Return to Revisions

I authored a piece of code that was merged into the nltk codebase. It is full of regex substitutions:

import re
from six import text_type
from nltk.tokenize.api import TokenizerI
class ToktokTokenizer(TokenizerI):
 """
 This is a Python port of the tok-tok.pl from
 https://github.com/jonsafari/tok-tok/blob/master/tok-tok.pl
 
 >>> toktok = ToktokTokenizer()
 >>> text = u'Is 9.5 or 525,600 my favorite number?'
 >>> print (toktok.tokenize(text, return_str=True))
 Is 9.5 or 525,600 my favorite number ?
 >>> text = u'The https://github.com/jonsafari/tok-tok/blob/master/tok-tok.pl is a website with/and/or slashes and sort of weird : things'
 >>> print (toktok.tokenize(text, return_str=True))
 The https://github.com/jonsafari/tok-tok/blob/master/tok-tok.pl is a website with/and/or slashes and sort of weird : things
 >>> text = u'\xa1This, is a sentence with weird\xbb symbols\u2026 appearing everywhere\xbf'
 >>> expected = u'\xa1 This , is a sentence with weird \xbb symbols \u2026 appearing everywhere \xbf'
 >>> assert toktok.tokenize(text, return_str=True) == expected
 >>> toktok.tokenize(text) == [u'\xa1', u'This', u',', u'is', u'a', u'sentence', u'with', u'weird', u'\xbb', u'symbols', u'\u2026', u'appearing', u'everywhere', u'\xbf']
 True
 """
 # Replace non-breaking spaces with normal spaces.
 NON_BREAKING = re.compile(u"\u00A0"), " "
 
 # Pad some funky punctuation.
 FUNKY_PUNCT_1 = re.compile(u'([،;؛¿!"\])}»›"؟¡%٪°±©®।॥...])'), r" 1円 "
 # Pad more funky punctuation.
 FUNKY_PUNCT_2 = re.compile(u'([({\["‘„‚«‹「『])'), r" 1円 "
 # Pad En dash and em dash
 EN_EM_DASHES = re.compile(u'([–—])'), r" 1円 "
 
 # Replace problematic character with numeric character reference.
 AMPERCENT = re.compile('& '), '& '
 TAB = re.compile('\t'), ' 	 '
 PIPE = re.compile('\|'), ' | '
 
 # Pad numbers with commas to keep them from further tokenization. 
 COMMA_IN_NUM = re.compile(r'(?<!,)([,،])(?![,\d])'), r' 1円 '
 
 # Just pad problematic (often neurotic) hyphen/single quote, etc.
 PROB_SINGLE_QUOTES = re.compile(r"(['’`])"), r' 1円 '
 # Group ` ` stupid quotes ' ' into a single token.
 STUPID_QUOTES_1 = re.compile(r" ` ` "), r" `` "
 STUPID_QUOTES_2 = re.compile(r" ' ' "), r" '' "
 
 # Don't tokenize period unless it ends the line and that it isn't 
 # preceded by another period, e.g. 
 # "something ..." -> "something ..." 
 # "something." -> "something ." 
 FINAL_PERIOD_1 = re.compile(r"(?<!\.)\.$"), r" ."
 # Don't tokenize period unless it ends the line eg. 
 # " ... stuff." -> "... stuff ."
 FINAL_PERIOD_2 = re.compile(r"""(?<!\.)\.\s*(["'’»›"]) *$"""), r" . 1円"
 # Treat continuous commas as fake German,Czech, etc.: „
 MULTI_COMMAS = re.compile(r'(,{2,})'), r' 1円 '
 # Treat continuous dashes as fake en-dash, etc.
 MULTI_DASHES = re.compile(r'(-{2,})'), r' 1円 '
 # Treat multiple periods as a thing (eg. ellipsis)
 MULTI_DOTS = re.compile(r'(\.{2,})'), r' 1円 '
 # This is the \p{Open_Punctuation} from Perl's perluniprops
 # see http://perldoc.perl.org/perluniprops.html
 OPEN_PUNCT = text_type(u'([{\u0f3a\u0f3c\u169b\u201a\u201e\u2045\u207d'
 u'\u208d\u2329\u2768\u276a\u276c\u276e\u2770\u2772'
 u'\u2774\u27c5\u27e6\u27e8\u27ea\u27ec\u27ee\u2983'
 u'\u2985\u2987\u2989\u298b\u298d\u298f\u2991\u2993'
 u'\u2995\u2997\u29d8\u29da\u29fc\u2e22\u2e24\u2e26'
 u'\u2e28\u3008\u300a\u300c\u300e\u3010\u3014\u3016'
 u'\u3018\u301a\u301d\ufd3e\ufe17\ufe35\ufe37\ufe39'
 u'\ufe3b\ufe3d\ufe3f\ufe41\ufe43\ufe47\ufe59\ufe5b'
 u'\ufe5d\uff08\uff3b\uff5b\uff5f\uff62')
 # This is the \p{Close_Punctuation} from Perl's perluniprops
 CLOSE_PUNCT = text_type(u')]}\u0f3b\u0f3d\u169c\u2046\u207e\u208e\u232a'
 u'\u2769\u276b\u276d\u276f\u2771\u2773\u2775\u27c6'
 u'\u27e7\u27e9\u27eb\u27ed\u27ef\u2984\u2986\u2988'
 u'\u298a\u298c\u298e\u2990\u2992\u2994\u2996\u2998'
 u'\u29d9\u29db\u29fd\u2e23\u2e25\u2e27\u2e29\u3009'
 u'\u300b\u300d\u300f\u3011\u3015\u3017\u3019\u301b'
 u'\u301e\u301f\ufd3f\ufe18\ufe36\ufe38\ufe3a\ufe3c'
 u'\ufe3e\ufe40\ufe42\ufe44\ufe48\ufe5a\ufe5c\ufe5e'
 u'\uff09\uff3d\uff5d\uff60\uff63')
 # This is the \p{Close_Punctuation} from Perl's perluniprops
 CURRENCY_SYM = text_type(u'$\xa2\xa3\xa4\xa5\u058f\u060b\u09f2\u09f3\u09fb'
 u'\u0af1\u0bf9\u0e3f\u17db\u20a0\u20a1\u20a2\u20a3'
 u'\u20a4\u20a5\u20a6\u20a7\u20a8\u20a9\u20aa\u20ab'
 u'\u20ac\u20ad\u20ae\u20af\u20b0\u20b1\u20b2\u20b3'
 u'\u20b4\u20b5\u20b6\u20b7\u20b8\u20b9\u20ba\ua838'
 u'\ufdfc\ufe69\uff04\uffe0\uffe1\uffe5\uffe6')
 
 # Pad spaces after opening punctuations.
 OPEN_PUNCT_RE = re.compile(u'([{}])'.format(OPEN_PUNCT)), r'1円 '
 # Pad spaces before closing punctuations.
 CLOSE_PUNCT_RE = re.compile(u'([{}])'.format(CLOSE_PUNCT)), r'1円 '
 # Pad spaces after currency symbols.
 CURRENCY_SYM_RE = re.compile(u'([{}])'.format(CURRENCY_SYM)), r'1円 '
 
 # Use for tokenizing URL-unfriendly characters: [:/?#]
 URL_FOE_1 = re.compile(r':(?!//)'), r' : ' # in perl s{:(?!//)}{ : }g;
 URL_FOE_2 = re.compile(r'\?(?!\S)'), r' ? ' # in perl s{\?(?!\S)}{ ? }g;
 # in perl: m{://} or m{\S+\.\S+/\S+} or s{/}{ / }g;
 URL_FOE_3 = re.compile(r'(:\/\/)[\S+\.\S+\/\S+][\/]'), ' / '
 URL_FOE_4 = re.compile(r' /'), r' / ' # s{ /}{ / }g;
 
 # Left/Right strip, i.e. remove heading/trailing spaces.
 # These strip regexes should NOT be used,
 # instead use str.lstrip(), str.rstrip() or str.strip() 
 # (They are kept for reference purposes to the original toktok.pl code) 
 LSTRIP = re.compile(r'^ +'), ''
 RSTRIP = re.compile(r'\s+$'),'\n' 
 # Merge multiple spaces.
 ONE_SPACE = re.compile(r' {2,}'), ' '
 
 TOKTOK_REGEXES = [NON_BREAKING, FUNKY_PUNCT_1, 
 URL_FOE_1, URL_FOE_2, URL_FOE_3, URL_FOE_4,
 AMPERCENT, TAB, PIPE,
 OPEN_PUNCT_RE, CLOSE_PUNCT_RE, 
 MULTI_COMMAS, COMMA_IN_NUM, FINAL_PERIOD_2,
 PROB_SINGLE_QUOTES, STUPID_QUOTES_1, STUPID_QUOTES_2,
 CURRENCY_SYM_RE, EN_EM_DASHES, MULTI_DASHES, MULTI_DOTS,
 FINAL_PERIOD_1, FINAL_PERIOD_2, ONE_SPACE]
 
 def tokenize(self, text, return_str=False):
 text = text_type(text) # Converts input string into unicode.
 for regexp, subsitution in self.TOKTOK_REGEXES:
 text = regexp.sub(subsitution, text)
 # Finally, strips heading and trailing spaces
 # and converts output string into unicode.
 text = text_type(text.strip()) 
 return text if return_str else text.split()

Is there a way to make the subtituition faster? E.g.

• Combine the chain of regexes into one super regex.
• Combine some of the regexes
• Coding it in Cython (but Cython regexes are slow, no?)
• Running the regex substitution in Julia and wrapping Julia code in Python

The use case for the tokenize() function usually takes a single input but if the same function is called 1,000,000,000 times, it's rather slow and the GIL is going to lock up the core and process each sentence at a time.

The aim of the question is to ask for ways to speed up a Python code that's made up of regex substitution, esp. when running the tokenize() function for 1,000,000,000+ times.

If Cython/Julia or any faster language + wrapper is suggested, it would be good if you give an one regex example of how the regex is written in Cython/Julia/Others and the suggestion on how the wrapper would look like.

Thanks in advance!