3 d=A@spdZddlZddlZddlmZmZmZddlmZddl m Z ddl m Z GdddeZ Gd d d eZdS) 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. N)IteratorListTuple) TokenizerI)MacIntyreContractions) align_tokensc@seZdZdZejddfejddfejddfgZejdd fejd dfejd d fejd dfejddfejddfejddfgZejddfZejddfejddfejddfejddfejddfejdd fgZ ejd!d"fZ ejd#d$fejd%d$fejd&d'fejd(d'fgZ e Z eeeje jZeeeje jZd1eeeeed*d+d,Zeeeeefd-d.d/Zd0S)2TreebankWordTokenizera  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^\"z``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\(z-LRB-z\)z-RRB-z\[z-LSB-z\]z-RSB-z\{z-LCB-z\}z-RCB-z--z -- z''z '' "z([^' ])('[sS]|'[mM]|'[dD]|') z\1 \2 z)([^' ])('ll|'LL|'re|'RE|'ve|'VE|n't|N'T) F)textconvert_parentheses return_strreturncCs|dk rtjdtddx|jD]\}}|j||}q Wx|jD]\}}|j||}q@W|j\}}|j||}|rx|jD]\}}|j||}qzW|j\}}|j||}d|d}x|j D]\}}|j||}qWx|j D]}|jd|}qWx|j D]}|jd|}qW|j S)aqReturn a tokenized copy of `text`. >>> from nltk.tokenize import TreebankWordTokenizer >>> s = '''Good muffins cost $3.88 (roughly 3,36 euros)\nin New York. Please buy me\ntwo of them.\nThanks.''' >>> TreebankWordTokenizer().tokenize(s) ['Good', 'muffins', 'cost', '$', '3.88', '(', 'roughly', '3,36', 'euros', ')', 'in', 'New', 'York.', 'Please', 'buy', 'me', 'two', 'of', 'them.', 'Thanks', '.'] >>> TreebankWordTokenizer().tokenize(s, convert_parentheses=True) ['Good', 'muffins', 'cost', '$', '3.88', '-LRB-', 'roughly', '3,36', 'euros', '-RRB-', 'in', 'New', 'York.', 'Please', 'buy', 'me', 'two', 'of', 'them.', 'Thanks', '.'] >>> TreebankWordTokenizer().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] FzHParameter 'return_str' has been deprecated and should no longer be used.)category stacklevel z \1 \2 ) warningswarnDeprecationWarningSTARTING_QUOTESsub PUNCTUATIONPARENS_BRACKETSCONVERT_PARENTHESES DOUBLE_DASHES ENDING_QUOTES CONTRACTIONS2 CONTRACTIONS3split)selfr r r regexp substitutionr"6/tmp/pip-build-v9q4h5k9/nltk/nltk/tokenize/treebank.pytokenizees0       zTreebankWordTokenizer.tokenize)r r c#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 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] r z''cSsg|] }|jqSr")group).0mr"r"r# sz7TreebankWordTokenizer.span_tokenize..z ``|'{2}|\"cs"g|]}|dkrjdn|qS)r ``''r)r r)r*)pop)r&tok)matchedr"r#r(sN)r$refinditerr)rr Z raw_tokenstokensr")r-r# span_tokenizes   z#TreebankWordTokenizer.span_tokenizeN)FF)__name__ __module__ __qualname____doc__r.compilerrrrrrr _contractionslistmaprrstrboolrr$rrintr1r"r"r"r#rs<               Grc@seZdZdZeZddejDZddejDZej ddfej ddfej dd fej d d fej d d fgZ ej d dfZ ej ddfej ddfej ddfej ddfej ddfej ddfgZ ej ddfej ddfej dd fgZ ej dd fej d!dfej d"d#fej d$dfej d%dfej d&d'fej d(d)fgZej d*d+fej d,d)fej d-d fgZd5eeeed/d0d1Zd6eeeed/d2d3Zd4S)7TreebankWordDetokenizera The Treebank detokenizer uses the reverse regex operations corresponding to the Treebank tokenizer's regexes. Note: - There're additional assumption mades when undoing the padding of ``[;@#$%&]`` 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?!" cCsg|]}tj|jddqS)z(?#X)z\s)r.r6replace)r&patternr"r"r#r(sz"TreebankWordDetokenizer.cCsg|]}tj|jddqS)z(?#X)z\s)r.r6r>)r&r?r"r"r#r(sz+([^' ])\s('ll|'LL|'re|'RE|'ve|'VE|n't|N'T) z\1\2 z([^' ])\s('[sS]|'[mM]|'[dD]|') z (\S)\s(\'\')z\1\2z(\'\')\s([.,:)\]>};%])z''r z -- z--z-LRB-(z-RRB-)z-LSB-[z-RSB-]z-LCB-{z-RCB-}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(``)\sz``F)r0r r cCs dj|}x|jD]}|jd|}qWx|jD]}|jd|}q.Wx|jD]\}}|j||}qJW|j}|j\}}|j||}|rx|jD]\}}|j||}qWx|jD]\}}|j||}qWx|j D]\}}|j||}qWx|j D]\}}|j||}qW|jS)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 rz\1\2) joinrrrrstriprrrrr)rr0r r r r!r"r"r#r$]s(     z TreebankWordDetokenizer.tokenizecCs |j||S)z&Duck-typing the abstract *tokenize()*.)r$)rr0r r"r"r# detokenizesz"TreebankWordDetokenizer.detokenizeN)F)F)r2r3r4r5rr7rrr.r6rrrrrrrr:r;r$rHr"r"r"r#r=sF;                    1r=)r5r.rZtypingrrrZnltk.tokenize.apirZnltk.tokenize.destructiverZnltk.tokenize.utilrrr=r"r"r"r#s   >