3 dX%@s^ddlZddlZddlmZmZmZddlmZddlm Z GdddZ GdddeZ dS) N)IteratorListTuple) TokenizerI) align_tokensc@s4eZdZdZdddddddd gZd d gZd d gZdS)MacIntyreContractionszI 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)__name__ __module__ __qualname____doc__ CONTRACTIONS2 CONTRACTIONS3Z CONTRACTIONS4rr9/tmp/pip-build-v9q4h5k9/nltk/nltk/tokenize/destructive.pyrsrc @seZdZdZejdejdfejddfejddfejddfejd ejd fgZejd ejdfejd d fejdd fejddfejddfgZejdejdfejddfejddfejdejdfejddfejddfejddfejddfejdejdfg Z ejd dfZ ejd!d"fejd#d$fejd%d&fejd'd(fejd)d*fejd+d,fgZ ejd-d.fZ e ZeeejejZeeejejZd7eeeeed0d1d2Zeeeeefd3d4d5Zd6S)8NLTKWordTokenizeraE 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^\"z``z(``)z([ \(\[{<])(\"|\'{2})z\1 `` z$(?i)(\')(?!re|ve|ll|m|t|s|d|n)(\w)\bz\1 \2u ([»”’])z''z '' "z([^' ])('[sS]|'[mM]|'[dD]|') z\1 \2 z)([^' ])('ll|'LL|'re|'RE|'ve|'VE|n't|N'T) u&([^\.])(\.)([\]\)}>"\'»”’ ]*)\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)textconvert_parentheses return_strreturncCs|rtjdtddx|jD]\}}|j||}qWx|jD]\}}|j||}q>> 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.)category stacklevel z \1 \2 ) warningswarnDeprecationWarningSTARTING_QUOTESsub PUNCTUATIONPARENS_BRACKETSCONVERT_PARENTHESES DOUBLE_DASHES ENDING_QUOTESr r split)selfrrrregexpZ substitutionrrrtokenizexs0       zNLTKWordTokenizer.tokenize)rrc#s\|j|}d|ksd|krDddtjd|Dfdd|D}n|}t||EdHdS)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] rz''cSsg|] }|jqSr)group).0mrrr sz3NLTKWordTokenizer.span_tokenize..z ``|'{2}|\"cs"g|]}|dkrjdn|qS)r``''r)rr,r-)pop)r)tok)matchedrrr+sN)r'refinditerr)r%rZ raw_tokenstokensr)r0r span_tokenizes   zNLTKWordTokenizer.span_tokenizeN)FF)rr r r r1compileUrr#rr r!r"rZ _contractionslistmapr r strboolrr'rrintr4rrrrr%sJ                   Gr) r1rZtypingrrrZnltk.tokenize.apirZnltk.tokenize.utilrrrrrrr s