spaCy/spacy/lang/fo/tokenizer_exceptions.py
Lise b6e022381d
Feature/nn and fo language extensions (#13116)
* add language extensions for norwegian nynorsk and faroese

* update docstring for nn/examples.py

* use relative imports

* add fo and nn tokenizers to pytest fixtures

* add unittests for fo and nn and fix bug in nn

* remove module docstring from fo/__init__.py

* add comments about example sentences' origin

* add license information to faroese data credit

* format unittests using black

* add __init__ files to test/lang/nn and tests/lang/fo

* fix import order and use relative imports in fo/__nit__.py and nn/__init__.py

* Make the tests a bit more compact

* Add fo and nn to website languages

* Add note about jul.

* Add "jul." as exception

---------

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
2023-11-20 07:49:59 +01:00

91 lines
1.3 KiB
Python

from ...symbols import ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = {}
for orth in [
"apr.",
"aug.",
"avgr.",
"árg.",
"ávís.",
"beinl.",
"blkv.",
"blaðkv.",
"blm.",
"blaðm.",
"bls.",
"blstj.",
"blaðstj.",
"des.",
"eint.",
"febr.",
"fyrrv.",
"góðk.",
"h.m.",
"innt.",
"jan.",
"kl.",
"m.a.",
"mðr.",
"mió.",
"nr.",
"nto.",
"nov.",
"nút.",
"o.a.",
"o.a.m.",
"o.a.tíl.",
"o.fl.",
"ff.",
"o.m.a.",
"o.o.",
"o.s.fr.",
"o.tíl.",
"o.ø.",
"okt.",
"omf.",
"pst.",
"ritstj.",
"sbr.",
"sms.",
"smst.",
"smb.",
"sb.",
"sbrt.",
"sp.",
"sept.",
"spf.",
"spsk.",
"t.e.",
"t.s.",
"t.s.s.",
"tlf.",
"tel.",
"tsk.",
"t.o.v.",
"t.d.",
"uml.",
"ums.",
"uppl.",
"upprfr.",
"uppr.",
"útg.",
"útl.",
"útr.",
"vanl.",
"v.",
"v.h.",
"v.ø.o.",
"viðm.",
"viðv.",
"vm.",
"v.m.",
]:
_exc[orth] = [{ORTH: orth}]
capitalized = orth.capitalize()
_exc[capitalized] = [{ORTH: capitalized}]
TOKENIZER_EXCEPTIONS = update_exc(BASE_EXCEPTIONS, _exc)