3 d(@sfddlmZddlmZmZddZddZddZGd d d Zd d Z d dZ ddZ ddZ dS))finditer)escapeunescapec cst|dkrtdd}xdy"|j||}|dkr:||fVWn0tk rl|t|krf|t|fVPYnX|t|}qWdS)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, " ")) [(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)) rz!Token delimiter must not be emptyN)len ValueErrorindex)ssepleftrightr 2/tmp/pip-build-v9q4h5k9/nltk/nltk/tokenize/util.pystring_span_tokenize s   rccsLd}x4t||D]&}|j\}}||kr2||fV|}qW|t|fVdS)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')) [(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)) rN)rspanr)rregexpr mr nextr r r regexp_span_tokenize.s  rccs0d}x&|D]\}}||||fV|}q WdS)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 $3.88\nin New York. Please buy me ... two of them.\n\nThanks.''' >>> list(spans_to_relative(WhitespaceTokenizer().span_tokenize(s))) [(0, 4), (1, 7), (1, 4), (1, 5), (1, 2), (1, 3), (1, 5), (2, 6), (1, 3), (1, 2), (1, 3), (1, 2), (1, 5), (2, 7)] :param spans: a sequence of (start, end) offsets of the tokens :type spans: iter(tuple(int, int)) :rtype: iter(tuple(int, int)) rNr )Zspansprevr r r r r spans_to_relativeIsrc@sDeZdZdZdZdZdZdZdZdZ dZ dZ eeeeee e e gZ dS)CJKCharsa^ An object that enumerates the code points of the CJK characters as listed on https://en.wikipedia.org/wiki/Basic_Multilingual_Plane#Basic_Multilingual_Plane This is a Python port of the CJK code point enumerations of Moses tokenizer: https://github.com/moses-smt/mosesdecoder/blob/master/scripts/tokenizer/detokenizer.perl#L309 .Ϥ@0OeN)rr)rr)rr)rr)rr )r!r")r#r$)r%r&) __name__ __module__ __qualname____doc__Z Hangul_JamoZ CJK_RadicalsZPhags_PaZHangul_SyllablesZCJK_Compatibility_IdeographsZCJK_Compatibility_FormsZKatakana_Hangul_HalfwidthZSupplementary_Ideographic_Planerangesr r r r r_s$rc stfdddDS)u Python port of Moses' code to check for CJK character. >>> CJKChars().ranges [(4352, 4607), (11904, 42191), (43072, 43135), (44032, 55215), (63744, 64255), (65072, 65103), (65381, 65500), (131072, 196607)] >>> is_cjk(u'㏾') True >>> is_cjk(u'﹟') False :param character: The character that needs to be checked. :type character: char :return: bool cs,g|]$\}}|tko"|knqSr )ord).0startend) characterr r szis_cjk...Ϥ@0Oer2r3r4r5r6r7r8r9r:r;r<r=r>r?r@rA)rBrCrDrErFrGrHrI)any)r0r )r0r is_cjks rKcCst|dddddddS)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 = ''')| & < > ' " ] [''' >>> escape(input_str) == expected_output True >>> xml_escape(input_str) ')| & < > ' " ] [' :param text: The text that needs to be escaped. :type text: str :rtype: str z'z"z|z[z])'"|[])entities)r)textr r r xml_escapesrScCst|dddddddS)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 = ')| & < > ' " ] [' >>> expected = ''')| & < > ' " ] [''' >>> xml_unescape(s) == expected True :param text: The text that needs to be unescaped. :type text: str :rtype: str rLrMrNrOrP)z'z"z|z[z])rQ)r)rRr r r xml_unescapesrTcCsd}g}xr|D]j}y|j||}Wn:tk r\}ztd|d|d|WYdd}~XnX|t|}|j||fqW|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)) rz substring "z" not found in "rMN)rrrappend)tokensZsentenceZpointoffsetstokenr.er r r align_tokenss * rZN) rerxml.sax.saxutilsrrrrrrrKrSrTrZr r r r s "B