spaCy/spacy/lang/nb/punctuation.py
2018-01-24 12:28:29 +01:00

26 lines
919 B
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
"""Punctuation stolen from Danish"""
from __future__ import unicode_literals
from ..char_classes import LIST_ELLIPSES, LIST_ICONS
from ..char_classes import QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
from ..punctuation import TOKENIZER_SUFFIXES
_quotes = QUOTES.replace("'", '')
_infixes = (LIST_ELLIPSES + LIST_ICONS +
[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}])([{q}\)\]\(\[])(?=[\{a}])'.format(a=ALPHA, q=_quotes),
r'(?<=[{a}])--(?=[{a}])'.format(a=ALPHA)])
_suffixes = [suffix for suffix in TOKENIZER_SUFFIXES if suffix not in ["'s", "'S", "s", "S", r"\'"]]
_suffixes += [r"(?<=[^sSxXzZ])\'"]
TOKENIZER_INFIXES = _infixes
TOKENIZER_SUFFIXES = _suffixes