o rZh= @sdZddlZddlmZddlZddlmZdZdZdZ dZ eed d d d d de df Z e de ge ddRZ e dZe eejejBejBZe dZe dZd%ddZd&ddZGdddeZddZd d!Z  " " d'd#d$ZdS)(a Twitter-aware tokenizer, designed to be flexible and easy to adapt to new domains and tasks. The basic logic is this: 1. The tuple REGEXPS defines a list of regular expression strings. 2. The REGEXPS strings are put, in order, into a compiled regular expression object called WORD_RE, under the TweetTokenizer class. 3. The tokenization is done by WORD_RE.findall(s), where s is the user-supplied string, inside the tokenize() method of the class TweetTokenizer. 4. When instantiating Tokenizer objects, there are several options: * preserve_case. By default, it is set to True. If it is set to False, then the tokenizer will downcase everything except for emoticons. * reduce_len. By default, it is set to False. It specifies whether to replace repeated character sequences of length 3 or greater with sequences of length 3. * strip_handles. By default, it is set to False. It specifies whether to remove Twitter handles of text used in the `tokenize` method. * match_phone_numbers. By default, it is set to True. It indicates whether the `tokenize` method should look for phone numbers. N)List) TokenizerIac (?: [<>]? [:;=8] # eyes [\-o\*\']? # optional nose [\)\]\(\[dDpP/\:\}\{@\|\\] # mouth | [\)\]\(\[dDpP/\:\}\{@\|\\] # mouth [\-o\*\']? # optional nose [:;=8] # eyes [<>]? | {}\[\]]+ # 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`!()\[\]{};:'".,<>?«»“”‘’] # not a space or one of these punct chars ) | # OR, the following to match naked domains: (?: (?\s]+>z [\-]+>|<[\-]+z (?:@[\w_]+)z(?:\#+[\w_]+[\w\'_\-]*[\w_]+)z#[\w.+-]+@[\w-]+\.(?:[\w-]\.?)+[\w-]uR.(?: [🏻-🏿]?(?:‍.[🏻-🏿]?)+ | [🏻-🏿] )a (?:[^\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. z([^a-zA-Z0-9])\1{3,}z&(#?(x?))([^&;\s]+);zZ(?>> from nltk.tokenize.casual import _replace_html_entities >>> _replace_html_entities(b'Price: £100') 'Price: \xa3100' >>> print(_replace_html_entities(b'Price: £100')) Price: £100 >>> c s|d}|dr=z'|drt|d}nt|d}d|kr%dkr0nn t|fdWSWnty<d}Ynw|vrF|d Stjj|}|durbzt |WStt fyaYnwrfd S|d S) Nr cp1252r) groupintrr ValueErrorhtmlentitiesname2codepointgetchr OverflowError)matchZ entity_bodynumberkeepremove_illegalr r_convert_entitys,        z/_replace_html_entities.._convert_entity)ENT_REsubr)r r$r%r r&r r#r_replace_html_entitiessr)c@s\eZdZdZdZdZ    dddZdedeefd d Z e dd d Z e dddZ dS)TweetTokenizera Tokenizer for tweets. >>> from nltk.tokenize import TweetTokenizer >>> tknzr = TweetTokenizer() >>> s0 = "This is a cooool #dummysmiley: :-) :-P <3 and some arrows < > -> <--" >>> tknzr.tokenize(s0) # doctest: +NORMALIZE_WHITESPACE ['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', '!', '!', '!'] NTFcCs||_||_||_||_dS)ae Create a `TweetTokenizer` instance with settings for use in the `tokenize` method. :param preserve_case: Flag indicating whether to preserve the casing (capitalisation) of text used in the `tokenize` method. Defaults to True. :type preserve_case: bool :param reduce_len: Flag indicating whether to replace repeated character sequences of length 3 or greater with sequences of length 3. Defaults to False. :type reduce_len: bool :param strip_handles: Flag indicating whether to remove Twitter handles of text used in the `tokenize` method. Defaults to False. :type strip_handles: bool :param match_phone_numbers: Flag indicating whether the `tokenize` method should look for phone numbers. Defaults to True. :type match_phone_numbers: bool N preserve_case reduce_len strip_handlesmatch_phone_numbers)selfr,r-r.r/r r r__init__Ls zTweetTokenizer.__init__r returncCslt|}|jr t|}|jrt|}td|}|jr"|j |}n|j |}|j s4t t dd|}|S)zTokenize the input text. :param text: str :rtype: list(str) :return: a tokenized list of strings; joining this list returns the original string if `preserve_case=False`. \1\1\1cSst|r|S|S)N) EMOTICON_REsearchlower)xr r rsz)TweetTokenizer.tokenize..)r)r.remove_handlesr-reduce_lengtheningHANG_REr(r/ PHONE_WORD_REfindallWORD_REr,listmap)r0r Z safe_textwordsr r rtokenizehs    zTweetTokenizer.tokenize regex.PatterncCBt|jstddtdtjtjBtjBt|_t|jS)zCore TweetTokenizer regex(|)) type_WORD_REregexcompilejoinREGEXPSVERBOSEIUNICODEr0r r rr>  zTweetTokenizer.WORD_REcCrD)z#Secondary core TweetTokenizer regexrErFrG) rH_PHONE_WORD_RErJrKrL REGEXPS_PHONErNrOrPrQr r rr<rRzTweetTokenizer.PHONE_WORD_RETFFT)r2rC) __name__ __module__ __qualname____doc__rIrSr1strrrBpropertyr>r<r r r rr*2s   r*cCstd}|d|S)ze Replace repeated character sequences of length 3 or greater with sequences of length 3. z (.)\1{2,}r3)rJrKr()r patternr r rr:s  r:cCs td|S)z4 Remove Twitter username handles from text.  ) HANDLES_REr()r r r rr9s r9FcCst||||d|S)z: Convenience function for wrapping the tokenizer. r+)r*rB)r r,r-r.r/r r rcasual_tokenizes r_)Nr)r TrrU)rYrtypingrrJZnltk.tokenize.apirZ EMOTICONSZURLSFLAGSZ PHONE_REGEXrMrTrKr;rNrOrPr4r'r^rr)r*r:r9r_r r r rsJ   3%   >p