spaCy/spacy/lang/punctuation.py

51 lines
1.3 KiB
Python
Raw Normal View History

2017-03-12 15:07:28 +03:00
# coding: utf8
2016-12-08 21:46:43 +03:00
from __future__ import unicode_literals
from .char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_CURRENCY, LIST_ICONS
from .char_classes import HYPHENS
from .char_classes import CURRENCY, UNITS
from .char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA
_prefixes = (
["§", "%", "=", r"\+(?![0-9])"]
+ 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])(?:{c})".format(c=CURRENCY),
r"(?<=[0-9])(?:{u})".format(u=UNITS),
r"(?<=[0-9{al}{e}(?:{q})])\.".format(al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES),
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
]
)
_infixes = (
LIST_ELLIPSES
+ LIST_ICONS
+ [
r"(?<=[0-9])[+\-\*^](?=[0-9-])",
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
r'(?<=[{a}])(?:{h})(?=[{a}])'.format(a=ALPHA, h=HYPHENS),
r'(?<=[{a}])[:<>=/](?=[{a}])'.format(a=ALPHA),
]
)
2017-05-09 01:00:46 +03:00
TOKENIZER_PREFIXES = _prefixes
TOKENIZER_SUFFIXES = _suffixes
TOKENIZER_INFIXES = _infixes