o rZŽh‹?ã@spdZddlZddlZddlmZmZmZddlmZddl m Z ddl m Z Gdd„deƒZ Gd d „d eƒZdS) a  Penn Treebank Tokenizer The Treebank tokenizer uses regular expressions to tokenize text as in Penn Treebank. This implementation is a port of the tokenizer sed script written by Robert McIntyre and available at http://www.cis.upenn.edu/~treebank/tokenizer.sed. éN)ÚIteratorÚListÚTuple)Ú TokenizerI)ÚMacIntyreContractions)Ú align_tokensc @s–eZdZdZe d¡dfe d¡dfe d¡dfgZe d¡d fe d ¡dfe d ¡d fe d ¡dfe d¡dfe d¡dfe d¡dfgZe d¡dfZe d¡dfe d¡dfe d¡dfe d¡dfe d¡dfe d¡d fgZ e d!¡d"fZ e d#¡d$fe d%¡d$fe d&¡d'fe d(¡d'fgZ e ƒZ eeeje jƒƒZeeeje jƒƒZ )d3d*ed+ed,ed-eefd.d/„Zd*ed-eeeeffd0d1„Zd2S)4ÚTreebankWordTokenizera  The Treebank tokenizer uses regular expressions to tokenize text as in Penn Treebank. This tokenizer performs the following steps: - split standard contractions, e.g. ``don't`` -> ``do n't`` and ``they'll`` -> ``they 'll`` - treat most punctuation characters as separate tokens - split off commas and single quotes, when followed by whitespace - separate periods that appear at the end of line >>> from nltk.tokenize import TreebankWordTokenizer >>> s = '''Good muffins cost $3.88\nin New York. Please buy me\ntwo of them.\nThanks.''' >>> TreebankWordTokenizer().tokenize(s) ['Good', 'muffins', 'cost', '$', '3.88', 'in', 'New', 'York.', 'Please', 'buy', 'me', 'two', 'of', 'them.', 'Thanks', '.'] >>> s = "They'll save and invest more." >>> TreebankWordTokenizer().tokenize(s) ['They', "'ll", 'save', 'and', 'invest', 'more', '.'] >>> s = "hi, my name can't hello," >>> TreebankWordTokenizer().tokenize(s) ['hi', ',', 'my', 'name', 'ca', "n't", 'hello', ','] z^\"ú``z(``)z \1 z([ \(\[{<])(\"|\'{2})z\1 `` z ([:,])([^\d])z \1 \2z([:,])$z\.\.\.z ... z[;@#$%&]z \g<0> z([^\.])(\.)([\]\)}>"\']*)\s*$z\1 \2\3 z[?!]z([^'])' z\1 ' z[\]\[\(\)\{\}\<\>]z\(ú-LRB-z\)ú-RRB-z\[ú-LSB-z\]ú-RSB-z\{ú-LCB-z\}ú-RCB-ú--ú -- ú''z '' ú"z([^' ])('[sS]|'[mM]|'[dD]|') z\1 \2 z)([^' ])('ll|'LL|'re|'RE|'ve|'VE|n't|N'T) FÚtextÚconvert_parenthesesÚ return_strÚreturncCsü|dur tjdtdd|jD] \}}| ||¡}q|jD] \}}| ||¡}q|j\}}| ||¡}|rC|jD] \}}| ||¡}q8|j\}}| ||¡}d|d}|j D] \}}| ||¡}qW|j D]}| d|¡}qe|j D]}| d|¡}qq|  ¡S)aýReturn a tokenized copy of `text`. >>> from nltk.tokenize import TreebankWordTokenizer >>> s = '''Good muffins cost $3.88 (roughly 3,36 euros)\nin New York. Please buy me\ntwo of them.\nThanks.''' >>> TreebankWordTokenizer().tokenize(s) # doctest: +NORMALIZE_WHITESPACE ['Good', 'muffins', 'cost', '$', '3.88', '(', 'roughly', '3,36', 'euros', ')', 'in', 'New', 'York.', 'Please', 'buy', 'me', 'two', 'of', 'them.', 'Thanks', '.'] >>> TreebankWordTokenizer().tokenize(s, convert_parentheses=True) # doctest: +NORMALIZE_WHITESPACE ['Good', 'muffins', 'cost', '$', '3.88', '-LRB-', 'roughly', '3,36', 'euros', '-RRB-', 'in', 'New', 'York.', 'Please', 'buy', 'me', 'two', 'of', 'them.', 'Thanks', '.'] :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] FzHParameter '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_QUOTESÚ CONTRACTIONS2Ú CONTRACTIONS3Úsplit)ÚselfrrrÚregexpÚ substitution©r,úE/var/www/auris/lib/python3.10/site-packages/nltk/tokenize/treebank.pyÚtokenizees2ü       zTreebankWordTokenizer.tokenizec#s^| |¡}d|vsd|vr#dd„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 TreebankWordTokenizer >>> s = '''Good muffins cost $3.88\nin New (York). Please (buy) me\ntwo of them.\n(Thanks).''' >>> expected = [(0, 4), (5, 12), (13, 17), (18, 19), (19, 23), ... (24, 26), (27, 30), (31, 32), (32, 36), (36, 37), (37, 38), ... (40, 46), (47, 48), (48, 51), (51, 52), (53, 55), (56, 59), ... (60, 62), (63, 68), (69, 70), (70, 76), (76, 77), (77, 78)] >>> list(TreebankWordTokenizer().span_tokenize(s)) == expected True >>> expected = ['Good', 'muffins', 'cost', '$', '3.88', 'in', ... 'New', '(', 'York', ')', '.', 'Please', '(', 'buy', ')', ... 'me', 'two', 'of', 'them.', '(', 'Thanks', ')', '.'] >>> [s[start:end] for start, end in TreebankWordTokenizer().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.0Úmr,r,r-Ú Ësz7TreebankWordTokenizer.span_tokenize..z ``|'{2}|\"cs"g|] }|dvr ˆ d¡n|‘qS))rr rr)Úpop)r0Útok©Zmatchedr,r-r2ÎsÿÿN)r.ÚreÚfinditerr)r)rZ raw_tokensÚtokensr,r5r-Ú span_tokenize¬s€  þz#TreebankWordTokenizer.span_tokenizeN)FF)Ú__name__Ú __module__Ú __qualname__Ú__doc__r6Úcompilerr!r"r#r$r%rÚ _contractionsÚlistÚmapr&r'ÚstrÚboolrr.rrÚintr9r,r,r,r-rsX   ý    þ  ö      ú    üÿÿÿÿ þ"Grc @s°eZdZdZeƒZdd„ejDƒZdd„ejDƒZe  d¡dfe  d¡dfe  d¡d fe  d ¡d fe  d ¡d fgZ e  d ¡dfZ e  d¡dfe  d¡dfe  d¡dfe  d¡dfe  d¡dfe  d¡dfgZ e  d¡dfe  d¡dfe  d¡d fgZ e  d¡d fe  d!¡dfe  d"¡d#fe  d$¡dfe  d%¡dfe  d&¡d'fe  d(¡d)fgZe  d*¡d+fe  d,¡d)fe  d-¡d fgZd7d/eed0ed1efd2d3„Zd7d/eed0ed1efd4d5„Zd6S)8ÚTreebankWordDetokenizera‹ The Treebank detokenizer uses the reverse regex operations corresponding to the Treebank tokenizer's regexes. Note: - There're additional assumption mades when undoing the padding of ``[;@#$%&]`` punctuation symbols that isn't presupposed in the TreebankTokenizer. - There're additional regexes added in reversing the parentheses tokenization, such as the ``r'([\]\)\}\>])\s([:;,.])'``, which removes the additional right padding added to the closing parentheses precedding ``[:;,.]``. - It's not possible to return the original whitespaces as they were because there wasn't explicit records of where `'\n'`, `'\t'` or `'\s'` were removed at the text.split() operation. >>> from nltk.tokenize.treebank import TreebankWordTokenizer, TreebankWordDetokenizer >>> s = '''Good muffins cost $3.88\nin New York. Please buy me\ntwo of them.\nThanks.''' >>> d = TreebankWordDetokenizer() >>> t = TreebankWordTokenizer() >>> toks = t.tokenize(s) >>> d.detokenize(toks) 'Good muffins cost $3.88 in New York. Please buy me two of them. Thanks.' The MXPOST parentheses substitution can be undone using the ``convert_parentheses`` parameter: >>> s = '''Good muffins cost $3.88\nin New (York). Please (buy) me\ntwo of them.\n(Thanks).''' >>> expected_tokens = ['Good', 'muffins', 'cost', '$', '3.88', 'in', ... 'New', '-LRB-', 'York', '-RRB-', '.', 'Please', '-LRB-', 'buy', ... '-RRB-', 'me', 'two', 'of', 'them.', '-LRB-', 'Thanks', '-RRB-', '.'] >>> expected_tokens == t.tokenize(s, convert_parentheses=True) True >>> expected_detoken = 'Good muffins cost $3.88 in New (York). Please (buy) me two of them. (Thanks).' >>> expected_detoken == d.detokenize(t.tokenize(s, convert_parentheses=True), convert_parentheses=True) True During tokenization it's safe to add more spaces but during detokenization, simply undoing the padding doesn't really help. - During tokenization, left and right pad is added to ``[!?]``, when detokenizing, only left shift the ``[!?]`` is needed. Thus ``(re.compile(r'\s([?!])'), r'\g<1>')``. - During tokenization ``[:,]`` are left and right padded but when detokenizing, only left shift is necessary and we keep right pad after comma/colon if the string after is a non-digit. Thus ``(re.compile(r'\s([:,])\s([^\d])'), r'\1 \2')``. >>> from nltk.tokenize.treebank import TreebankWordDetokenizer >>> toks = ['hello', ',', 'i', 'ca', "n't", 'feel', 'my', 'feet', '!', 'Help', '!', '!'] >>> twd = TreebankWordDetokenizer() >>> twd.detokenize(toks) "hello, i can't feel my feet! Help!!" >>> toks = ['hello', ',', 'i', "can't", 'feel', ';', 'my', 'feet', '!', ... 'Help', '!', '!', 'He', 'said', ':', 'Help', ',', 'help', '?', '!'] >>> twd.detokenize(toks) "hello, i can't feel; my feet! Help!! He said: Help, help?!" cCóg|] }t | dd¡¡‘qS©z(?#X)z\s©r6r>Úreplace©r0Úpatternr,r,r-r2óÿÿz"TreebankWordDetokenizer.cCrFrGrHrJr,r,r-r2rLz+([^' ])\s('ll|'LL|'re|'RE|'ve|'VE|n't|N'T) z\1\2 z([^' ])\s('[sS]|'[mM]|'[dD]|') z (\S)\s(\'\')ú\1\2z(\'\')\s([.,:)\]>};%])rrrrr ú(r ú)r ú[r ú]rÚ{rÚ}z([\[\(\{\<])\sz\g<1>z\s([\]\)\}\>])z([\]\)\}\>])\s([:;,.])z ([^'])\s'\sz\1' z\s([?!])z([^\.])\s(\.)([\]\)}>"\']*)\s*$z\1\2\3z([#$])\sz\s([;%])z \s\.\.\.\sz...z\s([:,])z\1z([ (\[{<])\s``z\1``z(``)\sr Fr8rrcCsüd |¡}d|d}|jD]}| d|¡}q|jD]}| d|¡}q|jD] \}}| ||¡}q&| ¡}|j\}}| ||¡}|rP|jD] \}}| ||¡}qE|jD] \}}| ||¡}qS|j D] \}}| ||¡}qa|j D] \}}| ||¡}qo| ¡S)a¥ Treebank detokenizer, created by undoing the regexes from the TreebankWordTokenizer.tokenize. :param tokens: A list of strings, i.e. tokenized text. :type tokens: List[str] :param convert_parentheses: if True, replace PTB symbols with parentheses, e.g. `-LRB-` to `(`. Defaults to False. :type convert_parentheses: bool, optional :return: str rrM) Újoinr'r r&r%Ústripr$r#r"r!r)r)r8rrr*r+r,r,r-r.[s*     z TreebankWordDetokenizer.tokenizecCs | ||¡S)z&Duck-typing the abstract *tokenize()*.)r.)r)r8rr,r,r-Ú detokenizes z"TreebankWordDetokenizer.detokenizeN)F)r:r;r<r=rr?r&r'r6r>r%r$r#r"r!rrrBrCr.rVr,r,r,r-rEØsZ<þþ   þ ø      ú  ý      þò   ý 5rE)r=r6rÚtypingrrrZnltk.tokenize.apirZnltk.tokenize.destructiverZnltk.tokenize.utilrrrEr,r,r,r-Ús     <