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
def date():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().defaults(validator=seps_surround)
rebulk.regex(
r"\d{4}", name="year", formatter=int, validator=lambda match: seps_surround(match) and valid_year(match.value)
)
def date_functional(string, context):
"""
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]},
conflict_solver=lambda match, other: other if other.name in ["episode", "season"] else "__default__",
)
rebulk.rules(KeepMarkedYearInFilepart)
return rebulk
def part():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE, abbreviations=[dash], validator={'__parent__': seps_surround})
prefixes = ['pt', 'part']
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': compose(validate_roman, lambda m: 0 < m.value < 100)})
return rebulk
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': compose(validate_roman, lambda m: 0 < m.value < 100)})
return rebulk
def cds():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
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
def film():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE)
rebulk.regex(r'f(\d{1,2})', name='film', private_parent=True, children=True, formatter=int)
rebulk.rules(FilmTitleRule)
return rebulk
def when(self, matches, context):
expected_rebulk = Rebulk().defaults(name='release_group')
for expected_group in context.get('expected_group'):
if expected_group.startswith('re:'):
expected_group = expected_group[3:]
expected_group = expected_group.replace(' ', '-')
expected_rebulk.regex(expected_group, abbreviations=[dash], flags=re.IGNORECASE)
else:
expected_rebulk.string(expected_group, ignore_case=True)
matches = expected_rebulk.matches(matches.input_string, context)
return matches
def part():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE, abbreviations=[dash], validator={'__parent__': seps_surround})
prefixes = ['pt', 'part']
rebulk.regex(build_or_pattern(prefixes) + r'-?(' + numeral + r')', prefixes=prefixes,
name='part', validate_all=True, private_parent=True, children=True, formatter=parse_numeral)
return rebulk
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
def size():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
def format_size(value):
"""Format size using uppercase and no space."""
return re.sub(r'(?<=\d)[.](?=[^\d])', '', value.upper())
rebulk = 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=format_size, tags=['release-group-prefix'])
return rebulk
def bonus():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE)
rebulk.regex(r'x(\d+)', name='bonus', private_parent=True, children=True, formatter=int,
validator={'__parent__': lambda match: seps_surround},
conflict_solver=lambda match, conflicting: match
if conflicting.name in ['video_codec', 'episode'] and 'bonus-conflict' not in conflicting.tags
else '__default__')
rebulk.rules(BonusTitleRule)
return rebulk
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)+'$', exts=nzb, tags=['extension', 'nzb'])
rebulk.defaults(name='container',
validator=seps_surround,
formatter=lambda s: s.lower(),
conflict_solver=lambda match, other: match
if other.name in ('source',
'video_codec') or other.name == 'container' and 'extension' in other.tags
else '__default__')
rebulk.string(*[sub for sub in subtitles if sub not in ('sub', 'ass')], tags=['subtitle'])
rebulk.string(*videos, tags=['video'])
rebulk.string(*torrent, tags=['torrent'])
rebulk.string(*nzb, tags=['nzb'])
return rebulk
def container():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE).string_defaults(ignore_case=True)
rebulk.defaults(name='container',
formatter=lambda value: value.strip(seps),
tags=['extension'],
conflict_solver=lambda match, other: other
if other.name in ['format', 'video_codec'] or
other.name == 'container' and 'extension' not in other.tags
else '__default__')
subtitles = ['srt', 'idx', 'sub', 'ssa', 'ass']
info = ['nfo']
videos = ['3g2', '3gp', '3gp2', 'asf', 'avi', 'divx', 'flv', 'm4v', 'mk2',
'mka', 'mkv', 'mov', 'mp4', 'mp4a', 'mpeg', 'mpg', 'ogg', 'ogm',
'ogv', 'qt', 'ra', 'ram', 'rm', 'ts', 'wav', 'webm', 'wma', 'wmv',
'iso', 'vob']
torrent = ['torrent']
nzb = ['nzb']
rebulk.regex(r'\.'+build_or_pattern(subtitles)+'$', 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(name='container',
validator=seps_surround,
formatter=lambda s: s.lower(),
conflict_solver=lambda match, other: match
if other.name in ['format',
'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']], tags=['subtitle'])
rebulk.string(*videos, tags=['video'])
rebulk.string(*torrent, tags=['torrent'])
rebulk.string(*nzb, tags=['nzb'])
return rebulk
def edition():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
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-edition', 'edition-collector', value='Collector Edition')
rebulk.regex('special-edition', 'edition-special', value='Special Edition',
conflict_solver=lambda match, other: other
if other.name == 'episode_details' and other.value == 'Special'
else '__default__')
rebulk.regex('criterion-edition', 'edition-criterion', value='Criterion Edition')
rebulk.regex('deluxe', 'deluxe-edition', 'edition-deluxe', value='Deluxe Edition')
rebulk.regex('director\'?s?-cut', 'director\'?s?-cut-edition', 'edition-director\'?s?-cut', value='Director\'s cut')
return rebulk
def crc():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
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: match
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
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__': lambda match: seps_surround},
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
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
def cds():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
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: match.value > 0, 'cd_count': lambda match: match.value > 0},
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: match.value > 0, 'cd_count': lambda match: match.value > 0},
formatter={'cd_count': int},
children=True,
private_parent=True,
properties={'cd': [None], 'cd_count': [None]})
return rebulk
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
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
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
def website():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE)
rebulk.defaults(name="website")
tlds = [l.strip().decode('utf-8')
for l in resource_stream('guessit', 'tlds-alpha-by-domain.txt').readlines()
if b'--' not in l][1:] # All registered domain extension
safe_tlds = ['com', 'org', 'net'] # For sure a website extension
safe_subdomains = ['www'] # For sure a website subdomain
safe_prefix = ['co', 'com', 'org', 'net'] # Those words before a tlds are sure
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)
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 any(name in ['season', 'episode', 'year'] for name in match.names)
def when(self, matches, context):
to_remove = []
for website_match in matches.named('website'):
suffix = matches.next(website_match, PreferTitleOverWebsite.valid_followers, 0)
if suffix:
to_remove.append(website_match)
return to_remove
rebulk.rules(PreferTitleOverWebsite)
return rebulk
def other():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
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='AudioFix')
rebulk.regex('Sync-?Fix', 'Sync-?Fixed', value='SyncFix')
rebulk.regex('Dual-?Audio', value='DualAudio')
rebulk.regex('ws', 'wide-?screen', value='WideScreen')
rebulk.string('Real',
'Fix',
'Fixed',
value='Proper',
tags=['has-neighbor-before', 'has-neighbor-after'])
rebulk.string('Proper', 'Repack', 'Rerip', value='Proper')
rebulk.string('Fansub', value='Fansub', tags='has-neighbor')
rebulk.string('Fastsub', value='Fastsub', 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__': compose(seps_surround, validate_complete)})
rebulk.string('R5', 'RC', value='R5')
rebulk.regex('Pre-?Air', value='Preair')
rebulk.regex('(?:PS-?)?Vita', value='PS Vita')
for value in ('Screener', 'Remux', 'Remastered', '3D', 'HD', 'mHD',
'HDLight', 'HQ', 'DDC', 'HR', 'PAL', 'SECAM', 'NTSC', 'CC',
'LD', 'MD', 'XXX'):
rebulk.string(value, value=value)
rebulk.string('LDTV', value='LD')
for value in ('Limited', 'Complete', 'Classic', 'Unrated', 'LiNE', 'Bonus',
'Trailer', 'FINAL', 'Retail', 'Uncut', 'Extended',
'Extended Cut'):
rebulk.string(value,
value=value,
tags=['has-neighbor', 'release-group-prefix'])
rebulk.string('VO', 'OV', value='OV', tags='has-neighbor')
rebulk.regex('Scr(?:eener)?',
value='Screener',
validator=None,
tags='other.validate.screener')
rebulk.rules(ValidateHasNeighbor, ValidateHasNeighborAfter,
ValidateHasNeighborBefore, ValidateScreenerRule,
ProperCountRule)
return rebulk
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-DL'})
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
def other():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
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('Real',
'Fix',
'Fixed',
value='Proper',
tags=['has-neighbor-before', 'has-neighbor-after'])
rebulk.string(
'Proper',
'Repack',
'Rerip',
'Dirfix',
'Nfofix',
'Prooffix',
value='Proper',
tags=['streaming_service.prefix', 'streaming_service.suffix'])
rebulk.regex('(?:Proof-?)?Sample-?Fix',
value='Proper',
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__': compose(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('(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', '3D', 'PAL', 'SECAM', 'NTSC', 'XXX'):
rebulk.string(value, value=value)
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(
'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', 'release-group-prefix'])
rebulk.regex('Read-?NFO', value='Read NFO')
rebulk.string('CONVERT', value='Converted', tags='has-neighbor')
rebulk.string('DOCU', 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.rules(RenameAnotherToOther, ValidateHasNeighbor,
ValidateHasNeighborAfter, ValidateHasNeighborBefore,
ValidateScreenerRule, ValidateMuxRule, ValidateHardcodedSubs,
ValidateStreamingServiceNeighbor, ProperCountRule)
return rebulk
def episodes():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
# pylint: disable=too-many-branches,too-many-statements,too-many-locals
rebulk = Rebulk()
rebulk.regex_defaults(flags=re.IGNORECASE).string_defaults(ignore_case=True)
rebulk.defaults(private_names=['episodeSeparator', 'seasonSeparator'])
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) > 100:
return True
seasons = matches.named('season')
if len(seasons) > 1 and abs(seasons[-1].value - seasons[-2].value) > 100:
return True
return False
rebulk.chain_defaults(chain_breaker=episodes_season_chain_breaker)
def season_episode_conflict_solver(match, other):
"""
Conflict solver for episode/season patterns
:param match:
:param other:
:return:
"""
if match.name in ['season', 'episode'] and other.name in ['screen_size', 'video_codec',
'audio_codec', 'audio_channels',
'container', 'date']:
return match
elif match.name in ['season', 'episode'] and other.name in ['season', 'episode'] \
and match.initiator != other.initiator:
if 'weak-episode' in match.tags:
return match
if 'weak-episode' in other.tags:
return other
if 'x' in match.initiator.raw.lower():
return match
if 'x' in other.initiator.raw.lower():
return other
return '__default__'
season_episode_seps = []
season_episode_seps.extend(seps)
season_episode_seps.extend(['x', 'X', 'e', 'E'])
season_words = ['season', 'saison', 'serie', 'seasons', 'saisons', 'series']
episode_words = ['episode', 'episodes', 'eps', 'ep']
of_words = ['of', 'sur']
all_words = ['All']
season_markers = ["S"]
season_ep_markers = ["x"]
episode_markers = ["xE", "Ex", "EP", "E", "x"]
range_separators = ['-', '~', 'to', 'a']
weak_discrete_separators = list(sep for sep in seps if sep not in range_separators)
strong_discrete_separators = ['+', '&', 'and', 'et']
discrete_separators = strong_discrete_separators + weak_discrete_separators
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(implicit=True)
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.raw not in range_separators and separator.raw in weak_discrete_separators:
if not current_match.value - previous_match.value == 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')
# S01E02, 01x02, S01S02S03
rebulk.chain(formatter={'season': int, 'episode': int},
tags=['SxxExx'],
abbreviations=[alt_dash],
children=True,
private_parent=True,
validate_all=True,
validator={'__parent__': ordering_validator},
conflict_solver=season_episode_conflict_solver) \
.regex(build_or_pattern(season_markers) + r'(?P<season>\d+)@?' +
build_or_pattern(episode_markers) + r'@?(?P<episode>\d+)',
validate_all=True,
validator={'__parent__': seps_before}).repeater('+') \
.regex(build_or_pattern(episode_markers + discrete_separators + range_separators,
name='episodeSeparator',
escape=True) +
r'(?P<episode>\d+)').repeater('*') \
.chain() \
.regex(r'(?P<season>\d+)@?' +
build_or_pattern(season_ep_markers) +
r'@?(?P<episode>\d+)',
validate_all=True,
validator={'__parent__': seps_before}) \
.chain() \
.regex(r'(?P<season>\d+)@?' +
build_or_pattern(season_ep_markers) +
r'@?(?P<episode>\d+)',
validate_all=True,
validator={'__parent__': seps_before}) \
.regex(build_or_pattern(season_ep_markers + discrete_separators + range_separators,
name='episodeSeparator',
escape=True) +
r'(?P<episode>\d+)').repeater('*') \
.chain() \
.regex(build_or_pattern(season_markers) + r'(?P<season>\d+)',
validate_all=True,
validator={'__parent__': seps_before}) \
.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', 'Bonus', 'Omake', 'Ova', 'Oav', 'Pilot', 'Unaired'):
rebulk.string(episode_detail, value=episode_detail, name='episode_details')
rebulk.regex(r'Extras?', name='episode_details', value='Extras')
rebulk.defaults(private_names=['episodeSeparator', 'seasonSeparator'],
validate_all=True, validator={'__parent__': seps_surround}, children=True, private_parent=True)
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.chain(abbreviations=[alt_dash],
formatter={'season': parse_numeral, 'count': parse_numeral},
validator={'__parent__': compose(seps_surround, ordering_validator),
'season': validate_roman,
'count': validate_roman}) \
.defaults(validator=None) \
.regex(build_or_pattern(season_words) + '@?(?P<season>' + numeral + ')') \
.regex(r'' + build_or_pattern(of_words) + '@?(?P<count>' + numeral + ')').repeater('?') \
.regex(r'@?(?P<seasonSeparator>' +
build_or_pattern(range_separators + discrete_separators + ['@'], escape=True) +
r')@?(?P<season>\d+)').repeater('*')
rebulk.regex(build_or_pattern(episode_words) + r'-?(?P<episode>\d+)' +
r'(?:v(?P<version>\d+))?' +
r'(?:-?' + build_or_pattern(of_words) + r'-?(?P<count>\d+))?', # Episode 4
abbreviations=[dash], formatter=int,
disabled=lambda context: context.get('type') == 'episode')
rebulk.regex(build_or_pattern(episode_words) + r'-?(?P<episode>' + numeral + ')' +
r'(?:v(?P<version>\d+))?' +
r'(?:-?' + build_or_pattern(of_words) + r'-?(?P<count>\d+))?', # Episode 4
abbreviations=[dash],
validator={'episode': validate_roman},
formatter={'episode': parse_numeral, 'version': int, 'count': int},
disabled=lambda context: context.get('type') != 'episode')
rebulk.regex(r'S?(?P<season>\d+)-?(?:xE|Ex|E|x)-?(?P<other>' + build_or_pattern(all_words) + ')',
tags=['SxxExx'],
abbreviations=[dash],
validator=None,
formatter={'season': int, 'other': lambda match: 'Complete'})
rebulk.defaults(private_names=['episodeSeparator', 'seasonSeparator'], validate_all=True,
validator={'__parent__': seps_surround}, children=True, private_parent=True)
# 12, 13
rebulk.chain(tags=['bonus-conflict', 'weak-movie', 'weak-episode'], formatter={'episode': int, 'version': int}) \
.defaults(validator=None) \
.regex(r'(?P<episode>\d{2})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{2})').repeater('*')
# 012, 013
rebulk.chain(tags=['bonus-conflict', 'weak-movie', 'weak-episode'], formatter={'episode': int, 'version': int}) \
.defaults(validator=None) \
.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})').repeater('*')
# 112, 113
rebulk.chain(tags=['bonus-conflict', 'weak-movie', 'weak-episode'], formatter={'episode': int, 'version': int},
disabled=lambda context: not context.get('episode_prefer_number', False)) \
.defaults(validator=None) \
.regex(r'(?P<episode>\d{3,4})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{3,4})').repeater('*')
# 1, 2, 3
rebulk.chain(tags=['bonus-conflict', 'weak-movie', 'weak-episode'], formatter={'episode': int, 'version': int},
disabled=lambda context: context.get('type') != 'episode') \
.defaults(validator=None) \
.regex(r'(?P<episode>\d)') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{1,2})').repeater('*')
# e112, e113
# TODO: Enhance rebulk for validator to be used globally (season_episode_validator)
rebulk.chain(formatter={'episode': int, 'version': int}) \
.defaults(validator=None) \
.regex(r'e(?P<episode>\d{1,4})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>e|x|-)(?P<episode>\d{1,4})').repeater('*')
# ep 112, ep113, ep112, ep113
rebulk.chain(abbreviations=[dash], formatter={'episode': int, 'version': int}) \
.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})').repeater('*')
# 102, 0102
rebulk.chain(tags=['bonus-conflict', 'weak-movie', 'weak-episode', 'weak-duplicate'],
formatter={'season': int, 'episode': int, 'version': int},
conflict_solver=lambda match, other: match if other.name == 'year' else '__default__',
disabled=lambda context: context.get('episode_prefer_number', False)) \
.defaults(validator=None) \
.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})').repeater('*')
rebulk.regex(r'v(?P<version>\d+)', children=True, private_parent=True, formatter=int)
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) + '?',
abbreviations=[dash], children=True, private_parent=True, formatter=int)
rebulk.regex(r'Minisodes?', name='episode_format', value="Minisode")
# Harcoded movie to disable weak season/eps
rebulk.regex('OSS-?117',
abbreviations=[dash], name="hardcoded-movies", marker=True,
conflict_solver=lambda match, other: None)
rebulk.rules(EpisodeNumberSeparatorRange(range_separators),
SeasonSeparatorRange(range_separators), RemoveWeakIfMovie, RemoveWeakIfSxxExx,
RemoveWeakDuplicate, EpisodeDetailValidator, RemoveDetachedEpisodeNumber, VersionValidator,
CountValidator, EpisodeSingleDigitValidator)
return rebulk
def edition():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
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-edition',
'edition-collector',
value='Collector Edition')
rebulk.regex('special-edition',
'edition-special',
value='Special Edition',
conflict_solver=lambda match, other: other
if other.name == 'episode_details' and other.value ==
'Special' else '__default__')
rebulk.string('se', value='Special Edition', tags='has-neighbor')
rebulk.regex('criterion-edition',
'edition-criterion',
value='Criterion Edition')
rebulk.regex('deluxe',
'deluxe-edition',
'edition-deluxe',
value='Deluxe Edition')
rebulk.regex('limited',
'limited-edition',
value='Limited Edition',
tags=['has-neighbor', 'release-group-prefix'])
rebulk.regex(r'theatrical-cut',
r'theatrical-edition',
r'theatrical',
value='Theatrical Edition')
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'])
return rebulk
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(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(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
def video_codec():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(
flags=re.IGNORECASE,
abbreviations=[dash]).string_defaults(ignore_case=True)
rebulk.defaults(name="video_codec")
rebulk.regex(r"Rv\d{2}", value="Real")
rebulk.regex("Mpeg2", value="Mpeg2")
rebulk.regex("DVDivX", "DivX", value="DivX")
rebulk.regex("XviD", value="XviD")
rebulk.regex("[hx]-?264(?:-?AVC(HD)?)?",
"MPEG-?4(?:-?AVC(HD)?)",
"AVCHD",
value="h264")
rebulk.regex("[hx]-?265(?:-?HEVC)?", "HEVC", value="h265")
# http://blog.mediacoderhq.com/h264-profiles-and-levels/
# http://fr.wikipedia.org/wiki/H.264
rebulk.defaults(name="video_profile", validator=seps_surround)
rebulk.regex('10.?bits?', 'Hi10P', value='10bit')
rebulk.regex('8.?bits?', value='8bit')
rebulk.string('BP', value='BP', tags='video_profile.rule')
rebulk.string('XP', 'EP', value='XP', tags='video_profile.rule')
rebulk.string('MP', value='MP', tags='video_profile.rule')
rebulk.string('HP', 'HiP', value='HP', tags='video_profile.rule')
rebulk.regex('Hi422P', value='Hi422P', tags='video_profile.rule')
rebulk.regex('Hi444PP', value='Hi444PP', tags='video_profile.rule')
rebulk.string('DXVA', value='DXVA', name='video_api')
rebulk.rules(ValidateVideoCodec, VideoProfileRule)
return rebulk
def format_():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE, abbreviations=[dash])
rebulk.defaults(name="format",
tags=['video-codec-prefix', 'streaming_service.suffix'])
rebulk.regex("VHS", "VHS-?Rip", value="VHS")
rebulk.regex("CAM", "CAM-?Rip", "HD-?CAM", value="Cam")
rebulk.regex("TELESYNC", "TS", "HD-?TS", value="Telesync")
rebulk.regex("WORKPRINT", "WP", value="Workprint")
rebulk.regex("TELECINE", "TC", value="Telecine")
rebulk.regex("PPV", "PPV-?Rip", value="PPV") # Pay Per View
rebulk.regex("SD-?TV",
"SD-?TV-?Rip",
"Rip-?SD-?TV",
"TV-?Rip",
"Rip-?TV",
"TV-?(?=Dub)",
value="TV") # TV is too common to allow matching
rebulk.regex("DVB-?Rip", "DVB", "PD-?TV", value="DVB")
rebulk.regex(
"DVD",
"DVD-?Rip",
"VIDEO-?TS",
"DVD-?R(?:$|(?!E))", # "DVD-?R(?:$|^E)" => DVD-Real ...
"DVD-?9",
"DVD-?5",
value="DVD")
rebulk.regex("HD-?TV",
"TV-?RIP-?HD",
"HD-?TV-?RIP",
"HD-?RIP",
value="HDTV",
conflict_solver=lambda match, other: other
if other.name == 'other' else '__default__')
rebulk.regex("VOD", "VOD-?Rip", value="VOD")
rebulk.regex("WEB-?Rip", "WEB-?DL-?Rip", "WEB-?Cap", value="WEBRip")
rebulk.regex("WEB-?DL",
"WEB-?HD",
"WEB",
"DL-?WEB",
"DL(?=-?Mux)",
value="WEB-DL")
rebulk.regex("HD-?DVD-?Rip", "HD-?DVD", value="HD-DVD")
rebulk.regex("Blu-?ray(?:-?Rip)?",
"B[DR]",
"B[DR]-?Rip",
"BD[59]",
"BD25",
"BD50",
value="BluRay")
rebulk.regex("AHDTV", value="AHDTV")
rebulk.regex('UHD-?TV',
'UHD-?Rip',
value='UHDTV',
conflict_solver=lambda match, other: other
if other.name == 'other' else '__default__')
rebulk.regex("HDTC", value="HDTC")
rebulk.regex("DSR",
"DSR?-?Rip",
"SAT-?Rip",
"DTH",
"DTH-?Rip",
value="SATRip")
rebulk.rules(ValidateFormat)
return rebulk
def streaming_service():
"""Streaming service property.
:return:
:rtype: Rebulk
"""
rebulk = Rebulk().string_defaults(ignore_case=True).regex_defaults(flags=re.IGNORECASE, abbreviations=[dash])
rebulk.defaults(name='streaming_service', tags=['source-prefix'])
rebulk.string('AE', 'A&E', value='A&E')
rebulk.string('AMBC', value='ABC')
rebulk.string('AMC', value='AMC')
rebulk.string('AMZN', 'Amazon', 'AmazonPrime', value='Amazon Prime')
rebulk.regex('Amazon-Prime', value='Amazon Prime')
rebulk.string('AS', 'AdultSwim', value='Adult Swim')
rebulk.regex('Adult-Swim', value='Adult Swim')
rebulk.string('iP', 'BBCiPlayer', value='BBC iPlayer')
rebulk.regex('BBC-iPlayer', value='BBC iPlayer')
rebulk.string('CBS', value='CBS')
rebulk.string('CC', 'ComedyCentral', value='Comedy Central')
rebulk.regex('Comedy-Central', value='Comedy Central')
rebulk.string('CR', 'CrunchyRoll', value='Crunchy Roll')
rebulk.regex('Crunchy-Roll', value='Crunchy Roll')
rebulk.string('CW', 'TheCW', value='The CW')
rebulk.regex('The-CW', value='The CW')
rebulk.string('DISC', 'Discovery', value='Discovery')
rebulk.string('DIY', value='DIY Network')
rebulk.string('DSNY', 'Disney', value='Disney')
rebulk.string('EPIX', 'ePix', value='ePix')
rebulk.string('HBO', 'HBOGo', value='HBO Go')
rebulk.regex('HBO-Go', value='HBO Go')
rebulk.string('HIST', 'History', value='History')
rebulk.string('ID', value='Investigation Discovery')
rebulk.string('IFC', 'IFC', value='IFC')
rebulk.string('PBS', 'PBS', value='PBS')
rebulk.string('NATG', 'NationalGeographic', value='National Geographic')
rebulk.regex('National-Geographic', value='National Geographic')
rebulk.string('NBA', 'NBATV', value='NBA TV')
rebulk.regex('NBA-TV', value='NBA TV')
rebulk.string('NBC', value='NBC')
rebulk.string('NFL', value='NFL')
rebulk.string('NICK', 'Nickelodeon', value='Nickelodeon')
rebulk.string('NF', 'Netflix', value='Netflix')
rebulk.string('iTunes', 'iT', value='iTunes')
rebulk.string('RTE', value='RTÉ One')
rebulk.string('SESO', 'SeeSo', value='SeeSo')
rebulk.string('SPKE', 'SpikeTV', 'Spike TV', value='Spike TV')
rebulk.string('SYFY', 'Syfy', value='Syfy')
rebulk.string('TFOU', 'TFou', value='TFou')
rebulk.string('TLC', value='TLC')
rebulk.string('TV3', value='TV3 Ireland')
rebulk.string('TV4', value='TV4 Sweeden')
rebulk.string('TVL', 'TVLand', 'TV Land', value='TV Land')
rebulk.string('UFC', value='UFC')
rebulk.string('USAN', value='USA Network')
rebulk.rules(ValidateStreamingService)
return rebulk
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")
tlds = [
l.strip().decode('utf-8') for l in resource_stream(
'guessit', 'tlds-alpha-by-domain.txt').readlines()
if b'--' not in l
][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 any(name in ['season', 'episode', 'year']
for name in match.names)
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:
to_remove.append(website_match)
return to_remove
rebulk.rules(PreferTitleOverWebsite, ValidateWebsitePrefix)
return rebulk
def website():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE)
rebulk.defaults(name="website")
tlds = [
l.strip().decode('utf-8') for l in resource_stream(
'guessit', 'tlds-alpha-by-domain.txt').readlines()
if b'--' not in l
][1:] # All registered domain extension
safe_tlds = ['com', 'org', 'net'] # For sure a website extension
safe_subdomains = ['www'] # For sure a website subdomain
safe_prefix = ['co', 'com', 'org',
'net'] # Those words before a tlds are sure
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)
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 any(name in ['season', 'episode', 'year']
for name in match.names)
def when(self, matches, context):
to_remove = []
for website_match in matches.named('website'):
suffix = matches.next(website_match,
PreferTitleOverWebsite.valid_followers,
0)
if suffix:
to_remove.append(website_match)
return to_remove
rebulk.rules(PreferTitleOverWebsite)
return rebulk
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.defaults(name='source', tags=['video-codec-prefix', 'streaming_service.suffix'])
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' 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(ValidateSource, UltraHdBlurayRule)
return rebulk
def website():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE)
rebulk.defaults(name="website")
tlds = [l.strip().decode('utf-8')
for l in resource_stream('guessit', 'tlds-alpha-by-domain.txt').readlines()
if b'--' not in l][1:] # All registered domain extension
safe_tlds = ['com', 'org', 'net'] # For sure a website extension
safe_subdomains = ['www'] # For sure a website subdomain
safe_prefix = ['co', 'com', 'org', 'net'] # Those words before a tlds are sure
if REGEX_AVAILABLE:
rebulk.regex(r'(?:[^a-z0-9]|^)((?:\L<safe_subdomains>\.)+(?:[a-z-]+\.)+(?:\L<tlds>))(?:[^a-z0-9]|$)',
safe_subdomains=safe_subdomains, tlds=tlds, children=True)
rebulk.regex(r'(?:[^a-z0-9]|^)((?:\L<safe_subdomains>\.)*[a-z-]+\.(?:\L<safe_tlds>))(?:[^a-z0-9]|$)',
safe_subdomains=safe_subdomains, safe_tlds=safe_tlds, children=True)
rebulk.regex(
r'(?:[^a-z0-9]|^)((?:\L<safe_subdomains>\.)*[a-z-]+\.(?:\L<safe_prefix>\.)+(?:\L<tlds>))(?:[^a-z0-9]|$)',
safe_subdomains=safe_subdomains, safe_prefix=safe_prefix, tlds=tlds, children=True)
else:
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)
return rebulk
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(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(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
def format_():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE, abbreviations=[dash])
rebulk.defaults(name="format")
rebulk.regex("VHS", "VHS-?Rip", value="VHS")
rebulk.regex("CAM", "CAM-?Rip", "HD-?CAM", value="Cam")
rebulk.regex("TELESYNC", "TS", "HD-?TS", value="Telesync")
rebulk.regex("WORKPRINT", "WP", value="Workprint")
rebulk.regex("TELECINE", "TC", value="Telecine")
rebulk.regex("PPV", "PPV-?Rip", value="PPV") # Pay Per View
rebulk.regex(
"SD-?TV", "SD-?TV-?Rip", "Rip-?SD-?TV", "TV-?Rip", "Rip-?TV", value="TV"
) # TV is too common to allow matching
rebulk.regex("DVB-?Rip", "DVB", "PD-?TV", value="DVB")
rebulk.regex(
"DVD",
"DVD-?Rip",
"VIDEO-?TS",
"DVD-?R(?:$|(?!E))", # "DVD-?R(?:$|^E)" => DVD-Real ...
"DVD-?9",
"DVD-?5",
value="DVD",
)
rebulk.regex("HD-?TV", "TV-?RIP-?HD", "HD-?TV-?RIP", "HD-?RIP", value="HDTV")
rebulk.regex("VOD", "VOD-?Rip", value="VOD")
rebulk.regex("WEB-?Rip", "WEB-?DL-?Rip", "WEB-?Cap", value="WEBRip")
rebulk.regex("WEB-?DL", "WEB-?HD", "WEB", value="WEB-DL")
rebulk.regex("HD-?DVD-?Rip", "HD-?DVD", value="HD-DVD")
rebulk.regex("Blu-?ray(?:-?Rip)?", "B[DR]", "B[DR]-?Rip", "BD[59]", "BD25", "BD50", value="BluRay")
rebulk.regex("AHDTV", value="AHDTV")
rebulk.regex("HDTC", value="HDTC")
rebulk.regex("DSR", "DSR?-?Rip", "SAT-?Rip", "DTH", "DTH-?Rip", value="SATRip")
rebulk.rules(ValidateFormat)
return rebulk
def screen_size(config):
"""
Builder for rebulk object.
:param config: rule configuration
:type config: dict
:return: Created Rebulk object
:rtype: Rebulk
"""
interlaced = frozenset({res for res in config['interlaced']})
progressive = frozenset({res for res in 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
def other():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
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='AudioFix')
rebulk.regex('Sync-?Fix', 'Sync-?Fixed', value='SyncFix')
rebulk.regex('Dual-?Audio', value='DualAudio')
rebulk.regex('ws', 'wide-?screen', value='WideScreen')
rebulk.string('Real', 'Fix', 'Fixed', value='Proper', tags=['has-neighbor-before', 'has-neighbor-after'])
rebulk.string('Proper', 'Repack', 'Rerip', value='Proper')
rebulk.string('Fansub', value='Fansub', tags='has-neighbor')
rebulk.string('Fastsub', value='Fastsub', 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__': compose(seps_surround, validate_complete)})
rebulk.string('R5', 'RC', value='R5')
rebulk.regex('Pre-?Air', value='Preair')
rebulk.regex('(?:PS-?)?Vita', value='PS Vita')
for value in (
'Screener', 'Remux', 'Remastered', '3D', 'HD', 'mHD', 'HDLight', 'HQ', 'DDC', 'HR', 'PAL', 'SECAM', 'NTSC',
'CC', 'LD', 'MD', 'XXX'):
rebulk.string(value, value=value)
rebulk.string('LDTV', value='LD')
for value in ('Limited', 'Complete', 'Classic', 'Unrated', 'LiNE', 'Bonus', 'Trailer', 'FINAL', 'Retail', 'Uncut',
'Extended', 'Extended Cut'):
rebulk.string(value, value=value, tags=['has-neighbor', 'release-group-prefix'])
rebulk.string('VO', 'OV', value='OV', tags='has-neighbor')
rebulk.regex('Scr(?:eener)?', value='Screener', validator=None, tags='other.validate.screener')
rebulk.rules(ValidateHasNeighbor, ValidateHasNeighborAfter, ValidateHasNeighborBefore, ValidateScreenerRule,
ProperCountRule)
return rebulk
def website():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE)
rebulk.defaults(name="website")
tlds = [
l.strip().decode('utf-8') for l in resource_stream(
'guessit', 'tlds-alpha-by-domain.txt').readlines()
if b'--' not in l
][1:] # All registered domain extension
safe_tlds = ['com', 'org', 'net'] # For sure a website extension
safe_subdomains = ['www'] # For sure a website subdomain
safe_prefix = ['co', 'com', 'org',
'net'] # Those words before a tlds are sure
if REGEX_AVAILABLE:
rebulk.regex(
r'(?:[^a-z0-9]|^)((?:\L<safe_subdomains>\.)+(?:[a-z-]+\.)+(?:\L<tlds>))(?:[^a-z0-9]|$)',
safe_subdomains=safe_subdomains,
tlds=tlds,
children=True)
rebulk.regex(
r'(?:[^a-z0-9]|^)((?:\L<safe_subdomains>\.)*[a-z-]+\.(?:\L<safe_tlds>))(?:[^a-z0-9]|$)',
safe_subdomains=safe_subdomains,
safe_tlds=safe_tlds,
children=True)
rebulk.regex(
r'(?:[^a-z0-9]|^)((?:\L<safe_subdomains>\.)*[a-z-]+\.(?:\L<safe_prefix>\.)+(?:\L<tlds>))(?:[^a-z0-9]|$)',
safe_subdomains=safe_subdomains,
safe_prefix=safe_prefix,
tlds=tlds,
children=True)
else:
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)
return rebulk
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')
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE).string_defaults(
ignore_case=True)
rebulk.defaults(private_names=[
'episodeSeparator', 'seasonSeparator', 'episodeMarker', 'seasonMarker'
])
episode_max_range = config['episode_max_range']
season_max_range = config['season_max_range']
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
rebulk.chain_defaults(chain_breaker=episodes_season_chain_breaker)
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__'
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
max_range_gap = config['max_range_gap']
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.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')
# S01E02, 01x02, S01S02S03
rebulk.chain(formatter={'season': int, 'episode': int},
tags=['SxxExx'],
abbreviations=[alt_dash],
children=True,
private_parent=True,
validate_all=True,
validator={'__parent__': ordering_validator},
conflict_solver=season_episode_conflict_solver,
disabled=is_season_episode_disabled) \
.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+)',
validate_all=True,
validator={'__parent__': seps_before}).repeater('+') \
.regex(build_or_pattern(episode_markers + disc_markers + discrete_separators + range_separators,
name='episodeSeparator',
escape=True) +
r'(?P<episode>\d+)').repeater('*') \
.chain() \
.regex(r'(?P<season>\d+)@?' +
build_or_pattern(season_ep_markers, name='episodeMarker') +
r'@?(?P<episode>\d+)',
validate_all=True,
validator={'__parent__': seps_before}) \
.chain() \
.regex(r'(?P<season>\d+)@?' +
build_or_pattern(season_ep_markers, name='episodeMarker') +
r'@?(?P<episode>\d+)',
validate_all=True,
validator={'__parent__': seps_before}) \
.regex(build_or_pattern(season_ep_markers + discrete_separators + range_separators,
name='episodeSeparator',
escape=True) +
r'(?P<episode>\d+)').repeater('*') \
.chain() \
.regex(build_or_pattern(season_markers, name='seasonMarker') + r'(?P<season>\d+)',
validate_all=True,
validator={'__parent__': seps_before}) \
.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', 'Bonus', 'Pilot', 'Unaired', 'Final'):
rebulk.string(
episode_detail,
value=episode_detail,
name='episode_details',
disabled=lambda context: is_disabled(context, 'episode_details'))
rebulk.regex(
r'Extras?',
'Omake',
name='episode_details',
value='Extras',
disabled=lambda context: is_disabled(context, 'episode_details'))
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.defaults(private_names=[
'episodeSeparator', 'seasonSeparator', 'episodeMarker', 'seasonMarker'
],
validate_all=True,
validator={'__parent__': seps_surround},
children=True,
private_parent=True,
conflict_solver=season_episode_conflict_solver)
rebulk.chain(abbreviations=[alt_dash],
formatter={'season': parse_numeral, 'count': parse_numeral},
validator={'__parent__': compose(seps_surround, ordering_validator),
'season': validate_roman,
'count': validate_roman},
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'season')) \
.defaults(validator=None) \
.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.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
abbreviations=[dash],
formatter={
'episode': int,
'version': int,
'count': int
},
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
abbreviations=[dash],
validator={'episode': validate_roman},
formatter={
'episode': parse_numeral,
'version': int,
'count': int
},
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'],
abbreviations=[dash],
validator=None,
formatter={
'season': int,
'other': lambda match: 'Complete'
},
disabled=lambda context: is_disabled(context, 'season'))
# 12, 13
rebulk.chain(tags=['weak-episode'], formatter={'episode': int, 'version': int},
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'episode')) \
.defaults(validator=None) \
.regex(r'(?P<episode>\d{2})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{2})').repeater('*')
# 012, 013
rebulk.chain(tags=['weak-episode'], formatter={'episode': int, 'version': int},
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'episode')) \
.defaults(validator=None) \
.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})').repeater('*')
# 112, 113
rebulk.chain(tags=['weak-episode'],
formatter={'episode': int, 'version': int},
name='weak_episode',
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'episode')) \
.defaults(validator=None) \
.regex(r'(?P<episode>\d{3,4})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{3,4})').repeater('*')
# 1, 2, 3
rebulk.chain(tags=['weak-episode'], formatter={'episode': int, 'version': int},
disabled=lambda context: context.get('type') != 'episode' or is_disabled(context, 'episode')) \
.defaults(validator=None) \
.regex(r'(?P<episode>\d)') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{1,2})').repeater('*')
# e112, e113
# TODO: Enhance rebulk for validator to be used globally (season_episode_validator)
rebulk.chain(formatter={'episode': int, 'version': int},
disabled=lambda context: is_disabled(context, 'episode')) \
.defaults(validator=None) \
.regex(r'(?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})').repeater('*')
# ep 112, ep113, ep112, ep113
rebulk.chain(abbreviations=[dash], formatter={'episode': int, 'version': int},
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})').repeater('*')
# cap 112, cap 112_114
rebulk.chain(abbreviations=[dash],
tags=['see-pattern'],
formatter={'season': int, 'episode': int},
disabled=is_season_episode_disabled) \
.defaults(validator=None) \
.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'],
formatter={'season': int, 'episode': int, 'version': int},
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(validator=None) \
.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})').repeater('*')
rebulk.regex(r'v(?P<version>\d+)',
children=True,
private_parent=True,
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) + '?',
abbreviations=[dash],
children=True,
private_parent=True,
formatter=int,
disabled=lambda context: is_disabled(context, 'episode'))
rebulk.regex(
r'Minisodes?',
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, RenameToAbsoluteEpisode,
CountValidator, EpisodeSingleDigitValidator,
RenameToDiscMatch)
return rebulk
def other():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
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='AudioFix')
rebulk.regex('Sync-?Fix', 'Sync-?Fixed', value='SyncFix')
rebulk.regex('Dual-?Audio', value='DualAudio')
rebulk.regex('ws', 'wide-?screen', value='WideScreen')
rebulk.string('Netflix', 'NF', value='Netflix')
rebulk.string('Real', 'Fix', 'Fixed', value='Proper', tags=['has-neighbor-before', 'has-neighbor-after'])
rebulk.string('Proper', 'Repack', 'Rerip', value='Proper')
rebulk.string('Fansub', value='Fansub', tags='has-neighbor')
rebulk.string('Fastsub', value='Fastsub', tags='has-neighbor')
rebulk.regex('(?:Seasons?-)?Complete', value='Complete', tags=['release-group-prefix'],
validator=lambda match: seps_surround(match) and match.raw.lower().strip(seps) != "complete")
rebulk.string('R5', 'RC', value='R5')
rebulk.regex('Pre-?Air', value='Preair')
for value in (
'Screener', 'Remux', 'Remastered', '3D', 'HD', 'mHD', 'HDLight', 'HQ', 'DDC', 'HR', 'PAL', 'SECAM', 'NTSC',
'CC', 'LD', 'MD', 'XXX'):
rebulk.string(value, value=value)
for value in ('Limited', 'Complete', 'Classic', 'Unrated', 'LiNE', 'Bonus', 'Trailer', 'FINAL', 'Retail', 'Uncut',
'Extended', 'Extended Cut'):
rebulk.string(value, value=value, tags=['has-neighbor', 'release-group-prefix'])
rebulk.string('VO', 'OV', value='OV', tags='has-neighbor')
rebulk.regex('Scr(?:eener)?', value='Screener', validator=None, tags='other.validate.screener')
rebulk.rules(ValidateHasNeighbor, ValidateHasNeighborAfter, ValidateHasNeighborBefore, ValidateScreenerRule,
ProperCountRule)
return rebulk
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(r'super-duper-cut', value='Super Duper Cut')
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
def format_():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE, abbreviations=[dash])
rebulk.defaults(name="format")
rebulk.regex("VHS", "VHS-?Rip", value="VHS")
rebulk.regex("CAM", "CAM-?Rip", "HD-?CAM", value="Cam")
rebulk.regex("TELESYNC", "TS", "HD-?TS", value="Telesync")
rebulk.regex("WORKPRINT", "WP", value="Workprint")
rebulk.regex("TELECINE", "TC", value="Telecine")
rebulk.regex("PPV", "PPV-?Rip", value="PPV") # Pay Per View
rebulk.regex("SD-?TV",
"SD-?TV-?Rip",
"Rip-?SD-?TV",
"TV-?Rip",
"Rip-?TV",
value="TV") # TV is too common to allow matching
rebulk.regex("DVB-?Rip", "DVB", "PD-?TV", value="DVB")
rebulk.regex(
"DVD",
"DVD-?Rip",
"VIDEO-?TS",
"DVD-?R(?:$|(?!E))", # "DVD-?R(?:$|^E)" => DVD-Real ...
"DVD-?9",
"DVD-?5",
value="DVD")
rebulk.regex("HD-?TV",
"TV-?RIP-?HD",
"HD-?TV-?RIP",
"HD-?RIP",
value="HDTV")
rebulk.regex("VOD", "VOD-?Rip", value="VOD")
rebulk.regex("WEB-?Rip", "WEB-?DL-?Rip", "WEB-?Cap", value="WEBRip")
rebulk.regex("WEB-?DL", "WEB-?HD", "WEB", value="WEB-DL")
rebulk.regex("HD-?DVD-?Rip", "HD-?DVD", value="HD-DVD")
rebulk.regex("Blu-?ray(?:-?Rip)?",
"B[DR]",
"B[DR]-?Rip",
"BD[59]",
"BD25",
"BD50",
value="BluRay")
rebulk.regex("AHDTV", value="AHDTV")
rebulk.regex("HDTC", value="HDTC")
rebulk.regex("DSR",
"DSR?-?Rip",
"SAT-?Rip",
"DTH",
"DTH-?Rip",
value="SATRip")
rebulk.rules(ValidateFormat)
return rebulk
def audio_codec():
"""
Builder for rebulk object.
: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)
rebulk.regex("MP3", "LAME", r"LAME(?:\d)+-?(?:\d)+", value="MP3")
rebulk.regex("Dolby",
"DolbyDigital",
"Dolby-Digital",
"DDP?",
value="DolbyDigital")
rebulk.regex("DolbyAtmos", "Dolby-Atmos", "Atmos", value="DolbyAtmos")
rebulk.regex("AAC", value="AAC")
rebulk.regex("AC3D?", value="AC3")
rebulk.regex("Flac", value="FLAC")
rebulk.regex("DTS", value="DTS")
rebulk.regex("True-?HD", value="TrueHD")
rebulk.defaults(name="audio_profile")
rebulk.string("HD", value="HD", tags="DTS")
rebulk.regex("HD-?MA", value="HDMA", tags="DTS")
rebulk.string("HE", value="HE", tags="AAC")
rebulk.string("LC", value="LC", tags="AAC")
rebulk.string("HQ", value="HQ", tags="AC3")
rebulk.defaults(name="audio_channels")
rebulk.regex(r'(7[\W_][01](?:ch)?)(?:[^\d]|$)', value='7.1', children=True)
rebulk.regex(r'(5[\W_][01](?:ch)?)(?:[^\d]|$)', value='5.1', children=True)
rebulk.regex(r'(2[\W_]0(?:ch)?)(?:[^\d]|$)', value='2.0', children=True)
rebulk.string('7ch', '8ch', value='7.1')
rebulk.string('5ch', '6ch', value='5.1')
rebulk.string('2ch', 'stereo', value='2.0')
rebulk.string('1ch', 'mono', value='1.0')
rebulk.rules(DtsRule, AacRule, Ac3Rule, AudioValidatorRule, HqConflictRule)
return rebulk
def edition():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
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-edition', 'edition-collector', value='Collector Edition')
rebulk.regex('special-edition', 'edition-special', value='Special Edition',
conflict_solver=lambda match, other: other
if other.name == 'episode_details' and other.value == 'Special'
else '__default__')
rebulk.string('se', value='Special Edition', tags='has-neighbor')
rebulk.regex('criterion-edition', 'edition-criterion', value='Criterion Edition')
rebulk.regex('deluxe', 'deluxe-edition', 'edition-deluxe', value='Deluxe Edition')
rebulk.regex('limited', 'limited-edition', value='Limited Edition', tags=['has-neighbor', 'release-group-prefix'])
rebulk.regex(r'theatrical-cut', r'theatrical-edition', r'theatrical', value='Theatrical Edition')
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'])
return rebulk
def screen_size():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
def conflict_solver(match, other):
"""
Conflict solver for most screen_size.
"""
if other.name == 'screen_size':
if 'resolution' in other.tags:
# The chtouile to solve conflict in "720 x 432" string matching both 720p pattern
int_value = _digits_re.findall(match.raw)[-1]
if other.value.startswith(int_value):
return match
return other
return '__default__'
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE)
rebulk.defaults(name="screen_size", validator=seps_surround, conflict_solver=conflict_solver)
rebulk.regex(r"(?:\d{3,}(?:x|\*))?360(?:i|p?x?)", value="360p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?368(?:i|p?x?)", value="368p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?480(?:i|p?x?)", value="480p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?576(?:i|p?x?)", value="576p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?720(?:i|p?(?:50|60)?x?)", value="720p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?720(?:p(?:50|60)?x?)", value="720p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?720hd", value="720p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?900(?:i|p?x?)", value="900p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?1080i", value="1080i")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?1080p?x?", value="1080p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?1080(?:p(?:50|60)?x?)", value="1080p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?1080hd", value="1080p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?2160(?:i|p?x?)", value="4K")
_digits_re = re.compile(r'\d+')
rebulk.defaults(name="screen_size", validator=seps_surround)
rebulk.regex(r'\d{3,}-?(?:x|\*)-?\d{3,}',
formatter=lambda value: 'x'.join(_digits_re.findall(value)),
abbreviations=[dash],
tags=['resolution'],
conflict_solver=lambda match, other: '__default__' if other.name == 'screen_size' else other)
rebulk.rules(ScreenSizeOnlyOne)
return rebulk
def video_codec():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE, abbreviations=[dash]).string_defaults(ignore_case=True)
rebulk.defaults(name="video_codec")
rebulk.regex(r"Rv\d{2}", value="Real")
rebulk.regex("Mpeg2", value="Mpeg2")
rebulk.regex("DVDivX", "DivX", value="DivX")
rebulk.regex("XviD", value="XviD")
rebulk.regex("[hx]-?264(?:-?AVC(HD)?)?", "MPEG-?4(?:-?AVC(HD)?)", "AVCHD", value="h264")
rebulk.regex("[hx]-?265(?:-?HEVC)?", "HEVC", value="h265")
# http://blog.mediacoderhq.com/h264-profiles-and-levels/
# http://fr.wikipedia.org/wiki/H.264
rebulk.defaults(name="video_profile", validator=seps_surround)
rebulk.regex('10.?bits?', 'Hi10P', value='10bit')
rebulk.regex('8.?bits?', value='8bit')
rebulk.string('BP', value='BP', tags='video_profile.rule')
rebulk.string('XP', 'EP', value='XP', tags='video_profile.rule')
rebulk.string('MP', value='MP', tags='video_profile.rule')
rebulk.string('HP', 'HiP', value='HP', tags='video_profile.rule')
rebulk.regex('Hi422P', value='Hi422P', tags='video_profile.rule')
rebulk.regex('Hi444PP', value='Hi444PP', tags='video_profile.rule')
rebulk.string('DXVA', value='DXVA', name='video_api')
rebulk.rules(ValidateVideoCodec, VideoProfileRule)
return rebulk
def container():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE).string_defaults(
ignore_case=True)
rebulk.defaults(
name='container',
formatter=lambda value: value[1:],
tags=['extension'],
conflict_solver=lambda match, other: other
if other.name in ['format', 'video_codec'] or other.name == 'container'
and 'extension' not in other.tags else '__default__')
subtitles = ['srt', 'idx', 'sub', 'ssa', 'ass']
info = ['nfo']
videos = [
'3g2', '3gp', '3gp2', 'asf', 'avi', 'divx', 'flv', 'm4v', 'mk2', 'mka',
'mkv', 'mov', 'mp4', 'mp4a', 'mpeg', 'mpg', 'ogg', 'ogm', 'ogv', 'qt',
'ra', 'ram', 'rm', 'ts', 'wav', 'webm', 'wma', 'wmv', 'iso', 'vob'
]
torrent = ['torrent']
if REGEX_AVAILABLE:
rebulk.regex(r'\.\L<exts>$',
exts=subtitles,
tags=['extension', 'subtitle'])
rebulk.regex(r'\.\L<exts>$', exts=info, tags=['extension', 'info'])
rebulk.regex(r'\.\L<exts>$', exts=videos, tags=['extension', 'video'])
rebulk.regex(r'\.\L<exts>$',
exts=torrent,
tags=['extension', 'torrent'])
else:
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.defaults(
name='container',
validator=seps_surround,
formatter=lambda s: s.upper(),
conflict_solver=lambda match, other: match
if other.name in ['format', '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']],
tags=['subtitle'])
rebulk.string(*videos, tags=['video'])
rebulk.string(*torrent, tags=['torrent'])
return rebulk
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')
rebulk = Rebulk().regex_defaults(flags=re.IGNORECASE).string_defaults(ignore_case=True)
rebulk.defaults(private_names=['episodeSeparator', 'seasonSeparator', 'episodeMarker', 'seasonMarker'])
episode_max_range = config['episode_max_range']
season_max_range = config['season_max_range']
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
rebulk.chain_defaults(chain_breaker=episodes_season_chain_breaker)
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__'
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
max_range_gap = config['max_range_gap']
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.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')
# S01E02, 01x02, S01S02S03
rebulk.chain(formatter={'season': int, 'episode': int},
tags=['SxxExx'],
abbreviations=[alt_dash],
children=True,
private_parent=True,
validate_all=True,
validator={'__parent__': ordering_validator},
conflict_solver=season_episode_conflict_solver,
disabled=is_season_episode_disabled) \
.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+)',
validate_all=True,
validator={'__parent__': seps_before}).repeater('+') \
.regex(build_or_pattern(episode_markers + disc_markers + discrete_separators + range_separators,
name='episodeSeparator',
escape=True) +
r'(?P<episode>\d+)').repeater('*') \
.chain() \
.regex(r'(?P<season>\d+)@?' +
build_or_pattern(season_ep_markers, name='episodeMarker') +
r'@?(?P<episode>\d+)',
validate_all=True,
validator={'__parent__': seps_before}) \
.chain() \
.regex(r'(?P<season>\d+)@?' +
build_or_pattern(season_ep_markers, name='episodeMarker') +
r'@?(?P<episode>\d+)',
validate_all=True,
validator={'__parent__': seps_before}) \
.regex(build_or_pattern(season_ep_markers + discrete_separators + range_separators,
name='episodeSeparator',
escape=True) +
r'(?P<episode>\d+)').repeater('*') \
.chain() \
.regex(build_or_pattern(season_markers, name='seasonMarker') + r'(?P<season>\d+)',
validate_all=True,
validator={'__parent__': seps_before}) \
.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, value=episode_detail, name='episode_details',
disabled=lambda context: is_disabled(context, 'episode_details'))
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.defaults(private_names=['episodeSeparator', 'seasonSeparator', 'episodeMarker', 'seasonMarker'],
validate_all=True, validator={'__parent__': seps_surround}, children=True, private_parent=True,
conflict_solver=season_episode_conflict_solver)
rebulk.chain(abbreviations=[alt_dash],
formatter={'season': parse_numeral, 'count': parse_numeral},
validator={'__parent__': compose(seps_surround, ordering_validator),
'season': validate_roman,
'count': validate_roman},
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'season')) \
.defaults(validator=None) \
.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.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
abbreviations=[dash], formatter={'episode': int, 'version': int, 'count': int},
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
abbreviations=[dash],
validator={'episode': validate_roman},
formatter={'episode': parse_numeral, 'version': int, 'count': int},
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'],
abbreviations=[dash],
validator=None,
formatter={'season': int, 'other': lambda match: 'Complete'},
disabled=lambda context: is_disabled(context, 'season'))
# 12, 13
rebulk.chain(tags=['weak-episode'], formatter={'episode': int, 'version': int},
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'episode')) \
.defaults(validator=None) \
.regex(r'(?P<episode>\d{2})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{2})').repeater('*')
# 012, 013
rebulk.chain(tags=['weak-episode'], formatter={'episode': int, 'version': int},
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'episode')) \
.defaults(validator=None) \
.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})').repeater('*')
# 112, 113
rebulk.chain(tags=['weak-episode'],
formatter={'episode': int, 'version': int},
name='weak_episode',
disabled=lambda context: context.get('type') == 'movie' or is_disabled(context, 'episode')) \
.defaults(validator=None) \
.regex(r'(?P<episode>\d{3,4})') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{3,4})').repeater('*')
# 1, 2, 3
rebulk.chain(tags=['weak-episode'], formatter={'episode': int, 'version': int},
disabled=lambda context: context.get('type') != 'episode' or is_disabled(context, 'episode')) \
.defaults(validator=None) \
.regex(r'(?P<episode>\d)') \
.regex(r'v(?P<version>\d+)').repeater('?') \
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{1,2})').repeater('*')
# e112, e113, 1e18, 3e19
# TODO: Enhance rebulk for validator to be used globally (season_episode_validator)
rebulk.chain(formatter={'season': int, 'episode': int, 'version': int},
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})').repeater('*')
# ep 112, ep113, ep112, ep113
rebulk.chain(abbreviations=[dash], formatter={'episode': int, 'version': int},
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})').repeater('*')
# cap 112, cap 112_114
rebulk.chain(abbreviations=[dash],
tags=['see-pattern'],
formatter={'season': int, 'episode': int},
disabled=is_season_episode_disabled) \
.defaults(validator=None) \
.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'],
formatter={'season': int, 'episode': int, 'version': int},
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(validator=None) \
.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})').repeater('*')
rebulk.regex(r'v(?P<version>\d+)', children=True, private_parent=True, 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) + '?',
abbreviations=[dash], children=True, private_parent=True, formatter=int,
disabled=lambda context: is_disabled(context, 'episode'))
rebulk.regex(r'Minisodes?', 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, RenameToAbsoluteEpisode, CountValidator, EpisodeSingleDigitValidator, RenameToDiscMatch)
return rebulk
def episodes():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
#pylint: disable=too-many-branches,too-many-statements
rebulk = Rebulk()
rebulk.regex_defaults(flags=re.IGNORECASE).string_defaults(ignore_case=True)
rebulk.defaults(private_names=['episodeSeparator', 'seasonSeparator'])
# 01x02, 01x02x03x04
if REGEX_AVAILABLE:
rebulk.regex(r'(?P<season>\d+)@?x@?(?P<episode>\d+)' +
r'(?:(?P<episodeSeparator>x|-|\+|&)(?P<episode>\d+))*',
# S01E02, S01x02, S01E02E03, S01Ex02, S01xE02, SO1Ex02Ex03
r'S(?P<season>\d+)@?(?:xE|Ex|E|x)@?(?P<episode>\d+)' +
r'(?:(?P<episodeSeparator>xE|Ex|E|x|-|\+|&)(?P<episode>\d+))*',
# S01
r'S(?P<season>\d+)' +
r'(?:(?P<seasonSeparator>S|-|\+|&)(?P<season>\d+))*',
formatter={'season': int, 'episode': int},
tags=['SxxExx'],
abbreviations=[alt_dash],
children=True,
private_parent=True,
conflict_solver=lambda match, other: match
if match.name in ['season', 'episode'] and other.name in ['screen_size', 'video_codec',
'audio_codec', 'audio_channels',
'container', 'date']
else '__default__')
else:
rebulk.chain(formatter={'season': int, 'episode': int},
tags=['SxxExx'],
abbreviations=[alt_dash],
children=True,
private_parent=True,
conflict_solver=lambda match, other: match
if match.name in ['season', 'episode'] and other.name in ['screen_size', 'video_codec',
'audio_codec', 'audio_channels',
'container', 'date']
else '__default__') \
.defaults(validator=None)\
.regex(r'S(?P<season>\d+)@?(?:xE|Ex|E|x)@?(?P<episode>\d+)') \
.regex(r'(?:(?P<episodeSeparator>xE|Ex|E|x|-|\+|&)(?P<episode>\d+))').repeater('*') \
.chain() \
.regex(r'(?P<season>\d+)@?x@?(?P<episode>\d+)') \
.regex(r'(?:(?P<episodeSeparator>x|-|\+|&)(?P<episode>\d+))').repeater('*') \
.chain() \
.regex(r'S(?P<season>\d+)') \
.regex(r'(?:(?P<seasonSeparator>S|-|\+|&)(?P<season>\d+))').repeater('*')
# episode_details property
for episode_detail in ('Special', 'Bonus', 'Omake', 'Ova', 'Oav', 'Pilot', 'Unaired'):
rebulk.string(episode_detail, value=episode_detail, name='episode_details')
rebulk.regex(r'Extras?', name='episode_details', value='Extras')
rebulk.defaults(private_names=['episodeSeparator', 'seasonSeparator'],
validate_all=True, validator={'__parent__': seps_surround}, children=True, private_parent=True)
season_words = ['season', 'saison', 'serie', 'seasons', 'saisons', 'series']
episode_words = ['episode', 'episodes', 'ep']
of_words = ['of', 'sur']
all_words = ['All']
if REGEX_AVAILABLE:
rebulk.regex(r'\L<season_words>@?(?P<season>' + numeral + ')' +
r'(?:@?\L<of_words>@?(?P<count>' + numeral + '))?' +
r'(?:@?(?P<seasonSeparator>-)@?(?P<season>\d+))*' +
r'(?:@?(?P<seasonSeparator>\+|&)@?(?P<season>\d+))*',
of_words=of_words,
season_words=season_words, # Season 1, # Season one
abbreviations=[alt_dash], formatter={'season': parse_numeral, 'count': parse_numeral})
else:
rebulk.chain(abbreviations=[alt_dash], formatter={'season': parse_numeral, 'count': parse_numeral})\
.defaults(validator=None)\
.regex(build_or_pattern(season_words) + '@?(?P<season>' + numeral + ')') \
.regex(r'' + build_or_pattern(of_words) + '@?(?P<count>' + numeral + ')').repeater('?') \
.regex(r'@?(?P<seasonSeparator>-)@?(?P<season>\d+)').repeater('*') \
.regex(r'@?(?P<seasonSeparator>\+|&)@?(?P<season>\d+)').repeater('*')
if REGEX_AVAILABLE:
rebulk.regex(r'\L<episode_words>-?(?P<episode>\d+)' +
r'(?:v(?P<version>\d+))?' +
r'(?:-?\L<of_words>?-?(?P<count>\d+))?',
of_words=of_words,
episode_words=episode_words, # Episode 4
abbreviations=[dash], formatter=int,
disabled=lambda context: context.get('type') == 'episode')
else:
rebulk.regex(build_or_pattern(episode_words) + r'-?(?P<episode>\d+)' +
r'(?:v(?P<version>\d+))?' +
r'(?:-?' + build_or_pattern(of_words) + r'?-?(?P<count>\d+))?', # Episode 4
abbreviations=[dash], formatter=int,
disabled=lambda context: context.get('type') == 'episode')
if REGEX_AVAILABLE:
rebulk.regex(r'\L<episode_words>-?(?P<episode>' + numeral + ')' +
r'(?:v(?P<version>\d+))?' +
r'(?:-?\L<of_words>?-?(?P<count>\d+))?',
of_words=of_words,
episode_words=episode_words, # Episode 4
abbreviations=[dash], formatter={'episode': parse_numeral, 'version': int, 'count': int},
disabled=lambda context: context.get('type') != 'episode')
else:
rebulk.regex(build_or_pattern(episode_words) + r'-?(?P<episode>' + numeral + ')' +
r'(?:v(?P<version>\d+))?' +
r'(?:-?'+ build_or_pattern(of_words) + r'?-?(?P<count>\d+))?', # Episode 4
abbreviations=[dash], formatter={'episode': parse_numeral, 'version': int, 'count': int},
disabled=lambda context: context.get('type') != 'episode')
if REGEX_AVAILABLE:
rebulk.regex(r'S?(?P<season>\d+)-?(?:xE|Ex|E|x)-?(?P<other>\L<all_words>)',
tags=['SxxExx'],
all_words=all_words,
abbreviations=[dash],
validator=None,
formatter={'season': int, 'other': lambda match: 'Complete'})
else:
rebulk.regex(r'S?(?P<season>\d+)-?(?:xE|Ex|E|x)-?(?P<other>'+build_or_pattern(all_words)+')',
tags=['SxxExx'],
abbreviations=[dash],
validator=None,
formatter={'season': int, 'other': lambda match: 'Complete'})
rebulk.defaults(private_names=['episodeSeparator', 'seasonSeparator'], validate_all=True,
validator={'__parent__': seps_surround}, children=True, private_parent=True)
if REGEX_AVAILABLE:
# 12, 13
rebulk.regex(r'(?P<episode>\d{2})' +
r'(?:v(?P<version>\d+))?' +
r'(?:(?P<episodeSeparator>[x-])(?P<episode>\d{2}))*',
tags=['bonus-conflict', 'weak-movie'], formatter={'episode': int, 'version': int})
else:
rebulk.chain(tags=['bonus-conflict', 'weak-movie'], formatter={'episode': int, 'version': int}) \
.defaults(validator=None) \
.regex(r'(?P<episode>\d{2})')\
.regex(r'v(?P<version>\d+)').repeater('?')\
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{2})').repeater('*')
if REGEX_AVAILABLE:
# 012, 013
rebulk.regex(r'0(?P<episode>\d{1,2})' +
r'(?:v(?P<version>\d+))?' +
r'(?:(?P<episodeSeparator>[x-])0(?P<episode>\d{1,2}))*',
tags=['bonus-conflict', 'weak-movie'], formatter={'episode': int, 'version': int})
else:
rebulk.chain(tags=['bonus-conflict', 'weak-movie'], formatter={'episode': int, 'version': int}) \
.defaults(validator=None) \
.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})').repeater('*')
if REGEX_AVAILABLE:
# 112, 113
rebulk.regex(r'(?P<episode>\d{3,4})' +
r'(?:v(?P<version>\d+))?' +
r'(?:(?P<episodeSeparator>[x-])(?P<episode>\d{3,4}))*',
tags=['bonus-conflict', 'weak-movie'], formatter={'episode': int, 'version': int},
disabled=lambda context: not context.get('episode_prefer_number', False))
else:
rebulk.chain(tags=['bonus-conflict', 'weak-movie'], formatter={'episode': int, 'version': int},
disabled=lambda context: not context.get('episode_prefer_number', False)) \
.defaults(validator=None) \
.regex(r'(?P<episode>\d{3,4})')\
.regex(r'v(?P<version>\d+)').repeater('?')\
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{3,4})').repeater('*')
if REGEX_AVAILABLE:
# 1, 2, 3
rebulk.regex(r'(?P<episode>\d)' +
r'(?:v(?P<version>\d+))?' +
r'(?:(?P<episodeSeparator>[x-])(?P<episode>\d{1,2}))*',
tags=['bonus-conflict', 'weak-movie'], formatter={'episode': int, 'version': int},
disabled=lambda context: context.get('type') != 'episode')
else:
rebulk.chain(tags=['bonus-conflict', 'weak-movie'], formatter={'episode': int, 'version': int},
disabled=lambda context: context.get('type') != 'episode') \
.defaults(validator=None) \
.regex(r'(?P<episode>\d)')\
.regex(r'v(?P<version>\d+)').repeater('?')\
.regex(r'(?P<episodeSeparator>[x-])(?P<episode>\d{1,2})').repeater('*')
# e112, e113
if REGEX_AVAILABLE:
rebulk.regex(r'e(?P<episode>\d{1,4})' +
r'(?:v(?P<version>\d+))?' +
r'(?:(?P<episodeSeparator>e|x|-)(?P<episode>\d{1,4}))*',
formatter={'episode': int, 'version': int})
else:
rebulk.chain(formatter={'episode': int, 'version': int}) \
.defaults(validator=None) \
.regex(r'e(?P<episode>\d{1,4})')\
.regex(r'v(?P<version>\d+)').repeater('?')\
.regex(r'(?P<episodeSeparator>e|x|-)(?P<episode>\d{1,4})').repeater('*')
# ep 112, ep113, ep112, ep113
if REGEX_AVAILABLE:
rebulk.regex(r'ep-?(?P<episode>\d{1,4})' +
r'(?:v(?P<version>\d+))?' +
r'(?:(?P<episodeSeparator>ep|e|x|-)(?P<episode>\d{1,4}))*',
abbreviations=[dash],
formatter={'episode': int, 'version': int})
else:
rebulk.chain(abbreviations=[dash], formatter={'episode': int, 'version': int}) \
.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})').repeater('*')
# 102, 0102
if REGEX_AVAILABLE:
rebulk.regex(r'(?P<season>\d{1,2})(?P<episode>\d{2})' +
r'(?:v(?P<version>\d+))?' +
r'(?:(?P<episodeSeparator>x|-)(?P<episode>\d{2}))*',
tags=['bonus-conflict', 'weak-movie', 'weak-duplicate'],
formatter={'season': int, 'episode': int, 'version': int},
conflict_solver=lambda match, other: match if other.name == 'year' else '__default__',
disabled=lambda context: context.get('episode_prefer_number', False))
else:
rebulk.chain(tags=['bonus-conflict', 'weak-movie', 'weak-duplicate'],
formatter={'season': int, 'episode': int, 'version': int},
conflict_solver=lambda match, other: match if other.name == 'year' else '__default__',
disabled=lambda context: context.get('episode_prefer_number', False))\
.defaults(validator=None)\
.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})').repeater('*')
rebulk.regex(r'v(?P<version>\d+)', children=True, private_parent=True, formatter=int)
rebulk.defaults(private_names=['episodeSeparator', 'seasonSeparator'])
#TODO: List of words
# detached of X count (season/episode)
if REGEX_AVAILABLE:
rebulk.regex(r'(?P<episode>\d+)?-?\L<of_words>-?(?P<count>\d+)-?\L<episode_words>?', of_words=of_words,
episode_words=episode_words, abbreviations=[dash], children=True, private_parent=True,
formatter=int)
else:
rebulk.regex(r'(?P<episode>\d+)?-?' + build_or_pattern(of_words) +
r'-?(?P<count>\d+)-?' + build_or_pattern(episode_words) + '?',
abbreviations=[dash], children=True, private_parent=True, formatter=int)
rebulk.regex(r'Minisodes?', name='episode_format', value="Minisode")
# Harcoded movie to disable weak season/episodes
rebulk.regex('OSS-?117',
abbreviations=[dash], name="hardcoded-movies", marker=True,
conflict_solver=lambda match, other: None)
rebulk.rules(EpisodeNumberSeparatorRange, SeasonSeparatorRange, RemoveWeakIfMovie, RemoveWeakIfSxxExx,
RemoveWeakDuplicate, EpisodeDetailValidator, RemoveDetachedEpisodeNumber, VersionValidator,
CountValidator, EpisodeSingleDigitValidator)
return rebulk
def screen_size():
"""
Builder for rebulk object.
:return: Created Rebulk object
:rtype: Rebulk
"""
def conflict_solver(match, other):
"""
Conflict solver for most screen_size.
"""
if other.name == 'screen_size':
if 'resolution' in other.tags:
# The chtouile to solve conflict in "720 x 432" string matching both 720p pattern
int_value = _digits_re.findall(match.raw)[-1]
if other.value.startswith(int_value):
return match
return other
return '__default__'
rebulk = Rebulk().string_defaults(ignore_case=True).regex_defaults(flags=re.IGNORECASE)
rebulk.defaults(name="screen_size", validator=seps_surround, conflict_solver=conflict_solver)
rebulk.regex(r"(?:\d{3,}(?:x|\*))?360(?:i|p?x?)", value="360p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?368(?:i|p?x?)", value="368p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?480(?:i|p?x?)", value="480p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?576(?:i|p?x?)", value="576p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?720(?:i|p?(?:50|60)?x?)", value="720p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?720(?:p(?:50|60)?x?)", value="720p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?720p?hd", value="720p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?900(?:i|p?x?)", value="900p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?1080i", value="1080i")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?1080p?x?", value="1080p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?1080(?:p(?:50|60)?x?)", value="1080p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?1080p?hd", value="1080p")
rebulk.regex(r"(?:\d{3,}(?:x|\*))?2160(?:i|p?x?)", value="4K")
rebulk.string('4k', value='4K')
_digits_re = re.compile(r'\d+')
rebulk.defaults(name="screen_size", validator=seps_surround)
rebulk.regex(r'\d{3,}-?(?:x|\*)-?\d{3,}',
formatter=lambda value: 'x'.join(_digits_re.findall(value)),
abbreviations=[dash],
tags=['resolution'],
conflict_solver=lambda match, other: '__default__' if other.name == 'screen_size' else other)
rebulk.rules(ScreenSizeOnlyOne, RemoveScreenSizeConflicts)
return rebulk
def audio_codec():
"""
Builder for rebulk object.
: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)
rebulk.regex("MP3", "LAME", r"LAME(?:\d)+-?(?:\d)+", value="MP3")
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', value='DTS-HD')
rebulk.regex('True-?HD', value='Dolby TrueHD')
rebulk.string('Opus', value='Opus')
rebulk.defaults(name='audio_profile')
rebulk.string('MA', value='Master Audio', tags='DTS-HD')
rebulk.string('HR', 'HRA', value='High Resolution Audio', tags='DTS-HD')
rebulk.string('ES', value='Extended Surround', tags='DTS')
rebulk.string('HE', value='High Efficiency', tags='AAC')
rebulk.string('LC', value='Low Complexity', tags='AAC')
rebulk.string('HQ', value='High Quality', tags='Dolby Digital')
rebulk.string('EX', value='EX', tags='Dolby Digital')
rebulk.defaults(name="audio_channels")
rebulk.regex(r'(7[\W_][01](?:ch)?)(?:[^\d]|$)', value='7.1', children=True)
rebulk.regex(r'(5[\W_][01](?:ch)?)(?:[^\d]|$)', value='5.1', children=True)
rebulk.regex(r'(2[\W_]0(?:ch)?)(?:[^\d]|$)', value='2.0', children=True)
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')
rebulk.string('7ch', '8ch', value='7.1')
rebulk.string('5ch', '6ch', value='5.1')
rebulk.string('2ch', 'stereo', value='2.0')
rebulk.string('1ch', 'mono', value='1.0')
rebulk.rules(DtsHDRule, AacRule, DolbyDigitalRule, AudioValidatorRule, HqConflictRule, AudioChannelsValidatorRule)
return rebulk
