mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +03:00
41 lines
1.1 KiB
Python
41 lines
1.1 KiB
Python
# coding=utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from ..symbols import *
|
|
|
|
TOKENIZER_EXCEPTIONS = {}
|
|
|
|
ABBREVIATIONS = {
|
|
"ডঃ": [
|
|
{ORTH: "ডঃ", LEMMA: "ডক্টর"},
|
|
],
|
|
"ডাঃ": [
|
|
{ORTH: "ডাঃ", LEMMA: "ডাক্তার"},
|
|
],
|
|
"ড.": [
|
|
{ORTH: "ড.", LEMMA: "ডক্টর"},
|
|
],
|
|
"ডা.": [
|
|
{ORTH: "ডা.", LEMMA: "ডাক্তার"},
|
|
],
|
|
"মোঃ": [
|
|
{ORTH: "মোঃ", LEMMA: "মোহাম্মদ"},
|
|
],
|
|
"মো.": [
|
|
{ORTH: "মো.", LEMMA: "মোহাম্মদ"},
|
|
],
|
|
"সে.": [
|
|
{ORTH: "সে.", LEMMA: "সেলসিয়াস"},
|
|
],
|
|
"কি.মি": [
|
|
{ORTH: "কি.মি", LEMMA: "কিলোমিটার"},
|
|
{ORTH: "কি.মি.", LEMMA: "কিলোমিটার"},
|
|
],
|
|
"সে.মি": [
|
|
{ORTH: "সে.মি", LEMMA: "সেন্টিমিটার"},
|
|
{ORTH: "সে.মি.", LEMMA: "সেন্টিমিটার"},
|
|
],
|
|
}
|
|
|
|
TOKENIZER_EXCEPTIONS.update(ABBREVIATIONS)
|