o %e& @s,dZddlZddlmZddlmZdZZdZiZ e dj Z e dj Zd ZiZzed ZWneefyCeejd ZYnweeD]!Zejd krkejd dZeee<eddZeevrkeee<qJddeDZddZGdddZ Gddde!Z"GdddZ#GdddZ$dS)zY Pyphen ====== Pure Python module to hyphenate text, inspired by Ruby's Text::Hyphen. N) resources)Pathz0.14.0)Pyphen LANGUAGESlanguage_fallbackz\^{2}([0-9a-f]{2})z (\d?)(\D?))%# LEFTHYPHENMINRIGHTHYPHENMINCOMPOUNDLEFTHYPHENMINCOMPOUNDRIGHTHYPHENMINzpyphen.dictionaries dictionariesz.dic_cCsi|]}||qS)lower).0namerrB/var/www/html/venv/lib/python3.10/site-packages/pyphen/__init__.py -srcCsH|ddd}|r"d|}|tvrt|S||s dSdS)a Get a fallback language available in our dictionaries. http://www.unicode.org/reports/tr35/#Locale_Inheritance We use the normal truncation inheritance. This function needs aliases including scripts for languages with multiple regions available. -rN)replacersplitjoinLANGUAGES_LOWERCASEpop)languagepartsrrrr0s   rc@ eZdZdZddZddZdS)AlternativeParserzParser of nonstandard hyphen pattern alternative. The instance returns a special int with data about the current position in the pattern when called with an odd value. cCsP|d}|d|_t|d|_t|d|_|dr&|jd7_dSdS)N,r.)rchangeintindexcut startswith)selfpattern alternativerrr__init__Hs   zAlternativeParser.__init__cCs8|jd8_t|}|d@rt||j|j|jfS|S)Nr")r'r&DataIntr%r()r*valuerrr__call__Ps zAlternativeParser.__call__N)__name__ __module__ __qualname____doc__r-r0rrrrr As r c@seZdZdZdddZdS)r.zE``int`` with some other data can be stuck to in a ``data`` attribute.NcCs0t||}|rt|tr|j|_|S||_|S)zCreate a new ``DataInt``. Call with ``reference=dataint_object`` to use the data from another ``DataInt``. )r&__new__ isinstancer.data)clsr/r7 referenceobjrrrr5[s zDataInt.__new__)NN)r1r2r3r4r5rrrrr.Ysr.c@r)HyphDictzHyphenation patterns.c sJi|_|d}|dkrd}||dddD]t}|}|r-|t r.q t dd|}d |vrKd |vrK|d d\}}t ||nt t fd d t|D\}}t|d krcq d t|}}||sv|d7}||rn||ds|d8}||dr|||||f|jd|<q i|_tdd|jD|_dS)zhRead a ``hyph_*.dic`` and parse its patterns. :param path: Path of hyph_*.dic to read rbzmicrosoft-cp1251cp1251 r"NcSstt|ddS)Nr")chrr&group)matchrrrsz#HyphDict.__init__../=cs g|] \}}||p dfqS)0r)ristringfactoryrr sz%HyphDict.__init__..rcss|]}t|VqdS)N)len)rkeyrrr sz$HyphDict.__init__..)patternsopenreadlinedecoder read_textrstripr)ignored parse_hexr r&zipparsemaxrMrcachemaxlen) r*pathencodingr+r,tagsvaluesstartendrrIrr-ms<      zHyphDict.__init__c Cs|}|j|}|durtd|d}dgt|d}tt|dD]@}t||jt|d}t|d|D]*}|j|||}|sIq:|\} } t|| || t| } t t | || || <q:q%ddt |D|j|<}|S)aGet a list of positions where the word can be hyphenated. :param word: unicode string of the word to hyphenate E.g. for the dutch word 'lettergrepen' this method returns ``[3, 6, 9]``. Each position is a ``DataInt`` with a data attribute. If the data attribute is not ``None``, it contains a tuple with information about nonstandard hyphenation at that point: ``(change, index, cut)``. change a string like ``'ff=f'``, that describes how hyphenation should take place. index where to substitute the change, counting from the current point cut how many characters to remove while substituting the nonstandard hyphenation Nr$rr"cSs(g|]\}}|drt|d|dqS)r#r")r9)r.)rrGr9rrrrKs  z&HyphDict.positions..) rr[getrMrangeminr\rPslicemaprZ enumerate) r*wordpoints pointed_word referencesrGstopjr+offsetr`slice_rrr positionss&  zHyphDict.positionsN)r1r2r3r4r-rqrrrrr;js 0r;c@sBeZdZdZdddZddZd d Zdd d ZdddZeZ dS)rzEHyphenation class, with methods to hyphenate strings in various ways.Nr#TcCsB|stt|}||_||_|r|tvrt|t|<t||_dS)aCreate an hyphenation instance for given lang or filename. :param filename: filename of hyph_*.dic to read :param lang: lang of the included dict to use if no filename is given :param left: minimum number of characters of the first syllabe :param right: minimum number of characters of the last syllabe :param cache: if ``True``, use cached copy of the hyphenation patterns N)rrleftrighthdcacher;hd)r*filenamelangrrrsr[rrrr-s   zPyphen.__init__cs*t|jfddj|DS)zGet a list of positions where the word can be hyphenated. :param word: unicode string of the word to hyphenate See also ``HyphDict.positions``. The points that are too far to the left or right are removed. cs*g|]}j|krkrnn|qSr)rr)rrGrsr*rrrKs*z$Pyphen.positions..)rMrsrurq)r*rirrxrrqs zPyphen.positionsccst||D]?}|jr:|j\}}}||7}|r|}|d\}}|d||||||dfVq|d|||dfVqdS)zIterate over all hyphenation possibilities, the longest first. :param word: unicode string of the word to hyphenate rEN)reversedrqr7isupperupperr)r*ripositionr%r'r(c1c2rrriterates (zPyphen.iteratercCs@|t|8}||D]\}}t||kr|||fSq dS)aGet the longest possible first part and the last part of a word. :param word: unicode string of the word to hyphenate :param width: maximum length of the first part :param hyphen: unicode string used as hyphen character The first part has the hyphen already attached. Returns ``None`` if there is no hyphenation point before ``width``, or if the word could not be hyphenated. N)rMr)r*riwidthhyphenw1w2rrrwraps  z Pyphen.wrapcCsvt|}t||D]*}|jr/|j\}}}||7}|r"|}|d|||||<q |||q d|S)aGet the word as a string with all the possible hyphens inserted. :param word: unicode string of the word to hyphenate :param hyphen: unicode string used as hyphen character E.g. for the dutch word ``'lettergrepen'``, this method returns the unicode string ``'let-ter-gre-pen'``. The hyphen string to use can be given as the second parameter, that defaults to ``'-'``. rErL) listryrqr7rzr{rinsertr)r*rirlettersr|r%r'r(rrrinserteds   zPyphen.inserted)NNr#r#T)r) r1r2r3r4r-rqrrrr0rrrrrs   r)%r4re importlibrpathlibrVERSION __version____all__rtcompilesubrWfindallrYrVrfilesr AttributeError TypeError__file__parentsortediterdirr]suffixrr short_namerrr r&r.r;rrrrrs<     c