Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 panni
|
f8f99f0fb2 |
No files matched your search
@@ -1,54 +1,3 @@
|
||||
2.6.5.3109
|
||||
|
||||
subscene, addic7ed and titlovi
|
||||
- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
|
||||
|
||||
Changelog
|
||||
- providers: add Napisy24 (polish)
|
||||
- providers: subscene: reduce provider load by possibly half
|
||||
- providers: subscene: support logging in (username/password are now required)
|
||||
- providers: subscene: fallback to non year results if none found with year
|
||||
|
||||
|
||||
2.6.5.3099
|
||||
|
||||
subscene, addic7ed and titlovi
|
||||
- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
|
||||
|
||||
Changelog
|
||||
- core: allow system DNS again by putting "system" as the DNS
|
||||
- providers: subscene: fix again (subscene, contact us please, so we can end this)
|
||||
|
||||
|
||||
2.6.5.3092
|
||||
|
||||
subscene, addic7ed and titlovi
|
||||
- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
|
||||
|
||||
Changelog
|
||||
- providers: subscene: fix endpoint (hopefully for longer now)
|
||||
- providers: subscene: don't search for season packs (broken for now; relieves 50% of server load on provider)
|
||||
- providers: subscene: don't calculate video fn for now
|
||||
- providers: argenteam: backport fixes from bazarr
|
||||
- subtitle: try decoding with utf-16 by default as well (zho/farsi)
|
||||
- submod: HI: remove music tags by default
|
||||
- core: compat (bazarr): add env var SZ_KEEP_ENCODING to keep encoding of subtitles
|
||||
|
||||
|
||||
2.6.5.3074
|
||||
|
||||
Changelog
|
||||
- core: cf: bypass cf 95% of the time without captchas
|
||||
- core: fix breaking line endings of certain languages (chinese, UTF-16); fixes #646
|
||||
- core: update pysubs2 to 0.2.3
|
||||
|
||||
|
||||
2.6.5.3062
|
||||
|
||||
Changelog
|
||||
- core: cf: optimize
|
||||
- core: http: don't query DNS with IPs. thanks @fgump (fixes sonarr/radarr)
|
||||
|
||||
|
||||
2.6.5.3041
|
||||
|
||||
|
||||
@@ -119,23 +119,19 @@ def agent_extract_embedded(video_part_map):
|
||||
for plexapi_part in get_all_parts(plexapi_item):
|
||||
item_count = item_count + 1
|
||||
used_one_unknown_stream = False
|
||||
used_one_known_stream = False
|
||||
for requested_language in config.lang_list:
|
||||
skip_unknown = used_one_unknown_stream or used_one_known_stream
|
||||
embedded_subs = stored_subs.get_by_provider(plexapi_part.id, requested_language, "embedded")
|
||||
current = stored_subs.get_any(plexapi_part.id, requested_language) or \
|
||||
requested_language in scanned_video.external_subtitle_languages
|
||||
|
||||
if not embedded_subs:
|
||||
stream_data = get_embedded_subtitle_streams(plexapi_part, requested_language=requested_language,
|
||||
skip_unknown=skip_unknown)
|
||||
skip_unknown=used_one_unknown_stream)
|
||||
|
||||
if stream_data:
|
||||
stream = stream_data[0]["stream"]
|
||||
if stream_data[0]["is_unknown"]:
|
||||
used_one_unknown_stream = True
|
||||
else:
|
||||
used_one_known_stream = True
|
||||
|
||||
to_extract.append(({scanned_video: part_info}, plexapi_part, str(stream.index),
|
||||
str(requested_language), not current))
|
||||
|
||||
@@ -761,7 +761,6 @@ class Config(object):
|
||||
return {'opensubtitles': cast_bool(Prefs['provider.opensubtitles.enabled']),
|
||||
# 'thesubdb': Prefs['provider.thesubdb.enabled'],
|
||||
'podnapisi': cast_bool(Prefs['provider.podnapisi.enabled']),
|
||||
'napisy24': cast_bool(Prefs['provider.napisy24.enabled']),
|
||||
'titlovi': cast_bool(Prefs['provider.titlovi.enabled']),
|
||||
'addic7ed': cast_bool(Prefs['provider.addic7ed.enabled']) and self.has_anticaptcha,
|
||||
'tvsubtitles': cast_bool(Prefs['provider.tvsubtitles.enabled']),
|
||||
@@ -802,7 +801,6 @@ class Config(object):
|
||||
providers["argenteam"] = False
|
||||
providers["assrt"] = False
|
||||
providers["subscene"] = False
|
||||
providers["napisy24"] = False
|
||||
providers_forced_off = dict(providers)
|
||||
|
||||
if not self.unrar and providers["legendastv"]:
|
||||
@@ -866,14 +864,8 @@ class Config(object):
|
||||
'only_foreign': self.forced_only,
|
||||
'also_foreign': self.forced_also,
|
||||
},
|
||||
'napisy24': {
|
||||
'username': Prefs['provider.napisy24.username'],
|
||||
'password': Prefs['provider.napisy24.password'],
|
||||
},
|
||||
'subscene': {
|
||||
'only_foreign': self.forced_only,
|
||||
'username': Prefs['provider.subscene.username'],
|
||||
'password': Prefs['provider.subscene.password'],
|
||||
},
|
||||
'legendastv': {'username': Prefs['provider.legendastv.username'],
|
||||
'password': Prefs['provider.legendastv.password'],
|
||||
@@ -1092,12 +1084,11 @@ class Config(object):
|
||||
def parse_custom_dns(self):
|
||||
custom_dns = Prefs['use_custom_dns2'].strip()
|
||||
os.environ["dns_resolvers"] = ""
|
||||
|
||||
if custom_dns and custom_dns != "system":
|
||||
if custom_dns:
|
||||
ips = filter(lambda x: x, [d.strip() for d in custom_dns.split(",")])
|
||||
if ips:
|
||||
os.environ["dns_resolvers"] = json.dumps(ips)
|
||||
return os.environ["dns_resolvers"]
|
||||
return os.environ["dns_resolvers"]
|
||||
|
||||
def init_subliminal_patches(self):
|
||||
# configure custom subtitle destination folders for scanning pre-existing subs
|
||||
|
||||
@@ -394,7 +394,7 @@ def get_language_from_stream(lang_code):
|
||||
return Language.fromietf(lang)
|
||||
elif lang:
|
||||
try:
|
||||
return language_from_stream(lang_code)
|
||||
return language_from_stream(lang)
|
||||
except LanguageError:
|
||||
pass
|
||||
|
||||
|
||||
@@ -177,7 +177,6 @@ def get_all_parts(plex_item):
|
||||
def get_embedded_subtitle_streams(part, requested_language=None, skip_duplicate_unknown=True, skip_unknown=False):
|
||||
streams = []
|
||||
streams_unknown = []
|
||||
all_streams = []
|
||||
has_unknown = False
|
||||
found_requested_language = False
|
||||
for stream in part.streams:
|
||||
@@ -190,40 +189,27 @@ def get_embedded_subtitle_streams(part, requested_language=None, skip_duplicate_
|
||||
|
||||
is_unknown = False
|
||||
found_requested_language = requested_language and requested_language == language
|
||||
stream_data = None
|
||||
|
||||
if not language:
|
||||
if not language and config.treat_und_as_first:
|
||||
# only consider first unknown subtitle stream
|
||||
if requested_language and config.treat_und_as_first:
|
||||
if has_unknown and skip_duplicate_unknown:
|
||||
Log.Debug("skipping duplicate unknown")
|
||||
continue
|
||||
if has_unknown and skip_duplicate_unknown:
|
||||
continue
|
||||
|
||||
language = Language.rebuild(list(config.lang_list)[0], forced=is_forced)
|
||||
else:
|
||||
language = Language("unk")
|
||||
language = Language.rebuild(list(config.lang_list)[0], forced=is_forced)
|
||||
is_unknown = True
|
||||
has_unknown = True
|
||||
stream_data = {"stream": stream, "is_unknown": is_unknown, "language": language,
|
||||
"is_forced": is_forced}
|
||||
streams_unknown.append(stream_data)
|
||||
streams_unknown.append({"stream": stream, "is_unknown": is_unknown, "language": language,
|
||||
"is_forced": is_forced})
|
||||
|
||||
if not requested_language or found_requested_language:
|
||||
stream_data = {"stream": stream, "is_unknown": is_unknown, "language": language,
|
||||
"is_forced": is_forced}
|
||||
streams.append(stream_data)
|
||||
streams.append({"stream": stream, "is_unknown": is_unknown, "language": language,
|
||||
"is_forced": is_forced})
|
||||
|
||||
if found_requested_language:
|
||||
break
|
||||
|
||||
if stream_data:
|
||||
all_streams.append(stream_data)
|
||||
|
||||
if requested_language:
|
||||
if streams_unknown and not found_requested_language and not skip_unknown:
|
||||
streams = streams_unknown
|
||||
else:
|
||||
streams = all_streams
|
||||
if streams_unknown and not found_requested_language and not skip_unknown:
|
||||
streams = streams_unknown
|
||||
|
||||
return streams
|
||||
|
||||
|
||||
@@ -335,26 +335,6 @@
|
||||
"type": "bool",
|
||||
"default": "true"
|
||||
},
|
||||
{
|
||||
"id": "provider.napisy24.enabled",
|
||||
"label": "Provider: Enable Napisy24 (pl)",
|
||||
"type": "bool",
|
||||
"default": "false"
|
||||
},
|
||||
{
|
||||
"id": "provider.napisy24.username",
|
||||
"label": "Napisy24 Username",
|
||||
"type": "text",
|
||||
"default": ""
|
||||
},
|
||||
{
|
||||
"id": "provider.napisy24.password",
|
||||
"label": "Napisy24 Password",
|
||||
"type": "text",
|
||||
"option": "hidden",
|
||||
"default": "",
|
||||
"secure": "true"
|
||||
},
|
||||
{
|
||||
"id": "provider.addic7ed.enabled",
|
||||
"label": "Provider: Enable Addic7ed (needs AntiCaptcha)",
|
||||
@@ -451,20 +431,6 @@
|
||||
"type": "bool",
|
||||
"default": "true"
|
||||
},
|
||||
{
|
||||
"id": "provider.subscene.username",
|
||||
"label": "SubScene Username",
|
||||
"type": "text",
|
||||
"default": ""
|
||||
},
|
||||
{
|
||||
"id": "provider.subscene.password",
|
||||
"label": "SubScene Password",
|
||||
"type": "text",
|
||||
"option": "hidden",
|
||||
"default": "",
|
||||
"secure": "true"
|
||||
},
|
||||
{
|
||||
"id": "provider.supersubtitles.enabled",
|
||||
"label": "Provider: Enable feliratok.info (Hungarian)",
|
||||
@@ -895,7 +861,7 @@
|
||||
},
|
||||
{
|
||||
"id": "use_custom_dns2",
|
||||
"label": "Use custom DNS (IPs, comma-separated, set to 'system' for system DNS. Default: Google/CF)",
|
||||
"label": "Use custom DNS (IPs, comma-separated, leave empty for system DNS. Default: Google/CF)",
|
||||
"type": "text",
|
||||
"default": "1.1.1.1, 8.8.8.8"
|
||||
},
|
||||
|
||||
+3
-3
@@ -13,7 +13,7 @@
|
||||
<key>CFBundleSignature</key>
|
||||
<string>????</string>
|
||||
<key>CFBundleVersion</key>
|
||||
<string>2.6.5.3124</string>
|
||||
<string>2.6.5.3074</string>
|
||||
<key>PlexFrameworkVersion</key>
|
||||
<string>2</string>
|
||||
<key>PlexPluginClass</key>
|
||||
@@ -23,7 +23,7 @@
|
||||
<key>PlexPluginConsoleLogging</key>
|
||||
<string>0</string>
|
||||
<key>PlexPluginDevMode</key>
|
||||
<string>0</string>
|
||||
<string>1</string>
|
||||
<key>PlexPluginCodePolicy</key>
|
||||
<!-- this allows channels to access some python methods which are otherwise blocked, as well as import external code libraries, and interact with the PMS HTTP API -->
|
||||
<string>Elevated</string>
|
||||
@@ -32,7 +32,7 @@
|
||||
|
||||
<h1>Sub-Zero for Plex</h1><i>Subtitles done right</i>
|
||||
|
||||
Version 2.6.5.3124
|
||||
Version 2.6.5.3074 DEV
|
||||
|
||||
Originally based on @bramwalet's awesome <a href="https://github.com/bramwalet/Subliminal.bundle">Subliminal.bundle</a>
|
||||
|
||||
|
||||
@@ -12,13 +12,6 @@ from_subscene = {
|
||||
'Malay': 'msa', 'Pashto': 'pus', 'Punjabi': 'pan', 'Swahili': 'swa'
|
||||
}
|
||||
|
||||
from_subscene_with_country = {
|
||||
'Brazillian Portuguese': ('por', 'BR')
|
||||
}
|
||||
|
||||
to_subscene_with_country = {val: key for key, val in from_subscene_with_country.items()}
|
||||
|
||||
|
||||
to_subscene = {v: k for k, v in from_subscene.items()}
|
||||
|
||||
exact_languages_alpha3 = [
|
||||
@@ -41,12 +34,12 @@ language_ids = {
|
||||
'mkd': 48, 'mal': 64, 'mni': 65, 'mon': 72, 'pus': 67, 'pol': 31,
|
||||
'por': 32, 'pan': 66, 'rus': 34, 'srp': 35, 'sin': 58, 'slk': 36,
|
||||
'slv': 37, 'som': 70, 'tgl': 53, 'tam': 59, 'tel': 63, 'tha': 40,
|
||||
'tur': 41, 'ukr': 56, 'urd': 42, 'yor': 71, 'pt-BR': 4
|
||||
'tur': 41, 'ukr': 56, 'urd': 42, 'yor': 71
|
||||
}
|
||||
|
||||
# TODO: specify codes for unspecified_languages
|
||||
unspecified_languages = [
|
||||
'Big 5 code', 'Bulgarian/ English',
|
||||
'Big 5 code', 'Brazillian Portuguese', 'Bulgarian/ English',
|
||||
'Chinese BG code', 'Dutch/ English', 'English/ German',
|
||||
'Hungarian/ English', 'Rohingya'
|
||||
]
|
||||
@@ -57,8 +50,6 @@ alpha3_of_code = {l.name: l.alpha3 for l in supported_languages}
|
||||
|
||||
supported_languages.update({Language(l) for l in to_subscene})
|
||||
|
||||
supported_languages.update({Language(lang, cr) for lang, cr in to_subscene_with_country})
|
||||
|
||||
|
||||
class SubsceneConverter(LanguageReverseConverter):
|
||||
codes = {l.name for l in supported_languages}
|
||||
@@ -70,15 +61,9 @@ class SubsceneConverter(LanguageReverseConverter):
|
||||
if alpha3 in to_subscene:
|
||||
return to_subscene[alpha3]
|
||||
|
||||
if (alpha3, country) in to_subscene_with_country:
|
||||
return to_subscene_with_country[(alpha3, country)]
|
||||
|
||||
raise ConfigurationError('Unsupported language for subscene: %s, %s, %s' % (alpha3, country, script))
|
||||
|
||||
def reverse(self, code):
|
||||
if code in from_subscene_with_country:
|
||||
return from_subscene_with_country[code]
|
||||
|
||||
if code in from_subscene:
|
||||
return (from_subscene[code],)
|
||||
|
||||
|
||||
@@ -309,8 +309,7 @@ class SZProviderPool(ProviderPool):
|
||||
logger.error('Invalid subtitle')
|
||||
return False
|
||||
|
||||
if not os.environ.get("SZ_KEEP_ENCODING", False):
|
||||
subtitle.normalize()
|
||||
subtitle.normalize()
|
||||
|
||||
return True
|
||||
|
||||
@@ -473,7 +472,7 @@ if is_windows_special_path:
|
||||
SZAsyncProviderPool = SZProviderPool
|
||||
|
||||
|
||||
def scan_video(path, dont_use_actual_file=False, hints=None, providers=None, skip_hashing=False, hash_from=None):
|
||||
def scan_video(path, dont_use_actual_file=False, hints=None, providers=None, skip_hashing=False):
|
||||
"""Scan a video from a `path`.
|
||||
|
||||
patch:
|
||||
@@ -538,34 +537,28 @@ def scan_video(path, dont_use_actual_file=False, hints=None, providers=None, ski
|
||||
video.alternative_titles.append(alt_guess["title"])
|
||||
logger.debug("Adding alternative title: %s", alt_guess["title"])
|
||||
|
||||
if dont_use_actual_file and not hash_from:
|
||||
if dont_use_actual_file:
|
||||
return video
|
||||
|
||||
# size and hashes
|
||||
if not skip_hashing:
|
||||
hash_path = hash_from or path
|
||||
video.size = os.path.getsize(hash_path)
|
||||
video.size = os.path.getsize(path)
|
||||
if video.size > 10485760:
|
||||
logger.debug('Size is %d', video.size)
|
||||
osub_hash = None
|
||||
if "opensubtitles" in providers:
|
||||
video.hashes['opensubtitles'] = osub_hash = hash_opensubtitles(hash_path)
|
||||
video.hashes['opensubtitles'] = hash_opensubtitles(path)
|
||||
|
||||
if "shooter" in providers:
|
||||
video.hashes['shooter'] = hash_shooter(hash_path)
|
||||
video.hashes['shooter'] = hash_shooter(path)
|
||||
|
||||
if "thesubdb" in providers:
|
||||
video.hashes['thesubdb'] = hash_thesubdb(hash_path)
|
||||
video.hashes['thesubdb'] = hash_thesubdb(path)
|
||||
|
||||
if "napiprojekt" in providers:
|
||||
try:
|
||||
video.hashes['napiprojekt'] = hash_napiprojekt(hash_path)
|
||||
video.hashes['napiprojekt'] = hash_napiprojekt(path)
|
||||
except MemoryError:
|
||||
logger.warning(u"Couldn't compute napiprojekt hash for %s", hash_path)
|
||||
|
||||
if "napisy24" in providers:
|
||||
# Napisy24 uses the same hash as opensubtitles
|
||||
video.hashes['napisy24'] = osub_hash or hash_opensubtitles(hash_path)
|
||||
logger.warning(u"Couldn't compute napiprojekt hash for %s", path)
|
||||
|
||||
logger.debug('Computed hashes %r', video.hashes)
|
||||
else:
|
||||
@@ -581,7 +574,7 @@ def _search_external_subtitles(path, languages=None, only_one=False, scandir_gen
|
||||
subtitles = {}
|
||||
_scandir = _scandir_generic if scandir_generic else scandir
|
||||
for entry in _scandir(dirpath):
|
||||
if (not entry.name or entry.name in ('\x0c', '$', ',', '\x7f')) and not scandir_generic:
|
||||
if not entry.name and not scandir_generic:
|
||||
logger.debug('Could not determine the name of the file, retrying with scandir_generic')
|
||||
return _search_external_subtitles(path, languages, only_one, True)
|
||||
if not entry.is_file(follow_symlinks=False):
|
||||
|
||||
@@ -354,6 +354,7 @@ def patch_create_connection():
|
||||
return _orig_create_connection((ip, port), *args, **kwargs)
|
||||
except dns.exception.DNSException:
|
||||
logger.warning("DNS: Couldn't resolve %s with DNS: %s", host, custom_resolver.nameservers)
|
||||
raise
|
||||
|
||||
logger.debug("DNS: Falling back to default DNS or IP on %s", host)
|
||||
return _orig_create_connection((host, port), *args, **kwargs)
|
||||
|
||||
@@ -23,10 +23,9 @@ class ArgenteamSubtitle(Subtitle):
|
||||
hearing_impaired_verifiable = False
|
||||
_release_info = None
|
||||
|
||||
def __init__(self, language, page_link, download_link, movie_kind, title, season, episode, year, release, version, source,
|
||||
def __init__(self, language, download_link, movie_kind, title, season, episode, year, release, version, source,
|
||||
video_codec, tvdb_id, imdb_id, asked_for_episode=None, asked_for_release_group=None, *args, **kwargs):
|
||||
super(ArgenteamSubtitle, self).__init__(language, page_link=page_link, *args, **kwargs)
|
||||
self.page_link = page_link
|
||||
super(ArgenteamSubtitle, self).__init__(language, download_link, *args, **kwargs)
|
||||
self.download_link = download_link
|
||||
self.movie_kind = movie_kind
|
||||
self.title = title
|
||||
@@ -136,8 +135,7 @@ class ArgenteamProvider(Provider, ProviderSubtitleArchiveMixin):
|
||||
provider_name = 'argenteam'
|
||||
languages = {Language.fromalpha2(l) for l in ['es']}
|
||||
video_types = (Episode, Movie)
|
||||
BASE_URL = "http://www.argenteam.net/"
|
||||
API_URL = BASE_URL + "api/v1/"
|
||||
API_URL = "http://argenteam.net/api/v1/"
|
||||
subtitle_class = ArgenteamSubtitle
|
||||
hearing_impaired_verifiable = False
|
||||
language_list = list(languages)
|
||||
@@ -242,13 +240,12 @@ class ArgenteamProvider(Provider, ProviderSubtitleArchiveMixin):
|
||||
|
||||
for r in content['releases']:
|
||||
for s in r['subtitles']:
|
||||
movie_kind = "episode" if is_episode else "movie"
|
||||
page_link = self.BASE_URL + movie_kind + "/" + str(aid)
|
||||
sub = ArgenteamSubtitle(language, page_link, s['uri'], movie_kind, returned_title,
|
||||
sub = ArgenteamSubtitle(language, s['uri'], "episode" if is_episode else "movie", returned_title,
|
||||
season, episode, year, r.get('team'), r.get('tags'),
|
||||
r.get('source'), r.get('codec'), content.get("tvdb"), imdb_id,
|
||||
asked_for_release_group=video.release_group,
|
||||
asked_for_episode=episode)
|
||||
asked_for_episode=episode
|
||||
)
|
||||
subtitles.append(sub)
|
||||
|
||||
if has_multiple_ids:
|
||||
|
||||
@@ -1,124 +0,0 @@
|
||||
import logging
|
||||
import os
|
||||
from io import BytesIO
|
||||
from zipfile import ZipFile
|
||||
|
||||
from requests import Session
|
||||
|
||||
from subliminal_patch.subtitle import Subtitle
|
||||
from subliminal_patch.providers import Provider
|
||||
from subliminal import __short_version__
|
||||
from subliminal.exceptions import AuthenticationError, ConfigurationError
|
||||
from subliminal.subtitle import fix_line_ending
|
||||
from subzero.language import Language
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class Napisy24Subtitle(Subtitle):
|
||||
'''Napisy24 Subtitle.'''
|
||||
provider_name = 'napisy24'
|
||||
|
||||
def __init__(self, language, hash, imdb_id, napis_id):
|
||||
super(Napisy24Subtitle, self).__init__(language)
|
||||
self.hash = hash
|
||||
self.imdb_id = imdb_id
|
||||
self.napis_id = napis_id
|
||||
|
||||
@property
|
||||
def id(self):
|
||||
return self.hash
|
||||
|
||||
def get_matches(self, video):
|
||||
matches = set()
|
||||
|
||||
# hash
|
||||
if 'napisy24' in video.hashes and video.hashes['napisy24'] == self.hash:
|
||||
matches.add('hash')
|
||||
|
||||
# imdb_id
|
||||
if video.imdb_id and self.imdb_id == video.imdb_id:
|
||||
matches.add('imdb_id')
|
||||
|
||||
return matches
|
||||
|
||||
|
||||
class Napisy24Provider(Provider):
|
||||
'''Napisy24 Provider.'''
|
||||
languages = {Language(l) for l in ['pol']}
|
||||
required_hash = 'napisy24'
|
||||
api_url = 'http://napisy24.pl/run/CheckSubAgent.php'
|
||||
|
||||
def __init__(self, username=None, password=None):
|
||||
if all((username, password)):
|
||||
self.username = username
|
||||
self.password = password
|
||||
else:
|
||||
self.username = 'subliminal'
|
||||
self.password = 'lanimilbus'
|
||||
|
||||
self.session = None
|
||||
|
||||
def initialize(self):
|
||||
self.session = Session()
|
||||
self.session.headers['User-Agent'] = 'Subliminal/%s' % __short_version__
|
||||
self.session.headers['Content-Type'] = 'application/x-www-form-urlencoded'
|
||||
|
||||
def terminate(self):
|
||||
self.session.close()
|
||||
|
||||
def query(self, language, size, name, hash):
|
||||
params = {
|
||||
'postAction': 'CheckSub',
|
||||
'ua': self.username,
|
||||
'ap': self.password,
|
||||
'fs': size,
|
||||
'fh': hash,
|
||||
'fn': os.path.basename(name),
|
||||
'n24pref': 1
|
||||
}
|
||||
|
||||
response = self.session.post(self.api_url, data=params, timeout=10)
|
||||
response.raise_for_status()
|
||||
|
||||
response_content = response.content.split(b'||', 1)
|
||||
n24_data = response_content[0].decode()
|
||||
|
||||
if n24_data[:2] != 'OK':
|
||||
if n24_data[:11] == 'login error':
|
||||
raise AuthenticationError('Login failed')
|
||||
logger.error('Unknown response: %s', response.content)
|
||||
return None
|
||||
|
||||
n24_status = n24_data[:4]
|
||||
if n24_status == 'OK-0':
|
||||
logger.info('No subtitles found')
|
||||
return None
|
||||
|
||||
subtitle_info = dict(p.split(':', 1) for p in n24_data.split('|')[1:])
|
||||
logger.debug('Subtitle info: %s', subtitle_info)
|
||||
|
||||
if n24_status == 'OK-1':
|
||||
logger.info('No subtitles found but got video info')
|
||||
return None
|
||||
elif n24_status == 'OK-2':
|
||||
logger.info('Found subtitles')
|
||||
elif n24_status == 'OK-3':
|
||||
logger.info('Found subtitles but not from Napisy24 database')
|
||||
return None
|
||||
|
||||
subtitle_content = response_content[1]
|
||||
|
||||
subtitle = Napisy24Subtitle(language, hash, 'tt%s' % subtitle_info['imdb'].zfill(7), subtitle_info['napisId'])
|
||||
with ZipFile(BytesIO(subtitle_content)) as zf:
|
||||
subtitle.content = fix_line_ending(zf.open(zf.namelist()[0]).read())
|
||||
|
||||
return subtitle
|
||||
|
||||
def list_subtitles(self, video, languages):
|
||||
subtitles = [self.query(l, video.size, video.name, video.hashes['napisy24']) for l in languages]
|
||||
return [s for s in subtitles if s is not None]
|
||||
|
||||
def download_subtitle(self, subtitle):
|
||||
# there is no download step, content is already filled from listing subtitles
|
||||
pass
|
||||
@@ -4,34 +4,24 @@ import io
|
||||
import logging
|
||||
import os
|
||||
import time
|
||||
import traceback
|
||||
|
||||
import requests
|
||||
|
||||
import inflect
|
||||
import re
|
||||
import json
|
||||
import HTMLParser
|
||||
import urlparse
|
||||
|
||||
from zipfile import ZipFile
|
||||
from babelfish import language_converters
|
||||
from guessit import guessit
|
||||
from dogpile.cache.api import NO_VALUE
|
||||
from subliminal import Episode, ProviderError
|
||||
from subliminal.exceptions import ConfigurationError, ServiceUnavailable
|
||||
from subliminal.utils import sanitize_release_group
|
||||
from subliminal.cache import region
|
||||
from subliminal_patch.http import RetryingCFSession
|
||||
from subliminal_patch.providers import Provider
|
||||
from subliminal_patch.providers.mixins import ProviderSubtitleArchiveMixin
|
||||
from subliminal_patch.subtitle import Subtitle, guess_matches
|
||||
from subliminal_patch.converters.subscene import language_ids, supported_languages
|
||||
from subscene_api.subscene import search, Subtitle as APISubtitle, SITE_DOMAIN
|
||||
from subscene_api.subscene import search, Subtitle as APISubtitle
|
||||
from subzero.language import Language
|
||||
|
||||
p = inflect.engine()
|
||||
|
||||
|
||||
language_converters.register('subscene = subliminal_patch.converters.subscene:SubsceneConverter')
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -122,106 +112,28 @@ class SubsceneProvider(Provider, ProviderSubtitleArchiveMixin):
|
||||
skip_wrong_fps = False
|
||||
hearing_impaired_verifiable = True
|
||||
only_foreign = False
|
||||
username = None
|
||||
password = None
|
||||
|
||||
search_throttle = 8 # seconds
|
||||
|
||||
def __init__(self, only_foreign=False, username=None, password=None):
|
||||
if not all((username, password)):
|
||||
raise ConfigurationError('Username and password must be specified')
|
||||
search_throttle = 2 # seconds
|
||||
|
||||
def __init__(self, only_foreign=False):
|
||||
self.only_foreign = only_foreign
|
||||
self.username = username
|
||||
self.password = password
|
||||
|
||||
def initialize(self):
|
||||
logger.info("Creating session")
|
||||
self.session = RetryingCFSession()
|
||||
|
||||
prev_cookies = region.get("subscene_cookies2")
|
||||
if prev_cookies != NO_VALUE:
|
||||
logger.debug("Re-using old subscene cookies: %r", prev_cookies)
|
||||
self.session.cookies.update(prev_cookies)
|
||||
|
||||
else:
|
||||
logger.debug("Logging in")
|
||||
self.login()
|
||||
|
||||
def login(self):
|
||||
r = self.session.get("https://subscene.com/account/login")
|
||||
if "Server Error" in r.content:
|
||||
logger.error("Login unavailable; Maintenance?")
|
||||
raise ServiceUnavailable("Login unavailable; Maintenance?")
|
||||
|
||||
match = re.search(r"<script id='modelJson' type='application/json'>\s*(.+)\s*</script>", r.content)
|
||||
|
||||
if match:
|
||||
h = HTMLParser.HTMLParser()
|
||||
data = json.loads(h.unescape(match.group(1)))
|
||||
login_url = urlparse.urljoin(data["siteUrl"], data["loginUrl"])
|
||||
time.sleep(1.0)
|
||||
|
||||
r = self.session.post(login_url,
|
||||
{
|
||||
"username": self.username,
|
||||
"password": self.password,
|
||||
data["antiForgery"]["name"]: data["antiForgery"]["value"]
|
||||
})
|
||||
pep_content = re.search(r"<form method=\"post\" action=\"https://subscene\.com/\">"
|
||||
r".+name=\"id_token\".+?value=\"(?P<id_token>.+?)\".*?"
|
||||
r"access_token\".+?value=\"(?P<access_token>.+?)\".+?"
|
||||
r"token_type.+?value=\"(?P<token_type>.+?)\".+?"
|
||||
r"expires_in.+?value=\"(?P<expires_in>.+?)\".+?"
|
||||
r"scope.+?value=\"(?P<scope>.+?)\".+?"
|
||||
r"state.+?value=\"(?P<state>.+?)\".+?"
|
||||
r"session_state.+?value=\"(?P<session_state>.+?)\"",
|
||||
r.content, re.MULTILINE | re.DOTALL)
|
||||
|
||||
if pep_content:
|
||||
r = self.session.post(SITE_DOMAIN, pep_content.groupdict())
|
||||
try:
|
||||
r.raise_for_status()
|
||||
except Exception:
|
||||
raise ProviderError("Something went wrong when trying to log in: %s", traceback.format_exc())
|
||||
else:
|
||||
cj = self.session.cookies.copy()
|
||||
store_cks = ("scene", "idsrv", "idsrv.xsrf", "idsvr.clients", "idsvr.session", "idsvr.username")
|
||||
for cn in self.session.cookies.iterkeys():
|
||||
if cn not in store_cks:
|
||||
del cj[cn]
|
||||
|
||||
logger.debug("Storing cookies: %r", cj)
|
||||
region.set("subscene_cookies2", cj)
|
||||
return
|
||||
raise ProviderError("Something went wrong when trying to log in #1")
|
||||
|
||||
def terminate(self):
|
||||
logger.info("Closing session")
|
||||
self.session.close()
|
||||
|
||||
def _create_filters(self, languages):
|
||||
self.filters = dict(HearingImpaired="2")
|
||||
acc_filters = self.filters.copy()
|
||||
if self.only_foreign:
|
||||
self.filters["ForeignOnly"] = "True"
|
||||
acc_filters["ForeignOnly"] = self.filters["ForeignOnly"].lower()
|
||||
logger.info("Only searching for foreign/forced subtitles")
|
||||
|
||||
selected_ids = []
|
||||
for l in languages:
|
||||
lid = language_ids.get(l.basename, language_ids.get(l.alpha3, None))
|
||||
if lid:
|
||||
selected_ids.append(str(lid))
|
||||
|
||||
acc_filters["SelectedIds"] = selected_ids
|
||||
self.filters["LanguageFilter"] = ",".join(acc_filters["SelectedIds"])
|
||||
|
||||
last_filters = region.get("subscene_filters")
|
||||
if last_filters != acc_filters:
|
||||
region.set("subscene_filters", acc_filters)
|
||||
logger.debug("Setting account filters to %r", acc_filters)
|
||||
self.session.post("https://u.subscene.com/filter", acc_filters, allow_redirects=False)
|
||||
self.filters["LanguageFilter"] = ",".join((str(language_ids[l.alpha3]) for l in languages
|
||||
if l.alpha3 in language_ids))
|
||||
|
||||
logger.debug("Filter created: '%s'" % self.filters)
|
||||
|
||||
@@ -264,11 +176,7 @@ class SubsceneProvider(Provider, ProviderSubtitleArchiveMixin):
|
||||
def parse_results(self, video, film):
|
||||
subtitles = []
|
||||
for s in film.subtitles:
|
||||
try:
|
||||
subtitle = SubsceneSubtitle.from_api(s)
|
||||
except NotImplementedError, e:
|
||||
logger.info(e)
|
||||
continue
|
||||
subtitle = SubsceneSubtitle.from_api(s)
|
||||
subtitle.asked_for_release_group = video.release_group
|
||||
if isinstance(video, Episode):
|
||||
subtitle.asked_for_episode = video.episode
|
||||
@@ -281,16 +189,10 @@ class SubsceneProvider(Provider, ProviderSubtitleArchiveMixin):
|
||||
|
||||
return subtitles
|
||||
|
||||
def do_search(self, *args, **kwargs):
|
||||
try:
|
||||
return search(*args, **kwargs)
|
||||
except requests.HTTPError:
|
||||
region.delete("subscene_cookies2")
|
||||
|
||||
def query(self, video):
|
||||
# vfn = get_video_filename(video)
|
||||
vfn = get_video_filename(video)
|
||||
subtitles = []
|
||||
# logger.debug(u"Searching for: %s", vfn)
|
||||
#logger.debug(u"Searching for: %s", vfn)
|
||||
# film = search(vfn, session=self.session)
|
||||
#
|
||||
# if film and film.subtitles:
|
||||
@@ -299,17 +201,16 @@ class SubsceneProvider(Provider, ProviderSubtitleArchiveMixin):
|
||||
# else:
|
||||
# logger.debug('No release results found')
|
||||
|
||||
# time.sleep(self.search_throttle)
|
||||
#time.sleep(self.search_throttle)
|
||||
|
||||
# re-search for episodes without explicit release name
|
||||
if isinstance(video, Episode):
|
||||
titles = list(set([video.series] + video.alternative_series))[:2]
|
||||
# term = u"%s S%02iE%02i" % (video.series, video.season, video.episode)
|
||||
more_than_one = len(titles) > 1
|
||||
for series in titles:
|
||||
#term = u"%s S%02iE%02i" % (video.series, video.season, video.episode)
|
||||
more_than_one = len([video.series] + video.alternative_series) > 1
|
||||
for series in [video.series] + video.alternative_series:
|
||||
term = u"%s - %s Season" % (series, p.number_to_words("%sth" % video.season).capitalize())
|
||||
logger.debug('Searching for alternative results: %s', term)
|
||||
film = self.do_search(term, session=self.session, release=False, throttle=self.search_throttle)
|
||||
film = search(term, session=self.session, release=False, throttle=self.search_throttle)
|
||||
if film and film.subtitles:
|
||||
logger.debug('Alternative results found: %s', len(film.subtitles))
|
||||
subtitles += self.parse_results(video, film)
|
||||
@@ -317,27 +218,26 @@ class SubsceneProvider(Provider, ProviderSubtitleArchiveMixin):
|
||||
logger.debug('No alternative results found')
|
||||
|
||||
# packs
|
||||
# if video.season_fully_aired:
|
||||
# term = u"%s S%02i" % (series, video.season)
|
||||
# logger.debug('Searching for packs: %s', term)
|
||||
# time.sleep(self.search_throttle)
|
||||
# film = search(term, session=self.session, throttle=self.search_throttle)
|
||||
# if film and film.subtitles:
|
||||
# logger.debug('Pack results found: %s', len(film.subtitles))
|
||||
# subtitles += self.parse_results(video, film)
|
||||
# else:
|
||||
# logger.debug('No pack results found')
|
||||
# else:
|
||||
# logger.debug("Not searching for packs, because the season hasn't fully aired")
|
||||
if video.season_fully_aired:
|
||||
term = u"%s S%02i" % (series, video.season)
|
||||
logger.debug('Searching for packs: %s', term)
|
||||
time.sleep(self.search_throttle)
|
||||
film = search(term, session=self.session, throttle=self.search_throttle)
|
||||
if film and film.subtitles:
|
||||
logger.debug('Pack results found: %s', len(film.subtitles))
|
||||
subtitles += self.parse_results(video, film)
|
||||
else:
|
||||
logger.debug('No pack results found')
|
||||
else:
|
||||
logger.debug("Not searching for packs, because the season hasn't fully aired")
|
||||
if more_than_one:
|
||||
time.sleep(self.search_throttle)
|
||||
else:
|
||||
titles = list(set([video.title] + video.alternative_titles))[:2]
|
||||
more_than_one = len(titles) > 1
|
||||
for title in titles:
|
||||
logger.debug('Searching for movie results: %r', title)
|
||||
film = self.do_search(title, year=video.year, session=self.session, limit_to=None, release=False,
|
||||
throttle=self.search_throttle)
|
||||
more_than_one = len([video.title] + video.alternative_titles) > 1
|
||||
for title in [video.title] + video.alternative_titles:
|
||||
logger.debug('Searching for movie results: %s', title)
|
||||
film = search(title, year=video.year, session=self.session, limit_to=None, release=False,
|
||||
throttle=self.search_throttle)
|
||||
if film and film.subtitles:
|
||||
subtitles += self.parse_results(video, film)
|
||||
if more_than_one:
|
||||
|
||||
@@ -226,7 +226,7 @@ class TitloviProvider(Provider, ProviderSubtitleArchiveMixin):
|
||||
page_link = self.server_url + sub.a.attrs['href']
|
||||
# subtitle language
|
||||
_lang = sub.select_one('.lang')
|
||||
match = lang_re.search(_lang.attrs.get('src', _lang.attrs.get('data-cfsrc', '')))
|
||||
match = lang_re.search(_lang.attrs.get('src', _lang.attrs.get('cfsrc', '')))
|
||||
if match:
|
||||
try:
|
||||
# decode language
|
||||
|
||||
@@ -117,14 +117,14 @@ class Subtitle(Subtitle_):
|
||||
|
||||
logger.info('Guessing encoding for language %s', self.language)
|
||||
|
||||
encodings = ['utf-8']
|
||||
encodings = ['utf-8', 'utf-16']
|
||||
|
||||
# add language-specific encodings
|
||||
# http://scratchpad.wikia.com/wiki/Character_Encoding_Recommendation_for_Languages
|
||||
|
||||
if self.language.alpha3 == 'zho':
|
||||
encodings.extend(['cp936', 'gb2312', 'gbk', 'gb18030', 'hz', 'iso2022_jp_2', 'cp950', 'gb18030', 'big5',
|
||||
'big5hkscs', 'utf-16'])
|
||||
'big5hkscs'])
|
||||
elif self.language.alpha3 == 'jpn':
|
||||
encodings.extend(['shift-jis', 'cp932', 'euc_jp', 'iso2022_jp', 'iso2022_jp_1', 'iso2022_jp_2',
|
||||
'iso2022_jp_2004', 'iso2022_jp_3', 'iso2022_jp_ext', ])
|
||||
@@ -133,7 +133,7 @@ class Subtitle(Subtitle_):
|
||||
|
||||
# arabian/farsi
|
||||
elif self.language.alpha3 in ('ara', 'fas', 'per'):
|
||||
encodings.extend(['windows-1256', 'utf-16'])
|
||||
encodings.append('windows-1256')
|
||||
elif self.language.alpha3 == 'heb':
|
||||
encodings.extend(['windows-1255', 'iso-8859-8'])
|
||||
elif self.language.alpha3 == 'tur':
|
||||
@@ -251,7 +251,8 @@ class Subtitle(Subtitle_):
|
||||
subs = pysubs2.SSAFile.from_string(text, fps=self.plex_media_fps)
|
||||
|
||||
unicontent = self.pysubs2_to_unicode(subs)
|
||||
self.content = unicontent.encode(self._guessed_encoding)
|
||||
self.content = unicontent.encode("utf-8")
|
||||
self._guessed_encoding = "utf-8"
|
||||
except:
|
||||
logger.exception("Couldn't convert subtitle %s to .srt format: %s", self, traceback.format_exc())
|
||||
return False
|
||||
@@ -319,8 +320,7 @@ class Subtitle(Subtitle_):
|
||||
:return: string
|
||||
"""
|
||||
if not self.mods:
|
||||
return fix_text(self.content.decode(encoding=self._guessed_encoding), **ftfy_defaults).encode(
|
||||
encoding=self._guessed_encoding)
|
||||
return fix_text(self.content.decode("utf-8"), **ftfy_defaults).encode(encoding="utf-8")
|
||||
|
||||
submods = SubtitleModifications(debug=debug)
|
||||
if submods.load(content=self.text, language=self.language):
|
||||
@@ -329,7 +329,7 @@ class Subtitle(Subtitle_):
|
||||
self.mods = submods.mods_used
|
||||
|
||||
content = fix_text(self.pysubs2_to_unicode(submods.f, format=format), **ftfy_defaults)\
|
||||
.encode(encoding=self._guessed_encoding)
|
||||
.encode(encoding="utf-8")
|
||||
submods.f = None
|
||||
del submods
|
||||
return content
|
||||
|
||||
@@ -21,7 +21,7 @@ if debug:
|
||||
logging.basicConfig(level=logging.DEBUG)
|
||||
|
||||
#sub = Subtitle(Language.fromietf("eng:forced"), mods=["common", "remove_HI", "OCR_fixes", "fix_uppercase", "shift_offset(ms=-500)", "shift_offset(ms=500)", "shift_offset(s=2,ms=800)"])
|
||||
sub = Subtitle(Language.fromietf("eng"), mods=["common", "remove_HI", "OCR_fixes", "fix_uppercase", "shift_offset(ms=0,s=1)"])
|
||||
sub = Subtitle(Language.fromietf("eng:forced"), mods=["common", "remove_HI", "OCR_fixes", "fix_uppercase", "shift_offset(ms=0,s=1)"])
|
||||
sub.content = open(fn).read()
|
||||
sub.normalize()
|
||||
content = sub.get_modified_content(debug=True)
|
||||
|
||||
@@ -30,7 +30,6 @@ import enum
|
||||
import sys
|
||||
import requests
|
||||
import time
|
||||
import logging
|
||||
|
||||
is_PY2 = sys.version_info[0] < 3
|
||||
if is_PY2:
|
||||
@@ -40,13 +39,8 @@ else:
|
||||
from contextlib import suppress
|
||||
from urllib2.request import Request, urlopen
|
||||
|
||||
from dogpile.cache.api import NO_VALUE
|
||||
from subliminal.cache import region
|
||||
from bs4 import BeautifulSoup, NavigableString
|
||||
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# constants
|
||||
HEADERS = {
|
||||
}
|
||||
@@ -56,21 +50,14 @@ DEFAULT_USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_3) AppleWeb"\
|
||||
"Kit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.47 Safari/537.36"
|
||||
|
||||
|
||||
ENDPOINT_RE = re.compile(ur'(?uis)<form.+?action="/subtitles/(.+)">.*?<input type="text"')
|
||||
|
||||
|
||||
class NewEndpoint(Exception):
|
||||
pass
|
||||
|
||||
|
||||
# utils
|
||||
def soup_for(url, data=None, session=None, user_agent=DEFAULT_USER_AGENT):
|
||||
def soup_for(url, session=None, user_agent=DEFAULT_USER_AGENT):
|
||||
url = re.sub("\s", "+", url)
|
||||
if not session:
|
||||
r = Request(url, data=None, headers=dict(HEADERS, **{"User-Agent": user_agent}))
|
||||
html = urlopen(r).read().decode("utf-8")
|
||||
else:
|
||||
ret = session.post(url, data=data)
|
||||
ret = session.get(url)
|
||||
ret.raise_for_status()
|
||||
html = ret.text
|
||||
return BeautifulSoup(html, "html.parser")
|
||||
@@ -125,7 +112,7 @@ class Subtitle(object):
|
||||
subtitles = []
|
||||
|
||||
for row in rows:
|
||||
if row.td.a is not None and row.td.get("class", ["lazy"])[0] != "empty":
|
||||
if row.td.a is not None:
|
||||
subtitles.append(cls.from_row(row))
|
||||
|
||||
return subtitles
|
||||
@@ -255,42 +242,29 @@ def get_first_film(soup, section, year=None, session=None):
|
||||
url = SITE_DOMAIN + t.div.a.get("href")
|
||||
break
|
||||
if not url:
|
||||
# fallback to non-year results
|
||||
logger.info("Falling back to non-year results as year wasn't found (%s)", year)
|
||||
url = SITE_DOMAIN + tag.findNext("ul").find("li").div.a.get("href")
|
||||
return
|
||||
|
||||
return Film.from_url(url, session=session)
|
||||
|
||||
|
||||
def find_endpoint(session, content=None):
|
||||
endpoint = region.get("subscene_endpoint2")
|
||||
if endpoint is NO_VALUE:
|
||||
if not content:
|
||||
content = session.get(SITE_DOMAIN).text
|
||||
|
||||
m = ENDPOINT_RE.search(content)
|
||||
if m:
|
||||
endpoint = m.group(1).strip()
|
||||
logger.debug("Switching main endpoint to %s", endpoint)
|
||||
region.set("subscene_endpoint2", endpoint)
|
||||
return endpoint
|
||||
|
||||
|
||||
def search(term, release=True, session=None, year=None, limit_to=SearchTypes.Exact, throttle=0):
|
||||
# note to subscene: if you actually start to randomize the endpoint, we'll have to query your server even more
|
||||
|
||||
endpoints = ["searching", "search", "srch", "find"]
|
||||
if release:
|
||||
endpoint = "release"
|
||||
else:
|
||||
endpoint = find_endpoint(session)
|
||||
time.sleep(throttle)
|
||||
endpoints = ["release"]
|
||||
|
||||
if not endpoint:
|
||||
logger.error("Couldn't find endpoint, exiting")
|
||||
return
|
||||
|
||||
soup = soup_for("%s/subtitles/%s" % (SITE_DOMAIN, endpoint), data={"query": term},
|
||||
session=session)
|
||||
soup = None
|
||||
for endpoint in endpoints:
|
||||
try:
|
||||
soup = soup_for("%s/subtitles/%s?q=%s" % (SITE_DOMAIN, endpoint, term),
|
||||
session=session)
|
||||
except requests.HTTPError, e:
|
||||
if e.response.status_code == 404:
|
||||
time.sleep(throttle)
|
||||
# fixme: detect endpoint from html
|
||||
continue
|
||||
raise
|
||||
break
|
||||
|
||||
if soup:
|
||||
if "Subtitle search by" in str(soup):
|
||||
|
||||
@@ -8,25 +8,6 @@ repl_map = {
|
||||
"dk": "da",
|
||||
"nld": "nl",
|
||||
"english": "en",
|
||||
"alb": "sq",
|
||||
"arm": "hy",
|
||||
"baq": "eu",
|
||||
"bur": "my",
|
||||
"chi": "zh",
|
||||
"cze": "cs",
|
||||
"dut": "nl",
|
||||
"fre": "fr",
|
||||
"geo": "ka",
|
||||
"ger": "de",
|
||||
"gre": "el",
|
||||
"ice": "is",
|
||||
"mac": "mk",
|
||||
"mao": "mi",
|
||||
"may": "ms",
|
||||
"per": "fa",
|
||||
"rum": "ro",
|
||||
"slo": "sk",
|
||||
"tib": "bo",
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -42,7 +42,7 @@ data = {'bos': {'BeginLines': {'data': OrderedDict(),
|
||||
'pattern': u"(?um)(?:\\,\\ sin|\\ mothen|\\ can\\'t\\_|\\ openiL|\\ of\\\ufb02|pshycol|\\ i\\.\\.\\.|\\ L\\.)$"},
|
||||
'PartialLines': {'data': OrderedDict([(u' /be ', u' I be '), (u" aren '1'", u" aren't"), (u" aren'tyou", u" aren't you"), (u" doesn '1'", u" doesn't"), (u" fr/eno'", u' friend'), (u" fr/eno'.", u' friend.'), (u" haven 'z' ", u" haven't "), (u" haven 'z'.", u" haven't."), (u' I ha ve ', u' I have '), (u" I']I ", u" I'll "), (u' L am', u' I am'), (u' L can', u' I can'), (u" L don't ", u" I don't "), (u' L hate ', u' I hate '), (u' L have ', u' I have '), (u' L like ', u' I like '), (u' L will', u' I will'), (u' L would', u' I would'), (u" L'll ", u" I'll "), (u" L've ", u" I've "), (u' m y family', u' my family'), (u" 's ", u"'s "), (u" shou/dn '1 ", u" shouldn't "), (u" won 'z' ", u" won't "), (u" won 'z'.", u" won't."), (u" wou/c/n 'z' ", u" wouldn't "), (u" wou/c/n 'z'.", u" wouldn't."), (u" wou/dn 'z' ", u" wouldn't "), (u" wou/dn 'z'.", u" wouldn't."), (u'/ did', u'I did'), (u'/ have ', u'I have '), (u'/ just ', u'I just '), (u'/ loved ', u'I loved '), (u'/ need', u'I need'), (u'|was11', u'I was 11'), (u'at Hrst', u'at first'), (u"B ullshiz'", u'Bullshit'), (u'big lunk', u'love you'), (u"can 't", u"can't"), (u"can' t ", u"can't "), (u"can 't ", u"can't "), (u'CHA TTERING', u'CHATTERING'), (u'come 0n', u'come on'), (u'Come 0n', u'Come on'), (u"couldn 't", u"couldn't"), (u"couldn' t ", u"couldn't "), (u"couldn 't ", u"couldn't "), (u"Destin y's", u"Destiny's"), (u"didn 't", u"didn't"), (u"didn' t ", u"didn't "), (u"didn 't ", u"didn't "), (u"Doesn '1'", u"Doesn't"), (u"doesn '1' ", u"doesn't "), (u"doesn '1\u2018 ", u"doesn't "), (u"doesn 't", u"doesn't"), (u"doesn'1' ", u"doesn't "), (u"doesn'1\u2018 ", u"doesn't "), (u"don '1' ", u"don't "), (u"don '1\u2018 ", u"don't "), (u"don '2' ", u"don't "), (u" aren '2'", u" aren't"), (u"aren '2' ", u"aren't "), (u"don '2\u2018 ", u"don't "), (u"don 't", u"don't"), (u"Don' t ", u"Don't "), (u"Don 't ", u"Don't "), (u"don'1' ", u"don't "), (u"don'1\u2018 ", u"don't "), (u"there '5 ", u"there's "), (u'E very', u'Every'), (u'get 0n', u'get on'), (u'go 0n', u'go on'), (u'Go 0n', u'Go on'), (u"H3993' birthday", u'Happy birthday'), (u"hadn 't", u"hadn't"), (u"he 's", u"he's"), (u"He 's", u"He's"), (u'He y', u'Hey'), (u'he)/', u'hey'), (u'He)/', u'Hey'), (u'HEA VY', u'HEAVY'), (u'Henry ll', u'Henry II'), (u'Henry lll', u'Henry III'), (u'Henry Vlll', u'Henry VIII'), (u'Henry Vll', u'Henry VII'), (u'Henry Vl', u'Henry VI'), (u'Hold 0n', u'Hold on'), (u'I am. ls', u'I am. Is'), (u'I d0', u'I do'), (u"I 'm", u"I'm"), (u"I 'rn ", u"I'm "), (u"I 've", u"I've"), (u'I0 ve her', u'love her'), (u'I0 ve you', u'love you'), (u"I02'", u'lot'), (u"I'm sony", u"I'm sorry"), (u"isn' t ", u"isn't "), (u"isn 't ", u"isn't "), (u'K)/le', u'Kyle'), (u'L ook', u'Look'), (u'let me 90', u'let me go'), (u'Let me 90', u'Let me go'), (u"let's 90", u"let's go"), (u"Let's 90", u"Let's go"), (u'lfl had', u'If I had'), (u'lova you', u'love you'), (u'Lova you', u'love you'), (u'lovo you', u'love you'), (u'Lovo you', u'love you'), (u'ls anyone', u'Is anyone'), (u'ls he', u'Is he'), (u'-ls he', u'- Is he'), (u'ls it', u'Is it'), (u'-ls it', u'- Is it'), (u'ls she', u'Is she'), (u'-ls she', u'- Is she'), (u'ls that', u'Is that'), (u'-ls that', u'- Is that'), (u'ls this', u'Is this'), (u'-ls this', u'- Is this'), (u'Maze] tov', u'Mazel tov'), (u"N02' ", u'Not '), (u' of 0ur ', u' of our '), (u' ot mine ', u' of mine '), (u'PLA YING', u'PLAYING'), (u'REPEA TING ', u'REPEATING '), (u'Sa y', u'Say'), (u"she 's", u"she's"), (u"She 's", u"She's"), (u"shouldn 't", u"shouldn't"), (u'sta y', u'stay'), (u'Sta y', u'Stay'), (u'SWO rd', u'Sword'), (u'taka care', u'take care'), (u'Taka care', u'Take care'), (u'the Hrst', u'the first'), (u'toc late', u'too late'), (u'uf me', u'of me'), (u'uf our', u'of our'), (u'wa y', u'way'), (u'Wal-I\\/Iart', u'Wal-Mart'), (u"wasn '1' ", u"wasn't "), (u"Wasn '1' ", u"Wasn't "), (u"wasn '1\u2018 ", u"wasn't "), (u"Wasn '1\u2018 ", u"Wasn't "), (u"wasn 't", u"wasn't"), (u"Wasn 't", u"Wasn't"), (u"we 've", u"we've"), (u"We 've", u"We've"), (u"wem' off", u'went off'), (u"weren 't", u"weren't"), (u"who 's", u"who's"), (u"won 't", u"won't"), (u'would ha ve', u'would have '), (u"wouldn 't", u"wouldn't"), (u"Wouldn 't", u"Wouldn't"), (u'y()u', u'you'), (u'you QUYS', u'you guys'), (u"you' re ", u"you're "), (u"you 're ", u"you're "), (u"you 've", u"you've"), (u"You 've", u"You've"), (u"you' ve ", u"you've "), (u"you 've ", u"you've "), (u'aftera while', u'after a while'), (u'Aftera while', u'After a while'), (u'THUN DERCLAPS', u'THUNDERCLAPS'), (u'(BUZZI N G)', u'(BUZZING)'), (u'[BUZZI N G]', u'[BUZZING]'), (u'(G RU NTING', u'(GRUNTING'), (u'[G RU NTING', u'[GRUNTING'), (u'(G ROWLING', u'(GROWLING'), (u'[G ROWLING', u'[GROWLING'), (u' WAI LS)', u'WAILS)'), (u' WAI LS]', u'WAILS]'), (u'(scu RRYING)', u'(SCURRYING)'), (u'[scu RRYING]', u'[SCURRYING]'), (u'(GRUNT5)', u'(GRUNTS)'), (u'[GRUNT5]', u'[GRUNTS]'), (u'NARRA TOR:', u'NARRATOR:'), (u'(GROAN ING', u'(GROANING'), (u'[GROAN ING'Line truncated
|
||||
'pattern': u"(?um)(?:(?<=\\s)|(?<=^)|(?<=\\b))(?:\\ \\/be\\ |\\ aren\\ \\'1\\'|\\ aren\\'tyou|\\ doesn\\ \\'1\\'|\\ fr\\/eno\\'|\\ fr\\/eno\\'\\.|\\ haven\\ \\'z\\'\\ |\\ haven\\ \\'z\\'\\.|\\ I\\ ha\\ ve\\ |\\ I\\'\\]I\\ |\\ L\\ am|\\ L\\ can|\\ L\\ don\\'t\\ |\\ L\\ hate\\ |\\ L\\ have\\ |\\ L\\ like\\ |\\ L\\ will|\\ L\\ would|\\ L\\'ll\\ |\\ L\\'ve\\ |\\ m\\ y\\ family|\\ \\'s\\ |\\ shou\\/dn\\ \\'1\\ |\\ won\\ \\'z\\'\\ |\\ won\\ \\'z\\'\\.|\\ wou\\/c\\/n\\ \\'z\\'\\ |\\ wou\\/c\\/n\\ \\'z\\'\\.|\\ wou\\/dn\\ \\'z\\'\\ |\\ wou\\/dn\\ \\'z\\'\\.|\\/\\ did|\\/\\ have\\ |\\/\\ just\\ |\\/\\ loved\\ |\\/\\ need|\\|was11|at\\ Hrst|B\\ ullshiz\\'|big\\ lunk|can\\ \\'t|can\\'\\ t\\ |can\\ \\'t\\ |CHA\\ TTERING|come\\ 0n|Come\\ 0n|couldn\\ \\'t|couldn\\'\\ t\\ |couldn\\ \\'t\\ |Destin\\ y\\'s|didn\\ \\'t|didn\\'\\ t\\ |didn\\ \\'t\\ |Doesn\\ \\'1\\'|doesn\\ \\'1\\'\\ |doesn\\ \\'1\\\u2018\\ |doesn\\ \\'t|doesn\\'1\\'\\ |doesn\\'1\\\u2018\\ |don\\ \\'1\\'\\ |don\\ \\'1\\\u2018\\ |don\\ \\'2\\'\\ |\\ aren\\ \\'2\\'|aren\\ \\'2\\'\\ |don\\ \\'2\\\u2018\\ |don\\ \\'t|Don\\'\\ t\\ |Don\\ \\'t\\ |don\\'1\\'\\ |don\\'1\\\u2018\\ |there\\ \\'5\\ |E\\ very|get\\ 0n|go\\ 0n|Go\\ 0n|H3993\\'\\ birthday|hadn\\ \\'t|he\\ \\'s|He\\ \\'s|He\\ y|he\\)\\/|He\\)\\/|HEA\\ VY|Henry\\ ll|Henry\\ lll|Henry\\ Vlll|Henry\\ Vll|Henry\\ Vl|Hold\\ 0n|I\\ am\\.\\ ls|I\\ d0|I\\ \\'m|I\\ \\'rn\\ |I\\ \\'ve|I0\\ ve\\ her|I0\\ ve\\ you|I02\\'|I\\'m\\ sony|isn\\'\\ t\\ |isn\\ \\'t\\ |K\\)\\/le|L\\ ook|let\\ me\\ 90|Let\\ me\\ 90|let\\'s\\ 90|Let\\'s\\ 90|lfl\\ had|lova\\ you|Lova\\ you|lovo\\ you|Lovo\\ you|ls\\ anyone|ls\\ he|\\-ls\\ he|ls\\ it|\\-ls\\ it|ls\\ she|\\-ls\\ she|ls\\ that|\\-ls\\ that|ls\\ this|\\-ls\\ this|Maze\\]\\ tov|N02\\'\\ |\\ of\\ 0ur\\ |\\ ot\\ mine\\ |PLA\\ YING|REPEA\\ TING\\ |Sa\\ y|she\\ \\'s|She\\ \\'s|shouldn\\ \\'t|sta\\ y|Sta\\ y|SWO\\ rd|taka\\ care|Taka\\ care|the\\ Hrst|toc\\ late|uf\\ me|uf\\ our|wa\\ y|Wal\\-I\\\\\\/Iart|wasn\\ \\'1\\'\\ |Wasn\\ \\'1\\'\\ |wasn\\ \\'1\\\u2018\\ |Wasn\\ \\'1\\\u2018\\ |wasn\\ \\'t|Wasn\\ \\'t|we\\ \\'ve|We\\ \\'ve|wem\\'\\ off|weren\\ \\'t|who\\ \\'s|won\\ \\'t|would\\ ha\\ ve|wouldn\\ \\'t|Wouldn\\ \\'t|y\\(\\)u|you\\ QUYS|you\\'\\ re\\ |you\\ \\'re\\ |you\\ \\'ve|You\\ \\'ve|you\\'\\ ve\\ |you\\ \\'ve\\ |aftera\\ while|Aftera\\ while|THUN\\ DERCLAPS|\\(BUZZI\\ N\\ G\\)|\\[BUZZI\\ N\\ G\\]|\\(G\\ RU\\ NTING|\\[G\\ RU\\ NTING|\\(G\\ ROWLING|\\[G\\ ROWLING|\\ WAI\\ LS\\)|\\ WAI\\ LS\\]|\\(scu\\ RRYING\\)|\\[scu\\ RRYING\\]|\\(GRUNT5\\)|\\[GRUNT5\\]|NARRA\\ TOR\\:|\\(GROAN\\ ING|\\[GROAN\\ ING|GROAN\\ ING\\)|GROAN\\ ING\\]|\\(LAUGH\\ ING|\\[LAUGH\\ ING|LAUGH\\ ING\\)|LAUGH\\ ING\\]|\\(BU\\ BBLING|\\[BU\\ BBLING|BU\\ BBLING\\)|BU\\ BBLING\\]|\\(SH\\ USHING|\\[SH\\ USHING|SH\\ USHING\\)|SH\\ USHING\\]|\\(CH\\ ILDREN|\\[CH\\ ILDREN|CH\\ ILDREN\\)|CH\\ ILDREN\\]|\\(MURMU\\ RING|\\[MURMU\\ RING|MURMU\\ RING\\)|MURMU\\ RING\\]|\\(GU\\ N\\ |\\[GU\\ N\\ |GU\\ N\\)|GU\\ N\\]|CH\\ ILDREN\\:|STU\\ DENTS\\:|\\(WH\\ ISTLE|\\[WH\\ ISTLE|WH\\ ISTLE\\)|WH\\ ISTLE\\]|U\\ LU\\ LATING|AU\\ DIENCE\\:|HA\\ WAIIAN|\\(ARTH\\ UR|\\[ARTH\\ UR|ARTH\\ UR\\)|ARTH\\ UR\\]|J\\ EREMY\\:|\\(ELEVA\\ TOR|\\[ELEVA\\ TOR|ELEVA\\ TOR\\)|ELEVA\\ TOR\\]|CONTIN\\ U\\ ES|WIN\\ D\\ HOWLING|telis\\ me|Telis\\ me|\\.\\ Ls\\ |\\!\\ Ls\\ |\\?\\ Ls\\ |\\.\\ Lt\\ |\\!\\ Lt\\ |\\?\\ Lt\\ |SQMEWH\\ ERE\\ ELSE|\\ I\\,m\\ |\\ I\\,ve\\ |\\ you\\,re\\ |\\ you\\,ll\\ |\\ doesn\\,t\\ |\\ let\\,s\\ |\\ he\\,s\\ |\\ it\\,s\\ |\\ can\\,t\\ |\\ Can\\,t\\ |\\ don\\,t\\ |\\ Don\\,t\\ |wouldn\\ \\'tyou|\\ lgot\\ it|\\ you\\,ve\\ |\\ I\\ ve\\ |\\ I\\ ii\\ |\\ I\\ m\\ |\\ why\\ d\\ |\\ couldn\\ t\\ |\\ that\\ s\\ |\\ i\\.\\.\\.\\ |L\\ don\\'t|L\\ won\\'t|L\\ should|L\\ had|L\\ happen|L\\ wasn\\'t|H\\ i|L\\ didn\\'t|L\\ do|L\\ could|L\\ will|L\\ suggest|L\\ reckon|L\\ am|L\\ couldn\\'t|L\\ might|L\\ would|L\\ was|L\\ know|L\\ think|L\\ haven\\'t|L\\ have\\ |L\\ want|L\\ can|L\\ love|L\\ like)(?:(?=\\s)|(?=$)|(?=\\b))"},
|
||||
'PartialWordsAlways': {'data': OrderedDict([(u'\xa4', u'o'), (u'lVI', u'M'), (u'IVl', u'M'), (u'lVl', u'M'), (u'I\\/I', u'M'), (u'l\\/I', u'M'), (u'I\\/l', u'M'), (u'l\\/l', u'M'), (u'IVIa', u'Ma'), (u'IVIe', u'Me'), (u'IVIi', u'Mi'), (u'IVIo', u'Mo'), (u'IVIu', u'Mu'), (u'IVIy', u'My'), (u' l ', u' I '), (u'l/an', u'lian'), (u'\xb0x\xb0', u'%'), (u'\xc3\xc2s', u"'s"), (u'at/on', u'ation'), (u'lljust', u'll just'), (u"'sjust", u"'s just"), (u'";', u"'s"), (u'compiete', u'complete'), (u' L ', u' I '), (u'a/ion', u'ation'), (u'\xc2s', u"'s"), (u"'tjust", u"'t just")]),
|
||||
'PartialWordsAlways': {'data': OrderedDict([(u'\xa4', u'o'), (u'lVI', u'M'), (u'IVl', u'M'), (u'lVl', u'M'), (u'I\\/I', u'M'), (u'l\\/I', u'M'), (u'I\\/l', u'M'), (u'l\\/l', u'M'), (u'IVIa', u'Ma'), (u'IVIe', u'Me'), (u'IVIi', u'Mi'), (u'IVIo', u'Mo'), (u'IVIu', u'Mu'), (u'IVIy', u'My'), (u' l ', u' I '), (u'l/an', u'lian'), (u'\xb0x\xb0', u'%'), (u'\xc3\xc2s', u"'s"), (u'at/on', u'ation'), (u'lljust', u'll just'), (u"'sjust", u"'s just"), (u'compiete', u'complete'), (u' L ', u' I '), (u'a/ion', u'ation'), (u'\xc2s', u"'s"), (u"'tjust", u"'t just")]),
|
||||
'pattern': None},
|
||||
'WholeLines': {'data': OrderedDict([(u'H ey.', u'Hey.'), (u'He)\u2019-', u'Hey.'), (u'N0.', u'No.'), (u'-N0.', u'-No.'), (u'Noll', u'No!!'), (u'(G ROANS)', u'(GROANS)'), (u'[G ROANS]', u'[GROANS]'), (u'(M EOWS)', u'(MEOWS)'), (u'[M EOWS]', u'[MEOWS]'), (u'Uaughs]', u'[laughs]'), (u'[chitte rs]', u'[chitters]'), (u'Hil\u2018 it!', u'Hit it!'), (u'<i>Hil\u2018 it!</i>', u'<i>Hit it!</i>'), (u'ISIGHS]', u'[SIGHS]')]),
|
||||
'pattern': None},
|
||||
|
||||
@@ -36,7 +36,6 @@ SZ_FIX_DATA = {
|
||||
u" l ": u" I ",
|
||||
u"'sjust": u"'s just",
|
||||
u"'tjust": u"'t just",
|
||||
u"\";": u"'s",
|
||||
},
|
||||
"WholeWords": {
|
||||
u"I'11": u"I'll",
|
||||
|
||||
@@ -6,7 +6,7 @@ import pysubs2
|
||||
import logging
|
||||
import time
|
||||
|
||||
from mods import EMPTY_TAG_PROCESSOR, EmptyEntryError
|
||||
from mods import EMPTY_TAG_PROCESSOR, EmptyEntryError, FullContentRep
|
||||
from registry import registry
|
||||
from subzero.language import Language
|
||||
|
||||
@@ -257,7 +257,16 @@ class SubtitleModifications(object):
|
||||
mod.modify(None, debug=self.debug, parent=self, **args)
|
||||
|
||||
def apply_line_mods(self, new_entries, mods):
|
||||
for index, entry in enumerate(self.f, 1):
|
||||
index = 1
|
||||
entries = self.f[:]
|
||||
entry_count = len(entries)
|
||||
|
||||
while 1:
|
||||
if index > entry_count - 1:
|
||||
break
|
||||
|
||||
entry = entries[index]
|
||||
|
||||
applied_mods = []
|
||||
lines = []
|
||||
|
||||
@@ -265,116 +274,110 @@ class SubtitleModifications(object):
|
||||
start_tags = []
|
||||
end_tags = []
|
||||
|
||||
t = entry.text.strip()
|
||||
if not t:
|
||||
text = entry.text.replace(ur"\N", "\n").strip()
|
||||
if not text:
|
||||
if self.debug:
|
||||
logger.debug(u"Skipping empty line: %s", index)
|
||||
index += 1
|
||||
continue
|
||||
|
||||
skip_entry = False
|
||||
for line in t.split(ur"\N"):
|
||||
# don't bother the mods with surrounding tags
|
||||
old_line = line
|
||||
line = line.strip()
|
||||
skip_line = False
|
||||
line_count += 1
|
||||
try:
|
||||
for line in text.split("\n"):
|
||||
# don't bother the mods with surrounding tags
|
||||
old_line = line
|
||||
line = line.strip()
|
||||
skip_line = False
|
||||
line_count += 1
|
||||
|
||||
if not line:
|
||||
continue
|
||||
if not line:
|
||||
continue
|
||||
|
||||
# clean {\X0} tags before processing
|
||||
# fixme: handle nested tags?
|
||||
start_tag = u""
|
||||
end_tag = u""
|
||||
if line.startswith(self.font_style_tag_start):
|
||||
start_tag = line[:5]
|
||||
line = line[5:]
|
||||
if line[-5:-3] == self.font_style_tag_start:
|
||||
end_tag = line[-5:]
|
||||
line = line[:-5]
|
||||
# clean {\X0} tags before processing
|
||||
# fixme: handle nested tags?
|
||||
start_tag = u""
|
||||
end_tag = u""
|
||||
if line.startswith(self.font_style_tag_start):
|
||||
start_tag = line[:5]
|
||||
line = line[5:]
|
||||
if line[-5:-3] == self.font_style_tag_start:
|
||||
end_tag = line[-5:]
|
||||
line = line[:-5]
|
||||
|
||||
last_procs_mods = []
|
||||
last_procs_mods = []
|
||||
|
||||
# fixme: this double loop is ugly
|
||||
for order, identifier, args in mods:
|
||||
mod = self.initialized_mods[identifier]
|
||||
# fixme: this double loop is ugly
|
||||
for order, identifier, args in mods:
|
||||
mod = self.initialized_mods[identifier]
|
||||
|
||||
try:
|
||||
line = mod.modify(line.strip(), entry=entry.text, debug=self.debug, parent=self, index=index,
|
||||
line = mod.modify(line.strip(), entry=text, debug=self.debug, parent=self, index=index,
|
||||
**args)
|
||||
except EmptyEntryError:
|
||||
if self.debug:
|
||||
logger.debug(u"%d: %s: %r -> ''", index, identifier, entry.text)
|
||||
skip_entry = True
|
||||
break
|
||||
|
||||
if not line:
|
||||
if self.debug:
|
||||
logger.debug(u"%d: %s: %r -> ''", index, identifier, old_line)
|
||||
skip_line = True
|
||||
break
|
||||
if not line:
|
||||
if self.debug:
|
||||
logger.debug(u"%d: %s: %r -> ''", index, identifier, old_line)
|
||||
skip_line = True
|
||||
break
|
||||
|
||||
applied_mods.append(identifier)
|
||||
if mod.last_processors:
|
||||
last_procs_mods.append([identifier, args])
|
||||
applied_mods.append(identifier)
|
||||
if mod.last_processors:
|
||||
last_procs_mods.append([identifier, args])
|
||||
|
||||
if skip_entry:
|
||||
lines = []
|
||||
break
|
||||
if skip_line:
|
||||
continue
|
||||
|
||||
if skip_line:
|
||||
continue
|
||||
for identifier, args in last_procs_mods:
|
||||
mod = self.initialized_mods[identifier]
|
||||
|
||||
for identifier, args in last_procs_mods:
|
||||
mod = self.initialized_mods[identifier]
|
||||
|
||||
try:
|
||||
line = mod.modify(line.strip(), entry=entry.text, debug=self.debug, parent=self, index=index,
|
||||
line = mod.modify(line.strip(), entry=text, debug=self.debug, parent=self, index=index,
|
||||
procs=["last_process"], **args)
|
||||
except EmptyEntryError:
|
||||
|
||||
if not line:
|
||||
if self.debug:
|
||||
logger.debug(u"%d: %s: %r -> ''", index, identifier, old_line)
|
||||
skip_line = True
|
||||
break
|
||||
|
||||
if skip_line:
|
||||
continue
|
||||
|
||||
if start_tag:
|
||||
start_tags.append(start_tag)
|
||||
|
||||
if end_tag:
|
||||
end_tags.append(end_tag)
|
||||
|
||||
# append new line and clean possibly newly added empty tags
|
||||
cleaned_line = EMPTY_TAG_PROCESSOR.process(start_tag + line + end_tag, debug=self.debug).strip()
|
||||
if cleaned_line:
|
||||
# we may have a single closing tag, if so, try appending it to the previous line
|
||||
if len(cleaned_line) == 5 and cleaned_line.startswith("{\\") and cleaned_line.endswith("0}"):
|
||||
if lines:
|
||||
prev_line = lines.pop()
|
||||
lines.append(prev_line + cleaned_line)
|
||||
continue
|
||||
|
||||
lines.append(cleaned_line)
|
||||
else:
|
||||
if self.debug:
|
||||
logger.debug(u"%d: %s: %r -> ''", index, identifier, entry.text)
|
||||
skip_entry = True
|
||||
break
|
||||
logger.debug(u"%d: Ditching now empty line (%r)", index, line)
|
||||
|
||||
if not line:
|
||||
if self.debug:
|
||||
logger.debug(u"%d: %s: %r -> ''", index, identifier, old_line)
|
||||
skip_line = True
|
||||
break
|
||||
|
||||
if skip_entry:
|
||||
lines = []
|
||||
break
|
||||
|
||||
if skip_line:
|
||||
if not lines:
|
||||
# don't bother logging when the entry only had one line
|
||||
if self.debug and line_count > 1:
|
||||
logger.debug(u"%d: %r -> ''", index, text)
|
||||
index += 1
|
||||
continue
|
||||
except EmptyEntryError, e:
|
||||
if self.debug:
|
||||
logger.debug(u"%d: %s: %r -> ''", index, e.mod.identifier, e.entry)
|
||||
index += 1
|
||||
continue
|
||||
|
||||
if start_tag:
|
||||
start_tags.append(start_tag)
|
||||
|
||||
if end_tag:
|
||||
end_tags.append(end_tag)
|
||||
|
||||
# append new line and clean possibly newly added empty tags
|
||||
cleaned_line = EMPTY_TAG_PROCESSOR.process(start_tag + line + end_tag, debug=self.debug).strip()
|
||||
if cleaned_line:
|
||||
# we may have a single closing tag, if so, try appending it to the previous line
|
||||
if len(cleaned_line) == 5 and cleaned_line.startswith("{\\") and cleaned_line.endswith("0}"):
|
||||
if lines:
|
||||
prev_line = lines.pop()
|
||||
lines.append(prev_line + cleaned_line)
|
||||
continue
|
||||
|
||||
lines.append(cleaned_line)
|
||||
else:
|
||||
if self.debug:
|
||||
logger.debug(u"%d: Ditching now empty line (%r)", index, line)
|
||||
|
||||
if not lines:
|
||||
# don't bother logging when the entry only had one line
|
||||
if self.debug and line_count > 1:
|
||||
logger.debug(u"%d: %r -> ''", index, entry.text)
|
||||
except FullContentRep, e:
|
||||
if self.debug:
|
||||
logger.debug(u"%d: %s: %r -> %r", index, e.mod.identifier, text, e.new_content)
|
||||
new_entries.append(e.new_content.replace("\n", ur"\N"))
|
||||
index += 1
|
||||
continue
|
||||
|
||||
new_text = ur"\N".join(lines)
|
||||
@@ -403,6 +406,8 @@ class SubtitleModifications(object):
|
||||
entry.text = new_text
|
||||
|
||||
new_entries.append(entry)
|
||||
index += 1
|
||||
|
||||
|
||||
SubMod = SubtitleModifications
|
||||
|
||||
|
||||
@@ -47,7 +47,7 @@ class SubtitleModification(object):
|
||||
continue
|
||||
|
||||
old_content = new_content
|
||||
new_content = processor.process(new_content, debug=debug, **kwargs)
|
||||
new_content = processor.process(new_content, debug=debug, mod=self, **kwargs)
|
||||
if not new_content:
|
||||
if debug:
|
||||
logger.debug("Processor returned empty line: %s", processor.name)
|
||||
@@ -107,9 +107,22 @@ empty_line_post_processors = [
|
||||
]
|
||||
|
||||
|
||||
class EmptyEntryError(Exception):
|
||||
class ModEvent(Exception):
|
||||
def __init__(self, *args, **kwargs):
|
||||
self.mod = kwargs.pop("mod", None)
|
||||
self.entry = kwargs.pop("entry", None)
|
||||
super(ModEvent, self).__init__(*args, **kwargs)
|
||||
|
||||
|
||||
class EmptyEntryError(ModEvent):
|
||||
pass
|
||||
|
||||
|
||||
class EmptyLineError(Exception):
|
||||
class EmptyLineError(ModEvent):
|
||||
pass
|
||||
|
||||
|
||||
class FullContentRep(ModEvent):
|
||||
def __init__(self, *args, **kwargs):
|
||||
self.new_content = kwargs.pop("new_content", None)
|
||||
super(FullContentRep, self).__init__(*args, **kwargs)
|
||||
@@ -1,7 +1,8 @@
|
||||
# coding=utf-8
|
||||
import re
|
||||
|
||||
from subzero.modification.mods import SubtitleTextModification, empty_line_post_processors, EmptyEntryError, TAG
|
||||
from subzero.modification.mods import SubtitleTextModification, empty_line_post_processors, EmptyEntryError, TAG, \
|
||||
FullContentRep
|
||||
from subzero.modification.processors.re_processor import NReProcessor
|
||||
from subzero.modification import registry
|
||||
|
||||
@@ -10,9 +11,11 @@ class FullBracketEntryProcessor(NReProcessor):
|
||||
def process(self, content, debug=False, **kwargs):
|
||||
entry = kwargs.get("entry")
|
||||
if entry:
|
||||
rep_content = super(FullBracketEntryProcessor, self).process(entry, debug=debug, **kwargs)
|
||||
if not rep_content.strip():
|
||||
raise EmptyEntryError()
|
||||
rep_content = super(FullBracketEntryProcessor, self).process(entry, debug=debug, **kwargs).strip()
|
||||
if not rep_content:
|
||||
raise EmptyEntryError(mod=self.mod, entry=entry)
|
||||
if content != rep_content:
|
||||
raise FullContentRep(new_content=rep_content, mod=self.mod, entry=entry)
|
||||
return content
|
||||
|
||||
|
||||
@@ -49,8 +52,8 @@ class HearingImpaired(SubtitleTextModification):
|
||||
NReProcessor(re.compile(ur'(?sux)-?%(t)s[([][^([)\]]+?(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+[)\]][\s:]*%(t)s' %
|
||||
{"t": TAG}), "", name="HI_brackets"),
|
||||
|
||||
#NReProcessor(re.compile(ur'(?sux)-?%(t)s[([]%(t)s(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+%(t)s$' % {"t": TAG}),
|
||||
# "", name="HI_bracket_open_start"),
|
||||
FullBracketEntryProcessor(re.compile(ur'(?sux)-?%(t)s[([]%(t)s(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+%(t)s$' % {"t": TAG}),
|
||||
"", name="HI_bracket_open_start"),
|
||||
|
||||
#NReProcessor(re.compile(ur'(?sux)-?%(t)s(?=[A-zÀ-ž"\'.]{3,})[^([)\]]+[)\]][\s:]*%(t)s' % {"t": TAG}), "",
|
||||
# name="HI_bracket_open_end"),
|
||||
|
||||
@@ -7,12 +7,14 @@ class Processor(object):
|
||||
"""
|
||||
name = None
|
||||
parent = None
|
||||
mod = None
|
||||
supported = None
|
||||
enabled = True
|
||||
|
||||
def __init__(self, name=None, parent=None, supported=None):
|
||||
def __init__(self, name=None, parent=None, mod=None, supported=None):
|
||||
self.name = name
|
||||
self.parent = parent
|
||||
self.mod = mod
|
||||
self.supported = supported if supported else lambda parent: True
|
||||
|
||||
@property
|
||||
@@ -20,6 +22,8 @@ class Processor(object):
|
||||
return self.name
|
||||
|
||||
def process(self, content, debug=False, **kwargs):
|
||||
if not self.mod:
|
||||
self.mod = kwargs.get("mod", None)
|
||||
return content
|
||||
|
||||
def __repr__(self):
|
||||
|
||||
@@ -14,12 +14,13 @@ class ReProcessor(Processor):
|
||||
pattern = None
|
||||
replace_with = None
|
||||
|
||||
def __init__(self, pattern, replace_with, name=None, supported=None):
|
||||
super(ReProcessor, self).__init__(name=name, supported=supported)
|
||||
def __init__(self, pattern, replace_with, name=None, supported=None, **kwargs):
|
||||
super(ReProcessor, self).__init__(name=name, supported=supported, **kwargs)
|
||||
self.pattern = pattern
|
||||
self.replace_with = replace_with
|
||||
|
||||
def process(self, content, debug=False, **kwargs):
|
||||
super(ReProcessor, self).process(content, debug=debug, **kwargs)
|
||||
return self.pattern.sub(self.replace_with, content)
|
||||
|
||||
|
||||
|
||||
@@ -52,10 +52,10 @@ def set_existing_languages(video, video_info, external_subtitles=False, embedded
|
||||
video.subtitle_languages.add(language)
|
||||
|
||||
|
||||
def parse_video(fn, hints, skip_hashing=False, dry_run=False, providers=None, hash_from=None):
|
||||
def parse_video(fn, hints, skip_hashing=False, dry_run=False, providers=None):
|
||||
logger.debug("Parsing video: %s, hints: %s", os.path.basename(fn), hints)
|
||||
return scan_video(fn, hints=hints, dont_use_actual_file=dry_run, providers=providers,
|
||||
skip_hashing=skip_hashing, hash_from=hash_from)
|
||||
skip_hashing=skip_hashing)
|
||||
|
||||
|
||||
def refine_video(video, no_refining=False, refiner_settings=None):
|
||||
|
||||
@@ -91,28 +91,28 @@ the.vbm, mmgoodnow, Vertig0ne, thliu78, tattoomees, ostman, count_confucius, ehe
|
||||
## Changelog
|
||||
|
||||
|
||||
2.6.5.3124
|
||||
2.6.5.3074
|
||||
|
||||
subscene, addic7ed and titlovi
|
||||
- either of those providers might impose a reCAPTCHA verification. In order to use those providers, please create an account at an AntiCaptcha service ([anti-captcha.com](http://getcaptchasolution.com/kkvviom7nh) or [deathbycaptcha.com](http://deathbycaptcha.com)), add funds, then supply your credentials/apikey in the configuration
|
||||
|
||||
Changelog
|
||||
- core: http: fallback to default DNS when normal resolving fails; fixes #657
|
||||
- core: extract embedded/menu: fix detection of unknown streams; don't use unknown streams if a known language was previously found
|
||||
- core: language: use replacement map from bazarr
|
||||
- providers: titlovi: fix matching
|
||||
- providers: subscene: fix unknown language code error when "empty" result is returned
|
||||
- providers: subscene: add support for pt-BR (based on Diaoul/subliminal@b22cf08)
|
||||
- providers: subscene: explicitly set account filters for languages
|
||||
- providers: subscene: limit alternative searches to 3; set throttle to 8
|
||||
- providers: subscene: move login/cookies to initialization sequence
|
||||
- submod: generic: en: fix ";='s
|
||||
- core: cf: bypass cf 95% of the time without captchas
|
||||
- core: fix breaking line endings of certain languages (chinese, UTF-16); fixes #646
|
||||
- core: update pysubs2 to 0.2.3
|
||||
|
||||
|
||||
2.6.5.3062
|
||||
|
||||
Changelog
|
||||
- core: cf: optimize
|
||||
- core: http: don't query DNS with IPs. thanks @fgump (fixes sonarr/radarr)
|
||||
|
||||
|
||||
[older changes](CHANGELOG.md)
|
||||
|
||||
|
||||
Subtitles provided by [OpenSubtitles.org](http://www.opensubtitles.org/), [Podnapisi.NET](https://www.podnapisi.net/), [TVSubtitles.net](http://www.tvsubtitles.net/), [Addic7ed.com](http://www.addic7ed.com/), [Legendas TV](http://legendas.tv/), [Napi Projekt](http://www.napiprojekt.pl/), [Shooter](http://shooter.cn/), [Titlovi](http://titlovi.com), [aRGENTeaM](http://argenteam.net), [SubScene](https://subscene.com/), [Hosszupuska](http://hosszupuskasub.com/), [Napisy24](https://napisy24.pl/)
|
||||
Subtitles provided by [OpenSubtitles.org](http://www.opensubtitles.org/), [Podnapisi.NET](https://www.podnapisi.net/), [TVSubtitles.net](http://www.tvsubtitles.net/), [Addic7ed.com](http://www.addic7ed.com/), [Legendas TV](http://legendas.tv/), [Napi Projekt](http://www.napiprojekt.pl/), [Shooter](http://shooter.cn/), [Titlovi](http://titlovi.com), [aRGENTeaM](http://argenteam.net), [SubScene](https://subscene.com/), [Hosszupuska](http://hosszupuskasub.com/)
|
||||
|
||||
[3rd party licenses](https://github.com/pannal/Sub-Zero.bundle/tree/master/Licenses)
|
||||
|
||||
|
||||
Reference in new issue
Block a user