Files
wehub-resource-sync f877c37fc6
tests / Test (macos-latest, 3.14) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.10) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.11) (push) Has been cancelled
tests / Test (windows-latest, 3.13) (push) Has been cancelled
tests / Test (windows-latest, 3.14) (push) Has been cancelled
tests / Validate (push) Has been cancelled
tests / Test (macos-latest, 3.10) (push) Has been cancelled
tests / Test (macos-latest, 3.11) (push) Has been cancelled
tests / Test (macos-latest, 3.12) (push) Has been cancelled
tests / Test (macos-latest, 3.13) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.12) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.13) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.14) (push) Has been cancelled
tests / Test (windows-latest, 3.10) (push) Has been cancelled
tests / Test (windows-latest, 3.11) (push) Has been cancelled
tests / Test (windows-latest, 3.12) (push) Has been cancelled
universe validation / Validate (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:37:51 +08:00

36 lines
863 B
Python
Raw Permalink 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 (
ALPHA,
ALPHA_LOWER,
ALPHA_UPPER,
CONCAT_QUOTES,
LIST_ELLIPSES,
LIST_HYPHENS,
LIST_ICONS,
)
from ..punctuation import TOKENIZER_SUFFIXES
_quotes = CONCAT_QUOTES.replace("'", "")
DASHES = "|".join(x for x in LIST_HYPHENS if x != "-")
_infixes = (
LIST_ELLIPSES
+ LIST_ICONS
+ [
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes),
r"(?<=[{a}])(?:{d})(?=[{a}])".format(a=ALPHA, d=DASHES),
r"(?<=[{a}0-9])[<>=/](?=[{a}])".format(a=ALPHA),
]
)
_suffixes = [
suffix
for suffix in TOKENIZER_SUFFIXES
if suffix not in ["'s", "'S", "s", "S", r"\'"]
]
TOKENIZER_INFIXES = _infixes
TOKENIZER_SUFFIXES = _suffixes