mirror of
https://github.com/explosion/spaCy.git
synced 2025-11-04 09:57:26 +03:00
a7ee4b6f17
- added some tests for tokenization issues - fixed some issues with tokenization of words with hyphen infix - rewrote the "tokenizer_exceptions.py" file (stemming from the German version)
24 lines
704 B
Python
24 lines
704 B
Python
# coding: utf8
|
||
from __future__ import unicode_literals
|
||
|
||
from ..char_classes import LIST_ELLIPSES, LIST_ICONS
|
||
from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
|
||
|
||
ELISION = " ' ’ ".strip().replace(" ", "")
|
||
|
||
_infixes = (
|
||
LIST_ELLIPSES
|
||
+ LIST_ICONS
|
||
+ [
|
||
r"(?<=[{a}][{el}])(?=[{a}])".format(a=ALPHA, el=ELISION),
|
||
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}])--(?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[0-9])-(?=[0-9])",
|
||
]
|
||
)
|
||
|
||
TOKENIZER_INFIXES = _infixes
|