o
    rZh<'                     @   sf   d dl mZ d dlmZmZ dd Zdd Zdd ZG d	d
 d
Zdd Z	dd Z
dd Zdd ZdS )    )finditer)escapeunescapec                 c   s|    t |dkrtdd}	 z| ||}|dkr||fV  W n ty6   |t | kr3|t | fV  Y dS w |t | }q)a  
    Return the offsets of the tokens in *s*, as a sequence of ``(start, end)``
    tuples, by splitting the string at each occurrence of *sep*.

        >>> from nltk.tokenize.util import string_span_tokenize
        >>> s = '''Good muffins cost $3.88\nin New York.  Please buy me
        ... two of them.\n\nThanks.'''
        >>> list(string_span_tokenize(s, " ")) # doctest: +NORMALIZE_WHITESPACE
        [(0, 4), (5, 12), (13, 17), (18, 26), (27, 30), (31, 36), (37, 37),
        (38, 44), (45, 48), (49, 55), (56, 58), (59, 73)]

    :param s: the string to be tokenized
    :type s: str
    :param sep: the token separator
    :type sep: str
    :rtype: iter(tuple(int, int))
    r   z!Token delimiter must not be emptyTN)len
ValueErrorindex)ssepleftright r   A/var/www/auris/lib/python3.10/site-packages/nltk/tokenize/util.pystring_span_tokenize   s"   
r   c                 c   sJ    d}t || D ]}| \}}||kr||fV  |}q|t| fV  dS )a  
    Return the offsets of the tokens in *s*, as a sequence of ``(start, end)``
    tuples, by splitting the string at each successive match of *regexp*.

        >>> from nltk.tokenize.util import regexp_span_tokenize
        >>> s = '''Good muffins cost $3.88\nin New York.  Please buy me
        ... two of them.\n\nThanks.'''
        >>> list(regexp_span_tokenize(s, r'\s')) # doctest: +NORMALIZE_WHITESPACE
        [(0, 4), (5, 12), (13, 17), (18, 23), (24, 26), (27, 30), (31, 36),
        (38, 44), (45, 48), (49, 51), (52, 55), (56, 58), (59, 64), (66, 73)]

    :param s: the string to be tokenized
    :type s: str
    :param regexp: regular expression that matches token separators (must not be empty)
    :type regexp: str
    :rtype: iter(tuple(int, int))
    r   N)r   spanr   )r   regexpr
   mr   nextr   r   r   regexp_span_tokenize.   s   
r   c                 c   s.    d}| D ]\}}|| || fV  |}qdS )a  
    Return a sequence of relative spans, given a sequence of spans.

        >>> from nltk.tokenize import WhitespaceTokenizer
        >>> from nltk.tokenize.util import spans_to_relative
        >>> s = '''Good muffins cost $3.88\nin New York.  Please buy me
        ... two of them.\n\nThanks.'''
        >>> list(spans_to_relative(WhitespaceTokenizer().span_tokenize(s))) # doctest: +NORMALIZE_WHITESPACE
        [(0, 4), (1, 7), (1, 4), (1, 5), (1, 2), (1, 3), (1, 5), (2, 6),
        (1, 3), (1, 2), (1, 3), (1, 2), (1, 5), (2, 7)]

    :param spans: a sequence of (start, end) offsets of the tokens
    :type spans: iter(tuple(int, int))
    :rtype: iter(tuple(int, int))
    r   Nr   )spansprevr
   r   r   r   r   spans_to_relativeI   s   r   c                   @   sD   e 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gZd
S )CJKCharsa^  
    An object that enumerates the code points of the CJK characters as listed on
    https://en.wikipedia.org/wiki/Basic_Multilingual_Plane#Basic_Multilingual_Plane

    This is a Python port of the CJK code point enumerations of Moses tokenizer:
    https://github.com/moses-smt/mosesdecoder/blob/master/scripts/tokenizer/detokenizer.perl#L309
    i   i  i.  iϤ  i@  i  i   i  i   i  i0  iO  ie  i  i   i N)__name__
__module____qualname____doc__ZHangul_JamoZCJK_RadicalsZPhags_PaZHangul_SyllablesZCJK_Compatibility_IdeographsZCJK_Compatibility_FormsZKatakana_Hangul_HalfwidthZSupplementary_Ideographic_Planerangesr   r   r   r   r   _   s&    	r   c                    s   t  fdddD S )u  
    Python port of Moses' code to check for CJK character.

    >>> CJKChars().ranges
    [(4352, 4607), (11904, 42191), (43072, 43135), (44032, 55215), (63744, 64255), (65072, 65103), (65381, 65500), (131072, 196607)]
    >>> is_cjk(u'㏾')
    True
    >>> is_cjk(u'﹟')
    False

    :param character: The character that needs to be checked.
    :type character: char
    :return: bool
    c                    s,   g | ]\}}|t    ko|kn  qS r   )ord).0startend	characterr   r   
<listcomp>   s    zis_cjk.<locals>.<listcomp>)r   r   r   r   r   r   r   r   )anyr)   r   r)   r   is_cjk   s
   
r-   c                 C      t | dddddddS )a  
    This function transforms the input text into an "escaped" version suitable
    for well-formed XML formatting.

    Note that the default xml.sax.saxutils.escape() function don't escape
    some characters that Moses does so we have to manually add them to the
    entities dictionary.

        >>> input_str = ''')| & < > ' " ] ['''
        >>> expected_output =  ''')| &amp; &lt; &gt; ' " ] ['''
        >>> escape(input_str) == expected_output
        True
        >>> xml_escape(input_str)
        ')&#124; &amp; &lt; &gt; &apos; &quot; &#93; &#91;'

    :param text: The text that needs to be escaped.
    :type text: str
    :rtype: str
    &apos;&quot;&#124;&#91;&#93;)'"|[]entities)r   textr   r   r   
xml_escape   s   r=   c                 C   r.   )aj  
    This function transforms the "escaped" version suitable
    for well-formed XML formatting into humanly-readable string.

    Note that the default xml.sax.saxutils.unescape() function don't unescape
    some characters that Moses does so we have to manually add them to the
    entities dictionary.

        >>> from xml.sax.saxutils import unescape
        >>> s = ')&#124; &amp; &lt; &gt; &apos; &quot; &#93; &#91;'
        >>> expected = ''')| & < > ' " ] ['''
        >>> xml_unescape(s) == expected
        True

    :param text: The text that needs to be unescaped.
    :type text: str
    :rtype: str
    r4   r5   r6   r7   r8   )r/   r0   r1   r2   r3   r9   )r   r;   r   r   r   xml_unescape   s   r>   c                 C   sr   d}g }| D ]0}z| ||}W n ty( } ztd| d| d|d}~ww |t| }|||f q|S )a  
    This module attempt to find the offsets of the tokens in *s*, as a sequence
    of ``(start, end)`` tuples, given the tokens and also the source string.

        >>> from nltk.tokenize import TreebankWordTokenizer
        >>> from nltk.tokenize.util import align_tokens
        >>> s = str("The plane, bound for St Petersburg, crashed in Egypt's "
        ... "Sinai desert just 23 minutes after take-off from Sharm el-Sheikh "
        ... "on Saturday.")
        >>> tokens = TreebankWordTokenizer().tokenize(s)
        >>> expected = [(0, 3), (4, 9), (9, 10), (11, 16), (17, 20), (21, 23),
        ... (24, 34), (34, 35), (36, 43), (44, 46), (47, 52), (52, 54),
        ... (55, 60), (61, 67), (68, 72), (73, 75), (76, 83), (84, 89),
        ... (90, 98), (99, 103), (104, 109), (110, 119), (120, 122),
        ... (123, 131), (131, 132)]
        >>> output = list(align_tokens(tokens, s))
        >>> len(tokens) == len(expected) == len(output)  # Check that length of tokens and tuples are the same.
        True
        >>> expected == list(align_tokens(tokens, s))  # Check that the output is as expected.
        True
        >>> tokens == [s[start:end] for start, end in output]  # Check that the slices of the string corresponds to the tokens.
        True

    :param tokens: The list of strings that are the result of tokenization
    :type tokens: list(str)
    :param sentence: The original string
    :type sentence: str
    :rtype: list(tuple(int,int))
    r   zsubstring "z" not found in "r5   N)r   r   r   append)tokensZsentencepointoffsetstokenr'   er   r   r   align_tokens   s   rE   N)rer   Zxml.sax.saxutilsr   r   r   r   r   r   r-   r=   r>   rE   r   r   r   r   <module>   s   "B  