mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-16 14:47:16 +03:00
27 lines
490 B
Python
27 lines
490 B
Python
|
# coding: utf8
|
||
|
|
from __future__ import unicode_literals
|
||
|
|
|
||
|
|
from ...symbols import ORTH, LEMMA, NORM, PRON_LEMMA
|
||
|
|
|
||
|
|
|
||
|
|
_exc = {}
|
||
|
|
|
||
|
|
|
||
|
|
for exc_data in [
|
||
|
|
{ORTH: "ት/ቤት", LEMMA: "ትምህርት ቤት"},
|
||
|
|
{ORTH: "ወ/ሮ", LEMMA: PRON_LEMMA, NORM: "ወይዘሮ"},
|
||
|
|
{ORTH: "ወ/ሪ", LEMMA: PRON_LEMMA, NORM: "ወይዘሪት"},
|
||
|
|
|
||
|
|
]:
|
||
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
||
|
|
|
||
|
|
|
||
|
|
for orth in [
|
||
|
|
"ዓ.ም.",
|
||
|
|
"ኪ.ሜ.",
|
||
|
|
]:
|
||
|
|
_exc[orth] = [{ORTH: orth}]
|
||
|
|
|
||
|
|
|
||
|
|
TOKENIZER_EXCEPTIONS = _exc
|