Compare commits

...

6 Commits

Author SHA1 Message Date
Lise dfe27516d9 extend abbreviations list in Faroese tokenizer exceptions (#13366)
tests / Validate (push) Has been cancelled
tests / Test (macos-latest, 3.11) (push) Has been cancelled
tests / Test (macos-latest, 3.12) (push) Has been cancelled
tests / Test (macos-latest, 3.8) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.12) (push) Has been cancelled
tests / Test (ubuntu-latest, 3.9) (push) Has been cancelled
tests / Test (windows-latest, 3.10) (push) Has been cancelled
tests / Test (windows-latest, 3.12) (push) Has been cancelled
tests / Test (windows-latest, 3.7) (push) Has been cancelled
2024-03-25 15:36:11 +01:00
Sofie Van Landeghem c32c1289a9 Merge pull request #13282 from danieldk/maintenance/merge-main-into-develop-20240129
Merge main into `develop`
2024-01-30 13:51:33 +01:00
Daniël de Kok a36474600f Merge remote-tracking branch 'upstream/master' into maintenance/merge-main-into-develop-20240129 2024-01-29 14:31:09 +01:00
Daniël de Kok b25927251d Merge pull request #13271 from danieldk/maintenance/develop-merge-master-20240125
Merge `master` into `develop`
2024-01-26 12:50:51 +01:00
Daniël de Kok e1c1889acf Merge remote-tracking branch 'upstream/master' into develop 2024-01-25 16:09:51 +01:00
Adriane Boyd 7174588155 Merge pull request #13107 from adrianeboyd/chore/update-develop-from-master-v3.8-1
Update develop from master for v3.8
2023-11-05 16:12:08 +01:00
+67
View File
@@ -5,7 +5,9 @@ from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = {}
for orth in [
"Chr.",
"apr.",
"atm.",
"aug.",
"avgr.",
"árg.",
@@ -15,21 +17,53 @@ for orth in [
"blaðkv.",
"blm.",
"blaðm.",
"blaðstj.",
"blkv.",
"blm.",
"bls.",
"blstj.",
"blaðstj.",
"cand.",
"dagf.",
"des.",
"dkr.",
"dr.",
"e.Kr.",
"eint.",
"ex.",
"exam.",
"f.",
"f.Kr.",
"fa.",
"fam.",
"feb.",
"febr.",
"ff.",
"fl.",
"form.",
"frí.",
"fyrrv.",
"góðk.",
"h.m.",
"hósd.",
"innt.",
"jan.",
"kap.",
"kgl.",
"kl.",
"kr.",
"leyg.",
"m.a.",
"mðr.",
"m.o.",
"m.ø.",
"mia.",
"mik.",
"min.",
"mió.",
"mán.",
"mðr.",
"nov.",
"nr.",
"nto.",
"nov.",
@@ -43,12 +77,25 @@ for orth in [
"o.o.",
"o.s.fr.",
"o.tíl.",
"o.u.",
"o.ø.",
"okt.",
"omf.",
"ph.d.",
"phil.",
"pr.",
"pst.",
"ritstj.",
"s.",
"sb.",
"sbr.",
"sbrt.",
"sek.",
"sep.",
"sept.",
"serst.",
"smb.",
"smbr.",
"sms.",
"smst.",
"smb.",
@@ -58,14 +105,25 @@ for orth in [
"sept.",
"spf.",
"spsk.",
"stk.",
"sunnud.",
"t.",
"t.d.",
"t.e.",
"t.o.v.",
"t.s.",
"t.s.s.",
"tlf.",
"t.v.s",
"t.v.s.",
"tel.",
"tils.",
"tlf.",
"tsk.",
"t.o.v.",
"t.d.",
"tús.",
"týs.",
"uml.",
"ums.",
"uppl.",
@@ -75,13 +133,22 @@ for orth in [
"útl.",
"útr.",
"vanl.",
"upprfr.",
"v.",
"v.h.",
"v.m.",
"v.ø.o.",
"vanl.",
"viðm.",
"viðv.",
"vm.",
"v.m.",
"á.Kr.",
"árg.",
"ávís.",
"útg.",
"útl.",
"útr.",
]:
_exc[orth] = [{ORTH: orth}]
capitalized = orth.capitalize()