spaCy/spacy/lang/hu/punctuation.py

36 lines
1.2 KiB
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
from __future__ import unicode_literals
2017-05-09 01:01:59 +03:00
from ..punctuation import TOKENIZER_INFIXES
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
from ..char_classes import QUOTES, UNITS, ALPHA, ALPHA_LOWER, ALPHA_UPPER
2017-05-08 16:49:56 +03:00
2017-05-09 01:01:59 +03:00
_currency = r'\$|¢|£|€|¥|฿'
_quotes = QUOTES.replace("'", '')
_prefixes = ([r'\+'] + LIST_PUNCT + LIST_ELLIPSES + LIST_QUOTES)
_suffixes = (LIST_PUNCT + LIST_ELLIPSES + LIST_QUOTES +
[r'(?<=[0-9])\+',
r'(?<=°[FfCcKk])\.',
r'(?<=[0-9])(?:{})'.format(_currency),
r'(?<=[0-9])(?:{})'.format(UNITS),
r'(?<=[{}{}{}(?:{})])\.'.format(ALPHA_LOWER, r'%²\-\)\]\+', QUOTES, _currency),
r'(?<=[{})])-e'.format(ALPHA_LOWER)])
_infixes = (LIST_ELLIPSES +
[r'(?<=[{}])\.(?=[{}])'.format(ALPHA_LOWER, ALPHA_UPPER),
r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
r'(?<=[{a}"])[:<>=](?=[{a}])'.format(a=ALPHA),
r'(?<=[{a}])--(?=[{a}])'.format(a=ALPHA),
r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
r'(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])'.format(a=ALPHA, q=_quotes)])
TOKENIZER_PREFIXES = _prefixes
TOKENIZER_SUFFIXES = _suffixes
TOKENIZER_INFIXES = _infixes