[1.47.07b]

Reinstate language "az" (Azerbaijani) as a test voice.
Language changes: ga, hy, pt, sk.
Generate character names for subscript and superscript letters and digits.
 

git-svn-id: https://espeak.svn.sourceforge.net/svnroot/espeak/trunk@347 d46cf337-b52f-0410-862d-fd96e6ae7743

dictsource/az_list

+ 
+// This file is UTF8 encoded 
+// Spelling to phoneme rules for Azerbaijani
+
+
+// Numbers
+_0	s@f'@R
+_1	b'iR
+_2	ic'i
+_3	'ytS
+_4	d'WRd
+_5	b'eS
+_6	alt'@
+_7	jedd'i
+_8	s&Cc'iz
+_9	dogg'uz
+_1X	'on
+_2X	ijiRm'i
+_3X	ot'uz
+_4X	g'@Rx
+_5X	&ll'i
+_6X	altm'@S
+_7X	jetm'iS
+_8X	s&Cs'&n
+_9X	doxs'an
+_0C	j'yz
+_0M1	m'in
+_0M2	milj'on
+_0M3	milj'aRd
+_dpt	_t,am_|   // ??
+
+
+// Function words
+  // personal pronouns
+mən	$u+
+sən	$u+
+o	$u+
+biz	$u+
+siz	$u+
+onlar	$u+
+
+  // possessive pronouns
+mənim	$u+
+sənin	$u+
+onun	$u+
+bizim	$u+
+sizin	$u+
+onların	$u+
+
+bu	$u+
+
+
+// conjunctions
+və	$u+
+isə	$u+
+də	$u+
+həm	$u+
+ya	$u+
+da	$u+
+
+// prepositions
+aid	$u+ // about
+ilə	$u+ // with, by, in
+dair	$u+ // about
+
+// postpositions
+ci	$u
+cı	$u
+cü	$u
+de	$u
+dir	$u
+li	$u
+in	$u
+nə	$u
+ya	$u
+yə	$u
+
+// Character names
+b	be
+c	dZe
+ç	tSe
+_ə	&
+d	de
+f	fe
+g	Je
+ğ	Qe
+h	he
+x	xe
+j	Ze
+k	ka
+q	ge
+l	el
+m	em
+n	en
+_o      o
+p	pe
+r	eR
+s	se
+ş	Se
+t	te
+v	ve
+w	dubElv'E
+y	je
+z	ze
+
+*	ulduz $text
+%	faiz $text
+
+
+

dictsource/az_rules

+ 
+// This file is UTF8 encoded 
+// Spelling to phoneme rules for Azerbaijani
+
+// Stress rule: Right-most vowel, but stop before the vowel which is
+// marked as unstressed [%].
+
+.L02 ı a o u   // back vowels
+.L03 i e ö ü
+
+.group a
+        a        a
+        ai (K    aI
+     -) a (_     a
+
+.group b
+        b        b
+
+.group c
+        c        dZ
+
+.group ç
+        ç        tS
+
+.group d
+        d        d
+
+     -) dan (_   d%an
+     -) dən (_   d%&n
+     -) dək (_   d%&k
+     
+.group e
+        e        e
+
+.group ə
+        ə        &
+     @) ə (_     %&
+     -) ə (_     %&
+
+.group f
+        f        f
+
+.group g
+        g        J
+
+.group ğ
+        ğ        Q
+     A) ğ        : 
+     a) ğa       :
+     o) ğo       :
+     u) ğu       :
+     ö) ğö       :
+     ü) ğü       :
+     i) ğ        j
+     e) ğ        j
+
+.group h
+        h        h
+
+.group x
+        x        x
+
+.group ı
+        ı        @
+
+.group i
+        i        i
+        
+     @) iya (_   =i;a
+
+.group j
+        j        Z
+
+.group k
+        k        c
+        k (K     C
+
+.group q
+        q        g
+        q (_     x
+
+.group l
+        l        l
+        l (L02   L
+   L02) l (K     L
+
+.group m
+        m        m
+
+.group n
+        n        n
+
+.group o
+        o        o
+
+.group ö
+        ö        W
+
+.group p
+        p        p
+
+.group r
+        r        R
+     A) r (A     *
+     ğ) r (A     *
+     C) r (_     @-r
+
+.group s
+        s        s
+
+.group ş
+        ş        S
+
+.group t
+        t        t
+   L03) t (L03   ts
+
+.group u
+        u        u
+
+.group ü
+        ü        y
+
+.group v
+        v        v
+
+.group w
+        w        w
+
+.group y
+        y        j
+
+.group z
+        z        z
+
+.group
+        ä        &

dictsource/bn_list

 _1	'&k
 _2	d'uj
 _3	t'in
-_4	tS'ar
+_4	tSh'ar
 _5	p'a~tS
-_6	tSh'Oj
+_6	tS#'Oj
 _7	S'at
 _8	'at.#
 _9	n'Oj
 
 _2a	d'u     // with hundreds etc.
-_6a	tSh'O
+_6a	tS#'O
 _9a	n'O
 
 
 _11	'&garo
 _12	b'arO
 _13	t'erO
-_14	tS'oddO
+_14	tSh'oddO
 _15	p'OnerO
 _16	S'olO
 _17	S'OterO

dictsource/bn_rules

 
 
 .group ছ
-        ছ        tS#V
-        ছ  (B    tS#
+        ছ        tShV
+        ছ  (B    tSh
 
         
 .group জ

dictsource/de_list

 _??	zymb'o:l
 _?A	b'u:xstA:b@
 _cap	gr'o:s
+_sub	'Unt@R|3_!,IndEks||
+_sup	'o:b@R|3_!,IndEks||
 
 
 // accent names

dictsource/dict_phonemes

 t#   tS   w    x    
 
 
+Dictionary az_dict  2013-04-25
+
+&    @    @-   a    aI   e    E    i    
+o    u    W    y    
+
+*    :    ;    b    c    C    d    dZ   
+f    g    h    j    J    k    l    L    
+m    n    p    Q    r    R    s    S    
+t    tS   ts   v    w    x    z    Z    
+
+
 Dictionary bg_dict  2013-03-16
 
 @    a    e    i    o    u    
 Z    z;   
 
 
-Dictionary bn_dict  2013-04-18
+Dictionary bn_dict  2013-04-25
 
 &    a    a~   e    e~   i    i:   i~   
 l-   o    O    o:   O~   o~   r-   u    
 v    w    x    z    Z    
 
 
-Dictionary de_dict  2013-03-10
+Dictionary de_dict  2013-04-25
 
 3    @    @-   a    A    A:   aI   aU   
 A~   E    E2   E:   e:   EI   i    I    
 ts   v    x    z    
 
 
-Dictionary en_dict  2013-04-23
+Dictionary en_dict  2013-04-25
 
 0    0#   3    3:   @    @-   @2   @5   
 @L   a    a#   A:   A@   aa   aI   aI3  
 tS   v    z    Z    z2   z3   
 
 
-Dictionary ga_dict  2013-03-20
+Dictionary ga_dict  2013-04-25
 
 0    0#   @    a    a#   A:   aI   aI#  
 aU   aU#  e    E    E#   e:   eI   i    
 z    Z    
 
 
-Dictionary hy_dict  2008-12-22
+Dictionary hy_dict  2013-04-25
 
 @    a    aI   e    eI   i    i@   o    
 u    W    y    
 
-**   b    c    d    dZ   dz   f    g    
-h    j    k    k#   l    m    n    p    
-p#   r    R    r"   s    S    t    t#   
-tS   ts   ts#  v    X    z    Z    
+*    **   b    c    d    dZ   dz   f    
+g    h    j    k    k#   l    m    n    
+p    p#   r    R    r"   R2   s    S    
+t    t#   tS   ts   ts#  v    X    z    
+Z    
 
 
 Dictionary id_dict  2011-02-21
 t.#  v    w    x    z    
 
 
-Dictionary nl_dict  2013-04-23
+Dictionary nl_dict  2013-04-25
 
 8    @    @-   a    A    a:   A~   e    
 E    e#   E2   e:   EI   eU   i    I    
 z    Z    
 
 
-Dictionary pa_dict  2013-03-17
+Dictionary pa_dict  2013-04-24
 
 @    a    a~   e    E    e~   E~   i    
 I    i~   I~   o    O    o:   O~   o~   
 :    ;    b    b#   c    c#   d    d#   
 d.   d.#  f    g    g#   h    H    j    
 J    J#   k    k#   l    l.   m    n    
-N    n.   n^   p    p#   Q    R    r.   
-R2   s    S    t    t#   t.   t.#  v    
-x    z    
+N    n.   n^   p    p#   Q    r    R    
+r.   R2   s    S    t    t#   t.   t.#  
+v    x    z    
 
 
 Dictionary pl_dict  2013-04-06
 ts;  v    w    x    z    Z    Z;   
 
 
-Dictionary pt_dict  2013-04-23
+Dictionary pt_dict  2013-04-25
 
 &    &/   &U~  &~   @    @-   a    A    
 aI   aU   e    E    eI   EI   eU   EU   
 s.   t    t#   t.   t.#  tS   v    w    
 
 
-Dictionary sk_dict  2011-08-08
+Dictionary sk_dict  2013-04-25
 
 &    @-   a    a:   e    e:   i    i:   
 l-   l:   o    o:   oU   r-   r:   u    
 u:   
 
-*    ;    b    d    d;   dZ   dz   f    
-g    h    j    k    l    l^   m    n    
-N    n^   p    r    R    R^   R^/  s    
-S    t    t;   tS   ts   v    w    x    
-z    Z    
+*    ;    b    c    d    d;   dZ   dz   
+f    g    h    j    k    l    l^   m    
+n    N    n^   p    r    R    R^   R^/  
+s    S    t    t;   tS   ts   v    w    
+x    z    Z    
 
 
 Dictionary sl_dict  2013-01-30
 v    v#   w    z    
 
 
-Dictionary tr_dict  2013-04-20
+Dictionary tr_dict  2013-04-25
 
 @    a    e    E    i    I    o    O    
 u    U    W    y    Y    

dictsource/en_list

 
 // character names
 _cap	k,ap@-t@L
+_sub	s,VbskrIpt||
+_sup	s,u:p3skrIpt||
 _?A	l,Et3
 _??	sImb@L
 _braille br'eIl
 ?!3 temporary	tEmpr@rI
 ?3 template	tEmpl@t
 therefore	$1
+thereof		De@r'0v
 thermos		T3:m@s
 thermostable	$alt1
 thesis		Ti:sIs
 Andrea		$2
 Adrian		eIdri@n
 Agatha		aga#T@
+Angela		andZ@l@
 Angelika	$2
 Aggie		agi
 Agnes		agn@s
 Hadrian		heIdri:@n
 Hamish		heImIS
 Harriet		hari@t
+Harvey		hA@vi
 Heidi		haIdi
 Hecate		hEk@teI
 Hekate		hEk@teI
 Luigi		lu:'i:dZi
 Luis		lu:Is
 Lupe		lu:peI
+Luther		lu:T3
 Madeleine	mad@lI2n
 Madeline	mad@lI2n
 Maeve		meIv
 Wallace		w0lI#s
 Wally		w0li
 ?3 William	wIlj@m
+Yerevan		jEr@v'an
 Yves		i:v
 Yvonne		$2
 Zoe		zoUi

dictsource/ga_list

 // Irish Gaeilge dictionary
 // written by Ronan McGuirk
-// January 2013
-// version 2.5
+//  2013
+// version 2.6.1
+// Please send comments and suggestions to [email protected]
+
 // This file is UTF8 encoded
 
 // letters
 // accent names
 
 // names of symbols
-ª_.	pO#nk
+_.	pO#nk
 _,	k0m@
 _;	semI
 _:	ko:l0n
 amuigh	@mu1'I
 amháin @w'A:in
 am aUm
-an	@n
+anaithnid	'0nah@nIdZ
 anois	@nIS
 anonn @naUn
 ann aUn
 anseo	@nS'O
+anuas	a#n'u@s
 aodh e:
 aodha e:
 aon e:@n
 (ar ais) Er'aS
 arís	@r'i:S
 as 0s
+aschurtha	'0sxUrh@
+
 atá	@t['A:		$u
 baill	bu1'i:l
 bhaill	vu1'i:l
 beidh	bEg
 bhfuil w'Il
+bheas	v'e:@s
 bhuel	w'El
 ceithre kEr@
 cathair	k'0h@r
 chlainne	xl'InE
 chun	xUn		$u
 crainn kri:n
+chrainn	xri:n
 de	dE		$u+
 des	dEs		$u
 
 do	dO#		$u
 domhnach d[aUn@x
 domhnaigh d[aUnig
+dúghorm	d['u:Q"Or@m
 eile	'El@
 euro ju:ro:
 faic f@ak
 (muigheo)	mu1'i:||'o:
 mhuigh	vu1'i:
 (mhaigh eo)	vu1'i:||'o:
+mhama	w'0m@
 maith m'0
 mhaith w'0
 	   mbeadh m;O#X
 os	o:s
 rabh	raU
 raibh rEv
+raidió	r'adi:o:
 réamhrá r'e:@vr,a:
 réidh	re:
+'s	s
 samhain saUIn
 	  san s@n
 	  seo S@_

dictsource/ga_rules

 
 // translation rules for Irish Gaeilge
 // This file is UTF-8 encoded
-// written by Ronan McGuirk January 2013
-// Version 2.5B
+// written by Ronan McGuirk  2013
+// Version 2.6.1
+// Please send comments and suggestions to [email protected]
+
 
 // Conditional rules
 // ?1  allow eclipsis as 2 separate words
 .L03 b bh mb  c ch f m mh dh   // used for words likemuir or cuid
 .L04 b bh mb    // for words like beag
 .L05 nn nna nnas dh r s ntas nach nas nais dar mar rtha nta mh chas chais cht  chta nnach ntach llach d l  ll             // word endings where @ is to repleace ea or a
-.L06 aidh idh aí á eá eadh adh ad imid aimid imis aimis  ainn inn idís aidís éin     // word endings where f changes to h
+.L06 aidh idh aí á eá eadh adh ad adsa imid aimid imis aimis  ainn inn idís aidís éin      // word endings where f changes to h
 .L07 b c g ch bh gh mb
 .L08 lc ll nt bhse       // for words like cailc
 .L09 cl cr chr  f
 .L12 á é ó eo ua   // when followed by i
 .L13 oc omb
 .L14 río dún gnío        // followed with mh
-.L15 c ch  f  m d dh g gc  gh mh // aoi following
+.L15 c ch  f bhf  m d dh g gc  gh mh // aoi following
 .L16 b c bh ch gr ghr    // for inn word ending
 .L17 l le li niste nn
-.L18 n nt nte neann neadh ntear nim nfear nfinn
+.L18 n nt nte neann neadh ntear nim nfear nfinn nfidh nfidis neamar
 .L19 na nea ra rea la llea arga     // word endings with silent dh
 .L20 eo eoir eá eabh io iu iú               // slender m
 .L21 ll nn ndán nntán
-.L22  eadh eag eaga eagán eagáinín eo  io iu iú eall eabh ealtaine
+.L22  eadh eag eaga eagán eagáinín eo  io iu iú eall eabh ealtaine eann
 .L23 ea eo i
 .L24 b mb bh g gh p ph bp m mh
 
         abht       aU#t[
         amhr       aUr       //	words like amhras
      K) amhl       aUl
-        abhra      aUr@      //	words like slabhra
+        abh (C     aU        //	words like slabhra
         aghaidh    aIg
      t) abhair     u:@r
     th) abhair     u:@r
      t) abhar      u:@r
     th) abhar      u:@r
      _) an (sL01   @n
-     _) an (-      0n        // an prefix
+     _) a (nA      @
+     _) an (_      @n
+     _) an (-      '0n       // an prefix
      é) a          @         // words like féach
      X) a (nn_     aU#
      X) a (ll_     aU#
      _) ao         e:
         ae         e:
         amhna (_   aUn@
+        arraing    arIng
+     _) ath (@@P3  ,0_
 
-        
 .group á
         á          A:
      @) á          ,A:
         áinig      A:nIg
         ái         'A:i
 
-        
+
 .group ai
         ai         a#
    L04) ai (L17    0#
      m) ai (n      0#
      c) ai (th     0#
     ch) ai (th     0#
+        ai (tín    0#
         ai (d      0#
      p) ai (l      0#
      @) ai (L11_   I
      X) aigh       'aI
         aigh       aI#       L04)	aill	(_	wi:l
         aing (_    Ing
+        ai (llimh  '0        // words like Gaillimh
+
 
-        
 .group b
         b          b         // broad
    L01) b          b;        // slender
         bh (_      vv
         bh (L22    vj        // slender
    L01) bh         v
-?1 _m_) b (@
+?1 _m_) b (@ 
      _) bhf        v         // urú broad
      _) bhf (L22   v;        // urú slender
      _) bp         b         // urú broad
      a) bh (a      U         // for example cabhair
    ear) bha        u:        // words like Cearbhall
         bhfaigh    v'aI
+     _) beann (@   ba#n
+     _) bheann (@  va#n
+     _) bun (C@P3  b,Un
 
-        
 .group c
         c          k
         c (L01     k;        // slender
         ch (L01    C;
         ch (é+     C;
         ch (ei+    x;
-?1 _g_) c (@
-?1 _g_) c (L01
+?1 _g_) c (@ 
+?1 _g_) c (L01 
      _) cabhr      k'aUr
      _) chabhr     x'aUr
+     _) ceann (C@P5 k;,aUn
+     _) cheann (C@P6 C;,aUn
 
-     
 .group d
         d          d[        // broad
    L01) d          dZ        // slender
         d (L22     dZ        // slender
         d (L01     d;        // slender
      i) d (i       dZ
-?1 _n_) d (@
+?1 _n_) d (@ 
         dh         Q         // broad
         dh (ui     Q         // broad
         dh (ao     Q         // broad
 ?1   _) d (_t      d[
 ?1   _) d (_tL01   dZ
      _) d' (@P2    d
+
+     _) d'         d
+     _) d (_'fh    d
+
+        d'fh (L01  d
      i) dh (_      g
      a) dh (_      X
      o) dh (_      X
         dheartháir gr@h'A:r
         deirfiúr   d;r@f'u:r
         dheirfiúr  g;r@f'u:r
+     _) do (Ch@@P2 d[,U_
+     _) dí (@@P2   d,i:
 
-        
 .group e
         e          E#
         eá         A:
      r) ei (m      aI
         eighea     aI
         eighea     aI
+     s) ei (nn     aI
+    sh) ei (nn     aI
         eigh       aI
 
         eo         o:
-        eogh       o:
+        eoi        o:
+        eogha      o:
+        eoghai     o:
      d) eo (ch     O#
+    dh) eo (ch     O#
      _) eo (ch     O#
      s) eo (_      @
 
-     
+
 .group é
         é          'e:
         éi         'e:
+        éa         'e:
      _) éi (rig    aI        // words like éirigh
+    _h) éi (rí     aI
      _) éi (rí     aI        // words like éirí
      _) éireoidh   aIro:Ig
         éacs       e:@ks
 
-        
+
 .group ea
         ea         a#
+        eai        a#
      X) ea (L21_   aU
         ea (ltaine aU
      g) ea (ll     aU
+     l) eamh (n    aU
+    dr) ea (m      aU
      X) ea (ch     0
   _L04) ea (g      @
   _L04) ea (dh_    @
         eanbhean   'an@v,an
         eadhb      aIb
 
-        
+
 .group f
         f          f         // broad
         f (L22     f;        // slender
         fh (éin_   h
         fh (L22    ;         // slender
      @) f (L06_    h
-?1 _bh_) f (@
-?1 _bh_) f (L22    ;
+     _) fo (C@@P2  f,U
+     _) fogh       f'aU
+?1 _bh_) f (@ 
+?1 _bh_) f (L22     ;
+
 
-     
 .group g
         g          g         // broad
         g (L01     g;        // slender
-?1 _n_) g (@
+?1 _n_) g (@ 
      _) gh         Q"
      _) gh (L01    Q"j
      _) gc         g         // urú broad
         gh (n      X@
         gheobh     j'o:
         gabh       gaU
+     _) gearr (C@P5 g;,aR
+     _) ghearr (C@P6 Q"j,aR
 
-        
 .group h
         h          h         // silent
 
-        
+
 .group i
         i          I
      _) i          I
         ia         i@
         ia (tha    i:
         io         O#
+        io (dá     I
      _) io (nadh   u://      words like ionadh
+     s) io (mb     I
+    sh) io (mb     I
+
    _pr) io (n      u:
    L16) inn (_     i:n
         iai        i:i
    L12) i          i         // non syllabic short i after long vowel
         iú         u:
      m) i (d_      i:        // verb ending
+     _) in (@@P2   ,In_
+     _) ionad (C@@P5 ,Ona#d[
 
-     
 .group í
         í          'i:
+        íomh       'i:v
+        íochn      'i:xn
+        í (_       i:
+        ín (_      i:n
+        ío         i:@
+
 
-        
 .group l
         l          l         // broad
    L01) l          l;        // slender
         ll (L23    l;
         l (g       l@
         l (b       l@
+     _) lorg (@@P4 l,Or@g
+     _) lán (C@@P3 l,A:n
 
-        
 .group m
         m          m         // broad
         m (L20     m;        //slender
      _) mh (n      v@
   léir) mheas      vas
      r) m          @m        // words like gorm
+     _) mear (@@P4 m,ar
 
-     
 .group n
         n          n         // broad
         n (L01     n;        // slender
         n (ch      n@
      c) n          @n
     ch) n          @n
+     _) nasc (C@@  n,0sk
 
-    
 .group o
         o          O#
      _) o          'O
         odl (a     O#l
         oí         i:
 
-        
+
 .group ó
         ó          'o:
         ómhai      o:@
 
-        
+        ói (p@     'o:
+
 .group oi
         oi         O
   _L15) oi (+      @'I
      _) oi (leá    'I
         oidh       aI
         oir (_     'ERR
+   _sc) oi (r      O
         oigh (ea   aI
 
-        
+
 .group p
         p          p         // broad
         ph         f         // broad
         p (L22     p;        // slender
         ph (L20    f;        // slender
-?1 _b_) p (@
+?1 _b_) p (@ 
 
 
 .group r
   L12i) r (t_      Z
         rr         R
         rg         r@g
+        rgh        rQ"
    L01) rg         R@g       // slender
         r (bh      r@
-        ríomh      ri:@v
      s) r (A       R
      _) ramh       raU
 
-     
+
 .group s
         s          s         // broad
    L01) s          S         // slender
         s (cL01    S
         s (CCL01   S         // slender
         s (pCé     s         // broad
-?1 _t_) s (@
+?1 _t_) s (@ 
         sh         h
         sh (CL01   h
         sh (L01    h;
         s (lL01    S
+    _') s (_       s         // 's in poems etc
+     _) sain (@P4  s,an
 
-        
 .group t
         t          t[        // broad
    L01) t          c         // slender
 ?1   _) t (_L01    c
   L01C) t          tS        // slender after consonant
         t (CL01    tS        // slender with following consonant before vowels
-?1 _d_) t (@
+?1 _d_) t (@ 
         th         h
         th (L01    h;
   L01C) th         h
         thne (_    h@nE
      A) th (_                // silent th at word end
 
-     
+
 .group u
         u          U#
         ua         u@
         uai (d     ui
         uá         u:'A:
         ui         I
+        ui (s      U
+        ui (sce_   I
         uinn (_    'i:n
         uinti      U#'i:ntI
     _b) uí         wi:
    _bh) uí         wi:
      g) uí         wi:
+    gh) uí         wi:
         umh        u:
    L03) ui         @I
     _d) u (l_      O#
     gh) ui (gh_    @i:
         uí         i:
         uachai     'ux@
+     _) uimhir (C@P6 ,IvIR
+
 
-        
 .group ú
         ú          u:
         únmh       u:nv

dictsource/hy_list

 // This file is UTF8 encoded 
 // Spelling-to-phoneme words for Armenian
 
+// ?1  West Armenian
+
 // names of letters
 _ա	aIb
 բ	ben
 կ	ken
 հ	ho
 ձ	dza
-ղ	r"ad
+ղ	r"at
 ճ	ce
 մ	men
 յ	hi
 չ	tSa
 պ	pe
 ջ	dZe
-ռ	**a
+ռ	R2a
 ս	se
 վ	vev
 տ	tyn
 ր	re
-ց	tso
+ց	ts#o
 ւ	hyn
 փ	p#yr
 ք	k#e
+և	jev
 _օ	o
 ֆ	fe
 
 e	e
 f	ef
 
+// symbols
+$	dolar
+%	տոկոս $text
+*	աստղանիշ $text
++	գումարած $text
+=	հավասար $text
+
+
+_՝	b'ut#
+_՞	harts#ak'an
+_՛	S'eSt
+_։	verdZak'et  // U+0589
+_:	verdZak'et
+_,	storak'et
+_.	midZak'et
 
 
 // numbers
 
 
 // function words
+ես	$u+  // pronouns
+դու	$u+
+եք	$u+
+Դուք	$u+
+նա	$u+
+այն	$u+
+մենք	$u+
+նրանք	$u+
+
+դուք	$u+
+ենք	$u+
+են	$u+
+
+այդ	$u+
+այս	$u+
+դա	$u+
+որ	$u+
+էր	$u+
+
+մի	$u+
+է	$u+
+
+հետ	$u+  // prepositions
+
+եվ	$u+  // and
+իսկ	$u+ $brk  // and, but
+կամ	$u+  // or
+որը	$u+  // which
+	
+կարող	$u+  // can
+
+	
+
 
 
+// exceptions
+ով	ov
+ովքեր	ovk#er

dictsource/hy_rules

 //  (consonants are changed for Armenian-West in the voice file "hy-west")
 // This file is UTF-8 encoded
 
+// ?1  West Armenian
+
 .L01 բ գ թ կ պ տ ք
-.L02 ու այ իւ իյ ոյ               // other vowel sounds
+.L02 ու այ իւ իյ ոյ    ա ե ը ի ո օ     //  vowel sounds
 
 // ligature
 .replace
 
 .group ա
         ա        a
-        այ       aI
+        այ (K    aI
         այ (_    a
 
 .group բ
 .group է
         է        e
         էօ       W
-        էյ       eI
+        էյ (K    eI
 
 .group ը
         ը        @
         ի        i
         իւ       y
         իւ (_    iv
-        իյ       i@
+        իյ (K    i@
 
 .group լ
         լ        l
    L02) մ (_     m
 
 .group յ
-        յ        h       // ?? [j]
+     _) յ        h       // ?? [j]
      _) յ (C     h@
+        յ        j
 
 .group ն
         ն        n
      _) ջ (C     dZ@
 
 .group ռ
-        ռ        **
-     _) ռ (C     **@
+        ռ        R2
+     _) ռ (C     R2@
 
 .group ս
         ս        s
 
 .group ր
         ր        r
+   L02) ր (L02   *
      _) ր (C     r@
      C) ր (_     @r
    L02) ր (_     r
         ֆ        f
      _) ֆ (C     f@
 
-.group
-        $	dol@
 
 

dictsource/nl_list

 _t	te:
 
 _cap	h'o:fdlEt@r
+_sub	s'8pskrIpt||
+_sup	s'yp@rskrIpt||
 _?A	l'Et@r
 _??	s'imbo:l
 

dictsource/pa_rules

      ੱ) ਯ (_       j:
 
 .group ਰ
-        ਰ          RV
-        ਰ (B       R
-     @) ਰ (_       R
-     ੱ) ਰ          R:V
-     ੱ) ਰ (B       R:
-     ੱ) ਰ (_       R:
+        ਰ          rV
+        ਰ (B       r
+     @) ਰ (_       r
+     ੱ) ਰ          r:V
+     ੱ) ਰ (B       r:
+     ੱ) ਰ (_       r:
 
 .group ਲ
         ਲ          lV

dictsource/pt_list

 x	Sis#
 
 _cap	maI'uskulU
+_sub	||subskR'itU
+_sup	||sob*eskR'itU
 _?A	l'etR&_
 _??	s'imbolU_
 _#32	esp'asU
 usb	$abbrev
 
 
-dr	$dot
-dra	$dot
-mr	$dot
-mrs	$dot
+dr	dowtor	$dot
+dra	dowt'o*&	$dot
+mr	m'ister	$dot
+mrs	m'irsys	$dot
 prof	pR'Of	$dot
 profº	pR,ofes'or
 profª	pR,ofes'o*&
 abacaxi		abakaSy
 abordo		$alt
 aborto		$alt  $verb
+absorta		$alt2
 acerto		$alt2 $noun
 acertos		$alt2
 acocho		$alt2 $noun
 entorto		$alt
 entroso		$alt
 envelope	$alt
-envolto		$alt2
 enxaqueca	$alt2
 enxerto		$alt2 $noun
 epopeia		$alt
 horrores	$alt2
 humores		$alt2
 ideia		$alt
-imberbe		$alt
 interesse	$alt2
 interesse	$alt $verb
 iodo		$alt2
 leste		$alt2 $verb
 ?2   lhe	l^y
 lingueta	$alt2
+lisboeta		$alt2
 lodo		$alt2
 logro		$alt
 lopes		$alt
 moeda		$alt
 moem		$alt
 mofo		$alt $verb
-moleta		$alt2
 molho		$alt2 $noun
 monera		$alt
 morcego		$alt2
 mortos		$alt
 motora		$alt2
 mui		mwi
+muleta		$alt2
 mureta		$alt2
 mutreta		$alt2
 namoro		$alt2 $noun
 rock		$alt
 roem		$alt
 rola		$alt2 $noun
+roleta		$alt2
+rolete		$alt2
 rolo		$alt2 $noun
 rota		$alt2
 rota		$alt $noun
 traqueia	$alt
 travesso	$alt2
 tremores	$alt2
+treta		$alt2
 trevo		$alt2
 troco		$alt2 $noun
 tropa		$alt
 ?1 readme     r'i:dmi:
 ?1 sapi       s,ap'i
 ?1 scanner    sk'En&r
+sky   sk'ay
 shake	S'eIk
 ?1 shift      S'ift
 ?1 scroll     sk:r'ol
 ?4 símbolo	s'iNbolU
 ?2   software   s'Oftwe@-
 ?1 space      sp'eIsy
+?2 space      sp'eIs
 ?1 sporting   sp'Ort,ing
  tab        t'aby
  tablet  t'ablet
 ?1 telemóvel  t,El,Em'OvEl
 ?1 telemóveis t,El,Em'OveIs#
 ?1 up         &p
-?1 upload     &pl'oud
+update		&pd'eIt
+upgrade		&pgR'eId
+upload		&pl'oud
 ?2        web        w'Eb
 ?1 yahoo      'i,ah'u
 ?2 yahoo      iah'u
 // foreign product names
 ?1 access      'aks,Es
 ?1 adobe       &d'Oby
-   android &ndR'Oid
+   android &NdR'Oid
 apple  'Epow
 chrome  kR'owmi
    debian      d'Ebj&~N

dictsource/pt_rules

 
      i) e (r_      E
     @s) e (r_      E
-     u) e (r_      E
+     qu) e (r_      E
 
     ib) e (rL04_   E
      d) e (rL04_   E
     @s) e (rL04_   E
 
     sp) e (rL04_   E
-
      f) e (rL02_   E
 
         e (quL02_  E
-
+e (rbL04_   E
         e (rgL04_  E
 
         e (rsL04_  E
         e (ssL04_  E
         e (ss_     E         // stress and english words
 ?2      ection (_  'EkS&~N
+?2   ee (n_   i
         e (stL04_  E
 
         e (strL04_ E
    tiv) e (L05_    E         // es-
    viv) e (L05_    e
   _com) e (L05_    e
+  s_colh) e (res_   E
   _cos) e (L05_    e
   _pud) e (L05_    E
  _coub) e (L05_    E
 _interromp) e (L07_ e
 _troux) e (L07_    E
   _ens) e (bL03_   E
+  _enver) e (dL03_   E
 _amanc) e (bL03_   E
     qu) e (brL04_  E
   _cel) e (brL04_  E
  _boch) e (chL04_  e
-   _ex) e (crL04_  E
+ _on) e (rL04_   E
+    _ex) e (crL04_  E
   _enr) e (dL01_   E
     _v) e (dL03_   E
   _arr) e (dL03_   E
 _persev) e (rL04_  E
 _recup) e (rL04_   E
 _refrig) e (rL04_  E
-    _v) e (rbL03_  E
-   _ex) e (rcL02_  E
+       _ex) e (rcL02_  E
  _alic) e (rcL02_  E
     _p) e (rdL02_  E
     _l) e (rdL03_  E
     _h) e (rdL04_  E
   _des) e (rdL04_  E
      _) e (rgL03_  e
+_so) e (rgL03_   e 
    _re) e (rgL03_  e
   _bez) e (rrL03_  e
      v) e (rtL03_  e         // con- re- in-
 ?1   f) o (rmulá   u         // eg: formulário, formulários.
 ?1   v) o (lt      O
         o (luem_   o
-        o (CCuem_  o
+        o (ssuem_  o
     êC) o (CA_     o
    êCC) o (CA_     o
     ôC) o (CA_     o
    óCC) o (CA_     o
     úC) o (CA_     o
    úCC) o (CA_     o
-
+?2   otion (_   'owS&~N
+   
 //sort
     _f) o (L05_    o
 _pormen) o (L05_   O
   _esn) o (bL04_   O
  _engl) o (bL04_   O
   _sal) o (brL03_  o
+  _env) o (ltL03_   o
      _) o (cL03_   o
     _m) o (fL01_   O
     _m) o (fL02_   O
         u (a       u
      g) u (a+      w
      q) u (a+      w
+u (eC    u
+u (ei    u
      r) u (_A      u
         u (L04_    'u
 
         ui (_      'uI
         u (iu      w
         u (iCK     u
+u (éC   u
+u (íC   u
         uy         uI
         ul (K      uw
         u (lh+     u
 
      g) u (Y 
     _m) ui (tA_    'wiN
+?2   ution (_   'uS&~N
 
 
 .group ú

dictsource/sk_list

 
 // character names
 _cap	vel^ke:
+_sub	d,olni:||indeks||
+_sup	h,oRni:||indeks||
 _??	simbol
 _#9	t'ab
 _#32	'medzeRa
 
 *	hviezda	$max3
 +	plus	$max3
-=	Rovna:sa	$max3
+=	Rovna:||sa	$max3
 @	zavina:tS
 &	ampeRsand
 #	kRi:Zik	$max3
 _(	za:tvoRka
 _)	zatvoRit;
 _,	tSiaRka
-_-	poml-tSka
-__	podtSiaRknutie
+_-	spojovn^i:k
+__	podtSiaRkovn^i:k
 _.	bodka
-_/	lomeno
+_/	lomka
 _:	dvojbodka
 _;	bodkotSiaRka
 _<	menSi:
-_>	vetSSi:
+_>	v&tSSi:
 _?	ota:zn^ik
 _[	hRanata:||za:tvoRka
-_\	opatSne:||lomeno
+_\	opatSna:||lomka
 _]	hRanata:||zatvoRit;
-_^	stRieZka
+_^	voka:n^
 _`	aktsent
 _{	zloZena:||za:tvoRka
 _|	zvisla:||tSiaRa
 _}	zloZena:||zatvoRit;
 _~	vl-novka
-_     tvr-da:m'edzeRa    // U+00A0  no-break-space
-_¡    obra:t;eni:v'i:kRitSn^i:k
-_¦    pReRuSena:'tSiaRa
-_ª    hoRni:indeks'a:
-_«    dvojita:lomena:||za:tvoRka
-_­    mekka:poml-tSka
-_²    nadRuhu:
-_³    natRetju
-_´    dl:Zen^
-_·    bodka'vpRostRjedku
-_¸    tsedila
-_¹    napRvu:
-_»    dvojita:lomena:||zatvoRit;
-_¿    obRa:t;eni:'ota:zn^ik
-_–    dl-ha:'poml-tSka
-_‘    l^ava:'u:vodzovka
-_’    prava:'u:vodzovka
-_“    horne:'u:vodzovki
-_”    dolne:'u:vodzovki
-_‡    dvojiti:kRi:Z
-_•    odRa:Zka
-_‣    tRojuholni:kova:'odRa:Zka
+_ 	tvr-da:||m'edzeRa    // U+00A0  no-break-space
+_¡	obra:t;eni:||v'i:kRitSn^i:k
+_¦	pReRuSena:||tSiaRa
+_¨	pRehla:ska
+_«	dvojita:||lomena:||za:tvoRka
+_­	Rozd;el^ovn^i:k
+_´	dl:Zen^
+_·	bodka||v||pRostRjedku
+_¸	tsedila
+_»	dvojita:||lomena:||zatvoRit;
+_¿	obRa:t;eni:||ota:zn^ik
+_–	poml-tSka
+_‘	hoRne:||jednoduche:||u:vodzovki
+_’	odsuvn^i:k
+_“	hoRne:||u:vodzovki
+_”	dvojita:||hoRna:||opatSna:||u:vodzovka
+_„	dolne:||u:vodzovki
+_‚	dolne:||jednoduche:||u:vodzovki
+_‡	dvojkRi:Z
+_•	odRa:Zka
+_‣	odRa:Zka||tRojuholni:k
+_⁃	odRa:Zka||v||tvaRe||poml-tSki
 ‰	pRomile
 €	euRo
 §	paRagRaf
 ÷	d;eleno
 ×	kRa:t
 °	stupn^ou
-¢	tsentou
-£	libjeR
-¤	znatSkameni
+¢	tsent
+£	libRa
+¤	mena
+©	kopiRajt
+®	Registrovane:
+¥	jen
 −	mi:nus
-±	plus'mi:nus
-µ	mu:
-¼	Stvr-tina
+±	plus||mi:nus
+µ	mi:
+¼	Stvr-t;ina
 ½	polovitsa
-¾	tri_Stvr-tini
-¬	logitske:not
-æ	a'e:
-þ	poml-tSkanad
+¾	tRi_||Stvr-t;ini
+¬	logitski:||za:poR
+æ	otvoRene:||e:
+þ	soRn
+¯	pRuh||nad
+ð	ed
+ƒ	floRe:n
+_†	kRi:Z
+_≈	pRibliZn^e||sa||Rovna:
+_≠	n^eRovna:||sa
+_≤	menSi:||alebo||sa||Rovna:
+_≥	v&tSSi:||alebo||sa||Rovna:
+_√	dRuha:||odmotsn^ina
+_∛	tRet;ia||odmotsn^ina
+_∞	n^ekon^etSno
+_■	tSieRni||StvoRets
+_□	bieli||StvoRets
+_◆	tSieRni||diamant
+_○	bieli||kRuh
+_●	tSieRni||kRuh
+_◦	odRa:Zka||v||tvaRe||bielej||bodki
+_✓	zaSkr-tnutie
+_✔	tutSne:||zaSkr-tnutie
+_➔	Si:pka||vpravo
+_➢	odRa:Zka||v||tvaRe||Si:pki
 
 
 // Numbers

dictsource/tr_rules

 .L01 ç f h k p q s ş t   // unvoiced consonants
 
 .L02 ı a o u   // back vowels
-
 .L03 i e ö ü î â ô û  // not-back vowels
 
 .replace
 .group r
         r        R
      A) r (A     *
+     ğ) r (A     *
 
 	ra (_S2  %Ra
 	re (_S2  %Re

phsource/compile_report

                 [tl#] kl
 ufric/tlh       [K] nso
                 [K] tn
-ufric/x         [x] base
+ufric/x_        [x] base
 ufric/x2        [x2] af
                 [x] ku
                 [Q2] ka
                 [t] hr
 ustop/t_dnt2    [t] base2
                 [d] kn
-                [t] es
 ustop/t_hi      [t[] base
                 [t] et
                 [t^] et
                 [@3] ur
                 [@] da
                 [@] am
+vowel/&_3       [&] az
 vowel/3_2       [3:] en-n
                 [@] zh
 vowel/3_3       [3:] en-rp
                 [&] sr
                 [a#] rw
                 [a/] rw
+                [a] az
                 [a] wo
                 [a] dv
                 [a:] dv
                 [A:] no
                 [aa] zhy
                 [a] hy
-                [a] az
 vowel/aa#       [O] en-us
                 [0] en-wi
                 [a2] fi
                 [a:] hi
                 [a] ne
                 [a] pa
+                [a] az
                 [a] ak
                 [a] mt
                 [A] kk
                 [o] bg
                 [o] tr
                 [o] fa
-                [o] az
                 [o] dv
                 [o:] dv
                 [o] tt
 vowel/o_mid2    [O] fr
                 [O] ht
+                [o] az
 vowel/oo        [o] base
                 [O:] en-sc
                 [O] en-wi
                 [u] is
                 [u] tr
                 [u] sl
+                [u] az
                 [u] am
                 [u] wo
 vowel/u#_2      [u-] sv
                 [u] vi
                 [u] sw
                 [u] nso
-                [u] az
                 [u] tn
 vowel/u#_5      [y] vi
 vowel/u_6       [u] ta

phsource/ph_azerbaijani

+
+phoneme i
+  vowel starttype #i endtype #i
+  length 180
+  FMT(vowel/ii_5)
+endphoneme
+
+phoneme e
+  vowel starttype #e endtype #e
+  length 200
+  FMT(vowel/e_mid2)
+endphoneme
+
+phoneme &
+  vowel starttype #e endtype #e
+  length 200
+  IF thisPh(isWordEnd) THEN
+    FMT(vowel/&_3)
+  ENDIF
+  FMT(vowel/&)
+endphoneme
+
+phoneme y
+  vowel starttype #u endtype #u
+  length 200
+  FMT(vowel/y)
+endphoneme
+
+phoneme W
+  vowel starttype #@ endtype #@
+  length 200
+  FMT(vowel/y#_2)
+endphoneme
+
+phoneme u
+  vowel starttype #u endtype #u
+  length 180
+  FMT(vowel/u_2)
+endphoneme
+
+phoneme o
+  vowel starttype #o endtype #o
+  length 200
+  FMT(vowel/o_mid2)
+endphoneme
+
+phoneme a
+  vowel starttype #a endtype #a
+  length 200
+  IF thisPh(isWordEnd) THEN
+    FMT(vowel/a#)
+  ENDIF
+  FMT(vowel/aa_9)
+endphoneme
+
+phoneme @
+  vowel starttype #@ endtype #@
+  ipa ɯ
+  length 180
+  FMT(vowel/u#_7)
+endphoneme
+

phsource/ph_base2

 
 phoneme a
   vowel starttype #a endtype #a
-  length 180
+  length 190
   IF thisPh(isDiminished) THEN
     ChangePhoneme(a/)
     FMT(vowel/a#)
 
 phoneme a/
   vowel starttype #@ endtype #@
-  length 180
+  length 190
   FMT(vowel/a#)
 endphoneme
 
 
 phoneme e
   vowel starttype #e endtype #e
-  length 170
+  length 180
   FMT(vowel/e)
 endphoneme
 
 
 phoneme E
   vowel starttype #e endtype #e
-  length 170
+  length 180
   FMT(vowel/ee_1)
 endphoneme
 
 
 phoneme i
   vowel starttype #i endtype #i
-  length 150
+  length 170
   IfNextVowelAppend(;)
   FMT(vowel/i)
 endphoneme
 
 phoneme o
   vowel starttype #o endtype #o
-  length 170
+  length 180
   FMT(vowel/o)
 endphoneme
 
 
 phoneme O
   vowel starttype #o endtype #o
-  length 170
+  length 180
   FMT(vowel/oo_4)
 endphoneme
 
 
 phoneme u
   vowel starttype #u endtype #u
-  length 160
+  length 180
   FMT(vowel/u_bck)
 endphoneme
 
 
 phoneme U
   vowel starttype #u endtype #u
-  length 160
+  length 180
   FMT(vowel/uu_2)
 endphoneme
 
 
 phoneme y
   vowel starttype #i endtype #i
-  length 160
+  length 180
   FMT(vowel/y)
 endphoneme
 
 
 phoneme Y
   vowel starttype #@ endtype #@
-  length 160
+  length 180
   FMT(vowel/y#)
 endphoneme
 

phsource/ph_spanish

   ENDIF
 endphoneme
 
-phoneme t        // dental variant of /t/
-  vls dnt stop
-  voicingswitch d[
-  lengthmod 2
-  Vowelin f1=1  f2=1500 -250 250  f3=-100 80  amp=16
-  Vowelout f1=0 f2=1500 -300 250  f3=-100 80  rms=20
-
-  IF nextPh(isPause2) THEN
-    WAV(ustop/t_dnt2, 35)
-  ENDIF
-  WAV(ustop/t_dnt2, 70)
 
+phoneme t        // dental variant of /t/
+  import_phoneme base/t[
 endphoneme
 
 
-
 phoneme s
   vls alv frc sibilant
   lengthmod 3

phsource/phonemes

 
 
 phoneme j
-  liquid palatal
+  liquid palatal starttype #i
   lengthmod 7
 
   IF nextPhW(isVowel) THEN
   Vowelout f1=0 f2=2300 300 400  f3=-100 80  rms=20
 
   IF nextPh(isPause) THEN
-    WAV(ufric/x, 110)
+    WAV(ufric/x_, 60)
   ENDIF
   WAV(ufric/x_hr, 20)
 endphoneme

src/compiledict.cpp

 			ix = utf8_in(&c2,p);
 			if(c2 == 0)
 				break;
-			if(iswupper(c2))
+			if(iswupper2(c2))
 			{
-				utf8_out(towlower(c2),p);
+				utf8_out(towlower2(c2),p);
 			}
 			else
 			{

src/dictionary.cpp

 unsigned short ipa1[96] = {
 	0x20,0x21,0x22,0x2b0,0x24,0x25,0x0e6,0x2c8,0x28,0x27e,0x2a,0x2b,0x2cc,0x2d,0x2e,0x2f,
 	0x252,0x31,0x32,0x25c,0x34,0x35,0x36,0x37,0x275,0x39,0x2d0,0x2b2,0x3c,0x3d,0x3e,0x294,
-	0x259,0x251,0x3b2,0xe7,0xf0,0x25b,0x46,0x262,0x127,0x26a,0x25f,0x4b,0x29f,0x271,0x14b,0x254,
+	0x259,0x251,0x3b2,0xe7,0xf0,0x25b,0x46,0x262,0x127,0x26a,0x25f,0x4b,0x26b,0x271,0x14b,0x254,
 	0x3a6,0x263,0x280,0x283,0x3b8,0x28a,0x28c,0x153,0x3c7,0xf8,0x292,0x32a,0x5c,0x5d,0x5e,0x5f,
 	0x60,0x61,0x62,0x63,0x64,0x65,0x66,0x261,0x68,0x69,0x6a,0x6b,0x6c,0x6d,0x6e,0x6f,
 	0x70,0x71,0x72,0x73,0x74,0x75,0x76,0x77,0x78,0x79,0x7a,0x7b,0x7c,0x7d,0x303,0x7f
 
 
 
-void GetTranslatedPhonemeString(char *phon_out, int n_phon_out, int use_ipa)
-{//=========================================================================
-	/* Can be called after a clause has been translated into phonemes, in order
+void GetTranslatedPhonemeString(char *phon_out, int n_phon_out, int phoneme_mode)
+{//===============================================================================
+	/* Called after a clause has been translated into phonemes, in order
 	   to display the clause in phoneme mnemonic form.
+
+	   phoneme_mode  bits 0-3: 0=only phoneme names, 1=ties, 2=ZWJ, 3=underscore separator
+	                 bit  4:   0=eSpeak phoneme names, 1=IPA
 	*/
 
 	int  ix;
 	char *buf;
 	int count;
 	int flags;
+	int use_ipa;
+	int use_tie;
 	int separate_phonemes = 0;
 	char phon_buf[30];
 	char phon_buf2[30];
 	static const char *stress_chars = "==,,''";
 	static const int char_tie[] = {0x0361, 0x200d};  // combining-double-inverted-breve, zero-width-joiner
 
-	if(use_ipa >= 4)
+	use_ipa = phoneme_mode & 0x10;
+	use_tie = phoneme_mode & 0x0f;
+
+	if(use_tie >= 3)
 	{
 		// separate individual phonemes with underscores
 		separate_phonemes = '_';
-		if(use_ipa == 5)
-			use_ipa = 0;
-		else
-			use_ipa = 1;
+		use_tie = 0;
 	}
+
 	if(phon_out != NULL)
 	{
 		for(ix=1; ix<(n_phoneme_list-2); ix++)
 			buf = phon_buf;
 
 			plist = &phoneme_list[ix];
+
+			WritePhMnemonic(phon_buf2, plist->ph, plist, use_ipa, &flags);
 			if(plist->newword)
 				*buf++ = ' ';
 			else
 			{
 				if((separate_phonemes != 0) && (ix > 1))
 				{
-					*buf++ = separate_phonemes;
+					utf8_in(&c, phon_buf2);
+					if((c < 0x2b0) || (c > 0x36f))  // not if the phoneme starts with a superscript letter
+					{
+						*buf++ = separate_phonemes;
+					}
 				}
 			}
 
 			}
 
 			flags = 0;
-			WritePhMnemonic(phon_buf2, plist->ph, plist, use_ipa, &flags);
 			count = 0;
 			for(p=phon_buf2; *p != 0;)
 			{
 				p += utf8_in(&c, p);
-				if(use_ipa > 1)
+				if(use_tie > 0)
 				{
 					// look for non-inital alphabetic character, but not diacritic, superscript etc.
-					if((count>0) && !(flags & (1 << (count-1))) && ((c < 0x2b0) || (c > 0x36f)) && iswalpha(c))
+					if((count>0) && !(flags & (1 << (count-1))) && ((c < 0x2b0) || (c > 0x36f)) && iswalpha2(c))
 					{
-						buf += utf8_out(char_tie[use_ipa-2], buf);
+						buf += utf8_out(char_tie[use_tie-1], buf);
 					}
 				}
 				buf += utf8_out(c, buf);
 			break;
 		}
 
-		if((c != '\'') && !iswalpha(c))
+		if((c != '\'') && !iswalpha2(c))
 			return(0);
 	}
 
 					break;
 
 				case RULE_NONALPHA:
-					if(!iswalpha(letter_w))
+					if(!iswalpha2(letter_w))
 					{
 						add_points = (21-distance_right);
 						post_ptr += letter_xbytes;
 					break;
 
 				case RULE_NONALPHA:
-					if(!iswalpha(letter_w))
+					if(!iswalpha2(letter_w))
 					{
 						add_points = (21-distance_right);
 						pre_ptr -= letter_xbytes;
 						if(tr->letter_bits_offset > 0)
 						{
 							// not a Latin alphabet, switch to the default Latin alphabet language
-							if((letter <= 0x241) && iswalpha(letter))
+							if((letter <= 0x241) && iswalpha2(letter))
 							{
 								sprintf(phonemes,"%c%s",phonSWITCH,tr->langopts.ascii_language);
 								return(0);

src/espeakedit.cpp

 
 	case MENU_PATH0:
 		string = wxFileSelector(_T("Master phonemes file"),wxFileName(path_phfile).GetPath(),
-			_T(""),_T(""),_T("*"),wxOPEN);
+			_T("phonemes"),_T(""),_T("*"),wxOPEN);
 		if(!string.IsEmpty())
 		{
 			path_phfile = string;

src/extras.cpp

 		for(k=0; k<ix; )
 		{
 			k += utf8_in(&wc,&buf[k]);
-			wc = towlower(wc);       // convert to lower case
-			if(iswalpha(wc))
+			wc = towlower2(wc);       // convert to lower case
+			if(iswalpha2(wc))
 			{
 				j += utf8_out(wc,&wbuf[j]);
 				n_chars++;
 	}
 
 	fprintf(f, "\nstatic const short wchar_tolower[] = {\n");
-	exceptions[ex] = 0;
-	exceptions[ex+1] = 0;
-	for(ix=0; ix<=ex; ix+=2)
+
+	for(ix=0; ix<ex; ix+=2)
 	{
 		fprintf(f,"\t0x%.3x, 0x%.3x,\n", exceptions[ix], exceptions[ix+1]);
 	}
-	fprintf(f, "};\n");
+	fprintf(f, "\t0,0 };\n");
+
+	fprintf(f, "\nstatic const short wchar_toupper[] = {\n");
+	for(ix=0x80; ix<=MAX_WALPHA; ix++)
+	{
+		if(iswlower(ix))
+		{
+			c = towupper(ix);
+			value =  ix - c;
+			if((value != 32) && (value != 1))
+			{
+				fprintf(f,"\t0x%.3x, 0x%.3x,\n", ix, c);
+			}
+		}
+	}
+	fprintf(f, "\t0,0 };\n");
+
 	fclose(f);
 }
 
 //CharsetToUnicode("ISO-8859-4");
 //CharsetToUnicode("ISCII");
 
+
 if(control==2)
 {
 	return;

src/numbers.cpp

 	return(-1);
 }
 
+#define L_SUB 0x4000   // subscript
+#define L_SUP 0x8000   // superscript
+
+static const char *modifiers[] = {NULL, "_sub", "_sup", NULL};
+
+// this list must be in ascending order
+static unsigned short derived_letters[] = {
+	0x00aa, 'a'+L_SUP,
+	0x00b2, '2'+L_SUP,
+	0x00b3, '3'+L_SUP,
+	0x00b9, '1'+L_SUP,
+	0x00ba, 'o'+L_SUP,
+	0x02b0, 'h'+L_SUP,
+	0x02b1, 0x266+L_SUP,
+	0x02b2, 'j'+L_SUP,
+	0x02b3, 'r'+L_SUP,
+	0x02b4, 0x279+L_SUP,
+	0x02b5, 0x27b+L_SUP,
+	0x02b6, 0x281+L_SUP,
+	0x02b7, 'w'+L_SUP,
+	0x02b8, 'y'+L_SUP,
+	0x02c0, 0x294+L_SUP,
+	0x02c1, 0x295+L_SUP,
+	0x02e0, 0x263+L_SUP,
+	0x02e1, 'l'+L_SUP,
+	0x02e2, 's'+L_SUP,
+	0x02e3, 'x'+L_SUP,
+	0x2070, '0'+L_SUP,
+	0x2071, 'i'+L_SUP,
+	0x2074, '4'+L_SUP,
+	0x2075, '5'+L_SUP,
+	0x2076, '6'+L_SUP,
+	0x2077, '7'+L_SUP,
+	0x2078, '8'+L_SUP,
+	0x2079, '9'+L_SUP,
+	0x207a, '+'+L_SUP,
+	0x207b, '-'+L_SUP,
+	0x207c, '='+L_SUP,
+	0x207d, '('+L_SUP,
+	0x207e, ')'+L_SUP,
+	0x207f, 'n'+L_SUP,
+	0x2080, '0'+L_SUB,
+	0x2081, '1'+L_SUB,
+	0x2082, '2'+L_SUB,
+	0x2083, '3'+L_SUB,
+	0x2084, '4'+L_SUB,
+	0x2085, '5'+L_SUB,
+	0x2086, '6'+L_SUB,
+	0x2087, '7'+L_SUB,
+	0x2088, '8'+L_SUB,
+	0x2089, '9'+L_SUB,
+	0x208a, '+'+L_SUB,
+	0x208b, '-'+L_SUB,
+	0x208c, '='+L_SUB,
+	0x208d, '('+L_SUB,
+	0x208e, ')'+L_SUB,
+	0x2090, 'a'+L_SUB,
+	0x2091, 'e'+L_SUB,
+	0x2092, 'o'+L_SUB,
+	0x2093, 'x'+L_SUB,
+	0x2094, 0x259+L_SUB,
+	0x2095, 'h'+L_SUB,
+	0x2096, 'k'+L_SUB,
+	0x2097, 'l'+L_SUB,
+	0x2098, 'm'+L_SUB,
+	0x2099, 'n'+L_SUB,
+	0x209a, 'p'+L_SUB,
+	0x209b, 's'+L_SUB,
+	0x209c, 't'+L_SUB,
+	0,0};
+
 
 static const char *hex_letters[] = {"'e:j","b'i:","s'i:","d'i:","'i:","'ef"};  // names, using phonemes available to all languages
 
 	int letter;
 	int len;
 	int ix;
+	int c;
 	char *p2;
 	char *pbuf;
+	const char *modifier;
 	ALPHABET *alphabet;
 	int al_offset;
 	int al_flags;
 	int number;
 	int phontab_1;
 	int speak_letter_number;
-	char capital[20];
+	char capital[30];
 	char ph_buf[80];
 	char ph_buf2[80];
 	char ph_alphabet[80];
 	if(control & 2)
 	{
 		// include CAPITAL information
-		if(iswupper(letter))
+		if(iswupper2(letter))
 		{
 			Lookup(tr, "_cap", capital);
 		}
 	}
 	letter = towlower2(letter);
 
+	// is this a subscript or superscript letter ?
+	for(ix=0; (c = derived_letters[ix]) != 0; ix+=2)
+	{
+		if(c > letter)
+			break;
+		if(c == letter)
+		{
+			c = derived_letters[ix+1];
+			letter = c & 0x3fff;
+			if((modifier = modifiers[c >> 14]) != NULL)
+			{
+				Lookup(tr, modifier, capital);
+				if(capital[0] == 0)
+				{
+					capital[2] = SetTranslator2("en");   // overwrites previous contents of translator2
+					Lookup(translator2, modifier, &capital[3]);
+					if(capital[3] != 0)
+					{
+						capital[0] = phonPAUSE;
+						capital[1] = phonSWITCH;
+						len = strlen(&capital[3]);
+						capital[len+3] = phonSWITCH;
+						capital[len+4] = phontab_1;
+						capital[len+5] = 0;
+					}
+				}
+			}
+		}
+	}
 	LookupLetter(tr, letter, word[n_bytes], ph_buf, control & 1);
 
 	if(ph_buf[0] == phonSWITCH)
 		return(0);
 	}
 
+
 	if((ph_buf[0] == 0) && ((number = NonAsciiNumber(letter)) > 0))
 	{
 		// convert a non-ascii number to 0-9
 			speak_letter_number = 1;
 			if(!(al_flags & AL_NO_SYMBOL))
 			{
-				if(iswalpha(letter))
+				if(iswalpha2(letter))
 					Lookup(translator, "_?A", ph_buf);
 
 				if((ph_buf[0]==0) && !iswspace(letter))
 		if((tr->langopts.numbers & NUM_NOPAUSE) && (next_char == ' '))
 			utf8_in(&next_char,p);
 
-		if(!iswalpha(next_char) && (thousands_exact==0))
-//		if(!iswalpha(next_char) && !((wtab[thousandplex].flags & FLAG_HYPHEN_AFTER) && (thousands_exact != 0)))
+		if(!iswalpha2(next_char) && (thousands_exact==0))
+//		if(!iswalpha2(next_char) && !((wtab[thousandplex].flags & FLAG_HYPHEN_AFTER) && (thousands_exact != 0)))
 			strcat(ph_out,str_pause);  // don't add pause for 100s,  6th, etc.
 	}
 

src/readclause.cpp

 	0x23d, 0x19a,
 	0x23e, 0x2c66,
 	0x243, 0x180,
-	0x000, 0x000,
-};
+	0,0 };
+
+static const short wchar_toupper[] = {
+	0x0b5, 0x39c,
+	0x0df, 0x0df,
+	0x0ff, 0x178,
+	0x131, 0x049,
+	0x17f, 0x053,
+	0x180, 0x243,
+	0x195, 0x1f6,
+	0x19a, 0x23d,
+	0x19e, 0x220,
+	0x1bf, 0x1f7,
+	0x1c6, 0x1c4,
+	0x1c9, 0x1c7,
+	0x1cc, 0x1ca,
+	0x1dd, 0x18e,
+	0x1f3, 0x1f1,
+	0,0 };
 
 
 #ifdef NEED_WCHAR_FUNCTIONS
 
 int towupper(int c)
 {
+	int ix;
 	// check whether a previous character code is the upper-case equivalent of this character
 	if(towlower(c-32) == c)
 		return(c-32); // yes, use it
 	if(towlower(c-1) == c)
 		return(c-1);
-	if(towlower(c-2) == c)
-		return(c-2);
+	for(ix=0; wchar_toupper[ix] != 0; ix+=2)
+	{
+		if(wchar_toupper[ix] == c)
+			return(wchar_toupper[ix+1]);
+	}
 	return(c);  // no
 }
 
 	return(walpha_tab[c-0x80]);
 }
 
+int iswlower2(int c)
+{
+	if(c < 0x80)
+		return(islower(c));
+	if(c > MAX_WALPHA)
+		return(iswlower(c));
+	if(walpha_tab[c-0x80] == 0xff)
+		return(1);
+	return(0);
+}
+
+int iswupper2(int c)
+{
+	int x;
+	if(c < 0x80)
+		return(isupper(c));
+	if(c > MAX_WALPHA)
+		return(iswupper(c));
+	if(((x = walpha_tab[c-0x80]) > 0) && (x < 0xfe))
+		return(1);
+	return(0);
+}
 
 int towlower2(unsigned int c)
 {
 	// check for non-standard upper to lower case conversions
 	if(c == 'I')
 	{
-		if(translator->translator_name == L('t','r'))
+		if(translator->langopts.dotless_i)
 		{
 			c = 0x131;   // I -> ı
 		}
 	return(c + x);  // convert to lower case
 }
 
+int towupper2(unsigned int c)
+{
+	int ix;
+	if(c > MAX_WALPHA)
+		return(towupper(c));
+
+	// check whether a previous character code is the upper-case equivalent of this character
+	if(towlower2(c-32) == c)
+		return(c-32); // yes, use it
+	if(towlower2(c-1) == c)
+		return(c-1);
+	for(ix=0; wchar_toupper[ix] != 0; ix+=2)
+	{
+		if(wchar_toupper[ix] == c)
+			return(wchar_toupper[ix+1]);
+	}
+	return(c);  // no
+}
 
 static int IsRomanU(unsigned int c)
 {//================================
 					c2 = ' ';
 				}
 				else
-				if((c2 == '/') || iswalpha(c2))
+				if((c2 == '/') || iswalpha2(c2))
 				{
 					// check for space in the output buffer for embedded commands produced by the SSML tag
 					if(ix > (n_buf - 20))
 			}
 		}
 
-		if(iswupper(c1))
+		if(iswupper2(c1))
 		{
 			tr->clause_upper_count++;
-			if((option_capitals == 2) && (sayas_mode == 0) && !iswupper(cprev))
+			if((option_capitals == 2) && (sayas_mode == 0) && !iswupper2(cprev))
 			{
 				char text_buf[40];
 				char text_buf2[30];
 			}
 		}
 		else
-		if(iswalpha(c1))
+		if(iswalpha2(c1))
 			tr->clause_lower_count++;
 
 		if(option_phoneme_input)
 
 				if(!iswspace(c1))
 				{
-					if(!IsAlpha(c1) || !iswlower(c1))
-//					if(iswdigit(c1) || (IsAlpha(c1) && !iswlower(c1)))
+					if(!IsAlpha(c1) || !iswlower2(c1))
+//					if(iswdigit(c1) || (IsAlpha(c1) && !iswlower2(c1)))
 					{
 						UngetC(c2);
 						ungot_char2 = c1;
 
 				if(nl_count==0)
 				{
-					if((c1 == ',') && (cprev == '.') && (tr->translator_name == L('h','u')) && iswdigit(cprev2) && (iswdigit(c_next) || (iswlower(c_next))))
+					if((c1 == ',') && (cprev == '.') && (tr->translator_name == L('h','u')) && iswdigit(cprev2) && (iswdigit(c_next) || (iswlower2(c_next))))
 					{
 						// lang=hu, fix for ordinal numbers, eg:  "december 2., szerda", ignore ',' after ordinal number
 						c1 = CHAR_COMMA_BREAK;
 							}
 							else
 							{
-								if (iswlower(c_next) || (c_next=='-'))     // hyphen is needed for lang-hu (eg. 2.-kal)
+								if (iswlower2(c_next) || (c_next=='-'))     // hyphen is needed for lang-hu (eg. 2.-kal)
 									is_end_clause = 0;      // only if followed by lower-case, (or if there is a XML tag)
 							}
 						}
 						{
 							is_end_clause = 0;    // eg. u.s.a.'s
 						}
-						if(iswlower(c_next))
+						if(iswlower2(c_next))
 						{
 							// next word has no capital letter, this dot is probably from an abbreviation
 //							c1 = ' ';

src/speak_lib.cpp

 }   //  end of espeak_SetPhonemes
 
 
+ESPEAK_API void espeak_TextToPhonemes(const void *text, char *buffer, int size, int textmode, int phonememode)
+{//==============================================================================================================
+	/* phoneme_mode  bits 0-3: 0=only phoneme names, 1=ties, 2=ZWJ, 3=underscore separator
+	                 bit  4:   0=eSpeak phoneme names, 1=IPA
+	*/
+	option_multibyte = textmode & 7;
+	TranslateClause(translator, NULL, text, NULL, NULL);
+	GetTranslatedPhonemeString(buffer, size, phonememode);
+}
+
+
 ESPEAK_API void espeak_CompileDictionary(const char *path, FILE *log, int flags)
 {//=============================================================================
 	ENTER("espeak_CompileDictionary");

src/synthdata.cpp

 #include "translate.h"
 #include "wave.h"
 
-const char *version_string = "1.47.07a  23.Apr.13";
+const char *version_string = "1.47.07b  25.Apr.13";
 const int version_phdata  = 0x014701;
 
 int option_device_number = -1;

src/synthesize.cpp

 
 	if((option_phonemes > 0) || (phoneme_callback != NULL))
 	{
-		int use_ipa = 0;
+		int phoneme_mode = 0;
 		if(option_phonemes >= 3)
-			use_ipa = option_phonemes-2;   // 1=ipa, 2=ipa with tie, 3=ipa with ZWJ, 4=ipa with separators
+			phoneme_mode = 0x10 + option_phonemes-3;   // 0x10=ipa, 0x11=ipa with tie, 0x12=ipa with ZWJ, 0x13=ipa with separators
 
-		GetTranslatedPhonemeString(translator->phon_out, sizeof(translator->phon_out), use_ipa);
+		GetTranslatedPhonemeString(translator->phon_out, sizeof(translator->phon_out), phoneme_mode);
 		if(option_phonemes > 0)
 		{
 			fprintf(f_trans,"%s\n",translator->phon_out);
-
-			if(!iswalpha(0x010d))
-			{
-				// check that c-caron is recognized as an alphabetic character
-				fprintf(stderr,"Warning: Accented letters are not recognized, eg: U+010D\nSet LC_CTYPE to a UTF-8 locale\n");
-			}
 		}
 		if(phoneme_callback != NULL)
 		{

src/tr_languages.cpp

 			SetLetterBits(tr,LETTERGP_VOWEL2,hy_vowels);
 			SetLetterBits(tr,LETTERGP_C,hy_consonants);
 			tr->langopts.max_initial_consonants = 6;
-			tr->langopts.numbers = NUM_DECIMAL_COMMA | NUM_OMIT_1_HUNDRED;
+			tr->langopts.numbers = NUM_DECIMAL_COMMA | NUM_ALLOW_SPACE | NUM_OMIT_1_HUNDRED;
 		//	tr->langopts.param[LOPT_UNPRONOUNCABLE] = 1;   // disable check for unpronouncable words
 		}
 		break;
 			ResetLetterBits(tr,0x2);
 			SetLetterBits(tr,1,"bcdfgjkmnpqstvxz");      // B  hard consonants, excluding h,l,r,w,y
 			tr->langopts.param[LOPT_ALT] = 2;      // call ApplySpecialAttributes2() if a word has $alt or $alt2
+			tr->langopts.accents = 2;  // 'capital' after letter name
 		}
 		break;
 
 
 			tr->langopts.stress_rule = 7;   // stress on the last syllable, before any explicitly unstressed syllable
 			tr->langopts.stress_flags = S_NO_AUTO_2;  //no automatic secondary stress
+			tr->langopts.dotless_i = 1;
 			tr->langopts.param[LOPT_SUFFIX] = 1;
 
 			if(name2 == L('a','z'))

src/translate.cpp

 	while((*word != 0) && !isspace2(*word))
 	{
 		word += utf8_in(&c, word);
-		if(!iswupper(c))
+		if(!iswupper2(c))
 			return(0);
 	}
 	return(1);
 			}
 		}
 
-		if((wflags & FLAG_ALL_UPPER) && (word_length > 1)&& iswalpha(first_char))
+		if((wflags & FLAG_ALL_UPPER) && (word_length > 1)&& iswalpha2(first_char))
 		{
 			if((option_tone_flags & OPTION_EMPHASIZE_ALLCAPS) && !(dictionary_flags[0] & FLAG_ABBREV))
 			{
 			tr->expect_past--;
 	}
 
-	if((word_length == 1) && (tr->translator_name == L('e','n')) && iswalpha(first_char) && (first_char != 'i'))
+	if((word_length == 1) && (tr->translator_name == L('e','n')) && iswalpha2(first_char) && (first_char != 'i'))
 	{
 // English Specific !!!!
 		// any single letter before a dot is an abbreviation, except 'I'
 			while(*p2 != ' ') p2++;
 
 			utf8_in(&c_word2, p2+1);   // first character of the next word;
-			if(!iswalpha(c_word2))
+			if(!iswalpha2(c_word2))
 			{
 				ok =0;
 			}
 
 	// there is a list of character codes to be substituted with alternative codes
 
-	if(iswupper(c_lower = c))
+	if(iswupper2(c_lower = c))
 	{
-		c_lower = towlower(c);
+		c_lower = towlower2(c);
 		upper_case = 1;
 	}
 
 				new_c = replace_chars[ix+1];
 				break;
 			}
-			if((word >> 16) == (unsigned int)towlower(next_in))
+			if((word >> 16) == (unsigned int)towlower2(next_in))
 			{
 				new_c = replace_chars[ix+1];
 				ignore_next = 1;
 		// there is a second character to be inserted
 		// don't convert the case of the second character unless the next letter is also upper case
 		c2 = new_c >> 16;
-		if(upper_case && iswupper(next_in))
-			c2 = towupper(c2);
+		if(upper_case && iswupper2(next_in))
+			c2 = towupper2(c2);
 		*insert = c2;
 		new_c &= 0xffff;
 	}
 
 	if(upper_case)
-		new_c = towupper(new_c);
+		new_c = towupper2(new_c);
 
 	*wordflags |= FLAG_CHAR_REPLACED;
 	return(new_c);
 		// look for 'n  and replace by a special character (unicode: schwa)
 
 
-		if(!iswalpha(prev_in))
+		if(!iswalpha2(prev_in))
 		{
 			utf8_in(&next2, &ptr[1]);
 
 					}
 					else
 					{
-						if(iswupper(c))
+						if(iswupper2(c))
 							word_flags |= FLAG_FIRST_UPPER;
 
 						if((prev_out == ' ') && iswdigit(sbuf[ix-2]) && !iswdigit(prev_in))
 					}
 				}
 
-				if(iswupper(c))
+				if(iswupper2(c))
 				{
 					c = towlower2(c);
 
 					}
 					else
 					{
-						if((iswlower(prev_in)) && (prev_in != 0xba))  // Windows thinks masc.ordinal (0xba) is lower-case
+						if(iswlower2(prev_in))
 						{
 							// lower case followed by upper case in a word
 							if(UpperCaseInWord(tr, &sbuf[ix], c) == 1)
 								//							next_word_flags |= FLAG_NOSPACE;  // problem: prevents FLAG_HAS_DOT being set
 							}
 						}
-						else if((c != ' ') && iswupper(prev_in) && iswlower(next_in))
+						else if((c != ' ') && iswupper2(prev_in) && iswlower2(next_in))
 						{
 							int next2_in;
 							utf8_in(&next2_in,&source[source_index + next_in_nbytes]);

src/translate.h

 	char tone_numbers;
 	char ideographs;      // treat as separate words
 	char textmode;          // the meaning of FLAG_TEXTMODE is reversed (to save data when *_list file is compiled)
+	char dotless_i;         // uses letter U+0131
 	int testing;            // testing options: bit 1= specify stressed syllable in the form:  "outdoor/2"
 	int listx;    // compile *_listx after *list
 	const unsigned int *replace_chars;      // characters to be substitutes
 int IsVowel(Translator *tr, int c);
 int iswalpha2(int c);
 int isspace2(unsigned int c);
+int iswlower2(int c);
+int iswupper2(int c);
 int towlower2(unsigned int c);
-void GetTranslatedPhonemeString(char *phon_out, int n_phon_out, int use_ipa);
+int towupper2(unsigned int c);
+void GetTranslatedPhonemeString(char *phon_out, int n_phon_out, int phoneme_mode);
 const char *WordToString2(unsigned int word);
 ALPHABET *AlphabetFromChar(int c);
 ALPHABET *AlphabetFromName(const char *name);

src/transldlg.cpp

 		t_phonetic->SetDefaultStyle(style_phonetic_large);
 
 		translate_text = 3;
-		use_ipa = 1;
+		use_ipa = 0x10;
 		break;
 
 	case T_PROCESS:

src/voices.cpp

 
 	// which directory to look for a named voice. List of voice names, must end in a space.
 	static const char *voices_asia =
-		"bn fa fa-pin hi hy hy-west id ka kn ku ml ms ne pa ta te tr vi vi-hue vi-sgn zh zh-yue ";
+		"az bn fa fa-pin hi hy hy-west id ka kn ku ml ms ne pa ta te tr vi vi-hue vi-sgn zh zh-yue ";
 	static const char *voices_europe =
 		"an bg bs ca cs cy da de el en en-us es et fi fr fr-be ga hr hu is it lt lv mk nl no pl pt-pt ro ru sk sq sr sv ";