ó ù`]c@s@dZddlmZddlmZdefd„ƒYZdS(s( Multi-Word Expression Tokenizer A ``MWETokenizer`` takes a string which has already been divided into tokens and retokenizes it, merging multi-word expressions into single tokens, using a lexicon of MWEs: >>> from nltk.tokenize import MWETokenizer >>> tokenizer = MWETokenizer([('a', 'little'), ('a', 'little', 'bit'), ('a', 'lot')]) >>> tokenizer.add_mwe(('in', 'spite', 'of')) >>> tokenizer.tokenize('Testing testing testing one two three'.split()) ['Testing', 'testing', 'testing', 'one', 'two', 'three'] >>> tokenizer.tokenize('This is a test in spite'.split()) ['This', 'is', 'a', 'test', 'in', 'spite'] >>> tokenizer.tokenize('In a little or a little bit or a lot in spite of'.split()) ['In', 'a_little', 'or', 'a_little_bit', 'or', 'a_lot', 'in_spite_of'] iÿÿÿÿ(tTrie(t TokenizerIt MWETokenizercBs/eZdZddd„Zd„Zd„ZRS(shA tokenizer that processes tokenized text and merges multi-word expressions into single tokens. t_cCs+|sg}nt|ƒ|_||_dS(s¥Initialize the multi-word tokenizer with a list of expressions and a separator :type mwes: list(list(str)) :param mwes: A sequence of multi-word expressions to be merged, where each MWE is a sequence of strings. :type separator: str :param separator: String that should be inserted between words in a multi-word expression token. (Default is '_') N(Rt_mwest _separator(tselftmwest separator((s0lib/python2.7/site-packages/nltk/tokenize/mwe.pyt__init__)s  cCs|jj|ƒdS(s—Add a multi-word expression to the lexicon (stored as a word trie) We use ``util.Trie`` to represent the trie. Its form is a dict of dicts. The key True marks the end of a valid MWE. :param mwe: The multi-word expression we're adding into the word trie :type mwe: tuple(str) or list(str) :Example: >>> tokenizer = MWETokenizer() >>> tokenizer.add_mwe(('a', 'b')) >>> tokenizer.add_mwe(('a', 'b', 'c')) >>> tokenizer.add_mwe(('a', 'x')) >>> expected = {'a': {'x': {True: None}, 'b': {True: None, 'c': {True: None}}}} >>> tokenizer._mwes == expected True N(Rtinsert(Rtmwe((s0lib/python2.7/site-packages/nltk/tokenize/mwe.pytadd_mwe:scCsýd}t|ƒ}g}xÞ||krø|||jkrÚ|}|j}x©||krƒ|||krƒ|||}|d}qLWtj|kr¼|j|jj|||!ƒƒ|}qõ|j||ƒ|d7}q|j||ƒ|d7}qW|S(s­ :param text: A list containing tokenized text :type text: list(str) :return: A list of the tokenized text with multi-words merged together :rtype: list(str) :Example: >>> tokenizer = MWETokenizer([('hors', "d'oeuvre")], separator='+') >>> tokenizer.tokenize("An hors d'oeuvre tonight, sir?".split()) ['An', "hors+d'oeuvre", 'tonight,', 'sir?'] ii(tlenRRtLEAFtappendRtjoin(Rttexttitntresulttjttrie((s0lib/python2.7/site-packages/nltk/tokenize/mwe.pyttokenizePs$     N(t__name__t __module__t__doc__tNoneR R R(((s0lib/python2.7/site-packages/nltk/tokenize/mwe.pyR$s N(Rt nltk.utilRtnltk.tokenize.apiRR(((s0lib/python2.7/site-packages/nltk/tokenize/mwe.pyts