mirror of https://github.com/explosion/spaCy.git
27 lines
927 B
Python
27 lines
927 B
Python
# coding=utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from ...symbols import ORTH, LEMMA
|
|
|
|
|
|
_exc = {}
|
|
|
|
|
|
for exc_data in [
|
|
{ORTH: "ডঃ", LEMMA: "ডক্টর"},
|
|
{ORTH: "ডাঃ", LEMMA: "ডাক্তার"},
|
|
{ORTH: "ড.", LEMMA: "ডক্টর"},
|
|
{ORTH: "ডা.", LEMMA: "ডাক্তার"},
|
|
{ORTH: "মোঃ", LEMMA: "মোহাম্মদ"},
|
|
{ORTH: "মো.", LEMMA: "মোহাম্মদ"},
|
|
{ORTH: "সে.", LEMMA: "সেলসিয়াস"},
|
|
{ORTH: "কি.মি.", LEMMA: "কিলোমিটার"},
|
|
{ORTH: "কি.মি", LEMMA: "কিলোমিটার"},
|
|
{ORTH: "সে.মি.", LEMMA: "সেন্টিমিটার"},
|
|
{ORTH: "সে.মি", LEMMA: "সেন্টিমিটার"},
|
|
{ORTH: "মি.লি.", LEMMA: "মিলিলিটার"}]:
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
|
|
|
|
|
TOKENIZER_EXCEPTIONS = _exc
|