From 100f53335fb9925e1af241b2e9c0ba4a9f606767 Mon Sep 17 00:00:00 2001 From: Valdis Vitolins Date: Sun, 5 Feb 2017 23:33:44 +0200 Subject: [PATCH] Latvian language improvements. Rules with repeated letter groups changed to jump rules --- dictsource/lv_rules | 148 ++++++++++++-------------------------------- 1 file changed, 39 insertions(+), 109 deletions(-) diff --git a/dictsource/lv_rules b/dictsource/lv_rules index 11d8c125..afece51a 100644 --- a/dictsource/lv_rules +++ b/dictsource/lv_rules @@ -49,7 +49,7 @@ .L22 č ģ j k ļ ņ ŗ š ž dž bj pj mj vj // consonant narrowers of e .L23 s i m // remaining ending of the 2. and 5. decl. words .L27 č e ē f ģ h ḩ i ī j k ļ ņ q ŗ š w x y ž ei ie iu // all narrowers of e -// Also: .L41 — international consonants and diphthongs as a narrowers of e/ē +// Also: .L41 — international consonants and diphthongs as a narrowers of e/ē // E wideners .L24 a ā u ū ai au // vowel wideners of e @@ -57,7 +57,7 @@ // but it is mixed with ȯ and ō .L25 b c d g ķ l m n p r s t v z dz // consonant wideners of e .L28 a ā b c d e ē g ķ l m n p r s t u ū v z ai au // all wideners of e - + // +---------------------------+ // | Pronunciation of o | @@ -92,13 +92,13 @@ // | Consonant groups | // +---------------------------+ -.L60 b d dz dž g ģ j l ļ m n ņ r v z ž // voiced (loud) consonants +.L60 b d dz dž g ģ j l ļ m n ņ r v z ž // voiced (loud) consonants .L61 p t k ķ c č s š f h ḩ // unvoiced (silent) consonants .L62 b c d f g h j k l m n p q r s t v w x z // hard consonants .L63 č ģ ḩ ķ ļ ņ ŗ š ž // soft consonants .L64 s t .L65 t d j s š // root endings for verbs and adjectives -.L66 g ģ +.L66 g ģ .L67 k ķ .L68 n r .L69 k s @@ -131,13 +131,6 @@ .L93 m l n // vowel (pre)lengtheners — vowels after these are spelled longer than usual // j is vowel (post)lengthener, but as only one is handled in group j - -// +---------------------------+ -// | All letters | -// +---------------------------+ -// These are used for "." like padding -.L10 a ā b c č d e ē f g ģ h ḩ i ī j k ķ l ļ m n ņ o ō p q r ŗ s š t u ū v w x y z ž - // +---------------------------+ // | Pronunciation groups | // +---------------------------+ @@ -177,20 +170,16 @@ .group e e e // Default as narrow e ee e_|e // internationalisms, prefix: ne-e... - ei ei + ei (+ ei // narrow e ---------------------------------------------------------------------- // a) e (ro e // internationalsms e (o e // international consonants - e (L10L10L10L41 e - e (L10L10L41+ e - e (L10L41++ e + e (JL41+ e e (L41+++ e - L41) e (@ e // narrow only if there is another syllable for ending - L41L10) e (@ e - L41L10L10) e (@< e -L41L10L10L10) e (@<< e + L41) e (@ e // narrow only if there is another syllable for ending + L41J) e (@+ e // narrowing vowels follow e (Cinā e @@ -217,10 +206,7 @@ L41L10L10L10) e (@<< e e (CL05_ e // 5. decl. words e (CCL05_< e e (CCCL05_<< e - e (L10L05_+ e - e (L10L10L05_ e - e (L10L10L10L05_< e - e (L10L10L10L10L05_<< e + e (JL05_+ e // wide e ------------------------------------------------------------------------ // // widening consonants follow @@ -235,15 +221,16 @@ L41L10L10L10) e (@<< e e (L01_ E e (L25L01_ E e (L25L25L01_ E + e (Jam E L25) e (L18_+ E // vareni etc. // specific words ----------------------------------------------------------------- // -// āb) e (L77L05_ e // ābele - b) e (dL82L05_ e // bedre + e (lL88 e // ..el[tš] + b) e (dL82L05_ e // bedre _b) e (t_ e _b) e (z e _b) e (z_ e - _C) e (_ e // re, te, ve + _C) e (_ e // re, te, ve _č) e (trL07_ e // četri d) ebe (L83 ebe d) ebe (t ebe @@ -299,15 +286,11 @@ L41L10L10L10) e (@<< e // narrow ē ---------------------------------------------------------------------- // // narrowing international consonants - ē (L10L10L10L41 e: - ē (L10L10L41 e: - ē (L10L41 e: ē (L41+ e: - L41) ē (@ e: // narrow only if there is another syllable for ending - L41L10) ē (@ e: - L41L10L10) ē (@< e: -L41L10L10L10) ē (@<< e: -L41L10L10L10L10) ē (@<<< e: + ē (JL41+ e: + ē (L41+ e: + L41) ē (@+ e: // narrow only if there is another syllable for ending + L41J) ē (@ e: // narrowing vowels follow ē (CCCCL21 e: ē (CCCL21 e: @@ -355,10 +338,7 @@ L41L10L10L10L10) ē (@<<< e: ē (CL05_ e: ē (CCL05_< e: ē (CCCL05_<< e: - ē (L10L05_+ e: - ē (L10L10L05_ e: - ē (L10L10L10L05_< e: - ē (L10L10L10L10L05_<< e: + ē (JL05_+ e: // specific words ------------------------------------------------------------------- // @@ -370,7 +350,7 @@ L41L10L10L10L10) ē (@<<< e: ēdē e:de: ē (kL04_+ E: // ēka ē (L86L13_ e: // ēst - ē (rkšķ e: + ē (rkšķ e: ē (tā_ E: ē (tL55_ E: izp) ē (t e: @@ -394,7 +374,7 @@ L41L10L10L10L10) ē (@<<< e: šķ) ē (L77L05_ e: // šķēle šķ) ē (L82L05_ e: // šķēre _tāp) ē (c_ e: // tāpēc - t) ē (L90 e: + t) ē (L90 e: t) ē (mL04_ e: // ..tēma v) ērtē e:Rte: @@ -473,45 +453,14 @@ L41L10L10L10L10) ē (@<<< e: L42) o o: // o prefixes o (L43+ o // o postfixes - // o indicators before -L41L10L10L10L10L10L10L10L10L10) o (<<<<<<<<<< o -L41L10L10L10L10L10L10L10L10) o (<<<<<<<<< o -L41L10L10L10L10L10L10L10) o (<<<<<<< o -L41L10L10L10L10L10L10) o (<<<<<< o -L41L10L10L10L10L10) o (<<<<< o - L41L10L10L10L10) o (<<<< o - L41L10L10L10) o (<<< o - L41L10L10) o (<< o - L41L10) o (< o - L41) o o - // o indicators after - o (L10L10L10L10L10L10L10L41<<<<<< o - o (L10L10L10L10L10L10L41<<<<< o - o (L10L10L10L10L10L41<<<< o - o (L10L10L10L10L41<<< o - o (L10L10L10L41<< o - o (L10L10L41< o - o (L10L41 o - o (L41+ o - - // uo indicators before (facultative writing) -L30L10L10L10L10L10L10L10) o (<<<<<<< uo -L30L10L10L10L10L10L10) o (<<<<<< uo -L30L10L10L10L10L10) o (<<<<< uo - L30L10L10L10L10) o (<<<< uo - L30L10L10L10) o (<<< uo - L30L10L10) o (<< uo - L30L10) o (< uo - L30) o uo - // uo indicators after (facultative writing) - o (L10L10L10L10L10L10L30<<<<< uo - o (L10L10L10L10L10L30<<<< uo - o (L10L10L10L10L30<<< uo - o (L10L10L10L30<< uo - o (L10L10L30< uo - o (L10L30 uo - o (L30+ uo + L41J) o (+ o // o indicators before + o (L41+ o // o indicators after + o (JL41+ o + L30J) o uo // uo indicators before (facultative writing) + L30) o (+ uo + o (JL30 uo // uo indicators after (facultative writing) + o (L30+ uo o uo // words with Latvian roots are more common o (_++ uo // common ending for Latvian words @@ -547,27 +496,10 @@ L46L45L45) o (<< uo otu (_< uotu o (_$w_alt2++ uo // $alt2 (international) words in lv_list, which are spelled with uo at the end - L41L10L10L10L10L10L10L10) o (lL01_<<<<< o: // [fhqxw]..ols - L41L10L10L10L10L10L10) o (lL01_<<<< o: - L41L10L10L10L10L10) o (lL01_<<< o: - L41L10L10L10L10) o (lL01_<< o: - L41L10L10L10) o (lL01_< o: - L41L10L10) o (lL01_ o: - L41L10) o (lL01_+ o: - - oL10L10L10L10L10L10L10) o (lL01_<<<<<< o: // o...ols - oL10L10L10L10L10L10) o (lL01_<<<<< o: - oL10L10L10L10L10) o (lL01_<<<< o: - oL10L10L10L10) o (lL01_<<< o: - oL10L10L10) o (lL01_<< o: - oL10L10) o (lL01_< o: - oL10) o (lL01_ o: - + L41J) o (lL01_+ o: // [fhqxw]..ols + oJ) o (lL01_ o: // o...ols o (L62% o - - - aer) o o: agn) o o agr) o o @@ -597,7 +529,7 @@ L46L45L45) o (<< uo br) o (š o celm) o uo cet) o o - cēl) o (L80 uo + cēl) o (L80 uo cikl) o o: cit) o o _c) o (_+ o: @@ -691,7 +623,7 @@ L46L45L45) o (<< uo miel) o (L65 uo miel) o uo migl) o uo - mir) o (L80+ uo + mir) o (L80+ uo miz) o uo m) o (L86L14_+ uo // mosties mon) o o @@ -1043,7 +975,7 @@ L46L45L45) o (<< uo v) ol (ej ol v) ol (t ol v) ol (u ol - z) ol (it ol + z) ol (it ol @z) ol (L01_ o:l // ..zols z) ol (L05_ uol // ..zole @@ -1138,7 +1070,7 @@ L46L45L45) o (<< uo hr) on (o on ikr) on (+ o:n im) on o>n - ir) on (i< o:n + ir) on (i< o:n is) on on itr) on o:n j) on (i on @@ -1205,23 +1137,21 @@ L46L45L45) o (<< uo ž) on (g oN .group oo - _aut) oo (stL01_ o:uo // autoosta + _aut) oo (stL01_ o:uo // autoosta k) oo (per o:o oo (_ oo: z) oo oo: .group op -L41L10L10L10sk) op (L01_ o: // ...skops - L41L10L10sk) op (L01_ o: - L41L10sk) op (L01_ o: - + L41Jsk) op (L01_ o:p // ...skops ad) op op cikl) op (L01_ o:p // ciklops d) op op eir) op (L04_ o:p eir) op op _gal) op (L01_ op // galops + k) op (pr uop // ..koppr.. k) op (en op // Kopenhāgena k) op (ēC op // ..kopēt../..kopēš.. k) op (ējL01_ uop // ..kopējs @@ -1280,7 +1210,7 @@ L41L10L10L10sk) op (L01_ o: // ...skops ab) or oR ak) or oR aleg) or o:R - alg) or oR + alg) or oR am) or oR a) or oR aut) or (i@ oR @@ -1513,7 +1443,7 @@ L41L10L10L10sk) op (L01_ o: // ...skops @@) oz (L05_ o:z // ..oze ozo (lL01_ uozuo // ..ozols oz (on oz - ozo (_ o:zuo + ozo (_ o:zuo p) oz oz _r) oz (eL88L05_ oz // rozete _r) oz (īL80L05_ oz // rozīne @@ -1554,7 +1484,7 @@ L41L10L10L10sk) op (L01_ o: // ...skops ŗ r .group s - sh s_!h_! // probably no need to make distinct in other places + sh s_!h_! // probably no need to make distinct in other places _) s (L61 s_ // make s distinct at start of the word before unvocied consonants s s