mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 12:18:04 +03:00
1a944e5976
Improve Italian tokenization for UD_Italian-ISDT.
40 lines
951 B
Python
40 lines
951 B
Python
# coding: utf8
|
||
from __future__ import unicode_literals
|
||
|
||
from ..punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
|
||
from ..char_classes import LIST_ELLIPSES, LIST_ICONS
|
||
from ..char_classes import ALPHA, HYPHENS, CONCAT_QUOTES
|
||
from ..char_classes import ALPHA_LOWER, ALPHA_UPPER
|
||
|
||
|
||
ELISION = "'’"
|
||
|
||
|
||
_prefixes = (
|
||
[
|
||
r"'[0-9][0-9]",
|
||
r"[0-9]+°",
|
||
|
||
]
|
||
+ TOKENIZER_PREFIXES
|
||
)
|
||
|
||
|
||
_infixes = (
|
||
LIST_ELLIPSES
|
||
+ LIST_ICONS
|
||
+ [
|
||
r"(?<=[0-9])[+\-\*^](?=[0-9-])",
|
||
r"(?<=[{al}{q}])\.(?=[{au}{q}])".format(
|
||
al=ALPHA_LOWER, au=ALPHA_UPPER, q=CONCAT_QUOTES
|
||
),
|
||
r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}])(?:{h})(?=[{al}])".format(a=ALPHA, h=HYPHENS, al=ALPHA_LOWER),
|
||
r"(?<=[{a}0-9])[:<>=\/](?=[{a}])".format(a=ALPHA),
|
||
r"(?<=[{a}][{el}])(?=[{a}0-9\"])".format(a=ALPHA, el=ELISION)
|
||
]
|
||
)
|
||
|
||
TOKENIZER_PREFIXES = _prefixes
|
||
TOKENIZER_INFIXES = _infixes
|