/rules/properties/bonus.py Normal file
View File

@@ -0,0 +1,56 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
bonus property
"""
from rebulk.remodule import re
from rebulk import Rebulk, AppendMatch, Rule
from .title import TitleFromPosition
from ..common.formatters import cleanup
from ..common.pattern import is_disabled
from ..common.validators import seps_surround
def bonus(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'bonus'))
rebulk = rebulk.regex_defaults(flags=re.IGNORECASE)
rebulk.regex(r'x(\d+)', name='bonus', private_parent=True, children=True, formatter=int,
validator={'__parent__': seps_surround},
validate_all=True,
conflict_solver=lambda match, conflicting: match
if conflicting.name in ('video_codec', 'episode') and 'weak-episode' not in conflicting.tags
else '__default__')
rebulk.rules(BonusTitleRule)
return rebulk
class BonusTitleRule(Rule):
"""
Find bonus title after bonus.
"""
dependency = TitleFromPosition
consequence = AppendMatch
properties = {'bonus_title': [None]}
def when(self, matches, context): # pylint:disable=inconsistent-return-statements
bonus_number = matches.named('bonus', lambda match: not match.private, index=0)
if bonus_number:
filepath = matches.markers.at_match(bonus_number, lambda marker: marker.name == 'path', 0)
hole = matches.holes(bonus_number.end, filepath.end + 1, formatter=cleanup, index=0)
if hole and hole.value:
hole.name = 'bonus_title'
return hole

41
lib/guessit/rules/properties/cds.py Normal file
View File

@@ -0,0 +1,41 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
cd and cd_count properties
"""
from rebulk.remodule import re
from rebulk import Rebulk
from ..common import dash
from ..common.pattern import is_disabled
def cds(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'cd'))
rebulk = rebulk.regex_defaults(flags=re.IGNORECASE, abbreviations=[dash])
rebulk.regex(r'cd-?(?P<cd>\d+)(?:-?of-?(?P<cd_count>\d+))?',
validator={'cd': lambda match: 0 < match.value < 100,
'cd_count': lambda match: 0 < match.value < 100},
formatter={'cd': int, 'cd_count': int},
children=True,
private_parent=True,
properties={'cd': [None], 'cd_count': [None]})
rebulk.regex(r'(?P<cd_count>\d+)-?cds?',
validator={'cd': lambda match: 0 < match.value < 100,
'cd_count': lambda match: 0 < match.value < 100},
formatter={'cd_count': int},
children=True,
private_parent=True,
properties={'cd': [None], 'cd_count': [None]})
return rebulk

61
lib/guessit/rules/properties/container.py Normal file
View File

@@ -0,0 +1,61 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
container property
"""
from rebulk.remodule import re
from rebulk import Rebulk
from ..common import seps
from ..common.pattern import is_disabled
from ..common.validators import seps_surround
from ...reutils import build_or_pattern
def container(config):
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'container'))
rebulk = rebulk.regex_defaults(flags=re.IGNORECASE).string_defaults(ignore_case=True)
rebulk.defaults(name='container',
formatter=lambda value: value.strip(seps),
tags=['extension'],
conflict_solver=lambda match, other: other
if other.name in ('source', 'video_codec') or
other.name == 'container' and 'extension' not in other.tags
else '__default__')
subtitles = config['subtitles']
info = config['info']
videos = config['videos']
torrent = config['torrent']
nzb = config['nzb']
rebulk.regex(r'\.'+build_or_pattern(subtitles)+'$', exts=subtitles, tags=['extension', 'subtitle'])
rebulk.regex(r'\.'+build_or_pattern(info)+'$', exts=info, tags=['extension', 'info'])
rebulk.regex(r'\.'+build_or_pattern(videos)+'$', exts=videos, tags=['extension', 'video'])
rebulk.regex(r'\.'+build_or_pattern(torrent)+'$', exts=torrent, tags=['extension', 'torrent'])
rebulk.regex(r'\.'+build_or_pattern(nzb)+'$', exts=nzb, tags=['extension', 'nzb'])
rebulk.defaults(clear=True,
name='container',
validator=seps_surround,
formatter=lambda s: s.lower(),
conflict_solver=lambda match, other: match
if other.name in ('source',
'video_codec') or other.name == 'container' and 'extension' in other.tags
else '__default__')
rebulk.string(*[sub for sub in subtitles if sub not in ('sub', 'ass')], tags=['subtitle'])
rebulk.string(*videos, tags=['video'])
rebulk.string(*torrent, tags=['torrent'])
rebulk.string(*nzb, tags=['nzb'])
return rebulk

114
lib/guessit/rules/properties/country.py Normal file
View File

@@ -0,0 +1,114 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
country property
"""
# pylint: disable=no-member
import babelfish
from rebulk import Rebulk
from ..common.pattern import is_disabled
from ..common.words import iter_words
def country(config, common_words):
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:param common_words: common words
:type common_words: set
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'country'))
rebulk = rebulk.defaults(name='country')
def find_countries(string, context=None):
"""
Find countries in given string.
"""
allowed_countries = context.get('allowed_countries') if context else None
return CountryFinder(allowed_countries, common_words).find(string)
rebulk.functional(find_countries,
#  Prefer language and any other property over country if not US or GB.
conflict_solver=lambda match, other: match
if other.name != 'language' or match.value not in (babelfish.Country('US'),
babelfish.Country('GB'))
else other,
properties={'country': [None]},
disabled=lambda context: not context.get('allowed_countries'))
babelfish.country_converters['guessit'] = GuessitCountryConverter(config['synonyms'])
return rebulk
class GuessitCountryConverter(babelfish.CountryReverseConverter): # pylint: disable=missing-docstring
def __init__(self, synonyms):
self.guessit_exceptions = {}
for alpha2, synlist in synonyms.items():
for syn in synlist:
self.guessit_exceptions[syn.lower()] = alpha2
@property
def codes(self): # pylint: disable=missing-docstring
return (babelfish.country_converters['name'].codes |
frozenset(babelfish.COUNTRIES.values()) |
frozenset(self.guessit_exceptions.keys()))
def convert(self, alpha2):
if alpha2 == 'GB':
return 'UK'
return str(babelfish.Country(alpha2))
def reverse(self, name): # pylint:disable=arguments-differ
# exceptions come first, as they need to override a potential match
# with any of the other guessers
try:
return self.guessit_exceptions[name.lower()]
except KeyError:
pass
try:
return babelfish.Country(name.upper()).alpha2
except ValueError:
pass
for conv in [babelfish.Country.fromname]:
try:
return conv(name).alpha2
except babelfish.CountryReverseError:
pass
raise babelfish.CountryReverseError(name)
class CountryFinder(object):
"""Helper class to search and return country matches."""
def __init__(self, allowed_countries, common_words):
self.allowed_countries = {l.lower() for l in allowed_countries or []}
self.common_words = common_words
def find(self, string):
"""Return all matches for country."""
for word_match in iter_words(string.strip().lower()):
word = word_match.value
if word.lower() in self.common_words:
continue
try:
country_object = babelfish.Country.fromguessit(word)
if (country_object.name.lower() in self.allowed_countries or
country_object.alpha2.lower() in self.allowed_countries):
yield self._to_rebulk_match(word_match, country_object)
except babelfish.Error:
continue
@classmethod
def _to_rebulk_match(cls, word, value):
return word.span[0], word.span[1], {'value': value}

90
lib/guessit/rules/properties/crc.py Normal file
View File

@@ -0,0 +1,90 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
crc and uuid properties
"""
from rebulk.remodule import re
from rebulk import Rebulk
from ..common.pattern import is_disabled
from ..common.validators import seps_surround
def crc(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'crc32'))
rebulk = rebulk.regex_defaults(flags=re.IGNORECASE)
rebulk.defaults(validator=seps_surround)
rebulk.regex('(?:[a-fA-F]|[0-9]){8}', name='crc32',
conflict_solver=lambda match, other: other
if other.name in ['episode', 'season']
else '__default__')
rebulk.functional(guess_idnumber, name='uuid',
conflict_solver=lambda match, other: match
if other.name in ['episode', 'season']
else '__default__')
return rebulk
_DIGIT = 0
_LETTER = 1
_OTHER = 2
_idnum = re.compile(r'(?P<uuid>[a-zA-Z0-9-]{20,})') # 1.0, (0, 0))
def guess_idnumber(string):
"""
Guess id number function
:param string:
:type string:
:return:
:rtype:
"""
# pylint:disable=invalid-name
ret = []
matches = list(_idnum.finditer(string))
for match in matches:
result = match.groupdict()
switch_count = 0
switch_letter_count = 0
letter_count = 0
last_letter = None
last = _LETTER
for c in result['uuid']:
if c in '0123456789':
ci = _DIGIT
elif c in 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ':
ci = _LETTER
if c != last_letter:
switch_letter_count += 1
last_letter = c
letter_count += 1
else:
ci = _OTHER
if ci != last:
switch_count += 1
last = ci
# only return the result as probable if we alternate often between
# char type (more likely for hash values than for common words)
switch_ratio = float(switch_count) / len(result['uuid'])
letters_ratio = (float(switch_letter_count) / letter_count) if letter_count > 0 else 1
if switch_ratio > 0.4 and letters_ratio > 0.4:
ret.append(match.span())
return ret

84
lib/guessit/rules/properties/date.py Normal file
View File

@@ -0,0 +1,84 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
date and year properties
"""
from rebulk import Rebulk, RemoveMatch, Rule
from ..common.date import search_date, valid_year
from ..common.pattern import is_disabled
from ..common.validators import seps_surround
def date(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().defaults(validator=seps_surround)
rebulk.regex(r"\d{4}", name="year", formatter=int,
disabled=lambda context: is_disabled(context, 'year'),
conflict_solver=lambda match, other: other
if other.name in ('episode', 'season') and len(other.raw) < len(match.raw)
else '__default__',
validator=lambda match: seps_surround(match) and valid_year(match.value))
def date_functional(string, context): # pylint:disable=inconsistent-return-statements
"""
Search for date in the string and retrieves match
:param string:
:return:
"""
ret = search_date(string, context.get('date_year_first'), context.get('date_day_first'))
if ret:
return ret[0], ret[1], {'value': ret[2]}
rebulk.functional(date_functional, name="date", properties={'date': [None]},
disabled=lambda context: is_disabled(context, 'date'),
conflict_solver=lambda match, other: other
if other.name in ('episode', 'season', 'crc32')
else '__default__')
rebulk.rules(KeepMarkedYearInFilepart)
return rebulk
class KeepMarkedYearInFilepart(Rule):
"""
Keep first years marked with [](){} in filepart, or if no year is marked, ensure it won't override titles.
"""
priority = 64
consequence = RemoveMatch
def enabled(self, context):
return not is_disabled(context, 'year')
def when(self, matches, context):
ret = []
if len(matches.named('year')) > 1:
for filepart in matches.markers.named('path'):
years = matches.range(filepart.start, filepart.end, lambda match: match.name == 'year')
if len(years) > 1:
group_years = []
ungroup_years = []
for year in years:
if matches.markers.at_match(year, lambda marker: marker.name == 'group'):
group_years.append(year)
else:
ungroup_years.append(year)
if group_years and ungroup_years:
ret.extend(ungroup_years)
ret.extend(group_years[1:]) # Keep the first year in marker.
elif not group_years:
ret.append(ungroup_years[0]) # Keep first year for title.
if len(ungroup_years) > 2:
ret.extend(ungroup_years[2:])
return ret

52
lib/guessit/rules/properties/edition.py Normal file
View File

@@ -0,0 +1,52 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
edition property
"""
from rebulk.remodule import re
from rebulk import Rebulk
from ..common import dash
from ..common.pattern import is_disabled
from ..common.validators import seps_surround
def edition(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'edition'))
rebulk = rebulk.regex_defaults(flags=re.IGNORECASE, abbreviations=[dash]).string_defaults(ignore_case=True)
rebulk.defaults(name='edition', validator=seps_surround)
rebulk.regex('collector', "collector'?s?-edition", 'edition-collector', value='Collector')
rebulk.regex('special-edition', 'edition-special', value='Special',
conflict_solver=lambda match, other: other
if other.name == 'episode_details' and other.value == 'Special'
else '__default__')
rebulk.string('se', value='Special', tags='has-neighbor')
rebulk.string('ddc', value="Director's Definitive Cut")
rebulk.regex('criterion-edition', 'edition-criterion', 'CC', value='Criterion')
rebulk.regex('deluxe', 'deluxe-edition', 'edition-deluxe', value='Deluxe')
rebulk.regex('limited', 'limited-edition', value='Limited', tags=['has-neighbor', 'release-group-prefix'])
rebulk.regex(r'theatrical-cut', r'theatrical-edition', r'theatrical', value='Theatrical')
rebulk.regex(r"director'?s?-cut", r"director'?s?-cut-edition", r"edition-director'?s?-cut", 'DC',
value="Director's Cut")
rebulk.regex('extended', 'extended-?cut', 'extended-?version',
value='Extended', tags=['has-neighbor', 'release-group-prefix'])
rebulk.regex('alternat(e|ive)(?:-?Cut)?', value='Alternative Cut', tags=['has-neighbor', 'release-group-prefix'])
for value in ('Remastered', 'Uncensored', 'Uncut', 'Unrated'):
rebulk.string(value, value=value, tags=['has-neighbor', 'release-group-prefix'])
rebulk.string('Festival', value='Festival', tags=['has-neighbor-before', 'has-neighbor-after'])
rebulk.regex('imax', 'imax-edition', value='IMAX')
rebulk.regex('fan-edit(?:ion)?', 'fan-collection', value='Fan')
rebulk.regex('ultimate-edition', value='Ultimate')
rebulk.regex("ultimate-collector'?s?-edition", value=['Ultimate', 'Collector'])
rebulk.regex('ultimate-fan-edit(?:ion)?', 'ultimate-fan-collection', value=['Ultimate', 'Fan'])
return rebulk

300
lib/guessit/rules/properties/episode_title.py Normal file
View File

@@ -0,0 +1,300 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Episode title
"""
from collections import defaultdict
from rebulk import Rebulk, Rule, AppendMatch, RemoveMatch, RenameMatch, POST_PROCESS
from ..common import seps, title_seps
from ..common.formatters import cleanup
from ..common.pattern import is_disabled
from ..common.validators import or_
from ..properties.title import TitleFromPosition, TitleBaseRule
from ..properties.type import TypeProcessor
def episode_title(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
previous_names = ('episode', 'episode_count',
'season', 'season_count', 'date', 'title', 'year')
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'episode_title'))
rebulk = rebulk.rules(RemoveConflictsWithEpisodeTitle(previous_names),
EpisodeTitleFromPosition(previous_names),
AlternativeTitleReplace(previous_names),
TitleToEpisodeTitle,
Filepart3EpisodeTitle,
Filepart2EpisodeTitle,
RenameEpisodeTitleWhenMovieType)
return rebulk
class RemoveConflictsWithEpisodeTitle(Rule):
"""
Remove conflicting matches that might lead to wrong episode_title parsing.
"""
priority = 64
consequence = RemoveMatch
def __init__(self, previous_names):
super(RemoveConflictsWithEpisodeTitle, self).__init__()
self.previous_names = previous_names
self.next_names = ('streaming_service', 'screen_size', 'source',
'video_codec', 'audio_codec', 'other', 'container')
self.affected_if_holes_after = ('part', )
self.affected_names = ('part', 'year')
def when(self, matches, context):
to_remove = []
for filepart in matches.markers.named('path'):
for match in matches.range(filepart.start, filepart.end,
predicate=lambda m: m.name in self.affected_names):
before = matches.range(filepart.start, match.start, predicate=lambda m: not m.private, index=-1)
if not before or before.name not in self.previous_names:
continue
after = matches.range(match.end, filepart.end, predicate=lambda m: not m.private, index=0)
if not after or after.name not in self.next_names:
continue
group = matches.markers.at_match(match, predicate=lambda m: m.name == 'group', index=0)
def has_value_in_same_group(current_match, current_group=group):
"""Return true if current match has value and belongs to the current group."""
return current_match.value.strip(seps) and (
current_group == matches.markers.at_match(current_match,
predicate=lambda mm: mm.name == 'group', index=0)
)
holes_before = matches.holes(before.end, match.start, predicate=has_value_in_same_group)
holes_after = matches.holes(match.end, after.start, predicate=has_value_in_same_group)
if not holes_before and not holes_after:
continue
if match.name in self.affected_if_holes_after and not holes_after:
continue
to_remove.append(match)
if match.parent:
to_remove.append(match.parent)
return to_remove
class TitleToEpisodeTitle(Rule):
"""
If multiple different title are found, convert the one following episode number to episode_title.
"""
dependency = TitleFromPosition
def when(self, matches, context):
titles = matches.named('title')
title_groups = defaultdict(list)
for title in titles:
title_groups[title.value].append(title)
episode_titles = []
if len(title_groups) < 2:
return episode_titles
for title in titles:
if matches.previous(title, lambda match: match.name == 'episode'):
episode_titles.append(title)
return episode_titles
def then(self, matches, when_response, context):
for title in when_response:
matches.remove(title)
title.name = 'episode_title'
matches.append(title)
class EpisodeTitleFromPosition(TitleBaseRule):
"""
Add episode title match in existing matches
Must run after TitleFromPosition rule.
"""
dependency = TitleToEpisodeTitle
def __init__(self, previous_names):
super(EpisodeTitleFromPosition, self).__init__('episode_title', ['title'])
self.previous_names = previous_names
def hole_filter(self, hole, matches):
episode = matches.previous(hole,
lambda previous: previous.named(*self.previous_names),
0)
crc32 = matches.named('crc32')
return episode or crc32
def filepart_filter(self, filepart, matches):
# Filepart where title was found.
if matches.range(filepart.start, filepart.end, lambda match: match.name == 'title'):
return True
return False
def should_remove(self, match, matches, filepart, hole, context):
if match.name == 'episode_details':
return False
return super(EpisodeTitleFromPosition, self).should_remove(match, matches, filepart, hole, context)
def when(self, matches, context): # pylint:disable=inconsistent-return-statements
if matches.named('episode_title'):
return
return super(EpisodeTitleFromPosition, self).when(matches, context)
class AlternativeTitleReplace(Rule):
"""
If alternateTitle was found and title is next to episode, season or date, replace it with episode_title.
"""
dependency = EpisodeTitleFromPosition
consequence = RenameMatch
def __init__(self, previous_names):
super(AlternativeTitleReplace, self).__init__()
self.previous_names = previous_names
def when(self, matches, context): # pylint:disable=inconsistent-return-statements
if matches.named('episode_title'):
return
alternative_title = matches.range(predicate=lambda match: match.name == 'alternative_title', index=0)
if alternative_title:
main_title = matches.chain_before(alternative_title.start, seps=seps,
predicate=lambda match: 'title' in match.tags, index=0)
if main_title:
episode = matches.previous(main_title,
lambda previous: previous.named(*self.previous_names),
0)
crc32 = matches.named('crc32')
if episode or crc32:
return alternative_title
def then(self, matches, when_response, context):
matches.remove(when_response)
when_response.name = 'episode_title'
when_response.tags.append('alternative-replaced')
matches.append(when_response)
class RenameEpisodeTitleWhenMovieType(Rule):
"""
Rename episode_title by alternative_title when type is movie.
"""
priority = POST_PROCESS
dependency = TypeProcessor
consequence = RenameMatch
def when(self, matches, context): # pylint:disable=inconsistent-return-statements
if matches.named('episode_title', lambda m: 'alternative-replaced' not in m.tags) \
and not matches.named('type', lambda m: m.value == 'episode'):
return matches.named('episode_title')
def then(self, matches, when_response, context):
for match in when_response:
matches.remove(match)
match.name = 'alternative_title'
matches.append(match)
class Filepart3EpisodeTitle(Rule):
"""
If we have at least 3 filepart structured like this:
Serie name/SO1/E01-episode_title.mkv
AAAAAAAAAA/BBB/CCCCCCCCCCCCCCCCCCCC
Serie name/SO1/episode_title-E01.mkv
AAAAAAAAAA/BBB/CCCCCCCCCCCCCCCCCCCC
If CCCC contains episode and BBB contains seasonNumber
Then title is to be found in AAAA.
"""
consequence = AppendMatch('title')
def when(self, matches, context): # pylint:disable=inconsistent-return-statements
if matches.tagged('filepart-title'):
return
fileparts = matches.markers.named('path')
if len(fileparts) < 3:
return
filename = fileparts[-1]
directory = fileparts[-2]
subdirectory = fileparts[-3]
episode_number = matches.range(filename.start, filename.end, lambda match: match.name == 'episode', 0)
if episode_number:
season = matches.range(directory.start, directory.end, lambda match: match.name == 'season', 0)
if season:
hole = matches.holes(subdirectory.start, subdirectory.end,
ignore=or_(lambda match: 'weak-episode' in match.tags, TitleBaseRule.is_ignored),
formatter=cleanup, seps=title_seps, predicate=lambda match: match.value,
index=0)
if hole:
return hole
class Filepart2EpisodeTitle(Rule):
"""
If we have at least 2 filepart structured like this:
Serie name SO1/E01-episode_title.mkv
AAAAAAAAAAAAA/BBBBBBBBBBBBBBBBBBBBB
If BBBB contains episode and AAA contains a hole followed by seasonNumber
then title is to be found in AAAA.
or
Serie name/SO1E01-episode_title.mkv
AAAAAAAAAA/BBBBBBBBBBBBBBBBBBBBB
If BBBB contains season and episode and AAA contains a hole
then title is to be found in AAAA.
"""
consequence = AppendMatch('title')
def when(self, matches, context): # pylint:disable=inconsistent-return-statements
if matches.tagged('filepart-title'):
return
fileparts = matches.markers.named('path')
if len(fileparts) < 2:
return
filename = fileparts[-1]
directory = fileparts[-2]
episode_number = matches.range(filename.start, filename.end, lambda match: match.name == 'episode', 0)
if episode_number:
season = (matches.range(directory.start, directory.end, lambda match: match.name == 'season', 0) or
matches.range(filename.start, filename.end, lambda match: match.name == 'season', 0))
if season:
hole = matches.holes(directory.start, directory.end,
ignore=or_(lambda match: 'weak-episode' in match.tags, TitleBaseRule.is_ignored),
formatter=cleanup, seps=title_seps,
predicate=lambda match: match.value, index=0)
if hole:
hole.tags.append('filepart-title')
return hole

912
lib/guessit/rules/properties/episodes.py Normal file
View File

@@ -0,0 +1,912 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
episode, season, disc, episode_count, season_count and episode_details properties
"""
import copy
from collections import defaultdict
from rebulk import Rebulk, RemoveMatch, Rule, AppendMatch, RenameMatch
from rebulk.match import Match
from rebulk.remodule import re
from rebulk.utils import is_iterable
from guessit.rules import match_processors
from guessit.rules.common.numeral import parse_numeral, numeral
from .title import TitleFromPosition
from ..common import dash, alt_dash, seps, seps_no_fs
from ..common.formatters import strip
from ..common.pattern import is_disabled
from ..common.validators import seps_surround, int_coercable, and_
from ...reutils import build_or_pattern
def episodes(config):
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
# pylint: disable=too-many-branches,too-many-statements,too-many-locals
def is_season_episode_disabled(context):
"""Whether season and episode rules should be enabled."""
return is_disabled(context, 'episode') or is_disabled(context, 'season')
def episodes_season_chain_breaker(matches):
"""
Break chains if there's more than 100 offset between two neighbor values.
:param matches:
:type matches:
:return:
:rtype:
"""
eps = matches.named('episode')
if len(eps) > 1 and abs(eps[-1].value - eps[-2].value) > episode_max_range:
return True
seasons = matches.named('season')
if len(seasons) > 1 and abs(seasons[-1].value - seasons[-2].value) > season_max_range:
return True
return False
def season_episode_conflict_solver(match, other):
"""
Conflict solver for episode/season patterns
:param match:
:param other:
:return:
"""
if match.name != other.name:
if match.name == 'episode' and other.name == 'year':
return match
if match.name in ('season', 'episode'):
if other.name in ('video_codec', 'audio_codec', 'container', 'date'):
return match
if (other.name == 'audio_channels' and 'weak-audio_channels' not in other.tags
and not match.initiator.children.named(match.name + 'Marker')) or (
other.name == 'screen_size' and not int_coercable(other.raw)):
return match
if other.name in ('season', 'episode') and match.initiator != other.initiator:
if (match.initiator.name in ('weak_episode', 'weak_duplicate')
and other.initiator.name in ('weak_episode', 'weak_duplicate')):
return '__default__'
for current in (match, other):
if 'weak-episode' in current.tags or 'x' in current.initiator.raw.lower():
return current
return '__default__'
def ordering_validator(match):
"""
Validator for season list. They should be in natural order to be validated.
episode/season separated by a weak discrete separator should be consecutive, unless a strong discrete separator
or a range separator is present in the chain (1.3&5 is valid, but 1.3-5 is not valid and 1.3.5 is not valid)
"""
values = match.children.to_dict()
if 'season' in values and is_iterable(values['season']):
# Season numbers must be in natural order to be validated.
if not list(sorted(values['season'])) == values['season']:
return False
if 'episode' in values and is_iterable(values['episode']):
# Season numbers must be in natural order to be validated.
if not list(sorted(values['episode'])) == values['episode']:
return False
def is_consecutive(property_name):
"""
Check if the property season or episode has valid consecutive values.
:param property_name:
:type property_name:
:return:
:rtype:
"""
previous_match = None
valid = True
for current_match in match.children.named(property_name):
if previous_match:
match.children.previous(current_match,
lambda m: m.name == property_name + 'Separator')
separator = match.children.previous(current_match,
lambda m: m.name == property_name + 'Separator', 0)
if separator:
if separator.raw not in range_separators and separator.raw in weak_discrete_separators:
if not 0 < current_match.value - previous_match.value <= max_range_gap + 1:
valid = False
if separator.raw in strong_discrete_separators:
valid = True
break
previous_match = current_match
return valid
return is_consecutive('episode') and is_consecutive('season')
def validate_roman(match):
"""
Validate a roman match if surrounded by separators
:param match:
:type match:
:return:
:rtype:
"""
if int_coercable(match.raw):
return True
return seps_surround(match)
season_words = config['season_words']
episode_words = config['episode_words']
of_words = config['of_words']
all_words = config['all_words']
season_markers = config['season_markers']
season_ep_markers = config['season_ep_markers']
disc_markers = config['disc_markers']
episode_markers = config['episode_markers']
range_separators = config['range_separators']
weak_discrete_separators = list(sep for sep in seps_no_fs if sep not in range_separators)
strong_discrete_separators = config['discrete_separators']
discrete_separators = strong_discrete_separators + weak_discrete_separators
episode_max_range = config['episode_max_range']
season_max_range = config['season_max_range']
max_range_gap = config['max_range_gap']
rebulk = Rebulk() \
.regex_defaults(flags=re.IGNORECASE) \
.string_defaults(ignore_case=True) \
.chain_defaults(chain_breaker=episodes_season_chain_breaker) \
.defaults(private_names=['episodeSeparator', 'seasonSeparator', 'episodeMarker', 'seasonMarker'],
formatter={'season': int, 'episode': int, 'version': int, 'count': int},
children=True,
private_parent=True,
conflict_solver=season_episode_conflict_solver,
abbreviations=[alt_dash])
# S01E02, 01x02, S01S02S03
rebulk.chain(
tags=['SxxExx'],
validate_all=True,
validator={'__parent__': and_(seps_surround, ordering_validator)},
disabled=is_season_episode_disabled) \
.defaults(tags=['SxxExx']) \
.regex(build_or_pattern(season_markers, name='seasonMarker') + r'(?P<season>\d+)@?' +
build_or_pattern(episode_markers + disc_markers, name='episodeMarker') + r'@?(?P<episode>\d+)')\
.repeater('+') \
.regex(build_or_pattern(episode_markers + disc_markers + discrete_separators + range_separators,
name='episodeSeparator',
escape=True) +
r'(?P<episode>\d+)').repeater('*')
rebulk.chain(tags=['SxxExx'],
validate_all=True,
validator={'__parent__': and_(seps_surround, ordering_validator)},
disabled=is_season_episode_disabled) \
.defaults(tags=['SxxExx']) \
.regex(r'(?P<season>\d+)@?' +
build_or_pattern(season_ep_markers, name='episodeMarker') +
r'@?(?P<episode>\d+)').repeater('+') \
rebulk.chain(tags=['SxxExx'],
validate_all=True,
validator={'__parent__': and_(seps_surround, ordering_validator)},
disabled=is_season_episode_disabled) \
.defaults(tags=['SxxExx']) \
.regex(r'(?P<season>\d+)@?' +
build_or_pattern(season_ep_markers, name='episodeMarker') +
r'@?(?P<episode>\d+)') \
.regex(build_or_pattern(season_ep_markers + discrete_separators + range_separators,
name='episodeSeparator',
escape=True) +
r'(?P<episode>\d+)').repeater('*')
rebulk.chain(tags=['SxxExx'],
validate_all=True,
validator={'__parent__': and_(seps_surround, ordering_validator)},
disabled=is_season_episode_disabled) \
.defaults(tags=['SxxExx']) \
.regex(build_or_pattern(season_markers, name='seasonMarker') + r'(?P<season>\d+)') \
.regex('(?P<other>Extras)', name='other', value='Extras', tags=['no-release-group-prefix']).repeater('?') \
.regex(build_or_pattern(season_markers + discrete_separators + range_separators,
name='seasonSeparator',
escape=True) +
r'(?P<season>\d+)').repeater('*')
# episode_details property
for episode_detail in ('Special', 'Pilot', 'Unaired', 'Final'):
rebulk.string(episode_detail,
private_parent=False,
children=False,
value=episode_detail,
name='episode_details',
disabled=lambda context: is_disabled(context, 'episode_details'))
rebulk.defaults(private_names=['episodeSeparator', 'seasonSeparator', 'episodeMarker', 'seasonMarker'],
validate_all=True,
validator={'__parent__': and_(seps_surround, ordering_validator)},
children=True,
private_parent=True,
conflict_solver=season_episode_conflict_solver)
rebulk.chain(validate_all=True,
conflict_solver=season_episode_conflict_solver,
formatter={'season': parse_numeral, 'count': parse_numeral},
validator={'__parent__': and_(seps_surround, ordering_validator),
'season': validate_roman,
'count': validate_roman},
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'season')) \
.defaults(formatter={'season': parse_numeral, 'count': parse_numeral},
validator={'season': validate_roman, 'count': validate_roman},
conflict_solver=season_episode_conflict_solver) \
.regex(build_or_pattern(season_words, name='seasonMarker') + '@?(?P<season>' + numeral + ')') \
.regex(r'' + build_or_pattern(of_words) + '@?(?P<count>' + numeral + ')').repeater('?') \
.regex(r'@?' + build_or_pattern(range_separators + discrete_separators + ['@'],
name='seasonSeparator', escape=True) +
r'@?(?P<season>\d+)').repeater('*')
rebulk.defaults(abbreviations=[dash])
rebulk.regex(build_or_pattern(episode_words, name='episodeMarker') + r'-?(?P<episode>\d+)' +
r'(?:v(?P<version>\d+))?' +
r'(?:-?' + build_or_pattern(of_words) + r'-?(?P<count>\d+))?', # Episode 4
disabled=lambda context: context.get('type') == 'episode' or is_disabled(context, 'episode'))
rebulk.regex(build_or_pattern(episode_words, name='episodeMarker') + r'-?(?P<episode>' + numeral + ')' +
r'(?:v(?P<version>\d+))?' +
r'(?:-?' + build_or_pattern(of_words) + r'-?(?P<count>\d+))?', # Episode 4
validator={'episode': validate_roman},
formatter={'episode': parse_numeral},
disabled=lambda context: context.get('type') != 'episode' or is_disabled(context, 'episode'))
rebulk.regex(r'S?(?P<season>\d+)-?(?:xE|Ex|E|x)-?(?P<other>' + build_or_pattern(all_words) + ')',
tags=['SxxExx'],
formatter={'other': lambda match: 'Complete'},
disabled=lambda context: is_disabled(context, 'season'))
# 12, 13
rebulk.chain(tags=['weak-episode'],
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'episode')) \
.defaults(validator=None, tags=['weak-episode']) \
.regex(r'(?P<episode>\d{2})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{2})', abbreviations=None).repeater('*')
# 012, 013
rebulk.chain(tags=['weak-episode'],
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'episode')) \
.defaults(validator=None, tags=['weak-episode']) \
.regex(r'0(?P<episode>\d{1,2})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])0(?P<episode>\d{1,2})', abbreviations=None).repeater('*')
# 112, 113
rebulk.chain(tags=['weak-episode'],
name='weak_episode',
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'episode')) \
.defaults(validator=None, tags=['weak-episode'], name='weak_episode') \
.regex(r'(?P<episode>\d{3,4})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{3,4})', abbreviations=None).repeater('*')
# 1, 2, 3
rebulk.chain(tags=['weak-episode'],
disabled=lambda context: context.get('type') != 'episode' or is_disabled(context, 'episode')) \
.defaults(validator=None, tags=['weak-episode']) \
.regex(r'(?P<episode>\d)') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{1,2})', abbreviations=None).repeater('*')
# e112, e113, 1e18, 3e19
rebulk.chain(disabled=lambda context: is_disabled(context, 'episode')) \
.defaults(validator=None) \
.regex(r'(?P<season>\d{1,2})?(?P<episodeMarker>e)(?P<episode>\d{1,4})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>e|x|-)(?P<episode>\d{1,4})', abbreviations=None).repeater('*')
# ep 112, ep113, ep112, ep113
rebulk.chain(disabled=lambda context: is_disabled(context, 'episode')) \
.defaults(validator=None) \
.regex(r'ep-?(?P<episode>\d{1,4})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>ep|e|x|-)(?P<episode>\d{1,4})', abbreviations=None).repeater('*')
# cap 112, cap 112_114
rebulk.chain(tags=['see-pattern'],
disabled=is_season_episode_disabled) \
.defaults(validator=None, tags=['see-pattern']) \
.regex(r'(?P<seasonMarker>cap)-?(?P<season>\d{1,2})(?P<episode>\d{2})') \
.regex(r'(?P<episodeSeparator>-)(?P<season>\d{1,2})(?P<episode>\d{2})').repeater('?')
# 102, 0102
rebulk.chain(tags=['weak-episode', 'weak-duplicate'],
name='weak_duplicate',
conflict_solver=season_episode_conflict_solver,
disabled=lambda context: (context.get('episode_prefer_number', False) or
context.get('type') == 'movie') or is_season_episode_disabled(context)) \
.defaults(tags=['weak-episode', 'weak-duplicate'],
name='weak_duplicate',
validator=None,
conflict_solver=season_episode_conflict_solver) \
.regex(r'(?P<season>\d{1,2})(?P<episode>\d{2})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>x|-)(?P<episode>\d{2})', abbreviations=None).repeater('*')
rebulk.regex(r'v(?P<version>\d+)',
formatter=int,
disabled=lambda context: is_disabled(context, 'version'))
rebulk.defaults(private_names=['episodeSeparator', 'seasonSeparator'])
# TODO: List of words
# detached of X count (season/episode)
rebulk.regex(r'(?P<episode>\d+)-?' + build_or_pattern(of_words) +
r'-?(?P<count>\d+)-?' + build_or_pattern(episode_words) + '?',
formatter=int,
pre_match_processor=match_processors.strip,
disabled=lambda context: is_disabled(context, 'episode'))
rebulk.regex(r'Minisodes?',
children=False,
private_parent=False,
name='episode_format',
value="Minisode",
disabled=lambda context: is_disabled(context, 'episode_format'))
rebulk.rules(WeakConflictSolver, RemoveInvalidSeason, RemoveInvalidEpisode,
SeePatternRange(range_separators + ['_']),
EpisodeNumberSeparatorRange(range_separators),
SeasonSeparatorRange(range_separators), RemoveWeakIfMovie, RemoveWeakIfSxxExx, RemoveWeakDuplicate,
EpisodeDetailValidator, RemoveDetachedEpisodeNumber, VersionValidator, RemoveWeak(episode_words),
RenameToAbsoluteEpisode, CountValidator, EpisodeSingleDigitValidator, RenameToDiscMatch)
return rebulk
class WeakConflictSolver(Rule):
"""
Rule to decide whether weak-episode or weak-duplicate matches should be kept.
If an anime is detected:
- weak-duplicate matches should be removed
- weak-episode matches should be tagged as anime
Otherwise:
- weak-episode matches are removed unless they're part of an episode range match.
"""
priority = 128
consequence = [RemoveMatch, AppendMatch]
def enabled(self, context):
return context.get('type') != 'movie'
@classmethod
def is_anime(cls, matches):
"""Return True if it seems to be an anime.
Anime characteristics:
- version, crc32 matches
- screen_size inside brackets
- release_group at start and inside brackets
"""
if matches.named('version') or matches.named('crc32'):
return True
for group in matches.markers.named('group'):
if matches.range(group.start, group.end, predicate=lambda m: m.name == 'screen_size'):
return True
if matches.markers.starting(group.start, predicate=lambda m: m.name == 'path'):
hole = matches.holes(group.start, group.end, index=0)
if hole and hole.raw == group.raw:
return True
return False
def when(self, matches, context):
to_remove = []
to_append = []
anime_detected = self.is_anime(matches)
for filepart in matches.markers.named('path'):
weak_matches = matches.range(filepart.start, filepart.end, predicate=(
lambda m: m.initiator.name == 'weak_episode'))
weak_dup_matches = matches.range(filepart.start, filepart.end, predicate=(
lambda m: m.initiator.name == 'weak_duplicate'))
if anime_detected:
if weak_matches:
to_remove.extend(weak_dup_matches)
for match in matches.range(filepart.start, filepart.end, predicate=(
lambda m: m.name == 'episode' and m.initiator.name != 'weak_duplicate')):
episode = copy.copy(match)
episode.tags = episode.tags + ['anime']
to_append.append(episode)
to_remove.append(match)
elif weak_dup_matches:
episodes_in_range = matches.range(filepart.start, filepart.end, predicate=(
lambda m:
m.name == 'episode' and m.initiator.name == 'weak_episode'
and m.initiator.children.named('episodeSeparator')
))
if not episodes_in_range and not matches.range(filepart.start, filepart.end,
predicate=lambda m: 'SxxExx' in m.tags):
to_remove.extend(weak_matches)
else:
for match in episodes_in_range:
episode = copy.copy(match)
episode.tags = []
to_append.append(episode)
to_remove.append(match)
if to_append:
to_remove.extend(weak_dup_matches)
if to_remove or to_append:
return to_remove, to_append
return False
class CountValidator(Rule):
"""
Validate count property and rename it
"""
priority = 64
consequence = [RemoveMatch, RenameMatch('episode_count'), RenameMatch('season_count')]
properties = {'episode_count': [None], 'season_count': [None]}
def when(self, matches, context):
to_remove = []
episode_count = []
season_count = []
for count in matches.named('count'):
previous = matches.previous(count, lambda match: match.name in ['episode', 'season'], 0)
if previous:
if previous.name == 'episode':
episode_count.append(count)
elif previous.name == 'season':
season_count.append(count)
else:
to_remove.append(count)
if to_remove or episode_count or season_count:
return to_remove, episode_count, season_count
return False
class SeePatternRange(Rule):
"""
Create matches for episode range for SEE pattern. E.g.: Cap.102_104
"""
priority = 128
consequence = [RemoveMatch, AppendMatch]
def __init__(self, range_separators):
super(SeePatternRange, self).__init__()
self.range_separators = range_separators
def when(self, matches, context):
to_remove = []
to_append = []
for separator in matches.tagged('see-pattern', lambda m: m.name == 'episodeSeparator'):
previous_match = matches.previous(separator, lambda m: m.name == 'episode' and 'see-pattern' in m.tags, 0)
next_match = matches.next(separator, lambda m: m.name == 'season' and 'see-pattern' in m.tags, 0)
if not next_match:
continue
next_match = matches.next(next_match, lambda m: m.name == 'episode' and 'see-pattern' in m.tags, 0)
if previous_match and next_match and separator.value in self.range_separators:
to_remove.append(next_match)
for episode_number in range(previous_match.value + 1, next_match.value + 1):
match = copy.copy(next_match)
match.value = episode_number
to_append.append(match)
to_remove.append(separator)
if to_remove or to_append:
return to_remove, to_append
return False
class AbstractSeparatorRange(Rule):
"""
Remove separator matches and create matches for season range.
"""
priority = 128
consequence = [RemoveMatch, AppendMatch]
def __init__(self, range_separators, property_name):
super(AbstractSeparatorRange, self).__init__()
self.range_separators = range_separators
self.property_name = property_name
def when(self, matches, context):
to_remove = []
to_append = []
for separator in matches.named(self.property_name + 'Separator'):
previous_match = matches.previous(separator, lambda m: m.name == self.property_name, 0)
next_match = matches.next(separator, lambda m: m.name == self.property_name, 0)
initiator = separator.initiator
if previous_match and next_match and separator.value in self.range_separators:
to_remove.append(next_match)
for episode_number in range(previous_match.value + 1, next_match.value):
match = copy.copy(next_match)
match.value = episode_number
initiator.children.append(match)
to_append.append(match)
to_append.append(next_match)
to_remove.append(separator)
previous_match = None
for next_match in matches.named(self.property_name):
if previous_match:
separator = matches.input_string[previous_match.initiator.end:next_match.initiator.start]
if separator not in self.range_separators:
separator = strip(separator)
if separator in self.range_separators:
initiator = previous_match.initiator
for episode_number in range(previous_match.value + 1, next_match.value):
match = copy.copy(next_match)
match.value = episode_number
initiator.children.append(match)
to_append.append(match)
to_append.append(Match(previous_match.end, next_match.start - 1,
name=self.property_name + 'Separator',
private=True,
input_string=matches.input_string))
to_remove.append(next_match) # Remove and append match to support proper ordering
to_append.append(next_match)
previous_match = next_match
if to_remove or to_append:
return to_remove, to_append
return False
class RenameToAbsoluteEpisode(Rule):
"""
Rename episode to absolute_episodes.
Absolute episodes are only used if two groups of episodes are detected:
S02E04-06 25-27
25-27 S02E04-06
2x04-06 25-27
28. Anime Name S02E05
The matches in the group with higher episode values are renamed to absolute_episode.
"""
consequence = RenameMatch('absolute_episode')
def when(self, matches, context): # pylint:disable=inconsistent-return-statements
initiators = {match.initiator for match in matches.named('episode')
if len(match.initiator.children.named('episode')) > 1}
if len(initiators) != 2:
ret = []
for filepart in matches.markers.named('path'):
if matches.range(filepart.start + 1, filepart.end, predicate=lambda m: m.name == 'episode'):
ret.extend(
matches.starting(filepart.start, predicate=lambda m: m.initiator.name == 'weak_episode'))
return ret
initiators = sorted(initiators, key=lambda item: item.end)
if not matches.holes(initiators[0].end, initiators[1].start, predicate=lambda m: m.raw.strip(seps)):
first_range = matches.named('episode', predicate=lambda m: m.initiator == initiators[0])
second_range = matches.named('episode', predicate=lambda m: m.initiator == initiators[1])
if len(first_range) == len(second_range):
if second_range[0].value > first_range[0].value:
return second_range
if first_range[0].value > second_range[0].value:
return first_range
class EpisodeNumberSeparatorRange(AbstractSeparatorRange):
"""
Remove separator matches and create matches for episoderNumber range.
"""
def __init__(self, range_separators):
super(EpisodeNumberSeparatorRange, self).__init__(range_separators, "episode")
class SeasonSeparatorRange(AbstractSeparatorRange):
"""
Remove separator matches and create matches for season range.
"""
def __init__(self, range_separators):
super(SeasonSeparatorRange, self).__init__(range_separators, "season")
class RemoveWeakIfMovie(Rule):
"""
Remove weak-episode tagged matches if it seems to be a movie.
"""
priority = 64
consequence = RemoveMatch
def enabled(self, context):
return context.get('type') != 'episode'
def when(self, matches, context):
to_remove = []
to_ignore = set()
remove = False
for filepart in matches.markers.named('path'):
year = matches.range(filepart.start, filepart.end, predicate=lambda m: m.name == 'year', index=0)
if year:
remove = True
next_match = matches.range(year.end, filepart.end, predicate=lambda m: m.private, index=0)
if (next_match and not matches.holes(year.end, next_match.start, predicate=lambda m: m.raw.strip(seps))
and not matches.at_match(next_match, predicate=lambda m: m.name == 'year')):
to_ignore.add(next_match.initiator)
to_ignore.update(matches.range(filepart.start, filepart.end,
predicate=lambda m: len(m.children.named('episode')) > 1))
to_remove.extend(matches.conflicting(year))
if remove:
to_remove.extend(matches.tagged('weak-episode', predicate=(
lambda m: m.initiator not in to_ignore and 'anime' not in m.tags)))
return to_remove
class RemoveWeak(Rule):
"""
Remove weak-episode matches which appears after video, source, and audio matches.
"""
priority = 16
consequence = RemoveMatch, AppendMatch
def __init__(self, episode_words):
super(RemoveWeak, self).__init__()
self.episode_words = episode_words
def when(self, matches, context):
to_remove = []
to_append = []
for filepart in matches.markers.named('path'):
weaks = matches.range(filepart.start, filepart.end, predicate=lambda m: 'weak-episode' in m.tags)
if weaks:
weak = weaks[0]
previous = matches.previous(weak, predicate=lambda m: m.name in (
'audio_codec', 'screen_size', 'streaming_service', 'source', 'video_profile',
'audio_channels', 'audio_profile'), index=0)
if previous and not matches.holes(
previous.end, weak.start, predicate=lambda m: m.raw.strip(seps)):
if previous.raw.lower() in self.episode_words:
try:
episode = copy.copy(weak)
episode.name = 'episode'
episode.value = int(weak.value)
episode.start = previous.start
episode.private = False
episode.tags = []
to_append.append(episode)
except ValueError:
pass
to_remove.extend(weaks)
if to_remove or to_append:
return to_remove, to_append
return False
class RemoveWeakIfSxxExx(Rule):
"""
Remove weak-episode tagged matches if SxxExx pattern is matched.
Weak episodes at beginning of filepart are kept.
"""
priority = 64
consequence = RemoveMatch
def when(self, matches, context):
to_remove = []
for filepart in matches.markers.named('path'):
if matches.range(filepart.start, filepart.end,
predicate=lambda m: not m.private and 'SxxExx' in m.tags):
for match in matches.range(filepart.start, filepart.end, predicate=lambda m: 'weak-episode' in m.tags):
if match.start != filepart.start or match.initiator.name != 'weak_episode':
to_remove.append(match)
return to_remove
class RemoveInvalidSeason(Rule):
"""
Remove invalid season matches.
"""
priority = 64
consequence = RemoveMatch
def when(self, matches, context):
to_remove = []
for filepart in matches.markers.named('path'):
strong_season = matches.range(filepart.start, filepart.end, index=0,
predicate=lambda m: m.name == 'season'
and not m.private and 'SxxExx' in m.tags)
if strong_season:
if strong_season.initiator.children.named('episode'):
for season in matches.range(strong_season.end, filepart.end,
predicate=lambda m: m.name == 'season' and not m.private):
# remove weak season or seasons without episode matches
if 'SxxExx' not in season.tags or not season.initiator.children.named('episode'):
if season.initiator:
to_remove.append(season.initiator)
to_remove.extend(season.initiator.children)
else:
to_remove.append(season)
return to_remove
class RemoveInvalidEpisode(Rule):
"""
Remove invalid episode matches.
"""
priority = 64
consequence = RemoveMatch
def when(self, matches, context):
to_remove = []
for filepart in matches.markers.named('path'):
strong_episode = matches.range(filepart.start, filepart.end, index=0,
predicate=lambda m: m.name == 'episode'
and not m.private and 'SxxExx' in m.tags)
if strong_episode:
strong_ep_marker = RemoveInvalidEpisode.get_episode_prefix(matches, strong_episode)
for episode in matches.range(strong_episode.end, filepart.end,
predicate=lambda m: m.name == 'episode' and not m.private):
ep_marker = RemoveInvalidEpisode.get_episode_prefix(matches, episode)
if strong_ep_marker and ep_marker and strong_ep_marker.value.lower() != ep_marker.value.lower():
if episode.initiator:
to_remove.append(episode.initiator)
to_remove.extend(episode.initiator.children)
else:
to_remove.append(ep_marker)
to_remove.append(episode)
return to_remove
@staticmethod
def get_episode_prefix(matches, episode):
"""
Return episode prefix: episodeMarker or episodeSeparator
"""
return matches.previous(episode, index=0,
predicate=lambda m: m.name in ('episodeMarker', 'episodeSeparator'))
class RemoveWeakDuplicate(Rule):
"""
Remove weak-duplicate tagged matches if duplicate patterns, for example The 100.109
"""
priority = 64
consequence = RemoveMatch
def when(self, matches, context):
to_remove = []
for filepart in matches.markers.named('path'):
patterns = defaultdict(list)
for match in reversed(matches.range(filepart.start, filepart.end,
predicate=lambda m: 'weak-duplicate' in m.tags)):
if match.pattern in patterns[match.name]:
to_remove.append(match)
else:
patterns[match.name].append(match.pattern)
return to_remove
class EpisodeDetailValidator(Rule):
"""
Validate episode_details if they are detached or next to season or episode.
"""
priority = 64
consequence = RemoveMatch
def when(self, matches, context):
ret = []
for detail in matches.named('episode_details'):
if not seps_surround(detail) \
and not matches.previous(detail, lambda match: match.name in ['season', 'episode']) \
and not matches.next(detail, lambda match: match.name in ['season', 'episode']):
ret.append(detail)
return ret
class RemoveDetachedEpisodeNumber(Rule):
"""
If multiple episode are found, remove those that are not detached from a range and less than 10.
Fairy Tail 2 - 16-20, 2 should be removed.
"""
priority = 64
consequence = RemoveMatch
dependency = [RemoveWeakIfSxxExx, RemoveWeakDuplicate]
def when(self, matches, context):
ret = []
episode_numbers = []
episode_values = set()
for match in matches.named('episode', lambda m: not m.private and 'weak-episode' in m.tags):
if match.value not in episode_values:
episode_numbers.append(match)
episode_values.add(match.value)
episode_numbers = list(sorted(episode_numbers, key=lambda m: m.value))
if len(episode_numbers) > 1 and \
episode_numbers[0].value < 10 and \
episode_numbers[1].value - episode_numbers[0].value != 1:
parent = episode_numbers[0]
while parent: # TODO: Add a feature in rebulk to avoid this ...
ret.append(parent)
parent = parent.parent
return ret
class VersionValidator(Rule):
"""
Validate version if previous match is episode or if surrounded by separators.
"""
priority = 64
dependency = [RemoveWeakIfMovie, RemoveWeakIfSxxExx]
consequence = RemoveMatch
def when(self, matches, context):
ret = []
for version in matches.named('version'):
episode_number = matches.previous(version, lambda match: match.name == 'episode', 0)
if not episode_number and not seps_surround(version.initiator):
ret.append(version)
return ret
class EpisodeSingleDigitValidator(Rule):
"""
Remove single digit episode when inside a group that doesn't own title.
"""
dependency = [TitleFromPosition]
consequence = RemoveMatch
def when(self, matches, context):
ret = []
for episode in matches.named('episode', lambda match: len(match.initiator) == 1):
group = matches.markers.at_match(episode, lambda marker: marker.name == 'group', index=0)
if group:
if not matches.range(*group.span, predicate=lambda match: match.name == 'title'):
ret.append(episode)
return ret
class RenameToDiscMatch(Rule):
"""
Rename episodes detected with `d` episodeMarkers to `disc`.
"""
consequence = [RenameMatch('disc'), RenameMatch('discMarker'), RemoveMatch]
def when(self, matches, context):
discs = []
markers = []
to_remove = []
disc_disabled = is_disabled(context, 'disc')
for marker in matches.named('episodeMarker', predicate=lambda m: m.value.lower() == 'd'):
if disc_disabled:
to_remove.append(marker)
to_remove.extend(marker.initiator.children)
continue
markers.append(marker)
discs.extend(sorted(marker.initiator.children.named('episode'), key=lambda m: m.value))
if discs or markers or to_remove:
return discs, markers, to_remove
return False

48
lib/guessit/rules/properties/film.py Normal file
View File

@@ -0,0 +1,48 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
film property
"""
from rebulk import Rebulk, AppendMatch, Rule
from rebulk.remodule import re
from ..common.formatters import cleanup
from ..common.pattern import is_disabled
from ..common.validators import seps_surround
def film(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE, validate_all=True, validator={'__parent__': seps_surround})
rebulk.regex(r'f(\d{1,2})', name='film', private_parent=True, children=True, formatter=int,
disabled=lambda context: is_disabled(context, 'film'))
rebulk.rules(FilmTitleRule)
return rebulk
class FilmTitleRule(Rule):
"""
Rule to find out film_title (hole after film property
"""
consequence = AppendMatch
properties = {'film_title': [None]}
def enabled(self, context):
return not is_disabled(context, 'film_title')
def when(self, matches, context): # pylint:disable=inconsistent-return-statements
bonus_number = matches.named('film', lambda match: not match.private, index=0)
if bonus_number:
filepath = matches.markers.at_match(bonus_number, lambda marker: marker.name == 'path', 0)
hole = matches.holes(filepath.start, bonus_number.start + 1, formatter=cleanup, index=0)
if hole and hole.value:
hole.name = 'film_title'
return hole

510
lib/guessit/rules/properties/language.py Normal file
View File

@@ -0,0 +1,510 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
language and subtitle_language properties
"""
# pylint: disable=no-member
import copy
from collections import defaultdict, namedtuple
import babelfish
from rebulk import Rebulk, Rule, RemoveMatch, RenameMatch
from rebulk.remodule import re
from ..common import seps
from ..common.pattern import is_disabled
from ..common.words import iter_words
from ..common.validators import seps_surround
def language(config, common_words):
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:param common_words: common words
:type common_words: set
:return: Created Rebulk object
:rtype: Rebulk
"""
subtitle_both = config['subtitle_affixes']
subtitle_prefixes = sorted(subtitle_both + config['subtitle_prefixes'], key=length_comparator)
subtitle_suffixes = sorted(subtitle_both + config['subtitle_suffixes'], key=length_comparator)
lang_both = config['language_affixes']
lang_prefixes = sorted(lang_both + config['language_prefixes'], key=length_comparator)
lang_suffixes = sorted(lang_both + config['language_suffixes'], key=length_comparator)
weak_affixes = frozenset(config['weak_affixes'])
rebulk = Rebulk(disabled=lambda context: (is_disabled(context, 'language') and
is_disabled(context, 'subtitle_language')))
rebulk.string(*subtitle_prefixes, name="subtitle_language.prefix", ignore_case=True, private=True,
validator=seps_surround, tags=['release-group-prefix'],
disabled=lambda context: is_disabled(context, 'subtitle_language'))
rebulk.string(*subtitle_suffixes, name="subtitle_language.suffix", ignore_case=True, private=True,
validator=seps_surround,
disabled=lambda context: is_disabled(context, 'subtitle_language'))
rebulk.string(*lang_suffixes, name="language.suffix", ignore_case=True, private=True,
validator=seps_surround, tags=['source-suffix'],
disabled=lambda context: is_disabled(context, 'language'))
def find_languages(string, context=None):
"""Find languages in the string
:return: list of tuple (property, Language, lang_word, word)
"""
return LanguageFinder(context, subtitle_prefixes, subtitle_suffixes,
lang_prefixes, lang_suffixes, weak_affixes).find(string)
rebulk.functional(find_languages,
properties={'language': [None]},
disabled=lambda context: not context.get('allowed_languages'))
rebulk.rules(SubtitleExtensionRule,
SubtitlePrefixLanguageRule,
SubtitleSuffixLanguageRule,
RemoveLanguage,
RemoveInvalidLanguages(common_words))
babelfish.language_converters['guessit'] = GuessitConverter(config['synonyms'])
return rebulk
UNDETERMINED = babelfish.Language('und')
MULTIPLE = babelfish.Language('mul')
NON_SPECIFIC_LANGUAGES = frozenset([UNDETERMINED, MULTIPLE])
class GuessitConverter(babelfish.LanguageReverseConverter): # pylint: disable=missing-docstring
_with_country_regexp = re.compile(r'(.*)\((.*)\)')
_with_country_regexp2 = re.compile(r'(.*)-(.*)')
def __init__(self, synonyms):
self.guessit_exceptions = {}
for code, synlist in synonyms.items():
if '_' in code:
(alpha3, country) = code.split('_')
else:
(alpha3, country) = (code, None)
for syn in synlist:
self.guessit_exceptions[syn.lower()] = (alpha3, country, None)
@property
def codes(self): # pylint: disable=missing-docstring
return (babelfish.language_converters['alpha3b'].codes |
babelfish.language_converters['alpha2'].codes |
babelfish.language_converters['name'].codes |
babelfish.language_converters['opensubtitles'].codes |
babelfish.country_converters['name'].codes |
frozenset(self.guessit_exceptions.keys()))
def convert(self, alpha3, country=None, script=None):
return str(babelfish.Language(alpha3, country, script))
def reverse(self, name): # pylint:disable=arguments-differ
name = name.lower()
# exceptions come first, as they need to override a potential match
# with any of the other guessers
try:
return self.guessit_exceptions[name]
except KeyError:
pass
for conv in [babelfish.Language,
babelfish.Language.fromalpha3b,
babelfish.Language.fromalpha2,
babelfish.Language.fromname,
babelfish.Language.fromopensubtitles,
babelfish.Language.fromietf]:
try:
reverse = conv(name)
return reverse.alpha3, reverse.country, reverse.script
except (ValueError, babelfish.LanguageReverseError):
pass
raise babelfish.LanguageReverseError(name)
def length_comparator(value):
"""
Return value length.
"""
return len(value)
_LanguageMatch = namedtuple('_LanguageMatch', ['property_name', 'word', 'lang'])
class LanguageWord(object):
"""
Extension to the Word namedtuple in order to create compound words.
E.g.: pt-BR, soft subtitles, custom subs
"""
def __init__(self, start, end, value, input_string, next_word=None):
self.start = start
self.end = end
self.value = value
self.input_string = input_string
self.next_word = next_word
@property
def extended_word(self): # pylint:disable=inconsistent-return-statements
"""
Return the extended word for this instance, if any.
"""
if self.next_word:
separator = self.input_string[self.end:self.next_word.start]
next_separator = self.input_string[self.next_word.end:self.next_word.end + 1]
if (separator == '-' and separator != next_separator) or separator in (' ', '.'):
value = self.input_string[self.start:self.next_word.end].replace('.', ' ')
return LanguageWord(self.start, self.next_word.end, value, self.input_string, self.next_word.next_word)
def __repr__(self):
return '<({start},{end}): {value}'.format(start=self.start, end=self.end, value=self.value)
def to_rebulk_match(language_match):
"""
Convert language match to rebulk Match: start, end, dict
"""
word = language_match.word
start = word.start
end = word.end
name = language_match.property_name
if language_match.lang == UNDETERMINED:
return start, end, {
'name': name,
'value': word.value.lower(),
'formatter': babelfish.Language,
'tags': ['weak-language']
}
return start, end, {
'name': name,
'value': language_match.lang
}
class LanguageFinder(object):
"""
Helper class to search and return language matches: 'language' and 'subtitle_language' properties
"""
def __init__(self, context,
subtitle_prefixes, subtitle_suffixes,
lang_prefixes, lang_suffixes, weak_affixes):
allowed_languages = context.get('allowed_languages') if context else None
self.allowed_languages = {l.lower() for l in allowed_languages or []}
self.weak_affixes = weak_affixes
self.prefixes_map = {}
self.suffixes_map = {}
if not is_disabled(context, 'subtitle_language'):
self.prefixes_map['subtitle_language'] = subtitle_prefixes
self.suffixes_map['subtitle_language'] = subtitle_suffixes
self.prefixes_map['language'] = lang_prefixes
self.suffixes_map['language'] = lang_suffixes
def find(self, string):
"""
Return all matches for language and subtitle_language.
Undetermined language matches are removed if a regular language is found.
Multi language matches are removed if there are only undetermined language matches
"""
regular_lang_map = defaultdict(set)
undetermined_map = defaultdict(set)
multi_map = defaultdict(set)
for match in self.iter_language_matches(string):
key = match.property_name
if match.lang == UNDETERMINED:
undetermined_map[key].add(match)
elif match.lang == 'mul':
multi_map[key].add(match)
else:
regular_lang_map[key].add(match)
for key, values in multi_map.items():
if key in regular_lang_map or key not in undetermined_map:
for value in values:
yield to_rebulk_match(value)
for key, values in undetermined_map.items():
if key not in regular_lang_map:
for value in values:
yield to_rebulk_match(value)
for values in regular_lang_map.values():
for value in values:
yield to_rebulk_match(value)
def iter_language_matches(self, string):
"""
Return language matches for the given string.
"""
candidates = []
previous = None
for word in iter_words(string):
language_word = LanguageWord(start=word.span[0], end=word.span[1], value=word.value, input_string=string)
if previous:
previous.next_word = language_word
candidates.append(previous)
previous = language_word
if previous:
candidates.append(previous)
for candidate in candidates:
for match in self.iter_matches_for_candidate(candidate):
yield match
def iter_matches_for_candidate(self, language_word):
"""
Return language matches for the given candidate word.
"""
tuples = [
(language_word, language_word.next_word,
self.prefixes_map,
lambda string, prefix: string.startswith(prefix),
lambda string, prefix: string[len(prefix):]),
(language_word.next_word, language_word,
self.suffixes_map,
lambda string, suffix: string.endswith(suffix),
lambda string, suffix: string[:len(string) - len(suffix)])
]
for word, fallback_word, affixes, is_affix, strip_affix in tuples:
if not word:
continue
match = self.find_match_for_word(word, fallback_word, affixes, is_affix, strip_affix)
if match:
yield match
match = self.find_language_match_for_word(language_word)
if match:
yield match
def find_match_for_word(self, word, fallback_word, affixes, is_affix, strip_affix): # pylint:disable=inconsistent-return-statements
"""
Return the language match for the given word and affixes.
"""
for current_word in (word.extended_word, word):
if not current_word:
continue
word_lang = current_word.value.lower()
for key, parts in affixes.items():
for part in parts:
if not is_affix(word_lang, part):
continue
match = None
value = strip_affix(word_lang, part)
if not value:
if fallback_word and (
abs(fallback_word.start - word.end) <= 1 or abs(word.start - fallback_word.end) <= 1):
match = self.find_language_match_for_word(fallback_word, key=key)
if not match and part not in self.weak_affixes:
match = self.create_language_match(key, LanguageWord(current_word.start, current_word.end,
'und', current_word.input_string))
else:
match = self.create_language_match(key, LanguageWord(current_word.start, current_word.end,
value, current_word.input_string))
if match:
return match
def find_language_match_for_word(self, word, key='language'): # pylint:disable=inconsistent-return-statements
"""
Return the language match for the given word.
"""
for current_word in (word.extended_word, word):
if current_word:
match = self.create_language_match(key, current_word)
if match:
return match
def create_language_match(self, key, word): # pylint:disable=inconsistent-return-statements
"""
Create a LanguageMatch for a given word
"""
lang = self.parse_language(word.value.lower())
if lang is not None:
return _LanguageMatch(property_name=key, word=word, lang=lang)
def parse_language(self, lang_word): # pylint:disable=inconsistent-return-statements
"""
Parse the lang_word into a valid Language.
Multi and Undetermined languages are also valid languages.
"""
try:
lang = babelfish.Language.fromguessit(lang_word)
if ((hasattr(lang, 'name') and lang.name.lower() in self.allowed_languages) or
(hasattr(lang, 'alpha2') and lang.alpha2.lower() in self.allowed_languages) or
lang.alpha3.lower() in self.allowed_languages):
return lang
except babelfish.Error:
pass
class SubtitlePrefixLanguageRule(Rule):
"""
Convert language guess as subtitle_language if previous match is a subtitle language prefix
"""
consequence = RemoveMatch
properties = {'subtitle_language': [None]}
def enabled(self, context):
return not is_disabled(context, 'subtitle_language')
def when(self, matches, context):
to_rename = []
to_remove = matches.named('subtitle_language.prefix')
for lang in matches.named('language'):
prefix = matches.previous(lang, lambda match: match.name == 'subtitle_language.prefix', 0)
if not prefix:
group_marker = matches.markers.at_match(lang, lambda marker: marker.name == 'group', 0)
if group_marker:
# Find prefix if placed just before the group
prefix = matches.previous(group_marker, lambda match: match.name == 'subtitle_language.prefix',
0)
if not prefix:
# Find prefix if placed before in the group
prefix = matches.range(group_marker.start, lang.start,
lambda match: match.name == 'subtitle_language.prefix', 0)
if prefix:
to_rename.append((prefix, lang))
to_remove.extend(matches.conflicting(lang))
if prefix in to_remove:
to_remove.remove(prefix)
if to_rename or to_remove:
return to_rename, to_remove
return False
def then(self, matches, when_response, context):
to_rename, to_remove = when_response
super(SubtitlePrefixLanguageRule, self).then(matches, to_remove, context)
for prefix, match in to_rename:
# Remove suffix equivalent of prefix.
suffix = copy.copy(prefix)
suffix.name = 'subtitle_language.suffix'
if suffix in matches:
matches.remove(suffix)
matches.remove(match)
match.name = 'subtitle_language'
matches.append(match)
class SubtitleSuffixLanguageRule(Rule):
"""
Convert language guess as subtitle_language if next match is a subtitle language suffix
"""
dependency = SubtitlePrefixLanguageRule
consequence = RemoveMatch
properties = {'subtitle_language': [None]}
def enabled(self, context):
return not is_disabled(context, 'subtitle_language')
def when(self, matches, context):
to_append = []
to_remove = matches.named('subtitle_language.suffix')
for lang in matches.named('language'):
suffix = matches.next(lang, lambda match: match.name == 'subtitle_language.suffix', 0)
if suffix:
to_append.append(lang)
if suffix in to_remove:
to_remove.remove(suffix)
if to_append or to_remove:
return to_append, to_remove
return False
def then(self, matches, when_response, context):
to_rename, to_remove = when_response
super(SubtitleSuffixLanguageRule, self).then(matches, to_remove, context)
for match in to_rename:
matches.remove(match)
match.name = 'subtitle_language'
matches.append(match)
class SubtitleExtensionRule(Rule):
"""
Convert language guess as subtitle_language if next match is a subtitle extension.
Since it's a strong match, it also removes any conflicting source with it.
"""
consequence = [RemoveMatch, RenameMatch('subtitle_language')]
properties = {'subtitle_language': [None]}
def enabled(self, context):
return not is_disabled(context, 'subtitle_language')
def when(self, matches, context): # pylint:disable=inconsistent-return-statements
subtitle_extension = matches.named('container',
lambda match: 'extension' in match.tags and 'subtitle' in match.tags,
0)
if subtitle_extension:
subtitle_lang = matches.previous(subtitle_extension, lambda match: match.name == 'language', 0)
if subtitle_lang:
for weak in matches.named('subtitle_language', predicate=lambda m: 'weak-language' in m.tags):
weak.private = True
return matches.conflicting(subtitle_lang, lambda m: m.name == 'source'), subtitle_lang
class RemoveLanguage(Rule):
"""Remove language matches that were not converted to subtitle_language when language is disabled."""
consequence = RemoveMatch
def enabled(self, context):
return is_disabled(context, 'language')
def when(self, matches, context):
return matches.named('language')
class RemoveInvalidLanguages(Rule):
"""Remove language matches that matches the blacklisted common words."""
consequence = RemoveMatch
priority = 32
def __init__(self, common_words):
"""Constructor."""
super(RemoveInvalidLanguages, self).__init__()
self.common_words = common_words
def when(self, matches, context):
to_remove = []
for match in matches.range(0, len(matches.input_string),
predicate=lambda m: m.name in ('language', 'subtitle_language')):
if match.raw.lower() not in self.common_words:
continue
group = matches.markers.at_match(match, index=0, predicate=lambda m: m.name == 'group')
if group and (
not matches.range(
group.start, group.end, predicate=lambda m: m.name not in ('language', 'subtitle_language')
) and (not matches.holes(group.start, group.end, predicate=lambda m: m.value.strip(seps)))):
continue
to_remove.append(match)
return to_remove

55
lib/guessit/rules/properties/mimetype.py Normal file
View File

@@ -0,0 +1,55 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
mimetype property
"""
import mimetypes
from rebulk import Rebulk, CustomRule, POST_PROCESS
from rebulk.match import Match
from ..common.pattern import is_disabled
from ...rules.processors import Processors
def mimetype(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'mimetype'))
rebulk.rules(Mimetype)
return rebulk
class Mimetype(CustomRule):
"""
Mimetype post processor
:param matches:
:type matches:
:return:
:rtype:
"""
priority = POST_PROCESS
dependency = Processors
def when(self, matches, context):
mime, _ = mimetypes.guess_type(matches.input_string, strict=False)
return mime
def then(self, matches, when_response, context):
mime = when_response
matches.append(Match(len(matches.input_string), len(matches.input_string), name='mimetype', value=mime))
@property
def properties(self):
"""
Properties for this rule.
"""
return {'mimetype': [None]}

383
lib/guessit/rules/properties/other.py Normal file
View File

@@ -0,0 +1,383 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
other property
"""
import copy
from rebulk import Rebulk, Rule, RemoveMatch, RenameMatch, POST_PROCESS, AppendMatch
from rebulk.remodule import re
from ..common import dash
from ..common import seps
from ..common.pattern import is_disabled
from ..common.validators import seps_after, seps_before, seps_surround, and_
from ...reutils import build_or_pattern
from ...rules.common.formatters import raw_cleanup
def other(config): # pylint:disable=unused-argument,too-many-statements
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'other'))
rebulk = rebulk.regex_defaults(flags=re.IGNORECASE, abbreviations=[dash]).string_defaults(ignore_case=True)
rebulk.defaults(name="other", validator=seps_surround)
rebulk.regex('Audio-?Fix', 'Audio-?Fixed', value='Audio Fixed')
rebulk.regex('Sync-?Fix', 'Sync-?Fixed', value='Sync Fixed')
rebulk.regex('Dual', 'Dual-?Audio', value='Dual Audio')
rebulk.regex('ws', 'wide-?screen', value='Widescreen')
rebulk.regex('Re-?Enc(?:oded)?', value='Reencoded')
rebulk.string('Repack', 'Rerip', value='Proper',
tags=['streaming_service.prefix', 'streaming_service.suffix'])
rebulk.string('Proper', value='Proper',
tags=['has-neighbor', 'streaming_service.prefix', 'streaming_service.suffix'])
rebulk.regex('Real-Proper', 'Real-Repack', 'Real-Rerip', value='Proper',
tags=['streaming_service.prefix', 'streaming_service.suffix', 'real'])
rebulk.regex('Real', value='Proper',
tags=['has-neighbor', 'streaming_service.prefix', 'streaming_service.suffix', 'real'])
rebulk.string('Fix', 'Fixed', value='Fix', tags=['has-neighbor-before', 'has-neighbor-after',
'streaming_service.prefix', 'streaming_service.suffix'])
rebulk.string('Dirfix', 'Nfofix', 'Prooffix', value='Fix',
tags=['streaming_service.prefix', 'streaming_service.suffix'])
rebulk.regex('(?:Proof-?)?Sample-?Fix', value='Fix',
tags=['streaming_service.prefix', 'streaming_service.suffix'])
rebulk.string('Fansub', value='Fan Subtitled', tags='has-neighbor')
rebulk.string('Fastsub', value='Fast Subtitled', tags='has-neighbor')
season_words = build_or_pattern(["seasons?", "series?"])
complete_articles = build_or_pattern(["The"])
def validate_complete(match):
"""
Make sure season word is are defined.
:param match:
:type match:
:return:
:rtype:
"""
children = match.children
if not children.named('completeWordsBefore') and not children.named('completeWordsAfter'):
return False
return True
rebulk.regex('(?P<completeArticle>' + complete_articles + '-)?' +
'(?P<completeWordsBefore>' + season_words + '-)?' +
'Complete' + '(?P<completeWordsAfter>-' + season_words + ')?',
private_names=['completeArticle', 'completeWordsBefore', 'completeWordsAfter'],
value={'other': 'Complete'},
tags=['release-group-prefix'],
validator={'__parent__': and_(seps_surround, validate_complete)})
rebulk.string('R5', value='Region 5')
rebulk.string('RC', value='Region C')
rebulk.regex('Pre-?Air', value='Preair')
rebulk.regex('(?:PS-?)Vita', value='PS Vita')
rebulk.regex('Vita', value='PS Vita', tags='has-neighbor')
rebulk.regex('(HD)(?P<another>Rip)', value={'other': 'HD', 'another': 'Rip'},
private_parent=True, children=True, validator={'__parent__': seps_surround}, validate_all=True)
for value in ('Screener', 'Remux', 'PAL', 'SECAM', 'NTSC', 'XXX'):
rebulk.string(value, value=value)
rebulk.string('3D', value='3D', tags='has-neighbor')
rebulk.string('HQ', value='High Quality', tags='uhdbluray-neighbor')
rebulk.string('HR', value='High Resolution')
rebulk.string('LD', value='Line Dubbed')
rebulk.string('MD', value='Mic Dubbed')
rebulk.string('mHD', 'HDLight', value='Micro HD')
rebulk.string('LDTV', value='Low Definition')
rebulk.string('HFR', value='High Frame Rate')
rebulk.string('VFR', value='Variable Frame Rate')
rebulk.string('HD', value='HD', validator=None,
tags=['streaming_service.prefix', 'streaming_service.suffix'])
rebulk.regex('Full-?HD', 'FHD', value='Full HD', validator=None,
tags=['streaming_service.prefix', 'streaming_service.suffix'])
rebulk.regex('Ultra-?(?:HD)?', 'UHD', value='Ultra HD', validator=None,
tags=['streaming_service.prefix', 'streaming_service.suffix'])
rebulk.regex('Upscaled?', value='Upscaled')
for value in ('Complete', 'Classic', 'Bonus', 'Trailer', 'Retail',
'Colorized', 'Internal'):
rebulk.string(value, value=value, tags=['has-neighbor', 'release-group-prefix'])
rebulk.regex('LiNE', value='Line Audio', tags=['has-neighbor-before', 'has-neighbor-after', 'release-group-prefix'])
rebulk.regex('Read-?NFO', value='Read NFO')
rebulk.string('CONVERT', value='Converted', tags='has-neighbor')
rebulk.string('DOCU', 'DOKU', value='Documentary', tags='has-neighbor')
rebulk.string('OM', value='Open Matte', tags='has-neighbor')
rebulk.string('STV', value='Straight to Video', tags='has-neighbor')
rebulk.string('OAR', value='Original Aspect Ratio', tags='has-neighbor')
rebulk.string('Complet', value='Complete', tags=['has-neighbor', 'release-group-prefix'])
for coast in ('East', 'West'):
rebulk.regex(r'(?:Live-)?(?:Episode-)?' + coast + '-?(?:Coast-)?Feed', value=coast + ' Coast Feed')
rebulk.string('VO', 'OV', value='Original Video', tags='has-neighbor')
rebulk.string('Ova', 'Oav', value='Original Animated Video')
rebulk.regex('Scr(?:eener)?', value='Screener', validator=None,
tags=['other.validate.screener', 'source-prefix', 'source-suffix'])
rebulk.string('Mux', value='Mux', validator=seps_after,
tags=['other.validate.mux', 'video-codec-prefix', 'source-suffix'])
rebulk.string('HC', 'vost', value='Hardcoded Subtitles')
rebulk.string('SDR', value='Standard Dynamic Range', tags='uhdbluray-neighbor')
rebulk.regex('HDR(?:10)?', value='HDR10', tags='uhdbluray-neighbor')
rebulk.regex('Dolby-?Vision', value='Dolby Vision', tags='uhdbluray-neighbor')
rebulk.regex('BT-?2020', value='BT.2020', tags='uhdbluray-neighbor')
rebulk.string('Sample', value='Sample', tags=['at-end', 'not-a-release-group'])
rebulk.string('Extras', value='Extras', tags='has-neighbor')
rebulk.regex('Digital-?Extras?', value='Extras')
rebulk.string('Proof', value='Proof', tags=['at-end', 'not-a-release-group'])
rebulk.string('Obfuscated', 'Scrambled', value='Obfuscated', tags=['at-end', 'not-a-release-group'])
rebulk.string('xpost', 'postbot', 'asrequested', value='Repost', tags='not-a-release-group')
rebulk.rules(RenameAnotherToOther, ValidateHasNeighbor, ValidateHasNeighborAfter, ValidateHasNeighborBefore,
ValidateScreenerRule, ValidateMuxRule, ValidateHardcodedSubs, ValidateStreamingServiceNeighbor,
ValidateAtEnd, ValidateReal, ProperCountRule)
return rebulk
class ProperCountRule(Rule):
"""
Add proper_count property
"""
priority = POST_PROCESS
consequence = AppendMatch
properties = {'proper_count': [None]}
def when(self, matches, context): # pylint:disable=inconsistent-return-statements
propers = matches.named('other', lambda match: match.value == 'Proper')
if propers:
raws = {} # Count distinct raw values
for proper in propers:
raws[raw_cleanup(proper.raw)] = proper
proper_count_match = copy.copy(propers[-1])
proper_count_match.name = 'proper_count'
value = 0
for raw in raws.values():
value += 2 if 'real' in raw.tags else 1
proper_count_match.value = value
return proper_count_match
class RenameAnotherToOther(Rule):
"""
Rename `another` properties to `other`
"""
priority = 32
consequence = RenameMatch('other')
def when(self, matches, context):
return matches.named('another')
class ValidateHasNeighbor(Rule):
"""
Validate tag has-neighbor
"""
consequence = RemoveMatch
priority = 64
def when(self, matches, context):
ret = []
for to_check in matches.range(predicate=lambda match: 'has-neighbor' in match.tags):
previous_match = matches.previous(to_check, index=0)
previous_group = matches.markers.previous(to_check, lambda marker: marker.name == 'group', 0)
if previous_group and (not previous_match or previous_group.end > previous_match.end):
previous_match = previous_group
if previous_match and not matches.input_string[previous_match.end:to_check.start].strip(seps):
break
next_match = matches.next(to_check, index=0)
next_group = matches.markers.next(to_check, lambda marker: marker.name == 'group', 0)
if next_group and (not next_match or next_group.start < next_match.start):
next_match = next_group
if next_match and not matches.input_string[to_check.end:next_match.start].strip(seps):
break
ret.append(to_check)
return ret
class ValidateHasNeighborBefore(Rule):
"""
Validate tag has-neighbor-before that previous match exists.
"""
consequence = RemoveMatch
priority = 64
def when(self, matches, context):
ret = []
for to_check in matches.range(predicate=lambda match: 'has-neighbor-before' in match.tags):
next_match = matches.next(to_check, index=0)
next_group = matches.markers.next(to_check, lambda marker: marker.name == 'group', 0)
if next_group and (not next_match or next_group.start < next_match.start):
next_match = next_group
if next_match and not matches.input_string[to_check.end:next_match.start].strip(seps):
break
ret.append(to_check)
return ret
class ValidateHasNeighborAfter(Rule):
"""
Validate tag has-neighbor-after that next match exists.
"""
consequence = RemoveMatch
priority = 64
def when(self, matches, context):
ret = []
for to_check in matches.range(predicate=lambda match: 'has-neighbor-after' in match.tags):
previous_match = matches.previous(to_check, index=0)
previous_group = matches.markers.previous(to_check, lambda marker: marker.name == 'group', 0)
if previous_group and (not previous_match or previous_group.end > previous_match.end):
previous_match = previous_group
if previous_match and not matches.input_string[previous_match.end:to_check.start].strip(seps):
break
ret.append(to_check)
return ret
class ValidateScreenerRule(Rule):
"""
Validate tag other.validate.screener
"""
consequence = RemoveMatch
priority = 64
def when(self, matches, context):
ret = []
for screener in matches.named('other', lambda match: 'other.validate.screener' in match.tags):
source_match = matches.previous(screener, lambda match: match.initiator.name == 'source', 0)
if not source_match or matches.input_string[source_match.end:screener.start].strip(seps):
ret.append(screener)
return ret
class ValidateMuxRule(Rule):
"""
Validate tag other.validate.mux
"""
consequence = RemoveMatch
priority = 64
def when(self, matches, context):
ret = []
for mux in matches.named('other', lambda match: 'other.validate.mux' in match.tags):
source_match = matches.previous(mux, lambda match: match.initiator.name == 'source', 0)
if not source_match:
ret.append(mux)
return ret
class ValidateHardcodedSubs(Rule):
"""Validate HC matches."""
priority = 32
consequence = RemoveMatch
def when(self, matches, context):
to_remove = []
for hc_match in matches.named('other', predicate=lambda match: match.value == 'Hardcoded Subtitles'):
next_match = matches.next(hc_match, predicate=lambda match: match.name == 'subtitle_language', index=0)
if next_match and not matches.holes(hc_match.end, next_match.start,
predicate=lambda match: match.value.strip(seps)):
continue
previous_match = matches.previous(hc_match,
predicate=lambda match: match.name == 'subtitle_language', index=0)
if previous_match and not matches.holes(previous_match.end, hc_match.start,
predicate=lambda match: match.value.strip(seps)):
continue
to_remove.append(hc_match)
return to_remove
class ValidateStreamingServiceNeighbor(Rule):
"""Validate streaming service's neighbors."""
priority = 32
consequence = RemoveMatch
def when(self, matches, context):
to_remove = []
for match in matches.named('other',
predicate=lambda m: (m.initiator.name != 'source'
and ('streaming_service.prefix' in m.tags
or 'streaming_service.suffix' in m.tags))):
match = match.initiator
if not seps_after(match):
if 'streaming_service.prefix' in match.tags:
next_match = matches.next(match, lambda m: m.name == 'streaming_service', 0)
if next_match and not matches.holes(match.end, next_match.start,
predicate=lambda m: m.value.strip(seps)):
continue
if match.children:
to_remove.extend(match.children)
to_remove.append(match)
elif not seps_before(match):
if 'streaming_service.suffix' in match.tags:
previous_match = matches.previous(match, lambda m: m.name == 'streaming_service', 0)
if previous_match and not matches.holes(previous_match.end, match.start,
predicate=lambda m: m.value.strip(seps)):
continue
if match.children:
to_remove.extend(match.children)
to_remove.append(match)
return to_remove
class ValidateAtEnd(Rule):
"""Validate other which should occur at the end of a filepart."""
priority = 32
consequence = RemoveMatch
def when(self, matches, context):
to_remove = []
for filepart in matches.markers.named('path'):
for match in matches.range(filepart.start, filepart.end,
predicate=lambda m: m.name == 'other' and 'at-end' in m.tags):
if (matches.holes(match.end, filepart.end, predicate=lambda m: m.value.strip(seps)) or
matches.range(match.end, filepart.end, predicate=lambda m: m.name not in (
'other', 'container'))):
to_remove.append(match)
return to_remove
class ValidateReal(Rule):
"""
Validate Real
"""
consequence = RemoveMatch
priority = 64
def when(self, matches, context):
ret = []
for filepart in matches.markers.named('path'):
for match in matches.range(filepart.start, filepart.end, lambda m: m.name == 'other' and 'real' in m.tags):
if not matches.range(filepart.start, match.start):
ret.append(match)
return ret

46
lib/guessit/rules/properties/part.py Normal file
View File

@@ -0,0 +1,46 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
part property
"""
from rebulk.remodule import re
from rebulk import Rebulk
from ..common import dash
from ..common.pattern import is_disabled
from ..common.validators import seps_surround, int_coercable, and_
from ..common.numeral import numeral, parse_numeral
from ...reutils import build_or_pattern
def part(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'part'))
rebulk.regex_defaults(flags=re.IGNORECASE, abbreviations=[dash], validator={'__parent__': seps_surround})
prefixes = config['prefixes']
def validate_roman(match):
"""
Validate a roman match if surrounded by separators
:param match:
:type match:
:return:
:rtype:
"""
if int_coercable(match.raw):
return True
return seps_surround(match)
rebulk.regex(build_or_pattern(prefixes) + r'-?(?P<part>' + numeral + r')',
prefixes=prefixes, validate_all=True, private_parent=True, children=True, formatter=parse_numeral,
validator={'part': and_(validate_roman, lambda m: 0 < m.value < 100)})
return rebulk

347
lib/guessit/rules/properties/release_group.py Normal file
View File

@@ -0,0 +1,347 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
release_group property
"""
import copy
from rebulk import Rebulk, Rule, AppendMatch, RemoveMatch
from rebulk.match import Match
from ..common import seps
from ..common.comparators import marker_sorted
from ..common.expected import build_expected_function
from ..common.formatters import cleanup
from ..common.pattern import is_disabled
from ..common.validators import int_coercable, seps_surround
from ..properties.title import TitleFromPosition
def release_group(config):
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
forbidden_groupnames = config['forbidden_names']
groupname_ignore_seps = config['ignored_seps']
groupname_seps = ''.join([c for c in seps if c not in groupname_ignore_seps])
def clean_groupname(string):
"""
Removes and strip separators from input_string
:param string:
:type string:
:return:
:rtype:
"""
string = string.strip(groupname_seps)
if not (string.endswith(tuple(groupname_ignore_seps)) and string.startswith(tuple(groupname_ignore_seps))) \
and not any(i in string.strip(groupname_ignore_seps) for i in groupname_ignore_seps):
string = string.strip(groupname_ignore_seps)
for forbidden in forbidden_groupnames:
if string.lower().startswith(forbidden) and string[len(forbidden):len(forbidden) + 1] in seps:
string = string[len(forbidden):]
string = string.strip(groupname_seps)
if string.lower().endswith(forbidden) and string[-len(forbidden) - 1:-len(forbidden)] in seps:
string = string[:len(forbidden)]
string = string.strip(groupname_seps)
return string.strip()
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'release_group'))
expected_group = build_expected_function('expected_group')
rebulk.functional(expected_group, name='release_group', tags=['expected'],
validator=seps_surround,
conflict_solver=lambda match, other: other,
disabled=lambda context: not context.get('expected_group'))
return rebulk.rules(
DashSeparatedReleaseGroup(clean_groupname),
SceneReleaseGroup(clean_groupname),
AnimeReleaseGroup
)
_scene_previous_names = ('video_codec', 'source', 'video_api', 'audio_codec', 'audio_profile', 'video_profile',
'audio_channels', 'screen_size', 'other', 'container', 'language', 'subtitle_language',
'subtitle_language.suffix', 'subtitle_language.prefix', 'language.suffix')
_scene_previous_tags = ('release-group-prefix',)
_scene_no_previous_tags = ('no-release-group-prefix',)
class DashSeparatedReleaseGroup(Rule):
"""
Detect dash separated release groups that might appear at the end or at the beginning of a release name.
Series.S01E02.Pilot.DVDRip.x264-CS.mkv
release_group: CS
abc-the.title.name.1983.1080p.bluray.x264.mkv
release_group: abc
At the end: Release groups should be dash-separated and shouldn't contain spaces nor
appear in a group with other matches. The preceding matches should be separated by dot.
If a release group is found, the conflicting matches are removed.
At the beginning: Release groups should be dash-separated and shouldn't contain spaces nor appear in a group.
It should be followed by a hole with dot-separated words.
Detection only happens if no matches exist at the beginning.
"""
consequence = [RemoveMatch, AppendMatch]
def __init__(self, value_formatter):
"""Default constructor."""
super(DashSeparatedReleaseGroup, self).__init__()
self.value_formatter = value_formatter
@classmethod
def is_valid(cls, matches, candidate, start, end, at_end): # pylint:disable=inconsistent-return-statements
"""
Whether a candidate is a valid release group.
"""
if not at_end:
if len(candidate.value) <= 1:
return False
if matches.markers.at_match(candidate, predicate=lambda m: m.name == 'group'):
return False
first_hole = matches.holes(candidate.end, end, predicate=lambda m: m.start == candidate.end, index=0)
if not first_hole:
return False
raw_value = first_hole.raw
return raw_value[0] == '-' and '-' not in raw_value[1:] and '.' in raw_value and ' ' not in raw_value
group = matches.markers.at_match(candidate, predicate=lambda m: m.name == 'group', index=0)
if group and matches.at_match(group, predicate=lambda m: not m.private and m.span != candidate.span):
return False
count = 0
match = candidate
while match:
current = matches.range(start,
match.start,
index=-1,
predicate=lambda m: not m.private and not 'expected' in m.tags)
if not current:
break
separator = match.input_string[current.end:match.start]
if not separator and match.raw[0] == '-':
separator = '-'
match = current
if count == 0:
if separator != '-':
break
count += 1
continue
if separator == '.':
return True
def detect(self, matches, start, end, at_end): # pylint:disable=inconsistent-return-statements
"""
Detect release group at the end or at the beginning of a filepart.
"""
candidate = None
if at_end:
container = matches.ending(end, lambda m: m.name == 'container', index=0)
if container:
end = container.start
candidate = matches.ending(end, index=0, predicate=(
lambda m: not m.private and not (
m.name == 'other' and 'not-a-release-group' in m.tags
) and '-' not in m.raw and m.raw.strip() == m.raw))
if not candidate:
if at_end:
candidate = matches.holes(start, end, seps=seps, index=-1,
predicate=lambda m: m.end == end and m.raw.strip(seps) and m.raw[0] == '-')
else:
candidate = matches.holes(start, end, seps=seps, index=0,
predicate=lambda m: m.start == start and m.raw.strip(seps))
if candidate and self.is_valid(matches, candidate, start, end, at_end):
return candidate
def when(self, matches, context): # pylint:disable=inconsistent-return-statements
if matches.named('release_group'):
return
to_remove = []
to_append = []
for filepart in matches.markers.named('path'):
candidate = self.detect(matches, filepart.start, filepart.end, True)
if candidate:
to_remove.extend(matches.at_match(candidate))
else:
candidate = self.detect(matches, filepart.start, filepart.end, False)
if candidate:
releasegroup = Match(candidate.start, candidate.end, name='release_group',
formatter=self.value_formatter, input_string=candidate.input_string)
if releasegroup.value:
to_append.append(releasegroup)
if to_remove or to_append:
return to_remove, to_append
class SceneReleaseGroup(Rule):
"""
Add release_group match in existing matches (scene format).
Something.XViD-ReleaseGroup.mkv
"""
dependency = [TitleFromPosition]
consequence = AppendMatch
properties = {'release_group': [None]}
def __init__(self, value_formatter):
"""Default constructor."""
super(SceneReleaseGroup, self).__init__()
self.value_formatter = value_formatter
@staticmethod
def is_previous_match(match):
"""
Check if match can precede release_group
:param match:
:return:
"""
return not match.tagged(*_scene_no_previous_tags) if match.name in _scene_previous_names else \
match.tagged(*_scene_previous_tags)
def when(self, matches, context): # pylint:disable=too-many-locals
# If a release_group is found before, ignore this kind of release_group rule.
ret = []
for filepart in marker_sorted(matches.markers.named('path'), matches):
# pylint:disable=cell-var-from-loop
start, end = filepart.span
if matches.named('release_group', predicate=lambda m: m.start >= start and m.end <= end):
continue
titles = matches.named('title', predicate=lambda m: m.start >= start and m.end <= end)
def keep_only_first_title(match):
"""
Keep only first title from this filepart, as other ones are most likely release group.
:param match:
:type match:
:return:
:rtype:
"""
return match in titles[1:]
last_hole = matches.holes(start, end + 1, formatter=self.value_formatter,
ignore=keep_only_first_title,
predicate=lambda hole: cleanup(hole.value), index=-1)
if last_hole:
def previous_match_filter(match):
"""
Filter to apply to find previous match
:param match:
:type match:
:return:
:rtype:
"""
if match.start < filepart.start:
return False
return not match.private or self.is_previous_match(match)
previous_match = matches.previous(last_hole,
previous_match_filter,
index=0)
if previous_match and (self.is_previous_match(previous_match)) and \
not matches.input_string[previous_match.end:last_hole.start].strip(seps) \
and not int_coercable(last_hole.value.strip(seps)):
last_hole.name = 'release_group'
last_hole.tags = ['scene']
# if hole is inside a group marker with same value, remove [](){} ...
group = matches.markers.at_match(last_hole, lambda marker: marker.name == 'group', 0)
if group:
group.formatter = self.value_formatter
if group.value == last_hole.value:
last_hole.start = group.start + 1
last_hole.end = group.end - 1
last_hole.tags = ['anime']
ignored_matches = matches.range(last_hole.start, last_hole.end, keep_only_first_title)
for ignored_match in ignored_matches:
matches.remove(ignored_match)
ret.append(last_hole)
return ret
class AnimeReleaseGroup(Rule):
"""
Add release_group match in existing matches (anime format)
...[ReleaseGroup] Something.mkv
"""
dependency = [SceneReleaseGroup, TitleFromPosition]
consequence = [RemoveMatch, AppendMatch]
properties = {'release_group': [None]}
def when(self, matches, context):
to_remove = []
to_append = []
# If a release_group is found before, ignore this kind of release_group rule.
if matches.named('release_group'):
return False
if not matches.named('episode') and not matches.named('season') and matches.named('release_group'):
# This doesn't seems to be an anime, and we already found another release_group.
return False
for filepart in marker_sorted(matches.markers.named('path'), matches):
# pylint:disable=bad-continuation
empty_group = matches.markers.range(filepart.start,
filepart.end,
lambda marker: (marker.name == 'group'
and not matches.range(marker.start, marker.end,
lambda m:
'weak-language' not in m.tags)
and marker.value.strip(seps)
and not int_coercable(marker.value.strip(seps))), 0)
if empty_group:
group = copy.copy(empty_group)
group.marker = False
group.raw_start += 1
group.raw_end -= 1
group.tags = ['anime']
group.name = 'release_group'
to_append.append(group)
to_remove.extend(matches.range(empty_group.start, empty_group.end,
lambda m: 'weak-language' in m.tags))
if to_remove or to_append:
return to_remove, to_append
return False

163
lib/guessit/rules/properties/screen_size.py Normal file
View File

@@ -0,0 +1,163 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
screen_size property
"""
from rebulk.match import Match
from rebulk.remodule import re
from rebulk import Rebulk, Rule, RemoveMatch, AppendMatch
from ..common.pattern import is_disabled
from ..common.quantity import FrameRate
from ..common.validators import seps_surround
from ..common import dash, seps
from ...reutils import build_or_pattern
def screen_size(config):
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
interlaced = frozenset(config['interlaced'])
progressive = frozenset(config['progressive'])
frame_rates = [re.escape(rate) for rate in config['frame_rates']]
min_ar = config['min_ar']
max_ar = config['max_ar']
rebulk = Rebulk()
rebulk = rebulk.string_defaults(ignore_case=True).regex_defaults(flags=re.IGNORECASE)
rebulk.defaults(name='screen_size', validator=seps_surround, abbreviations=[dash],
disabled=lambda context: is_disabled(context, 'screen_size'))
frame_rate_pattern = build_or_pattern(frame_rates, name='frame_rate')
interlaced_pattern = build_or_pattern(interlaced, name='height')
progressive_pattern = build_or_pattern(progressive, name='height')
res_pattern = r'(?:(?P<width>\d{3,4})(?:x|\*))?'
rebulk.regex(res_pattern + interlaced_pattern + r'(?P<scan_type>i)' + frame_rate_pattern + '?')
rebulk.regex(res_pattern + progressive_pattern + r'(?P<scan_type>p)' + frame_rate_pattern + '?')
rebulk.regex(res_pattern + progressive_pattern + r'(?P<scan_type>p)?(?:hd)')
rebulk.regex(res_pattern + progressive_pattern + r'(?P<scan_type>p)?x?')
rebulk.string('4k', value='2160p')
rebulk.regex(r'(?P<width>\d{3,4})-?(?:x|\*)-?(?P<height>\d{3,4})',
conflict_solver=lambda match, other: '__default__' if other.name == 'screen_size' else other)
rebulk.regex(frame_rate_pattern + '(p|fps)', name='frame_rate',
formatter=FrameRate.fromstring, disabled=lambda context: is_disabled(context, 'frame_rate'))
rebulk.rules(PostProcessScreenSize(progressive, min_ar, max_ar), ScreenSizeOnlyOne, ResolveScreenSizeConflicts)
return rebulk
class PostProcessScreenSize(Rule):
"""
Process the screen size calculating the aspect ratio if available.
Convert to a standard notation (720p, 1080p, etc) when it's a standard resolution and
aspect ratio is valid or not available.
It also creates an aspect_ratio match when available.
"""
consequence = AppendMatch
def __init__(self, standard_heights, min_ar, max_ar):
super(PostProcessScreenSize, self).__init__()
self.standard_heights = standard_heights
self.min_ar = min_ar
self.max_ar = max_ar
def when(self, matches, context):
to_append = []
for match in matches.named('screen_size'):
if not is_disabled(context, 'frame_rate'):
for frame_rate in match.children.named('frame_rate'):
frame_rate.formatter = FrameRate.fromstring
to_append.append(frame_rate)
values = match.children.to_dict()
if 'height' not in values:
continue
scan_type = (values.get('scan_type') or 'p').lower()
height = values['height']
if 'width' not in values:
match.value = '{0}{1}'.format(height, scan_type)
continue
width = values['width']
calculated_ar = float(width) / float(height)
aspect_ratio = Match(match.start, match.end, input_string=match.input_string,
name='aspect_ratio', value=round(calculated_ar, 3))
if not is_disabled(context, 'aspect_ratio'):
to_append.append(aspect_ratio)
if height in self.standard_heights and self.min_ar < calculated_ar < self.max_ar:
match.value = '{0}{1}'.format(height, scan_type)
else:
match.value = '{0}x{1}'.format(width, height)
return to_append
class ScreenSizeOnlyOne(Rule):
"""
Keep a single screen_size per filepath part.
"""
consequence = RemoveMatch
def when(self, matches, context):
to_remove = []
for filepart in matches.markers.named('path'):
screensize = list(reversed(matches.range(filepart.start, filepart.end,
lambda match: match.name == 'screen_size')))
if len(screensize) > 1 and len(set((match.value for match in screensize))) > 1:
to_remove.extend(screensize[1:])
return to_remove
class ResolveScreenSizeConflicts(Rule):
"""
Resolve screen_size conflicts with season and episode matches.
"""
consequence = RemoveMatch
def when(self, matches, context):
to_remove = []
for filepart in matches.markers.named('path'):
screensize = matches.range(filepart.start, filepart.end, lambda match: match.name == 'screen_size', 0)
if not screensize:
continue
conflicts = matches.conflicting(screensize, lambda match: match.name in ('season', 'episode'))
if not conflicts:
continue
has_neighbor = False
video_profile = matches.range(screensize.end, filepart.end, lambda match: match.name == 'video_profile', 0)
if video_profile and not matches.holes(screensize.end, video_profile.start,
predicate=lambda h: h.value and h.value.strip(seps)):
to_remove.extend(conflicts)
has_neighbor = True
previous = matches.previous(screensize, index=0, predicate=(
lambda m: m.name in ('date', 'source', 'other', 'streaming_service')))
if previous and not matches.holes(previous.end, screensize.start,
predicate=lambda h: h.value and h.value.strip(seps)):
to_remove.extend(conflicts)
has_neighbor = True
if not has_neighbor:
to_remove.append(screensize)
return to_remove

30
lib/guessit/rules/properties/size.py Normal file
View File

@@ -0,0 +1,30 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
size property
"""
import re
from rebulk import Rebulk
from ..common import dash
from ..common.quantity import Size
from ..common.pattern import is_disabled
from ..common.validators import seps_surround
def size(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'size'))
rebulk.regex_defaults(flags=re.IGNORECASE, abbreviations=[dash])
rebulk.defaults(name='size', validator=seps_surround)
rebulk.regex(r'\d+-?[mgt]b', r'\d+\.\d+-?[mgt]b', formatter=Size.fromstring, tags=['release-group-prefix'])
return rebulk

235
lib/guessit/rules/properties/source.py Normal file
View File

@@ -0,0 +1,235 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
source property
"""
import copy
from rebulk.remodule import re
from rebulk import AppendMatch, Rebulk, RemoveMatch, Rule
from .audio_codec import HqConflictRule
from ..common import dash, seps
from ..common.pattern import is_disabled
from ..common.validators import seps_before, seps_after, or_
def source(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'source'))
rebulk = rebulk.regex_defaults(flags=re.IGNORECASE, abbreviations=[dash], private_parent=True, children=True)
rebulk = rebulk.defaults(name='source',
tags=['video-codec-prefix', 'streaming_service.suffix'],
validate_all=True,
validator={'__parent__': or_(seps_before, seps_after)})
rip_prefix = '(?P<other>Rip)-?'
rip_suffix = '-?(?P<other>Rip)'
rip_optional_suffix = '(?:' + rip_suffix + ')?'
def build_source_pattern(*patterns, **kwargs):
"""Helper pattern to build source pattern."""
prefix_format = kwargs.get('prefix') or ''
suffix_format = kwargs.get('suffix') or ''
string_format = prefix_format + '({0})' + suffix_format
return [string_format.format(pattern) for pattern in patterns]
def demote_other(match, other): # pylint: disable=unused-argument
"""Default conflict solver with 'other' property."""
return other if other.name == 'other' or other.name == 'release_group' else '__default__'
rebulk.regex(*build_source_pattern('VHS', suffix=rip_optional_suffix),
value={'source': 'VHS', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('CAM', suffix=rip_optional_suffix),
value={'source': 'Camera', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('HD-?CAM', suffix=rip_optional_suffix),
value={'source': 'HD Camera', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('TELESYNC', 'TS', suffix=rip_optional_suffix),
value={'source': 'Telesync', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('HD-?TELESYNC', 'HD-?TS', suffix=rip_optional_suffix),
value={'source': 'HD Telesync', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('WORKPRINT', 'WP'), value='Workprint')
rebulk.regex(*build_source_pattern('TELECINE', 'TC', suffix=rip_optional_suffix),
value={'source': 'Telecine', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('HD-?TELECINE', 'HD-?TC', suffix=rip_optional_suffix),
value={'source': 'HD Telecine', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('PPV', suffix=rip_optional_suffix),
value={'source': 'Pay-per-view', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('SD-?TV', suffix=rip_optional_suffix),
value={'source': 'TV', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('TV', suffix=rip_suffix), # TV is too common to allow matching
value={'source': 'TV', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('TV', 'SD-?TV', prefix=rip_prefix),
value={'source': 'TV', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('TV-?(?=Dub)'), value='TV')
rebulk.regex(*build_source_pattern('DVB', 'PD-?TV', suffix=rip_optional_suffix),
value={'source': 'Digital TV', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('DVD', suffix=rip_optional_suffix),
value={'source': 'DVD', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('DM', suffix=rip_optional_suffix),
value={'source': 'Digital Master', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('VIDEO-?TS', 'DVD-?R(?:$|(?!E))', # 'DVD-?R(?:$|^E)' => DVD-Real ...
'DVD-?9', 'DVD-?5'), value='DVD')
rebulk.regex(*build_source_pattern('HD-?TV', suffix=rip_optional_suffix), conflict_solver=demote_other,
value={'source': 'HDTV', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('TV-?HD', suffix=rip_suffix), conflict_solver=demote_other,
value={'source': 'HDTV', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('TV', suffix='-?(?P<other>Rip-?HD)'), conflict_solver=demote_other,
value={'source': 'HDTV', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('VOD', suffix=rip_optional_suffix),
value={'source': 'Video on Demand', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('WEB', 'WEB-?DL', suffix=rip_suffix),
value={'source': 'Web', 'other': 'Rip'})
# WEBCap is a synonym to WEBRip, mostly used by non english
rebulk.regex(*build_source_pattern('WEB-?(?P<another>Cap)', suffix=rip_optional_suffix),
value={'source': 'Web', 'other': 'Rip', 'another': 'Rip'})
rebulk.regex(*build_source_pattern('WEB-?DL', 'WEB-?U?HD', 'DL-?WEB', 'DL(?=-?Mux)'),
value={'source': 'Web'})
rebulk.regex('(WEB)', value='Web', tags='weak.source')
rebulk.regex(*build_source_pattern('HD-?DVD', suffix=rip_optional_suffix),
value={'source': 'HD-DVD', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('Blu-?ray', 'BD', 'BD[59]', 'BD25', 'BD50', suffix=rip_optional_suffix),
value={'source': 'Blu-ray', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('(?P<another>BR)-?(?=Scr(?:eener)?)', '(?P<another>BR)-?(?=Mux)'), # BRRip
value={'source': 'Blu-ray', 'another': 'Reencoded'})
rebulk.regex(*build_source_pattern('(?P<another>BR)', suffix=rip_suffix), # BRRip
value={'source': 'Blu-ray', 'other': 'Rip', 'another': 'Reencoded'})
rebulk.regex(*build_source_pattern('Ultra-?Blu-?ray', 'Blu-?ray-?Ultra'), value='Ultra HD Blu-ray')
rebulk.regex(*build_source_pattern('AHDTV'), value='Analog HDTV')
rebulk.regex(*build_source_pattern('UHD-?TV', suffix=rip_optional_suffix), conflict_solver=demote_other,
value={'source': 'Ultra HDTV', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('UHD', suffix=rip_suffix), conflict_solver=demote_other,
value={'source': 'Ultra HDTV', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('DSR', 'DTH', suffix=rip_optional_suffix),
value={'source': 'Satellite', 'other': 'Rip'})
rebulk.regex(*build_source_pattern('DSR?', 'SAT', suffix=rip_suffix),
value={'source': 'Satellite', 'other': 'Rip'})
rebulk.rules(ValidateSourcePrefixSuffix, ValidateWeakSource, UltraHdBlurayRule)
return rebulk
class UltraHdBlurayRule(Rule):
"""
Replace other:Ultra HD and source:Blu-ray with source:Ultra HD Blu-ray
"""
dependency = HqConflictRule
consequence = [RemoveMatch, AppendMatch]
@classmethod
def find_ultrahd(cls, matches, start, end, index):
"""Find Ultra HD match."""
return matches.range(start, end, index=index, predicate=(
lambda m: not m.private and m.name == 'other' and m.value == 'Ultra HD'
))
@classmethod
def validate_range(cls, matches, start, end):
"""Validate no holes or invalid matches exist in the specified range."""
return (
not matches.holes(start, end, predicate=lambda m: m.value.strip(seps)) and
not matches.range(start, end, predicate=(
lambda m: not m.private and (
m.name not in ('screen_size', 'color_depth') and (
m.name != 'other' or 'uhdbluray-neighbor' not in m.tags))))
)
def when(self, matches, context):
to_remove = []
to_append = []
for filepart in matches.markers.named('path'):
for match in matches.range(filepart.start, filepart.end, predicate=(
lambda m: not m.private and m.name == 'source' and m.value == 'Blu-ray')):
other = self.find_ultrahd(matches, filepart.start, match.start, -1)
if not other or not self.validate_range(matches, other.end, match.start):
other = self.find_ultrahd(matches, match.end, filepart.end, 0)
if not other or not self.validate_range(matches, match.end, other.start):
if not matches.range(filepart.start, filepart.end, predicate=(
lambda m: m.name == 'screen_size' and m.value == '2160p')):
continue
if other:
other.private = True
new_source = copy.copy(match)
new_source.value = 'Ultra HD Blu-ray'
to_remove.append(match)
to_append.append(new_source)
if to_remove or to_append:
return to_remove, to_append
return False
class ValidateSourcePrefixSuffix(Rule):
"""
Validate source with source prefix, source suffix.
"""
priority = 64
consequence = RemoveMatch
def when(self, matches, context):
ret = []
for filepart in matches.markers.named('path'):
for match in matches.range(filepart.start, filepart.end, predicate=lambda m: m.name == 'source'):
match = match.initiator
if not seps_before(match) and \
not matches.range(match.start - 1, match.start - 2,
lambda m: 'source-prefix' in m.tags):
if match.children:
ret.extend(match.children)
ret.append(match)
continue
if not seps_after(match) and \
not matches.range(match.end, match.end + 1,
lambda m: 'source-suffix' in m.tags):
if match.children:
ret.extend(match.children)
ret.append(match)
continue
return ret
class ValidateWeakSource(Rule):
"""
Validate weak source
"""
dependency = [ValidateSourcePrefixSuffix]
priority = 64
consequence = RemoveMatch
def when(self, matches, context):
ret = []
for filepart in matches.markers.named('path'):
for match in matches.range(filepart.start, filepart.end, predicate=lambda m: m.name == 'source'):
# if there are more than 1 source in this filepart, just before the year and with holes for the title
# most likely the source is part of the title
if 'weak.source' in match.tags \
and matches.range(match.end, filepart.end, predicate=lambda m: m.name == 'source') \
and matches.holes(filepart.start, match.start,
predicate=lambda m: m.value.strip(seps), index=-1):
if match.children:
ret.extend(match.children)
ret.append(match)
continue
return ret

78
lib/guessit/rules/properties/streaming_service.py Normal file
View File

@@ -0,0 +1,78 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
streaming_service property
"""
import re
from rebulk import Rebulk
from rebulk.rules import Rule, RemoveMatch
from ..common.pattern import is_disabled
from ...rules.common import seps, dash
from ...rules.common.validators import seps_before, seps_after
def streaming_service(config): # pylint: disable=too-many-statements,unused-argument
"""Streaming service property.
:param config: rule configuration
:type config: dict
:return:
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'streaming_service'))
rebulk = rebulk.string_defaults(ignore_case=True).regex_defaults(flags=re.IGNORECASE, abbreviations=[dash])
rebulk.defaults(name='streaming_service', tags=['source-prefix'])
for value, items in config.items():
patterns = items if isinstance(items, list) else [items]
for pattern in patterns:
if pattern.startswith('re:'):
rebulk.regex(pattern, value=value)
else:
rebulk.string(pattern, value=value)
rebulk.rules(ValidateStreamingService)
return rebulk
class ValidateStreamingService(Rule):
"""Validate streaming service matches."""
priority = 128
consequence = RemoveMatch
def when(self, matches, context):
"""Streaming service is always before source.
:param matches:
:type matches: rebulk.match.Matches
:param context:
:type context: dict
:return:
"""
to_remove = []
for service in matches.named('streaming_service'):
next_match = matches.next(service, lambda match: 'streaming_service.suffix' in match.tags, 0)
previous_match = matches.previous(service, lambda match: 'streaming_service.prefix' in match.tags, 0)
has_other = service.initiator and service.initiator.children.named('other')
if not has_other:
if (not next_match or
matches.holes(service.end, next_match.start,
predicate=lambda match: match.value.strip(seps)) or
not seps_before(service)):
if (not previous_match or
matches.holes(previous_match.end, service.start,
predicate=lambda match: match.value.strip(seps)) or
not seps_after(service)):
to_remove.append(service)
continue
if service.value == 'Comedy Central':
# Current match is a valid streaming service, removing invalid Criterion Collection (CC) matches
to_remove.extend(matches.named('edition', predicate=lambda match: match.value == 'Criterion'))
return to_remove

349
lib/guessit/rules/properties/title.py Normal file
View File

@@ -0,0 +1,349 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
title property
"""
from rebulk import Rebulk, Rule, AppendMatch, RemoveMatch, AppendTags
from rebulk.formatters import formatters
from .film import FilmTitleRule
from .language import (
SubtitlePrefixLanguageRule,
SubtitleSuffixLanguageRule,
SubtitleExtensionRule,
NON_SPECIFIC_LANGUAGES
)
from ..common import seps, title_seps
from ..common.comparators import marker_sorted
from ..common.expected import build_expected_function
from ..common.formatters import cleanup, reorder_title
from ..common.pattern import is_disabled
from ..common.validators import seps_surround
def title(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'title'))
rebulk.rules(TitleFromPosition, PreferTitleWithYear)
expected_title = build_expected_function('expected_title')
rebulk.functional(expected_title, name='title', tags=['expected', 'title'],
validator=seps_surround,
formatter=formatters(cleanup, reorder_title),
conflict_solver=lambda match, other: other,
disabled=lambda context: not context.get('expected_title'))
return rebulk
class TitleBaseRule(Rule):
"""
Add title match in existing matches
"""
# pylint:disable=no-self-use,unused-argument
consequence = [AppendMatch, RemoveMatch]
def __init__(self, match_name, match_tags=None, alternative_match_name=None):
super(TitleBaseRule, self).__init__()
self.match_name = match_name
self.match_tags = match_tags
self.alternative_match_name = alternative_match_name
def hole_filter(self, hole, matches):
"""
Filter holes for titles.
:param hole:
:type hole:
:param matches:
:type matches:
:return:
:rtype:
"""
return True
def filepart_filter(self, filepart, matches):
"""
Filter filepart for titles.
:param filepart:
:type filepart:
:param matches:
:type matches:
:return:
:rtype:
"""
return True
def holes_process(self, holes, matches):
"""
process holes
:param holes:
:type holes:
:param matches:
:type matches:
:return:
:rtype:
"""
cropped_holes = []
group_markers = matches.markers.named('group')
for group_marker in group_markers:
path_marker = matches.markers.at_match(group_marker, predicate=lambda m: m.name == 'path', index=0)
if path_marker and path_marker.span == group_marker.span:
group_markers.remove(group_marker)
for hole in holes:
cropped_holes.extend(hole.crop(group_markers))
return cropped_holes
@staticmethod
def is_ignored(match):
"""
Ignore matches when scanning for title (hole).
Full word language and countries won't be ignored if they are uppercase.
"""
return not (len(match) > 3 and match.raw.isupper()) and match.name in ('language', 'country', 'episode_details')
def should_keep(self, match, to_keep, matches, filepart, hole, starting):
"""
Check if this match should be accepted when ending or starting a hole.
:param match:
:type match:
:param to_keep:
:type to_keep: list[Match]
:param matches:
:type matches: Matches
:param hole: the filepart match
:type hole: Match
:param hole: the hole match
:type hole: Match
:param starting: true if match is starting the hole
:type starting: bool
:return:
:rtype:
"""
if match.name in ('language', 'country'):
# Keep language if exactly matching the hole.
if len(hole.value) == len(match.raw):
return True
# Keep language if other languages exists in the filepart.
outside_matches = filepart.crop(hole)
other_languages = []
for outside in outside_matches:
other_languages.extend(matches.range(outside.start, outside.end,
lambda c_match: c_match.name == match.name and
c_match not in to_keep and
c_match.value not in NON_SPECIFIC_LANGUAGES))
if not other_languages and (not starting or len(match.raw) <= 3):
return True
return False
def should_remove(self, match, matches, filepart, hole, context):
"""
Check if this match should be removed after beeing ignored.
:param match:
:param matches:
:param filepart:
:param hole:
:return:
"""
if context.get('type') == 'episode' and match.name == 'episode_details':
return match.start >= hole.start and match.end <= hole.end
return True
def check_titles_in_filepart(self, filepart, matches, context): # pylint:disable=inconsistent-return-statements
"""
Find title in filepart (ignoring language)
"""
# pylint:disable=too-many-locals,too-many-branches,too-many-statements
start, end = filepart.span
holes = matches.holes(start, end + 1, formatter=formatters(cleanup, reorder_title),
ignore=self.is_ignored,
predicate=lambda m: m.value)
holes = self.holes_process(holes, matches)
for hole in holes:
if not hole or (self.hole_filter and not self.hole_filter(hole, matches)):
continue
to_remove = []
to_keep = []
ignored_matches = matches.range(hole.start, hole.end, self.is_ignored)
if ignored_matches:
for ignored_match in reversed(ignored_matches):
# pylint:disable=undefined-loop-variable, cell-var-from-loop
trailing = matches.chain_before(hole.end, seps, predicate=lambda m: m == ignored_match)
if trailing:
should_keep = self.should_keep(ignored_match, to_keep, matches, filepart, hole, False)
if should_keep:
# pylint:disable=unpacking-non-sequence
try:
append, crop = should_keep
except TypeError:
append, crop = should_keep, should_keep
if append:
to_keep.append(ignored_match)
if crop:
hole.end = ignored_match.start
for ignored_match in ignored_matches:
if ignored_match not in to_keep:
starting = matches.chain_after(hole.start, seps,
predicate=lambda m: m == ignored_match)
if starting:
should_keep = self.should_keep(ignored_match, to_keep, matches, filepart, hole, True)
if should_keep:
# pylint:disable=unpacking-non-sequence
try:
append, crop = should_keep
except TypeError:
append, crop = should_keep, should_keep
if append:
to_keep.append(ignored_match)
if crop:
hole.start = ignored_match.end
for match in ignored_matches:
if self.should_remove(match, matches, filepart, hole, context):
to_remove.append(match)
for keep_match in to_keep:
if keep_match in to_remove:
to_remove.remove(keep_match)
if hole and hole.value:
hole.name = self.match_name
hole.tags = self.match_tags
if self.alternative_match_name:
# Split and keep values that can be a title
titles = hole.split(title_seps, lambda m: m.value)
for title_match in list(titles[1:]):
previous_title = titles[titles.index(title_match) - 1]
separator = matches.input_string[previous_title.end:title_match.start]
if len(separator) == 1 and separator == '-' \
and previous_title.raw[-1] not in seps \
and title_match.raw[0] not in seps:
titles[titles.index(title_match) - 1].end = title_match.end
titles.remove(title_match)
else:
title_match.name = self.alternative_match_name
else:
titles = [hole]
return titles, to_remove
def when(self, matches, context):
ret = []
to_remove = []
if matches.named(self.match_name, lambda match: 'expected' in match.tags):
return False
fileparts = [filepart for filepart in list(marker_sorted(matches.markers.named('path'), matches))
if not self.filepart_filter or self.filepart_filter(filepart, matches)]
# Priorize fileparts containing the year
years_fileparts = []
for filepart in fileparts:
year_match = matches.range(filepart.start, filepart.end, lambda match: match.name == 'year', 0)
if year_match:
years_fileparts.append(filepart)
for filepart in fileparts:
try:
years_fileparts.remove(filepart)
except ValueError:
pass
titles = self.check_titles_in_filepart(filepart, matches, context)
if titles:
titles, to_remove_c = titles
ret.extend(titles)
to_remove.extend(to_remove_c)
break
# Add title match in all fileparts containing the year.
for filepart in years_fileparts:
titles = self.check_titles_in_filepart(filepart, matches, context)
if titles:
# pylint:disable=unbalanced-tuple-unpacking
titles, to_remove_c = titles
ret.extend(titles)
to_remove.extend(to_remove_c)
if ret or to_remove:
return ret, to_remove
return False
class TitleFromPosition(TitleBaseRule):
"""
Add title match in existing matches
"""
dependency = [FilmTitleRule, SubtitlePrefixLanguageRule, SubtitleSuffixLanguageRule, SubtitleExtensionRule]
properties = {'title': [None], 'alternative_title': [None]}
def __init__(self):
super(TitleFromPosition, self).__init__('title', ['title'], 'alternative_title')
def enabled(self, context):
return not is_disabled(context, 'alternative_title')
class PreferTitleWithYear(Rule):
"""
Prefer title where filepart contains year.
"""
dependency = TitleFromPosition
consequence = [RemoveMatch, AppendTags(['equivalent-ignore'])]
properties = {'title': [None]}
def when(self, matches, context):
with_year_in_group = []
with_year = []
titles = matches.named('title')
for title_match in titles:
filepart = matches.markers.at_match(title_match, lambda marker: marker.name == 'path', 0)
if filepart:
year_match = matches.range(filepart.start, filepart.end, lambda match: match.name == 'year', 0)
if year_match:
group = matches.markers.at_match(year_match, lambda m: m.name == 'group')
if group:
with_year_in_group.append(title_match)
else:
with_year.append(title_match)
to_tag = []
if with_year_in_group:
title_values = {title_match.value for title_match in with_year_in_group}
to_tag.extend(with_year_in_group)
elif with_year:
title_values = {title_match.value for title_match in with_year}
to_tag.extend(with_year)
else:
title_values = {title_match.value for title_match in titles}
to_remove = []
for title_match in titles:
if title_match.value not in title_values:
to_remove.append(title_match)
if to_remove or to_tag:
return to_remove, to_tag
return False

83
lib/guessit/rules/properties/type.py Normal file
View File

@@ -0,0 +1,83 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
type property
"""
from rebulk import CustomRule, Rebulk, POST_PROCESS
from rebulk.match import Match
from ..common.pattern import is_disabled
from ...rules.processors import Processors
def _type(matches, value):
"""
Define type match with given value.
:param matches:
:param value:
:return:
"""
matches.append(Match(len(matches.input_string), len(matches.input_string), name='type', value=value))
def type_(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'type'))
rebulk = rebulk.rules(TypeProcessor)
return rebulk
class TypeProcessor(CustomRule):
"""
Post processor to find file type based on all others found matches.
"""
priority = POST_PROCESS
dependency = Processors
properties = {'type': ['episode', 'movie']}
def when(self, matches, context): # pylint:disable=too-many-return-statements
option_type = context.get('type', None)
if option_type:
return option_type
episode = matches.named('episode')
season = matches.named('season')
absolute_episode = matches.named('absolute_episode')
episode_details = matches.named('episode_details')
if episode or season or episode_details or absolute_episode:
return 'episode'
film = matches.named('film')
if film:
return 'movie'
year = matches.named('year')
date = matches.named('date')
if date and not year:
return 'episode'
bonus = matches.named('bonus')
if bonus and not year:
return 'episode'
crc32 = matches.named('crc32')
anime_release_group = matches.named('release_group', lambda match: 'anime' in match.tags)
if crc32 and anime_release_group:
return 'episode'
return 'movie'
def then(self, matches, when_response, context):
_type(matches, when_response)

126
lib/guessit/rules/properties/video_codec.py Normal file
View File

@@ -0,0 +1,126 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
video_codec and video_profile property
"""
from rebulk import Rebulk, Rule, RemoveMatch
from rebulk.remodule import re
from ..common import dash
from ..common.pattern import is_disabled
from ..common.validators import seps_after, seps_before, seps_surround
def video_codec(config): # pylint:disable=unused-argument
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk()
rebulk = rebulk.regex_defaults(flags=re.IGNORECASE, abbreviations=[dash]).string_defaults(ignore_case=True)
rebulk.defaults(name="video_codec",
tags=['source-suffix', 'streaming_service.suffix'],
disabled=lambda context: is_disabled(context, 'video_codec'))
rebulk.regex(r'Rv\d{2}', value='RealVideo')
rebulk.regex('Mpe?g-?2', '[hx]-?262', value='MPEG-2')
rebulk.string("DVDivX", "DivX", value="DivX")
rebulk.string('XviD', value='Xvid')
rebulk.regex('VC-?1', value='VC-1')
rebulk.string('VP7', value='VP7')
rebulk.string('VP8', 'VP80', value='VP8')
rebulk.string('VP9', value='VP9')
rebulk.regex('[hx]-?263', value='H.263')
rebulk.regex('[hx]-?264', '(MPEG-?4)?AVC(?:HD)?', value='H.264')
rebulk.regex('[hx]-?265', 'HEVC', value='H.265')
rebulk.regex('(?P<video_codec>hevc)(?P<color_depth>10)', value={'video_codec': 'H.265', 'color_depth': '10-bit'},
tags=['video-codec-suffix'], children=True)
# http://blog.mediacoderhq.com/h264-profiles-and-levels/
# https://en.wikipedia.org/wiki/H.264/MPEG-4_AVC
rebulk.defaults(clear=True,
name="video_profile",
validator=seps_surround,
disabled=lambda context: is_disabled(context, 'video_profile'))
rebulk.string('BP', value='Baseline', tags='video_profile.rule')
rebulk.string('XP', 'EP', value='Extended', tags='video_profile.rule')
rebulk.string('MP', value='Main', tags='video_profile.rule')
rebulk.string('HP', 'HiP', value='High', tags='video_profile.rule')
# https://en.wikipedia.org/wiki/Scalable_Video_Coding
rebulk.string('SC', 'SVC', value='Scalable Video Coding', tags='video_profile.rule')
# https://en.wikipedia.org/wiki/AVCHD
rebulk.regex('AVC(?:HD)?', value='Advanced Video Codec High Definition', tags='video_profile.rule')
# https://en.wikipedia.org/wiki/H.265/HEVC
rebulk.string('HEVC', value='High Efficiency Video Coding', tags='video_profile.rule')
rebulk.regex('Hi422P', value='High 4:2:2')
rebulk.regex('Hi444PP', value='High 4:4:4 Predictive')
rebulk.regex('Hi10P?', value='High 10') # no profile validation is required
rebulk.string('DXVA', value='DXVA', name='video_api',
disabled=lambda context: is_disabled(context, 'video_api'))
rebulk.defaults(clear=True,
name='color_depth',
validator=seps_surround,
disabled=lambda context: is_disabled(context, 'color_depth'))
rebulk.regex('12.?bits?', value='12-bit')
rebulk.regex('10.?bits?', 'YUV420P10', 'Hi10P?', value='10-bit')
rebulk.regex('8.?bits?', value='8-bit')
rebulk.rules(ValidateVideoCodec, VideoProfileRule)
return rebulk
class ValidateVideoCodec(Rule):
"""
Validate video_codec with source property or separated
"""
priority = 64
consequence = RemoveMatch
def enabled(self, context):
return not is_disabled(context, 'video_codec')
def when(self, matches, context):
ret = []
for codec in matches.named('video_codec'):
if not seps_before(codec) and \
not matches.at_index(codec.start - 1, lambda match: 'video-codec-prefix' in match.tags):
ret.append(codec)
continue
if not seps_after(codec) and \
not matches.at_index(codec.end + 1, lambda match: 'video-codec-suffix' in match.tags):
ret.append(codec)
continue
return ret
class VideoProfileRule(Rule):
"""
Rule to validate video_profile
"""
consequence = RemoveMatch
def enabled(self, context):
return not is_disabled(context, 'video_profile')
def when(self, matches, context):
profile_list = matches.named('video_profile', lambda match: 'video_profile.rule' in match.tags)
ret = []
for profile in profile_list:
codec = matches.at_span(profile.span, lambda match: match.name == 'video_codec', 0)
if not codec:
codec = matches.previous(profile, lambda match: match.name == 'video_codec')
if not codec:
codec = matches.next(profile, lambda match: match.name == 'video_codec')
if not codec:
ret.append(profile)
return ret

110
lib/guessit/rules/properties/website.py Normal file
View File

@@ -0,0 +1,110 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Website property.
"""
# from pkg_resources import resource_stream # @UnresolvedImport
import os
from rebulk.remodule import re
from rebulk import Rebulk, Rule, RemoveMatch
from ..common import seps
from ..common.formatters import cleanup
from ..common.pattern import is_disabled
from ..common.validators import seps_surround
from ...reutils import build_or_pattern
def website(config):
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk(disabled=lambda context: is_disabled(context, 'website'))
rebulk = rebulk.regex_defaults(flags=re.IGNORECASE).string_defaults(ignore_case=True)
rebulk.defaults(name="website")
with open(os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(__file__))), 'tlds-alpha-by-domain.txt')) as tld_file:
tlds = [
tld.strip().decode('utf-8')
for tld in tld_file.readlines()
if b'--' not in tld
][1:] # All registered domain extension
safe_tlds = config['safe_tlds'] # For sure a website extension
safe_subdomains = config['safe_subdomains'] # For sure a website subdomain
safe_prefix = config['safe_prefixes'] # Those words before a tlds are sure
website_prefixes = config['prefixes']
rebulk.regex(r'(?:[^a-z0-9]|^)((?:'+build_or_pattern(safe_subdomains) +
r'\.)+(?:[a-z-]+\.)+(?:'+build_or_pattern(tlds) +
r'))(?:[^a-z0-9]|$)',
children=True)
rebulk.regex(r'(?:[^a-z0-9]|^)((?:'+build_or_pattern(safe_subdomains) +
r'\.)*[a-z-]+\.(?:'+build_or_pattern(safe_tlds) +
r'))(?:[^a-z0-9]|$)',
safe_subdomains=safe_subdomains, safe_tlds=safe_tlds, children=True)
rebulk.regex(r'(?:[^a-z0-9]|^)((?:'+build_or_pattern(safe_subdomains) +
r'\.)*[a-z-]+\.(?:'+build_or_pattern(safe_prefix) +
r'\.)+(?:'+build_or_pattern(tlds) +
r'))(?:[^a-z0-9]|$)',
safe_subdomains=safe_subdomains, safe_prefix=safe_prefix, tlds=tlds, children=True)
rebulk.string(*website_prefixes,
validator=seps_surround, private=True, tags=['website.prefix'])
class PreferTitleOverWebsite(Rule):
"""
If found match is more likely a title, remove website.
"""
consequence = RemoveMatch
@staticmethod
def valid_followers(match):
"""
Validator for next website matches
"""
return match.named('season', 'episode', 'year')
def when(self, matches, context):
to_remove = []
for website_match in matches.named('website'):
safe = False
for safe_start in safe_subdomains + safe_prefix:
if website_match.value.lower().startswith(safe_start):
safe = True
break
if not safe:
suffix = matches.next(website_match, PreferTitleOverWebsite.valid_followers, 0)
if suffix:
group = matches.markers.at_match(website_match, lambda marker: marker.name == 'group', 0)
if not group:
to_remove.append(website_match)
return to_remove
rebulk.rules(PreferTitleOverWebsite, ValidateWebsitePrefix)
return rebulk
class ValidateWebsitePrefix(Rule):
"""
Validate website prefixes
"""
priority = 64
consequence = RemoveMatch
def when(self, matches, context):
to_remove = []
for prefix in matches.tagged('website.prefix'):
website_match = matches.next(prefix, predicate=lambda match: match.name == 'website', index=0)
if (not website_match or
matches.holes(prefix.end, website_match.start,
formatter=cleanup, seps=seps, predicate=lambda match: match.value)):
to_remove.append(prefix)
return to_remove

3
lib/guessit/test/__init__.py Normal file
View File

@@ -0,0 +1,3 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# pylint: disable=no-self-use, pointless-statement, missing-docstring, invalid-name

1
lib/guessit/test/config/dummy.txt Normal file
View File

@@ -0,0 +1 @@
Not a configuration file

4
lib/guessit/test/config/test.json Normal file
View File

@@ -0,0 +1,4 @@
{
"expected_title": ["The 100", "OSS 117"],
"yaml": false
}

4
lib/guessit/test/config/test.yaml Normal file
View File

@@ -0,0 +1,4 @@
expected_title:
- The 100
- OSS 117
yaml: True

4
lib/guessit/test/config/test.yml Normal file
View File

@@ -0,0 +1,4 @@
expected_title:
- The 100
- OSS 117
yaml: True

335
lib/guessit/test/enable_disable_properties.yml Normal file
View File

@@ -0,0 +1,335 @@
? vorbis
: options: --exclude audio_codec
-audio_codec: Vorbis
? DTS-ES
: options: --exclude audio_profile
audio_codec: DTS
-audio_profile: Extended Surround
? DTS.ES
: options: --include audio_codec
audio_codec: DTS
-audio_profile: Extended Surround
? 5.1
? 5ch
? 6ch
: options: --exclude audio_channels
-audio_channels: '5.1'
? Movie Title-x01-Other Title.mkv
? Movie Title-x01-Other Title
? directory/Movie Title-x01-Other Title/file.mkv
: options: --exclude bonus
-bonus: 1
-bonus_title: Other Title
? Title-x02-Bonus Title.mkv
: options: --include bonus
bonus: 2
-bonus_title: Other Title
? cd 1of3
: options: --exclude cd
-cd: 1
-cd_count: 3
? This.is.Us
: options: --exclude country
title: This is Us
-country: US
? 2015.01.31
: options: --exclude date
year: 2015
-date: 2015-01-31
? Something 2 mar 2013)
: options: --exclude date
-date: 2013-03-02
? 2012 2009 S01E02 2015 # If no year is marked, the second one is guessed.
: options: --exclude year
-year: 2009
? Director's cut
: options: --exclude edition
-edition: Director's Cut
? 2x5
? 2X5
? 02x05
? 2X05
? 02x5
? S02E05
? s02e05
? s02e5
? s2e05
? s02ep05
? s2EP5
: options: --exclude season
-season: 2
-episode: 5
? 2x6
? 2X6
? 02x06
? 2X06
? 02x6
? S02E06
? s02e06
? s02e6
? s2e06
? s02ep06
? s2EP6
: options: --exclude episode
-season: 2
-episode: 6
? serie Season 2 other
: options: --exclude season
-season: 2
? Some Dummy Directory/S02 Some Series/E01-Episode title.mkv
: options: --exclude episode_title
-episode_title: Episode title
season: 2
episode: 1
? Another Dummy Directory/S02 Some Series/E01-Episode title.mkv
: options: --include season --include episode
-episode_title: Episode title
season: 2
episode: 1
# pattern contains season and episode: it wont work enabling only one
? Some Series S03E01E02
: options: --include episode
-season: 3
-episode: [1, 2]
# pattern contains season and episode: it wont work enabling only one
? Another Series S04E01E02
: options: --include season
-season: 4
-episode: [1, 2]
? Show.Name.Season.4.Episode.1
: options: --include episode
-season: 4
episode: 1
? Another.Show.Name.Season.4.Episode.1
: options: --include season
season: 4
-episode: 1
? Some Series S01 02 03
: options: --exclude season
-season: [1, 2, 3]
? Some Series E01 02 04
: options: --exclude episode
-episode: [1, 2, 4]
? A very special episode s06 special
: options: -t episode --exclude episode_details
season: 6
-episode_details: Special
? S01D02.3-5-GROUP
: options: --exclude disc
-season: 1
-disc: [2, 3, 4, 5]
-episode: [2, 3, 4, 5]
? S01D02&4-6&8
: options: --exclude season
-season: 1
-disc: [2, 4, 5, 6, 8]
-episode: [2, 4, 5, 6, 8]
? Film Title-f01-Series Title.mkv
: options: --exclude film
-film: 1
-film_title: Film Title
? Another Film Title-f01-Series Title.mkv
: options: --exclude film_title
film: 1
-film_title: Film Title
? English
? .ENG.
: options: --exclude language
-language: English
? SubFrench
? SubFr
? STFr
: options: --exclude subtitle_language
-language: French
-subtitle_language: French
? ST.FR
: options: --exclude subtitle_language
language: French
-subtitle_language: French
? ENG.-.sub.FR
? ENG.-.FR Sub
: options: --include language
language: [English, French]
-subtitle_language: French
? ENG.-.SubFR
: options: --include language
language: English
-subtitle_language: French
? ENG.-.FRSUB
? ENG.-.FRSUBS
? ENG.-.FR-SUBS
: options: --include subtitle_language
-language: English
subtitle_language: French
? DVD.Real.XViD
? DVD.fix.XViD
: options: --exclude other
-other: Fix
-proper_count: 1
? Part 3
? Part III
? Part Three
? Part Trois
? Part3
: options: --exclude part
-part: 3
? Some.Title.XViD-by.Artik[SEDG].avi
: options: --exclude release_group
-release_group: Artik[SEDG]
? "[ABC] Some.Title.avi"
? some/folder/[ABC]Some.Title.avi
: options: --exclude release_group
-release_group: ABC
? 360p
? 360px
? "360"
? +500x360
: options: --exclude screen_size
-screen_size: 360p
? 640x360
: options: --exclude aspect_ratio
screen_size: 360p
-aspect_ratio: 1.778
? 8196x4320
: options: --exclude screen_size
-screen_size: 4320p
-aspect_ratio: 1.897
? 4.3gb
: options: --exclude size
-size: 4.3GB
? VhS_rip
? VHS.RIP
: options: --exclude source
-source: VHS
-other: Rip
? DVD.RIP
: options: --include other
-source: DVD
-other: Rip
? Title Only.avi
: options: --exclude title
-title: Title Only
? h265
? x265
? h.265
? x.265
? hevc
: options: --exclude video_codec
-video_codec: H.265
? hevc10
: options: --include color_depth
-video_codec: H.265
-color_depth: 10-bit
? HEVC-YUV420P10
: options: --include color_depth
-video_codec: H.265
color_depth: 10-bit
? h265-HP
: options: --exclude video_profile
video_codec: H.265
-video_profile: High
? House.of.Cards.2013.S02E03.1080p.NF.WEBRip.DD5.1.x264-NTb.mkv
? House.of.Cards.2013.S02E03.1080p.Netflix.WEBRip.DD5.1.x264-NTb.mkv
: options: --exclude streaming_service
-streaming_service: Netflix
? wawa.co.uk
: options: --exclude website
-website: wawa.co.uk
? movie.mp4
: options: --exclude mimetype
-mimetype: video/mp4
? another movie.mkv
: options: --exclude container
-container: mkv
? series s02e01
: options: --exclude type
-type: episode
? series s02e01
: options: --exclude type
-type: episode
? Hotel.Hell.S01E01.720p.DD5.1.448kbps-ALANiS
: options: --exclude audio_bit_rate
-audio_bit_rate: 448Kbps
? Katy Perry - Pepsi & Billboard Summer Beats Concert Series 2012 1080i HDTV 20 Mbps DD2.0 MPEG2-TrollHD.ts
: options: --exclude video_bit_rate
-video_bit_rate: 20Mbps
? "[Figmentos] Monster 34 - At the End of Darkness [781219F1].mkv"
: options: --exclude crc32
-crc32: 781219F1
? 1080p25
: options: --exclude frame_rate
screen_size: 1080p
-frame_rate: 25fps
? 1080p25
: options: --exclude screen_size
-screen_size: 1080p
-frame_rate: 25fps
? 1080p25
: options: --include frame_rate
-screen_size: 1080p
-frame_rate: 25fps
? 1080p 30fps
: options: --exclude screen_size
-screen_size: 1080p
frame_rate: 30fps

4693
lib/guessit/test/episodes.yml Normal file
View File

File diff suppressed because it is too large Load Diff

1786
lib/guessit/test/movies.yml Normal file
View File

File diff suppressed because it is too large Load Diff

3
lib/guessit/test/rules/__init__.py Normal file
View File

@@ -0,0 +1,3 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# pylint: disable=no-self-use, pointless-statement, missing-docstring, invalid-name

134
lib/guessit/test/rules/audio_codec.yml Normal file
View File

@@ -0,0 +1,134 @@
# Multiple input strings having same expected results can be chained.
# Use $ marker to check inputs that should not match results.
? +MP3
? +lame
? +lame3.12
? +lame3.100
: audio_codec: MP3
? +MP2
: audio_codec: MP2
? +DolbyDigital
? +DD
? +Dolby Digital
? +AC3
: audio_codec: Dolby Digital
? +DDP
? +DD+
? +EAC3
: audio_codec: Dolby Digital Plus
? +DolbyAtmos
? +Dolby Atmos
? +Atmos
? -Atmosphere
: audio_codec: Dolby Atmos
? +AAC
: audio_codec: AAC
? +Flac
: audio_codec: FLAC
? +DTS
: audio_codec: DTS
? +True-HD
? +trueHD
: audio_codec: Dolby TrueHD
? +True-HD51
? +trueHD51
: audio_codec: Dolby TrueHD
audio_channels: '5.1'
? +DTSHD
? +DTS HD
? +DTS-HD
: audio_codec: DTS-HD
? +DTS-HDma
? +DTSMA
: audio_codec: DTS-HD
audio_profile: Master Audio
? +AC3-hq
: audio_codec: Dolby Digital
audio_profile: High Quality
? +AAC-HE
: audio_codec: AAC
audio_profile: High Efficiency
? +AAC-LC
: audio_codec: AAC
audio_profile: Low Complexity
? +AAC2.0
? +AAC20
: audio_codec: AAC
audio_channels: '2.0'
? +7.1
? +7ch
? +8ch
: audio_channels: '7.1'
? +5.1
? +5ch
? +6ch
: audio_channels: '5.1'
? +2ch
? +2.0
? +stereo
: audio_channels: '2.0'
? +1ch
? +mono
: audio_channels: '1.0'
? DD5.1
? DD51
: audio_codec: Dolby Digital
audio_channels: '5.1'
? -51
: audio_channels: '5.1'
? DTS-HD.HRA
? DTSHD.HRA
? DTS-HD.HR
? DTSHD.HR
? -HRA
? -HR
: audio_codec: DTS-HD
audio_profile: High Resolution Audio
? DTSES
? DTS-ES
? -ES
: audio_codec: DTS
audio_profile: Extended Surround
? DD-EX
? DDEX
? -EX
: audio_codec: Dolby Digital
audio_profile: EX
? OPUS
: audio_codec: Opus
? Vorbis
: audio_codec: Vorbis
? PCM
: audio_codec: PCM
? LPCM
: audio_codec: LPCM

9
lib/guessit/test/rules/bonus.yml Normal file
View File

@@ -0,0 +1,9 @@
# Multiple input strings having same expected results can be chained.
# Use - marker to check inputs that should not match results.
? Movie Title-x01-Other Title.mkv
? Movie Title-x01-Other Title
? directory/Movie Title-x01-Other Title/file.mkv
: title: Movie Title
bonus_title: Other Title
bonus: 1

10
lib/guessit/test/rules/cds.yml Normal file
View File

@@ -0,0 +1,10 @@
# Multiple input strings having same expected results can be chained.
# Use - marker to check inputs that should not match results.
? cd 1of3
: cd: 1
cd_count: 3
? Some.Title-DVDRIP-x264-CDP
: cd: !!null
release_group: CDP
video_codec: H.264

467
lib/guessit/test/rules/common_words.yml Normal file
View File

@@ -0,0 +1,467 @@
? is
: title: is
? it
: title: it
? am
: title: am
? mad
: title: mad
? men
: title: men
? man
: title: man
? run
: title: run
? sin
: title: sin
? st
: title: st
? to
: title: to
? 'no'
: title: 'no'
? non
: title: non
? war
: title: war
? min
: title: min
? new
: title: new
? car
: title: car
? day
: title: day
? bad
: title: bad
? bat
: title: bat
? fan
: title: fan
? fry
: title: fry
? cop
: title: cop
? zen
: title: zen
? gay
: title: gay
? fat
: title: fat
? one
: title: one
? cherokee
: title: cherokee
? got
: title: got
? an
: title: an
? as
: title: as
? cat
: title: cat
? her
: title: her
? be
: title: be
? hat
: title: hat
? sun
: title: sun
? may
: title: may
? my
: title: my
? mr
: title: mr
? rum
: title: rum
? pi
: title: pi
? bb
: title: bb
? bt
: title: bt
? tv
: title: tv
? aw
: title: aw
? by
: title: by
? md
: other: Mic Dubbed
? mp
: title: mp
? cd
: title: cd
? in
: title: in
? ad
: title: ad
? ice
: title: ice
? ay
: title: ay
? at
: title: at
? star
: title: star
? so
: title: so
? he
: title: he
? do
: title: do
? ax
: title: ax
? mx
: title: mx
? bas
: title: bas
? de
: title: de
? le
: title: le
? son
: title: son
? ne
: title: ne
? ca
: title: ca
? ce
: title: ce
? et
: title: et
? que
: title: que
? mal
: title: mal
? est
: title: est
? vol
: title: vol
? or
: title: or
? mon
: title: mon
? se
: title: se
? je
: title: je
? tu
: title: tu
? me
: title: me
? ma
: title: ma
? va
: title: va
? au
: country: AU
? lu
: title: lu
? wa
: title: wa
? ga
: title: ga
? ao
: title: ao
? la
: title: la
? el
: title: el
? del
: title: del
? por
: title: por
? mar
: title: mar
? al
: title: al
? un
: title: un
? ind
: title: ind
? arw
: title: arw
? ts
: source: Telesync
? ii
: title: ii
? bin
: title: bin
? chan
: title: chan
? ss
: title: ss
? san
: title: san
? oss
: title: oss
? iii
: title: iii
? vi
: title: vi
? ben
: title: ben
? da
: title: da
? lt
: title: lt
? ch
: title: ch
? sr
: title: sr
? ps
: title: ps
? cx
: title: cx
? vo
: title: vo
? mkv
: container: mkv
? avi
: container: avi
? dmd
: title: dmd
? the
: title: the
? dis
: title: dis
? cut
: title: cut
? stv
: title: stv
? des
: title: des
? dia
: title: dia
? and
: title: and
? cab
: title: cab
? sub
: title: sub
? mia
: title: mia
? rim
: title: rim
? las
: title: las
? une
: title: une
? par
: title: par
? srt
: container: srt
? ano
: title: ano
? toy
: title: toy
? job
: title: job
? gag
: title: gag
? reel
: title: reel
? www
: title: www
? for
: title: for
? ayu
: title: ayu
? csi
: title: csi
? ren
: title: ren
? moi
: title: moi
? sur
: title: sur
? fer
: title: fer
? fun
: title: fun
? two
: title: two
? big
: title: big
? psy
: title: psy
? air
: title: air
? brazil
: title: brazil
? jordan
: title: jordan
? bs
: title: bs
? kz
: title: kz
? gt
: title: gt
? im
: title: im
? pt
: language: pt
? scr
: title: scr
? sd
: title: sd
? hr
: other: High Resolution

13
lib/guessit/test/rules/country.yml Normal file
View File

@@ -0,0 +1,13 @@
# Multiple input strings having same expected results can be chained.
# Use $ marker to check inputs that should not match results.
? Us.this.is.title
? this.is.title.US
: country: US
title: this is title
? This.is.Us
: title: This is Us
? This.Is.Us
: options: --no-default-config
title: This Is Us

50
lib/guessit/test/rules/date.yml Normal file
View File

@@ -0,0 +1,50 @@
# Multiple input strings having same expected results can be chained.
# Use - marker to check inputs that should not match results.
? +09.03.08
? +09.03.2008
? +2008.03.09
: date: 2008-03-09
? +31.01.15
? +31.01.2015
? +15.01.31
? +2015.01.31
: date: 2015-01-31
? +01.02.03
: date: 2003-02-01
? +01.02.03
: options: --date-year-first
date: 2001-02-03
? +01.02.03
: options: --date-day-first
date: 2003-02-01
? 1919
? 2030
: !!map {}
? 2029
: year: 2029
? (1920)
: year: 1920
? 2012
: year: 2012
? 2011 2013 (2012) (2015) # first marked year is guessed.
: title: "2011 2013"
year: 2012
? 2012 2009 S01E02 2015 # If no year is marked, the second one is guessed.
: title: "2012"
year: 2009
episode_title: "2015"
? Something 2 mar 2013)
: title: Something
date: 2013-03-02
type: episode

63
lib/guessit/test/rules/edition.yml Normal file
View File

@@ -0,0 +1,63 @@
# Multiple input strings having same expected results can be chained.
# Use - marker to check inputs that should not match results.
? Director's cut
? Edition Director's cut
: edition: Director's Cut
? Collector
? Collector Edition
? Edition Collector
: edition: Collector
? Special Edition
? Edition Special
? -Special
: edition: Special
? Criterion Edition
? Edition Criterion
? CC
? -Criterion
: edition: Criterion
? Deluxe
? Deluxe Edition
? Edition Deluxe
: edition: Deluxe
? Super Movie Alternate XViD
? Super Movie Alternative XViD
? Super Movie Alternate Cut XViD
? Super Movie Alternative Cut XViD
: edition: Alternative Cut
? ddc
: edition: Director's Definitive Cut
? IMAX
? IMAX Edition
: edition: IMAX
? ultimate edition
? -ultimate
: edition: Ultimate
? ultimate collector edition
? ultimate collector's edition
? ultimate collectors edition
? -collectors edition
? -ultimate edition
: edition: [Ultimate, Collector]
? ultimate collectors edition dc
: edition: [Ultimate, Collector, Director's Cut]
? fan edit
? fan edition
? fan collection
: edition: Fan
? ultimate fan edit
? ultimate fan edition
? ultimate fan collection
: edition: [Ultimate, Fan]

331
lib/guessit/test/rules/episodes.yml Normal file
View File

@@ -0,0 +1,331 @@
# Multiple input strings having same expected results can be chained.
# Use $ marker to check inputs that should not match results.
? +2x5
? +2X5
? +02x05
? +2X05
? +02x5
? S02E05
? s02e05
? s02e5
? s2e05
? s02ep05
? s2EP5
? -s03e05
? -s02e06
? -3x05
? -2x06
: season: 2
episode: 5
? "+0102"
? "+102"
: season: 1
episode: 2
? "0102 S03E04"
? "S03E04 102"
: season: 3
episode: 4
? +serie Saison 2 other
? +serie Season 2 other
? +serie Saisons 2 other
? +serie Seasons 2 other
? +serie Season Two other
? +serie Season II other
: season: 2
? Some Series.S02E01.Episode.title.mkv
? Some Series/Season 02/E01-Episode title.mkv
? Some Series/Season 02/Some Series-E01-Episode title.mkv
? Some Dummy Directory/Season 02/Some Series-E01-Episode title.mkv
? -Some Dummy Directory/Season 02/E01-Episode title.mkv
? Some Series/Unsafe Season 02/Some Series-E01-Episode title.mkv
? -Some Series/Unsafe Season 02/E01-Episode title.mkv
? Some Series/Season 02/E01-Episode title.mkv
? Some Series/ Season 02/E01-Episode title.mkv
? Some Dummy Directory/Some Series S02/E01-Episode title.mkv
? Some Dummy Directory/S02 Some Series/E01-Episode title.mkv
: title: Some Series
episode_title: Episode title
season: 2
episode: 1
? Some Series.S02E01.mkv
? Some Series/Season 02/E01.mkv
? Some Series/Season 02/Some Series-E01.mkv
? Some Dummy Directory/Season 02/Some Series-E01.mkv
? -Some Dummy Directory/Season 02/E01.mkv
? Some Series/Unsafe Season 02/Some Series-E01.mkv
? -Some Series/Unsafe Season 02/E01.mkv
? Some Series/Season 02/E01.mkv
? Some Series/ Season 02/E01.mkv
? Some Dummy Directory/Some Series S02/E01-AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA.mkv
: title: Some Series
season: 2
episode: 1
? Some Series S03E01E02
: title: Some Series
season: 3
episode: [1, 2]
? Some Series S01S02S03
? Some Series S01-02-03
? Some Series S01 S02 S03
? Some Series S01 02 03
: title: Some Series
season: [1, 2, 3]
? Some Series E01E02E03
? Some Series E01-02-03
? Some Series E01-03
? Some Series E01 E02 E03
? Some Series E01 02 03
: title: Some Series
episode: [1, 2, 3]
? Some Series E01E02E04
? Some Series E01 E02 E04
? Some Series E01 02 04
: title: Some Series
episode: [1, 2, 4]
? Some Series E01-02-04
? Some Series E01-04
? Some Series E01-04
: title: Some Series
episode: [1, 2, 3, 4]
? Some Series E01-02-E04
: title: Some Series
episode: [1, 2, 3, 4]
? Episode 3
? -Episode III
: episode: 3
? Episode 3
? Episode III
: options: -t episode
episode: 3
? -A very special movie
: episode_details: Special
? -A very special episode
: options: -t episode
episode_details: Special
? A very special episode s06 special
: options: -t episode
title: A very special episode
episode_details: Special
? 12 Monkeys\Season 01\Episode 05\12 Monkeys - S01E05 - The Night Room.mkv
: container: mkv
title: 12 Monkeys
episode: 5
season: 1
? S03E02.X.1080p
: episode: 2
screen_size: 1080p
season: 3
? Something 1 x 2-FlexGet
: options: -t episode
title: Something
season: 1
episode: 2
episode_title: FlexGet
? Show.Name.-.Season.1.to.3.-.Mp4.1080p
? Show.Name.-.Season.1~3.-.Mp4.1080p
? Show.Name.-.Saison.1.a.3.-.Mp4.1080p
: container: mp4
screen_size: 1080p
season:
- 1
- 2
- 3
title: Show Name
? Show.Name.Season.1.3&5.HDTV.XviD-GoodGroup[SomeTrash]
? Show.Name.Season.1.3 and 5.HDTV.XviD-GoodGroup[SomeTrash]
: source: HDTV
release_group: GoodGroup[SomeTrash]
season:
- 1
- 3
- 5
title: Show Name
type: episode
video_codec: Xvid
? Show.Name.Season.1.2.3-5.HDTV.XviD-GoodGroup[SomeTrash]
? Show.Name.Season.1.2.3~5.HDTV.XviD-GoodGroup[SomeTrash]
? Show.Name.Season.1.2.3 to 5.HDTV.XviD-GoodGroup[SomeTrash]
: source: HDTV
release_group: GoodGroup[SomeTrash]
season:
- 1
- 2
- 3
- 4
- 5
title: Show Name
type: episode
video_codec: Xvid
? The.Get.Down.S01EP01.FRENCH.720p.WEBRIP.XVID-STR
: episode: 1
source: Web
other: Rip
language: fr
release_group: STR
screen_size: 720p
season: 1
title: The Get Down
type: episode
video_codec: Xvid
? My.Name.Is.Earl.S01E01-S01E21.SWE-SUB
: episode:
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
season: 1
subtitle_language: sv
title: My Name Is Earl
type: episode
? Show.Name.Season.4.Episodes.1-12
: episode:
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
season: 4
title: Show Name
type: episode
? show name s01.to.s04
: season:
- 1
- 2
- 3
- 4
title: show name
type: episode
? epi
: options: -t episode
title: epi
? Episode20
? Episode 20
: episode: 20
? Episode50
? Episode 50
: episode: 50
? Episode51
? Episode 51
: episode: 51
? Episode70
? Episode 70
: episode: 70
? Episode71
? Episode 71
: episode: 71
? S01D02.3-5-GROUP
: disc: [2, 3, 4, 5]
? S01D02&4-6&8
: disc: [2, 4, 5, 6, 8]
? Something.4x05-06
? Something - 4x05-06
? Something:4x05-06
? Something 4x05-06
? Something-4x05-06
: title: Something
season: 4
episode:
- 5
- 6
? Something.4x05-06
? Something - 4x05-06
? Something:4x05-06
? Something 4x05-06
? Something-4x05-06
: options: -T something
title: something
season: 4
episode:
- 5
- 6
? Colony 23/S01E01.Some.title.mkv
: title: Colony 23
season: 1
episode: 1
episode_title: Some title
? Show.Name.E02.2010.mkv
: options: -t episode
title: Show Name
year: 2010
episode: 2
? Show.Name.E02.S2010.mkv
: options: -t episode
title: Show Name
year: 2010
season: 2010
episode: 2
? Show.Name.E02.2010.mkv
: title: Show Name
year: 2010
episode: 2
? Show.Name.E02.S2010.mkv
: title: Show Name
year: 2010
season: 2010
episode: 2

9
lib/guessit/test/rules/film.yml Normal file
View File

@@ -0,0 +1,9 @@
# Multiple input strings having same expected results can be chained.
# Use - marker to check inputs that should not match results.
? Film Title-f01-Series Title.mkv
? Film Title-f01-Series Title
? directory/Film Title-f01-Series Title/file.mkv
: title: Series Title
film_title: Film Title
film: 1

47
lib/guessit/test/rules/language.yml Normal file
View File

@@ -0,0 +1,47 @@
# Multiple input strings having same expected results can be chained.
# Use - marker to check inputs that should not match results.
? +English
? .ENG.
: language: English
? +French
: language: French
? +SubFrench
? +SubFr
? +STFr
? ST.FR
: subtitle_language: French
? +ENG.-.sub.FR
? ENG.-.FR Sub
? +ENG.-.SubFR
? +ENG.-.FRSUB
? +ENG.-.FRSUBS
? +ENG.-.FR-SUBS
: language: English
subtitle_language: French
? "{Fr-Eng}.St{Fr-Eng}"
? "Le.Prestige[x264.{Fr-Eng}.St{Fr-Eng}.Chaps].mkv"
: language: [French, English]
subtitle_language: [French, English]
? +ENG.-.sub.SWE
? ENG.-.SWE Sub
? +ENG.-.SubSWE
? +ENG.-.SWESUB
? +ENG.-.sub.SV
? ENG.-.SV Sub
? +ENG.-.SubSV
? +ENG.-.SVSUB
: language: English
subtitle_language: Swedish
? The English Patient (1996)
: title: The English Patient
-language: english
? French.Kiss.1995.1080p
: title: French Kiss
-language: french

169
lib/guessit/test/rules/other.yml Normal file
View File

@@ -0,0 +1,169 @@
# Multiple input strings having same expected results can be chained.
# Use - marker to check inputs that should not match results.
? +DVDSCR
? +DVDScreener
? +DVD-SCR
? +DVD Screener
? +DVD AnythingElse Screener
? -DVD AnythingElse SCR
: other: Screener
? +AudioFix
? +AudioFixed
? +Audio Fix
? +Audio Fixed
: other: Audio Fixed
? +SyncFix
? +SyncFixed
? +Sync Fix
? +Sync Fixed
: other: Sync Fixed
? +DualAudio
? +Dual Audio
: other: Dual Audio
? +ws
? +WideScreen
? +Wide Screen
: other: Widescreen
# Fix must be surround by others properties to be matched.
? DVD.fix.XViD
? -DVD.Fix
? -Fix.XViD
: other: Fix
-proper_count: 1
? -DVD.BlablaBla.Fix.Blablabla.XVID
? -DVD.BlablaBla.Fix.XVID
? -DVD.Fix.Blablabla.XVID
: other: Fix
-proper_count: 1
? DVD.Real.PROPER.REPACK
: other: Proper
proper_count: 3
? Proper.720p
? +Repack
? +Rerip
: other: Proper
proper_count: 1
? XViD.Fansub
: other: Fan Subtitled
? XViD.Fastsub
: other: Fast Subtitled
? +Season Complete
? -Complete
: other: Complete
? R5
: other: Region 5
? RC
: other: Region C
? PreAir
? Pre Air
: other: Preair
? Screener
: other: Screener
? Remux
: other: Remux
? 3D.2019
: other: 3D
? HD
: other: HD
? FHD
? FullHD
? Full HD
: other: Full HD
? UHD
? Ultra
? UltraHD
? Ultra HD
: other: Ultra HD
? mHD # ??
? HDLight
: other: Micro HD
? HQ
: other: High Quality
? hr
: other: High Resolution
? PAL
: other: PAL
? SECAM
: other: SECAM
? NTSC
: other: NTSC
? LDTV
: other: Low Definition
? LD
: other: Line Dubbed
? MD
: other: Mic Dubbed
? -The complete movie
: other: Complete
? +The complete movie
: title: The complete movie
? +AC3-HQ
: audio_profile: High Quality
? Other-HQ
: other: High Quality
? reenc
? re-enc
? re-encoded
? reencoded
: other: Reencoded
? CONVERT XViD
: other: Converted
? +HDRIP # it's a Rip from non specified HD source
: other: [HD, Rip]
? SDR
: other: Standard Dynamic Range
? HDR
? HDR10
? -HDR100
: other: HDR10
? BT2020
? BT.2020
? -BT.20200
? -BT.2021
: other: BT.2020
? Upscaled
? Upscale
: other: Upscaled

Some files were not shown because too many files have changed in this diff Show More