spaCy/spacy/lang/punctuation.py

47 lines
1.3 KiB
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.

from .char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_CURRENCY
from .char_classes import LIST_ICONS, HYPHENS, CURRENCY, UNITS
from .char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA, PUNCT
TOKENIZER_PREFIXES = (
["§", "%", "=", "", "", r"\+(?![0-9])"]
+ LIST_PUNCT
+ LIST_ELLIPSES
+ LIST_QUOTES
+ LIST_CURRENCY
+ LIST_ICONS
)
TOKENIZER_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}{p}(?:{q})])\.".format(
al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES, p=PUNCT
),
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
]
)
TOKENIZER_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})(?=[{a}])".format(a=ALPHA, h=HYPHENS),
r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
]
)