spaCy/spacy/lang/tt/punctuation.py

24 lines
836 B
Python
Raw Normal View History

# coding: utf8
from __future__ import unicode_literals
from ..char_classes import ALPHA, ALPHA_LOWER, ALPHA_UPPER, QUOTES, HYPHENS
from ..char_classes import LIST_ELLIPSES, LIST_ICONS
_hyphens_no_dash = HYPHENS.replace("-", "").strip("|").replace("||", "")
_infixes = (
LIST_ELLIPSES
+ LIST_ICONS
+ [
r"(?<=[{}])\.(?=[{}])".format(ALPHA_LOWER, ALPHA_UPPER),
r"(?<=[{a}])[,!?/\(\)]+(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}{q}])[:<>=](?=[{a}])".format(a=ALPHA, q=QUOTES),
r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])".format(a=ALPHA, q=QUOTES),
r'(?<=[{a}])[?";:=,.]*(?:{h})(?=[{a}])'.format(a=ALPHA, h=_hyphens_no_dash),
r"(?<=[0-9])-(?=[0-9])",
]
)
TOKENIZER_INFIXES = _infixes