2017-03-04 09:20:08 +03:00
|
|
|
# coding=utf-8
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
2017-05-08 23:29:04 +03:00
|
|
|
from ...symbols import ORTH, LEMMA
|
2017-03-04 09:20:08 +03:00
|
|
|
|
|
|
|
|
|
2017-05-08 23:29:49 +03:00
|
|
|
_exc = {}
|
2017-03-04 09:20:08 +03:00
|
|
|
|
2017-05-08 23:29:49 +03:00
|
|
|
|
|
|
|
|
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]] = [dict(exc_data)]
|
|
|
|
|
|
|
|
|
|
|
2017-10-31 23:05:29 +03:00
|
|
|
TOKENIZER_EXCEPTIONS = _exc
|
