spaCy/spacy/bn/tokenizer_exceptions.py

37 lines
926 B
Python
Raw Normal View History

# 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"},
],
}
TOKENIZER_EXCEPTIONS.update(ABBREVIATIONS)