o
    rZh                     @   s<   d Z ddlT ddlT ddlmZ G dd deZdd ZdS )	a  
The Carnegie Mellon Pronouncing Dictionary [cmudict.0.6]
ftp://ftp.cs.cmu.edu/project/speech/dict/
Copyright 1998 Carnegie Mellon University

File Format: Each line consists of an uppercased word, a counter
(for alternative pronunciations), and a transcription.  Vowels are
marked for stress (1=primary, 2=secondary, 0=no stress).  E.g.:
NATURAL 1 N AE1 CH ER0 AH0 L

The dictionary contains 127069 entries.  Of these, 119400 words are assigned
a unique pronunciation, 6830 words have two pronunciations, and 839 words have
three or more pronunciations.  Many of these are fast-speech variants.

Phonemes: There are 39 phonemes, as shown below:

Phoneme Example Translation    Phoneme Example Translation
------- ------- -----------    ------- ------- -----------
AA      odd     AA D           AE      at      AE T
AH      hut     HH AH T        AO      ought   AO T
AW      cow     K AW           AY      hide    HH AY D
B       be      B IY           CH      cheese  CH IY Z
D       dee     D IY           DH      thee    DH IY
EH      Ed      EH D           ER      hurt    HH ER T
EY      ate     EY T           F       fee     F IY
G       green   G R IY N       HH      he      HH IY
IH      it      IH T           IY      eat     IY T
JH      gee     JH IY          K       key     K IY
L       lee     L IY           M       me      M IY
N       knee    N IY           NG      ping    P IH NG
OW      oat     OW T           OY      toy     T OY
P       pee     P IY           R       read    R IY D
S       sea     S IY           SH      she     SH IY
T       tea     T IY           TH      theta   TH EY T AH
UH      hood    HH UH D        UW      two     T UW
V       vee     V IY           W       we      W IY
Y       yield   Y IY L D       Z       zee     Z IY
ZH      seizure S IY ZH ER
    )*)Indexc                   @   s$   e Zd Zdd Zdd Zdd ZdS )CMUDictCorpusReaderc                 C   s   t dd | ddD S )zy
        :return: the cmudict lexicon as a list of entries
            containing (word, transcriptions) tuples.
        c                 S   s   g | ]\}}t |t|d qS ))encoding)ZStreamBackedCorpusViewread_cmudict_block).0Zfileidenc r	   I/var/www/auris/lib/python3.10/site-packages/nltk/corpus/reader/cmudict.py
<listcomp><   s    z/CMUDictCorpusReader.entries.<locals>.<listcomp>NT)concatZabspathsselfr	   r	   r
   entries6   s
   
zCMUDictCorpusReader.entriesc                 C   s   dd |   D S )zN
        :return: a list of all words defined in the cmudict lexicon.
        c                 S   s   g | ]\}}|  qS r	   )lower)r   word_r	   r	   r
   r   F   s    z-CMUDictCorpusReader.words.<locals>.<listcomp>)r   r   r	   r	   r
   wordsB   s   zCMUDictCorpusReader.wordsc                 C   s   t t|  S )z
        :return: the cmudict lexicon as a dictionary, whose keys are
            lowercase words and whose values are lists of pronunciations.
        )dictr   r   r   r	   r	   r
   r   H   s   zCMUDictCorpusReader.dictN)__name__
__module____qualname__r   r   r   r	   r	   r	   r
   r   5   s    r   c                 C   sZ   g }t |dk r+|  }|dkr|S | }||d  |dd  f t |dk s|S )Nd    r      )lenreadlinesplitappendr   )streamr   linepiecesr	   r	   r
   r   P   s   r   N)__doc__Znltk.corpus.reader.apiZnltk.corpus.reader.utilZ	nltk.utilr   ZCorpusReaderr   r   r	   r	   r	   r
   <module>   s   (