
    i+                     8    d dl mZmZmZ d dlZd Zd Zd Zd Zy)    )PreProcessorRegexPreProcessorSubsymbolsNc                 Z    t        t        j                  d d      j                  |       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.

    c                 $    dj                  |       S )Nz(?<={})formatxs    [/var/www/auto_recruiter/arenv/lib/python3.12/site-packages/gtts/tokenizer/pre_processors.py<lambda>ztone_marks.<locals>.<lambda>   s    j//2      search_argssearch_funcrepl)r   r   
TONE_MARKSruntexts    r   
tone_marksr      s+     &&2 
c$i	r   c                 >    t        dd d      j                  |       S )zPRe-form words cut by end-of-line hyphens.

    Remove "<hyphen><newline>".

    -c                 $    dj                  |       S )Nz{}
r   r
   s    r   r   zend_of_line.<locals>.<lambda>   s    w~~a/@ r    r   )r   r   r   s    r   end_of_liner      s"     %@r	c$ir   c                 x    t        t        j                  d dt        j                        j                  |       S )a  Remove 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'.

    c                 $    dj                  |       S )Nz(?<={})(?=\.).r   r
   s    r   r   zabbreviations.<locals>.<lambda>/   s    /66q9 r   r   )r   r   r   flags)r   r   ABBREVIATIONSre
IGNORECASEr   r   s    r   abbreviationsr$      s2     ))9mm	
 
c$ir   c                 T    t        t        j                        j                  |       S )zWord-for-word substitutions.)	sub_pairs)r   r   	SUB_PAIRSr   r   s    r   word_subr(   5   s    W%6%67;;DAAr   )	gtts.tokenizerr   r   r   r"   r   r   r$   r(    r   r   <module>r+      s#    F F 	,Br   