a Tg@s<ddlmZmZddZddZddZdd Zd d Zd S) ) RegexBuildersymbolscCsttjdddjS)zKeep tone-modifying punctuation by matching following character. Assumes the `tone_marks` pre-processor was run for cases where there might not be any space after a tone-modifying punctuation mark. cSs d|S)Nz(?<={}).formatxr\/var/www/html/texto_audio/venv/lib/python3.9/site-packages/gtts/tokenizer/tokenizer_cases.py ztone_marks..Z pattern_argsZ pattern_func)rr TONE_MARKSregexrrrr tone_markss rcCsttjdddjS)aJPeriod and comma case. Match if not preceded by "." and only if followed by space. Won't cut in the middle/after dotted abbreviations; won't cut numbers. Note: Won't match if a dotted abbreviation ends a sentence. Note: Won't match the end of a sentence if not followed by a space. cSs d|S)Nz(?.r )rr PERIOD_COMMArrrrr period_commas rcCsttjdddjS)zColon case. Match a colon ":" only if not preceded by a digit. Mainly to prevent a cut in the middle of time notations e.g. 10:01 cSs d|S)Nz (?.r )rrCOLONrrrrr colon#s rcCs@dttjttjttjttj}t|dddjS)zMatch other punctuation. Match other punctuation to split on; punctuation that naturally inserts a break in speech. cSs d|SNz{}rrrrr r <r z#other_punctuation..r ) joinsetrALL_PUNCr rrrrZpuncrrr other_punctuation/srcCstj}t|dddjS)z[Match all punctuation. Use as only tokenizer case to mimic gTTS 1.x tokenization. cSs d|Srrrrrr r Er z(legacy_all_punctuation..r )rrrrrrrr legacy_all_punctuation?srN)Zgtts.tokenizerrrrrrrrrrrr s