Files
INTUIA/Programa final/spacy/lang/ar/punctuation.py
T
2026-03-15 13:27:50 +00:00

24 lines
463 B
Python

from ..char_classes import (
ALPHA_UPPER,
CURRENCY,
LIST_ELLIPSES,
LIST_PUNCT,
LIST_QUOTES,
UNITS,
)
_suffixes = (
LIST_PUNCT
+ LIST_ELLIPSES
+ LIST_QUOTES
+ [
r"(?<=[0-9])\+",
# Arabic is written from Right-To-Left
r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
r"(?<=[0-9])(?:{u})".format(u=UNITS),
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
]
)
TOKENIZER_SUFFIXES = _suffixes