mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-27 18:36:36 +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
1.1 KiB
Python
25 lines
1.1 KiB
Python
from ...symbols import ORTH, LEMMA, POS, NORM, NOUN
|
||
|
||
|
||
_exc = {}
|
||
|
||
for exc_data in [
|
||
{ORTH: "вул.", LEMMA: "вулиця", NORM: "вулиця", POS: NOUN},
|
||
{ORTH: "ім.", LEMMA: "ім'я", NORM: "імені", POS: NOUN},
|
||
{ORTH: "просп.", LEMMA: "проспект", NORM: "проспект", POS: NOUN},
|
||
{ORTH: "бул.", LEMMA: "бульвар", NORM: "бульвар", POS: NOUN},
|
||
{ORTH: "пров.", LEMMA: "провулок", NORM: "провулок", POS: NOUN},
|
||
{ORTH: "пл.", LEMMA: "площа", NORM: "площа", POS: NOUN},
|
||
{ORTH: "г.", LEMMA: "гора", NORM: "гора", POS: NOUN},
|
||
{ORTH: "п.", LEMMA: "пан", NORM: "пан", POS: NOUN},
|
||
{ORTH: "м.", LEMMA: "місто", NORM: "місто", POS: NOUN},
|
||
{ORTH: "проф.", LEMMA: "професор", NORM: "професор", POS: NOUN},
|
||
{ORTH: "акад.", LEMMA: "академік", NORM: "академік", POS: NOUN},
|
||
{ORTH: "доц.", LEMMA: "доцент", NORM: "доцент", POS: NOUN},
|
||
{ORTH: "оз.", LEMMA: "озеро", NORM: "озеро", POS: NOUN},
|
||
]:
|
||
_exc[exc_data[ORTH]] = [exc_data]
|
||
|
||
|
||
TOKENIZER_EXCEPTIONS = _exc
|