"#hddlmZddlmZmZmZddlZddlZddlZddlZejdejZ dZ dZ dZdZd Zy) )absolute_import)divisionprint_functionunicode_literalsNz\s+c6tjt|S)z Translates multiple whitespace into single space character. If there is at least one new line character chunk is replaced by single LF (Unix new line) character. )MULTIPLE_WHITESPACE_PATTERNsub_replace_whitespace)texts J/var/www/html/sandstorm/venv/lib/python3.12/site-packages/justext/utils.pynormalize_whitespacer s ' * *+> EEc:|j}d|vsd|vrdSdS)zBNormalize all spacing characters that aren't a newline to a space.   )group)matchr s r r r s$ ;;=D4<44<48S8rc,| xs|jS)zw Returns `True` if string contains only white-space characters or is empty. Otherwise `False` is returned. )isspace)strings r is_blankrs : )))rcvtjjtjdj }tjj |d}g}tj|D];}tjj|\}}|dk(s+|j|=t|S)z,Returns a collection of built-in stop-lists.justext stoplistsz.txt) ospathdirnamesysmodules__file__joinlistdirsplitextappend frozenset)path_to_stoplistsstoplist_namesfilenamename extensions r get_stoplistsr,%s I(>(G(GH %6 DNJJ01(''**84i    ! !$ '( ^ $$rctjjdd|z} tjd|}td|jDS#t $rt d|zwxYw)zAReturns an built-in stop-list for the language as a set of words.rz%s.txtrzStoplist for language '%s' is missing. Please use function 'get_stoplists' for complete list of stoplists and feel free to contribute by your own stoplist.c3ZK|]#}|jdj%yw)utf8N)decodelower).0ws r zget_stoplist..?s"N!QXXf%++-Ns)+) rrr"pkgutilget_dataIOError ValueErrorr& splitlines)language file_path stopwordss r get_stoplistr=3s{ [(X*=>I $$Y :  Ny7K7K7MN NN   @BJ K   s AA3) __future__rrrrrerrr5compileUNICODErr r rr,r=rr rCsN'AA (bjj<F9 * % Or