spaCy/spacy/lang/it/punctuation.py

33 lines
929 B
Python
Raw Normal View History

# coding: utf8
from __future__ import unicode_literals
2020-03-25 14:28:12 +03:00
from ..punctuation import TOKENIZER_PREFIXES as BASE_TOKENIZER_PREFIXES
from ..char_classes import LIST_ELLIPSES, LIST_ICONS
from ..char_classes import ALPHA, HYPHENS, CONCAT_QUOTES
from ..char_classes import ALPHA_LOWER, ALPHA_UPPER
ELISION = "'"
2020-03-25 14:28:12 +03:00
_prefixes = [r"'[0-9][0-9]", r"[0-9]+°"] + BASE_TOKENIZER_PREFIXES
_infixes = (
LIST_ELLIPSES
+ LIST_ICONS
+ [
r"(?<=[0-9])[+\-\*^](?=[0-9-])",
r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
),
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])(?:{h})(?=[{al}])".format(a=ALPHA, h=HYPHENS, al=ALPHA_LOWER),
r"(?<=[{a}0-9])[:<>=\/](?=[{a}])".format(a=ALPHA),
2020-03-25 14:28:12 +03:00
r"(?<=[{a}][{el}])(?=[{a}0-9\"])".format(a=ALPHA, el=ELISION),
]
)
TOKENIZER_PREFIXES = _prefixes
TOKENIZER_INFIXES = _infixes