uz: add initial support for Uzbek language

CHANGELOG.md

@@ -53,6 +53,7 @@ new languages:
 *  quc (K'iche') -- Valdis Vitolins
 *  ru-lv (Russian Latvia) -- Valdis Vitolins
 *  shn (Shan Tay Yai) -- ronaldaug
+*  uz (Uzbek) -- Valdis Vitolins
 
 updated languages:
 

Makefile.am

@@ -543,6 +543,7 @@ dictionaries: \
 	espeak-ng-data/tr_dict \
 	espeak-ng-data/tt_dict \
 	espeak-ng-data/ur_dict \
+	espeak-ng-data/uz_dict \
 	espeak-ng-data/vi_dict \
 	espeak-ng-data/zh_dict \
 	espeak-ng-data/zhy_dict
@@ -831,6 +832,9 @@ espeak-ng-data/tt_dict: dictsource/tt_list dictsource/tt_rules dictsource/tt_ext
 ur: espeak-ng-data/ur_dict
 espeak-ng-data/ur_dict: dictsource/ur_list dictsource/ur_rules dictsource/ur_extra dictsource/ur_emoji
 
+uz: espeak-ng-data/uz_dict
+espeak-ng-data/uz_dict: dictsource/uz_list dictsource/uz_rules dictsource/uz_extra
+
 vi: espeak-ng-data/vi_dict
 espeak-ng-data/vi_dict: dictsource/vi_list dictsource/vi_rules dictsource/vi_extra dictsource/vi_emoji
 

dictsource/uz_list

@@ -0,0 +1,132 @@
+// This file is UTF8 encoded
+// Specifi words for Uzbek language
+
+// names of letters
+
+a   a
+b   be
+d   de
+e   e
+f   ef
+g   ge
+h   ha
+i   i
+j   je
+k   ka
+l   el
+m   em
+n   en
+o   o
+p   pe
+q   qa
+r   er
+s   es
+t   te
+u   u
+v   ve
+x   xa
+y   ye
+z   ze
+oʻ  o
+gʻ  ga
+sh  sha
+ch  che
+ng  nge
+
+// numbers
+_1    bir
+_2    ikki
+_3    uc
+_4    to'rt
+_5    besh
+_6    olti
+_7    etti
+_8    sakkiz
+_9    to'qqiz
+_10   o'n
+_20   yigirma
+_30   o'ttiz
+_40   qirq
+_50   ellik
+_60   oltmish
+_70   etmish
+_80   sakson
+_90   to'qson
+_0C   yuz
+_1M1  ming
+_1M2  million
+_1M3  milliard
+
+// unstressed words
+atrofida                   $u
+bilan                      $u
+bu                         $u
+bular                      $u
+(dan||tashqari)            $u
+(dan||uzoq)                $u
+davomida                   $u
+ga                         $u
+gacha                      $u
+haqida                     $u
+ichida                     $u
+ichidan                    $u
+ichiga                     $u
+yaqin                      $u
+yonida                     $u
+yonma-yon                  $u
+keyin                      $u
+(Ko'rsatish||olmoshlari)   $u
+lekin                      $u
+lozim                      $u
+mobaynida                  $u
+(narigi||tomonida)         $u
+oldin                      $u
+orasidan                   $u
+orqada                     $u
+orqali                     $u
+orqasida                   $u
+o'y                        $u
+o'rtasida                  $u
+ostida                     $u
+o'stida                    $u
+o'xshab                    $u
+pastda                     $u
+pastida                    $u
+past||tomoniga             $u
+qaramay                    $u
+qarama-qarshi              $u
+qarshi                     $u
+qo'shuv                    $u
+sababida                   $u
+tagida                     $u
+tashqarida                 $u
+taxminan                   $u
+tepada                     $u
+tepasida                   $u
+tomonidan                  $u
+u                          $u
+(uchta||so'zlar)           $u
+uchun                      $u
+ular                       $u
+
+// pronouns
+biz        $u
+bizga      $u
+bizniki    $u
+bizning    $u
+men        $u
+menga      $u
+meniki     $u
+mening     $u
+sen        $u
+senga      $u
+sening     $u
+senini     $u
+u          $u
+ular       $u
+ularga     $u
+ularniki   $u
+ularning   $u
+unga       $u
+uniki      $u
+uning      $u

dictsource/uz_rules

@@ -0,0 +1,139 @@
+// This file is UTF8 encoded
+// Spelling to phoneme rules for Uzbek language
+
+.replace
+// Replace Cyrrilic script to Latin script
+    а    a
+    б    b
+    ц    c
+    д    d
+    е    e
+    э    e
+    ф    f
+    г    g
+    ҳ    h
+    и    i
+    ж    j
+    к    k
+    л    l
+    м    m
+    н    n
+    о    o
+    п    p
+    қ    q
+    р    r
+    с    s
+    т    t
+    у    u
+    в    v
+    х    x
+    й    y
+    з    z
+    ў    ó
+    ғ    ǵ
+    ш    š
+    ч    ç
+    ю    ju  
+    я    ja
+    ь    ʼ   
+    ъ    ʼ 
+
+// Replace left single quotation mark to  modifier letter turned comma 
+    ‘    ʻ     
+
+.group a
+    a    a
+
+.group b
+    b    b
+
+.group c
+    c     ts
+    ch    tS
+
+.group d
+    d    d
+
+.group e
+    e    e
+
+.group f
+    f    f
+
+.group g
+    g    g
+
+.group h
+    h    h
+
+.group i
+    i    i
+
+.group j
+    j    j
+
+.group k
+    k    k
+
+.group l
+    l    l
+
+.group m
+    m    m
+
+.group n
+    n    n
+    ng   N
+
+.group o
+    o    o
+
+.group p
+    p    p
+
+.group q
+    q    q
+
+.group r
+    r    r
+
+.group s
+    s    s
+    sh    sh
+
+.group t
+    t    t
+
+.group u
+    u    u
+
+.group v
+    v    v
+
+.group x
+    x    X
+
+.group y
+    y    j
+
+.group z
+    z    z
+
+.group o
+    o     o
+    oʻ    o
+
+.group g
+    g     g
+    gʻ    g
+
+.group ʼ
+    ʼ     ?
+
+.group
+    '     ?
+    ʻ     ?
+    ó     o:
+    ǵ     J
+    ş     S
+    ç     tS

espeak-ng-data/lang/trk/uz

@@ -0,0 +1,4 @@
+name Uzbek
+language uz
+
+status testing

phsource/ph_uzbek

@@ -0,0 +1,2 @@
+// This file is currently empty and all phonemes are inherited from Turkish language
+// i.e. phsource/ph_turkish (and phsource/phonemes files)

phsource/phonemes

@@ -1999,6 +1999,9 @@ include ph_russian_lv
 phonemetable az tr
 include ph_azerbaijani
 
+phonemetable uz tr
+include ph_uzbek
+
 phonemetable pt-pt pt
 include ph_portugal