submod: global: fix paragraph as music sign

This commit is contained in:
panni committed 2017-11-04 03:31:07 +01:00
1 parent 73bcfc6151
commit 7da48b7dc5
2 files changed
+24 -14

No files matched your search

@@ -6,7 +6,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict([(u'\xa4', u'o'), (u'IVI', u'M'), (u'lVI', u'M'), (u'IVl', u'M'), (u'lVl', u'M')]),
'PartialWordsAlways': {'data': OrderedDict([(u'\xa4', u'o'), (u'IVI', u'M'), (u'lVI', u'M'), (u'IVl', u'M'), (u'lVl', u'M'), (u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
@@ -18,7 +18,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict([(u'IVI', u'M'), (u'IVl', u'M'), (u'I\\/I', u'M'), (u'I\\/l', u'M'), (u'lVI', u'M'), (u'lVl', u'M'), (u'l\\/I', u'M'), (u'l\\/l', u'M'), (u'\xa4', u'o')]),
'PartialWordsAlways': {'data': OrderedDict([(u'IVI', u'M'), (u'IVl', u'M'), (u'I\\/I', u'M'), (u'I\\/l', u'M'), (u'lVI', u'M'), (u'lVl', u'M'), (u'l\\/I', u'M'), (u'l\\/l', u'M'), (u'\xa4', u'o'), (u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
@@ -30,7 +30,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': u"(?um)(?:\\,\\ sin|\\ mothen|\\ can\\'t\\_|\\ openiL|\\ of\\\ufb02|pshycol)$"},
'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'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', u'[GROANING'), (u'GROAN ING)', u'GROANING)'), (u'GROAN ING]', u'GROANING]'), (u'(LAUGH ING', u'(LAUGHING'), (u'[LAUGH ING', u'[LAUGHING'), (u'LAUGLine 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|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)(?:(?=\\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'\xc3\xc2s', u"'s"), (u'. L ', u'. I '), (u'a/ion', u'ation'), (u'compiete', u'complete'), (u'\xc2s', u"'s"), (u'at/on', u'ation'), (u'l/an', u'lian'), (u'\xb0x\xb0', u'%'), (u'lljust', u'll 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'\xc3\xc2s', u"'s"), (u'. L ', u'. I '), (u'a/ion', u'ation'), (u'compiete', u'complete'), (u'\xc2s', u"'s"), (u'at/on', u'ation'), (u'l/an', u'lian'), (u'\xb0x\xb0', u'%'), (u'lljust', u'll just'), (u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'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},
@@ -42,7 +42,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'PartialWordsAlways': {'data': OrderedDict([(u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict([(u'Katsokaa pa.', u'Katsokaapa.'), (u'Mik!\r\n""e\u201c9ir\xe4\u0131', u'Mik!\r\n-Hengit\xe4!'), (u'Tu lta!', u'Tulta!'), (u'...0I1...', u'...on...'), (u'Ken g\xe4n nauh oja?', u'Keng\xe4nnauhoja?'), (u'k\xe3mmott\xe3V\xe3ll\xe3 mUiStoll\xe3.', u'kammottavana muistona.'), (u'H\xe4n n\xe4ki naisen menev\xe4n\r\nkellarikerroksen ksen asun to o ns\xe4.', u'H\xe4n n\xe4ki naisen menev\xe4n\r\nkellarikerroksen asuntoonsa.'), (u'Min\xe4 etsin k\xe4siini miehen, joka\r\non aurtanutiestradea ja minua:', u'Min\xe4 etsin k\xe4siini miehen, joka\r\non auttanut Lestradea ja minua:'), (u'Huomaa erityisesti\r\npunaisella merkitty "kitoris.', u'Huomaa erityisesti\r\npunaisella merkitty "klitoris".'), (u'Tulkaa, meill\xe4 on\r\nHa va\u0131ji-bileet suihkussa', u'Tulkaa, meill\xe4 on\r\nHavaiji-bileet suihkussa'), (u'Ta rkoitatko ett\xe4\r\nh\xe4net myrkytettiin?', u'Tarkoitatko ett\xe4\r\nh\xe4net myrkytettiin?'), (u'Odotta kaa soittoani\r\nIev\xe4hdyspaikalla.', u'Odottakaa soittoani\r\nlev\xe4hdyspaikalla.'), (u'Nyt kuuntelet, perska rva.', u'Nyt kuuntelet, perskarva.'), (u'Ta patko h\xe4net sitten?', u'Tapatko h\xe4net sitten?'), (u'Seuraa vissa va/oissa.', u'Seuraavissa valoissa.'), (u'A\u0131o\u0131t rapattaa minut.\r\n- En.', u'Aioit tapattaa minut.\r\n- En.'), (u'Todella vaku uttavaa.', u'Todella vakuuttavaa.'), (u'I-le ovat tuolla alhaalla', u'He ovat tuolla alhaalla'), (u'Nainen kuuluu minulle.\r\n- I-I\xe0ivy siit\xe4, ylikasvuinen hyttynen!', u'Nainen kuuluu minulle.\r\n- H\xe4ivy siit\xe4, ylikasvuinen hyttynen!'), (u'I-Ialuatte k\xe4ytt\xe4\xe4 pyh\xe0\xe0 kive\xe4\r\ndynastian aarteen l\xf6yt\xe4miseksi.', u'Haluatte k\xe4ytt\xe4\xe4 pyh\xe0\xe0 kive\xe4\r\ndynastian aarteen l\xf6yt\xe4miseksi.'), (u'Mit\xe4f?', u'Mit\xe4.. ?'), (u'Kuuluuko Hiru ko-klaanista mit\xe4\xe4n?\r\n- Ninjasoturit ovat edell\xe4mme.', u'Kuuluuko Hiruko-klaanista mit\xe4\xe4n?\r\n- Ninjasoturit ovat edell\xe4mme.'), (u'Anteeks\u0131} painoin kai... -', u'Anteeksi, painoin kai... -'), (u'ja Rea! Ho usew\xedves.', u'ja Real Housewives.'), (u'Et halu n n ut Julkkistansseihinkaan.', u'Et halunnut Julkkistansseihinkaan.'), (u'Laard i k\xe4si?', u'Laardik\xe4si?'), (u'Varo kaa!', u'Varokaa!'), (u'N\xe4ytt\xe4v\xe4t k\xf6 tyt\xf6t v\xe4h \xe4n\r\nh uorahtavi m m i lta?', u'N\xe4ytt\xe4v\xe4tk\xf6 tyt\xf6t v\xe4h\xe4n\r\nhuorahtavimmilta?'), (u'Stif... Ier.', u'Stif... ler.'), (u'J u mantsu kka! M it\xe4?', u'Jumantsukka! Mit\xe4?'), (u'Varasin Ch u m bawam ban,', u'Varasin Chumbawamban,'), (u'J u malavita!', u'Jumalavita!'), (u'S', u'Isi...'), (u'Haluan kertoa jotai n', u'Haluan kertoa jotain'), (u'I-Ialuatte', u'Haluatte')]),
'pattern': None},
@@ -54,7 +54,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict([(u" I'", u" l'"), (u" |'", u" l'")]),
'pattern': u"(?um)(?:(?<=\\s)|(?<=^)|(?<=\\b))(?:\\ I\\'|\\ \\|\\')(?:(?=\\s)|(?=$)|(?=\\b))"},
'PartialWordsAlways': {'data': OrderedDict(),
'PartialWordsAlways': {'data': OrderedDict([(u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict([(u'"D\'ac:c:ord."', u'"D\'accord."'), (u'\u201ci QU\xce gagne, qui perd,', u'ni qui gagne, qui perd,'), (u"L'ac:c:ent est mis \r\n \r\n sur son trajet jusqu'en Suisse.", u"L'accent est mis \r\n \r\n sur son trajet jusqu'en Suisse."), (u"C'est la plus gentille chose \r\n \r\n qu'Hitchc:oc:k m'ait jamais dite.", u"C'est la plus gentille chose \r\n \r\n qu'Hitchcock m'ait jamais dite."), (u"Tout le monde, en revanche, qualifie \r\n \r\n Goldfinger d'aventu re structur\xe9e,", u"Tout le monde, en revanche, qualifie \r\n \r\n Goldfinger d'aventure structur\xe9e,"), (u'et le film Shadow of a man \r\n \r\n a lanc\xe9 sa carri\xe8re au cin\xe9ma.', u'et le film <i>Shadow of a man</i> \r\n \r\n a lanc\xe9 sa carri\xe8re au cin\xe9ma.'), (u'En 1948, Young est pass\xe9 \xe0 la r\xe9alisation \r\n \r\n avec One night with you.', u'En 1948, Young est pass\xe9 \xe0 la r\xe9alisation \r\n \r\n avec <i>One night with you</i>.'), (u'Il a construit tous ces v\xe9hicules \r\n \r\n \xe0 C)c:ala, en Floride.', u'Il a construit tous ces v\xe9hicules \r\n \r\n \xe0 Ocala, en Floride.'), (u'Tokyo Pop et A Taxing Woman? Return.', u"Tokyo Pop et A Taxing Woman's Return."), (u'Peter H u nt.', u'Peter Hunt.'), (u'"C\'est bien mieux dans Peau. \r\n \r\n On peut s\ufb02\xe9clabousser, faire du bruit."', u'"C\'est bien mieux dans l\'eau. \r\n \r\n On peut s\'\xe9clabousser, faire du bruit."')]),
'pattern': None},
@@ -66,7 +66,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict([(u'Ako ej', u'Ako je'), (u'ako ej', u'ako je'), (u'bez svesti', u'bez svijesti'), (u'Bi\u0107u uz', u'Bit \u0107u uz'), (u'bi ja', u'bih ja'), (u'bi la', u'bila'), (u'biti uredu', u'biti u redu'), (u'bi da bude', u'bi biti'), (u'Bi ste', u'Biste'), (u'bilo ko', u'bilo tko'), (u'\u0107e da do\u0111e', u'\u0107e do\u0107i'), (u'Da li \u0107emo', u'Ho\u0107emo li'), (u'da li \u0107u', u'ho\u0107u li'), (u'dali \u0107u', u'ho\u0107u li'), (u'Da li je', u'Je li'), (u'da li je', u'je li'), (u'Da li ste', u'Jeste li'), (u'Da li si', u'Jesi li'), (u'dali si', u'jesi li'), (u'da li \u0107e', u'ho\u0107e li'), (u'dali \u0107e', u'ho\u0107e li'), (u'do srede', u'do srijede'), (u'Dobro ve\u010de', u'Dobra ve\u010der'), (u'Dobro ve\u010der', u'Dobra ve\u010der'), (u'Dobar ve\u010der', u'Dobra ve\u010der'), (u'gdje ide\u0161', u'kamo ide\u0161'), (u'Gdje ide\u0161', u'Kamo ide\u0161'), (u'Gdje sada', u'Kamo sada'), (u'gle ko', u'gle tko'), (u'ho\u0107u da budem', u'\u017eelim biti'), (u'Ho\u0107u da budem', u'\u017delim biti'), (u'ho\u0107u da ka\u017eem', u'\u017eelim re\u0107i'), (u'ho\u0107e\u0161 da ka\u017ee\u0161', u'\u017eeli\u0161 re\u0107i'), (u'ho\u0107e da ka\u017ee', u'\u017eeli re\u0107i'), (u'Izvini se', u'Ispri\u010daj se'), (u'izvini se', u'ispri\u010daj se'), (u'Izvinite me', u'Ispri\u010dajte me'), (u'Izvinite nas', u'Ispri\u010dajte nas'), (u'izvinite nas', u'ispri\u010dajte nas'), (u'Izvinjavamo se', u'Ispri\u010davamo se'), (u'ja bi', u'ja bih'), (u'Ja bi', u'Ja bih'), (u'Jel sam ti', u'Jesam li ti'), (u'Jeli se', u'Je li se'), (u'Jeli sve', u'Je li sve'), (u'Jeli ti', u'Je li ti'), (u'ko zna', u'tko zna'), (u'moglo da bude', u'moglo biti'), (u'moje sau\u010de\u0161\u0107e', u'moja su\u0107ut'), (u'mora da bude', u'mora biti'), (u'Moram da idem', u'Moram i\u0107i'), (u'Moramo da idemo', u'Moramo i\u0107i'), (u'mora\u0161 da ide\u0161', u'mora\u0161 i\u0107i'), (u'na ve\u010der', u'nave\u010der'), (u'Na ve\u010der', u'Nave\u010der'), (u'neko ko', u'netko tko'), (u'nedjelju dana', u'tjedan dana'), (u'Ne mogu da verujem', u'Ne mogu vjerovati'), (u'od kako', u'otkako'), (u'Pla\u0161im se', u'Bojim se'), (u'pla\u0161im se', u'bojim se'), (u'pravo u o\u010di', u'ravno u o\u010di'), (u'sa njom', u's njom'), (u'sa tim', u's tim'), (u'sa tom', u's tom'), (u'sa tobom', u's tobom'), (u'Si dobro', u'Jesi li dobro'), (u'Svako ko', u'Svatko tko'), (u'Svo vreme', u'Sve vrijeme'), (u'Svo vrijeme', u'Sve vrijeme'), (u'smeo da', u'smio'), (u'smeli da', u'smjeli'), (u'\u0160to ej', u'\u0160to je'), (u'\u0161to ej', u'\u0161to je'), (u'to ej', u'to je'), (u'To ej', u'To je'), (u'tamo natrag', u'tamo iza'), (u'tamo je natrag', u'tamo je iza'), (u'Tamo je natrag', u'Tamo je iza'), (u'zato sto', u'zato \u0161to'), (u'zna ko', u'zna tko'), (u'znati ko', u'znati tko'), (u'\u017eelim da budem', u'\u017eelim biti'), (u'\u017delim da budem', u'\u017delim biti'), (u'\u017eeli\u0161 da bude\u0161', u'\u017eeli\u0161 biti'), (u'\u017eelim da odem', u'\u017eelim oti\u0107i'), (u'\u017eeli\u0161 da ode\u0161', u'\u017eeli\u0161 oti\u0107i'), (u'\u017eelim da znam', u'\u017eelim znati'), (u'\u017eeli\u0161 da zna\u0161', u'\u017eeli\u0161 znati')]),
'pattern': u'(?um)(?:(?<=\\s)|(?<=^)|(?<=\\b))(?:Ako\\ ej|ako\\ ej|bez\\ svesti|Bi\\\u0107u\\ uz|bi\\ ja|bi\\ la|biti\\ uredu|bi\\ da\\ bude|Bi\\ ste|bilo\\ ko|\\\u0107e\\ da\\ do\\\u0111e|Da\\ li\\ \\\u0107emo|da\\ li\\ \\\u0107u|dali\\ \\\u0107u|Da\\ li\\ je|da\\ li\\ je|Da\\ li\\ ste|Da\\ li\\ si|dali\\ si|da\\ li\\ \\\u0107e|dali\\ \\\u0107e|do\\ srede|Dobro\\ ve\\\u010de|Dobro\\ ve\\\u010der|Dobar\\ ve\\\u010der|gdje\\ ide\\\u0161|Gdje\\ ide\\\u0161|Gdje\\ sada|gle\\ ko|ho\\\u0107u\\ da\\ budem|Ho\\\u0107u\\ da\\ budem|ho\\\u0107u\\ da\\ ka\\\u017eem|ho\\\u0107e\\\u0161\\ da\\ ka\\\u017ee\\\u0161|ho\\\u0107e\\ da\\ ka\\\u017ee|Izvini\\ se|izvini\\ se|Izvinite\\ me|Izvinite\\ nas|izvinite\\ nas|Izvinjavamo\\ se|ja\\ bi|Ja\\ bi|Jel\\ sam\\ ti|Jeli\\ se|Jeli\\ sve|Jeli\\ ti|ko\\ zna|moglo\\ da\\ bude|moje\\ sau\\\u010de\\\u0161\\\u0107e|mora\\ da\\ bude|Moram\\ da\\ idem|Moramo\\ da\\ idemo|mora\\\u0161\\ da\\ ide\\\u0161|na\\ ve\\\u010der|Na\\ ve\\\u010der|neko\\ ko|nedjelju\\ dana|Ne\\ mogu\\ da\\ verujem|od\\ kako|Pla\\\u0161im\\ se|pla\\\u0161im\\ se|pravo\\ u\\ o\\\u010di|sa\\ njom|sa\\ tim|sa\\ tom|sa\\ tobom|Si\\ dobro|Svako\\ ko|Svo\\ vreme|Svo\\ vrijeme|smeo\\ da|smeli\\ da|\\\u0160to\\ ej|\\\u0161to\\ ej|to\\ ej|To\\ ej|tamo\\ natrag|tamo\\ je\\ natrag|Tamo\\ je\\ natrag|zato\\ sto|zna\\ ko|znati\\ ko|\\\u017eelim\\ da\\ budem|\\\u017delim\\ da\\ budem|\\\u017eeli\\\u0161\\ da\\ bude\\\u0161|\\\u017eelim\\ da\\ odem|\\\u017eeli\\\u0161\\ da\\ ode\\\u0161|\\\u017eelim\\ da\\ znam|\\\u017eeli\\\u0161\\ da\\ zna\\\u0161)(?:(?=\\s)|(?=$)|(?=\\b))'},
'PartialWordsAlways': {'data': OrderedDict(),
'PartialWordsAlways': {'data': OrderedDict([(u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
@@ -78,7 +78,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'PartialWordsAlways': {'data': OrderedDict([(u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
@@ -90,7 +90,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict([(u'\u010d', u'\xe8'), (u'I\u05bb', u'I'), (u'\u05d0', u'\xe0'), (u'\u05d9', u'\xe9'), (u'\u05d8', u'\xe8'), (u'\u05db', u'\xeb'), (u'\u05dd', u'i'), (u'\u05df', u'\xef'), (u'\u05e3', u'\xf3'), (u'\u05e4', u'o'), (u'\u05e6', u'\xeb')]),
'PartialWordsAlways': {'data': OrderedDict([(u'\u010d', u'\xe8'), (u'I\u05bb', u'I'), (u'\u05d0', u'\xe0'), (u'\u05d9', u'\xe9'), (u'\u05d8', u'\xe8'), (u'\u05db', u'\xeb'), (u'\u05dd', u'i'), (u'\u05df', u'\xef'), (u'\u05e3', u'\xf3'), (u'\u05e4', u'o'), (u'\u05e6', u'\xeb'), (u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
@@ -102,7 +102,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'PartialWordsAlways': {'data': OrderedDict([(u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
@@ -114,7 +114,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict([(u'IN 6-E', u'N 6 E'), (u'in tegrar-se', u'integrar-se'), (u'in teresse', u'interesse'), (u'in testinos', u'intestinos'), (u'indica \xe7\xe3o', u'indica\xe7\xe3o'), (u'inte tino', u'intestino'), (u'intes tinos', u'intestinos'), (u'L da', u'Lda'), (u'mal estar', u'mal-estar'), (u'mastiga \xe7\xe1o', u'mastiga\xe7\xe3o'), (u'm\xe9di cas', u'm\xe9dicas'), (u'mineo rais', u'minerais'), (u'mola res', u'molares'), (u'movi mentos', u'movimentos'), (u'movimen to', u'movimento'), (u'N 5-Estendido', u'N\xba 5 Estendido'), (u'oxig\xe9 nio', u'oxig\xe9nio'), (u'pod mos', u'podemos'), (u'poder-se ia', u'poder-se-ia'), (u'pos sibilidade', u'possibilidade'), (u'possibi lidades', u'possibilidades'), (u'pro duto', u'produto'), (u'procu rar', u'procurar'), (u'Q u e', u'Que'), (u'qualifi cam', u'qualificam'), (u'R egi\xe3o', u'Regi\xe3o'), (u'unsuficien temente', u'insuficientemente')]),
'pattern': u'(?um)(?:(?<=\\s)|(?<=^)|(?<=\\b))(?:IN\\ 6\\-E|in\\ tegrar\\-se|in\\ teresse|in\\ testinos|indica\\ \\\xe7\\\xe3o|inte\\ tino|intes\\ tinos|L\\ da|mal\\ estar|mastiga\\ \\\xe7\\\xe1o|m\\\xe9di\\ cas|mineo\\ rais|mola\\ res|movi\\ mentos|movimen\\ to|N\\ 5\\-Estendido|oxig\\\xe9\\ nio|pod\\ mos|poder\\-se\\ ia|pos\\ sibilidade|possibi\\ lidades|pro\\ duto|procu\\ rar|Q\\ u\\ e|qualifi\\ cam|R\\ egi\\\xe3o|unsuficien\\ temente)(?:(?=\\s)|(?=$)|(?=\\b))'},
'PartialWordsAlways': {'data': OrderedDict(),
'PartialWordsAlways': {'data': OrderedDict([(u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
@@ -126,7 +126,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict(),
'PartialWordsAlways': {'data': OrderedDict([(u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
@@ -138,7 +138,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': u'(?um)(?:\\.\\\xbb\\.)$'},
'PartialLines': {'data': OrderedDict([(u'de gratis', u'gratis'), (u'si quiera', u'siquiera'), (u'Cada una de los', u'Cada uno de los'), (u'Cada uno de las', u'Cada una de las'), (u'haber que', u'a ver qu\xe9'), (u'haber qu\xe9', u'a ver qu\xe9'), (u'Haber si', u'A ver si'), (u' que hora', u' qu\xe9 hora'), (u'yo que se', u'yo qu\xe9 s\xe9'), (u'Yo que se', u'Yo qu\xe9 s\xe9'), (u' tu!', u' t\xfa!'), (u' si!', u' s\xed!'), (u' mi!', u' m\xed!'), (u' el!', u' \xe9l!'), (u' tu?', u' t\xfa?'), (u' si?', u' s\xed?'), (u' mi?', u' m\xed?'), (u' el?', u' \xe9l?'), (u' aun?', u' a\xfan?'), (u' mas?', u' m\xe1s?'), (u' que?', u' qu\xe9?'), (u' paso?', u' pas\xf3?'), (u' cuando?', u' cu\xe1ndo?'), (u' cuanto?', u' cu\xe1nto?'), (u' cuanta?', u' cu\xe1nta?'), (u' cuantas?', u' cu\xe1ntas?'), (u' cuantos?', u' cu\xe1ntos?'), (u' donde?', u' d\xf3nde?'), (u' quien?', u' qui\xe9n?'), (u' como?', u' c\xf3mo?'), (u' adonde?', u' ad\xf3nde?'), (u' cual?', u' cu\xe1l?'), (u'\xbfSi?', u'\xbfS\xed?'), (u'\xbfesta bien?', u'\xbfest\xe1 bien?'), (u'\xbfPero qu\xe9 haces?', u'\xa1\xbfPero qu\xe9 haces?!'), (u'\xbfpero qu\xe9 haces?', u'\xa1\xbfpero qu\xe9 haces?!'), (u'\xbfEs que no me has escuchado?', u'\xa1\xbfEs que no me has escuchado?!'), (u'\xa1\xbfes que no me has escuchado?!', u'\xa1\xbfes que no me has escuchado?!'), (u'\xbfaun', u'\xbfa\xfan'), (u'\xbftu ', u'\xbft\xfa '), (u'\xbfque ', u'\xbfqu\xe9 '), (u'\xbfsabes que', u'\xbfsabes qu\xe9'), (u'\xbfsabes adonde', u'\xbfsabes ad\xf3nde'), (u'\xbfsabes cual', u'\xbfsabes cu\xe1l'), (u'\xbfsabes quien', u'\xbfsabes qui\xe9n'), (u'\xbfsabes como', u'\xbfsabes c\xf3mo'), (u'\xbfsabes cuan', u'\xbfsabes cu\xe1n'), (u'\xbfsabes cuanto', u'\xbfsabes cu\xe1nto'), (u'\xbfsabes cuanta', u'\xbfsabes cu\xe1nta'), (u'\xbfsabes cuantos', u'\xbfsabes cu\xe1ntos'), (u'\xbfsabes cuantas', u'\xbfsabes cu\xe1ntas'), (u'\xbfsabes cuando', u'\xbfsabes cu\xe1ndo'), (u'\xbfsabes donde', u'\xbfsabes d\xf3nde'), (u'\xbfsabe que', u'\xbfsabe qu\xe9'), (u'\xbfsabe adonde', u'\xbfsabe ad\xf3nde'), (u'\xbfsabe cual', u'\xbfsabe cu\xe1l'), (u'\xbfsabe quien', u'\xbfsabe qui\xe9n'), (u'\xbfsabe como', u'\xbfsabe c\xf3mo'), (u'\xbfsabe cuan', u'\xbfsabe cu\xe1n'), (u'\xbfsabe cuanto', u'\xbfsabe cu\xe1nto'), (u'\xbfsabe cuanta', u'\xbfsabe cu\xe1nta'), (u'\xbfsabe cuantos', u'\xbfsabe cu\xe1ntos'), (u'\xbfsabe cuantas', u'\xbfsabe cu\xe1ntas'), (u'\xbfsabe cuando', u'\xbfsabe cu\xe1ndo'), (u'\xbfsabe donde', u'\xbfsabe d\xf3nde'), (u'\xbfsaben que', u'\xbfsaben qu\xe9'), (u'\xbfsaben adonde', u'\xbfsaben ad\xf3nde'), (u'\xbfsaben cual', u'\xbfsaben cu\xe1l'), (u'\xbfsaben quien', u'\xbfsaben qui\xe9n'), (u'\xbfsaben como', u'\xbfsaben c\xf3mo'), (u'\xbfsaben cuan', u'\xbfsaben cu\xe1n'), (u'\xbfsaben cuanto', u'\xbfsaben cu\xe1nto'), (u'\xbfsaben cuanta', u'\xbfsaben cu\xe1nta'), (u'\xbfsaben cuantos', u'\xbfsaben cu\xe1ntos'), (u'\xbfsaben cuantas', u'\xbfsaben cu\xe1ntas'), (u'\xbfsaben cuando', u'\xbfsaben cu\xe1ndo'), (u'\xbfsaben donde', u'\xbfsaben d\xf3nde'), (u'\xbfde que', u'\xbfde qu\xe9'), (u'\xbfde donde', u'\xbfde d\xf3nde'), (u'\xbfde cual', u'\xbfde cu\xe1l'), (u'\xbfde quien', u'\xbfde qui\xe9n'), (u'\xbfde cuanto', u'\xbfde cu\xe1nto'), (u'\xbfde cuanta', u'\xbfde cu\xe1nta'), (u'\xbfde cuantos', u'\xbfde cu\xe1ntos'), (u'\xbfde cuantas', u'\xbfde cu\xe1ntas'), (u'\xbfde cuando', u'\xbfde cu\xe1ndo'), (u'\xbfsobre que', u'\xbfsobre qu\xe9'), (u'\xbfcomo ', u'\xbfc\xf3mo '), (u'\xbfcual ', u'\xbfcu\xe1l '), (u'\xbfen cual', u'\xbfen cu\xe1l'), (u'\xbfcuando', u'\xbfcu\xe1ndo'), (u'\xbfhasta cual', u'\xbfhasta cu\xe1l'), (u'\xbfhasta quien', u'\xbfhasta qui\xe9n'), (u'\xbfhasta cuanto', u'\xbfhasta cu\xe1nto'), (u'\xbfhasta cuantas', u'\xbfhasta cu\xe1ntas'), (u'\xbfhasta cuantos', u'\xbfhasta cu\xe1ntos'), (u'\xbfhasta cuando', u'\xbfhasta cu\xe1ndo'), (u'\xbfhasta donde', u'\xbfhasta d\xf3nde'), (u'\xbfhasta que', u'\xbfhasta qu\xe9'), (u'\xbfhasta adonde', u'\xbfhasta ad\xf3nde'), (u'\xbfdesde que', u'\xbfdesde qu\xe9'), (u'\xbfdesde cuando', u'\xbfdesde cu\xe1ndo'), (u'\xbfdesde quien', u'\xbfdesde qui\xe9n'), (u'\xbfdesde donde', u'\xbfdesde d\xf3nde'), (u'\xbfcuanto', u'\xbfcu\xe1nto'), (u'\xbfcuantos', u'\xbfcu\xe1ntos'), (u'\xbfdonde', u'\xbfd\xf3nde'), (u'\xbfadonde', u'\xbfad\xf3nde'), (u'\xbfcon que', u'\xbfcon qu\xe9'), (u'\xbfcon cual', u'\xbfcon cu\xe1l'), (u'\xbfcon quien', u'\xbfcon qui\xe9n'), (u'\xbfcon cuantos', u'\xbfcon cu\xe1ntos'), (u'\xbfcon cuantas', u'\xbfcon cu\xe1ntas'), (u'\xbfcon cuanta', u'\xbfcon cu\xe1nta'), (u'\xbfcon cuanto', u'\xbfcon cu\xe1nto'), (u'\xbfpara donde', u'\xbfpara d\xf3nde'), (u'\xbfpara adonde', u'\xbfpara ad\xf3nde'), (u'\xbfpara cuando', u'\xbfpara cu\xe1ndo'), (u'\xbfpara que', u'\xbfpara qu\xe9'), (u'\xbfpara quien', u'\xbfpara qui\xe9n'), (u'\xbfpara cuanto', u'\xbfpara cu\xe1nto'), (u'\xbfpara cuanta', u'\xbfpara cu\xe1nta'), (u'\xbfpara cuantos', u'\xbfpara cu\xe1ntos'), (u'\xbfpara cuantas', u'\xbfpara cu\xe1ntas'), (Line truncated
'pattern': u'(?um)(?:(?<=\\s)|(?<=^)|(?<=\\b))(?:de\\ gratis|si\\ quiera|Cada\\ una\\ de\\ los|Cada\\ uno\\ de\\ las|haber\\ que|haber\\ qu\\\xe9|Haber\\ si|\\ que\\ hora|yo\\ que\\ se|Yo\\ que\\ se|\\ tu\\!|\\ si\\!|\\ mi\\!|\\ el\\!|\\ tu\\?|\\ si\\?|\\ mi\\?|\\ el\\?|\\ aun\\?|\\ mas\\?|\\ que\\?|\\ paso\\?|\\ cuando\\?|\\ cuanto\\?|\\ cuanta\\?|\\ cuantas\\?|\\ cuantos\\?|\\ donde\\?|\\ quien\\?|\\ como\\?|\\ adonde\\?|\\ cual\\?|\\\xbfSi\\?|\\\xbfesta\\ bien\\?|\\\xbfPero\\ qu\\\xe9\\ haces\\?|\\\xbfpero\\ qu\\\xe9\\ haces\\?|\\\xbfEs\\ que\\ no\\ me\\ has\\ escuchado\\?|\\\xa1\\\xbfes\\ que\\ no\\ me\\ has\\ escuchado\\?\\!|\\\xbfaun|\\\xbftu\\ |\\\xbfque\\ |\\\xbfsabes\\ que|\\\xbfsabes\\ adonde|\\\xbfsabes\\ cual|\\\xbfsabes\\ quien|\\\xbfsabes\\ como|\\\xbfsabes\\ cuan|\\\xbfsabes\\ cuanto|\\\xbfsabes\\ cuanta|\\\xbfsabes\\ cuantos|\\\xbfsabes\\ cuantas|\\\xbfsabes\\ cuando|\\\xbfsabes\\ donde|\\\xbfsabe\\ que|\\\xbfsabe\\ adonde|\\\xbfsabe\\ cual|\\\xbfsabe\\ quien|\\\xbfsabe\\ como|\\\xbfsabe\\ cuan|\\\xbfsabe\\ cuanto|\\\xbfsabe\\ cuanta|\\\xbfsabe\\ cuantos|\\\xbfsabe\\ cuantas|\\\xbfsabe\\ cuando|\\\xbfsabe\\ donde|\\\xbfsaben\\ que|\\\xbfsaben\\ adonde|\\\xbfsaben\\ cual|\\\xbfsaben\\ quien|\\\xbfsaben\\ como|\\\xbfsaben\\ cuan|\\\xbfsaben\\ cuanto|\\\xbfsaben\\ cuanta|\\\xbfsaben\\ cuantos|\\\xbfsaben\\ cuantas|\\\xbfsaben\\ cuando|\\\xbfsaben\\ donde|\\\xbfde\\ que|\\\xbfde\\ donde|\\\xbfde\\ cual|\\\xbfde\\ quien|\\\xbfde\\ cuanto|\\\xbfde\\ cuanta|\\\xbfde\\ cuantos|\\\xbfde\\ cuantas|\\\xbfde\\ cuando|\\\xbfsobre\\ que|\\\xbfcomo\\ |\\\xbfcual\\ |\\\xbfen\\ cual|\\\xbfcuando|\\\xbfhasta\\ cual|\\\xbfhasta\\ quien|\\\xbfhasta\\ cuanto|\\\xbfhasta\\ cuantas|\\\xbfhasta\\ cuantos|\\\xbfhasta\\ cuando|\\\xbfhasta\\ donde|\\\xbfhasta\\ que|\\\xbfhasta\\ adonde|\\\xbfdesde\\ que|\\\xbfdesde\\ cuando|\\\xbfdesde\\ quien|\\\xbfdesde\\ donde|\\\xbfcuanto|\\\xbfcuantos|\\\xbfdonde|\\\xbfadonde|\\\xbfcon\\ que|\\\xbfcon\\ cual|\\\xbfcon\\ quien|\\\xbfcon\\ cuantos|\\\xbfcon\\ cuantas|\\\xbfcon\\ cuanta|\\\xbfcon\\ cuanto|\\\xbfpara\\ donde|\\\xbfpara\\ adonde|\\\xbfpara\\ cuando|\\\xbfpara\\ que|\\\xbfpara\\ quien|\\\xbfpara\\ cuanto|\\\xbfpara\\ cuanta|\\\xbfpara\\ cuantos|\\\xbfpara\\ cuantas|\\\xbfa\\ donde|\\\xbfa\\ que|\\\xbfa\\ cual|\\\xbfa\\ quien|\\\xbfa\\ como|\\\xbfa\\ cuanto|\\\xbfa\\ cuanta|\\\xbfa\\ cuantos|\\\xbfa\\ cuantas|\\\xbfpor\\ que|\\\xbfpor\\ cual|\\\xbfpor\\ quien|\\\xbfpor\\ cuanto|\\\xbfpor\\ cuanta|\\\xbfpor\\ cuantos|\\\xbfpor\\ cuantas|\\\xbfpor\\ donde|\\\xbfporque|\\\xbfporqu\\\xe9|\\\xbfy\\ que|\\\xbfy\\ como|\\\xbfy\\ cuando|\\\xbfy\\ cual|\\\xbfy\\ quien|\\\xbfy\\ cuanto|\\\xbfy\\ cuanta|\\\xbfy\\ cuantos|\\\xbfy\\ cuantas|\\\xbfy\\ donde|\\\xbfy\\ adonde|\\\xbfquien\\ |\\\xbfesta\\ |\\\xbfestas\\ |\\\xbfAun|\\\xbfQue\\ |\\\xbfSabes\\ que|\\\xbfSabes\\ adonde|\\\xbfSabes\\ cual|\\\xbfSabes\\ quien|\\\xbfSabes\\ como|\\\xbfSabes\\ cuan|\\\xbfSabes\\ cuanto|\\\xbfSabes\\ cuanta|\\\xbfSabes\\ cuantos|\\\xbfSabes\\ cuantas|\\\xbfSabes\\ cuando|\\\xbfSabes\\ donde|\\\xbfSabe\\ que|\\\xbfSabe\\ adonde|\\\xbfSabe\\ cual|\\\xbfSabe\\ quien|\\\xbfSabe\\ como|\\\xbfSabe\\ cuan|\\\xbfSabe\\ cuanto|\\\xbfSabe\\ cuanta|\\\xbfSabe\\ cuantos|\\\xbfSabe\\ cuantas|\\\xbfSabe\\ cuando|\\\xbfSabe\\ donde|\\\xbfSaben\\ que|\\\xbfSaben\\ adonde|\\\xbfSaben\\ cual|\\\xbfSaben\\ quien|\\\xbfSaben\\ como|\\\xbfSaben\\ cuan|\\\xbfSaben\\ cuanto|\\\xbfSaben\\ cuanta|\\\xbfSaben\\ cuantos|\\\xbfSaben\\ cuantas|\\\xbfSaben\\ cuando|\\\xbfSaben\\ donde|\\\xbfDe\\ que|\\\xbfDe\\ donde|\\\xbfDe\\ cual|\\\xbfDe\\ quien|\\\xbfDe\\ cuanto|\\\xbfDe\\ cuanta|\\\xbfDe\\ cuantos|\\\xbfDe\\ cuantas|\\\xbfDe\\ cuando|\\\xbfDesde\\ que|\\\xbfDesde\\ cuando|\\\xbfDesde\\ quien|\\\xbfDesde\\ donde|\\\xbfSobre\\ que|\\\xbfComo\\ |\\\xbfCual\\ |\\\xbfEn\\ cual|\\\xbfCuando|\\\xbfHasta\\ cual|\\\xbfHasta\\ quien|\\\xbfHasta\\ cuanto|\\\xbfHasta\\ cuantas|\\\xbfHasta\\ cuantos|\\\xbfHasta\\ cuando|\\\xbfHasta\\ donde|\\\xbfHasta\\ que|\\\xbfHasta\\ adonde|\\\xbfCuanto|\\\xbfCuantos|\\\xbfDonde|\\\xbfAdonde|\\\xbfCon\\ que|\\\xbfCon\\ cual|\\\xbfCon\\ quien|\\\xbfCon\\ cuantos|\\\xbfCon\\ cuanta|\\\xbfCon\\ cuanto|\\\xbfPara\\ donde|\\\xbfPara\\ adonde|\\\xbfPara\\ cuando|\\\xbfPara\\ que|\\\xbfPara\\ quien|\\\xbfPara\\ cuanto|\\\xbfPara\\ cuanta|\\\xbfPara\\ cuantos|\\\xbfPara\\ cuantas|\\\xbfA\\ donde|\\\xbfA\\ que|\\\xbfA\\ cual|\\\xbfA\\ quien|\\\xbfA\\ como|\\\xbfA\\ cuanto|\\\xbfA\\ cuanta|\\\xbfA\\ cuantos|\\\xbfA\\ cuantas|\\\xbfPor\\ que|\\\xbfPor\\ cual|\\\xbfPor\\ quien|\\\xbfPor\\ cuanto|\\\xbfPor\\ cuanta|\\\xbfPor\\ cuantos|\\\xbfPor\\ cuantas|\\\xbfPor\\ donde|\\\xbfPorque|\\\xbfPorqu\\\xe9|\\\xbfY\\ que|\\\xbfY\\ como|\\\xbfY\\ cuando|\\\xbfY\\ cual|\\\xbfY\\ quien|\\\xbfY\\ cuanto|\\\xbfY\\ cuanta|\\\xbfY\\ cuantos|\\\xbfY\\ cuantas|\\\xbfY\\ donde|\\\xbfY\\ adonde|\\\xbfQuien\\ |\\\xbfEsta\\ |el\\ porque|su\\ porque|los\\ porqu\\\xe9s|aun\\,|aun\\ no|\\ de\\ y\\ |\\ nLine truncated
'PartialWordsAlways': {'data': OrderedDict(),
'PartialWordsAlways': {'data': OrderedDict([(u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict([(u'No', u'No.')]),
'pattern': None},
@@ -150,7 +150,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict([(u'bi smo', u'bismo'), (u'dali je', u'da li je'), (u'dali si', u'da li si'), (u'Dali si', u'Da li si'), (u'Jel sam ti', u'Jesam li ti'), (u'Jel si', u'Jesi li'), (u"Jel' si", u'Jesi li'), (u"Je I'", u'Jesi li'), (u'Jel si to', u'Jesi li to'), (u"Jel' si to", u'Da li si to'), (u'jel si to', u'da li si to'), (u"jel' si to", u'jesi li to'), (u'Jel si ti', u'Da li si ti'), (u"Jel' si ti", u'Da li si ti'), (u'jel si ti', u'da li si ti'), (u"jel' si ti", u'da li si ti'), (u'jel ste ', u'jeste li '), (u'Jel ste', u'Jeste li'), (u"jel' ste ", u'jeste li '), (u"Jel' ste ", u'Jeste li '), (u'Jel su ', u'Jesu li '), (u'Jel da ', u'Zar ne'), (u'jel da ', u'zar ne'), (u"jel'da ", u'zar ne'), (u'Jeli sve ', u'Je li sve'), (u'Jeli on ', u'Je li on'), (u'Jeli ti ', u'Je li ti'), (u'jeli ti ', u'je li ti'), (u'Jeli to ', u'Je li to'), (u'Nebrini', u'Ne brini'), (u'nedaj', u'ne daj'), (u'ne \u0107u', u'ne\u0107u'), (u'Nemogu', u'Ne mogu'), (u'ne mogu', u'ne mogu'), (u'Nemora\u0161', u'Ne mora\u0161'), (u'od kako', u'otkako'), (u'Si dobro', u'Jesi li dobro'), (u'Svo vreme', u'Sve vrijeme'), (u'Svo vrijeme', u'Sve vrijeme'), (u'Cijelo vrijeme', u'Sve vrijeme')]),
'pattern': u"(?um)(?:(?<=\\s)|(?<=^)|(?<=\\b))(?:bi\\ smo|dali\\ je|dali\\ si|Dali\\ si|Jel\\ sam\\ ti|Jel\\ si|Jel\\'\\ si|Je\\ I\\'|Jel\\ si\\ to|Jel\\'\\ si\\ to|jel\\ si\\ to|jel\\'\\ si\\ to|Jel\\ si\\ ti|Jel\\'\\ si\\ ti|jel\\ si\\ ti|jel\\'\\ si\\ ti|jel\\ ste\\ |Jel\\ ste|jel\\'\\ ste\\ |Jel\\'\\ ste\\ |Jel\\ su\\ |Jel\\ da\\ |jel\\ da\\ |jel\\'da\\ |Jeli\\ sve\\ |Jeli\\ on\\ |Jeli\\ ti\\ |jeli\\ ti\\ |Jeli\\ to\\ |Nebrini|nedaj|ne\\ \\\u0107u|Nemogu|ne\\ mogu|Nemora\\\u0161|od\\ kako|Si\\ dobro|Svo\\ vreme|Svo\\ vrijeme|Cijelo\\ vrijeme)(?:(?=\\s)|(?=$)|(?=\\b))"},
'PartialWordsAlways': {'data': OrderedDict(),
'PartialWordsAlways': {'data': OrderedDict([(u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
@@ -162,7 +162,7 @@ data = {'dan': {'BeginLines': {'data': OrderedDict(),
'pattern': None},
'PartialLines': {'data': OrderedDict(),
'pattern': None},
'PartialWordsAlways': {'data': OrderedDict([(u'\u013a', u'\xe5')]),
'PartialWordsAlways': {'data': OrderedDict([(u'\u0139', u'\xc5'), (u'\u013a', u'\xe5'), (u'\xb6\xb6', u'\u266b'), (u'\xb6', u'\u266a')]),
'pattern': None},
'WholeLines': {'data': OrderedDict(),
'pattern': None},
@@ -76,6 +76,13 @@ SZ_FIX_DATA = {
}
}
SZ_FIX_DATA_GLOBAL = {
"PartialWordsAlways": {
u"¶¶": u"♫",
u"": u"♪"
}
}
if __name__ == "__main__":
cur_dir = os.path.dirname(os.path.realpath(__file__))
xml_dir = os.path.join(cur_dir, "xml")
@@ -114,6 +121,9 @@ if __name__ == "__main__":
if lang in SZ_FIX_DATA and grp in SZ_FIX_DATA[lang]:
data[lang][grp]["data"].update(SZ_FIX_DATA[lang][grp])
if grp in SZ_FIX_DATA_GLOBAL:
data[lang][grp]["data"].update(SZ_FIX_DATA_GLOBAL[grp])
if pattern:
data[lang][grp]["pattern"] = pattern(data[lang][grp]["data"])