mirror of https://github.com/explosion/spaCy.git
27 lines
602 B
Python
27 lines
602 B
Python
from ..char_classes import (
|
|
ALPHA,
|
|
ALPHA_LOWER,
|
|
ALPHA_UPPER,
|
|
CONCAT_QUOTES,
|
|
HYPHENS,
|
|
LIST_ELLIPSES,
|
|
LIST_ICONS,
|
|
)
|
|
|
|
_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}0-9])(?:{h})(?=[{a}])".format(a=ALPHA, h=HYPHENS),
|
|
r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA),
|
|
]
|
|
)
|
|
|
|
|
|
TOKENIZER_INFIXES = _infixes
|