mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
a8e58e04ef
Currently doesn't work for Hungarian, because of conflicts with the
custom punctuation rules. Also doesn't take multi-character emoji like
👩🏽💻 into account.
34 lines
1.2 KiB
Python
34 lines
1.2 KiB
Python
# 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
|