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

70 lines
1.6 KiB
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,
CURRENCY,
LIST_CURRENCY,
LIST_ELLIPSES,
LIST_ICONS,
LIST_PUNCT,
LIST_QUOTES,
PUNCT,
UNITS,
)
# Punctuation adapted from Danish
_quotes = CONCAT_QUOTES.replace("'", "")
_list_punct = [x for x in LIST_PUNCT if x != "#"]
_list_icons = [x for x in LIST_ICONS if x != "°"]
_list_icons = [x.replace("\\u00B0", "") for x in _list_icons]
_list_quotes = [x for x in LIST_QUOTES if x != "\\'"]
_prefixes = (
["§", "%", "=", "—", "", r"\+(?![0-9])"]
+ _list_punct
+ LIST_ELLIPSES
+ LIST_QUOTES
+ LIST_CURRENCY
+ LIST_ICONS
)
_infixes = (
LIST_ELLIPSES
+ _list_icons
+ [
r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])[:<>=/](?=[{a}])".format(a=ALPHA),
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
r"(?<=[{a}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes),
r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA),
]
)
_suffixes = (
LIST_PUNCT
+ LIST_ELLIPSES
+ _list_quotes
+ _list_icons
+ ["—", ""]
+ [
r"(?<=[0-9])\+",
r"(?<=°[FfCcKk])\.",
r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
r"(?<=[0-9])(?:{u})".format(u=UNITS),
r"(?<=[{al}{e}{p}(?:{q})])\.".format(
al=ALPHA_LOWER, e=r"%²\-\+", q=_quotes, p=PUNCT
),
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
]
+ [r"(?<=[^sSxXzZ])'"]
)
TOKENIZER_PREFIXES = _prefixes
TOKENIZER_INFIXES = _infixes
TOKENIZER_SUFFIXES = _suffixes