26 lines
970 B
Python
26 lines
970 B
Python
|
from ...symbols import NORM, ORTH
|
||
|
|
from ...util import update_exc
|
||
|
|
from ..tokenizer_exceptions import BASE_EXCEPTIONS
|
||
|
|
|
||
|
|
_exc = {}
|
||
|
|
|
||
|
|
|
||
|
|
for exc_data in [
|
||
|
|
{ORTH: "ডঃ", NORM: "ডক্টর"},
|
||
|
|
{ORTH: "ডাঃ", NORM: "ডাক্তার"},
|
||
|
|
{ORTH: "ড.", NORM: "ডক্টর"},
|
||
|
|
{ORTH: "ডা.", NORM: "ডাক্তার"},
|
||
|
|
{ORTH: "মোঃ", NORM: "মোহাম্মদ"},
|
||
|
|
{ORTH: "মো.", NORM: "মোহাম্মদ"},
|
||
|
|
{ORTH: "সে.", NORM: "সেলসিয়াস"},
|
||
|
|
{ORTH: "কি.মি.", NORM: "কিলোমিটার"},
|
||
|
|
{ORTH: "কি.মি", NORM: "কিলোমিটার"},
|
||
|
|
{ORTH: "সে.মি.", NORM: "সেন্টিমিটার"},
|
||
|
|
{ORTH: "সে.মি", NORM: "সেন্টিমিটার"},
|
||
|
|
{ORTH: "মি.লি.", NORM: "মিলিলিটার"},
|
||
|
|
]:
|
||
|
|
_exc[exc_data[ORTH]] = [exc_data]
|
||
|
|
|
||
|
|
|
||
|
|
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)
|