explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 11:29:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Tidy up Bengali tokenizer exceptions

Browse Source
This commit is contained in:
ines 2017-05-08 22:29:49 +02:00
parent 73b577cb01
commit 614aa09582
1 changed files with 19 additions and 40 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

59
spacy/lang/bn/tokenizer_exceptions.py
View File

@ -3,45 +3,24 @@ from __future__ import unicode_literals
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"},
],
"কি.মি.": [
{ORTH: "কি.মি.", LEMMA: "কিলোমিটার"},
],
"কি.মি": [
{ORTH: "কি.মি", LEMMA: "কিলোমিটার"},
],
"সে.মি.": [
{ORTH: "সে.মি.", LEMMA: "সেন্টিমিটার"},
],
"সে.মি": [
{ORTH: "সে.মি", LEMMA: "সেন্টিমিটার"},
],
"মি.লি.": [
{ORTH: "মি.লি.", LEMMA: "মিলিলিটার"},
]
}
_exc = {}
TOKENIZER_EXCEPTIONS.update(ABBREVIATIONS)
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)]
TOKENIZER_EXCEPTIONS = dict(_exc)