36 lines
863 B
Python
36 lines
863 B
Python
|
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
|