ó ł`]c @sBdZddlmZddlZddlmZmZddlmZdZ dZ e de d d d d d df Z ej ddj e ƒejejBejBƒZej dƒZej e ejejBejBƒZej dƒZddd„Zdedd„Zddd„ƒYZd„Zd„Zeeed„ZdS(uœ Twitter-aware tokenizer, designed to be flexible and easy to adapt to new domains and tasks. The basic logic is this: 1. The tuple regex_strings defines a list of regular expression strings. 2. The regex_strings strings are put, in order, into a compiled regular expression object called word_re. 3. The tokenization is done by word_re.findall(s), where s is the user-supplied string, inside the tokenize() method of the class Tokenizer. 4. When instantiating Tokenizer objects, there is a single option: preserve_case. By default, it is set to True. If it is set to False, then the tokenizer will downcase everything except for emoticons. i’’’’(tunicode_literalsN(tint2bytetunichr(t html_entitiesuc (?: [<>]? [:;=8] # eyes [\-o\*\']? # optional nose [\)\]\(\[dDpP/\:\}\{@\|\\] # mouth | [\)\]\(\[dDpP/\:\}\{@\|\\] # mouth [\-o\*\']? # optional nose [:;=8] # eyes [<>]? | <3 # heart )u # Capture 1: entire matched URL (?: https?: # URL protocol and colon (?: /{1,3} # 1-3 slashes | # or [a-z0-9%] # Single letter or digit or '%' # (Trying not to match e.g. "URI::Escape") ) | # or # looks like domain name followed by a slash: [a-z0-9.\-]+[.] (?:[a-z]{2,13}) / ) (?: # One or more: [^\s()<>{}\[\]]+ # Run of non-space, non-()<>{}[] | # or \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (...(...)...) | \([^\s]+?\) # balanced parens, non-recursive: (...) )+ (?: # End with: \([^\s()]*?\([^\s()]+\)[^\s()]*?\) # balanced parens, one level deep: (...(...)...) | \([^\s]+?\) # balanced parens, non-recursive: (...) | # or [^\s`!()\[\]{};:'".,<>?Ā«Ā»ā€œā€ā€˜ā€™] # not a space or one of these punct chars ) | # OR, the following to match naked domains: (?: (?\s]+>u [\-]+>|<[\-]+u (?:@[\w_]+)u(?:\#+[\w_]+[\w\'_\-]*[\w_]+)u#[\w.+-]+@[\w-]+\.(?:[\w-]\.?)+[\w-]u… (?:[^\W\d_](?:[^\W\d_]|['\-_])+[^\W\d_]) # Words with apostrophes or dashes. | (?:[+\-]?\d+[,/.:-]\d+[+\-]?) # Numbers, including fractions, decimals. | (?:[\w_]+) # Words without apostrophes or dashes. | (?:\.(?:\s*\.){1,}) # Ellipsis dots. | (?:\S) # Everything else that isn't whitespace. u(%s)u|u([^a-zA-Z0-9])\1{3,}u&(#?(x?))([^&;\s]+);ustrictcCs8|dkrd}nt|tƒr4|j||ƒS|S(Nuutf-8(tNonet isinstancetbytestdecode(ttexttencodingterrors((s3lib/python2.7/site-packages/nltk/tokenize/casual.pyt_str_to_unicode»s   uutf-8cs+‡‡fd†}tj|t||ƒƒS(u· Remove entities from text by converting them to their corresponding unicode character. :param text: a unicode string or a byte string encoded in the given `encoding` (which defaults to 'utf-8'). :param list keep: list of entity names which should not be replaced. This supports both numeric entities (``&#nnnn;`` and ``&#hhhh;``) and named entities (such as `` `` or ``>``). :param bool remove_illegal: If `True`, entities that can't be converted are removed. Otherwise, entities that can't be converted are kept "as is". :returns: A unicode string with the entities removed. See https://github.com/scrapy/w3lib/blob/master/w3lib/html.py >>> from nltk.tokenize.casual import _replace_html_entities >>> _replace_html_entities(b'Price: £100') 'Price: \xa3100' >>> print(_replace_html_entities(b'Price: £100')) Price: Ā£100 >>> cs|jdƒ}|jdƒržyc|jdƒrBt|dƒ}nt|dƒ}d|kohdknr€t|ƒjdƒSWqÉtk ršd}qÉXn+|ˆkr·|jd ƒStjj|ƒ}|dk rśyt |ƒSWqśtk röqśXnˆrd S|jd ƒS( Niiiii i€iŸucp1252iu( tgrouptintRRt ValueErrorRRtname2codepointtgetR(tmatcht entity_bodytnumber(tkeeptremove_illegal(s3lib/python2.7/site-packages/nltk/tokenize/casual.pyt_convert_entityßs&      (tENT_REtsubR (RRRR R((RRs3lib/python2.7/site-packages/nltk/tokenize/casual.pyt_replace_html_entitiesĆstTweetTokenizercBs)eZdZeeed„Zd„ZRS(u° Tokenizer for tweets. >>> from nltk.tokenize import TweetTokenizer >>> tknzr = TweetTokenizer() >>> s0 = "This is a cooool #dummysmiley: :-) :-P <3 and some arrows < > -> <--" >>> tknzr.tokenize(s0) ['This', 'is', 'a', 'cooool', '#dummysmiley', ':', ':-)', ':-P', '<3', 'and', 'some', 'arrows', '<', '>', '->', '<--'] Examples using `strip_handles` and `reduce_len parameters`: >>> tknzr = TweetTokenizer(strip_handles=True, reduce_len=True) >>> s1 = '@remy: This is waaaaayyyy too much for you!!!!!!' >>> tknzr.tokenize(s1) [':', 'This', 'is', 'waaayyy', 'too', 'much', 'for', 'you', '!', '!', '!'] cCs||_||_||_dS(N(t preserve_caset reduce_lent strip_handles(tselfRRR((s3lib/python2.7/site-packages/nltk/tokenize/casual.pyt__init__s  cCs…t|ƒ}|jr$t|ƒ}n|jr<t|ƒ}ntjd|ƒ}tj|ƒ}|j st t d„|ƒƒ}n|S(u¾ :param text: str :rtype: list(str) :return: a tokenized list of strings; concatenating this list returns the original string if `preserve_case=False` u\1\1\1cSstj|ƒr|S|jƒS(N(t EMOTICON_REtsearchtlower(tx((s3lib/python2.7/site-packages/nltk/tokenize/casual.pyt/t( RRtremove_handlesRtreduce_lengtheningtHANG_RERtWORD_REtfindallRtlisttmap(RRt safe_texttwords((s3lib/python2.7/site-packages/nltk/tokenize/casual.pyttokenizes    (t__name__t __module__t__doc__tTruetFalseRR/(((s3lib/python2.7/site-packages/nltk/tokenize/casual.pyRscCstjdƒ}|jd|ƒS(ue Replace repeated character sequences of length 3 or greater with sequences of length 3. u (.)\1{2,}u\1\1\1(tretcompileR(Rtpattern((s3lib/python2.7/site-packages/nltk/tokenize/casual.pyR'9scCstjdƒ}|jd|ƒS(u4 Remove Twitter username handles from text. uv(?!s2 . 0#?7