2017-03-12 15:07:28 +03:00
|
|
|
# coding: utf8
|
2017-02-28 18:07:14 +03:00
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
2017-05-08 23:29:04 +03:00
|
|
|
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, UNITS
|
|
|
|
|
from ..char_classes import ALPHA_LOWER, ALPHA_UPPER, ALPHA, HYPHENS, QUOTES
|
2017-05-09 01:01:52 +03:00
|
|
|
|
|
|
|
|
|
|
|
|
|
_currency = r"\$|¢|£|€|¥|฿|৳"
|
|
|
|
|
_quotes = QUOTES.replace("'", '')
|
|
|
|
|
_list_punct = LIST_PUNCT + '। ॥'.strip().split()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
_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('|'.join([ALPHA_LOWER, r'%²\-\)\]\+', QUOTES]), _currency)])
|
|
|
|
|
|
|
|
|
|
_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
|
