mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 11:26:28 +03:00
c09d2fa25b
* luganda language extension * __init__.py changes * New enhancements * Lexical attribute changed * punctuaction and sentence additions * Remove comment header * Fix typos, reformat * reformated version * Add tokenizer test * Remove contractions from stop words * Format * Add Luganda to website Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
20 lines
569 B
Python
20 lines
569 B
Python
from ..char_classes import LIST_ELLIPSES, LIST_ICONS, HYPHENS
|
|
from ..char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA
|
|
|
|
_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
|