From 7f8966e55839d7b589b5adf20cf36855ff94695d Mon Sep 17 00:00:00 2001
From: Jack Rueter <rueter.jack@gmail.com>
Date: Sat, 16 Nov 2024 23:13:26 +0200
Subject: [PATCH] Add more words

missing 3652 unique forms
---
 src/fst/morphology/affixes/nouns.lexc         | 16 +++---
 src/fst/morphology/affixes/quantifiers.lexc   | 10 ++--
 src/fst/morphology/affixes/verbs.lexc         | 50 +++++++++++++++++++
 src/fst/morphology/phonology.twolc            |  4 +-
 .../morphology/stems/adjectives_newwords.lexc |  1 +
 src/fst/morphology/stems/nouns_newwords.lexc  | 34 ++++++++++++-
 src/fst/morphology/stems/numerals.lexc        |  5 +-
 src/fst/morphology/stems/verbs_newwords.lexc  |  2 +
 8 files changed, 109 insertions(+), 13 deletions(-)

diff --git a/src/fst/morphology/affixes/nouns.lexc b/src/fst/morphology/affixes/nouns.lexc
index 3f3f8f3b..35b7a45f 100644
--- a/src/fst/morphology/affixes/nouns.lexc
+++ b/src/fst/morphology/affixes/nouns.lexc
@@ -180,12 +180,12 @@ LEXICON N_PERT1 ! pertʼ:pert
 !pertin
 !pertid
 :ʼ SG-NOM-SUF ;
-+Sg+Ill:%>hä K ;
-:%>ä SG-OBLIQUE ;
++Sg+Ill:ʼ%>he K ;
+:i SG-OBLIQUE ;
 R ; ! xxx check
 ! Plural
-:%>ä PL-NOM-SUF ;
-:%>ä PL-ACC-SUF ;
+:i PL-NOM-SUF ;
+:i PL-ACC-SUF ;
 : PL-OBLIQUE ;
 
 
@@ -350,7 +350,8 @@ LEXICON N_SEIBAZ ! seibaz:seib
 !!€  d: +N+Pl+Par
 :az SG-NOM-SUF ;
 :as SG-PAR-SUF_t ;
-:ha SG-OBLIQUE ;
++Sg+Ill:haze K ;
+:ha SG-OBLIQUE_NO_DERIV/ILL/PAR ;
 R ; ! xxx check
 ! Plural
 :ha PL-NOM-SUF ;
@@ -420,7 +421,8 @@ LEXICON N_VEDEKAZ ! vedekaz:vedeka
 !!€  d: +N+Pl+Par
 :z SG-NOM-SUF ;
 :s SG-PAR-SUF_t ;
-:ha SG-OBLIQUE ;
++Sg+Ill:haze K	;
+:ha SG-OBLIQUE_NO_DERIV/ILL/PAR ;
 R ; ! xxx check
 ! Plural
 :ha PL-NOM-SUF ;
@@ -637,6 +639,7 @@ LEXICON N_SAMAL !samal:samal syncope
 !!€  n: +N+Sg+Gen
 !!€  d: +N+Pl+Par
 : SG-NOM-SUF ;
+: SG-PAR-SUF_t ;  
 :%^RmVow%^DEVOICE%>o SG-OBLIQUE ;
 R ; ! xxx check
 ! Plural
@@ -771,6 +774,7 @@ LEXICON N_ine/izhen/isht/izhehe/izhid
 !!€  d: +N+Pl+Par
 :ne SG-NOM-SUF ;
 :š SG-PAR-SUF_t ;
++Sg+Ill:žhe K ;!CHECKME 2024-11-16
 :že SG-OBLIQUE ;
 R ; ! xxx check
 ! Plural
diff --git a/src/fst/morphology/affixes/quantifiers.lexc b/src/fst/morphology/affixes/quantifiers.lexc
index 86caf21a..09bec478 100644
--- a/src/fst/morphology/affixes/quantifiers.lexc
+++ b/src/fst/morphology/affixes/quantifiers.lexc
@@ -3,13 +3,17 @@
 LEXICON NUM_KAKS1
 !! **LEXICON @LEXNAME@** 
 +Sg+Nom:ksʼ K ;
-+Sg+Gen:hten K ;
++Sg:hte OBLIQUE_CASES_FOR_PRONOUNS ;
 
 LEXICON NUM_YKS1
 !! **LEXICON @LEXNAME@** 
-+Sg+Nom:ks' K ;
-+Sg+Gen:hten K ;
++Sg+Nom:ksʼ K ;
++Sg:hte OBLIQUE_CASES_FOR_PRONOUNS ;
 
+LEXICON NUM_UEHESA
+!! **LEXICON @LEXNAME@**
++Sg+Nom: K ;
++Sg: OBLIQUE_CASES_FOR_PRONOUNS ;
 
 !LEXICON NUM_NORUZ
 !!! **LEXICON @LEXNAME@** 
diff --git a/src/fst/morphology/affixes/verbs.lexc b/src/fst/morphology/affixes/verbs.lexc
index bd262855..90d04de0 100644
--- a/src/fst/morphology/affixes/verbs.lexc
+++ b/src/fst/morphology/affixes/verbs.lexc
@@ -625,6 +625,30 @@ LEXICON V_2Syl_DVta/eb/i/DVkaha
 !! preterite stem vowel
 : ACT_IND_PRT ;! gets i
 
+LEXICON V_1Syl_DVta/ub/i/DVkaha
+!! @LEXNAME@ = seišta:seiž
+! V_??
+!! preceding vowel always required for affix
+:u V-VowelStem-PRS ;
+!! refl-ind-prs, act-imprt-sg2, act-ind-prs, ind-sg-conneg, NomAg
++Der+Der/NomAg+N:u N_KACUI ;! this will need its own work with ‹e› present stems20241109
+
+!! sometimes requires preceding vowel
+:u ACT_COND_type ;
+: ACT_PRFPRC_type_nu ;
+
+: VNONFIN_m ; !does not include -matoi 20241109
+
+!!consonant stem if there is one takes both te, tes,... and kaha, koi
+:%^DEVOICE V-ConsonantStem_t/k ;
+! refl-imprt-sg2, refl-ind-prs-sg-conneg
+
+!! problems with tta, ta, da
+:%^DEVOICE INF_ta ; !pagišta
+
+!! preterite stem vowel
+:u ACT_IND_PRT ;! gets i
+
 LEXICON V_1Syl_DVta/eb/i/DVkaha
 !! @LEXNAME@ = pesta:pez only for verbs with devoicing
 ! V_PESTA
@@ -649,6 +673,31 @@ LEXICON V_1Syl_DVta/eb/i/DVkaha
 !! preterite stem vowel
 : ACT_IND_PRT ;! gets i
 
+LEXICON V_1Syl_DVta/eb/i/ggaha
+!! @LEXNAME@ = pesta:pez only for verbs with devoicing
+! V_PESTA
+!! preceding vowel always required for affix
+:e V-VowelStem-PRS ;
+!! refl-ind-prs, act-imprt-sg2, act-ind-prs, ind-sg-conneg, NomAg
++Der+Der/NomAg+N:i N_TEGII ;! this will need its own work with ‹e› present stems20241109
+
+!! sometimes requires preceding vowel
+: ACT_COND_type ;
+: ACT_PRFPRC_type_nu ;
+
+:e VNONFIN_m ; !does not include -matoi 20241109
+
+!!consonant stem if there is one takes both te, tes,... and kaha, koi
+:%^DEVOICE V-ConsonantStem_te/tud/tas ; !DV devoice
+: V-ConsonantStem_gaha/goi ;
+! refl-imprt-sg2, refl-ind-prs-sg-conneg
+
+!! problems with tta, ta, da
+:%^DEVOICE INF_ta ;
+
+!! preterite stem vowel
+: ACT_IND_PRT ;! gets i
+
 LEXICON V_kta/gub/gui/ggaha
 !! @LEXNAME@ = kirkta:kir
 ! V_??
@@ -1281,6 +1330,7 @@ LEXICON V-VowelStem-PRS
  ACT_IND_PRT_SG_CONNEG ;
 
 +Der+Der/V:%>škande ACT_IND_PRS ;!inchoative?
++Der+Der/V:%>škande REFL_IND_PRS ;!inchoative?
 +Der+Der/V:%>škanz ACT_IND_PRT ;!inchoative?
 +Der+Der/V:%>ška V-ConsonantStem_t/k ;!inchoative? CHECKME 20241110
 
diff --git a/src/fst/morphology/phonology.twolc b/src/fst/morphology/phonology.twolc
index 5c6cf5a6..961738bb 100644
--- a/src/fst/morphology/phonology.twolc
+++ b/src/fst/morphology/phonology.twolc
@@ -230,8 +230,8 @@ V1:Vx <=> Vx Cns:* %> h _ ;
 !! **@RULENAME@** vauged: vauktan
  Cx:Cy <=>  _ [%{eØ%}: |%{uØ%}: ] Cns:CnsVoiceless %^RmVow: %^DEVOICE: %> ;
             Cns:CnsVoiceless [ %{eØ%}: | %{uØ%}: ] _ %^RmVow: %^DEVOICE: %> ;
-	    [i | r | n | Vow:] _ (%^PEN: %^DEVOICE:) (%^RmVow:) %^DEVOICE: ;
-	    [i | r | n | Vow:] _ Vow: Cns: %^PEN: %^DEVOICE: ;
+	    [Vow:] _ (%^PEN: %^DEVOICE:) (%^RmVow:) %^DEVOICE: ;
+	    [i | l (ʼ) | n | r | Vow:] _ Vow: Cns: %^PEN: %^DEVOICE: ;
               where Cx in (g d)
                     Cy in (k t) matched ;
 !! oiged+A+Sg+Gen: __right/oikea__
diff --git a/src/fst/morphology/stems/adjectives_newwords.lexc b/src/fst/morphology/stems/adjectives_newwords.lexc
index 87e2d3cc..8101a29e 100644
--- a/src/fst/morphology/stems/adjectives_newwords.lexc
+++ b/src/fst/morphology/stems/adjectives_newwords.lexc
@@ -86,6 +86,7 @@ aigvotte+A:aigvo A_IN_TTE ;
 kaikenvuitte+A:kaikenvui A_IN_TTE ;
 tozioiged+A:tozi#oiged A_OIGED ;
 huiged+A:huiged A_OIGED ;
+selʼged+A:selʼged A_OIGED ;
 lämoinrusked+A:lämoin#rusked A_RUSKED ;
 purpuranrusked+A:purpuranrusked A_RUSKED ;
 päivänvauged+A:päivänvauged A_OIGED ;
diff --git a/src/fst/morphology/stems/nouns_newwords.lexc b/src/fst/morphology/stems/nouns_newwords.lexc
index 95617ba7..7d98e045 100644
--- a/src/fst/morphology/stems/nouns_newwords.lexc
+++ b/src/fst/morphology/stems/nouns_newwords.lexc
@@ -297,4 +297,36 @@ 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
+oza+N:oz N_MUNA ;
+semen+N:semen N_samal ;
+smokvanpu+N:smokvanpu N_PU ;
+soba+N:sob N_MUNA ;
+sorm+N:sorm N_SARV ;
+soton+N:soton N_POIG ;
+spasib+N:spasib N_JAUH ;
+starin+N:starin N_MARJ ;
+sud+N:sud N_POIG ;
+suim+N:suim N_POIG ;
+suimpertʼ+N:suimpert N_PERT1 ;
+süvüzʼ+N:süvüd N_NORUZ1 ;
+taba+N:tab N_SANA ;
+rahvazkogo+N:rahvazkogo N_PU ;
+razbainik+N:razbainik N_MARJ ;
+ridanik+N:ridanik N_MARJ ;
+kalanik+N:kalanik N_MARJ ;
+praznik+N:praznik N_MARJ ;
+jälʼgnik+N:jälʼgnik N_MARJ ;
+kesknik+N:kesknik N_MARJ ;
+matknik+N:matknik N_MARJ ;
+merimatknik+N:merimatknik N_MARJ ;
+nahknik+N:nahknik N_MARJ ;
+nužnik+N:nužnik N_MARJ ;
+nägudez+N:nägudez N_ALUZ ;
+padanik+N:padanik N_MARJ ;
+pagenik+N:pagenik N_MARJ ;
+pagan+N:pagan N_MARJ ;
+torasebranik+N:torasebranik N_MARJ ;
+türmnik+N:türmnik N_MARJ ;
+verijälʼgnik+N:verijälʼgnik N_MARJ ;
+vozʼpraznik+N:vozʼpraznik N_MARJ ;
+käskištonopendai+N:käskištonopenda N_KACUI ;
\ No newline at end of file
diff --git a/src/fst/morphology/stems/numerals.lexc b/src/fst/morphology/stems/numerals.lexc
index 0f15fdf1..01159a12 100644
--- a/src/fst/morphology/stems/numerals.lexc
+++ b/src/fst/morphology/stems/numerals.lexc
@@ -20,7 +20,10 @@ LEXICON Numerals
  +Use/Circ: ISOLATED-NUMEXP ; ! for ½ etc.                     !
 
 LEXICON NUM_CARD_ALL
-yksi+Num:yksi # ;
+kahesa+Num:kahesa NUM_UEHESA ;
+kaksʼ+Num:ka NUM_KAKS1 ;
+ühesa+Num:ühesa NUM_UEHESA ;
+üksʼ+Num:ü NUM_YKS1 ;
 seičeme+Num:seičeme NUM_SEICHEME ;
 
 LEXICON NUM_SEICHEME !seičeme:seičem
diff --git a/src/fst/morphology/stems/verbs_newwords.lexc b/src/fst/morphology/stems/verbs_newwords.lexc
index 3261d550..b3342284 100644
--- a/src/fst/morphology/stems/verbs_newwords.lexc
+++ b/src/fst/morphology/stems/verbs_newwords.lexc
@@ -952,6 +952,8 @@ vinkta+V:ving V_kta/gub/gui/ggaha ;
 činkta+V:čing V_kta/gub/gui/ggaha ;
 štarkta+V:štarg V_kta/gub/gui/ggaha ;
 !#V_kuda/ub/ui/Q ;_haukkuda+V:hauk V_kuda/ub/ui/Q ;
+seišta+V:seiž V_1Syl_DVta/ub/i/DVkaha ;
+sülʼkta+V:sülʼg V_1Syl_DVta/eb/i/ggaha ;
 börišta+V:böriž V_2Syl_DVta/eb/i/DVkaha ;
 hogišta+V:hogiž V_2Syl_DVta/eb/i/DVkaha ;
 jurišta+V:juriž V_2Syl_DVta/eb/i/DVkaha ;