o vZh+@s@ddlmZmZmZddlZddZddZddZd d ZdS) )PreProcessorRegexPreProcessorSubsymbolsNcCsttjdddd|S)zAdd a space after tone-modifying punctuation. Because the `tone_marks` tokenizer case will split after a tone-modifying punctuation mark, make sure there's whitespace after. cS d|S)Nz(?<={})formatxr L/var/www/auris/lib/python3.10/site-packages/gtts/tokenizer/pre_processors.py ztone_marks..  search_args search_funcrepl)rrZ TONE_MARKSruntextr r r tone_markssrcCstddddd|S)zPRe-form words cut by end-of-line hyphens. Remove "". -cSr)Nz{} rrr r r r r zend_of_line..r)rrrr r r end_of_lines  rcCsttjdddtjd|S)aRemove periods after an abbreviation from a list of known abbreviations that can be spoken the same without that period. This prevents having to handle tokenization of that period. Note: Could potentially remove the ending period of a sentence. Note: Abbreviations that Google Translate can't pronounce without (or even with) a period should be added as a word substitution with a :class:`PreProcessorSub` pre-processor. Ex.: 'Esq.', 'Esquire'. cSr)Nz(?<={})(?=\.).rrr r r r /r zabbreviations..r)rrrflags)rrZ ABBREVIATIONSre IGNORECASErrr r r abbreviationssrcCsttjd|S)zWord-for-word substitutions.)Z sub_pairs)rrZ SUB_PAIRSrrr r r word_sub5sr) Zgtts.tokenizerrrrrrrrrr r r r s