
    $HJjv                     x   d dl Z d dlZd dlmZ  e j                  d      Z e j                  d      Zddddd	d
dddZej                   ej                   ee
dddd      j                         j                  d                   ddj                  ej                               z   dz   Zd Zd Zd Zd Zd Zy)    N)Pathz	([ ]?[%])z*([a-zA-Z])\.(com|gov|org|vn|com.vn|edu.vn)u    vân vân. u   về việcu   địa chỉu   kính gửiu   thân gửiu   khôngu   biết)zv\.vzv/vu   đ/czk/gzth/gkobitbikz..datazvi_teencode.jsonzutf-8)encoding(|)c                      y)Nu    phần trăm ms    k/Users/ahmed/devFolder/claude-voice/.venv/lib/python3.12/site-packages/misaki/vi_cleaner/abbreviation_vi.py_expand_percent_vir      s        c                 L    | j                  d       d| j                  d       S )N   u    chấm    )groupr   s    r   _expand_urls_vir      s#    ggaj\!''!*..r   c                 v    | j                  d      }|j                  dd      j                         }t        |   S )Nr   .z\.)r   replacelower_abbreviations_vi)r   keys     r   _expand_abbreviations_vir   !   s3    
''!*C
++c4
 
&
&
(CS!!r   c                     t        |       } t        j                  t        t        |       } t        j                  dt
        z   dz   t        | t        j                        } | S )Nz\b)flags)normalize_speacial_symbol_viresub_url_rer   _abbreviations_combine_rer   
IGNORECASEtexts    r   normalize_abbreviations_vir)   '   sK    '-D66'?D1D66%33e;=UW[cecpcpqDKr   c                     t        j                  t        t        |       } t        j                  dd|       } t        j                  dd|       } t        j                  dd|       } t        j                  dd|       } | S )	N&u    và @u	    a còng z\+u    cộng z//u	    xuyệt )r"   r#   _percent_rer   r'   s    r   r!   r!   .   sb    66+148D66#w%D66#{D)D66$
D)D66$T*DKr   )r"   jsonpathlibr   compiler-   r$   r   updateloads__file__resolve	read_textjoinkeysr%   r   r   r   r)   r!   r   r   r   <module>r8      s    	  bjj&
"**B
C 
	    DJJtHdD&2DEMMOYYcjYkl !388,=,B,B,D#EEL /"r   