Ë
    çÍ:jKC  ã                   ó˜  — d Z ddlZddlmZ ddlmZ  ej                  d«      Z�dJd„Z�dKd„Z	d„ Z
d	„ Z�dJd
„Zd„ Zd„ Z ej                  «         eej                   «      Zi dd“dd“dd“dd“dd“dd“dd“dd“dd“dd “d!d"“d#d$“d%d&“d'd(“d)d*“d+d,“d-d.“i d/d0“d1d2“d3d4“d5d6“d7d8“d9d:“d;d<“d=d>“d?d@“dAdB“dCdD“dEdF“dGdH“dIdJ“dKdL“dMdN“dOdP“¥i dQdR“dSdT“dUdV“dWdX“dYdZ“d[d\“d]d^“d_d`“dadb“dcdd“dedf“dgdh“didj“dkdl“dmdn“dodp“dqdr“¥i dsdt“dudv“dwdx“dydz“d{d|“d}d~“dd€“d�d‚“dƒd„“d…d†“d‡dˆ“d‰dŠ“d‹dŒ“d�dŽ“d�d�“d‘d’“d“d”“¥i d•d–“d—d˜“d™dš“d›dœ“d�dž“dŸd “d¡d¢“d£d¤“d¥d¦“d§d¨“d©dª“d«d¬“d­d®“d¯d°“d±d²“d³d´“dµd¶“¥i d·d¸“d¹dº“d»d¼“d½d¾“d¿dÀ“dÁdÂ“dÃdÄ“dÅdÆ“dÇdÈ“dÉdÊ“dËdÌ“dÍdÎ“dÏdÐ“dÑdÒ“dÓdÔ“dÕdÖ“d×dØ“¥i dÙdÚ“dÛdÜ“dÝdÞ“dßdà“dádâ“dãdä“dådæ“dçdè“dédê“dëdì“dídî“dïdð“dñdò“dódô“dõdö“d÷dø“dùdú“¥i dûdü“dýdþ“dÿ�d “�d�d“�d�d“�d�d“�d�d“�d	�d
“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“¥i �d�d“�d�d “�d!�d"“�d#�d$“�d%�d&“�d'�d(“�d)�d*“�d+�d,“�d-�d.“�d/�d0“�d1�d2“�d3�d4“�d5�d6“�d7�d8“�d9�d:“�d;�d<“�d=�d>“¥i �d?�d@“�dA�dB“�dC�dD“�dE�dF“�dG�dH“�dI�dJ“�dK�dL“�dM�dN“�dO�dP“�dQ�dR“�dS�dT“�dU�dV“�dW�dX“�dY�dZ“�d[�d\“�d]�d^“�d_�d`“¥�da�db�dc�dd�de�df�dg�dh�di�dj�dk�dl�dm�dn�doœ¥Zi �dp�dq“�dr�ds“�dt�du“�dv�dw“�dx�dy“�dz�d{“�d|�d}“�d~�d“�d€�d�“�d‚�dƒ“�d„�d…“�d†�d‡“�dˆ�d‰“�dŠ�d‹“�dŒ�d�“�dŽ�d�“�d��d‘“i �d’�d““�d”�d•“�d–�d—“�d˜�d™“�dš�d›“�dœ�d�“�dž�dŸ“�d �d¡“�d¢�d£“�d¤�d¥“�d¦�d§“�d¨�d©“�dª�d«“�d¬�d­“�d®�d¯“�d°�d±“�d²�d³“¥i �d´�dµ“�d¶�d·“�d¸�d¹“�dº�d»“�d¼�d½“�d¾�d¿“�dÀ�dÁ“�dÂ�dÃ“�dÄ�dÅ“�dÆ�dÇ“�dÈ�dÉ“�dÊ�dË“�dÌ�dÍ“�dÎ�dÏ“�dÐ�dÑ“�dÒ�dÓ“�dÔ�dÕ“¥i �dÖ�d×“�dØ�dÙ“�dÚ�dÛ“�dÜ�dÝ“�dÞ�dß“�dà�dá“�dâ�dã“�dä�då“�dæ�dç“�dè�dé“�dê�dë“�dì�dí“�dî�dï“�dð�dñ“�dò�dó“�dô�dõ“�dö�d÷“¥i �dø�dù“�dú�dû“�dü�dý“�dþ�dÿ“�d �d“�d�d“�d�d“�d�d“�d�d	“�d
�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“¥i �d�d“�d�d“�d�d“�d �d!“�d"�d#“�d$�d%“�d&�d'“�d(�d)“�d*�d+“�d,�d-“�d.�d/“�d0�d1“�d2�d3“�d4�d5“�d6�d7“�d8�d9“�d:�d;“¥i �d<�d=“�d>�d?“�d@�dA“�dB�dC“�dD�dE“�dF�dG“�dH�dI“�dJ�dK“�dL�dM“�dN�dO“�dP�dQ“�dR�dS“�dT�dU“�dV�dW“�dX�dY“�dZ�d[“�d\�d]“¥i �d^�d_“�d`�da“�db�dc“�dd�de“�df�dg“�dh�di“�dj�dk“�dl�dm“�dn�do“�dp�dq“�dr�ds“�dt�du“�dv�dw“�dx�dy“�dz�d{“�d|�d}“�d~�d“¥i �d€�d�“�d‚�dƒ“�d„�d…“�d†�d‡“�dˆ�d‰“�dŠ�d‹“�dŒ�d�“�dŽ�d�“�d��d‘“�d’�d““�d”�d•“�d–�d—“�d˜�d™“�dš�d›“�dœ�d�“�dž�dŸ“�d �d¡“¥i �d¢�d£“�d¤�d¥“�d¦�d§“�d¨�d©“�dª�d«“�d¬�d­“�d®�d¯“�d°�d±“�d²�d³“�d´�dµ“�d¶�d·“�d¸�d¹“�dº�d»“�d¼�d½“�d¾�d¿“�dÀ�dÁ“�dÂ�dÃ“¥i �dÄ�dÅ“�dÆ�dÇ“�dÈ�dÉ“�dÊ�dË“�dÌ�dÍ“�dÎ�dÏ“�dÐ�dÑ“�dÒ�dÓ“�dÔ�dÕ“�dÖ�d×“�dØ�dÙ“�dÚ�dÛ“�dÜ�dÝ“�dÞ�dß“�dà�dá“�dâ�dã“�dä�då“¥i �dæ�dç“�dè�dé“�dê�dë“�dì�dí“�dî�dï“�dð�dñ“�dò�dó“�dô�dõ“�dö�d÷“�dø�dù“�dú�dû“�dü�dý“�dþ�dÿ“�d �d“�d�d“�d�d“�d�d“¥i �d�d	“�d
�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d �d!“�d"�d#“�d$�d%“�d&�d'“�d(�d)“¥i �d*�d+“�d,�d-“�d.�d/“�d0�d1“�d2�d3“�d4�d5“�d6�d7“�d8�d9“�d:�d;“�d<�d=“�d>�d?“�d@�dA“�dB�dC“�dD�dE“�dF�dG“�dH�dI“�dJ�dK“¥i �dL�dM“�dN�dO“�dP�dQ“�dR�dS“�dT�dU“�dV�dW“�dX�dY“�dZ�d[“�d\�d]“�d^�d_“�d`�da“�db�dc“�dd�de“�df�dg“�dh�di“�dj�dk“�dl�dm“¥i �dn�do“�dp�dq“�dr�ds“�dt�du“�dv�dw“�dx�dy“�dz�d{“�d|�d}“�d~�d“�d€�d�“�d‚�dƒ“�d„�d…“�d†�d‡“�dˆ�d‰“�dŠ�d‹“�dŒ�d�“�dŽ�d�“¥i �d��d‘“�d’�d““�d”�d•“�d–�d—“�d˜�d™“�dš�d›“�dœ�d�“�dž�dŸ“�d �d¡“�d¢�d£“�d¤�d¥“�d¦�d§“�d¨�d©“�dª�d«“�d¬�d­“�d®�d¯“�d°�d±“¥i �d²�d³“�d´�dµ“�d¶�d·“�d¸�d¹“�dº�d»“�d¼�d½“�d¾�d¿“�dÀ�dÁ“�dÂ�dÃ“�dÄ�dÅ“�dÆ�dÇ“�dÈ�dÉ“�dÊ�dË“�dÌ�dÍ“�dÎ�dÏ“�dÐ�dÑ“�dÒ�dÓ“¥i �dÔ�dÕ“�dÖ�d×“�dØ�dÙ“�dÚ�dÛ“�dÜ�dÝ“�dÞ�dß“�dà�dá“�dâ�dã“�dä�då“�dæ�dç“�dè�dé“�dê�dë“�dì�dí“�dî�dï“�dð�dñ“�dò�dó“�dô�dõ“¥i �dö�d÷“�dø�dù“�dú�dû“�dü�dý“�dþ�dÿ“�d �d“�d�d“�d�d“�d�d“�d�d	“�d
�d“�d�d“�d�d“�d�d“�d�d“�d�d“�d�d“¥i �d�d“�d�d“�d�d“�d�d“�d �d!“�d"�d#“�d$�d%“�d&�d'“�d(�d)“�d*�d+“�d,�d-“�d.�d/“�d0�d1“�d2�d3“�d4�d5“�d6�d7“�d8�d9“¥�d:�d;�d<�d=�d>�d?�d@�dA�dB�dC�dD�dE�dF�dG�dH�dIœ¥Z ee«      Z ee«      Zy(L  a–  
Translate between language names and language codes.

The iso639-3 language codes were downloaded from the registration authority at
https://iso639-3.sil.org/

The iso639-3 codeset is evolving, so retired language codes are kept in the
"iso639retired" dictionary, which is used as fallback by the wrapper functions
"langname" and "langcode", in order to support the lookup of retired codes.

The "langcode" function returns the current iso639-3 code if there is one,
and falls back to the retired code otherwise. As specified by BCP-47,
it returns the shortest (2-letter) code by default, but 3-letter codes
are also available:

    >>> import nltk.langnames as lgn
    >>> lgn.langname('fri')          #'fri' is a retired code
    'Western Frisian'

    The current code is different from the retired one:
    >>> lgn.langcode('Western Frisian')
    'fy'

    >>> lgn.langcode('Western Frisian', typ = 3)
    'fry'

é    N)Úwarn)Úbcp47z[a-z][a-z][a-z]?c                 ó–  — | j                  d«      }|d   j                  «       }t        j                  |«      r€|t        v r	t        |   S |t
        v r4t
        |   }t        d|›d|›�d¬«       dj                  |g|dd z   «      } t        j                  | «      }|d	k(  r|S |r|j                  d
«      d   S yt        d|›�d¬«       y)zû
    Convert a composite BCP-47 tag to a language name

    >>> from nltk.langnames import langname
    >>> langname('ca-Latn-ES-valencia')
    'Catalan: Latin: Spain: Valencian'

    >>> langname('ca-Latn-ES-valencia', typ="short")
    'Catalan'
    ú-r   zShortening z to é   ©Ú
stacklevelé   NÚfullú:zCould not find code in )
ÚsplitÚlowerÚcodepatternÚ	fullmatchÚiso639retiredÚiso639shortr   Újoinr   Úname)ÚtagÚtypÚtagsÚcodeÚcode2r   s         úc/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/nltk/langnames.pyÚlangnamer   .   sÍ   € ð �9‰9�S‹>€DØ�‰7�=‰=‹?€DÜ×Ñ˜TÔ"Ø”=Ñ Ü  Ñ&Ð&Ø”[Ñ Ü Ñ%ˆEÜ�;˜t˜h d¨5¨)Ð4ÀÕCØ—(‘(˜E˜7 T¨!¨" XÑ-Ó.ˆCÜ�z‰z˜#‹ˆØ�&Š=ØˆKÙØ—:‘:˜c“? 1Ñ%Ð%ð ô 	Ð& t hÐ/¸AÖ>ó    c                 óÀ   — | t         j                  v r+t         j                  |    }|dk(  r|t        v r	t        |   }|S | t        v r	t        |    S t	        d| ›�d¬«       y)ai  
    Convert language name to iso639-3 language code. Returns the short 2-letter
    code by default, if one is available, and the 3-letter code otherwise:

    >>> from nltk.langnames import langcode
    >>> langcode('Modern Greek (1453-)')
    'el'

    Specify 'typ=3' to get the 3-letter code:

    >>> langcode('Modern Greek (1453-)', typ=3)
    'ell'
    é   zCould not find language in r   r   N)r   ÚlangcodeÚ
iso639longÚiso639code_retiredr   )r   r   r   s      r   r   r   K   sa   € ð Œu�~‰~ÑÜ�~‰~˜dÑ#ˆØ�!Š8˜¤
Ñ*Ü˜dÑ#ˆDØˆØ	Ô#Ñ	#Ü! $Ñ'Ð'äÐ*¨4¨(Ð3ÀÖBr   c                 ó(   — t         j                  |    S )z^
    Convert BCP-47 tag to Wikidata Q-code

    >>> tag2q('nds-u-sd-demv')
    'Q4289225'
    )r   Úwiki_q)r   s    r   Útag2qr$   i   s   € ô �<‰<˜ÑÐr   c                 ó   — t         |    S )z^
    Convert Wikidata Q-code to BCP-47 tag

    >>> q2tag('Q4289225')
    'nds-u-sd-demv'
    )Ú
wiki_bcp47)Úqcodes    r   Úq2tagr(   s   s   € ô �eÑÐr   c                 ó,   — t        t        | «      |«      S )zÄ
    Convert Wikidata Q-code to BCP-47 (full or short) language name

    >>> q2name('Q4289225')
    'Low German: Mecklenburg-Vorpommern'

    >>> q2name('Q4289225', "short")
    'Low German'
    )r   r(   )r'   r   s     r   Úq2namer*   }   s   € ô ”E˜%“L #Ó&Ð&r   c                 ó*   — t        t        | «      «      S )zd
    Convert simple language name to Wikidata Q-code

    >>> lang2q('Low German')
    'Q25433'
    )r$   r   )r   s    r   Úlang2qr,   Š   s   € ô ”˜$“Ó Ð r   c                 óæ   — t        | j                  «       «      t        t        | j                  «       «      «      k(  r$| j	                  «       D ��ci c]  \  }}||“Œ
 c}}S t        d«       yc c}}w )z3Return inverse mapping, but only if it is bijectivez1This dictionary has no bijective inverse mapping.N)ÚlenÚkeysÚsetÚvaluesÚitemsr   )ÚdicÚkeyÚvals      r   Úinverse_dictr6   ™   sQ   € ä
ˆ3�8‰8‹:ƒœ#œc #§*¡*£,Ó/Ó0Ò0Ø+.¯9©9«;×7™Z˜c 3��S‘Ó7Ð7äÐ@ÕAùó 8s   ÁA-ÚaarÚaaÚabkÚabÚafrÚafÚakaÚakÚamhÚamÚaraÚarÚargÚanÚasmÚasÚavaÚavÚaveÚaeÚaymÚayÚazeÚazÚbakÚbaÚbamÚbmÚbelÚbeÚbenÚbnÚbisÚbiÚbodÚboÚbosÚbsÚbreÚbrÚbulÚbgÚcatÚcaÚcesÚcsÚchaÚchÚcheÚceÚchuÚcuÚchvÚcvÚcorÚkwÚcosÚcoÚcreÚcrÚcymÚcyÚdanÚdaÚdeuÚdeÚdivÚdvÚdzoÚdzÚellÚelÚengÚenÚepoÚeoÚestÚetÚeusÚeuÚeweÚeeÚfaoÚfoÚfasÚfaÚfijÚfjÚfinÚfiÚfraÚfrÚfryÚfyÚfulÚffÚglaÚgdÚgleÚgaÚglgÚglÚglvÚgvÚgrnÚgnÚgujÚguÚhatÚhtÚhauÚhaÚhbsÚshÚhebÚheÚherÚhzÚhinÚhiÚhmoÚhoÚhrvÚhrÚhunÚhuÚhyeÚhyÚiboÚigÚidoÚioÚiiiÚiiÚikuÚiuÚileÚieÚinaÚiaÚindÚidÚipkÚikÚislÚisÚitaÚitÚjavÚjvÚjpnÚjaÚkalÚklÚkanÚknÚkasÚksÚkatÚkaÚkauÚkrÚkazÚkkÚkhmÚkmÚkikÚkiÚkinÚrwÚkirÚkyÚkomÚkvÚkonÚkgÚkorÚkoÚkuaÚkjÚkurÚkuÚlaoÚloÚlatÚlaÚlavÚlvÚlimÚliÚlinÚlnÚlitÚltÚltzÚlbÚlubÚluÚlugÚlgÚmahÚmhÚmalÚmlÚmarÚmrÚmkdÚmkÚmlgÚmgÚmltÚmtÚmonÚmnÚmriÚmiÚmsaÚmsÚmyaÚmyÚnauÚnaÚnavÚnvÚnblÚnrÚndeÚndÚndoÚngÚnepÚneÚnldÚnlÚnnoÚnnÚnobÚnbÚnorÚnoÚnyaÚnyÚociÚocÚojiÚojÚoriÚorÚormÚomÚossÚosÚpanÚpaÚpliÚpiÚpolÚplÚporÚptÚpusÚpsÚqueÚquÚrohÚrmÚronÚroÚrunÚrnÚrusÚruÚsagÚsgÚsanÚsaÚsinÚsiÚslkÚskÚslvÚslÚsmeÚseÚsmoÚsmÚsnaÚsnÚsndÚsdÚsomÚsoÚsotÚstÚspaÚesÚsqiÚsqÚsrdÚscÚsrpÚsrÚsswÚssÚsunÚsuÚswaÚswÚsweÚsvÚtahÚtyÚtamÚtaÚtatÚttÚtelÚteÚtgkÚtgÚtglÚtlÚthaÚthÚtirÚtiÚtonÚtoÚtsnÚtnÚtsoÚtsÚtukÚtkÚturÚtrÚtwiÚtwÚuigÚugÚukÚurÚuzÚveÚviÚvoÚwaÚwoÚxhÚyiÚyoÚzaÚzhÚzu)ÚukrÚurdÚuzbÚvenÚvieÚvolÚwlnÚwolÚxhoÚyidÚyorÚzhaÚzhoÚzulÚfrizWestern FrisianÚauvÚ	AuvergnatÚgscÚGasconÚlmsÚLimousinÚlncÚLanguedocienÚprvu
   ProvenÃ§alÚamdu   AmapÃ¡ CreoleÚbghÚBoganÚbnhu   BanawÃ¡ÚbvszBelgian Sign LanguageÚccyzSouthern ZhuangÚcitÚChittagonianÚflmz
Falam ChinÚjapu   JaruÃ¡raÚkobÚKohoroxitariÚmobÚMoinbaÚmzfÚAikuÚnhjzTlalitzlipa NahuatlÚnhszSoutheastern Puebla NahuatlÚoccÚ
OccidentalÚtmxÚTomyangÚtotzPatla-Chicontla TotonacÚxmiu   MiarrÃ£ÚyibÚYinglishÚztczLachirioag ZapotecÚatfÚAtuenceÚbqezNavarro-Labourdin BasqueÚbszzSouletin BasqueÚaexÚAmeraxÚaheÚAheÚaizÚAariÚaknÚAmikoanaÚarfÚArafundiÚazrÚAdzeraÚbcxÚPamonaÚbiiÚBisuÚbkeÚBengkuluÚbluz
Hmong NjuaÚboczBakung KenyahÚbsdzSarawak BisayaÚbwvzBahau River KenyahÚbxtÚBuxinhuaÚbyuÚBuyangÚccxzNorthern ZhuangÚcruu	   CarÃºtanaÚdatzDarang DengÚdykz
Land DayakÚeniÚEnimÚfizÚIzereÚgenz
Geman DengÚgghzGarreh-AjuranÚituÚItutangÚkdszLahu ShiÚknhzKayan River KenyahÚkrgzNorth KorowaiÚkrqÚKruiÚkxgÚKatinganÚlmtÚLematangÚlntÚLintangÚlodÚBerawanÚmbgu   Northern NambikuÃ¡raÚmdozSouthwest GbayaÚmhvÚ	ArakaneseÚmivÚMimiÚmqdÚMadangÚnkyzKhiamniungan NagaÚnxjÚNyaduÚognÚOganÚorkÚOrokaivaÚpajzIpeka-TapuiaÚpeczSouthern PesisirÚpenÚPenesakÚplmÚ	PalembangÚpojzLower PokomoÚpunÚPubianÚraeÚRanauÚrjbÚ	RajbanshiÚrwsÚRawasÚsddÚSemendoÚsdizSindang KelingiÚsklÚSelakoÚslbzKahumamahon SaluanÚsrjÚSerawaiÚsufÚTarpiaÚsuhÚSubaÚsuuÚSungkaiÚszkÚSizakiÚtlezSouthern MarakwetÚtnjÚTanjongÚttxzTutong 1ÚubmzUpper Baram KenyahÚvkyz
Kayu AgungÚvmoz	Muko-MukoÚwreÚWareÚxahÚKahayanÚxkmzMahakam KenyahÚxufÚKunfalÚyiozDayao YiÚymjzMuji YiÚyplzPula YiÚypwzPuwa YiÚywmz	Wumeng YiÚyymzYuanjiang-Mojiang YiÚmlyzMalay (individual language)ÚmuwÚMundariÚxstzSilt'eÚopezOld PersianÚsccÚSerbianÚscrÚCroatianÚxskÚSakanÚmolÚ	MoldavianÚaayÚAariyaÚaccu   Cubulco AchÃ­Úcbmz Yepocapa Southwestern CakchiquelÚchsÚChumashÚckczNorthern CakchiquelÚckdzSouth Central CakchiquelÚckezEastern CakchiquelÚckfzSouthern CakchiquelÚckiu!   Santa MarÃ­a De JesÃºs CakchiquelÚckjz Santo Domingo Xenacoj CakchiquelÚckkz"Acatenango Southwestern CakchiquelÚckwzWestern CakchiquelÚcnmu   IxtatÃ¡n ChujÚctiz	Tila CholÚcunu   CunÃ©n QuichÃ©ÚemlzEmiliano-RomagnoloÚeurÚ	EuropantoÚgmozGamo-Gofa-DawroÚhsfzSoutheastern HuastecÚhvau   San LuÃ­s PotosÃ­ HuastecÚixiz
Nebaj IxilÚixjzChajul IxilÚjaizWestern JacaltecoÚmmszSouthern MamÚmpfzTajumulco MamÚmtzÚTacanecÚmvczCentral MamÚmvju   Todos Santos CuchumatÃ¡n MamÚpoazEastern PokomamÚpobu   Western PokomchÃ­ÚpouzSouthern PokomamÚppvu   PapavÃ´Úquju   Joyabaj QuichÃ©Úqutu   West Central QuichÃ©Úquuu   Eastern QuichÃ©Úqxiu   San AndrÃ©s QuichÃ©ÚsicÚ	MalinguatÚstcz
Santa CruzÚtlzzToala'Útzbu   BachajÃ³n TzeltalÚtzczChamula TzotzilÚtzeu   ChenalhÃ³ TzotzilÚtzsu   San AndrÃ©s Larrainzar TzotzilÚtztzWestern TzutujilÚtzuu   HuixtÃ¡n TzotzilÚtzzu   ZinacantÃ¡n TzotzilÚvlrÚVatrataÚyuszChan Santa Cruz MayaÚnfgÚNyengÚnfkÚShakaraÚagpÚParananÚbhkzAlbay BicolanoÚbkbÚFinalligÚbtbzBeti (Cameroon)ÚcjrÚ	ChorotegaÚcmkÚChimakumÚdrhÚDarkhatÚdrwÚDarwaziÚgavÚ	GabutamonÚmofzMohegan-Montauk-NarragansettÚmstzCataelano MandayaÚmytzSangab MandayaÚrmru   CalÃ³ÚsglzSanglechi-IshkashimiÚsulÚ
SurigaononÚsumzSumo-MayangnaÚtnfÚ	TangshewiÚwgwÚWagawagaÚayxzAyi (China)ÚbjqzSouthern Betsimisaraka MalagasyÚdhazDhanwar (India)ÚdklzKolum So DogonÚmjaÚMaheiÚnbfÚNaxiÚnooÚNootkaÚtieÚTingalÚtkkÚTakpaÚbazÚTunenÚbjdÚ
BandjigaliÚccqÚ	ChaungthaÚckazKhumi Awa ChinÚdapzNisi (India)ÚdwlzWalo Kumbe DogonÚelpÚ	ElpaputihÚgbcÚGarawaÚgioÚGelaoÚhrrÚHoruruÚibiÚIbiloÚjarzJarawa (Nigeria)ÚkdvÚKadoÚkghzUpper Tanudan KalingaÚkppz
Paku KarenÚkzhzKenuzi-DongolaÚlcqÚLuhuÚmgxÚOmatiÚnlnzDurango NahuatlÚpbzÚPaluÚpgyÚPongyongÚscaÚSansuÚtlwzSouth WemaleÚunpÚWororaÚwiwÚWiranguÚybdÚYangbyeÚyenÚYendangÚymaÚYampheÚdafÚDanÚdjlÚDjiwarliÚggrzAghu TharnggaluÚilwÚTalurÚizizIzi-Ezaa-Ikwo-MgboÚmegÚMeaÚmldÚMalakhelÚmntÚMaykulanÚmwdÚMudburaÚmyqzForest ManinkaÚnbxÚNguraÚnlrÚNgarlaÚpcrÚPanangÚpprÚPiruÚtggÚTanggaÚwitÚWintuÚxiaÚXiandaoÚyiyz
Yir YorontÚyosÚYosÚemoÚEmokÚggmz	Gugu MiniÚlegÚLenguaÚlmmÚLamamÚmhhzMaskoy PidginÚpuzz
Purum NagaÚsapu	   SanapanÃ¡ÚyuuÚYughÚaamÚAramanikÚadpÚAdapÚaueu   Ç‚KxÊ¼auÇ�Ê¼einÚbmyz$Bemba (Democratic Republic of Congo)Úbxxz$Borna (Democratic Republic of Congo)ÚbyyÚBuyaÚdzdÚDazaÚgfxu   Mangetti Dune ÇƒXungÚgtizGbati-riÚimeÚ	ImeraguenÚkbfÚKakauhuaÚkojz
Sara DunjoÚkwqÚKwakÚkxeÚKakihumÚliiÚLingkhimÚmwjÚMaligoÚnnxÚNgongÚounu   ÇƒOÇƒungÚpmuzMirpur PanjabiÚsgoÚSongaÚthxÚTheÚtsfzSouthwestern TamangÚuokÚUokhaÚxsjÚSubiÚydszYiddish Sign LanguageÚymtzMator-Taygi-KaragasÚynhÚYanghoÚbgmzBaga MboteniÚbtlÚBhatolaÚcbeÚ	ChipiajesÚcbhÚCaguaÚcoyÚCoyaimaÚcquzChilean QuechuaÚcumÚCumeralÚdujÚDhuwalÚggnzEastern GurungÚggozSouthern GondiÚguvÚGeyÚiapÚIapamaÚillÚIranunÚkgcÚKassengÚkoxÚCoximaÚktrzKota Marudu TinagasÚkvsÚKunggaraÚkzjzCoastal KadazanÚkztzTambunan DusunÚnadÚNijadaliÚntsÚ
NatagaimasÚomeÚOmejesÚpmcÚPalumataÚpodÚPonaresÚppaÚPaoÚpryzPray 3ÚrnaÚRunaÚsvrÚSavaraÚtduzTempasuk DusunÚthczTai Hang TongÚtidÚTidongÚtmpu	   Tai MÃ¨neÚtnezTinoc KallahanÚtoeÚTomedesÚxbazKamba (Brazil)Úxbxu   KabixÃ­Úxipu	   XipinÃ¡waÚxkhÚKarahawyanaÚyriu   YarÃ­ÚjegÚJengÚkgdÚKataangÚkrmÚKrimÚprbzLua'ÚpukzPu KoÚrieÚRienÚrsizRennellese Sign LanguageÚskkÚSokÚsnhÚShinaboÚlsgzLyons Sign LanguageÚmwxÚMediakÚmwyÚMosiroÚncpÚNdaktupÚaiszNataoran AmisÚasdÚAsasÚditÚDirariÚdudz	Hun-SaareÚlbaÚLuiÚlloÚKhlorÚmydÚMarambaÚmyizMina (India)ÚnnsÚNingyeÚaohÚArmaÚayyzTayabas AytaÚbbzzBabalia Creole ArabicÚbpbÚ	BarbacoasÚccaÚCaucaÚcdgÚChamariÚdguÚDegaruÚdrrÚDororoÚekczEastern KarnicÚgliÚGuliguliÚkjfÚKhalajÚkxlzNepali KuruxÚkxuzKui (India)ÚlmzÚLumbeeÚnxuÚNarauÚplpÚPalpaÚsdmÚ	SemandangÚtbbÚTapebaÚxrqÚKarrangaÚxtzÚ	TasmanianÚzirÚZiriyaÚthwÚThudamÚbicÚBikaruÚbijzVaghat-Ya-Bijim-LegeriÚblgÚBalauÚgjiÚGejiÚMuyaÚNgoniÚ	PapitalaizIja-ZubaÚWarapuzJudeo-Tunisian ArabicÚ
ChungmbokozLaka (Nigeria)zLango (South Sudan)ÚPiniÚSamaÚSebuyauzKulon-PazehÚWardujiÚWyandot)ÚmvmÚngoÚpatÚvkiÚwraÚajtÚcugÚlakÚlnoÚpiiÚsmdÚsnbÚuunÚwrdÚwya)r   )r   )Ú__doc__ÚreÚwarningsr   Únltk.corpusr   Úcompiler   r   r   r$   r(   r*   r,   r6   Úload_wiki_qr#   r&   r   r   r    r!   © r   r   ú<module>rï     s¹  ðñó8 
Ý å àˆb�j‰jÐ+Ó,€ô?ô:Cò<òô
'ò!òBð €× Ñ Ô Ù˜%Ÿ,™,Ó'€
ðyØ	ˆ4ðyà	ˆ4ðyð 
ˆ4ðyð 
ˆ4ð	yð
 
ˆ4ðyð 
ˆ4ðyð 
ˆ4ðyð 
ˆ4ðyð 
ˆ4ðyð 
ˆ4ðyð 
ˆ4ðyð 
ˆ4ðyð 
ˆ4ðyð 
ˆ4ðyð 
ˆ4ðyð  
ˆ4ð!yð" 
ˆ4ñ#yð$ 
ˆ4ð%yð& 
ˆ4ð'yð( 
ˆ4ð)yð* 
ˆ4ð+yð, 
ˆ4ð-yð. 
ˆ4ð/yð0 
ˆ4ð1yð2 
ˆ4ð3yð4 
ˆ4ð5yð6 
ˆ4ð7yð8 
ˆ4ð9yð: 
ˆ4ð;yð< 
ˆ4ð=yð> 
ˆ4ð?yð@ 
ˆ4ðAyðB 
ˆ4ðCyðD 
ˆ4òEyðF 
ˆ4ðGyðH 
ˆ4ðIyðJ 
ˆ4ðKyðL 
ˆ4ðMyðN 
ˆ4ðOyðP 
ˆ4ðQyðR 
ˆ4ðSyðT 
ˆ4ðUyðV 
ˆ4ðWyðX 
ˆ4ðYyðZ 
ˆ4ð[yð\ 
ˆ4ð]yð^ 
ˆ4ð_yð` 
ˆ4ðayðb 
ˆ4ðcyðd 
ˆ4ðeyðf 
ˆ4ògyðh 
ˆ4ðiyðj 
ˆ4ðkyðl 
ˆ4ðmyðn 
ˆ4ðoyðp 
ˆ4ðqyðr 
ˆ4ðsyðt 
ˆ4ðuyðv 
ˆ4ðwyðx 
ˆ4ðyyðz 
ˆ4ð{yð| 
ˆ4ð}yð~ 
ˆ4ðyð@ 
ˆ4ðAyðB 
ˆ4ðCyðD 
ˆ4ðEyðF 
ˆ4ðGyðH 
ˆ4òIyðJ 
ˆ4ðKyðL 
ˆ4ðMyðN 
ˆ4ðOyðP 
ˆ4ðQyðR 
ˆ4ðSyðT 
ˆ4ðUyðV 
ˆ4ðWyðX 
ˆ4ðYyðZ 
ˆ4ð[yð\ 
ˆ4ð]yð^ 
ˆ4ð_yð` 
ˆ4ðayðb 
ˆ4ðcyðd 
ˆ4ðeyðf 
ˆ4ðgyðh 
ˆ4ðiyðj 
ˆ4òkyðl 
ˆ4ðmyðn 
ˆ4ðoyðp 
ˆ4ðqyðr 
ˆ4ðsyðt 
ˆ4ðuyðv 
ˆ4ðwyðx 
ˆ4ðyyðz 
ˆ4ð{yð| 
ˆ4ð}yð~ 
ˆ4ðyð@ 
ˆ4ðAyðB 
ˆ4ðCyðD 
ˆ4ðEyðF 
ˆ4ðGyðH 
ˆ4ðIyðJ 
ˆ4ðKyðL 
ˆ4òMyðN 
ˆ4ðOyðP 
ˆ4ðQyðR 
ˆ4ðSyðT 
ˆ4ðUyðV 
ˆ4ðWyðX 
ˆ4ðYyðZ 
ˆ4ð[yð\ 
ˆ4ð]yð^ 
ˆ4ð_yð` 
ˆ4ðayðb 
ˆ4ðcyðd 
ˆ4ðeyðf 
ˆ4ðgyðh 
ˆ4ðiyðj 
ˆ4ðkyðl 
ˆ4ðmyðn 
ˆ4òoyðp 
ˆ4ðqyðr 
ˆ4ðsyðt 
‰4ðuyñv 
‰4ðwyñx 
‰4ðyyñz 
‰4ð{yñ| 
‰4ð}yñ~ 
‰4ðyñ@ 
‰4ðAyñB 
‰4ðCyñD 
‰4ðEyñF 
‰4ðGyñH 
‰4ðIyñJ 
‰4ðKyñL 
‰4ðMyñN 
‰4ðOyñP 
‰4òQyñR 
‰4ðSyñT 
‰4ðUyñV 
‰4ðWyñX 
‰4ðYyñZ 
‰4ð[yñ\ 
‰4ð]yñ^ 
‰4ð_yñ` 
‰4ðayñb 
‰4ðcyñd 
‰4ðeyñf 
‰4ðgyñh 
‰4ðiyñj 
‰4ðkyñl 
‰4ðmyñn 
‰4ðoyñp 
‰4ðqyñr 
‰4òsyñt 
‰4ðuyñv 
‰4ðwyñx 
‰4ðyyñz 
‰4ð{yñ| 
‰4ð}yñ~ 
‰4ðyñ@ 
‰4ðAyñB 
‰4ðCyñD 
‰4ðEyñF 
‰4ðGyñH 
‰4ðIyñJ 
‰4ðKyñL 
‰4ðMyñN 
‰4ðOyñP 
‰4ðQyñR 
‰4ðSyñT 
‰4ñUyñV ÙÙÙÙÙÙÙÙÙÙÙÙÙóqy€ðxuÙ	Ñðuá	‰;ðuñ 
‰8ðuñ 
‰:ð	uñ
 
‰>ðuñ 
‰<ðuñ 
‰?ðuñ 
‰7ðuñ 
‰9ðuñ 
Ñ"ðuñ 
Ñðuñ 
‰>ðuñ 
‰<ðuñ 
‰:ðuñ 
‰>ðuñ  
‰8ð!uñ" 
‰6ñ#uñ$ 
Ñ ð%uñ& 
Ñ(ð'uñ( 
‰<ð)uñ* 
‰9ð+uñ, 
Ñ$ð-uñ. 
‰9ð/uñ0 
‰:ð1uñ2 
Ñð3uñ4 
‰9ð5uñ6 
Ñ%ð7uñ8 
Ñð9uñ: 
‰8ð;uñ< 
‰5ð=uñ> 
‰6ð?uñ@ 
‰:ðAuñB 
‰:ðCuñD 
‰8òEuñF 
‰8ðGuñH 
‰6ðIuñJ 
‰:ðKuñL 
‰<ðMuñN 
‰?ðOuñP 
ÑðQuñR 
ÑðSuñT 
‰:ðUuñV 
‰8ðWuñX 
ÑðYuñZ 
‰;ð[uñ\ 
‰=ð]uñ^ 
‰<ð_uñ` 
‰6ðauñb 
‰7ðcuñd 
‰<ðeuñf 
‰?òguñh 
‰9ðiuñj 
‰:ðkuñl 
Ñðmuñn 
‰?ðouñp 
‰6ðquñr 
‰:ðsuñt 
‰:ðuuñv 
‰9ðwuñx 
‰9ðyuñz 
Ñ!ð{uñ| 
Ñð}uñ~ 
‰;ðuñ@ 
‰6ðAuñB 
‰8ðCuñD 
ÑðEuñF 
‰7ðGuñH 
‰6òIuñJ 
‰:ðKuñL 
‰>ðMuñN 
ÑðOuñP 
‰9ðQuñR 
‰;ðSuñT 
‰>ðUuñV 
‰8ðWuñX 
‰7ðYuñZ 
‰;ð[uñ\ 
‰7ð]uñ^ 
‰9ð_uñ` 
Ñðauñb 
‰8ðcuñd 
Ñðeuñf 
‰9ðguñh 
‰8ðiuñj 
‰6òkuñl 
‰9ðmuñn 
‰8ðouñp 
Ñðquñr 
‰9ðsuñt 
‰:ðuuñv 
Ñðwuñx 
‰<ðyuñz 
‰;ð{uñ| 
‰6ð}uñ~ 
‰9ðuñ@ 
ÑðAuñB 
‰8ðCuñD 
‰:ðEuñF 
‰9ðGuñH 
‰9ðIuñJ 
‰9ðKuñL 
‰;òMuñN 
Ñ!ðOuñP 
Ñ(ðQuñR 
‰9ðSuñT 
‰8ðUuñV 
‰=ðWuñX 
‰9ðYuñZ 
‰:ð[uñ\ 
‰7ð]uñ^ 
‰;ð_uñ` 
‰8ðauñb 
‰?ðcuñd 
Ñ-ðeuñf 
‰9ðguñh 
Ñ ðiuñj 
Ñ%ðkuñl 
Ñðmuñn 
Ñ òouñp 
Ñ.ðquñr 
Ñ-ðsuñt 
Ñ/ðuuñv 
Ñðwuñx 
‰?ðyuñz 
‰;ð{uñ| 
Ñð}uñ~ 
Ñðuñ@ 
‰;ðAuñB 
ÑðCuñD 
Ñ!ðEuñF 
Ñ&ðGuñH 
‰<ðIuñJ 
‰=ðKuñL 
ÑðMuñN 
‰>ðOuñP 
‰?òQuñR 
‰9ðSuñT 
‰=ðUuñV 
Ñ)ðWuñX 
ÑðYuñZ 
Ñð[uñ\ 
Ñð]uñ^ 
‰9ð_uñ` 
Ñðauñb 
Ñ!ðcuñd 
Ñðeuñf 
Ñ ðguñh 
‰;ðiuñj 
‰<ðkuñl 
‰8ðmuñn 
Ñðouñp 
Ñðquñr 
Ñòsuñt 
Ñ+ðuuñv 
Ñðwuñx 
Ñðyuñz 
Ñ ð{uñ| 
‰9ð}uñ~ 
Ñ!ðuñ@ 
‰7ðAuñB 
‰9ðCuñD 
‰9ðEuñF 
ÑðGuñH 
‰:ðIuñJ 
ÑðKuñL 
‰;ðMuñN 
‰:ðOuñP 
‰9ðQuñR 
‰9ðSuñT 
‰;òUuñV 
Ñ)ðWuñX 
ÑðYuñZ 
Ñð[uñ\ 
‰7ð]uñ^ 
Ñ!ð_uñ` 
‰<ðauñb 
‰?ðcuñd 
‰;ðeuñf 
‰:ðguñh 
‰=ðiuñj 
Ñ,ðkuñl 
Ñðmuñn 
Ñðouñp 
‰7ðquñr 
‰6ðsuñt 
‰8ðuuñv 
‰8òwuñx 
‰7ðyuñz 
‰7ð{uñ| 
‰<ð}uñ~ 
‰;ðuñ@ 
ÑðAuñB 
‰>ðCuñD 
ÑðEuñF 
‰;ðGuñH 
‰8ðIuñJ 
‰7ðKuñL 
‰8ðMuñN 
‰7ðOuñP 
ÑðQuñR 
‰6ðSuñT 
Ñ"ðUuñV 
‰<ðWuñX 
ÑòYuñZ 
‰6ð[uñ\ 
‰7ð]uñ^ 
Ñð_uñ` 
‰6ðauñb 
‰:ðcuñd 
‰7ðeuñf 
‰>ðguñh 
‰8ðiuñj 
‰9ðkuñl 
‰9ðmuñn 
‰9ðouñp 
‰8ðquñr 
‰5ðsuñt 
‰:ðuuñv 
Ñðwuñx 
‰7ðyuñz 
Ñò{uñ| 
‰5ð}uñ~ 
‰:ðuñ@ 
‰:ðAuñB 
‰9ðCuñD 
ÑðEuñF 
‰7ðGuñH 
‰8ðIuñJ 
‰8ðKuñL 
‰6ðMuñN 
‰8ðOuñP 
‰7ðQuñR 
‰9ðSuñT 
‰<ðUuñV 
‰5ðWuñX 
‰6ðYuñZ 
‰;ð[uñ\ 
‰8ò]uñ^ 
‰7ð_uñ` 
‰?ðauñb 
‰<ðcuñd 
‰;ðeuñf 
‰6ðguñh 
‰:ðiuñj 
‰6ðkuñl 
Ñðmuñn 
Ñ1ðouñp 
Ñ1ðquñr 
‰6ðsuñt 
‰6ðuuñv 
Ñ!ðwuñx 
‰:ðyuñz 
‰;ð{uñ| 
‰:ð}uñ~ 
‰<òuñ@ 
‰6ðAuñB 
‰9ðCuñD 
‰:ðEuñF 
‰8ðGuñH 
‰7ðIuñJ 
‰:ðKuñL 
ÑðMuñN 
‰7ðOuñP 
‰5ðQuñR 
Ñ ðSuñT 
‰7ðUuñV 
‰6ðWuñX 
Ñ"ðYuñZ 
Ñ ð[uñ\ 
‰8ð]uñ^ 
‰>ð_uñ` 
‰9òauñb 
‰;ðcuñd 
‰7ðeuñf 
‰9ðguñh 
Ñðiuñj 
‰9ðkuñl 
‰8ðmuñn 
Ñðouñp 
Ñðquñr 
‰5ðsuñt 
‰8ðuuñv 
‰8ðwuñx 
‰9ðyuñz 
‰8ð{uñ| 
Ñ ð}uñ~ 
‰:ðuñ@	 
ÑðA	uñB	 
ÑòC	uñD	 
‰:ðE	uñF	 
‰<ðG	uñH	 
‰8ðI	uñJ	 
‰:ðK	uñL	 
‰9ðM	uñN	 
‰5ðO	uñP	 
‰8ðQ	uñR	 
‰6ðS	uñT	 
‰8ðU	uñV	 
ÑðW	uñX	 
‰?ðY	uñZ	 
‰8ð[	uñ\	 
‰;ð]	uñ^	 
Ñð_	uñ`	 
‰9ða	uñb	 
Ñðc	uñd	 
‰9òe	uñf	 
‰;ðg	uñh	 
‰=ði	uñj	 
‰7ðk	uñl	 
‰6ðm	uñn	 
‰9ðo	uñp	 
‰6ðq	uñr	 
‰6ðs	uñt	 
‰7ðu	uñv	 
‰6ðw	uñx	 
Ñ%ðy	uñz	 
‰5ð{	uñ|	 
‰9ð}	uñ~	 
Ñ ð	uñ@
 
‰8ðA
uñB
 
‰8ðC
uñD
 
‰9ðE
uñF
 
‰?òG
uñH
 
‰6ðI
uñJ
 
‰8ðK
uñL
 
‰;ðM
uñN
 
‰5ðO
uñP
 
‰7ðQ
uñR
 
‰9ðS
uñT
 
‰>ðU
uñV
 
‰8ðW
uñX
 
‰6ðY
uñZ
 
‰>ð[
uñ\
 
Ñ"ð]
uñ^
 
‰;ð_
uñ`
 
‰7ða
uñb
 
‰9ðc
uñd
 
‰8ðe
uñf
 
‰8ðg
uñh
 
Ñòi
uñj
 
‰:ðk
uñl
 
‰8ðm
uñn
 
‰>ðo
uñp
 
‰=ðq
uñr
 
‰8ðs
uñt
 
‰7ðu
uñv
 
‰7ðw
uñx
 
‰;ðy
uñz
 
‰8ð{
uñ|
 
‰:ð}
uñ~
 
‰;ð
uñ@ 
‰8ðAuñB 
‰8ðCuñD 
‰8ðEuñF 
Ñ#ðGuñH 
‰7ðIuñJ 
‰6ñKuñL ÙÙÙÙÙ"ÙÙÙ ÙÙÙÙÙÙóiu€ñp ˜+Ó&€
á! -Ó0Ñ r   