spaCy/spacy/lang/bn/tokenizer_exceptions.py

48 lines
1.3 KiB
Python
Raw Normal View History

# coding=utf-8
from __future__ import unicode_literals
2017-05-08 20:29:04 +00:00
from ...symbols import ORTH, LEMMA
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"},
],
2017-03-10 04:45:01 +00:00
"কি.মি.": [
{ORTH: "কি.মি.", LEMMA: "কিলোমিটার"},
],
2017-03-10 04:45:01 +00:00
"কি.মি": [
{ORTH: "কি.মি", LEMMA: "কিলোমিটার"},
],
2017-03-10 04:45:01 +00:00
"সে.মি.": [
2017-03-08 11:27:12 +00:00
{ORTH: "সে.মি.", LEMMA: "সেন্টিমিটার"},
],
2017-03-10 04:45:01 +00:00
"সে.মি": [
{ORTH: "সে.মি", LEMMA: "সেন্টিমিটার"},
],
2017-03-08 11:29:39 +00:00
"মি.লি.": [
{ORTH: "মি.লি.", LEMMA: "মিলিলিটার"},
]
}
TOKENIZER_EXCEPTIONS.update(ABBREVIATIONS)