a ±KbX%ã@s^ddlZddlZddlmZmZmZddlmZddlm Z Gdd„dƒZ Gdd„deƒZ dS) éN)ÚIteratorÚListÚTuple)Ú TokenizerI)Ú align_tokensc@s(eZdZdZgd¢ZddgZddgZdS)ÚMacIntyreContractionszI List of contractions adapted from Robert MacIntyre's tokenizer. )z(?i)\b(can)(?#X)(not)\bz(?i)\b(d)(?#X)('ye)\bz(?i)\b(gim)(?#X)(me)\bz(?i)\b(gon)(?#X)(na)\bz(?i)\b(got)(?#X)(ta)\bz(?i)\b(lem)(?#X)(me)\bz(?i)\b(more)(?#X)('n)\bz(?i)\b(wan)(?#X)(na)(?=\s)z(?i) ('t)(?#X)(is)\bz(?i) ('t)(?#X)(was)\bz(?i)\b(whad)(dd)(ya)\bz(?i)\b(wha)(t)(cha)\bN)Ú__name__Ú __module__Ú __qualname__Ú__doc__Ú CONTRACTIONS2Ú CONTRACTIONS3Z CONTRACTIONS4©rrú8lib/python3.9/site-packages/nltk/tokenize/destructive.pyrs rc @sàeZdZdZe dej¡dfe d¡dfe d¡dfe d¡dfe d ej¡d fgZe d ej¡dfe d ¡d fe d¡d fe d¡dfe d¡dfgZe dej¡dfe d¡dfe d¡dfe dej¡dfe d¡dfe d¡dfe d¡dfe d¡dfe dej¡dfg Z e d ¡dfZ e d!¡d"fe d#¡d$fe d%¡d&fe d'¡d(fe d)¡d*fe d+¡d,fgZ e d-¡d.fZ e ƒZeeejejƒƒZeeejejƒƒZd7eeeeed0œd1d2„Zeeeeefd3œd4d5„Zd6S)8ÚNLTKWordTokenizeraE The NLTK tokenizer that has improved upon the TreebankWordTokenizer. This is the method that is invoked by ``word_tokenize()``. It assumes that the text has already been segmented into sentences, e.g. using ``sent_tokenize()``. The tokenizer is "destructive" such that the regexes applied will munge the input string to a state beyond re-construction. It is possible to apply `TreebankWordDetokenizer.detokenize` to the tokenized outputs of `NLTKDestructiveWordTokenizer.tokenize` but there's no guarantees to revert to the original string. u([«“‘„]|[`]+)z \1 z^\"ú``z(``)z([ \(\[{<])(\"|\'{2})z\1 `` z$(?i)(\')(?!re|ve|ll|m|t|s|d|n)(\w)\bz\1 \2u ([»â€â€™])ú''z '' ú"z([^' ])('[sS]|'[mM]|'[dD]|') z\1 \2 z)([^' ])('ll|'LL|'re|'RE|'ve|'VE|n't|N'T) u&([^\.])(\.)([\]\)}>"\'»â€â€™ ]*)\s*$z \1 \2 \3 z ([:,])([^\d])z \1 \2z([:,])$z\.{2,}z \g<0> z[;@#$%&]z([^\.])(\.)([\]\)}>"\']*)\s*$z\1 \2\3 z[?!]z([^'])' z\1 ' z[*]z[\]\[\(\)\{\}\<\>]z\(z-LRB-z\)z-RRB-z\[z-LSB-z\]z-RSB-z\{z-LCB-z\}z-RCB-z--z -- F)ÚtextÚconvert_parenthesesÚ return_strÚreturncCsø|rtjdtdd|jD]\}}| ||¡}q|jD]\}}| ||¡}q6|j\}}| ||¡}|r‚|jD]\}}| ||¡}ql|j\}}| ||¡}d|d}|j D]\}}| ||¡}qª|j D]}| d|¡}qÆ|j D]}| d|¡}qÞ|  ¡S)abReturn a tokenized copy of `text`. >>> from nltk.tokenize import NLTKWordTokenizer >>> s = '''Good muffins cost $3.88 (roughly 3,36 euros)\nin New York. Please buy me\ntwo of them.\nThanks.''' >>> NLTKWordTokenizer().tokenize(s) ['Good', 'muffins', 'cost', '$', '3.88', '(', 'roughly', '3,36', 'euros', ')', 'in', 'New', 'York.', 'Please', 'buy', 'me', 'two', 'of', 'them.', 'Thanks', '.'] >>> NLTKWordTokenizer().tokenize(s, convert_parentheses=True) ['Good', 'muffins', 'cost', '$', '3.88', '-LRB-', 'roughly', '3,36', 'euros', '-RRB-', 'in', 'New', 'York.', 'Please', 'buy', 'me', 'two', 'of', 'them.', 'Thanks', '.'] >>> NLTKWordTokenizer().tokenize(s, return_str=True) ' Good muffins cost $ 3.88 ( roughly 3,36 euros ) \nin New York. Please buy me\ntwo of them.\nThanks . ' :param text: A string with a sentence or sentences. :type text: str :param convert_parentheses: if True, replace parentheses to PTB symbols, e.g. `(` to `-LRB-`. Defaults to False. :type convert_parentheses: bool, optional :param return_str: If True, return tokens as space-separated string, defaults to False. :type return_str: bool, optional :return: List of tokens from `text`. :rtype: List[str] zHParameter 'return_str' has been deprecated and should no longer be used.é)ÚcategoryÚ stacklevelú z \1 \2 ) ÚwarningsÚwarnÚDeprecationWarningÚSTARTING_QUOTESÚsubÚ PUNCTUATIONÚPARENS_BRACKETSÚCONVERT_PARENTHESESÚ DOUBLE_DASHESÚ ENDING_QUOTESr r Úsplit)ÚselfrrrZregexpZ substitutionrrrÚtokenizexs2ü       zNLTKWordTokenizer.tokenize)rrc#s\| |¡}d|vsd|vrDdd„t d|¡Dƒ‰‡fdd„|Dƒ}n|}t||ƒEdHdS)a} Returns the spans of the tokens in ``text``. Uses the post-hoc nltk.tokens.align_tokens to return the offset spans. >>> from nltk.tokenize import NLTKWordTokenizer >>> s = '''Good muffins cost $3.88\nin New (York). Please (buy) me\ntwo of them.\n(Thanks).''' >>> expected = [(0, 4), (5, 12), (13, 17), (18, 19), (19, 23), ... (24, 26), (27, 30), (31, 32), (32, 36), (36, 37), (37, 38), ... (40, 46), (47, 48), (48, 51), (51, 52), (53, 55), (56, 59), ... (60, 62), (63, 68), (69, 70), (70, 76), (76, 77), (77, 78)] >>> list(NLTKWordTokenizer().span_tokenize(s)) == expected True >>> expected = ['Good', 'muffins', 'cost', '$', '3.88', 'in', ... 'New', '(', 'York', ')', '.', 'Please', '(', 'buy', ')', ... 'me', 'two', 'of', 'them.', '(', 'Thanks', ')', '.'] >>> [s[start:end] for start, end in NLTKWordTokenizer().span_tokenize(s)] == expected True :param text: A string with a sentence or sentences. :type text: str :yield: Tuple[int, int] rrcSsg|] }| ¡‘qSr)Úgroup)Ú.0ÚmrrrÚ àóz3NLTKWordTokenizer.span_tokenize..z ``|'{2}|\"cs"g|]}|dvrˆ d¡n|‘qS))rrrr)Úpop)r*Útok©Zmatchedrrr,ãsÿN)r(ÚreÚfinditerr)r'rZ raw_tokensÚtokensrr0rÚ span_tokenizeÁs  þzNLTKWordTokenizer.span_tokenizeN)FF)rr r r r1ÚcompileÚUrr%r!r"r#r$rZ _contractionsÚlistÚmapr r ÚstrÚboolrr(rrÚintr4rrrrr%s^   û     û   þ þ   þñ      ú ÿþ Ir) r1rÚtypingrrrZnltk.tokenize.apirZnltk.tokenize.utilrrrrrrrÚ s