mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-29 11:26:28 +03:00
db55577c45
* Remove unicode declarations * Remove Python 3.5 and 2.7 from CI * Don't require pathlib * Replace compat helpers * Remove OrderedDict * Use f-strings * Set Cython compiler language level * Fix typo * Re-add OrderedDict for Table * Update setup.cfg * Revert CONTRIBUTING.md * Revert lookups.md * Revert top-level.md * Small adjustments and docs [ci skip]
25 lines
873 B
Python
25 lines
873 B
Python
from ...symbols import ORTH, LEMMA
|
|
|
|
|
|
_exc = {}
|
|
|
|
|
|
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]] = [exc_data]
|
|
|
|
|
|
TOKENIZER_EXCEPTIONS = _exc
|