spaCy/spacy/lang/punctuation.py
ines a8e58e04ef Add symbols class to punctuation rules to handle emoji (see #1088)
Currently doesn't work for Hungarian, because of conflicts with the
custom punctuation rules. Also doesn't take multi-character emoji like
👩🏽‍💻 into account.
2017-05-27 17:57:10 +02:00

34 lines
1.2 KiB
Python
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# coding: utf8
from __future__ import unicode_literals
from .char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_CURRENCY
from .char_classes import LIST_ICONS, ALPHA_LOWER, ALPHA_UPPER, ALPHA, HYPHENS
from .char_classes import QUOTES, CURRENCY, UNITS
_prefixes = (['§', '%', '=', r'\+'] + LIST_PUNCT + LIST_ELLIPSES + LIST_QUOTES +
LIST_CURRENCY + LIST_ICONS)
_suffixes = (LIST_PUNCT + LIST_ELLIPSES + LIST_QUOTES + LIST_ICONS +
["'s", "'S", "s", "S"] +
[r'(?<=[0-9])\+',
r'(?<=°[FfCcKk])\.',
r'(?<=[0-9])(?:{})'.format(CURRENCY),
r'(?<=[0-9])(?:{})'.format(UNITS),
r'(?<=[0-9{}{}(?:{})])\.'.format(ALPHA_LOWER, r'%²\-\)\]\+', QUOTES),
r'(?<=[{a}][{a}])\.'.format(a=ALPHA_UPPER)])
_infixes = (LIST_ELLIPSES + LIST_ICONS +
[r'(?<=[0-9])[+\-\*^](?=[0-9-])',
r'(?<=[{}])\.(?=[{}])'.format(ALPHA_LOWER, ALPHA_UPPER),
r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
r'(?<=[{a}])[?";:=,.]*(?:{h})(?=[{a}])'.format(a=ALPHA, h=HYPHENS),
r'(?<=[{a}"])[:<>=/](?=[{a}])'.format(a=ALPHA)])
TOKENIZER_PREFIXES = _prefixes
TOKENIZER_SUFFIXES = _suffixes
TOKENIZER_INFIXES = _infixes