o
    ±ƒðjò7  ã                   @  s  d dl mZ d dlZd dlZd dlmZ d dlm	Z	m
Z
 dZdZdZdZd	Zd
ZdZdZdZdZdZdZdZdZdZdZdZdZdZeeeeeeeeeeeehZdZdZ dZ!dZ"dZ#dZ$dZ%dZ&d Z'd!Z(d"Z)d#Z*d$Z+d%Z,d&Z-d'Z.d(Z/d)Z0d*Z1d+Z2d,Z3d-Z4d.Z5d/Z6d0Z7d1Z8d2Z9e*e)e-e,e/e.e3e2e5e4iZ:e e)e2e9e"e!hZ;e!e d3e%e d4e4e d5iZ<eG d6d7„ d7ƒƒZ=dpd;d<„Z>dpd=d>„Z?dqdAdB„Z@drdDdE„ZAdsdLdM„ZBdtdOdP„ZCdudQdR„ZDdvdVdW„ZEdwdYdZ„ZFdxd[d\„ZGdyd^d_„ZHeG d`da„ daƒƒZIdzdcdd„ZJd{dfdg„ZKd|didj„ZLd}dkdl„ZMd~dndo„ZNdS )é    )ÚannotationsN)Ú	dataclass)ÚListÚTuplez[\u0591-\u05AF]z[\u0591-\u05C7]u   Ö¼u   ×�u   ×‚u   ×³u   ×´u   Ö°u   Ö±u   Ö²u   Ö³u   Ö´u   Öµu   Ö¶u   Ö·u   Ö¸u   Ö¹u   Ö»u   ×‡u   ×�u   ×‘u   ×’u   ×“u   ×”u   ×•u   ×–u   ×—u   ×˜u   ×™u   ×›u   ×šu   ×œu   ×žu   ×�u   × u   ×Ÿu   ×¡u   ×¢u   ×¤u   ×£u   ×¦u   ×¥u   ×§u   ×¨u   ×©u   ×ªu   dÍ¡Ê’u   Ê’u   tÍ¡Êƒc                   @  s2   e Zd ZU ded< ded< ddd	„Zddd„ZdS )ÚGlyphÚstrÚbaseú	List[str]ÚmarksÚmarkÚreturnÚboolc                 C  s
   || j v S ©N©r
   )Úselfr   © r   ú™/tmp/claude-1000/-var-www-html-academy/3f42efd1-c2b7-4d08-9b05-30d86bb35479/scratchpad/piper/venv/lib/python3.10/site-packages/piper/hebrew/hebrew_ipa.pyÚhasj   s   
z	Glyph.hasúset[str]c                   s   t ‡ fdd„| jD ƒƒS )Nc                 3  s   � | ]}|ˆ v V  qd S r   r   ©Ú.0Úmr   r   r   Ú	<genexpr>n   ó   € zGlyph.any.<locals>.<genexpr>)Úanyr
   )r   r
   r   r   r   r   m   s   z	Glyph.anyN)r   r   r   r   )r
   r   r   r   )Ú__name__Ú
__module__Ú__qualname__Ú__annotations__r   r   r   r   r   r   r   e   s
   
 
r   Úsr   r   c                 C  s   t  d| ¡S )NÚNFC)Ú_udÚ	normalize©r   r   r   r   Ú_nfcq   s   r$   c                 C  s   t  td| ¡S )NÚ )Ú_reÚsubÚTAAMIMr#   r   r   r   Ú_strip_taamimu   s   r)   ÚwordúList[Glyph]c                 C  sN   t t| ƒƒ} g }| D ]}t |¡r|r|d j |¡ q
| t|g ƒ¡ q
|S )zFSplit a Hebrew word into base letters + combining marks (niqqud/dots).éÿÿÿÿ)r$   r)   r!   Ú	combiningr
   Úappendr   )r*   ÚglyphsÚchr   r   r   Ú_iter_glyphsy   s   
€r1   r/   c                 C  sÄ   g }d}|t | ƒk r`| | }|d t | ƒk rQ| |d  jtkrQ|j| |d  j tt tt tt fv rQt|j| |d  j  }| td|› d�g ƒ¡ |d7 }q| |¡ |d7 }|t | ƒk s
|S )uJ   Collapse ×’×³ ×–×³ ×¦×³ into placeholder IPA tokens via special base tags.r   é   z<IPA:ú>é   )	Úlenr   ÚGERESHÚGIMELÚZAYINÚTSADIÚGERESH_DIGRAPHSr.   r   )r/   ÚoutÚiÚgÚipar   r   r   Ú_apply_geresh_digraphs†   s"   ÿ
ór?   r   r
   r	   Úis_finalr   Únext_is_vowelc                 C  s\  t  | | ¡}|ttfv rdS |tkr|rt|vrdS dS |tkr"dS |tkr(dS |tkr:t	|v r2dS t
|v r8dS dS |tkrFt|v rDdS dS |tkrRt|v rPd	S d
S |tkr^t|v r\dS dS |tkrddS |tkrjdS |tkrpd
S |tkrvdS |tkr|dS |tkr‚dS |tkrˆdS |tkrŽdS |tkr”dS |tkršd	S |tkr dS |tkr¦dS |tkr¬dS dS )zKReturn IPA (possibly empty) for a consonant letter considering dots/dagesh.ú<GLT>r%   ÚhÚjÚvu   Êƒr   ÚbÚku   Ï‡ÚpÚfr=   ÚdÚtÚlr   Únu   tÍ¡su   Ê�Úz)ÚFINAL_FORM_BASEÚgetÚALEFÚAYINÚHEÚDAGESHÚYODÚVAVÚSHINÚSHIN_DOTÚSIN_DOTÚBETÚKAFÚPEr7   ÚDALETÚHETÚTETÚLAMEDÚMEMÚNUNÚSAMEKHr9   ÚQOFÚRESHÚTAVr8   )r   r
   r@   rA   rF   r   r   r   Ú_map_consonantœ   sh   rg   r   c                 C  s   | t v S r   )ÚVOWEL_MARKS)r   r   r   r   Ú_is_vowel_markç   s   ri   c                 C  s   t dd„ | D ƒƒS )Nc                 s  s   � | ]}t |ƒV  qd S r   )ri   r   r   r   r   r   ì   r   z#_has_vowel_marks.<locals>.<genexpr>)r   r   r   r   r   Ú_has_vowel_marksë   s   rj   ÚcurrÚnxtúGlyph | Nonec                 C  s(   |   t¡o|d uo|jtkot|jƒ S r   )r   ÚHIRIQr   rU   rj   r
   )rk   rl   r   r   r   Ú_is_hiriq_yodï   s   
ÿþ
üro   r=   c                 C  s    | j tko|  t¡o|  t¡ S r   )r   rV   r   ÚHOLAMrT   ©r=   r   r   r   Ú_is_holam_maleø   s    rr   c                 C  s*   | j tko|  t¡otdd„ | jD ƒƒ S )Nc                 s  s0   � | ]}|t ttttttttt	t
thv V  qd S r   )rp   rn   ÚTSEREÚSEGOLÚPATAHÚQAMATSÚQUBUTZÚQAMATS_QATANÚSHEVAÚHATAF_SEGOLÚHATAF_PATAHÚHATAF_QAMATSr   r   r   r   r     s&   € ñôÿ
ÿz_is_shuruk.<locals>.<genexpr>)r   rV   r   rT   r   r
   )rk   r   r   r   Ú
_is_shuruký   s   
ÿðýr}   úTuple[str, bool]c                 C  sž   |   t¡rdS |   t¡rdS |   t¡rdS |   t¡rdS |   t¡r#dS |   t¡r*dS |   t¡r1dS |   t¡r8dS |   t	¡r?dS |   t
¡rFdS |   t¡rMdS dS )zQReturn (ipa, is_vocalic) from marks on current glyph (not including mater cases).)ÚoT)ÚuT)r<   T)ÚeT)ÚaT)õ   É™F)r%   F)r   rx   rw   rn   rs   rt   ru   rv   r{   rz   r|   ry   rq   r   r   r   Ú_map_basic_vowel  s.   










r„   c                   @  s2   e Zd ZU ded< ded< ded< dZded< d	S )
ÚSegmentr	   Úonsetr   ÚnucleusÚcodaFr   ÚdageshN)r   r   r   r   r‰   r   r   r   r   r…   3  s
   
 r…   úList[Segment]c              	   C  sð  t t| ƒƒ}g }g }d}|t|ƒk rè|| }|d t|ƒk r$||d  nd}|t|ƒd k}t|ƒrF|s6g }| t|dg ƒ¡ g }|d7 }qt||ƒrpt|j|j	ddd�}|r`|dkr`| |¡ | t|d	g ƒ¡ g }|d
7 }qt
|ƒr„| t|dg ƒ¡ g }|d7 }qt|j|j	|dd�}t|ƒ\}	}
|
r­|r¡|dkr¡| |¡ | t||	g ƒ¡ g }n1| t¡rÍ|r½|dkr½| |¡ | t|dg | t¡ƒ¡ g }n|dkr×| d¡ n|rÞ| |¡ |d7 }|t|ƒk s|rö|rö|d j |¡ g }|S )zRParse a diacritized word into syllable-like segments with rough nucleus detection.r   r2   Nr€   FT)r@   rA   rB   r<   r4   r   rƒ   õ   Ê”r,   )r?   r1   r5   r}   r.   r…   ro   rg   r   r
   rr   r„   r   ry   rT   rˆ   Úextend)r*   r/   Úsegsr†   r<   r=   rl   r@   ÚconsrE   Úis_vocr   r   r   Ú_word_to_segments;  sd    





Æ=r�   r�   c                 C  sÔ   d}t | ƒD ]<\}}|jdkrd}q|jo|dk}|dkp |p |}|r)d|_d}q|d dkr:| |d  j |j¡ g |_d|_d}qg }| D ]}|jdkr`|rZ|d j |j¡ n| |¡ qG| |¡ qG|} | S )	uŸ  Resolve each shva ('É™' nucleus) to na (pronounced /e/) or nach (silent).

    Modern Israeli Hebrew: a shva is *na* (realized as /e/, not schwa) only in a
    few positions; otherwise it is *nach* (silent, closing the previous syllable).
    We treat as na:
      - word-initial shva (prefixes be-/le-/ve-/she-/ke-, etc.),
      - a shva under a consonant with dagesh chazak (gemination),
      - the second of two consecutive shvas (the first is nach).
    Everything else is nach. Defaulting to nach matches how the marks are actually
    spoken (careful modern reading) and avoids the spurious schwas that made words
    like nir'eit / le'eineinu unintelligible.
    Frƒ   r   r�   r2   r%   Tr,   )Ú	enumerater‡   r‰   rˆ   rŒ   r†   r.   )r�   Úprev_silenced_shvar<   r   Údagesh_chazakÚnaÚmergedr   r   r   Ú_resolve_sheva_and_qamats…  s2   


r–   ú!Tuple[str, List[Tuple[int, int]]]c           
      C  sÞ   g }| D ]}d  |j¡|j d  |j¡ }| |¡ qt|ƒd }t|ƒdkr.| d jr.d}g }t| ƒD ]1\}}d  |j¡|j d  |j¡ }||kr`d  |j¡}d  |j¡}|d |j | }| |¡ q4d  |¡}	|	g fS )z­Join segments to IPA string and compute stress placement.
    Returns (ipa, syllable_spans) where spans are offsets (start,end) in the string for each syllable nucleus.
    r%   r2   r4   r,   r   u   Ëˆ)Újoinr†   r‡   rˆ   r.   r5   r‘   )
r�   Úsylsr   ÚsylÚstress_indexÚpiecesÚidxÚbeforeÚafterr>   r   r   r   Ú_syllabify_to_ipa¹  s"   
r    c                 C  sV   t | ƒ}t|ƒ}t|ƒ\}}t dd|¡}t dd|¡}t dd|¡}| dd¡}|S )z6Convert a single fully-diacritized Hebrew word to IPA.u   Ê”(?=Ëˆ?[aeiouÉ™])r‹   u   (?<=^)Ê”u   Ê”(?=[^aeiouÉ™Ëˆ]|$)r%   u   Í¡)r�   r–   r    r&   r'   Úreplace)r*   r�   r>   Ú_r   r   r   Úhebrew_word_to_ipa×  s   r£   Útextc                 C  s:   t t| ƒƒ} |  ¡ }g }|D ]	}| t|ƒ¡ qd |¡S )z2Convert a sentence (space-separated words) to IPA.ú )r$   r)   Úsplitr.   r£   r˜   )r¤   Úwordsr;   Úwr   r   r   Úhebrew_to_ipaç  s   
r©   )r   r   r   r   )r*   r   r   r+   )r/   r+   r   r+   )
r   r   r
   r	   r@   r   rA   r   r   r   )r   r   r   r   )r
   r	   r   r   )rk   r   rl   rm   r   r   )r=   r   r   r   )rk   r   r   r   )r=   r   r   r~   )r*   r   r   rŠ   )r�   rŠ   r   rŠ   )r�   rŠ   r   r—   )r*   r   r   r   )r¤   r   r   r   )OÚ
__future__r   Úrer&   Úunicodedatar!   Údataclassesr   Útypingr   r   r(   Ú
NIQQUD_ALLrT   rX   rY   r6   Ú	GERSHAYIMry   rz   r{   r|   rn   rs   rt   ru   rv   rp   rw   rx   rh   rQ   rZ   r7   r]   rS   rV   r8   r^   r_   rU   r[   Ú	KAF_FINALr`   ra   Ú	MEM_FINALrb   Ú	NUN_FINALrc   rR   r\   ÚPE_FINALr9   ÚTSADI_FINALrd   re   rW   rf   rO   Ú
BEGADKEFATr:   r   r$   r)   r1   r?   rg   ri   rj   ro   rr   r}   r„   r…   r�   r–   r    r£   r©   r   r   r   r   Ú<module>   sÊ    ôû	úý





K


	



J
4
