spaCy/spacy/lang/lb/punctuation.py
Peter Gilles 428887b8f2 Initial commit: New language Luxembourgish (lb) (#4424)
* new language: Luxembourgish (lb)

* update

* update

* Update and rename .github/CONTRIBUTOR_AGREEMENT.md to .github/contributors/PeterGilles.md

* Update and rename .github/contributors/PeterGilles.md to .github/CONTRIBUTOR_AGREEMENT.md

* Update norm_exceptions.py

* Delete README.md

* moved test_lemma.py

* deactivated 'lemma_lookup = LOOKUP'

* update

* Update conftest.py

* update

* tests updated

* import unicode_literals

* Update spacy/tests/lang/lb/test_text.py

Co-Authored-By: Ines Montani <ines@ines.io>

* Create PeterGilles.md
2019-10-14 12:27:50 +02:00

25 lines
710 B
Python

# coding: utf8
from __future__ import unicode_literals
from ..char_classes import LIST_ELLIPSES, LIST_ICONS
from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
_quotes = CONCAT_QUOTES.replace("'", "")
_infixes = (
LIST_ELLIPSES
+ LIST_ICONS
+ [
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=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),
r"(?<=[0-9])-(?=[0-9])",
]
)
TOKENIZER_INFIXES = _infixes