From c0e9f252b4a598cd6ecfb74fdc8c7fb9e2c6d48d Mon Sep 17 00:00:00 2001 From: Jack Rueter Date: Sat, 16 Nov 2024 21:50:25 +0200 Subject: [PATCH] more words for 2013 NT --- src/fst/morphology/affixes/adjectives.lexc | 2 +- src/fst/morphology/affixes/nouns.lexc | 56 +++++- src/fst/morphology/affixes/pronouns.lexc | 15 +- src/fst/morphology/affixes/verbs.lexc | 37 +++- src/fst/morphology/root.lexc | 26 ++- src/fst/morphology/stems/adjectives.lexc | 2 + src/fst/morphology/stems/adverbs.lexc | 17 ++ src/fst/morphology/stems/nouns_newwords.lexc | 182 +++++++++++------- .../stems/propernouns_newwords.lexc | 22 +++ src/fst/morphology/stems/verbs.lexc | 3 +- src/fst/morphology/stems/verbs_newwords.lexc | 14 +- 11 files changed, 274 insertions(+), 102 deletions(-) diff --git a/src/fst/morphology/affixes/adjectives.lexc b/src/fst/morphology/affixes/adjectives.lexc index 6ec7c591..7ebae546 100644 --- a/src/fst/morphology/affixes/adjectives.lexc +++ b/src/fst/morphology/affixes/adjectives.lexc @@ -87,7 +87,7 @@ LEXICON A_VEDEKAZ !!≈ * **@CODE@** = vedekaz:vedeka LEXICON A_SEIBAZ !!≈ * **@CODE@** = seibaz:seib N_SEIBAZ ; -+Comp:ha%>mb N_POIG ; ++Comp:he%>mb N_POIG ;!CHECKME armhemb LEXICON A_CIPUINE !!≈ * **@CODE@** = cipuine:cipu N_CIPUINE ; diff --git a/src/fst/morphology/affixes/nouns.lexc b/src/fst/morphology/affixes/nouns.lexc index 1c53aaf8..3f3f8f3b 100644 --- a/src/fst/morphology/affixes/nouns.lexc +++ b/src/fst/morphology/affixes/nouns.lexc @@ -269,13 +269,14 @@ R ; ! xxx check : PL-OBLIQUE ; LEXICON N_POIG ! poig:poig -! _a/an/Q/ha/id +! _a/an/ad/ha/id !Sg+Nom/Sg+Gen/Sg+Par/Sg+Ill/Pl+Par !!€gt-norm: Noun ' / ' !!€ poig: poig+N+Sg+Nom !!€ poigan: poig+N+Sg+Gen !!€ poigid: poig+N+Pl+Par : SG-NOM-SUF ; ++Sg+Ill:ha K ; :a SG-OBLIQUE ; R ; ! xxx check ! Plural @@ -496,6 +497,21 @@ R ; ! xxx check :me PL-ACC-SUF ; :m PL-OBLIQUE ; +LEXICON N_SUEDAEIN ! südäin:südä +!!€gt-norm: Noun ' / ' +!!€ südäin: südäin+N+Sg+Nom +!!€ südäimen: südäin+N+Sg+Gen +!!€ südänt: südäin+N+Sg+Par +!!€ südäid: südäin+N+Pl+Par +:in SG-NOM-SUF ; +:n SG-PAR-SUF_t ; +:ime SG-OBLIQUE ; +R ; ! xxx check +! Plural +:ime PL-NOM-SUF ; +:ime PL-ACC-SUF ; +:im PL-OBLIQUE ; + LEXICON N_LUMI ! lumi:lu !!€gt-norm: Noun ' / ' !!€ : +N+Sg+Nom @@ -557,13 +573,13 @@ R ; ! xxx check :ja PL-ACC-SUF ; :j PL-OBLIQUE ; -LEXICON N_KEL1 !kel':kel +LEXICON N_KEL1 !kelʼ:kel !!€gt-norm: Noun ' / ' !!€ : +N+Sg+Nom !!€ n: +N+Sg+Gen !!€ d: +N+Pl+Par -:' SG-NOM-SUF ; -:' SG-PAR-SUF_t ; +:ʼ SG-NOM-SUF ; +:ʼ SG-PAR-SUF_t ; :%>e SG-OBLIQUE ; R ; ! xxx check ! Plural @@ -645,12 +661,40 @@ R ; ! xxx check : PL-ACC-SUF ; : PL-OBLIQUE ; -LEXICON N_VIDENZ1 ! videnz':viden (-den, -t, -zid) +LEXICON N_1/in/id/ihe/id ! papʼ:pap +!!€gt-norm: Noun ' / ' +!!€ papʼ: +N+Sg+Nom +!!€ papin: +N+Sg+Gen +!!€ papid: +N+Pl+Par +:ʼ SG-NOM-SUF ; ++Err/Orth-no-pal: SG-NOM-SUF ; +:i SG-OBLIQUE ; +R ; ! xxx check +! Plural +:i PL-NOM-SUF ; +:i PL-ACC-SUF ; +:i PL-OBLIQUE ; + +LEXICON N_1/en/ed/ehe/id ! apʼ:ap +!!€gt-norm: Noun ' / ' +!!€ papʼ: +N+Sg+Nom +!!€ papin: +N+Sg+Gen +!!€ papid: +N+Pl+Par +:ʼ SG-NOM-SUF ; ++Err/Orth-no-pal: SG-NOM-SUF ; +:e SG-OBLIQUE ; +R ; ! xxx check +! Plural +:e PL-NOM-SUF ; +:e PL-ACC-SUF ; +:i PL-OBLIQUE ; + +LEXICON N_VIDENZ1 ! videnzʼ:viden (-den, -t, -zid) !!€gt-norm: Noun ' / ' !!€ : +N+Sg+Nom !!€ n: +N+Sg+Gen !!€ d: +N+Pl+Par -:z' SG-NOM-SUF ; +:zʼ SG-NOM-SUF ; : SG-PAR-SUF_t ; :de SG-OBLIQUE ; R ; ! xxx check diff --git a/src/fst/morphology/affixes/pronouns.lexc b/src/fst/morphology/affixes/pronouns.lexc index c86b5082..6f43e850 100644 --- a/src/fst/morphology/affixes/pronouns.lexc +++ b/src/fst/morphology/affixes/pronouns.lexc @@ -73,6 +73,7 @@ LEXICON PersSg1 +Pers+Sg1+Par:dai K ; +Pers+Sg1:u ACC-SUF ;!is this distinguishable at morphosyntactic level better than later? 20230620 !+Pers+Sg1:u ALL-SUF ;! ?minule does this exist ++Pers+Sg1+Ade:ai K ;! minai +Pers+Sg1+All:ei K ;! minei ?Dat +Pers+Sg1:u OBLIQUE_CASES_FOR_PRONOUNS ; ! minunnoks @@ -81,6 +82,7 @@ LEXICON PersSg2 +Pers+Sg2+Nom:ä NOM-SUF ; +Pers+Sg2+Par:dai K ; +Pers+Sg2:u ACC-SUF ; ++Pers+Sg2+Ade:ai K ;! sinai +Pers+Sg2+All:ei K ; +Pers+Sg2:u OBLIQUE_CASES_FOR_PRONOUNS ; ! sinunnoks.. @@ -165,17 +167,20 @@ se+Pron+Dem+Sg+Par:sidä K ; LEXICON NEG-PRON !! @LEXNAME@ split in Nom Gen Par niken+Pron+Neg+Sg+Nom:niken K ; -niken+Pron+Neg+Sg+Gen:nikenen K ; +niken+Pron+Neg+Sg:nikene OBLIQUE_CASES_FOR_PRONOUNS ; niken+Pron+Neg+Sg+Par:nikeda K ; LEXICON DET_NECE !nece+Pron:ne +Dem:ce SG-ABE-SUF ; -+Dem:ci SG-ADE-SUF ; +Dem:ce SG-COM-SUF ; +Dem:ce SG-GEN-SUF ; -+Dem:ci SG-INE-SUF_iš ; -+Dem:ci SG-ELA-SUF_išpäi ; -+Dem:c SG-ILL-SUF ; ++Dem+Sg+Abe:cita K ; ++Dem+Sg+Ade:cil K ; ++Dem+Sg+All:cile K ; ++Dem+Sg+Ine:ciš K ; ++Dem+Sg+Ela:cišpäi K ; ++Dem+Sg+Ill:che K ; ++Dem+Sg+Ter1:chesai K ; +Dem+Sg+Nom:ce K ; +Dem+Sg+Par:cidä K ; +Dem:c SG-TER1-SUF ; diff --git a/src/fst/morphology/affixes/verbs.lexc b/src/fst/morphology/affixes/verbs.lexc index b148f494..bd262855 100644 --- a/src/fst/morphology/affixes/verbs.lexc +++ b/src/fst/morphology/affixes/verbs.lexc @@ -85,13 +85,31 @@ LEXICON V_da/vab/voi/gaha !! preterite stem vowel :vo ACT_IND_PRT ;! has i at affix +LEXICON V_da/ab/oi/gaha +!! @LEXNAME@ = nagrda:nagr +! V_ +: INF_da ; +:a V-VowelStem-PRS ; +!! refl-ind-prs, act-imprt-sg2, act-ind-prs, ind-sg-conneg ++Der+Der/NomAg+N:a N_KACUI ;! this will need its own work with ‹e› present + +:a ACT_COND_type ; +: ACT_PRFPRC_type_nu ; + +: V-ConsonantStem_d/g ; + +:a VNONFIN_m ; + +!! preterite stem vowel +:o ACT_IND_PRT ;! has i at affix + LEXICON V_ada/ab/oi/agaha !! @LEXNAME@ = jagada:jag ! V_JAGADA :a INF_da ; :a V-VowelStem-PRS ; !! refl-ind-prs, act-imprt-sg2, act-ind-prs, ind-sg-conneg -+Der+Der/NomAg+N:a N_TEGII ;! this will need its own work with ‹e› present ++Der+Der/NomAg+N:a N_KACUI ;! this will need its own work with ‹e› present :a ACT_COND_type ; :a ACT_PRFPRC_type_nu ; @@ -100,7 +118,6 @@ LEXICON V_ada/ab/oi/agaha :a VNONFIN_m ; -+Der/NomAg+PrsPrc:a%>jA1 K ; ! This will have to be AdjTag or something !! preterite stem vowel :o ACT_IND_PRT ;! has i at affix @@ -1046,6 +1063,8 @@ LEXICON V_OLDA ! olda: !!consonant stem if there is one takes both te, tes,... and kaha, koi :ol V-ConsonantStem_d/g ; +:ol V-ConsonantStem_de/dud/das ; +:ol IMPRT_gha ; !! problems with tta, ta, da :ol INF_da ; @@ -1058,7 +1077,7 @@ LEXICON V_TEHTA ! :ge V-VowelStem-PRS ; :g V-VowelStem-PRT ; :g V-ConsonantStem_OTHER ; -:h V-ConsonantStem_te/tud/tas ; +:h V-ConsonantStem_t/k ; : V-ConsonantStem_kaha/koi ; :ge INDPRS3 ; :h INF_ta ; @@ -1495,6 +1514,13 @@ LEXICON IMPRT_gaha IMPRTPL3_gaha ; IMPRTPLCONNEG_goi ; +LEXICON IMPRT_gha + IMPRTSG3_gha ; + IMPRTPL1_gam ; + IMPRTPL2_gat ; + IMPRTPL3_gha ; + IMPRTPLCONNEG_goi ; + LEXICON IMPRT_kaha IMPRTSG3_kaha ; IMPRTPL1_kam ; @@ -1508,12 +1534,17 @@ LEXICON IMPRTPLCONNEG_goi LEXICON IMPRTSG3_gaha +Imprt+Sg3:%>gaha K ; +LEXICON IMPRTSG3_gha ++Imprt+Sg3:%>gha K ; + LEXICON IMPRTPL1_gam +Imprt+Pl1:%>gam K ; LEXICON IMPRTPL2_gat +Imprt+Pl2:%>gat K ; LEXICON IMPRTPL3_gaha +Imprt+Pl3:%>gaha K ; +LEXICON IMPRTPL3_gha ++Imprt+Pl3:%>gha K ; LEXICON IMPRTPLCONNEG_koi +Imprt+Pl+ConNeg:%>koi K ; diff --git a/src/fst/morphology/root.lexc b/src/fst/morphology/root.lexc index ed9042f8..abf569b6 100644 --- a/src/fst/morphology/root.lexc +++ b/src/fst/morphology/root.lexc @@ -57,6 +57,11 @@ Multichar_Symbols +Use/TTS !!≈ * **@CODE@** – **only** retained in the HFST Text-To-Speech disambiguation tokeniser +Use/-TTS !!≈ * **@CODE@** – **never** retained in the HFST Text-To-Speech disambiguation tokeniser ++Hom1 !!≈ * **@CODE@** ++Hom2 !!≈ * **@CODE@** ++Hom3 !!≈ * **@CODE@** + + +v1 !!≈ * **@CODE@** +v2 !!≈ * **@CODE@** +v3 !!≈ * **@CODE@** @@ -265,7 +270,8 @@ Multichar_Symbols !! #### Usage tags: - +Err/Orth !!≈ * **@CODE@** = + +Err/Orth !!≈ * **@CODE@** = + +Err/Orth-no-pal !!≈ * **@CODE@** = palatalization mark missing +Use/-Spell !!≈ * **@CODE@** = @@ -543,15 +549,15 @@ LEXICON ORDINAL ! LEXICON PUNCTUATION ! # ; -LEXICON CADJ -!! @LEXNAME@ -+A: #; -LEXICON DADJ -!! @LEXNAME@ -+A: #; -LEXICON VADJ -!! @LEXNAME@ -+A: #; +!LEXICON CADJ +!!! @LEXNAME@ +!+A: #; +!LEXICON DADJ +!!! @LEXNAME@ +!+A: #; +!LEXICON VADJ +!!! @LEXNAME@ +!+A: #; LEXICON ADV_ !! @LEXNAME@ diff --git a/src/fst/morphology/stems/adjectives.lexc b/src/fst/morphology/stems/adjectives.lexc index 544e5433..a15ace9c 100644 --- a/src/fst/morphology/stems/adjectives.lexc +++ b/src/fst/morphology/stems/adjectives.lexc @@ -581,6 +581,7 @@ ustügalaine+A:ustügala A_CIPUINE "" ; uzbekalaine+A:uzbekala A_CIPUINE "" ; uzʼlidnalaine+A:uzʼlidnala A_CIPUINE "" ; uzʼ+A:ud A_UZ1 "" ; +täuzʼ+A:täud A_UZ1 ; vägehine+A:vägehi A_TOSHTMINE "" ; vägekaz+A:vägeka A_VEDEKAZ "" ; vägelaine+A:vägela A_CIPUINE "" ; @@ -622,6 +623,7 @@ verhine+A:verhi A_TOSHTMINE "" ; verhoturjelaine+A:verhoturjela A_CIPUINE "" ; vezo+A:vezo A_PU "" ; videnzʼ+A:viden A_VIDENZ1 "" ; +kudenzʼ+A:kuden A_VIDENZ1 "" ; vihalaine+A:vihala A_CIPUINE "" ; vihand+A:vihand A_MARJ "" ; viher+A:viher A_POIG "" ; diff --git a/src/fst/morphology/stems/adverbs.lexc b/src/fst/morphology/stems/adverbs.lexc index 79e0e965..f9276a7d 100644 --- a/src/fst/morphology/stems/adverbs.lexc +++ b/src/fst/morphology/stems/adverbs.lexc @@ -1,10 +1,27 @@ LEXICON adverbs +ani+Adv:ani ADV_ ; +aminʼ+Adv:aminʼ ADV_ ; äi+Adv:äi ADV_ ; ühtes+Adv:ühtes ADV_ ; tarbiž+Adv:tarbiž ADV_ ; mugažo+Adv:mugažo ADV_ ; +ezmäi+Adv:ezmäi ADV_ ; +ezmäks+Adv:ezmäks ADV_ ; +ezmässai+Adv:ezmässai ADV_ ; +tämbei+Adv:tämbei ADV_TEMP ; +tägä+Adv:tägä ADV_ ; +täs+Adv:täs ADV_ ; +täspäi+Adv:täspäi ADV_ ; +tähä+Adv:tähä ADV_ ; +sihe+Adv:sihe ADV_ ; +sihesai+Adv:sihesai ADV_ ; +sil+Adv:sil ADV_ ; +siš+Adv:siš ADV_ ; +sišpäi+Adv:sišpäi ADV_ ; +sidʼ+Adv:sidʼ ADV_ ; +vedʼ+Adv:vedʼ ADV_ ; amu+Adv:amu ADV_TEMP ; edes+Adv:edes ADV_ ; ka+Adv:ka ADV_ ; diff --git a/src/fst/morphology/stems/nouns_newwords.lexc b/src/fst/morphology/stems/nouns_newwords.lexc index a82e28e7..95617ba7 100644 --- a/src/fst/morphology/stems/nouns_newwords.lexc +++ b/src/fst/morphology/stems/nouns_newwords.lexc @@ -189,76 +189,112 @@ mušt+N:mušt N_0/on/od/ho/oid ; heim+N:heim N_0/on/od/oho/oid ; uskond+N:uskond N_0/an/ad/aha/id ; -alenzoitand:alenzoitand N_0/an/ad/aha/id ; -baffalind:baffalind N_MARJ ; -blahoslovind:blahoslovind N_MARJ ; -bruncind:bruncind N_MARJ ; -ecind:ecind N_MARJ ; -heimokund:heimokund N_0/an/ad/aha/id ; -heitänd:heitänd N_0/an/ad/aha/id ; -iškend:iškend N_MARJ ; -kacund:kacund N_0/an/ad/aha/id ; -kadond:kadond N_0/an/ad/aha/id ; -kadotand:kadotand N_0/an/ad/aha/id ; -katand:katand N_0/an/ad/aha/id ; -kazvand:kazvand N_0/an/ad/aha/id ; -kazvatand:kazvatand N_0/an/ad/aha/id ; -kirgund:kirgund N_0/an/ad/aha/id ; -kitänd:kitänd N_0/an/ad/aha/id ; -kohtištund:kohtištund N_0/an/ad/aha/id ; -kolend:kolend N_MARJ ; -kucund:kucund N_0/an/ad/aha/id ; -kukoinlaund:kukoinlaund N_0/an/ad/aha/id ; -kulend:kulend N_MARJ ; -kurktund:kurktund N_0/an/ad/aha/id ; -käskend:käskend N_MARJ ; -lajind:lajind N_MARJ ; -lanktend:lanktend N_MARJ ; -laskend:laskend N_MARJ ; -libund:libund N_0/an/ad/aha/id ; -lönd:lönd N_0/an/ad/aha/id ; -mahapanend:mahapanend N_MARJ ; -manižand:manižand N_0/an/ad/aha/id ; -mokičend:mokičend N_MARJ ; -märičend:märičend N_MARJ ; -mönd:mönd N_0/an/ad/aha/id ; -nagloičend:nagloičend N_MARJ ; -nagrand:nagrand N_0/an/ad/aha/id ; -naind:naind N_0/an/ad/aha/id ; -naprind:naprind N_MARJ ; -navedind:navedind N_MARJ ; -noidund:noidund N_0/an/ad/aha/id ; -olend:olend N_MARJ ; -otand:otand N_0/an/ad/aha/id ; -pagižend:pagižend N_MARJ ; -pakičend:pakičend N_MARJ ; -panend:panend N_MARJ ; -papkund:papkund N_0/an/ad/aha/id ; -pidänd:pidänd N_0/an/ad/aha/id ; -pičkund:pičkund N_0/an/ad/aha/id ; -pičkutand:pičkutand N_0/an/ad/aha/id ; -prostind:prostind N_MARJ ; -puhtastand:puhtastand N_0/an/ad/aha/id ; -purend:purend N_MARJ ; -pututand:pututand N_0/an/ad/aha/id ; -pästand:pästand N_0/an/ad/aha/id ; -päzund:päzund N_0/an/ad/aha/id ; -päzutand:päzutand N_0/an/ad/aha/id ; -pühütand:pühütand N_0/an/ad/aha/id ; -püžund:püžund N_0/an/ad/aha/id ; -ridlend:ridlend N_MARJ ; -rikond:rikond N_0/an/ad/aha/id ; -sanelend:sanelend N_MARJ ; -sauvond:sauvond N_0/an/ad/aha/id ; -sugind:sugind N_MARJ ; -sündund:sündund N_0/an/ad/aha/id ; -sündutand:sündutand N_0/an/ad/aha/id ; -tartläžund:tartläžund N_0/an/ad/aha/id ; -tegend:tegend N_MARJ ; -tirpand:tirpand N_0/an/ad/aha/id ; -tordand:tordand N_0/an/ad/aha/id ; -torguind:torguind N_MARJ ; -upotand:upotand N_0/an/ad/aha/id ; -vargastand:vargastand N_0/an/ad/aha/id ; -znamoičend:znamoičend N_MARJ ; -žalleičend:žalleičend N_MARJ ; \ No newline at end of file +alenzoitand+N:alenzoitand N_0/an/ad/aha/id ; +baffalind+N:baffalind N_MARJ ; +blahoslovind+N:blahoslovind N_MARJ ; +bruncind+N:bruncind N_MARJ ; +ecind+N:ecind N_MARJ ; +heimokund+N:heimokund N_0/an/ad/aha/id ; +heitänd+N:heitänd N_0/an/ad/aha/id ; +iškend+N:iškend N_MARJ ; +kacund+N:kacund N_0/an/ad/aha/id ; +kadond+N:kadond N_0/an/ad/aha/id ; +kadotand+N:kadotand N_0/an/ad/aha/id ; +katand+N:katand N_0/an/ad/aha/id ; +kazvand+N:kazvand N_0/an/ad/aha/id ; +kazvatand+N:kazvatand N_0/an/ad/aha/id ; +kirgund+N:kirgund N_0/an/ad/aha/id ; +kitänd+N:kitänd N_0/an/ad/aha/id ; +kohtištund+N:kohtištund N_0/an/ad/aha/id ; +kolend+N:kolend N_MARJ ; +kucund+N:kucund N_0/an/ad/aha/id ; +kukoinlaund+N:kukoinlaund N_0/an/ad/aha/id ; +kulend+N:kulend N_MARJ ; +kurktund+N:kurktund N_0/an/ad/aha/id ; +käskend+N:käskend N_MARJ ; +lajind+N:lajind N_MARJ ; +lanktend+N:lanktend N_MARJ ; +laskend+N:laskend N_MARJ ; +libund+N:libund N_0/an/ad/aha/id ; +lönd+N:lönd N_0/an/ad/aha/id ; +mahapanend+N:mahapanend N_MARJ ; +manižand+N:manižand N_0/an/ad/aha/id ; +mokičend+N:mokičend N_MARJ ; +märičend+N:märičend N_MARJ ; +mönd+N:mönd N_0/an/ad/aha/id ; +nagloičend+N:nagloičend N_MARJ ; +nagrand+N:nagrand N_0/an/ad/aha/id ; +naind+N:naind N_0/an/ad/aha/id ; +naprind+N:naprind N_MARJ ; +navedind+N:navedind N_MARJ ; +noidund+N:noidund N_0/an/ad/aha/id ; +olend+N:olend N_MARJ ; +otand+N:otand N_0/an/ad/aha/id ; +pagižend+N:pagižend N_MARJ ; +pakičend+N:pakičend N_MARJ ; +panend+N:panend N_MARJ ; +papʼkund+v1+N:papʼkund N_0/an/ad/aha/id ; +papʼkund+v2+N:papkund N_0/an/ad/aha/id ; +pidänd+N:pidänd N_0/an/ad/aha/id ; +pičkund+N:pičkund N_0/an/ad/aha/id ; +pičkutand+N:pičkutand N_0/an/ad/aha/id ; +prostind+N:prostind N_MARJ ; +puhtastand+N:puhtastand N_0/an/ad/aha/id ; +purend+N:purend N_MARJ ; +pututand+N:pututand N_0/an/ad/aha/id ; +pästand+N:pästand N_0/an/ad/aha/id ; +päzund+N:päzund N_0/an/ad/aha/id ; +päzutand+N:päzutand N_0/an/ad/aha/id ; +pühütand+N:pühütand N_0/an/ad/aha/id ; +püžund+N:püžund N_0/an/ad/aha/id ; +ridlend+N:ridlend N_MARJ ; +rikond+N:rikond N_0/an/ad/aha/id ; +sanelend+N:sanelend N_MARJ ; +sauvond+N:sauvond N_0/an/ad/aha/id ; +sugind+N:sugind N_MARJ ; +sündund+N:sündund N_0/an/ad/aha/id ; +sündutand+N:sündutand N_0/an/ad/aha/id ; +tartläžund+N:tartläžund N_0/an/ad/aha/id ; +tegend+N:tegend N_MARJ ; +tirpand+N:tirpand N_0/an/ad/aha/id ; +tordand+N:tordand N_0/an/ad/aha/id ; +torguind+N:torguind N_MARJ ; +upotand+N:upotand N_0/an/ad/aha/id ; +vargastand+N:vargastand N_0/an/ad/aha/id ; +znamoičend+N:znamoičend N_MARJ ; +žalleičend+N:žalleičend N_MARJ ; +papʼ+N:pap N_1/in/id/ihe/id ; +südäin+N:südä N_SUEDAEIN ; +tozi+N:tod N_KEZI ; +sija+N:sij N_SANA ; +altarʼ+N:altar N_1/in/id/ihe/id ; +kesarʼ+N:kesar N_1/in/id/ihe/id ; +apʼ+N:ap N_1/en/ed/ehe/id ; +anopʼ+N:anop N_1/en/ed/ehe/id ; +arb+N:arb N_MARJ ; +arf+N:arf N_MARJ ; +artelʼ+N:artel N_1/in/id/ihe/id ; +ažlakuzʼ+N:ažlakud N_NORUZ1 ; +bohatuzʼ+N:bohatud N_NORUZ1 ; +ozoitezstarin+N:ozoitezstarin N_MARJ ; + +meletomuzʼ+N:meletomud N_NORUZ1 ; +melevuzʼ+N:melevud N_NORUZ1 ; +oiktuzʼ+N:oiktud N_NORUZ1 ; +ozatomuzʼ+N:ozatomud N_NORUZ1 ; +pahuzʼ+N:pahud N_NORUZ1 ; +piduzʼ+N:pidud N_NORUZ1 ; +pimeduzʼ+N:pimedud N_NORUZ1 ; +tozioiktuzʼ+N:tozioiktud N_NORUZ1 ; +täudehuzʼ+N:täudehud N_NORUZ1 ; +vahvuzʼ+N:vahvud N_NORUZ1 ; +vajaguzʼ+N:vajagud N_NORUZ1 ; +värhuzʼ+N:värhud N_NORUZ1 ; +čomuzʼ+N:čomud N_NORUZ1 ; +kuld+N:kuld N_POIG ; +nadei+N:nade N_TEGII ; +nalog+N:nalog N_MARJ ; +naižjumal+N:naižjumal N_MARJ ; +noid+N:noid N_POIG ; +orj+N:orj N_0/an/ad/aha/id ; +oza+N:oz N_MUNA ; \ No newline at end of file diff --git a/src/fst/morphology/stems/propernouns_newwords.lexc b/src/fst/morphology/stems/propernouns_newwords.lexc index ff110c54..df601aeb 100644 --- a/src/fst/morphology/stems/propernouns_newwords.lexc +++ b/src/fst/morphology/stems/propernouns_newwords.lexc @@ -235,3 +235,25 @@ Veniamin+N+Prop:Veniamin N_MARJ ; Kornili+N+Prop:Kornili N_MARJ ; Juli+N+Prop:Juli N_MARJ ; Juni+N+Prop:Juni N_MARJ ; +Fiatir+N+Prop:Fiatir N_MARJ ; +Gennisaret+N+Prop:Gennisaret N_MARJ ; +Gennisaretjärv+N+Prop:Gennisaret#järv N_SARV ; +Tiveriijärv+N+Prop:Tiveriijärv N_SARV ; +Effratjogi+N+Prop:Effrat#jog N_NIMI ; +Azot-lidn+N+Prop:Azot-lidn N_MARJ ; +Efraim-lidn+N+Prop:Efraim-lidn N_MARJ ; +Jerusalim-lidn+N+Prop:Jerusalim-lidn N_MARJ ; +Laseja-lidn+N+Prop:Laseja-lidn N_MARJ ; +Salamin-lidn+N+Prop:Salamin-lidn N_MARJ ; +Sidon-lidn+N+Prop:Sidon-lidn N_MARJ ; +Sihar-lidn+N+Prop:Sihar-lidn N_MARJ ; +Tars-lidn+N+Prop:Tars-lidn N_MARJ ; +Tars+N+Prop:Tars N_MARJ ; +Vavilon-lidn+N+Prop:Vavilon-lidn N_MARJ ; +Izrailʼ+N+Prop:Izrailʼ N_MARJ ; +Jair+N+Prop:Jair N_MARJ ; +Agrippa-kunigaz+N+Prop:Agrippa-kuniga N_VEDEKAZ ; +Areta-kunigaz+N+Prop:Areta-kuniga N_VEDEKAZ ; +David-kunigaz+N+Prop:David-kuniga N_VEDEKAZ ; +Irod-kunigaz+N+Prop:Irod-kuniga N_VEDEKAZ ; +Solomon-kunigaz+N+Prop:Solomon-kuniga N_VEDEKAZ ; diff --git a/src/fst/morphology/stems/verbs.lexc b/src/fst/morphology/stems/verbs.lexc index 06cf18ca..29adbec6 100644 --- a/src/fst/morphology/stems/verbs.lexc +++ b/src/fst/morphology/stems/verbs.lexc @@ -144,7 +144,6 @@ hengestuda+V:hengestu V_da/b/i/gaha ; hengištoitta+V:hengištoi V_ABIDOITTA ; hengištuda+V:hengištu V_da/b/i/gaha ; heragata+V:heraga V_ta/ndeb/nzi/kaha ; -heraštoitta+V:heraštoi V_ABIDOITTA ; heraštuda+V:heraštu V_da/b/i/gaha ; heredoitta+V:heredoi V_ABIDOITTA ; heregata+V:herega V_ta/ndeb/nzi/kaha ; @@ -835,6 +834,7 @@ peneta+v1+V:pene V_OIGETA ; peništuda+V:peništu V_da/b/i/gaha ; penzastuda+V:penzastu V_da/b/i/gaha ; pesta+V:pez V_1Syl_DVta/eb/i/DVkaha ; +noust+V:nouz V_1Syl_DVta/eb/i/DVkaha ; pezaduda+V:pezadu V_da/b/i/gaha ; pezelta+V:pezel V_JOKSTA ; pezetada+V:pezet V_ada/ab/i/agaha ; @@ -1176,7 +1176,6 @@ tühjeta+V:tühje V_OIGETA ; tühjištuda+V:tühjištu V_da/b/i/gaha ; tülʼctuda+V:tülʼctu V_da/b/i/gaha ; tünduda+V:tündu V_da/b/i/gaha ; -tüništoitta+V:tüništoi V_ABIDOITTA ; tüništuda+V:tüništu V_da/b/i/gaha ; tüpäkzuda+V:tüpäkzu V_da/b/i/gaha ; tüukta+V:tüuk V_ASTTA ; diff --git a/src/fst/morphology/stems/verbs_newwords.lexc b/src/fst/morphology/stems/verbs_newwords.lexc index 0886daca..3261d550 100644 --- a/src/fst/morphology/stems/verbs_newwords.lexc +++ b/src/fst/morphology/stems/verbs_newwords.lexc @@ -485,6 +485,7 @@ värpitada+V:värpit V_ada/ab/i/agaha ; šlibahtada+V:šlibaht V_ada/ab/i/agaha ; štargutada+V:štargut V_ada/ab/i/agaha ; štolahtada+V:štolaht V_ada/ab/i/agaha ; +nagrda+V:nagr V_da/ab/oi/gaha ; ajada+V:aj V_ada/ab/oi/agaha ; jagada+V:jag V_ada/ab/oi/agaha ; palada+V:pal V_ada/ab/oi/agaha ; @@ -495,9 +496,11 @@ ahjata+V:ahj V_ata/ab/oi/akaha ; harjata+V:harj V_ata/ab/oi/akaha ; hapata+V:hap V_ata/neb/ni/akaha ; !#V_ata/tab/si/Q ;_ezipaukata+V:ezipauk V_ata/tab/si/Q ; +sugida+V:sugi V_da/b/0/gaha ; aidoida+V:aidoi V_da/b/0/gaha ; annuliruida+V:annulirui V_da/b/0/gaha ; arboida+V:arboi V_da/b/0/gaha ; +baffalida+V:baffali V_da/b/0/gaha ; blahoslovida+V:blahoslovi V_da/b/0/gaha ; buhvostida+V:buhvosti V_da/b/0/gaha ; capnida+V:capni V_da/b/0/gaha ; @@ -890,7 +893,7 @@ grazda+V:graz V_da/ib/i/gaha ;!CHECKME barabanda+V:baraban V_da/ib/i/gaha ; hobda+V:hob V_da/ib/i/gaha ; horda+V:hor V_da/ib/i/gaha ; -kertehtida+V:kertehti V_da/ib/i/gaha ; +kertehtida+V:kertehti V_da/b/0/gaha ; kimda+V:kim V_da/ib/i/gaha ; kodvda+V:kodv V_da/ib/i/gaha ; korda+V:kor V_da/ib/i/gaha ; @@ -903,7 +906,6 @@ poimda+Hom2+V:poim V_da/ib/i/gaha ; pärmda+V:pärm V_da/ib/i/gaha ; ribda+V:rib V_da/ib/i/gaha ; savukurda+V:savukur V_da/ib/i/gaha ; -sugida+V:sugi V_da/b/0/gaha ; čvanda+V:čvan V_da/ib/i/gaha ; žarda+V:žar V_da/ib/i/gaha ; kaida+V:kai V_da/vab/voi/gaha ; @@ -958,9 +960,17 @@ pagišta+V:pagiž V_2Syl_DVta/eb/i/DVkaha ; värišta+V:väriž V_2Syl_DVta/eb/i/DVkaha ; čihišta+V:čihiž V_2Syl_DVta/eb/i/DVkaha ; šihišta+V:šihiž V_2Syl_DVta/eb/i/DVkaha ; +heraštoitta+V:heraštoit V_ta/ab/i/kaha ; alaštoitta+V:alaštoit V_ta/ab/i/kaha ; +tüništoitta+V:tüništoit V_ta/ab/i/kaha ; +bruncitoitta+V:bruncitoit V_ta/ab/i/kaha ; +elähtoitta+V:elähtoit V_ta/ab/i/kaha ; +kožutoitta+V:kožutoit V_ta/ab/i/kaha ; +kunutoitta+V:kunutoit V_ta/ab/i/kaha ; +mülütoitta+V:mülütoit V_ta/ab/i/kaha ; alenzoitta+V:alenzoit V_ta/ab/i/kaha ; astutoitta+V:astutoit V_ta/ab/i/kaha ; +čomenzoitta+V:čomenzoit V_ta/ab/i/kaha ; bohatoitta+V:bohatoit V_ta/ab/i/kaha ; budahtoitta+V:budahtoit V_ta/ab/i/kaha ; eläbzoitta+V:eläbzoit V_ta/ab/i/kaha ;