+
    ÖÇÜhó  ã                   ór   € ^ RI Ht ^ RIHtHtHt ^ RIHtHt ^ RI	H
t
Ht  ! R R]4      t ! R R]4      tR	# )
é    )ÚCorpusReader)ÚStreamBackedCorpusViewÚconcatÚread_alignedsent_block)ÚRegexpTokenizerÚWhitespaceTokenizer)ÚAlignedSentÚ	Alignmentc                   óp   a € ] tR t^t o RtR]! 4       ]! RRR7      ]R3R ltRR	 lt	RR
 lt
RR ltRtV tR# )ÚAlignedCorpusReaderz†
Reader for corpora of word-aligned sentences.  Tokens are assumed
to be separated by whitespace.  Sentences begin on separate lines.
Ú/Ú
T)ÚgapsÚlatin1c                ód   € \         P                  ! WW'4       W0n        W@n        WPn        W`n        R# )a`  
Construct a new Aligned Corpus reader for a set of documents
located at the given root directory.  Example usage:

    >>> root = '/...path to corpus.../'
    >>> reader = AlignedCorpusReader(root, '.*', '.txt') # doctest: +SKIP

:param root: The root directory for this corpus.
:param fileids: A list or regexp specifying the fileids in this corpus.
N)r   Ú__init__Ú_sepÚ_word_tokenizerÚ_sent_tokenizerÚ_alignedsent_block_reader)ÚselfÚrootÚfileidsÚsepÚword_tokenizerÚsent_tokenizerÚalignedsent_block_readerÚencodings   &&&&&&&&Ú</usr/lib/python3/dist-packages/nltk/corpus/reader/aligned.pyr   ÚAlignedCorpusReader.__init__   s+   € ô( 	×Ò˜d¨'Ô<ØŒ	Ø-ÔØ-ÔØ)AÖ&ó    Nc                óÆ   € \        V P                  VR4       UUu. uF4  w  r#\        VVRRV P                  V P                  V P
                  4      NK6  	  upp4      # u uppi )z^
:return: the given file(s) as a list of words
    and punctuation symbols.
:rtype: list(str)
TF©r   ÚabspathsÚAlignedSentCorpusViewr   r   r   ©r   r   ÚfileidÚencs   &&  r   ÚwordsÚAlignedCorpusReader.words2   sr   € ô ð &*§]¡]°7¸DÔ%Aôñ &B‘M�Vô &ØØØØØ×(Ñ(Ø×(Ñ(Ø×2Ñ2öñ &Bòó
ð 	
ùóó   ›:A
c                óÆ   € \        V P                  VR4       UUu. uF4  w  r#\        VVRRV P                  V P                  V P
                  4      NK6  	  upp4      # u uppi )zŠ
:return: the given file(s) as a list of
    sentences or utterances, each encoded as a list of word
    strings.
:rtype: list(list(str))
TFr#   r&   s   &&  r   ÚsentsÚAlignedCorpusReader.sentsG   sr   € ô ð &*§]¡]°7¸DÔ%Aôñ &B‘M�Vô &ØØØØØ×(Ñ(Ø×(Ñ(Ø×2Ñ2öñ &Bòó
ð 	
ùór+   c                óÆ   € \        V P                  VR4       UUu. uF4  w  r#\        VVRRV P                  V P                  V P
                  4      NK6  	  upp4      # u uppi )zX
:return: the given file(s) as a list of AlignedSent objects.
:rtype: list(AlignedSent)
Tr#   r&   s   &&  r   Úaligned_sentsÚ!AlignedCorpusReader.aligned_sents]   sr   € ô
 ð &*§]¡]°7¸DÔ%Aôñ &B‘M�Vô &ØØØØØ×(Ñ(Ø×(Ñ(Ø×2Ñ2öñ &Bòó
ð 	
ùór+   )r   r   r   r   )N)Ú__name__Ú
__module__Ú__qualname__Ú__firstlineno__Ú__doc__r   r   r   r   r)   r-   r0   Ú__static_attributes__Ú__classdictcell__©Ú__classdict__s   @r   r   r      s?   ø‡ € ñð Ù*Ó,Ù& t°$Ô7Ø!7ØôBô4
ô*
÷,
ò 
r!   r   c                   ó0   a € ] tR t^rt o RtR tR tRtV tR# )r%   z£
A specialized corpus view for aligned sentences.
``AlignedSentCorpusView`` objects are typically created by
``AlignedCorpusReader`` (not directly by nltk users).
c                ór   € W0n         W@n        WPn        W`n        Wpn        \
        P                  ! WVR 7       R# ))r   N)Ú_alignedÚ_group_by_sentr   r   r   r   r   )r   Úcorpus_filer   ÚalignedÚgroup_by_sentr   r   r   s   &&&&&&&&r   r   ÚAlignedSentCorpusView.__init__y   s1   € ð  ŒØ+ÔØ-ÔØ-ÔØ)AÔ&Ü×'Ò'¨ÀH×Mr!   c                ó´  € V P                  V4       UUu. uF@  pV P                  P                  V4       F  pV P                  P                  V4      NK   	  KB  	  pppV P                  '       d<   \
        P                  ! R P                  V^,          4      4      V^&   \        V!  .pV# V P                  '       d   V^ ,          .pV# V^ ,          pV# u uppi )Ú )
r   r   Útokenizer   r=   r
   Ú
fromstringÚjoinr	   r>   )r   ÚstreamÚalignedsent_strÚsent_strÚblocks   &&   r   Ú
read_blockÚ AlignedSentCorpusView.read_blockŠ   sØ   € ð $(×#AÑ#AÀ&Ô#Iô
á#I�Ø ×0Ñ0×9Ñ9¸/ÖJ�ð × Ñ ×)Ñ)¨(Ö3áJñ 4Ù#Ið 	ñ 
ð
 �=�=ˆ=Ü ×+Ò+Ø—‘˜˜q�Ó"óˆE�!‰Hô ! %Ñ(Ð)ˆEð ˆð × × Ð Ø˜1•X�JˆEð ˆð ˜!•HˆEàˆùó
s   •AC)r=   r   r>   r   r   N)	r2   r3   r4   r5   r6   r   rL   r7   r8   r9   s   @r   r%   r%   r   s   ø‡ € ñòN÷"ð r!   r%   N)Únltk.corpus.reader.apir   Únltk.corpus.reader.utilr   r   r   Únltk.tokenizer   r   Únltk.translater	   r
   r   r%   © r!   r   Ú<module>rS      s8   ðõ 0÷ñ ÷
 ?ß 1ô]
˜,ô ]
ô@(Ð2ö (r!   