mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-25 17:36:30 +03:00
e1f777b151
* don't split on a colon. Colon is used to attach suffixes for abbreviations * tokenize on any of LIST_HYPHENS (except a single hyphen), not just on -- * simplify infix rules by merging similar rules
33 lines
913 B
Python
33 lines
913 B
Python
# coding: utf8
|
||
from __future__ import unicode_literals
|
||
|
||
from ..char_classes import LIST_ELLIPSES, LIST_ICONS, LIST_HYPHENS
|
||
from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
|
||
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
|