65 lines
1.5 KiB
Python
65 lines
1.5 KiB
Python
from ..char_classes import (
|
||
ALPHA,
|
||
ALPHA_LOWER,
|
||
ALPHA_UPPER,
|
||
CONCAT_QUOTES,
|
||
CURRENCY,
|
||
LIST_ELLIPSES,
|
||
LIST_ICONS,
|
||
LIST_PUNCT,
|
||
LIST_QUOTES,
|
||
LIST_UNITS,
|
||
PUNCT,
|
||
merge_chars,
|
||
)
|
||
from ..punctuation import TOKENIZER_PREFIXES as BASE_TOKENIZER_PREFIXES
|
||
|
||
_prefixes = [",,"] + BASE_TOKENIZER_PREFIXES
|
||
|
||
|
||
# Copied from `de` package. Main purpose is to ensure that hyphens are not
|
||
# split on.
|
||
|
||
_quotes = CONCAT_QUOTES.replace("'", "")
|
||
|
||
_infixes = (
|
||
LIST_ELLIPSES
|
||
+ LIST_ICONS
|
||
+ [
|
||
r"(?<=[{}])\.(?=[{}])".format(ALPHA_LOWER, 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),
|
||
]
|
||
)
|
||
|
||
|
||
_list_units = [u for u in LIST_UNITS if u != "%"]
|
||
_units = merge_chars(" ".join(_list_units))
|
||
|
||
_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"(?<=[0-9{al}{e}{p}(?:{q})])\.".format(
|
||
al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES, p=PUNCT
|
||
),
|
||
r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
|
||
]
|
||
)
|
||
|
||
|
||
TOKENIZER_PREFIXES = _prefixes
|
||
TOKENIZER_INFIXES = _infixes
|
||
TOKENIZER_SUFFIXES = _suffixes
|