Ë
    çÍ:j  ã                   óx   — d dl mZ d dlmZ d dlmZmZ ej                  Z eedddd¬«      Z	de	_
        d	„ Zd
„ Zy)é    )Úpartial)Úchain)Ú
everygramsÚpad_sequenceTz<s>z</s>)Úpad_leftÚleft_pad_symbolÚ	pad_rightÚright_pad_symbolz‘Pads both ends of a sentence to length specified by ngram order.

    Following convention <s> pads the start of sentence </s> pads its end.
    c                 óD   — t        t        t        || ¬«      «      | ¬«      S )zpHelper with some useful defaults.

    Applies pad_both_ends to sentence and follows it up with everygrams.
    ©Ún©Úmax_len)r   ÚlistÚpad_both_ends)ÚorderÚsentences     új/home/mcse/projects/srt_converter/srt-converter-venv/lib/python3.12/site-packages/nltk/lm/preprocessing.pyÚpadded_everygramsr      s   € ô
 ”dœ=¨°UÔ;Ó<ÀeÔLÐLó    c                 ój   ‡ ‡— t        t        ‰ ¬«      Šˆ ˆfd„|D «       t        t        ‰|«      «      fS )aú  Default preprocessing for a sequence of sentences.

    Creates two iterators:

    - sentences padded and turned into sequences of `nltk.util.everygrams`
    - sentences padded as above and chained together for a flat stream of words

    :param order: Largest ngram length produced by `everygrams`.
    :param text: Text to iterate over. Expected to be an iterable of sentences.
    :type text: Iterable[Iterable[str]]
    :return: iterator over text as ngrams, iterator over text as vocabulary data
    r   c              3   óV   •K  — | ]   }t        t         ‰|«      «      ‰¬ «      –— Œ" y­w)r   N)r   r   )Ú.0Úsentr   Ú
padding_fns     €€r   ú	<genexpr>z,padded_everygram_pipeline.<locals>.<genexpr>1   s%   øè ø€ ÒL¸tŒ”D™ DÓ)Ó*°E×	:Ð	:ÑLùs   ƒ&))r   r   ÚflattenÚmap)r   Útextr   s   ` @r   Úpadded_everygram_pipeliner    "   s2   ù€ ô œ¨%Ô0€JäLÀtÔLÜ”�J Ó%Ó&ðð r   N)Ú	functoolsr   Ú	itertoolsr   Ú	nltk.utilr   r   Úfrom_iterabler   r   Ú__doc__r   r    © r   r   ú<module>r'      sI   ðõ Ý ç .à
×
Ñ
€ÙØØØØØô€ð€Ô òMór   