Merge branch 'development'

dictsource/bn_list

@@ -0,0 +1,278 @@
+// Translation rules for Bengali
+// This file is UTF8 encoded
+
+// Numbers
+ devanagari numbers are changed to latin characters before translation
+_0	S'u:n.nV'o:
+_1	a'k
+_2	d:UI
+_3	t'i:n
+_4	c'a:@'r
+_5	,pa~c
+_6	ch'O:j
+_7	S'a:t
+_8	'a:th.
+_9	n'O:j
+
+_10	d'O:S
+_11	a'g'a:rO:
+_12	b'a:rO:
+_13	t'a:rO:
+_14	ch:O:d'dO:
+_15	p'O:n'e:rO:
+_16	S'o:lO:
+_17	SO:t'e:rO:
+_18	a:th'e:rO:
+_19	U'n'IS
+
+_20	kU:'ri
+_21	e:kU'S
+_22	b'a:IS
+_23	t'e:IS
+_24	c'O:b'bIS
+_25	pa~O:c'IS
+_26	ch'a:'bb'IS
+_27	Sa:ta:S
+_28	ath'a:S
+_29	Unt'rIs
+_30	t'i:rIS
+
+_31	e:k't:rIS
+_32	bat:'rIS
+_33	tE't'rIS
+_34	ca~o:u:t'rIS
+_35	pa~O:it'rIS
+_36	cha'trIS
+_37	Sa~it'rIS
+_38	at'tr'IS
+_39	U'nO:cO:l'IS
+
+_40	co:l'lIS
+_41	e:k'co:l'lIS
+_42	bi'al'lIS
+_43	te:ta:l'lIS
+_44	cu:a:l'lIS
+_45	paI'nta:l'lIS
+_46	che:co:l'lIS
+_47	Sat'co:l'lIs
+_48	at'co:l'lIS
+_49	Uno:pan'ca:S
+
+_50	p@n'ca:s
+_51	e:ka:n'no:
+_52	ba:h@n'no:
+_53	t'Ip'pan'no:
+_54	cu:wan'no:
+_55	po:n'ca:n'no:
+_56	chh@p:'an'no:
+_57	Sa:ta:n'no:
+_58	ath'a:n'no:
+_59	Uno:s'ath
+
+_60	s'a:th.
+_61	e:k'so:t'tI
+_62	ba:so:t'tI
+_63	te:so:t'tI
+_64	ca~o:u:so:t'tI
+_65	pa~I'so:t'tI
+_66	che:so:t'tI
+_67	Sat'so:t'tI
+_68	atso:t'ti
+_69	,Uno:Sat'to:r
+
+_70	So:t'to:r
+_71	e:kat'to:r
+_72	ba:hat'to:r
+_73	tIat'to:r
+_74	cu:at'to:r
+_75	pa~chat'to:r
+_76	chI'at:to:r
+_77	Sa:t@'t:o:r
+_78	atat'to:r
+_79	,Uno:a:Si:
+
+_80	a:Si
+_81	e:ka:Si:
+_82	bI'ra:Si:
+_83	tIra:Si:
+_84	cu:ra:Si:
+_85	pa~ca:Si:
+_86	chIa:Si:
+_87	Sa:ta:Si:
+_88	O:sto:a:Si:
+_89	Uno:no:b'bo:I
+
+_90	no:b:bo:I
+_91	e:ka:no:b'bo:I
+_92	bIra:no:b'bo:I
+_93	tIr'a:no:b'bo:I
+_94	cu:r'a:no:b'bo:I
+_95	pa~ca:no:b'bo:I
+_96	chIa:no:b'bo:I
+_97	S@ta:no:b'bo:I
+_98	ata:no:b'bo:I
+_99	nIra:no:b'bo:I
+
+_0C	SO:
+_0M1	h@z'a:r
+_0M2	l'a:kh
+_0M3	ko:tI
+_0M4	o:r'bu:d
+_dpt	d@so:mIk
+
+// Single consonants
+ক	k@
+খ	kh@
+গ	g@
+ঘ	gh@
+ঙ	N'g
+চ	c@
+ছ	ch@
+জ	J@
+ঝ	Jh@
+ঞ	n^@
+ট	t.@
+ঠ	th.@
+ড	d.@
+ঢ	dh.@
+ণ	n.@   // retroflex n.@
+ত	t@
+থ	th@
+দ	d@
+ধ	dh@
+ন	n@
+প	p@
+ফ	ph@
+ব	b@
+ভ	bh@
+ম	m@
+য়	O:j
+য	J@
+র	r@
+ড়	r-@
+ঢ়	hr@
+ল	l@
+শ	S@
+ষ	s.@   //  retroflex [S]
+স	s@
+হ	H@
+ৎ	t@
+
+
+// combining vowel signs
+ा	#X2a:
+ि	#X1I
+ी	#X2i:
+ূ	#X1U
+ू	#X2u:
+ृ	#X1rI
+ে	#X1e:
+ৈ	#X2E:
+ো	#X1o:
+ৌ	#X1O:
+ॐ	#X1o~m
+
+
+// Punctuation
+।	dVn.d.V
+
+// Pronouns
+আমি 	$u	// main: I
+আমায়	$u
+আমার 	$u
+
+আমরা 	$u	// we
+আমাদের	$u
+
+আপনি	$u	// you(formal)
+আপনাকে	$u
+আপনার 	$u
+
+তুমি	$u	// you (informal)
+তোমায় 	$u
+তোমার 	$u
+তোমাদের 	$u
+
+তুই	$u	// you (informal)
+তোকে 	$u
+তোর 	$u
+
+এ	$u	// he/she/it
+একে 	$u
+এটার 	$u
+এর 	$u
+
+ইনি	$u	// they
+এনাকে	$u
+এনার 	$u
+
+ও	$u	// he/she/it
+সে 	$u
+ওর 	$u
+তার 	$u
+
+ওরা	$u	// they
+তারা	$u
+ওদের	$u	// unheṃ: them 
+তাদের	$u
+
+এই	$u	// e:I this/it
+এটা 	$u	// e:ta: this/it
+এটার 	$u	// e:ta:'r  this/it
+এর 	$u	// e:r  this/it
+
+ওটা	$u	// o:ta: that
+ওটাকে 	$u	// o:ta:ke: to that
+ওটার 	$u	// o:ta:'r  of that
+
+ওগুলো	$u	// o:gu:lo: those
+ওগুলোকে $u	// o:gu:lo:ke: to those
+ওগুলোর 	$u	// o:gu:lo:'r  of those
+
+
+
+// Prepositions/Postpositions
+মধ্যে	$u	// moddhe  in
+উপর	$u	// upor    on, above
+নীচে	$u	// niche   below
+
+পূর্ব্বে	$u	// purbe   before, prior
+পর্য্যন্ত 	$u	// parjonto  till
+অব্দি	$u 	// abdi      till
+বিনা	$u	// bina      without
+
+
+
+// Questions
+কেন	$u $pause	// kano why  interrogative particle
+কি	$u $pause	// ki  what
+কোথায়	$u $pause	// kothaay  where
+কখন	$u $pause	// kakhon   when
+কে	$u $pause	// ke       who
+
+// Conjunctions
+
+এবং	$u $pause	// ebong: and
+আর	$u $pause	// aar: and
+অথবা	$u $pause	// athoba: or
+কিন্তু	$u $pause	// kintu: but
+যদি	$pause	// jodi: if
+তবু	$pause	// tobu: still, yet
+তবে	$pause	// tabe: if...then
+অথচ	$u	// athacho: yet
+
+
+// Verbs
+
+ছিল	$u	// chilo: past aux
+ছিলেন 	$u	// chilen
+
+
+করছি 	$u	// korchi: continuous
+করছিলাম	$u	// korchilam: past indefinite
+করেছি 	$u	// korechi: past
+
+
+// Exceptions
+ক্রিকেট        krIk'Et
+সাইবার        s'aIb@r

dictsource/bn_rules

@@ -0,0 +1,316 @@
+
+// This file is UTF8 encoded 
+
+// letter groups:
+// A   vowel letters and vowel signs
+// B   vowel signs and virama ्
+// C   consonants
+// Y   vowel letters and vowel signs
+
+// conditional rules
+// ?2   use diphthong for "ai"
+// ?3   use diphthong for "au"
+
+
+.replace
+ ০	0
+ ১	1
+ ২	2
+ ৩	3
+ ৪	4
+ ৫	5
+ ৬	6
+ ৭	7
+ ৮	8
+ ৯	9
+
+
+// Vowels
+
+
+.group অ
+       অ        a
+      
+
+.group আ
+       আ        a:
+
+.group ই
+        ই        I
+        ইঁ        i~
+        ইং        I'ng
+
+.group ঈ
+        ঈ        i:
+        ঈ (_     i
+
+.group উ
+        উ        U
+
+.group ঊ
+        ঊ        u:
+        ঊং        u~  // + anusvara
+        ঊঁ        u~  // + candrabinbu
+
+.group ঋ
+        ঋ        rI
+
+.group এঁ
+        এঁ        E   // candra e
+
+.group ঐ
+        ঐ        e
+
+.group এ
+        এ        e:
+
+.group ঐ
+        ঐ        E:  // ?? [aI] [E:] [&:] 
+        ঐং        E~
+        ঐঁ        E~
+?2      ঐ        aI  // ?? [aI] [E:] [&:] 
+
+
+.group ওঁ
+        ওঁ        O  // candra O
+
+.group ঔ
+        ঔ        o
+
+.group ও
+        ও        o:
+        ওং        o~   // +anusvara
+        ওঁ        o~   // +candrabindu
+
+.group ঔ
+        ঔ        O:  // ?? [aU] [O:]
+        ঔঁ        O~  // +candrabindu
+
+
+// Vowel Signs
+
+.group া
+       া          a:
+       
+.group ি
+       ি        I
+    
+.group ী
+       ী        i:
+       ী (_  i
+
+.group ূ
+       ূ        U
+
+.group ু
+       ু        u:
+     
+.group ৃ
+       ৃ        rI
+
+.group ে
+       ে        e:
+
+.group ৈ
+       ৈ        E:    // ?? [aI] [E:] [&:] 
+    
+.group ো
+       ো        o:
+  
+.group ৌ
+       ৌ        O:    //  [O:] or [aU] ??
+  
+.group ॐ
+        ॐ        o~m
+
+// Consonants
+
+.group ক
+        ক        k@
+        ক (B     k
+        ক্য (्য    kja:
+        ক্ষ            kh'@
+
+.group খ
+        খ        khV
+        খ (B  kh@
+  
+.group গ
+        গ        gV
+        গ (B  g@
+    ঈ)গ (ল   g@
+
+.group ঘ
+        ঘ        ghV
+        ঘ (B  gh
+
+.group ঙ
+        ঙ        N'g
+        ঙ্ (B     N
+    গা)ঙ (চি     Ng@
+
+.group চ
+        চ        cV
+        চ (B     c
+  ্য) চ্য     c'j@
+
+.group ছ
+        ছ        chV
+        ছ  (B  ch@
+
+.group জ
+        জ        J@
+        জ (B  J@
+  ্) জ        zV
+        জ (B  J@
+
+.group ঝ
+        ঝ        Jh@
+        ঝ (B  Jh@
+
+.group ঞ
+        ঞ        n^V
+        ঞ্ (B     n^
+   
+.group ট
+        ট        tV
+        ট (B     tV
+        ট (्য়      t.j@
+
+.group ঠ
+        ঠ        thV
+        ঠ (B  th.
+
+.group ড
+        ড        d.V
+        ড (B     d.
+
+.group ঢ
+       ঢ        dh.V
+       ঢ (B     dh.
+.group ণ
+        ণ        n.V   // (temporary) same as dental [n]
+        ণ (B     n.
+        ণ্ম       n.m
+
+
+.group ত
+        ত        t@
+        ত (B  t@
+              
+.group থ
+        থ        th@
+        থ (B  th.
+ ক) থ (ন    th@
+
+.group দ
+        দ        d@
+        দ (B     d.
+ ব) দ (ল     d@
+
+.group ধ
+        ধ        dh@
+        ধ (B     dh.
+ সা) ধ (ন         dh@
+
+.group ন
+        ন        n@
+        ন  (B     n@
+  ্) ন (্          n@
+   র্) ন (_     r.n          // r +virama অর্ণব
+
+
+.group ন
+        ন        n:     // should this be a long [n] ?
+
+.group প
+        প        p@
+        প (B     p
+        প্য (्য    p:
+
+.group ফ
+        ফ        ph@
+        ফ (B     ph@
+        ফ        ph@
+  
+
+.group ব
+        ব        b@
+        ব (B     b@
+
+.group ভ
+        ভ        bh@
+        ভ (B     bh@
+
+.group ম
+        ম        mV
+ ्) ম (_  mV
+   র্) ম (_ r.m@          // r +virama
+   ন্) ম (_ n.m          // n +virama
+
+.group য়
+        য়            jV
+        য় (B    jV    
+    
+.group য
+        য       J@
+        য (B    J@     
+ ्) য (_    ja
+
+.group র
+        র        rV
+        র (B     r
+ ्) র (_     r@
+
+
+.group ল
+        ল         l
+        ল  (B  l@
+  ক) ল  (ম    l@
+
+
+.group শ
+        শ        S@
+        শ (B     S@
+
+.group ষ
+        ষ        s   
+        ষ (B     s    //??
+
+.group স
+        স        s@
+        স (B     s.
+
+.group হ
+        হ        H@  
+        হ (B     H@
+       হ্ব       v@
+.group হ্ব 
+  B) হ্ব (B v@
+     
+.group ৎ
+        ৎ (B     t@t
+
+
+
+                       // nukta,  modifies a consonant
+
+.group ্যা                // ja'falaa 
+        ্যা       a
+
+.group ँ
+	ँ	n	// candrabindu
+
+.group ং
+       ং        aN'g   //  anusvara
+
+.group ः
+        ः        H   //  visarga
+
+.group ্		// virama
+	্
+
+
+
+
+

dictsource/en_list

@@ -187,7 +187,7 @@ _‴	trIp@LpraIm
 _‼	Ekskla#m'eIS@nz
 _₠	jU@roU
 
-+	plVs  $max3
++	plVs
 #	haS   $max3
 @	_at_	$u+
 &	_and   $u+
@@ -1196,6 +1196,7 @@ convent		k0nv@nt
 converse	$1 $only
 converse	$verb
 convert		$1 $noun
+convict		$1
 convict		$2 $verb
 convolute	k0nv@l'u:t
 coop		ku:p
@@ -1961,6 +1962,7 @@ mercedes	m3:s'eIdi:z
 //mercenary	m3:s@n@rI
 merest		mi@r@st
 meringue	m@raN
+meson		mi:z0n
 metabolic	mEt@b'0lIk
 metaphor	mEt@fO@
 metastable	$alt1

dictsource/en_rules

@@ -1,6 +1,6 @@
 
 // ***************************************************************************
-// *   Copyright (C) 2005 to 2010 by Jonathan Duddington                     *
+// *   Copyright (C) 2005 to 2013 by Jonathan Duddington                     *
 // *   email: [email protected]                                    *
 // *                                                                         *
 // *   This program is free software; you can redistribute it and/or modify  *
@@ -1601,7 +1601,7 @@
             co (ntrol+   k@
             conva (l     k0nv@
          _) co (nvenA    k@
-         _) co (nvi      k0#
+         _) con (vi      k%0#n
          _) co (nvoy     k0
          _) co (nw       k0
          _) copy         k0pI
@@ -1734,7 +1734,7 @@
          _) des (k       dEs
             des (ol      dEs
             des (pot     dEs
-         _) dess         dI2z
+         _) dess (er     dI2z
             desta (b     d%i:steI
             desti        dEstI
             des (ul      d%i:s
@@ -2547,7 +2547,7 @@
          v) es (t+       Es
       harv) es (t        Is
             esti (m      EstI#
-            es (ty       @s
+         &) es (ty       @s
 
 .group et
          _) et (on       i:t
@@ -2994,6 +2994,7 @@
             iah (_       'aI@
             ia (m        i@
          &) ia (n        i@
+         @) ia (nd       I'a
          @) ia (nic      I'a
          @) ia (nit      I'a
          @) ia (na_      i:'a
@@ -3394,8 +3395,8 @@
             iority       I'0rI2t%I
             iou (rA      j@
             iour (K      j3
-         @) ious (_      =I2@s
-         g) ious (_      =@s
+         @) ious         =I2@s
+         g) ious         =@s
             ioux         u:
         _r) io (t        aI@
             io (t_       I|@
@@ -5881,6 +5882,7 @@
         &d) Ed (_S2vei   I#d
        &ch) Ed (_S2vei   t
         &k) Ed (_S2vei   t
+       ril) Ed (_S2      d
      &@@om) Ed (_S2v     d
         &p) Ed (_S2vei   t
         &t) Ed (_S2vei   I#d

dictsource/hi_list

@@ -2,12 +2,12 @@
 
 // Numbers
 // devanagari numbers are changed to latin characters before translation
-_0        S'u:n.jV
+_0        s'u:n.jV
 _1        'e:k
 _2        d'o:
 _3        t'i:n
-_4        c'a:r:
-_5        p'a:nc
+_4        c:'a:r:
+_5        'pa~c
 _6        ch'@2
 _7        s'a:t
 _8        'a:th.
@@ -15,30 +15,30 @@ _9        n'O:
 ?3  _9    n'aU
 
 _10       d'Vs
-_11       gj'a:r@2
-_12       b'a:r@2
-_13       t'E:r@2
-_14       ch'O:d@2
-_15       p'Vndr@2
-_16       s'o:l@2
-_17       s'Vt:r@2
-_18       Vth.:'a:r@2
+_11       gj'a:r-ah
+_12       b'a:rah
+_13       t'e:r@2h
+_14       ch'O:d@2h
+_15       p'Vndr@2h
+_16       s'o:l@2h
+_17       sVtr@2h
+_18       a:th:arah
 _19       Unn'Is
 
 _20       b'i:s
 _21       Ik:'Is
 _22       b'a:Is
-_23       t'e:Is
+_23       t'ue:Is
 _24       c'O:bIs
 _25       p@c:'Is
 _26       ch@bb'i:rs
 _27       s@t:'a:Is
 _28       ath:'a:Is
-_29       Unt'Is
+_29       ,Unt'Is
 _30       t'i:s
 
 _31       Ik@t:'Is
-_32       bat:'Is
+_32       b'at:'I'S
 _33       tE~t'Is      // E~ ?
 _34       cO~t'Is
 _35       pE~t'Is
@@ -65,16 +65,16 @@ _53       t'IrpVn
 _54       c'Ou:wVn
 _55       p'achpVn
 _56       chh@p:'Vn
-_57       sVt:'a:w@n
-_58       ath:'a:w@n
+_57       santa:'w@n
+_58       ath:a:'w@n
 _59       Uns'Vth
 
 _60       s'a:th.
 _61       'Iks@th.
 _62       b'a:s@th.
 _63       t'Irs@th.
-_64       c'O~s@th.
-_65       paIns@th.
+_64       cO:'s@th.
+_65       paI's@th.
 _66       ch'Ija:s@th.
 _67       s'Vrs@th.
 _68       ars@th.
@@ -92,15 +92,15 @@ _78       athhat:'Vr:
 _79       ,Un^Ia:s'i:
 
 _80       ,Vss'i:
-_81       Ikja:s'i:
-_82       baIa:s'i:
-_83       tIra:s'i:
-_84       cO:ra:s'i:
-_85       pI'ca:s'i:
-_86       chIja:s'i:
-_87       sVt:a:s'i:
-_88       ath:a:s'i:
-_89       nVwa:s'i:
+_81       Ikja:s'i
+_82       baIa:s'i
+_83       tIra:s'i
+_84       cO:ra:s'i
+_85       pI'ca:s'i
+_86       chIja:s'i
+_87       sVt:a:s'i
+_88       ath:a:s'i
+_89       nVwa:s'i
 
 _90       nVb:'e:
 _91       Ikj'a:n@we:
@@ -114,9 +114,9 @@ _98       ath:'a:n@we:
 _99       nIn^j'a:n@we:
 
 _0C	s'O:
-_0M1	h@z'a:r
+_0M1	h@J,a:r
 _0M2	l'a:kh
-_0M3	cr'ore
+_0M3	k@ro:r.V
 _0M4	'Vr@b
 _0M5	kh'Vr@b
 _dpt      _d@s@ml'o:_        // ?? what is Hi for "." ?
@@ -162,7 +162,7 @@ _dpt      _d@s@ml'o:_        // ?? what is Hi for "." ?
 श      S@
 ष      s.@   //  retroflex [S]
 स      s@
-ह      H@
+ह      H@-
 क़      q@
 ख़      x@
 ग़      Q@
@@ -199,14 +199,14 @@ _dpt      _d@s@ml'o:_        // ?? what is Hi for "." ?
 ।	dVn.d.V
 
 // Pronouns
-मैं 	$u	// main: I
+मैं 	$u	// main: IrI
 मुझे 	$u
 मेरा 	$u
 मेरी 	$u
 मेरे 	$u
 
 हम 	$u	// we
-हमें 	$u
+हमे 	$u
 हमारा 	$u
 हमारी 	$u
 हमारे 	$u
@@ -234,7 +234,7 @@ _dpt      _d@s@ml'o:_        // ?? what is Hi for "." ?
 इसका 	$u
 
 ये 	$u	// they
-इन्हें 	$u
+इन्हें	$u
 इनका 	$u
 
 वह	$u	// he/she/it
@@ -246,7 +246,7 @@ _dpt      _d@s@ml'o:_        // ?? what is Hi for "." ?
 
 वे	$u	// they
 वो 	$u
-उन्हें	$u	// unheṃ: them 
+उन्हे	$u	// unheṃ: them 
 उनका	$u
 उनकी	$u
 उनके	$u

dictsource/hi_rules

@@ -1,5 +1,5 @@
 
-// This file is UTF8 encoded 
+// This file is UTF8 encoded
 
 // letter groups:
 // A   vowel letters and vowel signs
@@ -28,423 +28,423 @@
 // Vowels
 
 .group अ
-        अ        V
-        अ (ह     E       //  (h
-    अह) अ        E
+        अ          V
+        अ (ह       E         //  (h
+    अह) अ          E
 
 .group आ
-        आ        a:
+        आ          a:
 
 .group इ
-        इ        I
+        इ          I
 //       इँ        i~
 //       इं        i~
 
 .group ई
-        ई        i:
-        ई (_     i
+        ई          i:
+        ई (_       i
 
 .group उ
-        उ        U
+        उ          U
 
 .group ऊ
-        ऊ        u:
-        ऊं        u~  // + anusvara
-        ऊँ        u~  // + candrabinbu
+        ऊ          u
+        ऊं         u~        // + anusvara
+        ऊँ         u~        // + candrabinbu
 
 .group ऋ
-        ऋ        rI
+        ऋ          rI
 
 .group ऌ
-        ऌ        l-   // vocalic l
+        ऌ          l-        // vocalic l
 
 .group ऍ
-        ऍ        E   // candra e
+        ऍ          E         // candra e
 
 .group ऎ
-        ऎ        e
+        ऎ          e
 
 .group ए
-        ए        e:
+        ए          e:
 
 .group ऐ
-        ऐ        E:  // ?? [aI] [E:] [&:] 
-        ऐं        E~
-        ऐँ        E~
-?2      ऐ        aI  // ?? [aI] [E:] [&:] 
+        ऐ          E:        // ?? [aI] [E:] [&:]
+        ऐं         E~
+        ऐँ         E~
+?2      ऐ          aI        // ?? [aI] [E:] [&:]
 
 
 .group ऑ
-        ऑ        O  // candra O
+        ऑ          O         // candra O
 
 .group ऒ
-        ऒ        o
+        ऒ          o
 
 .group ओ
-        ओ        o:
-        ओं        o~   // +anusvara
-        ओँ        o~   // +candrabindu
+        ओ          o:
+        ओं         o~        // +anusvara
+        ओँ         o~        // +candrabindu
 
 .group औ
-        औ        O:  // ?? [aU] [O:]
-        औं        O~  // +anusvara
-        औँ        O~  // +candrabindu
-?3      औ        aU  // ?? [aU] [O:]
+        औ          O:        // ?? [aU] [O:]
+        औं         O~        // +anusvara
+        औँ         O~        // +candrabindu
+?3      औ          aU        // ?? [aU] [O:]
 
 
 // Vowel Signs
 
 .group ा
         ा          a:
-        ाव       aU
+        ाव         aU
 
 .group ि
-        ि        I
+        ि          I
 //      िँ       i~
 //      िं       i~
 
 .group ी
-        ी        i:
-        ी (_     i
+        ी          i:
+        ी (_       i
 
 .group ु
-        ु        U
+        ु          u
 
 .group ू
-        ू        u:
-        ूं        u~    // or O~   ??
-        ूँ        u~
+        ू          u:
+        ूं         u~        // or O~   ??
+        ूँ         u~
 
 .group ृ
-        ृ        rI
+        ृ          rI
 
 .group ॄ
-        ॄ        rI
+        ॄ          rI
 
 .group ॅ
-        ॅ        E
+        ॅ          E
 
 .group ॆ
-        ॆ        e
+        ॆ          e
 
 .group े
-        े        e:
+        े          e:
 
 .group ै
-        ै        E:    // ?? [aI] [E:] [&:] 
-        ैं        E~
-        ैँ        E~
-?2      ै        aI    // ?? [aI] [E:] [&:] 
+        ै          E:        // ?? [aI] [E:] [&:]
+        ैं         E~
+        ैँ         E~
+?2      ै          aI        // ?? [aI] [E:] [&:]
 
 .group ॉ
-        ॉ        O
+        ॉ          O
 
 .group ॊ
-        ॊ        o
+        ॊ          o
 
 .group ो
-        ो        o:
-        ों       o~
-        ोँ       o~
+        ो          o:
+        ों         o~
+        ोँ         o~
 
 .group ौ
-        ौ        O:    //  [O:] or [aU] ??
-        ौं       O~   
-        ौँ       O~   
-?3      ौ        aU    //  [O:] or [aU] ??
+        ौ          O:        //  [O:] or [aU] ??
+        ौं         O~
+        ौँ         O~
+?3      ौ          aU        //  [O:] or [aU] ??
 
 .group ॢ     // vowel sign l
-        ॢ        l-
+        ॢ          l-
 
 .group ॣ    // vowel sign ll
-        ॣ        l-:
+        ॣ          l-:
 
 .group ॐ
-        ॐ        o~m
+        ॐ          o~m
 
 // Consonants
 
 .group क
-        क        kV
-        क (B     k
-        क (्य    k:
-        क़        qV
-        क़ (B     q
+        क          kV
+        क (B       k
+        क (्य      k:
+        क़         qV
+        क़ (B      q
 
 .group ख
-        ख        khV
-        ख (B     kh
-        ख़        xV
-        ख़ (B     x
+        ख          khV
+        ख (B       kh
+        ख़         xV
+        ख़ (B      x
 
 .group ग
-        ग        gV
-        ग (B     g
-        ग़        QV
-        ग़ (B     Q
+        ग          gV
+        ग (B       g
+        ग़         QV
+        ग़ (B      Q
 
 .group घ
-        घ        ghV
-        घ (B     gh
+        घ          ghV
+        घ (B       gh
 
 .group ङ
-        ङ        NV
-        ङ (B     N
-     ्) ङ (_     N@
+        ङ          NV
+        ङ (B       N
+     ्) ङ (_       N@
 
 .group च
-        च        cV
-        च (B     c
-        च (्य    c:
+        च          cV
+        च (B       c
+        च (्य      c:
 
 .group छ
-        छ        chV
-        छ (B     ch
+        छ          chV
+        छ (B       ch
 
 .group ज
-        ज        JV
-        ज (B     J
-        ज़        zV
-        ज़ (B     z
+        ज          JV
+        ज (B       J
+        ज़         zV
+        ज़ (B      z
 
 .group झ
-        झ        JhV
-        झ (B     Jh
+        झ          JhV
+        झ (B       Jh
 
 .group ञ
-        ञ        n^V
-        ञ (B     n^
-     ्) ञ (_     n^
+        ञ          n^V
+        ञ (B       n^
+     ्) ञ (_       n^
 
 .group ट
-        ट        t.V
-        ट (B     t.
-        ट (्य    t.:
+        ट          t.V
+        ट (B       t.
+        ट (्य      t.:
 
 .group ठ
-        ठ        th.V
-        ठ (B     th.
+        ठ          th.V
+        ठ (B       th.
 
 .group ड
-        ड        d.V
-        ड (B     d.
+        ड          d.V
+        ड (B       d.
 
-        ड़        r.V
-        ड़ (B     r.
+        ड़         r.V
+        ड़ (B      r.
 
 .group ढ
-        ढ        dh.V
-        ढ (B     dh.
-        ढ़        r.hV  // nukta  (should retroflex flap)
-        ढ़ (B     r.h   // nukta
+        ढ          dh.V
+        ढ (B       dh.
+        ढ़         r.hV      // nukta  (should retroflex flap)
+        ढ़ (B      r.h       // nukta
 
 .group ण
-        ण        n.V   // (temporary) same as dental [n]
-        ण (B     n.
-     ्) ण (_     n.@
+        ण          n.V       // (temporary) same as dental [n]
+        ण (B       n.
+     ्) ण (_       n.@
 
 .group त
-        त        tV
-        त (B     t
-        त (्य    t:
+        त          tV
+        त (B       t
+        त (्य      t:
 
 .group थ
-        थ        thV
-        थ (B     th
+        थ          thV
+        थ (B       th
 
 .group द
-        द        dV
-        द (B     d
+        द          dV
+        द (B       d
 
 .group ध
-        ध        dhV
-        ध (B     dh
+        ध          dhV
+        ध (B       dh
 
 .group न
-        न        nV
-        न (B     n
-     ्) न (_     n@
-     र्) न (_     n          // r +virama
+        न          nV
+        न (B       n
+     ्) न (_       n@
+    र्) न (_       n         // r +virama
 
 
 .group ऩ
-        ऩ        n:     // should this be a long [n] ?
+        ऩ          n:        // should this be a long [n] ?
 
 .group प
-        प        pV
-        प (B     p
-        प (्य    p:
+        प          pV
+        प (B       p
+        प (्य      p:
 
 .group फ
-        फ        phV
-        फ (B     ph
-        फ़        fV
-        फ़ (B     f
+        फ          phV
+        फ (B       ph
+        फ़         fV
+        फ़ (B      f
 
 .group ब
-        ब        bV
-        ब (B     b
+        ब          bV
+        ब (B       b
 
 .group भ
-        भ        bhV
-        भ (B     bh
+        भ          bhV
+        भ (B       bh
 
 .group म
-        म        mV
-        म (B     m
-     ्) म (_     m@
-     र्) म (_     m          // r +virama
-     न्) म (_     m          // n +virama
+        म          mV
+        म (B       m
+     ्) म (_       m@
+    र्) म (_       m         // r +virama
+    न्) म (_       m         // n +virama
 
 .group य
-        य        jV
-        य (B     j
-     ्) य (_     j@
+        य          j@
+        य (B       j
+     ्) य (_       j@
 
 .group र
-        र        rV
-        र (B     r
-     ्) र (_     r@
+        र          rV
+        र (B       r
+     ्) र (_       r@
 
 .group ऱ             // rra
-        ऱ        rV   // (temporary) same as [r]
-        ऱ (B     r
-     ्) ऱ (_     r@
+        ऱ          rV        // (temporary) same as [r]
+        ऱ (B       r
+     ्) ऱ (_       r@
 
 .group ल
-        ल        lV
-        ल (B     l
-     ्) ल (_     l@
+        ल          lV
+        ल (B       l
+     ्) ल (_       l@
 
 .group ळ
-        ळ        l.V
-        ळ (B     l.
-     ्) ळ (_     l.@
+        ळ          l.V
+        ळ (B       l.
+     ्) ळ (_       l.@
 
 .group ऴ
-        ऴ        l.V  // (temporary) same as [l.]
-        ऴ (B     l.
-     ्) ऴ (_     l.@
+        ऴ          l.V       // (temporary) same as [l.]
+        ऴ (B       l.
+     ्) ऴ (_       l.@
 
 .group व
-        व        vV
-        व (B     v
-     _) व        wV
-     _) व (B     w
-     _) व (्     v   // +virma
+        व          vV
+        व (B       v
+     _) व          wV
+     _) व (B       w
+     _) व (्       v         // +virma
 
 .group श
-        श        SV
-        श (B     S
+        श          SV
+        श (B       S
 
 .group ष
-        ष        s.V   //?? or retroflex [S]
-        ष (B     s.    //??
+        ष          s.V       //?? or retroflex [S]
+        ष (B       s.        //??
 
 .group स
-        स        sV
-        स (B     s
+        स          sV
+        स (B       s
 
 .group ह
-        ह        HV
-        ह (B     H
+        ह          H
+        ह (B       H
 
 
                         // nukta,  modifies a consonant
 
 .group ऽ                // avagraha, lengthens a vowel ??
-        ऽ        :
+        ऽ          :
 
 .group ँ
-	ँ	n	// candrabindu
-
-.group ं 
-        ं        n     // anusvara
-        ं  (प    m
-        ं  (फ    m
-        ं  (ब    m
-        ं  (भ    m
-        ं  (म    m
-
-        ं  (ट    n.
-        ं  (ठ    n.
-        ं  (ड    n.
-        ं  (ढ    n.
-        ं  (ण    n.
-
-        ं  (च    n^
-        ं  (छ    n^
-        ं  (ज    n^
-        ं  (झ    n^
-        ं  (ञ    n^
-        ं  (य    n^
-
-        ं  (क    N
-        ं  (ख    N
-        ं  (ग    N
-        ं  (घ    N
-        ं  (ङ    N
-        ं  (ह    N
+        ँ          n         // candrabindu
+
+.group ं
+        ं          n         // anusvara
+        ं (प       m
+        ं (फ       m
+        ं (ब       m
+        ं (भ       m
+        ं (म       m
+
+        ं (ट       n.
+        ं (ठ       n.
+        ं (ड       n.
+        ं (ढ       n.
+        ं (ण       n.
+
+        ं (च       n^
+        ं (छ       n^
+        ं (ज       n^
+        ं (झ       n^
+        ं (ञ       n^
+        ं (य       n^
+
+        ं (क       N
+        ं (ख       N
+        ं (ग       N
+        ं (घ       N
+        ं (ङ       N
+       
 
 .group ः
-        ः        H   //  visarga
+        ः          H         //  visarga
 
 .group ्		// virama
-	्
+् 
 
 // Extra consonants
 
 .group क़   // qa
-        क़        qV
-        क़ (B     q
+        क़          qV
+        क़ (B       q
 
 .group ख़   // khha
-        ख़        xV
-        ख़ (B     x
+        ख़          xV
+        ख़ (B       x
 
 .group ग़    // ghha
-        ग़        QV
-        ग़ (B     Q
+        ग़          QV
+        ग़ (B       Q
 
 .group ज़    // za
-        ज़        zV
-        ज़ (B     z
+        ज़          zV
+        ज़ (B       z
 
 .group ड़    // dddha   (should retroflex flap)
-        ड़        r.V
-        ड़ (B     r.
+        ड़          r.V
+        ड़ (B       r.
 
 .group ढ़    // rha  (aspirated version of dddha)
-        ढ़        r.hV
-        ढ़ (B     r.h
+        ढ़          r.hV
+        ढ़ (B       r.h
 
 .group फ़    // fa
-        फ़        fV
-        फ़ (B     f
+        फ़          fV
+        फ़ (B       f
 
 .group य़    // yya
-        य़        jV
-        य़ (B     j
+        य़          jV
+        य़ (B       j
 
 .group ॠ    // rr
-        ॠ        V-rr
+        ॠ          V-rr
 
 .group ॡ    // ll
-        ॡ        l-:     // long syllabic l
+        ॡ          l-:       // long syllabic l
 
 
 // If we find a Latin letter a-z, then translate as English
 // (This is now done automatically by the eSpeak program)
 
 .group o
-	o	_^_EN
-     D__) of (__D    me
+        o          _^_EN
+   D__) of (__D    me
 
 
 
 
 .group
-        $        dOlV
-        %        pVsEnt
+        $          dOlV
+        %          pVsEnt
 
 

dictsource/ml_list

@@ -87,33 +87,65 @@ _!	a:S;c@rjacihn@m
 // numbers
 _0	p'u:Jj@m
 _1	'onny
-_2	r'an.t.y
-_3	m'unny
+_2	r@n.d#y
+_3	m'u:nny
 _4	n'a:ly
 _5	'an^cy
-_6	'aR2y
+_6	'a:R2y
 _7	'e:r.y
 _8	'et.t.y
 _9	'onpaty
-_1X	p'ati
 _10	p'atty
+_1X	p'ati
+
 _11	p'atinonny
 _12	p'antran.t.y
-_15	p'atinan^cy
-_16	p'atinaR2y
-_17	p'atine:R2y
-_18	p'atine:t.t.y
 _19	p'attompatu
-_2X	'irupat
-_3X	m'uppat
-_4X	n'a:lppat
-_5X	'anpat
-_6X	'aR2upat
-_7X	'er.upat
-_8X	'en.pat
-_9X	t'on.n.u:R2
+_20	'irup'aty
+_2X	'irupatti
+_30	m'uppaty
+_3X	m'uppatti':
+_40	n'a:lppaty
+_4X	n'a:lppatti
+_50	'anpaty
+_5X	'anpatti
+_60	'aR2upaty
+_6X	'aR2upatti
+_70	'er.'upaty
+_7X	'er.'upatti
+_80	'en.paty
+_8X	'en.patti
+_90	t'on.n.u:r:
+_9X	t'on.n.u:t.t.i
+
 _0C	n'u:R
-_0M1	'a:jiRam
-_0M2	l'aks.am
+_1C0	n'u:r:
+_1C	n'u:t.t.i
+_2C0	irunn'u:r
+_2C	irunn'u:t.t.i
+_3C0	munn'u:r
+_3C	munn'u:t.t.i
+_4C0	na:nnu:r
+_4C	na:nnu:t.t.i
+_5C0	'an^cu:r
+_5C	'an^cu:t.t.i
+_6C0	aR2unu:r
+_6C	aR2unu:t.t.i
+_7C0	'er.'unu:r
+_7C	'er.'unu:t.t.i
+_8C0	'en.n.u:r
+_8C	'en.n.u:t.t.i
+_9C0	tol.l.'a:jiRam
+_9C	tol.l.'a:jiRatti
+
+_0M1x	'a:jiRam
+_0M1	'a:jiRat.t.i
+_0M2x	l'aks.am
+_0M2	l'aks.at.t.i
 _0M3	k'o:t.i
+
 _dpt	_d'aS;a:mS;@m_
+
+
+
+

dictsource/ml_rules

@@ -1,5 +1,5 @@
 
-// This file is UTF8 encoded 
+// This file is UTF8 encoded
 // Spelling to phoneme rules for Malayalam
 
 // A means vowel letters (not vowel signs)
@@ -17,266 +17,267 @@
 ൭	7
 ൮	8
 ൯	9
-ോ	ോ 
+ോ	ോ
 ൊ	ൊ
 ൌ	ൌ
 
 
 
 .group ക
-	ക	ka
-	ക (B	k
+        ക          ka
+        ക (B       k
 
 .group ഖ
-	ഖ	kha
-	ഖ (B	kh
+        ഖ          kha
+        ഖ (B       kh
 
 .group ഗ
-	ഗ	ga
-	ഗ (B	g
+        ഗ          ga
+        ഗ (B       g
 
 .group ഘ
-	ഘ	gha
-	ഘ (B	gh
+        ഘ          gha
+        ഘ (B       gh
 
 .group ങ
-	ങ	Na
-	ങ (B	N
+        ങ          Na
+        ങ (B       N
 
 .group ച
-	ച	ca
-	ച (B	c
+        ച          ca
+        ച (B       c
 
 .group ഛ
-	ഛ	cha
-	ഛ (B	ch
+        ഛ          cha
+        ഛ (B       ch
 
 .group ജ
-	ജ	Ja
-	ജ (B	J
+        ജ          Ja
+        ജ (B       J
 
 .group ഝ
-	ഝ	Jha
-	ഝ (B	Jh
+        ഝ          Jha
+        ഝ (B       Jh
 
 .group ഞ
-	ഞ	n^a
-	ഞ (B	n^
+        ഞ          n^a
+        ഞ (B       n^
 
 .group ട
-	ട	t.a
-	ട (B	t.
+        ട          t.a
+        ട (B       t.
 
 .group ഠ
-	ഠ	th.a
-	ഠ (B	th.
+        ഠ          th.a
+        ഠ (B       th.
 
 .group ഡ
-	ഡ	d.a
-	ഡ (B	d.
+        ഡ          d.a
+        ഡ (B       d.
 
 .group ഢ
-	ഢ	dh.a
-	ഢ (B	dh.
+        ഢ          dh.a
+        ഢ (B       dh.
 
 .group ണ
-	ണ	n.a
-	ണ (B	n.
+        ണ          n.a
+        ണ (B       n.
 
 .group ത
-	ത	ta
-	ത (B	t
+        ത          ta
+        ത (B       t
 
 .group ഥ
-	ഥ	tha
-	ഥ (B	th
+        ഥ          tha
+        ഥ (B       th
 
 .group ദ
-	ദ	da
-	ദ (B	d
+        ദ          da
+        ദ (B       d
 
 .group ധ
-	ധ	dha
-	ധ (B	dh
+        ധ          dha
+        ധ (B       dh
 
 .group ന
-	ന	na
-	ന (B	n
+        ന          na
+        ന (B       n
 
 .group പ
-	പ	pa
-	പ (B	p
+        പ          pa
+        പ (B       p
 
 .group ഫ
-	ഫ	pha
-	ഫ (B	p
+        ഫ          pha
+        ഫ (B       p
 
-_പ്രൊ) ഫ (സര്	fa
+ _പ്രൊ) ഫ (സര്     fa
 
 
 .group ബ
-	ബ	ba
-	ബ (B	b
+        ബ          ba
+        ബ (B       b
 
 .group ഭ
-	ഭ	bha
-	ഭ (B	bh
+        ഭ          bha
+        ഭ (B       bh
 
 .group മ
-	മ	ma
-	മ (B	m
+        മ          ma
+        മ (B       m
 
 .group യ
-	യ	ja
-	യ (B	j
+        യ          ja
+        യ (B       j
 
 .group ര
-	ര	ra
-	ര (B	r
+        ര          ra
+        ര (B       r
 
 .group റ
-	റ	R2a
-	റ (B	R2
-     ന്) റ	d#
-	റ്റ	t.t.   // ?? R2R2 = t.t.
+        റ          R2a
+        റ (B       R2
+    ന്) റ          d#
+        റ്റ        t.t.      // ?? R2R2 = t.t.
 
 .group ല
-	ല	la
-	ല (B	l
+        ല          la
+        ല (B       l
 
 .group ള
-	ള	l.a
-	ള (B	l.
+        ള          l.a
+        ള (B       l.
 
 .group ഴ    // retroflex [r.] ?
-	ഴ	r.a
-	ഴ (B	r.
+        ഴ          r.a
+        ഴ (B       r.
 
 .group വ
-	വ	va
-	വ (B	v
+        വ          va
+        വ (B       v
 
 .group ശ
-	ശ	S;a
-	ശ (B	S;
+        ശ          S;a
+        ശ (B       S;
 
 .group ഷ
-	ഷ	s.a
-	ഷ (B	s.
+        ഷ          s.a
+        ഷ (B       s.
 
 .group സ
-	സ	sa
-	സ (B	s
+        സ          sa
+        സ (B       s
 
 .group ഹ
-	ഹ	ha
-	ഹ (B	h
+        ഹ          ha
+        ഹ (B       h
 
 
 // chillu consonants
 .group ൺ
-	ൺ	n.
+        ൺ          n.
 
 .group ൻ
-	ൻ	n
+        ൻ          n
 
 .group ർ
-	ർ	r
+        ർ          r
 
 .group ൽ
-	ൽ	l
+        ൽ          l
 
 .group ൾ
-	ൾ	l.
+        ൾ          l.
 
 .group ൿ
-	ൿ	k
+        ൿ          k
 
 
 .group 0xe0b4   // characters which start with UTF-8 bytes: [e0 b4]
 
-	ഽ	// avagraha
+        ഽ                    // avagraha
 
-	ം	m	// anusvara (this should nasalize the vowel)
+        ം          m         // anusvara (this should nasalize the vowel)
 
-	ഃ	h	// visarga
+        ഃ          h         // visarga
 
-	അ	a
+        അ          a
 
-	ആ	a:
+        ആ          a:
 
-	ഇ	i
+        ഇ          i
 
-	ഈ	i:
+        ഈ          i:
 
-	ഉ	u
+        ഉ          u
 
-	ഊ	u:
+        ഊ          u:
 
-	ഋ	Ry
+        ഋ          Ry
 
-	എ	e
-     _) എ	;e
+        എ          e
+     _) എ          ;e
 
-	ഏ	e:
-     _) ഏ	;e:
+        ഏ          e:
+     _) ഏ          ;e:
 
-	ഐ	aI
+        ഐ          aI
 
-	ഒ	o
+        ഒ          o
 
-	ഓ	o:
+        ഓ          o:
 
-	ഔ	aU
+        ഔ          aU
 
 // combining vowel signs
 
-	ാ	a:
+        ാ          a:
 
-	ി	i
-	ി  (ല്K     I
+        ി          i
+        ി (ല്K     I
 
 .group 0xe0b5   // characters which start with UTF-8 bytes: [e0 b5]
 
-	ീ	i:
+        ീ          i:
 
-	ു	u
+        ു          u
 
-	ൂ	u:
+        ൂ          u:
 
-	ൃ	r-
+        ൃ          r-
 
-	ൄ	r-:
+        ൄ          r-:
 
-	െ	e
+        െ          e
 
-	േ	e:
+        േ          e:
 
-	ൈ	aI
+        ൈ          aI
 
-	ൊ	o
+        ൊ          o
 
-	ോ	o:
+        ോ          o:
 
-	ൌ	aU
-	ൗ	aU   // au length mark, treat at [aU] ?
+        ൌ          aU
+        ൗ          aU        // au length mark, treat at [aU] ?
 
-	്	// virama
-	ൎ	// chillu-virama (unofficial)
-	്്	// espeak uses double-virama for "virama + U+200d" (zero-width joiner), to indicate a chillu character
-	്  (_   y //   epenthetic vowel at end of word
+        ്                    // virama
+        ൎ                    // chillu-virama (unofficial)
+        ്്                   // espeak uses double-virama for "virama + U+200d" (zero-width joiner), to indicate a chillu character
+        ് (_       y         //   epenthetic vowel at end of word
 
-	ൠ	Ry:
+        ൠ          Ry:
 
-	ൡ	ly:
+        ൡ          ly:
 
 
 
 .group 0xe0a4  // devanagari
-	0xe0a4  _^_HI  // switch to hindi voice
+        0xe0a4     _^_HI     // switch to hindi voice
+
 .group 0xe0a5  // devanagari
-	0xe0a5  _^_HI
+        0xe0a5     _^_HI
 
 
 .group
-	$	do:l.ar
+        $          do:l.ar

dictsource/pa_list

@@ -1,4 +1,4 @@
- 
+ 
 // This file is UTF8 encoded 		
 // Punjabi/Gurmukhi
 
@@ -24,14 +24,14 @@ _15	p'Vnd@Ra~
 _16	s'ol.a~
 _17	s@t'aRa~
 _18	Vth.'aRa~
-_19	'Uni
+_19	'Unni
 
 _20	v'iH
 _21	Ik:i
 _22	b'ai
 _23	t'ei
 _24	c'Ovi
-_25	p'VnJhi
+_25	p'Vc:i
 _26	ch'Vb:i
 _27	s@t'ai
 _28	Vth.'ai
@@ -40,79 +40,80 @@ _29	Un'Vt:i
 _30	t'iH
 _31	Ik'Vt:i
 _32	b'Vt:i
-_33	t'eti
-_34	c'O~ti
-_35	p'E~ti
+_33	t'et:i
+_34	c'ONti
+_35	p'ENti
 _36	ch'Vt:i
-_37	s'E~ti
+_37	s'ENti
+
 _38	Vth.'Vt:i
-_39	Un@t'ali
+_39	U~Nt'ali
 
 _40	c'ali
 _41	Ik@t'ali
-_42	b@t'ali
+_42	be'ali
 _43	t@R@t'ali
-_44	cOt'ali
-_45	p@nJ@t'ali
+_44	cUt'ali
+_45	p@nt'ali
 _46	chI'ali
 _47	s@nt'ali
-_48	Vth.:@t'ali
-_49	'Un.I~Ja
+_48	,@R2@t'ali
+_49	Un'VnJa
 
 _50	p@nJ'aH
-_51	'Ik@vI~Ja
-_52	b'VvI~Ja
-_53	t'VR@vI~Ja
-_54	c'VRI~Ja
-_55	p'Vc@vI~Ja
-_56	ch'VpI~Ja
-_57	s'Vt@vI~Ja
-_58	'Vth.:@vI~Ja
+_51	,@k@v'VnJa
+_52	b@v'VnJa
+_53	t,@R@v'VnJa
+_54	cUR'VnJa
+_55	p,@c@v'VnJa
+_56	ch@p'VnJa
+_57	s,@t@v'VnJa
+_58	,@th.@v'VnJa
 _59	Un.'ath.
 
 _60	s'Vth.:
-_61	Ik'ath.
-_62	b'ath.H
-_63	t@R'eth.H
-_64	c'Oth.H
-_65	p'E~th.
-_66	chI'ath.
-_67	s@t'aH@th.
-_68	Vth.:'ath.
+_61	Ik'aH@t.
+_62	b'aH@t.
+_63	t@R'e~H@t.
+_64	c'O~H@t.
+_65	p'E~H@t.
+_66	che'aH@t.
+_67	s@t'aH@t.
+_68	,@th.'aH@t.
 _69	Un.'Vt:@R
 
 _70	s'Vt:@R
-_71	IkH'Vt:@R
+_71	Ik'Vt:@R
 _72	b@H'Vt:@R
-_73	t@H'Vt:@R
+_73	t@H'et:@R
 _74	cOH'Vt:@R
-_75	p@nJ'Vt:@R
+_75	p@J'Vt:@R
 _76	chIH'Vt:@R
 _77	s@t'Vt:@R
 _78	Vth.'Vt:@R
 _79	Un.'asi
 
 _80	'Vssi
-_81	Ik'asi
-_82	bI'asi
-_83	t@R@'asi
-_84	c@R'asi
-_85	p@nJ'asi
-_86	chI'asi
+_81	,IkI;'asi
+_82	bI;'asi
+_83	t,@RI;'asi
+_84	cUR'asi
+_85	p@c'asi
+_86	chI;'asi
 _87	s@t'asi
 _88	Vth.'asi
-_89	Un.a~n@v'eN
+_89	Un'an@v,e~
 
 _90	n'Vb:e
-_91	Ik@'an@v,e~
-_92	bI;'an@v,e~
-_93	t@R@'an@ve~
-_94	c@R'an@ve~
-_95	p@c'an@ve~
+_91	Ik'an@v,e~
+_92	b'an@v,e~
+_93	t@R'a~n@v,e~
+_94	cUR'an@v,e~
+_95	p@c'an@v,e~
 _96	chI'an@ve~
 _97	s@t'an@ve~
 _98	Vth.'an@ve~
-_99	nIR'Vnn@ve~
+_99	n@R2'I~n@v,e~
 
 _0C	s'O
 _0M1	H@J'aR
@@ -130,8 +131,6 @@ _dpt	_dOth  // ??
 ੱ	VddVk
 ਃ	visaRg
 ੍	hVlVnt
-ॄ 	addak
-
 
 ਅ	'ERV
 ੲ	'IRI
@@ -157,15 +156,13 @@ _ਔ	'ERV||kVnOR'a
 ੌ	kVn'ORa
 
 ।	d.'Vnd.i
-₹ 	rupi
-
-
 ਸਰਕਾਰ	 sR@k'aR
  ਸਰਕਾਰੀ	sR@k'aRi
 
+$textmode
+ਸੋਫਟਵਿਅਰ  software
+ਈਮੇਲ   email
+ਕੀਬੋਰਡ  keyboard
+ਬੋਰਡ    board
+$phonememode
 
-// English words
-ਸੋਫਟਵਿਅਰ	 s'OftwER
-ਵੈਬਪੇਜ	w'EbpeIdZ
-ਈਮੇਲ	'i:meIl
-ਕੀਬੋਰਡ	k'i:boRd

dictsource/pt_list

@@ -647,6 +647,7 @@ almoço	$alt $verb
 amarelo		$alt
 ameba		$alt
 amores		$alt2
+antonieta	$alt2
 apego		$alt2 $noun
 apelo		$alt  $verb
 aposto		$alt  $verb
@@ -723,7 +724,7 @@ coice		$alt2
 colabore	$alt
 colete		$alt2
 colchete		$alt2
-colher	$alt $verb
+colher	$alt $noun
 colheres	$alt $noun
 colmeia		$alt
 colore		$alt
@@ -762,8 +763,6 @@ descordo	$alt
 desespero	$alt2 $noun
 desfecho	$alt2
 desprezo	$alt  $verb
-deva		$alt2
-devo		$alt2
 deveras		$alt
 dez		$alt
 diarreia	$alt
@@ -839,6 +838,8 @@ fogos		$alt
 foguete		$alt2
 foice		$alt2
 forca		$alt2
+força	$alt2 $noun
+forço	$alt
 forças		$alt2
 fordes	$alt2
 fores	$alt2

dictsource/pt_rules

@@ -407,6 +407,7 @@ respond) e (L07_   e         // cor-
    viv) e (L07_    e         // re-
     qu) e (brL04_  E
  _hosp) e (dL03_   E
+ _d) e (vL03_   e
    _gr) e (gL03_   e
     _n) e (grL03_  e
  _estr) ei (L03_   EI

dictsource/ur_list

@@ -164,4 +164,9 @@ _dpt	_ISaRI'Ia_
 
 // Exception of phonemes
 
+یہ	jE	$u
+کہ	kE	$u
+وہ	wo:	$u
+
+
 پاکستان	p'a:k'i:st'a:n

dictsource/ur_rules

@@ -19,7 +19,7 @@
 
 
 // vowel signs, alif acts as consonants  at start of word if these follow
-.L01  َ  ِ  ُ  و  ی   ع  ا
+.L01  َ ِ ُ و ی ع ا ے 
 
 
 // VOWELS
@@ -52,6 +52,7 @@
 _) ا	a
 _) او	u:
 _) ای	i:
+	ائ	a:j
 
 .group آ
 	آ	a:
@@ -68,13 +69,13 @@ _) ای	i:
 	وُ	u:
 	وٗ	u:
 	و (L01	v
-	_) و	v
+	_) و	vV
 
 .group ی
 	ی	e:
 	ی (L01	j
 	ی (_	i:
-	_) ی	j
+	_) ی	jV
 
 
 .group ے		// yeh barree

espeak-data/voices/id → espeak-data/voices/asia/id

@@ -1,4 +1,4 @@
-name indonesian-test
+name indonesian
 language id
 gender male
 

espeak-data/voices/asia/ka

@@ -0,0 +1,2 @@
+name georgian
+language ka

espeak-data/voices/test/ne → espeak-data/voices/asia/ne

@@ -1,4 +1,4 @@
-name nepali-test
+name nepali
 language ne
 gender male
 

espeak-data/voices/europe/bg

@@ -0,0 +1,5 @@
+name bulgarian
+language bg
+
+stressAmp 13 12 17 17 20 22 22 21 
+stressLength 180 170  200 200  200 200  210 220

espeak-data/voices/cy → espeak-data/voices/europe/cy

@@ -1,5 +1,5 @@
 language cy
-name welsh-test
+name welsh
 gender male
 
 intonation 4

espeak-data/voices/is → espeak-data/voices/europe/is

@@ -1,4 +1,4 @@
-name icelandic-test
+name icelandic
 language is
 gender male
 

espeak-data/voices/mk → espeak-data/voices/europe/mk

@@ -1,4 +1,4 @@
-name macedonian-test
+name macedonian
 language mk
 gender male
 

espeak-data/voices/ru → espeak-data/voices/europe/ru

@@ -1,4 +1,4 @@
-name russian_test
+name russian
 language ru
 gender male
 

espeak-data/voices/ka

@@ -1,2 +0,0 @@
-name georgian-test
-language ka

espeak-data/voices/test/bg

@@ -1,5 +0,0 @@
-name bulgarian-test
-language bg
-
-stressAmp 13 12 17 17 20 22 22 21 
-stressLength 180 170  200 200  200 200  210 220

espeak-data/voices/test/ga

@@ -1,4 +0,0 @@
-name irish-test
-language ga
-stressrule 0
-

phsource/ph_bengali

@@ -0,0 +1,37 @@
+
+//====================================================
+//  Bengali, inherits from Hindi
+//====================================================
+
+phoneme @
+  vowel flag1 starttype #@  endtype #@
+  length 65
+
+  ChangeIfDiminished(@-)
+  IF nextPh(H) THEN
+    FMT(vowel/@_low)
+  ENDIF
+  FMT(vowel/@_bck)
+endphoneme
+
+
+phoneme V
+  vowel flag1 starttype #@  endtype #@
+  length 180
+  CALL hi/V
+endphoneme
+
+
+phoneme a:
+  vowel long starttype #a endtype #a
+  length 230
+  FMT(vowel/aa_9)
+endphoneme
+
+
+phoneme o:
+  vowel long starttype #o endtype #o
+  length 220
+  FMT(vowel/o_2)
+endphoneme
+

phsource/ph_hindi

@@ -136,7 +136,7 @@ endphoneme
 
 phoneme a:
   vowel long starttype #a endtype #a
-  length 230
+  length 190
   FMT(vowel/aa_9)
 endphoneme
 
@@ -149,7 +149,7 @@ endphoneme
 
 phoneme o:
   vowel long starttype #o endtype #o
-  length 220
+  length 227
   FMT(vowel/o_2)
 endphoneme
 

phsource/ph_malayalam

@@ -132,7 +132,7 @@ phoneme v
 endphoneme
 
 phoneme r
-  import_phoneme base/*
+  import_phoneme base/**
 endphoneme
 
 phoneme R
@@ -142,3 +142,20 @@ endphoneme
 phoneme d#   // 'rr' sounds like English 'd'
   import_phoneme base/d
 endphoneme
+
+
+phoneme kh2
+  vls vel stop
+  lengthmod 2
+  voicingswitch g
+  Vowelin f1=0  f2=2300 200 300  f3=-150 80
+  Vowelout f1=0 f2=2300 300 400  f3=-150 80  rms=20
+  IF nextPh(isPause2) THEN
+    WAV(ustop/k_asp2, 50)
+  ENDIF
+  IF nextPh(l) THEN
+    WAV(ustop/kl)
+  ENDIF
+  WAV(ustop/k_asp2, 90)
+endphoneme
+

phsource/ph_pt_brazil

@@ -189,18 +189,8 @@ phoneme l
 endphoneme
 
 
-phoneme x   // this is [R] from Slovak/Czech
-  liquid
-  trill
-  ipa ʁ
-  lengthmod 6
-  IF thisPh(isWordStart) THEN
-    ChangePhoneme(h)  // Change by Cleverson 22.09.2012
-  ENDIF
-
-  Vowelin  f1=0  f2=1700 -300 300  f3=-300 80
-  Vowelout f1=2  f2=1700 -300 300  f3=-300 80 brk
-  FMT(r3/r_trill) addWav(r3/r_trill.wav, 50)
+phoneme x   // (previously [R] from Slovak/Czech)
+  import_phoneme base/h
 endphoneme
 
 

phsource/phonemes

@@ -1718,6 +1718,15 @@ include ph_french_ca
 phonemetable hi base
 include ph_hindi
 
+phonemetable bn hi
+include ph_bengali
+
+phonemetable ne hi
+include ph_nepali
+
+phonemetable ur hi
+include ph_urdu
+
 phonemetable ta hi
 include ph_tamil
 
@@ -1727,9 +1736,6 @@ include ph_kannada
 phonemetable ml hi
 include ph_malayalam
 
-phonemetable ur hi
-include ph_urdu
-
 
 phonemetable hu base
 include ph_hungarian
@@ -1857,12 +1863,6 @@ include ph_georgian
 phonemetable rw base2
 include ph_kinyarwanda
 
-//phonemetable bn hi
-//include ph_bengali
-
-phonemetable ne hi
-include ph_nepali
-
 //phonemetable mr hi
 //include ph_marathi
 

src/compiledict.cpp

@@ -51,15 +51,21 @@ static char letterGroupsDefined[N_LETTER_GROUPS];
 
 MNEM_TAB mnem_rules[] = {
 	{"unpr",   0x01},
+
 	{"w_alt1", 0x11},
 	{"w_alt2", 0x12},
 	{"w_alt3", 0x13},
-//	{"w_alt4", 0x14},
+	{"w_alt4", 0x14},
+	{"w_alt5", 0x15},
+	{"w_alt6", 0x16},
 	{"w_alt", 0x11},   // note: put longer names before their sub-strings
+
 	{"p_alt1", 0x21},
 	{"p_alt2", 0x22},
 	{"p_alt3", 0x23},
-//	{"p_alt4", 0x24},
+	{"p_alt4", 0x24},
+	{"p_alt5", 0x25},
+	{"p_alt6", 0x26},
 	{"p_alt", 0x21},
 	{NULL, -1} };
 
@@ -83,24 +89,22 @@ MNEM_TAB mnem_flags[] = {
 
 
 	// these set the corresponding numbered bit if dictionary_flags
-	{"$pause",     8},    /* ensure pause before this word */
-	{"$only",      9},    /* only match on this word without suffix */
-	{"$onlys",     10},    /* only match with none, or with 's' suffix */
-	{"$strend",    11},    /* full stress if at end of clause */
-	{"$strend2",   12},    /* full stress if at end of clause, or only followed by unstressed */
-	{"$unstressend",13},   /* reduce stress at end of clause */
-	{"$atend",     14},    /* use this pronunciation if at end of clause */
-	{"$atstart",   15},   // use this pronunciation at start of clause
-
-	{"$abbrev",    17},    /* use this pronuciation rather than split into letters */
-	{"$stem",      18},   // must have a suffix
+	{"$pause",     8},    // ensure pause before this word
+	{"$strend",    9},   // full stress if at end of clause
+	{"$strend2",   10},   // full stress if at end of clause, or only followed by unstressed
+	{"$unstressend",11},  // reduce stress at end of clause
+	{"$abbrev",    13},   // use this pronuciation rather than split into letters
 
 // language specific
-	{"$double",    19},   // IT double the initial consonant of next word
-	{"$alt",       20},   // use alternative pronunciation
-	{"$alt1",      20},   // synonym for $alt
-	{"$alt2",      21},
-	{"$alt3",      22},
+	{"$double",    14},   // IT double the initial consonant of next word
+	{"$alt",       15},   // use alternative pronunciation
+	{"$alt1",      15},   // synonym for $alt
+	{"$alt2",      16},
+	{"$alt3",      17},
+	{"$alt4",      18},
+	{"$alt5",      19},
+	{"$alt6",      20},
+
 	{"$combine",   23},   // Combine with the next word
 
 	{"$dot",       24},   // ignore '.' after this word (abbreviation)
@@ -111,18 +115,23 @@ MNEM_TAB mnem_flags[] = {
 	{"$text",      29},   // word translates to replcement text, not phonemes
 
 // flags in dictionary word 2
-	{"$verbf",   0x20},    /* verb follows */
-	{"$verbsf",  0x21},    /* verb follows, allow -s suffix */
-	{"$nounf",   0x22},    /* noun follows */
-	{"$pastf",   0x23},   /* past tense follows */
-	{"$verb",    0x24},   /* use this pronunciation when its a verb */
-	{"$noun",    0x25},   /* use this pronunciation when its a noun */
-	{"$past",    0x26},   /* use this pronunciation when its past tense */
-	{"$verbextend",0x28},   /* extend influence of 'verb follows' */
-	{"$capital", 0x29},   /* use this pronunciation if initial letter is upper case */
-	{"$allcaps", 0x2a},   /* use this pronunciation if initial letter is upper case */
+	{"$verbf",   0x20},   // verb follows
+	{"$verbsf",  0x21},   // verb follows, allow -s suffix
+	{"$nounf",   0x22},   // noun follows
+	{"$pastf",   0x23},   // past tense follows
+	{"$verb",    0x24},   // use this pronunciation when its a verb
+	{"$noun",    0x25},   // use this pronunciation when its a noun
+	{"$past",    0x26},   // use this pronunciation when its past tense
+	{"$verbextend",0x28}, // extend influence of 'verb follows'
+	{"$capital", 0x29},   // use this pronunciation if initial letter is upper case
+	{"$allcaps", 0x2a},   // use this pronunciation if initial letter is upper case
 	{"$accent",  0x2b},   // character name is base-character name + accent name
 	{"$sentence",0x2d},   // only if this clause is a sentence (i.e. terminator is {. ? !} not {, ; :}
+	{"$only",    0x2e},   // only match on this word without suffix
+	{"$onlys",   0x2f},   // only match with none, or with 's' suffix
+	{"$stem",    0x30},   // must have a suffix
+	{"$atend",   0x31},   // use this pronunciation if at end of clause
+	{"$atstart", 0x32},   // use this pronunciation at start of clause
 
 	// doesn't set dictionary_flags
 	{"$?",        100},   // conditional rule, followed by byte giving the condition number
@@ -611,7 +620,7 @@ static char nullstring[] = {0};
 
 	// PROBLEM  vowel reductions are not applied to the translated phonemes
 	// condition rules are not applied
-			TranslateWord(translator,phonetic,0,NULL);
+			TranslateWord(translator,phonetic,0,NULL,NULL);
 			text_not_phonemes = 0;
 			strncpy0(encoded_ph, word_phonemes, N_WORD_BYTES-4);
 

src/dictionary.cpp

@@ -3012,10 +3012,10 @@ static const char *LookupDict2(Translator *tr, const char *word, const char *wor
 	int  no_phonemes;
 	int  skipwords;
 	int  ix;
+	int  c;
 	const char *word_end;
 	const char *word1;
 	int wflags = 0;
-//	int wflags2;
 	char word_buf[N_WORD_BYTES+1];
 
 	if(wtab != NULL)
@@ -3165,20 +3165,20 @@ static const char *LookupDict2(Translator *tr, const char *word, const char *wor
 		if((end_flags & FLAG_SUFX)==0)
 		{
 			// no suffix has been removed
-			if(dictionary_flags & FLAG_STEM)
+			if(dictionary_flags2 & FLAG_STEM)
 				continue;   // this word must have a suffix
 		}
 
-		if((end_flags & SUFX_P) && (dictionary_flags & (FLAG_ONLY | FLAG_ONLY_S)))
+		if((end_flags & SUFX_P) && (dictionary_flags2 & (FLAG_ONLY | FLAG_ONLY_S)))
 			continue;    // $only or $onlys, don't match if a prefix has been removed
 
 		if(end_flags & FLAG_SUFX)
 		{
 			// a suffix was removed from the word
-			if(dictionary_flags & FLAG_ONLY)
+			if(dictionary_flags2 & FLAG_ONLY)
 				continue;        // no match if any suffix
 
-			if((dictionary_flags & FLAG_ONLY_S) && ((end_flags & FLAG_SUFX_S)==0))
+			if((dictionary_flags2 & FLAG_ONLY_S) && ((end_flags & FLAG_SUFX_S)==0))
 			{
 				// only a 's' suffix allowed, but the suffix wasn't 's'
 				continue;
@@ -3212,13 +3212,13 @@ static const char *LookupDict2(Translator *tr, const char *word, const char *wor
 				continue;
 		}
 
-		if((dictionary_flags & FLAG_ATEND) && (word_end < tr->clause_end))
+		if((dictionary_flags2 & FLAG_ATEND) && (word_end < tr->clause_end))
 		{
 			// only use this pronunciation if it's the last word of the clause
 			continue;
 		}
 
-		if((dictionary_flags & FLAG_ATSTART) && !(wtab->flags & FLAG_FIRST_WORD))
+		if((dictionary_flags2 & FLAG_ATSTART) && !(wtab->flags & FLAG_FIRST_WORD))
 		{
 			// only use this pronunciation if it's the first word of a clause
 			continue;
@@ -3318,6 +3318,12 @@ static const char *LookupDict2(Translator *tr, const char *word, const char *wor
 				fprintf(f_trans,"' [%s]  %s\n",ph_decoded,print_dictionary_flags(flags));
 			}
 		}
+
+		ix = utf8_in(&c, word);
+		if((word[ix] == 0) && !IsAlpha(c))
+		{
+		    flags[0] |= FLAG_MAX3;
+		}
 		return(word_end);
 
 	}
@@ -3390,6 +3396,7 @@ int LookupDictList(Translator *tr, char **wordptr, char *ph_out, unsigned int *f
 
 	found = LookupDict2(tr, word, word1, ph_out, flags, end_flags, wtab);
 
+
 	if(flags[0] & FLAG_MAX3)
 	{
 		if(strcmp(ph_out, tr->phonemes_repeat) == 0)

src/extras.cpp

@@ -464,7 +464,7 @@ void Lexicon_It(int pass)
 		}
 
 		// translate
-		TranslateWord(translator,&word1[1],0, NULL);
+		TranslateWord(translator,&word1[1],0, NULL, NULL);
 		DecodePhonemes(word_phonemes,phonemes);
 
 		stress_posn1 = 0;
@@ -487,7 +487,7 @@ void Lexicon_It(int pass)
 				vowel_ix++;
 		}
 
-		TranslateWord(translator,&word2[1],0, NULL);
+		TranslateWord(translator,&word2[1],0, NULL, NULL);
 		DecodePhonemes(word_phonemes,phonemes2);
 
 		vowel_ix = 1;
@@ -802,7 +802,7 @@ void Lexicon_De()
 		}
 
 		// translate
-		TranslateWord(translator,&word2[1],0, NULL);
+		TranslateWord(translator,&word2[1],0, NULL, NULL);
 
 		DecodePhonemes2(word_phonemes,phonemes);  // also need to change some phoneme names
 
@@ -1042,7 +1042,7 @@ void Lexicon_Bg()
 		*pw1 = 0;
 
 		// translate
-		TranslateWord(translator, &word[2],0, NULL);
+		TranslateWord(translator, &word[2],0, NULL, NULL);
 		DecodePhonemes(word_phonemes,phonemes);
 
 		// find the stress position in the translation
@@ -1300,7 +1300,7 @@ void Lexicon_Ru()
 		}
 
 		// translate
-		TranslateWord(translator, &word2[1],0, NULL);
+		TranslateWord(translator, &word2[1],0, NULL, NULL);
 		DecodePhonemes(word_phonemes,phonemes);
 
 		// find the stress position in the translation

src/menus.cpp

@@ -89,10 +89,10 @@ wxMenuBar *MakeMenu(int type, const char *dict_name)
 
         // DATA MENU
         data_menu = new wxMenu;
-        data_menu->Append(MENU_COMPILE_PH, _("Compile &phoneme data"));
-        data_menu->Append(MENU_COMPILE_PH2, _("Change sample &rate"));
         data_menu->Append(MENU_COMPILE_DICT, _("Compile &dictionary"));
         data_menu->Append(MENU_COMPILE_DICT_DEBUG, _("Compile dictionary (debu&g)"));
+        data_menu->Append(MENU_COMPILE_PH, _("Compile &phoneme data"));
+        data_menu->Append(MENU_COMPILE_PH2, _("Change sample &rate"));
         data_menu->AppendSeparator();
         data_menu->Append(MENU_COMPILE_MBROLA, _("Compile &mbrola phonemes list..."));
         data_menu->Append(MENU_COMPILE_INTONATION, _("Compile &intonation data"));

src/numbers.cpp

@@ -656,20 +656,32 @@ int TranslateLetter(Translator *tr, char *word, char *phonemes, int control)
         current_alphabet = alphabet;
         if((alphabet != NULL) && !(alphabet->flags & AL_DONT_NAME))
         {
+            phontab_1 = tr->phoneme_tab_ix;
+            ph_buf2[0] = 0;
             if(Lookup(translator, alphabet->name, ph_alphabet) == 0)  // the original language for the current voice
             {
                 // Can't find the local name for this alphabet, use the English name
-                phontab_1 = tr->phoneme_tab_ix;
                 ph_alphabet[2] = SetTranslator2("en");   // overwrites previous contents of translator2
-                if(Lookup(translator2, alphabet->name, &ph_alphabet[3]) != 0)
-                {
-                    ph_alphabet[0] = phonPAUSE;
-                    ph_alphabet[1] = phonSWITCH;
-                    len = strlen(&ph_alphabet[3]) + 3;
-                    ph_alphabet[len] = phonSWITCH;  // switch back
-                    ph_alphabet[len+1] = phontab_1;
-                    ph_alphabet[len+2] = 0;
-                }
+                Lookup(translator2, alphabet->name, ph_buf2);
+            }
+            else
+            if(translator != tr)
+            {
+                phontab_1 = tr->phoneme_tab_ix;
+                strcpy(ph_buf2, ph_alphabet);
+                ph_alphabet[2] = translator->phoneme_tab_ix;
+            }
+
+            if(ph_buf2[0] != 0)
+            {
+                // we used a different language for the alphabet name (now in ph_buf2)
+                ph_alphabet[0] = phonPAUSE;
+                ph_alphabet[1] = phonSWITCH;
+                strcpy(&ph_alphabet[3], ph_buf2);
+                len = strlen(ph_buf2) + 3;
+                ph_alphabet[len] = phonSWITCH;
+                ph_alphabet[len+1] = phontab_1;
+                ph_alphabet[len+2] = 0;
             }
         }
     }
@@ -876,7 +888,7 @@ static int CheckDotOrdinal(Translator *tr, char *word, char *word_end, WORD_TAB
 					nextflags = 0;
 					if(IsAlpha(c2))
 					{
-						nextflags = TranslateWord(tr, &word_end[2], 0, NULL);
+						nextflags = TranslateWord(tr, &word_end[2], 0, NULL, NULL);
 					}
 
 if((tr->prev_dict_flags & FLAG_ALT_TRANS) && ((c2 == 0) || (wtab[0].flags & FLAG_COMMA_AFTER) || iswdigit(c2)))

src/synthdata.cpp

@@ -35,8 +35,8 @@
 #include "translate.h"
 #include "wave.h"
 
-const char *version_string = "1.46.38  27.Feb.13";
-const int version_phdata  = 0x014636;
+const char *version_string = "1.46.39  01.Mar.13";
+const int version_phdata  = 0x014639;
 
 int option_device_number = -1;
 FILE *f_logespeak = NULL;

src/tr_languages.cpp

@@ -808,6 +808,13 @@ Translator *SelectTranslator(const char *name)
 		}
 		break;
 
+    case L('g','a'):   // irish
+        {
+            tr->langopts.stress_rule = STRESSPOSN_1L;
+            tr->langopts.numbers = 1;
+        }
+        break;
+
 	case L('h','i'):    // Hindi
 	case L('n','e'):    // Nepali
 	case L('p','a'):    // Punjabi

src/translate.cpp

@@ -807,8 +807,8 @@ int ChangeEquivalentPhonemes(Translator *tr, int lang2, char *phonemes)
 
 
 
-int TranslateWord(Translator *tr, char *word_start, int next_pause, WORD_TAB *wtab)
-{//===========================================================================
+int TranslateWord(Translator *tr, char *word_start, int next_pause, WORD_TAB *wtab, char *word_out)
+{//==================================================================================================
 // word1 is terminated by space (0x20) character
 
 	char *word1;
@@ -943,6 +943,9 @@ int TranslateWord(Translator *tr, char *word_start, int next_pause, WORD_TAB *wt
 
 		if(dictionary_flags[0] & FLAG_TEXTMODE)
 		{
+		    if(word_out != NULL)
+                strcpy(word_out, word1);
+
 			first_char = word1[0];
 			stress_bits = dictionary_flags[0] & 0x7f;
 			found = LookupDictList(tr, &word1, phonemes, dictionary_flags2, 0, wtab);   // the text replacement
@@ -1760,6 +1763,7 @@ static int TranslateWord2(Translator *tr, char *word, WORD_TAB *wtab, int pre_pa
 	int word_flags;
 	int word_copy_len;
 	char word_copy[N_WORD_BYTES+1];
+	char word_replaced[N_WORD_BYTES+1];
 	char old_dictionary_name[40];
 
 	if((f_logespeak != NULL) && (logging_type & 8))
@@ -1871,7 +1875,8 @@ static int TranslateWord2(Translator *tr, char *word, WORD_TAB *wtab, int pre_pa
 		while(((c2 = word_copy[ix] = word[ix]) != ' ') && (c2 != 0) && (ix < N_WORD_BYTES)) ix++;
 		word_copy_len = ix;
 
-		flags = TranslateWord(translator, word, next_pause, wtab);
+        word_replaced[2] = 0;
+		flags = TranslateWord(translator, word, next_pause, wtab, &word_replaced[2]);
 
 		if(flags & FLAG_SPELLWORD)
 		{
@@ -1906,7 +1911,7 @@ static int TranslateWord2(Translator *tr, char *word, WORD_TAB *wtab, int pre_pa
 			{
 				strcpy(ph_buf,word_phonemes);
 
-				flags2[0] = TranslateWord(translator, p2+1, 0, wtab+1);
+				flags2[0] = TranslateWord(translator, p2+1, 0, wtab+1, NULL);
 				if((flags2[0] & FLAG_WAS_UNPRONOUNCABLE) || (word_phonemes[0] == phonSWITCH))
 					ok = 0;
 
@@ -1934,12 +1939,12 @@ static int TranslateWord2(Translator *tr, char *word, WORD_TAB *wtab, int pre_pa
 			if(ok)
 			{
 				*p2 = '-'; // replace next space by hyphen
-				flags = TranslateWord(translator, word, next_pause, wtab);  // translate the combined word
+				flags = TranslateWord(translator, word, next_pause, wtab, NULL);  // translate the combined word
 				if((sylimit > 0) && (CountSyllables(p) > (sylimit & 0x1f)))
 				{
 					// revert to separate words
 					*p2 = ' ';
-					flags = TranslateWord(translator, word, next_pause, wtab);
+					flags = TranslateWord(translator, word, next_pause, wtab, NULL);
 				}
 				else
 				{
@@ -1967,7 +1972,14 @@ static int TranslateWord2(Translator *tr, char *word, WORD_TAB *wtab, int pre_pa
 			{
 				// re-translate the word using the new translator
 				wtab[0].flags |= FLAG_TRANSLATOR2;
-				flags = TranslateWord(translator2, word, next_pause, wtab);
+				if(word_replaced[2] != 0)
+				{
+				    word_replaced[0] = 0;   // byte before the start of the word
+				    word_replaced[1] = ' ';
+                    flags = TranslateWord(translator2, &word_replaced[1], next_pause, wtab, NULL);
+				}
+				else
+                    flags = TranslateWord(translator2, word, next_pause, wtab, NULL);
 //				strcpy((char *)p,translator2->word_phonemes);
 				if(p[0] == phonSWITCH)
 				{

src/translate.h

@@ -37,26 +37,18 @@
 #define FLAG_SKIPWORDS        0x80
 #define FLAG_PREPAUSE        0x100
 
-#define FLAG_ONLY            0x200
-#define FLAG_ONLY_S          0x400
-#define BITNUM_FLAG_ONLY         9  // bit 9 is set
-#define BITNUM_FLAG_ONLY_S      10  // bit 10 is set
-
-#define FLAG_STRESS_END      0x800  /* full stress if at end of clause */
-#define FLAG_STRESS_END2    0x1000  /* full stress if at end of clause, or only followed by unstressed */
-#define FLAG_UNSTRESS_END   0x2000  /* reduce stress at end of clause */
-#define FLAG_ATEND          0x4000  /* use this pronunciation if at end of clause */
-#define FLAG_ATSTART        0x8000  // use this pronunciation if at start of clause
-#define FLAG_SPELLWORD     0x10000  // re-translate the word as individual letters, separated by spaces
-#define FLAG_ABBREV        0x20000  // spell as letters, even with a vowel, OR use specified pronunciation rather than split into letters
-#define FLAG_STEM          0x40000  // must have a suffix
-
-#define FLAG_DOUBLING      0x80000  // doubles the following consonant
-#define BITNUM_FLAG_ALT         19  // bit number of FLAG_ALT_TRANS - 1
-#define FLAG_ALT_TRANS    0x100000  // language specific
-#define FLAG_ALT2_TRANS   0x200000  // language specific
-#define FLAG_ALT3_TRANS   0x400000  // language specific
-#define FLAG_COMBINE      0x800000  // combine with the next word
+#define FLAG_STRESS_END      0x200  // full stress if at end of clause
+#define FLAG_STRESS_END2     0x400  // full stress if at end of clause, or only followed by unstressed
+#define FLAG_UNSTRESS_END    0x800  // reduce stress at end of clause
+#define FLAG_SPELLWORD      0x1000  // re-translate the word as individual letters, separated by spaces
+#define FLAG_ABBREV         0x2000  // spell as letters, even with a vowel, OR use specified pronunciation rather than split into letters
+#define FLAG_DOUBLING       0x4000  // doubles the following consonant
+
+#define BITNUM_FLAG_ALT         14  // bit number of FLAG_ALT_TRANS - 1
+#define FLAG_ALT_TRANS      0x8000  // language specific
+#define FLAG_ALT2_TRANS    0x10000  // language specific
+#define FLAG_ALT3_TRANS    0x20000  // language specific
+#define FLAG_COMBINE       0x40000  // combine with the next word
 
 #define FLAG_ALLOW_DOT  0x01000000  // ignore '.' after word (abbreviation)
 #define FLAG_NEEDS_DOT  0x02000000  // only if the word is followed by a dot
@@ -83,8 +75,16 @@
 #define FLAG_ACCENT          0x800  // character name is base-character name + accent name
 #define FLAG_HYPHENATED     0x1000  // multiple-words, but needs hyphen between parts 1 and 2
 #define FLAG_SENTENCE       0x2000  // only if the clause is a sentence
+#define FLAG_ONLY           0x4000
+#define FLAG_ONLY_S         0x8000
+#define FLAG_STEM          0x10000  // must have a suffix
+#define FLAG_ATEND         0x20000  /* use this pronunciation if at end of clause */
+#define FLAG_ATSTART       0x30000  // use this pronunciation if at start of clause
+
 #define BITNUM_FLAG_ALLCAPS   0x2a
 #define BITNUM_FLAG_HYPHENATED  0x2c
+#define BITNUM_FLAG_ONLY      0x2e
+#define BITNUM_FLAG_ONLY_S    0x2f
 
 
 // wordflags, flags in source word
@@ -714,7 +714,7 @@ int RemoveEnding(Translator *tr, char *word, int end_type, char *word_copy);
 int Unpronouncable(Translator *tr, char *word, int posn);
 void SetWordStress(Translator *tr, char *output, unsigned int *dictionary_flags, int tonic, int prev_stress);
 int TranslateRules(Translator *tr, char *p, char *phonemes, int size, char *end_phonemes, int end_flags, unsigned int *dict_flags);
-int TranslateWord(Translator *tr, char *word1, int next_pause, WORD_TAB *wtab);
+int TranslateWord(Translator *tr, char *word1, int next_pause, WORD_TAB *wtab, char *word_out);
 void *TranslateClause(Translator *tr, FILE *f_text, const void *vp_input, int *tone, char **voice_change);
 int ReadClause(Translator *tr, FILE *f_in, char *buf, short *charix, int *charix_top, int n_buf, int *tone_type, char *voice_change);
 

src/voices.cpp

@@ -798,14 +798,25 @@ voice_t *LoadVoice(const char *vname, int control)
 			break;
 
 		case V_DICTRULES:   // conditional dictionary rules and list entries
+		case V_NUMBERS:
+            // expect a list of numbers
 			while(*p != 0)
 			{
 				while(isspace(*p)) p++;
 				n = -1;
-				if(((n = atoi(p)) > 0) && (n < 32))
+				if((n = atoi(p)) > 0)
 				{
 					p++;
-					conditional_rules |= (1 << n);
+					if((key==V_DICTRULES) && (n < 32))
+                        conditional_rules |= (1 << n);
+					else
+					if((key==V_NUMBERS) && (n < 32))
+                        langopts->numbers |= (1 << n);
+                    else
+                    if((key==V_NUMBERS) && (n < 64))
+                        langopts->numbers |= (1 << (n-32));
+                    else
+                        fprintf(stderr,"Bad option number %d\n", n);
 				}
 				while(isalnum(*p)) p++;
 			}
@@ -837,10 +848,6 @@ voice_t *LoadVoice(const char *vname, int control)
 				new_translator->charset_a0 = charsets[value];
 			break;
 
-		case V_NUMBERS:
-			sscanf(p,"%d %d",&langopts->numbers,&langopts->numbers2);
-			break;
-
 		case V_OPTION:
 			value2 = 0;
 			if((sscanf(p,"%s %d %d",option_name,&value,&value2) >= 2) && ((ix = LookupMnem(options_tab, option_name)) >= 0))

src/wave_sada.cpp

@@ -535,7 +535,7 @@ int wave_get_remaining_time(uint32_t sample, uint32_t* time)
 #else
 // notdef USE_SADA
 
-void wave_init() {}
+init wave_init() {}
 void* wave_open(const char* the_api) {return (void *)1;}
 size_t wave_write(void* theHandler, char* theMono16BitsWaveBuffer, size_t theSize) {return theSize;}
 int wave_close(void* theHandler) {return 0;}