o
    ooi;2                     @   s  g d Z dZi dddgdddgdd	d
gdddgdddgdddgdddgdddgdddgdddgdddgdddgdddgd ddgd!d"d#gd$d"d#gZg d%Zg d&Zg d'Zd(d)gd*d+gd,d-gd.d/ggZd0Zd1Zd2Z	d1Z
d3Zd4Zd5Zd6Zd7Zd8Zd9d:gZd;d<gZd=d>gZd?d@gZdAdBgZg dCZg dDZg dEZg dFZg dGZg dHZg dIZdJdK ZdLdM ZdNdO ZdPdQ Z dRdS Z!dTdU Z"dVdW Z#dXdY Z$dZd[ Z%d\d] Z&d^d_ Z'd`da Z(dbdc Z)ddde Z*dfdg Z+dhdi Z,djdk Z-dldm Z.dndo Z/dpdq Z0drds Z1dtdu Z2dvdw Z3dxdy Z4dzd{ Z5d|d} Z6d~d Z7dd Z8dd Z9dd Z:dd Z;dd Z<dd Z=dd Z>dd Z?dd Z@dd ZAdd ZBdd ZCdd ZDdd ZEdd ZFdd ZGdS ))GLC_TASCRIPT_RANGESDRAVIDIAN_LANGUAGESIE_LANGUAGESDANDA_DELIM_LANGUAGESURDU_RANGES!COORDINATED_RANGE_START_INCLUSIVECOORDINATED_RANGE_END_INCLUSIVENUMERIC_OFFSET_STARTNUMERIC_OFFSET_ENDHALANTA_OFFSET
AUM_OFFSETNUKTA_OFFSET
RUPEE_SIGNDANDADOUBLE_DANDAVELAR_RANGEPALATAL_RANGERETROFLEX_RANGEDENTAL_RANGELABIAL_RANGEVOICED_LISTUNVOICED_LISTASPIRATED_LISTUNASPIRATED_LIST
NASAL_LISTFRICATIVE_LISTAPPROXIMANT_LISTis_danda_delim
get_offsetoffset_to_charin_coordinated_rangeis_indiclang_charis_vowelis_vowel_sign
is_halantais_nuktais_aumis_consonantis_velar
is_palatalis_retroflex	is_dental	is_labial	is_voicedis_unvoicedis_aspiratedis_unaspiratedis_nasalis_fricativeis_approximant	is_numberis_vowel_offsetis_vowel_sign_offsetis_halanta_offsetis_nukta_offsetis_aum_offsetis_consonant_offsetis_velar_offsetis_palatal_offsetis_retroflex_offsetis_dental_offsetis_labial_offsetis_voiced_offsetis_unvoiced_offsetis_aspirated_offsetis_unaspirated_offsetis_nasal_offsetis_fricative_offsetis_approximant_offsetis_number_offsettapai 
  i
  gui
  i
  ori   i  i  i  tei   i  kni  i  mli   i  sii  i  hii 	  i	  mrkKsanesdbni	  i	  as)rH   rL   rM   rN   )rP   rQ   rR   rS   rT   rU   rV   rW   rI   rJ   rK   rO   )rW   rV   rP   rT   rK   rI   rS   rU   i   i  iP  i  iP  i  ip  i      o   f   M   P   <   i   id	  ie	                 #   $   )   *   .   )
            !   "   &   '   ,   -   )
r^      r`      rb       rd   %   rf   +   )
rr   ri   rs   rk   rt   rm   ru   ro   rv   rq   )
r^   rh   r`   rj   rb   rl   rd   rn   rf   rp   )r_   ra   rc   (   re   rq   )6   7   8   )/   0   1   2   3   4   5   c                 C      | t v S )zU
    Returns True if danda/double danda is a possible delimiter for the language
    )r   )lang r   O/home/ubuntu/.local/lib/python3.10/site-packages/whisper_normalizer/langinfo.pyr   z      r   c                 C   s   t | t| d  S 4
    Applicable to Brahmi derived Indic scripts
    rX   )ordr   cr   r   r   r   r         r   c                 C   s   t | t| d  S r   )chrr   r   r   r   r   r      r   r   c                 C   s   | t ko| tkS )r   )r   r   c_offsetr   r   r   r       s   r    c                 C   s2   t | |}|dkr|dkpt| tkpt| tkS )r   rX      )r   r   r   r   r   r   or   r   r   r!      s   
(r!   c                 C      t | |}|dko|dkS )z"
    Is the character a vowel
          r   r   r   r   r   r"   '     
r"   c                 C   r   )1
    Is the character a vowel sign (maatraa)
    >   L   r   r   r   r   r   r#   /  r   r#   c                 C      t | |}|tkS z0
    Is the character the halanta character
    )r   r   r   r   r   r   r$   7     
r$   c                 C   r   r   )r   r   r   r   r   r   r%   ?  r   r%   c                 C   r   )r   )r   r   r   r   r   r   r&   G  r   r&   c                 C   r   )z&
    Is the character a consonant
    r^   9   r   r   r   r   r   r'   O  r   r'   c                 C   "   t | |}|td ko|td kS )z"
    Is the character a velar
    rX      )r   r   r   r   r   r   r(   W     
r(   c                 C   r   )z$
    Is the character a palatal
    rX   r   )r   r   r   r   r   r   r)   _  r   r)   c                 C   r   )z&
    Is the character a retroflex
    rX   r   )r   r   r   r   r   r   r*   g  r   r*   c                 C   r   )z#
    Is the character a dental
    rX   r   )r   r   r   r   r   r   r+   o  r   r+   c                 C   r   )z#
    Is the character a labial
    rX   r   )r   r   r   r   r   r   r,   w  r   r,   c                 C      t | |}|tv S )z-
    Is the character a voiced consonant
    )r   r   r   r   r   r   r-     r   r-   c                 C   r   )z/
    Is the character a unvoiced consonant
    )r   r   r   r   r   r   r.     r   r.   c                 C   r   )z0
    Is the character a aspirated consonant
    )r   r   r   r   r   r   r/     r   r/   c                 C   r   )z2
    Is the character a unaspirated consonant
    )r   r   r   r   r   r   r0     r   r0   c                 C   r   )z,
    Is the character a nasal consonant
    )r   r   r   r   r   r   r1     r   r1   c                 C   r   )z0
    Is the character a fricative consonant
    )r   r   r   r   r   r   r2     r   r2   c                 C   r   )z3
    Is the character an approximant consonant
    )r   r   r   r   r   r   r3     r   r3   c                 C   r   )z#
    Is the character a number
    rZ   rY   r   r   r   r   r   r4     r   r4   c                 C      | dko| dkS )z
    Is the offset a vowel
    r   r   r   r   r   r   r   r5        r5   c                 C   r   ).
    Is the offset a vowel sign (maatraa)
    r   r   r   r   r   r   r   r6     r   r6   c                 C      | t kS z*
    Is the offset the halanta offset
    )r   r   r   r   r   r7     r   r7   c                 C   r   r   )r   r   r   r   r   r8     r   r8   c                 C   r   )r   )r   r   r   r   r   r9     r   r9   c                 C   r   )z#
    Is the offset a consonant
    r^   r   r   r   r   r   r   r:     r   r:   c                 C      | t d ko| t d kS )z
    Is the offset a velar
    rX   r   )r   r   r   r   r   r;        r;   c                 C   r   )z!
    Is the offset a palatal
    rX   r   )r   r   r   r   r   r<     r   r<   c                 C   r   )z#
    Is the offset a retroflex
    rX   r   )r   r   r   r   r   r=     r   r=   c                 C   r   )z 
    Is the offset a dental
    rX   r   )r   r   r   r   r   r>     r   r>   c                 C   r   )z 
    Is the offset a labial
    rX   r   )r   r   r   r   r   r?     r   r?   c                 C   r   )z*
    Is the offset a voiced consonant
    )r   r   r   r   r   r@     r   r@   c                 C   r   )z,
    Is the offset a unvoiced consonant
    )r   r   r   r   r   rA     r   rA   c                 C   r   )z-
    Is the offset a aspirated consonant
    )r   r   r   r   r   rB     r   rB   c                 C   r   )z/
    Is the offset a unaspirated consonant
    )r   r   r   r   r   rC   $  r   rC   c                 C   r   )z)
    Is the offset a nasal consonant
    )r   r   r   r   r   rD   +  r   rD   c                 C   r   )z-
    Is the offset a fricative consonant
    )r   r   r   r   r   rE   2  r   rE   c                 C   r   )z0
    Is the offset an approximant consonant
    )r   r   r   r   r   rF   9  r   rF   c                 C   r   )z 
    Is the offset a number
    rZ   rY   r   r   r   r   r   rG   @  r   rG   N)H__all__r   r   r   r   r   r   r   r   r	   r
   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r   r    r!   r"   r#   r$   r%   r&   r'   r(   r)   r*   r+   r,   r-   r.   r/   r0   r1   r2   r3   r4   r5   r6   r7   r8   r9   r:   r;   r<   r=   r>   r?   r@   rA   rB   rC   rD   rE   rF   rG   r   r   r   r   <module>   s   	

 