mahta.fetrat
/
HomoFast-eSpeak-Persian
Watch 1
Star 0
Fork 0
Code Issues 0 Pull Requests 0 Releases 0 Wiki Activity
Browse Source

Merge branch 'upstream' into development 

Conflicts:
	dictsource/dict_phonemes
	dictsource/kl_list
	dictsource/kl_rules
	dictsource/pa_list
	dictsource/pa_rules
	phsource/compile_report
master
Reece H. Dunn 12 years ago
parent
9ce297b0cb 61edd2d38f
commit
67ae48acc7
27 changed files with 1631 additions and 466 deletions
Split View Show Diff Stats
  1. 16
    13
      dictsource/bn_list
  2. 23
    45
      dictsource/bn_rules
  3. 20
    8
      dictsource/en_list
  4. 1
    0
      dictsource/en_rules
  5. 784
    0
      dictsource/ms_list
  6. 233
    0
      dictsource/ms_rules
  7. 246
    246
      dictsource/pa_list
  8. 29
    16
      dictsource/pt_list
  9. 40
    46
      dictsource/pt_rules
  10. 1
    1
      dictsource/sw_rules
  11. 1
    1
      dictsource/zhy_rules
  12. 28
    6
      docs/phontab.html
  13. 40
    2
      phsource/mbrola/id1
  14. 4
    0
      phsource/ph_bengali
  15. 51
    1
      phsource/ph_indonesian
  16. 42
    40
      phsource/phonemes
  17. BIN
      phsource/vwl_fr/trr
  18. 15
    5
      src/compiledata.cpp
  19. 5
    5
      src/compiledict.cpp
  20. 2
    2
      src/dictionary.cpp
  21. 18
    18
      src/numbers.cpp
  22. 2
    2
      src/readclause.cpp
  23. 17
    1
      src/synthdata.cpp
  24. 4
    1
      src/tr_languages.cpp
  25. 6
    5
      src/translate.cpp
  26. 1
    0
      src/translate.h
  27. 2
    2
      src/voices.cpp

+ 16
- 13
dictsource/bn_list View File

@@ -16,22 +16,22 @@ _9 n'Oj

_10 d'OS
_11 '&garo
_12 b'aro
_13 t'ero
_14 tS'owddo
_15 p'Onero
_16 S'olo
_17 S'Otero
_18 'at.#aro
_12 b'arO
_13 t'erO
_14 tS'owddO
_15 p'OnerO
_16 S'olO
_17 S'OterO
_18 'at.#arO
_19 'uniS

_20 b'iS // ??
_20 k'uri // or b'iS ??
_21 'ekuS
_22 b'ajS
_23 t'ejS
_24 tS'ObbiS
_25 p'O~tSiS
_26 tS#'ObbiS
_26 tSh'ObbiS
_27 S'ataS
_28 'at.#aS
_29 'untriS
@@ -108,14 +108,17 @@ _dpt dOsomik
ধ d#O
ন d'ontennO
প pO
ফ p#O
ফ fO // or [p#O] ?
ব bO
ভ b#O
ম mO
য় Oj
য ontostedZ'O
র rO
ঢ় hrO
ড় r.O
ড় r.O // (d. + nukta)
ঢ় hr.O
ঢ় hr.O // (d#. + nukta)
ল lO
শ taleboS:O
ষ mud#en:oS:O
@@ -124,8 +127,8 @@ _dpt dOsomik
ৎ kh'Ond.otO

// full vowels
অ SOro'O
আ SOro'a
অ O
আ a
ই hrOS:o'i
ঈ dirg#o'i
উ hrOS:o'u

+ 23
- 45
dictsource/bn_rules View File

@@ -136,57 +136,47 @@
ৌ ow
ৌঁ o~w

// Consonants

.group ক
ক kV
ক (B k
ক (_ k

.group খ
খ k#V
খ (B k#
খ (_ k#
.group গ
গ gV
গ (B g
গ (_ g


.group ঘ
ঘ g#V
ঘ (B g#
ঘ (_ g#

.group ঙ
ঙ NV
ঙ্ (B N
ঙ্ (_ N


.group চ
চ tSV
চ (B tS
চ (_ tS


.group ছ
ছ tS#V
ছ (B tS#
ছ (_ tS#

.group জ
জ JV
জ (B J
জ (_ J
জ্ব JV
জ্ব (B J
@@ -197,142 +187,122 @@
.group ঝ
ঝ J#V
ঝ (B J#
ঝ (_ J#

.group ঞ
ঞ nV
ঞ্ (B n
ঞ্ (_ n

.group ট
ট t.V
ট (B t.
ট (_ t.


.group ঠ
ঠ t.#V
ঠ (B t.#
ঠ (_ t.#

.group ড
ড d.V
ড (B d.
ড (_ d.

ড় r.V // nukta
ড় (B r.

.group ঢ
ঢ d.#V
ঢ (B d.#
ঢ (_ d.#
ঢ d.#V
ঢ (B d.#

ঢ় hr.V
ঢ় (B hr.
.group ণ
ণ nV // should be [n.] if adjacent to t. or d. ?
ণ (B n
ণ (_ n



.group ত
ত tV
ত (B t
ত (_ t

.group থ
থ t#V
থ (B t#
থ (_ t#


.group দ
দ dV
দ (B d
দ (_ d


.group ধ
ধ d#V
ধ (B d#
ধ (_ d#


.group ন
ন nV
ন (B n
ন (_ n

.group প
প pV
প (B p
প (_ p

.group ফ
ফ fV // or [p#] ?
ফ (B f
ফ (_ f

.group ব
ব bV
ব (B b
ব (_ b

.group ভ
ভ b#V
ভ (B b#
ভ (_ b#

.group ম
ম mV
ম (B m
ম (_ m

.group য়
য় jV
য় (B j
য় (_ j

.group য
য dZV
য (B dZ
য (_ dZ
য় jV // nukta
য় (B j
@) য় (_ j

.group র
র rV
র (B r
র (_ r
্) র (_ rV

.group ল
ল lV
ল (B l
ল (_ l



.group শ
শ SV // or [s] ?
শ (B S
শ (_ S
শ (্ল s
@@ -341,7 +311,6 @@
.group ষ
ষ SV
ষ (B S
ষ (_ S

.group স
@@ -358,26 +327,25 @@
.group হ
হ hV
হ (B h
হ (_ h

.group হ্ব
হ্ব vV
হ্ব (B v
হ্ব (_ v

.group ৎ
ৎ t


.group ড়
ড় r.V
ড় (B r.
.group ড় // can be ড plus nukta
ড় r.V
ড় (B r.

.group ঢ়
ঢ় r.V
ঢ় (B r.
.group ঢ় // can be ঢ plus nukta
ঢ় hr.V
ঢ় (B hr.


@@ -399,4 +367,14 @@



.group
// obsolete letters
ঋ r-
ৠ r-
ঌ l-
ৡ l-
ৃ r-
ৄ r-
ৢ l-
ৣ l-


+ 20
- 8
dictsource/en_list View File

@@ -150,12 +150,14 @@ _¨ daIa#r'i:sIs
_ª fEmI2nIn'O@dI2n@L
_« lEft'gIl@mEt
_­ makr0n
² tu:
³ Tri:
_¹ su:p@skrIptw'0n
_² su:p@skrIptt'u:
_³ su:p@skrIptT'ri:
_´ a#kju:taksEnt
_· mId@Ld0t
_¸ sEd'Il@
_¹ su:p@skrIptw'0n
//_º maskjUlIn'O@dI2n@L
_º dI2gr'i:z
_» raIt'gIl@mEt
@@ -943,7 +945,7 @@ blancmange bl@m0nZ
blase blA:z'eI
blasé blA:z'eI
bleh blEh
blockade $2
blockade bl0k'eId
blouse blaUz
bluest blu:@st
blurry bl3:rI
@@ -1279,6 +1281,7 @@ dais deIIs
dandelion dandI2laI@n
ddu DI $only // Welsh
de d@ $only
(de jure) deIdZ'U@ri
debacle deIb'A:k@L
debrief di:br'i:f
debris dEbri:
@@ -1429,6 +1432,8 @@ ember Emb3
emphasis Emf@sIs $only
empire $1
emu i:mju:
(en masse) 0n||m'as
(en route) 0n||r'u:t
enroute 0nr'u:t
ensemble 0ns'0mb@L
entendre 0nt'0ndr@-
@@ -1674,6 +1679,7 @@ hello h@loU
henceforth hEnsfo@T
?3 herb 3:b
hercules h3:kjUli:z
?3 hereford h3:f3d
heretical hI2rEtI2k@L
hereto hi@3'tu:
heretofore hi@3t2Ufo@
@@ -1697,6 +1703,7 @@ holme hoUm
holster hoUlst3
homeowner hoUmoUn3
homepage hoUmpeIdZ
homily h0m@li
hominem h0mInEm
?3 hominem h0m@n@m
hooah h'u:'A:
@@ -1802,6 +1809,8 @@ interven Int3v'i:n // for intervening
intray IntreI
intro $1
?3 investigative Inv,EstI2g'eItIv
ipad aIpad
iphone aIfoUn
irate aIr'eIt
iris aIrIs
iron aI3n
@@ -2822,6 +2831,7 @@ tonne tVn
torment $1
torment $2 $verb
tornado tO@n'eIdoU
torrential t@rEnS@L
tortilla tO@t'i:a#
touche tu:SeI $only
toupee tu:peI
@@ -2835,6 +2845,7 @@ trajectory tr@dZEkt@rI
traverse $alt3
travesty trav@sti
treatise tri:tIz
trebuchet trEbUSeI
tremendous $alt3
triage tri:A:Z
tribunal traIb'ju:n@L
@@ -3337,6 +3348,7 @@ Tokyo toUkIoU
Topeka toUp'i:k@
Toronto t@r0ntoU
Toulouse tu:l'u:z
Trafalgar $alt3
?3 Tunisia tu:n'i:Z@
Tripoli trIp@li
tuareg twA@rEg
@@ -3500,6 +3512,7 @@ Evette I2vEt
Fainne fan;@
Freda fri:d@
Fírinne fi:rIn;@
Gareth gar@T
Gary gari
Geraint gEraInt
Gerhard ge@hA@t
@@ -3672,6 +3685,7 @@ Susanne $2
Suzy su:zi
Tatiana tatI'A:n@
?3 Tatiana tA:tj'A:n@
Terese t@reIz
Theresa t@ri:z@
Therese t@ri:z
Thomas t0m@s
@@ -3762,9 +3776,7 @@ zhivago ZI2vA:goU



(de jure) deIdZ'U@ri
(en masse) ,0n||m'as
(en route) ,0n||r'u:t

(each of) i:tS||@v $pause
(far more) f'A@_m,o@
(few more) f'ju:m,o@
@@ -3775,9 +3787,9 @@ zhivago ZI2vA:goU
(most of) moUst||@v
(such as) sVtS||_a#z $pause

(too few) t'u:||f,ju:
(too many) t'u:||m,Eni
(too much) t'u:||m,VtS
(too few) t'u:||fju:
(too many) t'u:||mEni
(too much) t'u:||mVtS

//*************************************************************************
// COMMON WORDS

+ 1
- 0
dictsource/en_rules View File

@@ -4315,6 +4315,7 @@
d) or (_ o@
_f) or (@ O@
_f) ore (A O@
_f) ore (kn O@,
f) or (k O@
_f) or (s@ %O@
ch) or (d O@

+ 784
- 0
dictsource/ms_list View File

@@ -0,0 +1,784 @@
// Last updated: 14 October 2010, Jason Ong ([email protected])
// This file is UTF8 encoded
// Spelling-to-phoneme words for Malay

a e:
b bi:
c si:
d di:
e i:
f Ef
g dZi:
h etS
i aI
j dZe
k ke
l El
m Em
n En
o o:
p pi:
q kju:
r ar
s Es
t ti:
u ju:
v vi:
w d'ab@liu:
x Eks
y waI
z zEd


// numeric
_0 k'osoN
_1 s'atu
_2 d'u@
_3 t'ig@
_4 '@mpat
_5 l'im@
_6 '@nam
_7 t'udZ%oh
_8 l'apan
_9 s@mb'ilan
_10 s@p'uluh
_11 s'@b@las
_12 d'u@b@las
_13 t'ig@b@las
_14 '@mpatb@las
_15 l'im@b@las
_16 '@namb@las
_17 t'udZ%ohb@las
_18 l'apanb@las
_19 s@mb'ilanb@las
_2X d'u@puloh
_3X t'ig@puloh
_4X 'Empatpuloh
_5X l'im@puloh
_6X 'Enampuloh
_7X t'udZ%ohpuloh
_8X l'apanpuloh
_9X s@mb'ilanpuloh
_0C R'atus_|
_1C s@*'atus_|
_0M1 R'ibu_
_1M1 s@r'ibu_
_0M2 dZ'ut@_
_1M2 s@dZ'ut@_
_0M3 b'ili@n
_1M3 s@b'ili@n
_dpt _p'@rpul'uhan_


_cap b'EsaR // after the letter
_?? k,odeh'uR2uf

// accented letters
_lig d'aIgRaf
_acu akj'ut
_ac2 dub@lakj'ut
_brv bR2'i:v
_ced s@d'ila
_cir t'opi
_dia 'umlaUt
_dot d'Ot
_grv gR2'av
_hac h'atSEk
_mcn m'akR2On
_ogo 'OgonEk
_rng R2'iNg
_stk stR'ok
_tld t'ild@

// punctuation
_! t,anda||s'ER2u
_" t,andak'utip
£ ponst'E*RliN
% p@*Ratus
^ t,andat'opi
& d'an
_* b'intaN
_( k,uR2uN||b'uk@
_) k,uR2uN||t'utup
__ g,aR2is||b'awah
_- t,andah'ubuN
+ c'ampor
= s,am@||d'@Nan
_{ k,uR2uN||kuR2'awal
_} k,uR2uN||kuR2,awal||t'utup
_[ k,uR2uN||s'iku
_] k,uR2uN||s,iku||t'utup
_: t,iti?||d'u@
_; t,iti?||k'om@
@ a||k'EOng
_' k,utip||t'uNgal
~ t'ilde
# p'agaR
_< k,uR2aN||d'aR2i
_> l,Ebih||d'aR2i
_, k'om@
_. t'iti?
_? t,and@||t'an^@
/ stR2'ok
_\ 'bEkslES





// exceptions
// (use phoneme [E2] for an unstressed 'e' which does not reduce to [@] )

bebek bEbE2?
becek bEtSE2?
//bekas $2
perang $2


// ABBREVIATIONS
//**************
abd 'abdul $dot
agenda ag'enda
bhd b'@Rhad $dot
cimb $abbrev
cm s@ntim'et@r
com d'Ot||kOm
(co ltd) k'amp@ni||lim'it@d
dr d'okt@R $dot
drp daR2ip'ad@
dun d'un
dymm d'uli||jang||mah'a||m'uli@
exco 'Eksko
en 'intSek $dot
felda f'elda
hb h,arib'ulan
hj h'adZi $dot
ir $abbrev $dot
klci $abbrev
km kilom'et@r
kol kol'on@l $dot
ltd lim'it@d $dot
m'sia malaysia $text
md moh'amad $dot
mm milim'et@r
mohd moh'amad $dot
mr m'ist@r $dot
mw m'egawat
pas p'a:s
pibg $abbrev
prof prof'es@r $dot
pte p'raiv@t
rm R'iNget
sdn s@ndiR2'ian $dot
sdr saUd'aR@ $dot
umno 'amno:
upm $abbrev
utk unto?
yab jang||amat||b@rh'ormat
yb jang||b@rh'ormat
ym jang|m'uli@
yg jang


// MAIN WORD DICTIONARY
//*********************

// e(pepet)-a
banteras bant'@Ras
membanteras m@mbant'@Ras
bedah b'@dah
bekas b'@kas
belah b'@lah
perbelanjaan p@Rb,@landZ'a|an
sebelah s@b'@lah
benar b'@nar
sebenar s@b'@nar
benda b'@nd@
kecelaruan k@tS,@laR'uan
berhad b'@Rhad
besar b'@sar
membesar m@mb'@sar
pembesar p@mb'@sar
sebesar s@b'@sar
terbesar t@Rb'@sar
cegah tS'@gah
mencegah m@ntS'@gah
pencegah p@ntS'@gah
cepat tS'@pat
dipercepat dip@RtS'@pat
secepat s@tS'@pat
dekat d'@kat
terdekat t@Rd'@kat
demam d'@mam
denda d'@nd@
didenda did'@nd@
dengan d'@Nan
dengar d'@Nar
didengar did'@Nar
mendengar m@nd'@Nar
depan d'@pan
berdepan b@Rd'@pan
dera d'@R@
pendera p@nd'@R@
deras d'@Ras
desak d'@sak
mendesak m@nd'@sak
terdesak t@Rd'@sak
empat '@mpat
engkau '@NkaU
gelar g'@lar
bergelar b@Rg'@lar
gemar g'@mar
penggemar p@Ng'@mar
gesa g'@s@
menggesa m@Ng'@s@
tergesa t@Rg'@s@
hendak h'@nda?
dikehendaki dik,@h@nd'aki
kehendak k@h'@nda?
kelas k'@las
sekelas s@k'@las
kemas k'@mas
keras k'@Ras
berkeras b@Rk'@Ras
kertas k'@Rtas
kesan k'@san
dikesan dik'@san
lembah l'@mbah
letak l'@tak
diletak dil'@tak
emak '@mak
emas '@mas
enam '@nam
keenam k@'@nam
enggan '@Ngan
gerak g'@ra?
bergerak b@Rg'@ra?
penggerak p@Ng'@ra?
jebak dZ'@bak
terjebak t@RdZ'@bak
jejas dZ'@dZas
terjejas t@RdZ'@dZas
jelas dZ'@las
kejar k'@dZar
dikejar dik'@dZar
kekal k'@kal
kelam k'@lam
mengembalikan m@N,@mbal'ikan
kembang k'@mbaN
mengembang m@N'@mbaN
perkembangannya p@Rk,@mbaN'ann^@
kelak k'@lak
kena k'@n@
kenal k'@nal
dikenal dik'@nal
terkenal t@Rk'@nal
kerap k@Rap
kerja k'@RdZ@
bekerja b@k'@RdZ@
bekerjasama b@k,@RdZ@s'am@
kerjasama k@RdZ@s'am@
pekerja p@k'@RdZ@
sekerja s@k'@RdZ@
kesal k'@sal
menyesal m@n^'@sal
kesan k'@san
berkesan b@Rk'@san
keberkesanan k@b,@Rk@s'anan
kesat k'@sat
mengesat m@N'@sat
lekas l'@kas
lelakinya l@lak'in^@
lekat l'@kat
melekat m@l'@kat
lemah l'@mah
lembaga l@mb'aga
berperlembagaan b@Rp@Rl,@mbag'a|an
lengan l'@Nan
lepas l'@pas
berlepas b@Rl'@pas
terlepas t@Rl'@pas
letak l'@ta?
peletakan p@l@t'akan
terletak t@Rl'@tak
menang m'@naN
pemenang p@m'@naN
mentah m'@ntah
mesra m'@sR@
pecah p'@tSah
berpecah b@Rp'@tSah
peka p'@k@
pegang p'@gaN
dipegang dip'@gaN
memegang m@m'@gaN
pentas p'@ntas
pernah p'@rnah
pesat p'@sat
petang p'@taN
rendah R'@ndah
terendah t@R'@ndah
rentak R'@ntak
berentak b@R'@ntak
retak r'@tak
keretakan k@R@t'akan
rentak r'@ntak
serentak s@r'@ntak
sebak s'@ba?
kesebakan k@s@b'akan
sebentar s@b'@ntar
sedang s'@daN
sedar s'@dar
tersedar t@Rs'@dar
segera s@g'@R@
disegerakan dis@g@R'@kan
menyegerakan m@n^,@g@R'@kan
sejahtera s@dZaht'@R@
kesejahteraan k@s@dZ,aht@R'@an
sejak s'@dZak
sekat s'@kat
menyekat m@n^'@kat
selam s'@lam
penyelam p@n^'@lam
keselamatan k@s,@lam'atan
selaras s@l'aRas
keselarasan k@s@laR'asan
selepas s@l'@pas
kesesuaian k@s@su'aIan
sembah s'@mbah
persembahannya p@Rs,@mbah'ann^@
sempat s'@mpat
berkesempatan b@Rk,@s@mp'atan
sempena s@mp'@n@
beserta b@s'@Rt@
peserta p@s'@Rt@
sertai s@Rt'a|i
serang s'@RaN
diserang dis'@RaN
menyerang m@n^'@raN
penyerang p@n^'@raN
serba s'@Rb@
tegang t'@gaN
bertegang b'@Rt@gaN
tegas t'@gas
tekak t'@kak
menekak m@n'@kak
tekan t'@kan
menekan m@n'@kan
telah t'@lah
teman t'@man
tempa t'@mp@
ditempa dit'@mp@
menempa m@n'@mp@
tempah t'@mpah
menempah m@n'@mpah
tempat t'@mpat
bertempat b@rt'@mpat
tenang t'@naN
bertenang b@Rt'@naN
tengah t'@Nah
menengah m@n'@Nah
sesetengah s@s@t'@Nah
tengkar t'@Nkar
bertengkar b@Rt'@Nkar
tentang t'@ntaN
ditentang dit'@ntaN
menentang m@n'@ntaN
penentang p@n'@ntaN
tepat t'@pat
juruterbang dZuRut'@RbaN
teram t'@Ram
ketenteraman k@t@nt@R'aman
terkam t'@Rkam
diterkam dit'@Rkam
menerkam m@n'@Rkam
tetap t'@tap
bertetap b@Rt'@tap
menetap m@n'@tap

// exceptions
kehebatan k@heb'atan
dibelenggu dib@l'@Ngu
perbendaharaan p@Rb@nd,@haR'a|an
kejayaan k,@dZaj'a|an
galakan gal'akan
setong s@t'oN
aneh 'anE2h
menyelamatkan m@n^,@lam'atkan
//berbaur b@Rb'aUr
gementar g@m'@ntar
hebatnya hEb'atn^@
diedarkan diEd'aRkan
//berkeliaran b@Rk@li'aRan
//bersebelahan b@Rs@b@l'ahan
//sebaik s@b'aIk
cedera tS@d'@R@
kecederaan k@tS,@d@r'a|an
tercedera t@RtS@d'@R@
//ekoran Ek'oRan
kekecewaan k@k,@tSew'a|an
//bermain b@Rm'aIn
//kedai k'@daI
//pekedai p@k'@daI
disertai dis@Rt'ai
persediaan p@Rs,@di'a|an
//bergaul b@Rg'aul
elakkan El'akkan
kebanyakan k@ban^'akan
anda 'anda
//berkepentingan b@Rk,@p@nt'iNan
//berleluasa b@Rl@lu'as@
iaitu ja|'itu
masalah mas'alah
masakan mas'akan
mengelakkan m@NE2l'akkan
menyelesaikan m@n^,@l@s'aIkan
pergolakan p@Rgol'akan
perempuan p@R@mp'uan
perempuannya p@R,@mpu'ann^@
pesta p'esta
berpesta b@Rp'esta
menyalah m@n^'alah
setengah s@t'@Nah
berpengalaman b@Rp@Nal'aman
kesemuanya k@s,@mu'@nn^@
selesema s@l@s'@m@
tindakan tind'akan
pesalah p@s'alah
wanita wan'ita
bersalah b@Rs'alah
//persetujuan p@Rs,@tudZ'uan
//persetujuannya p@Rs@tudZu'ann^@
//keseluruhan k@s,@luR'ohan
memberitahu m@mb,@Rit'ahu
//persekutuan p@Rs,@kut'uan
tema t'Ema
kepercayaan k@p,@RtSaj'a|an
dendangan dEnd'aNan
peperiksaan p@p,@Reks'a|an
kebebasan k@bEb'asan
//cerai tS'@RaI
//berbaik b@Rb'aIk
menyembunyikan m@n^,@mbun^'ikan
bermesyuarat b@Rm,@Su'aRat
//pengetahuan p@N,@tah'uan
mengenai m@N@n'ai
penyelesaian p@n^,@l@s'aIan
diselesaikan dis,@l@s'aIkan
ditanya dit'an^@
prestasi pREst'asi
pembelajaran p@mb,@ladZ'aRan
kepong k'@poN
demikian d@mik'ian
piket p'ikEt
kempennya kEmp'enn^@
jentera dZ@nt'@R@
perlembagaan p@Rl,@mbag'a|an
bersesuaian b@Rs,@su'aIan
bumiputera bumip'ut?Ra
kecemerlangan k@tS,@Rm@l'aNan
merdeka m@Rd'eka
kemerdekaan k@m,@Rdek'a|an
kelewatan k@lew'atan
menyelesaikannya m@n^@l@saIk'ann^@


// english derived words
akta 'akta
album 'Elb@m
aspek 'aspE2k
balada bal'ada
digit di'dZit
digital didZ'it@l
doktor d'okt@r
dolar d'Ol@r
domestik dOm'Estik
entiti Ent'iti
flora fl'ora
frekuensi fRiku'@nsi
imej 'imedZ
indeks 'indEks
insentif ins'E2ntif
jean dZ'in
jeneral dZEn'@R@l
kabinet kEb'in@t
kamera kEm'@R@
kes k'es
komponen komp'on@n
komprehensif kompRih'ensif
koroner koR'on@r
laser l'es@r
majoriti mEdZor'iti
meter m'it@r
muzik m'iuzek
muzium m'iuzi@m
nasional nESh'@n@l
negatif nEg'@tif
nostalgia nost'aldZja
november nov'Emb@r
oktober okt'ob@r
polis p'olis
personaliti p@Rs,@nal'iti
presiden pRE2s'id@n
profesor pRof'E2s@r
produk pR'odak
prospek pR'ospE2k
republik Rip'abli?
saintis s'aIntis
sesi s'esi
subjek s'abdZE2k
surcaj s'@RtSadZ
radio R'edio
realiti Rial'iti
sentimen sEnt'im@n
september sEpt'@mb@r
teater ti'et@r
teknik t'Eknik
teknikal tEkn'ikal
telefon tel'ifon
tenis t'Enis
tiara ti'aRa
unit j'unit
universiti jun,iv@Rs'iti
virus v'aIR@s
zoo zu:

// place names
Australia _^_EN
Arsenal _^_EN
Asia as'ia
Barcelona b'aRs@l'ona
Borneo _^_EN
Britain _^_EN
Brunei b'R2unaI
Cheras tS'@ras
Coast _^_EN
Commonwealth _^_EN
Denmark _^_EN
England _^_EN
Eropah Er'opah
France _^_EN
George _^_EN
Georgetown _^_EN
Indonesia indon'eIsi@
Ireland _^_EN
Jamaica _^_EN
Kingdom _^_EN
Korea _^_EN
Liverpool _^_EN
London _^_EN
New _^_EN
Nigeria _^_EN
Macau _^_EN
Malaysia m@l'esi@
Melbourne _^_EN
Guinea _^_EN
Penang pin'EN
Perak p'erak
Phuket ph'ukEt
Putrajaya putR2@dZ'aj@
Republic _^_EN
Scotland _^_EN
Seputeh s@p'uteh
Seremban s@R'@mban
Setar s?tar
Sydney _^_EN
Temerloh t@m'@Rloh
Tonga t'onga
Town _^_EN
United _^_EN
Valencia vel'@nsia
Zambia z'ambia
Zealand _^_EN

// person names
Azura az'uR2a
Barack _^_EN
David _^_EN
Davidson _^_EN
Douglas _^_EN
Edward _^_EN
Karen _^_EN
Jason _^_EN
Lee _^_EN
Leela l'ila
Linda l'inda
Mahathir mah'ater
Michael _^_EN
Merican m'erikan
Ng '@N
Nora n'oRa
Nurhaliza n,uRhal'iza
Obama ob'ama
Ong ON
Ramlee R'amli
Saleh s'aleh
Seha s'eha
Shafie Saf'i?i
Sidek s'idek
Syed s'aId
Teresa t@R2'isa
Tony _^_EN
Yaacob j'a?kob
Yew jiu
Zakaria zak'aRja
Zaleha zal'eha


// English words
(& co) En||k'amp@ni
american _^_EN
bank b'Enk
banking b'EnkiN
commerce _^_EN
corp _^_EN $dot
city _^_EN
company _^_EN
consortium _^_EN
daily _^_EN
distribution _^_EN
east _^_EN
education _^_EN
engineering _^_EN
euro _^_EN
girl _^_EN
grand gR2End
genre _^_EN
government _^_EN
group _^_EN
hero h'iR2o
idea 'aIdi@
island _^_EN
jazz dZ'E:s
international _^_EN
internet _^_EN
left _^_EN
land lEnd
malayan _^_EN
malaysian m@l'esi@n
media _^_EN
methodist _^_EN
multi _^_EN
north _^_EN
pound _^_EN
right _^_EN
school _^_EN
speaker _^_EN
south _^_EN
the _^_EN
enterprise _^_EN
omnibus 'omnibas
online _^_EN
power _^_EN
punk _^_EN
serius _^_EN
service _^_EN
street _^_EN
technologies _^_EN
tender _^_EN
trading _^_EN
trend _^_EN
unity _^_EN
union _^_EN
wall _^_EN
west _^_EN


// brands
afp $abbrev
(air asia) 'E:_'e:si@_
(air france) _^_EN
airbus _^_EN
boeing _^_EN
eon 'ion
firefly _^_EN
iphone aI||fon
ipod aI||pod
malaysiakini m@l'esi@||k'ini
maybank m'eib'Enk
reuters _^_EN
(sime darby) _^_EN
toyota toj'ota
wikipedia wik,ip'idja



// unstressed words
//suatu $u
dari $u
pada $u
daripada $u
ke k@ $u
di $u
si $u
sang $u
hang $u
yang $u
//dan $u
//atau $u
//untuk $u
ialah $u
adalah $u
sebagai $u
bahwa $u
per p@r $u


// conjunctions
agar $pause
apabila ap@bil@ $pause
apatah ap@t'ah $pause
atau $pause
ataupun $pause
bagi $pause
bahkan $pause
(bukan sahaja) $pause
dan $pause $u
(di mana) $pause
hanya $pause
jika $pause
kalau $pause
kerana $pause
ketika $pause
mahupun $pause
maka $pause
malah $pause
malahan $pause
manakala $pause
meskipun $pause
misalnya $pause
namun $pause
(sama ada) $pause
sambil $pause
sebab s'@bab $pause
sedangkan $pause
sehingga $pause
selain s@l'ain $pause
semasa $pause
serta s'@rt@ $pause
setelah s@t'@lah $pause
seperti $pause
sepertimana s@p,@Rtim'an@ $pause
supaya $pause
tapi $pause
tetapi $pause
walau $pause
walaupun $pause
untuk $pause
//yang $pause $u
(yang mana) $pause


// nuances
anugerah an'ug*Rah
dilaksanakan dil,aksan'@kan
kementerian k@m,@ntR2'ian
sebahagian s@b'ah?gian
mewarnai m@warn'a|i
mulai mul'a|i
meraikan m@Ra|'ikan
sibuk s'ebok
terengganu tR2@Ng'anu
dirasai diRas'a|i
direka diR'ek@
negeri n'@gR2i

+ 233
- 0
dictsource/ms_rules View File

@@ -0,0 +1,233 @@
// Last updated: 14 October 2010, Jason Ong ([email protected])
// This file is UTF8 encoded
// Spelling-to-phoneme rules for Malay

.group a
a a
a) a _|a
A_) a _|a
au) a _|a
ai aI
au aU
_) au o // (automatik)

@) a (_ @ // (pula)
@) a (kah_ '@ // (apakah)
@) a (kan_ '@ // (bukakan)
@) a (lah_ '@ // (mintalah)
@) a (nya_ '@ // (puncanya)
@) a (pun_ '@ // (bagaimanapun)


.group b
b b

_) be (@@ b@

_) ber (@@ b@R // (berdasarkan)
_) ber (CaiX b@R // (bermain)
_) ber (CauX b@R // (bergaul, berbaur)
_) berke (@@ b@Rk@ // (berkeliaran, berkesempatan)
_) berle (@@ b@Rl@ // (berleluasa)
_) berper (@@ b@Rp@R //
_) berse (@@ b@Rs@ // (bersebelahan)
_) bh b // added (kota bharu)

.group c
c tS
//*************
ch tS // (kuching)
//**************

.group d
d d
dj dZ // Dutch

.group e
e E //jason: E changed to E2
e) e _|E
A_) e _|E // *** to check on this ***
e (_ e


// *********************
_) e (Co@ E2 // e-o (ekoran)
e (CaiX '@ // e-ai (kedai, petai, belai, cerai)
e (CiX '@ // e-i (betik, ketil, lebih, kerisik, kesedihan, sering, seri, segi, seni)
e (CCiX '@ // e-i (penting, jentik)
e (CCuX '@ // e-u (dibendung, bentuk)
e (CuX '@ // e-u (belut, telur, perut, ketulan, bertemu)
e (CCuX '@ // e-u (perlu, merdu)
e (CCCuX '@ // e-u (tengku, tengkuk)

e (nyuX '@ // e-u (senyum)
eCC) e (X e // e-e (pendek, benteng)
eC) e (X e // e-e (belek, gelek, leceh, geleng)
e (Ce e // e-e (kelecehan)
oC) e (X e // o-e (oleh, boleh, celoteh, topeng)
oCC) e (X e // o-e (ponteng)
C) e (CCCoCkan_ e // (bengkokkan)
m) e (_ @ // (autisme)

// ******************
.group f
f f
ff f

.group g
g g

.group h
h h

.group i
i i
i) i _|i
A_) i _|i

@) i (CX e // (tekik, masing, masin)
@) i (Cnya_ 'e // (masinnya)
@) i (CCaan_ e // (pemeriksaan)

.group j
j dZ

.group k
k k
k (_ ?
kh x

_) ke (@@ k@
@@) k (annya_ k'
_) kese (@@ k@s@ // keseluruhannya

.group l
l l
ll l

.group m
m m

_) me (@@ m@
_) mempe (@ m@mp@
//*****************
_) mem (@@ m@m
_) mene (@@ m@n@ // (menerajui)
_) menge (@@ m@N@ // (mengenepikan)
_) mempenge (@@ m@mp@N@ // (mempengerusikan)
//****************

.group n
n n
ng N
ny n^
// nj n^

.group o
o o
o) o _|o
A_) o _|o
o (r O
oe u // Dutch spelling

.group p
p p
pp p

_) pe (@@ p@

_) pe (CaiX p@ // (pemain, pesaing)
_) peme (@@ p@m@ // (pemeriksaan)
_) pene (@@ p@n@ // (penerokaan)
_) penge (@@ p@N@ // (pengetahuan)
_) penje (@@ p@ndZ@ // (penjenamaan)
_) perse (@@ p@Rs@ // (persetujuan)


.group q
q k
qu kw

.group r
r R //(jason change: R2 to r)
r (K r //(jason change: R to r)
e) r (K *r //(jason change: *R to r)

r (_ r // jason: added (silent r at the end)

.group s
s s
ss s
sy S // perhaps [S;] ??
sj S

_) se (@@ s@
//*************
_) se (CaiX s@ // (sebaik)
sh S
//***************


.group t
t t
tj tS // Dutch

_) ter (@@ t@*R

//***************
_) ter (@ t'@*R // ter- (terbaik, teruk)
//******************

.group u
u u
u) u _|u
A_) u _|u
@) u (CX o // (puluh, tudung)
@) u (Cnya_ 'o // (bentuknya)
@) u (CCnya_ 'o // (tudungnya)

.group v
v v

.group w
w w

.group x
x ks
_) x z

.group y
y j

.group z
z z

.group
$ dOl@R


__) - (_D n'eg@tif

* b'intaN
*) * (*
**
**) * (_ _::

+ 246
- 246
dictsource/pa_list View File

@@ -1,246 +1,246 @@
// This file is UTF8 encoded
// Punjabi/Gurmukhi
// Numbers
_0 z'iRo
_1 'Ik:
_2 d'o
_3 t'I~n
_4 c'aR
_5 p'VnJ
_6 c#'e
_7 s'Vt:
_8 'Vt.#:
_9 n'O~
_10 d'Vs
_11 gI'aRa~
_12 b'aRa~
_13 t'eRa~
_14 c'Oda~
_15 p'Vnd@Ra~
_16 s'ol.a~
_17 s@t'aRa~
_18 Vt.#'aRa~
_19 'Unni
_20 v'iH
_21 Ik:i
_22 b'ai
_23 t'ei
_24 c'Ovi
_25 p'Vc:i
_26 c#'Vb:i
_27 s@t'ai
_28 Vt.#'ai
_29 Un'Vt:i
_30 t'iH
_31 Ik'Vt:i
_32 b'Vt:i
_33 t'et:i
_34 c'ONti
_35 p'ENti
_36 c#'Vt:i
_37 s'ENti
_38 Vt.#'Vt:i
_39 U~Nt'ali
_40 c'ali
_41 Ik@t'ali
_42 be'ali
_43 t@R@t'ali
_44 cUt'ali
_45 p@nt'ali
_46 c#I'ali
_47 s@nt'ali
_48 ,@R2@t'ali
_49 Un'VnJa
_50 p@nJ'aH
_51 ,@k@v'VnJa
_52 b@v'VnJa
_53 t,@R@v'VnJa
_54 cUR'VnJa
_55 p,@c@v'VnJa
_56 c#@p'VnJa
_57 s,@t@v'VnJa
_58 ,@t.#@v'VnJa
_59 Un.'at.#
_60 s'Vt.#:
_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 c#e'aH@t.
_67 s@t'aH@t.
_68 ,@t.#'aH@t.
_69 Un.'Vt:@R
_70 s'Vt:@R
_71 Ik'Vt:@R
_72 b@H'Vt:@R
_73 t@H'et:@R
_74 cOH'Vt:@R
_75 p@J'Vt:@R
_76 c#IH'Vt:@R
_77 s@t'Vt:@R
_78 Vt.#'Vt:@R
_79 Un.'asi
_80 'Vssi
_81 ,IkI;'asi
_82 bI;'asi
_83 t,@RI;'asi
_84 cUR'asi
_85 p@c'asi
_86 c#I;'asi
_87 s@t'asi
_88 Vt.#'asi
_89 Un'an@v,e~
_90 n'Vb:e
_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 c#I'an@ve~
_97 s@t'an@ve~
_98 Vt.#'an@ve~
_99 n@R2'I~n@v,e~
_0C s'O
_0M1 H@J'aR
_0M2 l'Vk#: // 100,000
_0M3 k'VRoR // 10,000,000
_0M4 'VR@b // 1,000,000,000
_0M5 k#'VR@b // 100,000,000,000
_dpt _d@s@ml'o:
// character names
ਂ bInd'i
ੰ tIpp'i
ੱ VddVk
ਃ visaRg
੍ hVlVnt
ਅ 'ERV
ੲ 'IRI
ੳ 'URV
_ਆ 'ERV||kVnn'a
_ਇ 'IRI||sIh'aRi
_ਈ 'IRI||bIh'aRi
_ਉ 'URV||'OnkaR
_ਊ 'URV||dUl'EnkaR
_ਏ 'IRI||l'avam
_ਐ 'ERV||dUl'avam
_ਓ 'URV||hoR'a
_ਔ 'ERV||kVnOR'a
ਾ kVnn'a
ਿ sIh'aRi
ੀ bIh'aRi
ੁ OnkaR
ੂ dUl'EnkaR
ੇ l'ava~
ੈ d@l'ava~
ੋ hoR'a
ੌ kVn'ORa
// Punctuation
_?? 'Vk#:@R
। d.'Vnd.i
+ J'Vuma
= b@R'ab@R
% pR'VtIS@t
* t'aRa
// Pronouns
// ਪੁਰਖਵਾਚੀ ਪੜਨਾਂਵ
ਮੈਂ $u // main: I
ਮੈਨੂੰ $u
ਮੇਰਾ $u
ਮੇਰੀ $u
ਮੇਰੇ $u
ਅਸੀਂ $u // we
ਸਾਨੂੰ $u
ਸਾਡਾ $u
ਸਾਡੀ $u
ਸਾਡੇ $u
ਆਪ $u // you(formal)
ਆਪਨੂੰ $u
ਆਪਦਾ $u
ਆਪਦੀ $u
ਆਪਦੇ $u
ਤੂੰ $u // you (informal)
ਤੂਸੀਂ $u // you(formal)
ਤੁਹਾਨੂੰ $u
ਤੁਹਾਡਾ $u
ਤੁਹਾਡੀ $u
ਤੁਹਾਡੇ $u
ਤੂੰ $u // you (informal)
ਤੈਨੂੰ $u
ਤੇਰਾ $u
ਇਹ $u // he/she/it
ਇਸਤੋਂ $u
ਇਸਦਾ $u
ਇਹ $u // they
ਇਨ੍ਹਾਂਨੂੰ $u
ਇਨ੍ਹਾਂਦਾ $u
ਉਹ $u // he/she/it
ਉਸਤੋਂ $u
ਉਸਦਾ $u
ਉਸਦੀ $u
ਉਸਦੇ $u
ਉਹ $u // they
ਉਨ੍ਹਾਂਨੂੰ $u // unhannu: them
ਉਨ੍ਹਾਂਦਾ $u
ਉਨ੍ਹਾਂਦੀ $u
ਉਨ੍ਹਾਂਦੇ $u
// Prepositions/Postpositions
ਦਾ $u // dā: of, possessive particle
ਦੀ $u // dī
ਦੇ $u // de
ਨੂੰ $u // nu: to
ਤੱਕ $u // tak: until, for(time)
ਬਿਨਾ $u $pause // without (preposition)
ਵਿਚ $u // in
ਵਿੱਚ $u // in
ਤੋਂ $u // ton: from, with, by
// Verbs
ਹਾਂ $u // to be
ਹੋ $u
ਹੈ $u
ਹੈਂ $u
ਹਨ $u
ਸੀ $u // si: past aux
ਸਨ $u // san: past aux
ਰਹਾ $u // rahā: continuous
ਰਹੇ $u // rahe
ਰਹੀ $u // rahī
$textmode
ਸੋਫਟਵਿਅਰ software
ਈਮੇਲ email
ਕੀਬੋਰਡ keyboard
ਬੋਰਡ board
$phonememode
// This file is UTF8 encoded
// Punjabi/Gurmukhi
// Numbers
_0 z'iRo
_1 'Ik:
_2 d'o
_3 t'I~n
_4 c'aR
_5 p'VnJ
_6 c#'e
_7 s'Vt:
_8 'Vt.#:
_9 n'O~
_10 d'Vs
_11 gI'aRa~
_12 b'aRa~
_13 t'eRa~
_14 c'Oda~
_15 p'Vnd@Ra~
_16 s'ol.a~
_17 s@t'aRa~
_18 Vt.#'aRa~
_19 'Unni
_20 v'iH
_21 Ik:i
_22 b'ai
_23 t'ei
_24 c'Ovi
_25 p'Vc:i
_26 c#'Vb:i
_27 s@t'ai
_28 Vt.#'ai
_29 Un'Vt:i
_30 t'iH
_31 Ik'Vt:i
_32 b'Vt:i
_33 t'et:i
_34 c'ONti
_35 p'ENti
_36 c#'Vt:i
_37 s'ENti
_38 Vt.#'Vt:i
_39 U~Nt'ali
_40 c'ali
_41 Ik@t'ali
_42 be'ali
_43 t@R@t'ali
_44 cUt'ali
_45 p@nt'ali
_46 c#I'ali
_47 s@nt'ali
_48 ,@R2@t'ali
_49 Un'VnJa
_50 p@nJ'aH
_51 ,@k@v'VnJa
_52 b@v'VnJa
_53 t,@R@v'VnJa
_54 cUR'VnJa
_55 p,@c@v'VnJa
_56 c#@p'VnJa
_57 s,@t@v'VnJa
_58 ,@t.#@v'VnJa
_59 Un.'at.#
_60 s'Vt.#:
_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 c#e'aH@t.
_67 s@t'aH@t.
_68 ,@t.#'aH@t.
_69 Un.'Vt:@R
_70 s'Vt:@R
_71 Ik'Vt:@R
_72 b@H'Vt:@R
_73 t@H'et:@R
_74 cOH'Vt:@R
_75 p@J'Vt:@R
_76 c#IH'Vt:@R
_77 s@t'Vt:@R
_78 Vt.#'Vt:@R
_79 Un.'asi
_80 'Vssi
_81 ,IkI;'asi
_82 bI;'asi
_83 t,@RI;'asi
_84 cUR'asi
_85 p@c'asi
_86 c#I;'asi
_87 s@t'asi
_88 Vt.#'asi
_89 Un'an@v,e~
_90 n'Vb:e
_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 c#I'an@ve~
_97 s@t'an@ve~
_98 Vt.#'an@ve~
_99 n@R2'I~n@v,e~
_0C s'O
_0M1 H@J'aR
_0M2 l'Vk#: // 100,000
_0M3 k'VRoR // 10,000,000
_0M4 'VR@b // 1,000,000,000
_0M5 k#'VR@b // 100,000,000,000
_dpt _d@s@ml'o:
// character names
ਂ bInd'i
ੰ tIpp'i
ੱ VddVk
ਃ visaRg
੍ hVlVnt
ਅ 'ERV
ੲ 'IRI
ੳ 'URV
_ਆ 'ERV||kVnn'a
_ਇ 'IRI||sIh'aRi
_ਈ 'IRI||bIh'aRi
_ਉ 'URV||'OnkaR
_ਊ 'URV||dUl'EnkaR
_ਏ 'IRI||l'avam
_ਐ 'ERV||dUl'avam
_ਓ 'URV||hoR'a
_ਔ 'ERV||kVnOR'a
ਾ kVnn'a
ਿ sIh'aRi
ੀ bIh'aRi
ੁ OnkaR
ੂ dUl'EnkaR
ੇ l'ava~
ੈ d@l'ava~
ੋ hoR'a
ੌ kVn'ORa
// Punctuation
_?? 'Vk#:@R
। d.'Vnd.i
+ J'Vuma
= b@R'ab@R
% pR'VtIS@t
* t'aRa
// Pronouns
// ਪੁਰਖਵਾਚੀ ਪੜਨਾਂਵ
ਮੈਂ $u // main: I
ਮੈਨੂੰ $u
ਮੇਰਾ $u
ਮੇਰੀ $u
ਮੇਰੇ $u
ਅਸੀਂ $u // we
ਸਾਨੂੰ $u
ਸਾਡਾ $u
ਸਾਡੀ $u
ਸਾਡੇ $u
ਆਪ $u // you(formal)
ਆਪਨੂੰ $u
ਆਪਦਾ $u
ਆਪਦੀ $u
ਆਪਦੇ $u
ਤੂੰ $u // you (informal)
ਤੂਸੀਂ $u // you(formal)
ਤੁਹਾਨੂੰ $u
ਤੁਹਾਡਾ $u
ਤੁਹਾਡੀ $u
ਤੁਹਾਡੇ $u
ਤੂੰ $u // you (informal)
ਤੈਨੂੰ $u
ਤੇਰਾ $u
ਇਹ $u // he/she/it
ਇਸਤੋਂ $u
ਇਸਦਾ $u
ਇਹ $u // they
ਇਨ੍ਹਾਂਨੂੰ $u
ਇਨ੍ਹਾਂਦਾ $u
ਉਹ $u // he/she/it
ਉਸਤੋਂ $u
ਉਸਦਾ $u
ਉਸਦੀ $u
ਉਸਦੇ $u
ਉਹ $u // they
ਉਨ੍ਹਾਂਨੂੰ $u // unhannu: them
ਉਨ੍ਹਾਂਦਾ $u
ਉਨ੍ਹਾਂਦੀ $u
ਉਨ੍ਹਾਂਦੇ $u
// Prepositions/Postpositions
ਦਾ $u // dā: of, possessive particle
ਦੀ $u // dī
ਦੇ $u // de
ਨੂੰ $u // nu: to
ਤੱਕ $u // tak: until, for(time)
ਬਿਨਾ $u $pause // without (preposition)
ਵਿਚ $u // in
ਵਿੱਚ $u // in
ਤੋਂ $u // ton: from, with, by
// Verbs
ਹਾਂ $u // to be
ਹੋ $u
ਹੈ $u
ਹੈਂ $u
ਹਨ $u
ਸੀ $u // si: past aux
ਸਨ $u // san: past aux
ਰਹਾ $u // rahā: continuous
ਰਹੇ $u // rahe
ਰਹੀ $u // rahī
$textmode
ਸੋਫਟਵਿਅਰ software
ਈਮੇਲ email
ਕੀਬੋਰਡ keyboard
ਬੋਰਡ board
$phonememode

+ 29
- 16
dictsource/pt_list View File

@@ -337,7 +337,7 @@ la $u
lo $u
las $u
los $u
//se $u
se $u

?2 este $u+ $nounf 'estSi // this
?2 estes $u+ $nounf 'estSis // these
@@ -637,7 +637,6 @@ acertos $alt2
acordo $alt $verb
acervo $alt2
adepto $alt
adereço $alt2
adore $alt
adorno $alt $verb
albatrozes $alt
@@ -654,8 +653,8 @@ apego $alt2 $noun
apelo $alt $verb
aposto $alt $verb
aperto $alt2 $noun
apoio $alt2 $noun
aprovo $alt
apneia $alt
apoio $alt $verb
arredores $alt
arremesso $alt2 $noun
arroz $alt2
@@ -668,6 +667,8 @@ atrozes $alt
autora $alt2
avesso $alt2
axé aSE
azeda $alt $verb
azedo $alt $verb
baqueta $alt2
beco $alt2
belo $alt
@@ -675,7 +676,6 @@ besta $alt2
bilhete $alt2
boca $alt2
bochecha $alt2
boio $alt
bojo $alt2
boleia $alt
bolero $alt
@@ -683,13 +683,14 @@ bolo $alt2
bolo $alt $verb
borboleta $alt2
bordo $alt
bosque $alt
boto $alt2 $noun
bromelha $alt
cabeça $alt2
cabresto $alt2
cacete $alt2
cachorra $alt2
caderneta $alt2
cadete $alt2
camiseta $alt2
cantora $alt2
capacete $alt2
@@ -704,6 +705,7 @@ cateto $alt2
catorze $alt2
cebola $alt2
cefaleia $alt
centopeia $alt
cerca $alt
cerca $alt2 $noun
cerco $alt $verb
@@ -728,7 +730,7 @@ colher $alt $noun
colheres $alt $noun
colmeia $alt
colore $alt
começo $alt2 $noun
começo $alt $verb
comodo $alt2
concerto $alt2 $noun
concertos $alt2
@@ -758,12 +760,14 @@ desemprego $alt2
desemprego $alt $verb
desespero $alt2 $noun
desfecho $alt2
desmantelo $alt $verb
desprezo $alt2 $noun
desse $alt2
desse $alt $verb
deste $alt2
deste $alt $verb
desterro $alt2
destroem $alt
deveras $alt
dez $alt
diarreia $alt
@@ -779,11 +783,11 @@ elo $alt
emprego $alt2 $noun
empregos $alt2
encosto $alt $verb
endereço $alt2
endereço $alt $verb
enforco $alt
engordo $alt
enredo $alt $verb
enrosco $alt $verb
enterro $alt2 $noun
enumerem $alt
envelope $alt
@@ -809,20 +813,23 @@ espiroqueta $alt2
espoleta $alt2
esposa $alt2
esqueleto $alt2
estilete $alt2
estrela $alt2
estrofe $alt
estorno $alt $verb
estorvo $alt $verb
etiqueta $alt2
europa $alt
europeia $alt
exagero $alt $verb
explore $alt
faceta $alt2
fantoche $alt
farelo $alt
farofa $alt
febre $alt
feitora $alt2
fera $alt
feitora $alt2
ferozes $alt
fezes $alt
?1 fixe fiSy
@@ -867,11 +874,13 @@ ideia $alt
interesse $alt2 $noun
jogo $alt2 $noun
joguete $alt2
lagosta $alt2
lambreta $alt2
lebre $alt
lembrete $alt2
leste $alt2 $verb
lopes $alt
macete $alt2
maior $alt
maleta $alt2
marcelo $alt
@@ -894,6 +903,7 @@ minueto $alt2
miolo $alt2
miolos $alt
moeda $alt
mofo $alt $verb
molho $alt2 $noun
monera $alt
morcego $alt2
@@ -901,10 +911,10 @@ morda $alt2
moreia $alt
mortos $alt
motora $alt2
mulher $alt
mui mwi
muito mw'iNtU // -s is included as a suffix
muita mw'iNt&
mulher $alt
mulheres $alt
mureta $alt2
mutreta $alt2
@@ -917,11 +927,13 @@ obstetra $alt
odisseia $alt
onu $1
olho $alt2 $noun
onomatopeia $alt
opereta $alt2
ordens $alt
osso $alt2
ossos $alt
ostra $alt2
ovelha $alt2
ovos $alt
pachorra $alt2
paexa paeSa
@@ -937,6 +949,7 @@ pastora $alt2
pedra $alt
pela $alt $verb
pelego $alt2
pela $alt $verb
pelo $alt $verb
peso $alt $verb
piloto $alt2 $noun
@@ -948,32 +961,32 @@ plateia $alt
plebeia $alt
polca $alt
porcos $alt
porrete $alt2
porra $alt2
porrete $alt2
porto $alt2
portos $alt
pose $alt2
povos $alt
poxa p'oS&
primavera $alt
provo $alt
prosopopeia $alt
quarteto $alt2
queda $alt
quede $alt2
quinteto $alt2
recomeço $alt2 $noun
raposa $alt2
recomeço $alt $verb
recordo $alt
recorto $alt
rede $alt2
redor $alt
reembolso $alt $verb
reforços $alt
reforço $alt $verb
reforços $alt
refresco $alt $verb
reitora $alt2
relevo $alt2 $noun
remorso $alt
reprovo $alt
retorno $alt $verb
rixa x'iS&
rocha $alt
@@ -984,7 +997,7 @@ rota $alt2
rota $alt $noun
rumores $alt2
saleta $alt2
sarjeta $alt
sarjeta $alt2
seborreia $alt
seca $alt2 $noun
secas $alt2

+ 40
- 46
dictsource/pt_rules View File

@@ -1,3 +1,4 @@
// translation rules Brazilian
// translation rules Brazilian
// translation rules Brazilian
// This file is UTF-8 encoded
@@ -178,8 +179,6 @@
e (co_ E
e (ctA_ E
e (ctAm_ E
e (çA_ E
e (çAm_ E

e (de_ E
e (dem_ E
@@ -447,17 +446,21 @@ proteg) e (L07_ e // des-
respond) e (L07_ e // cor-
qu) e (brL04_ E
_cel) e (brL04_ E
_enr) e (dL01_ E
_arr) e (dL03_ E
_depr) e (dL03_ E
_hosp) e (dL03_ E
_gr) e (gL03_ e
_gal) e (gL03_ e
_n) e (grL03_ e
_estr) ei (L03_ EI
estr) ei (L04_ EI
_inv) e (jL04_ E
tr) e (pL04_ E // es-
_dec) e (pL04_ E
_in) e (ptL03_ E
_p) e (quL02_ E
_s) e (quL02_ E
ad) e (quL04_ E
l) e (que_ E
_imp) e (rL03_ E
_sev) e (rL03_ E
@@ -473,6 +476,7 @@ respond) e (L07_ e // cor-
_tol) e (rL04_ E
_ven) e (rL04_ E
acel) e (rL04_ E // des-
_apod) e (rL04_ E
_coop) e (rL04_ E
_temp) e (rL04_ E
_recup) e (rL04_ E
@@ -488,13 +492,14 @@ _refrig) e (rL04_ E
_bez) e (rrL03_ e
_inv) e (rtL03_ e
_f) e (rvL03_ e
_p) e (sL01_ E
_refr) e (scL01_ E
_d) e (scL02_ E
_cr) e (scL02_ E
_p) e (scL03_ E
_m) e (sclL04 E
_d) e (spL02_ E
_p) e (squL02_ E
_refr) e (squL02_ E
_l) e (ssL02_ e
_esp) e (ssL03_ e
_c) e (stL03_ e
@@ -515,43 +520,10 @@ _obsol) e (tL03_ e
_despr) e (zL04_ E
_embel) e (zL04_ E
_menospr) e (zL04_ E
_emagr) e (çL03
pr) e (çL03_ e // a-
aqu) e (çL03_ e // re-
mer) e (çL03_ e // des-
pad) e (çL03_ e // com-
par) e (çL03_ e // a- re- com- rea- desa-
_ado) e (çL03_ e
_car) e (çL03_ e
_per) e (çL03_ e_
conh) e (çL03_ e // re-
obed) e (çL03_ e // des-
_esqu) e (çL03_ e
_forn) e (çL03_ e
_ofer) e (çL03_ e
abast) e (çL03_ e // re-
_aborr) e (çL03_ e
_acont) e (çL03_ e
_agrad) e (çL03_ e
_amanh) e (çL03_ e
_amort) e (çL03_ e
_anoit) e (çL03_ e
_arref) e (çL03_ e
_desguarn) e (çL03_ e
_desguarnec) e (çL03_ e
_enfraqu) e (çL03_ e
_enlouqu) e (çL03_ e
_enraiv) e (çL03_ e
_enriqu) e (çL03_ e
_entrist) e (çL03_ e
_envaid) e (çL03_ e
_envelh) e (çL03_ e
_esclar) e (çL03_ e
_espair) e (çL03_ e
_estrem) e (çL03_ e
_fortal) e (çL03_ e
_rejuven) e (çL03_ e
estabel) e (çL03_ e // re-
com) e (çL01_ E
p) e (çL03_ E
_m) e (çL03_ E
_entorp) e (çL03_ e
//endsort


@@ -600,7 +572,12 @@ estabel) e (çL03_ e // re-
?3 g (_C g_
g (Y Z // ge gi
gu (Y g
?1 guen (C gw'eIN // aguenta, etc.
a) gu (ent gw
enxa) gu (e gw
lin) gu (e gw
lin) gu (i gw
san) gu (ín gw
san) gu (in gw
?1 n) gu (A gw // eg: língua, etc.
?1 man) gu (ei g // mangueira
?1 gu (ém_ g // eg: alguém, ninguém, etc...
@@ -847,15 +824,19 @@ estabel) e (çL03_ e // re-
_engl) o (bL01_ O
_s) o (bL02_ O
_esn) o (bL04_ O
br) o (chL04_ O
_deb) o (chL04_ O
_desabr) o (chL04_ O
_m) o (fL01_ O
_m) o (fL02_ O
_s) o (frL02_ O
r) o (gL04_ O // inter-
_j) o (gL04_ O
_af) o (gL04_ O
_adv) o (gL04_ O
_ref) o (gL04_ O
_ap) oi (L04_ OI
_ap) oi (L01_ OI
_ap) oi (L02_ OI
_b) oi (L04_ OI
_t) o (lL03_ o
c) o (lhL02_ O // es- en- re-
_t) o (lhL02_ O
@@ -870,10 +851,13 @@ _desabr) o (chL04_ O
_ens) o (pL04_ O
_s) o (prL04_ O
_) o (ptL04_ O
_defl) o (rL02_ O
_impl) o (rL02_ O
_inod) o (rL03_ O
_inson) o (rL03_ O
_comem) o (rL04 O
_remem) o (rL04_ O
f) o (rmL03_ O
_enf) o (rquL02_ O
_ext) o (rquL02_ O
c) o (rrL01_ o // escorra, incorra, corra, recorra
@@ -882,8 +866,10 @@ _remem) o (rL04_ O
t) o (rçL01_ O // con-
_r) o (snL04_ O
_c) o (spL02_ O
_enr) o (squL02_ O
p) ostos (_ Ost=Us# // dispostos etc.
_gar) o (tL03_ o
pr) o (vL03_ O
_g) o (zL04_ O
_esb) o (çL01_ O
_r) o (çL03_ O
@@ -940,8 +926,16 @@ _remem) o (rL04_ O
?1 _) qua kwa // quatro, etc.
?1 _) que ke // quente, etc.
?1 _) quei (C k'eI // queira, queima, etc
?1 C) quen (C kw'eIN // cinquenta, etc.
?1 A) quen (C kw'eIN // frequência, etc.
A) quên (C kw'eIN // frequência, etc.
ade) qu (e kw
e) qu (estr kw
_e) qu (in kw
fre) qu (ent kw
li) qu (id kw
lí) qu (id kw
n) qu (en kw
se) qu (en kw
tran) qu (il kw
?1 quec kes // esquece, etc.
?1 queç kes // esqueça.
?1 A) que (nA_ ke // pequeno, etc.

+ 1
- 1
dictsource/sw_rules View File

@@ -70,7 +70,7 @@
_) n (k N-
_) n (k@@ N-
n (g N
_) n (g N-
K) n (g N-
_) n (g@@ N-

.group o

+ 1
- 1
dictsource/zhy_rules View File

@@ -3,7 +3,7 @@
// condition ?1 Speak English letters as English words
// condition ?2 Speak English letter as jyutping romanisation

//voice=zh-yue // to find the voice for this dictionary

.group a
?1 a _^_EN

+ 28
- 6
docs/phontab.html View File

@@ -228,31 +228,50 @@ where the <code>ELSE</code> and multiple <code>ELSE</code> parts are optional.
<p>
Multiple conditions may be joined with <code>AND</code> or <code>OR</code>, but not a mixture of <code>AND</code>s and <code>OR</code>s.
<p>
A condition may be preceded by <code>NOT</code>. For example:
<pre>
IF &lt;condition&gt; AND NOT &lt;condition&gt; THEN
&lt;statements&gt;
ENDIF
</pre>
<p>
<strong>Condition</strong>
Can be:
<ul>
<dl>
<dt>thisPh(&lt;attribute&gt;)
<dd>Test this current phoneme
<p>
<dt>prevPh(&lt;attribute&gt;)
<dd>Test the previous phoneme
<p>
<dt>prevPhW(&lt;attribute&gt;)
<dd>Test the previous phoneme, but only within the same word. Returns false if there is no previous phoneme in the word.
<p>
<dt>thisPh(&lt;attribute&gt;)
<dd>Test this current phoneme
<dt>prev2PhW(&lt;attribute&gt;)
<dd>Test the phoneme before the previous phoneme, but only within the same word. Returns false if it is not in this word.
<p>
<dt>nextPh(&lt;attribute&gt;)
<dd>Test the following phoneme
<p>
<dt>nextPhW(&lt;attribute&gt;)
<dd>Test the following phoneme, but only within the same word. Returns false if there is no following phoneme in the word.
<p>
<dt>next2Ph(&lt;attribute&gt;)
<dd>Test the phoneme after the next phoneme.
<p>
<dt>nextPhW(&lt;attribute&gt;)
<dd>Test the next phoneme, but only within the same word. Returns false if there is no following phoneme in the word.
<p>
<dt>next2PhW(&lt;attribute&gt;)
<dd>Test the phoneme after the next phoneme, but only within the same word. Returns false if not found before the word end.
<p>
<dt>next3PhW(&lt;attribute&gt;)
<dd>Test the third phoneme after the current phoneme, but only within the same word. Returns false if not found before the word end.
<p>
<dt>nextVowel(&lt;attribute&gt;)
<dd>Test the next vowel after the current phoneme, but only within the same word. Returns false if there is none.
<p>
<dt>prevVowel(&lt;attribute&gt;)
<dd>Test the previous vowel before the current phoneme, but only within the same word. Returns false if there is none.
<p>
<dt>PreVoicing()
<dd>This is used as part of the instructions for voiced stop consonants (eg. [d] [g]). If true then produce a voiced murmur before the stop.
<p>
@@ -263,6 +282,7 @@ Can be:
<strong>Attributes</strong>
<ul>
Note: Additional attributes could be added to eSpeak if needed.
<p>
<dl>
<dt>&lt;phoneme name&gt;
<dd>True if the phoneme has this phoneme name.
@@ -294,8 +314,10 @@ Note: Additional attributes could be added to eSpeak if needed.
<dt>isWordEnd
<dd>True if this is the final phoneme in a word.
<p>
<dt>isFirstVowel
<dt>isSecondVowel
<dt>isFinalVowel
<dd>True if this is the last vowel in a word.
<dd>True if this is the First, Second, or Last vowel in a word.
<p>
<dt>isAfterStress
<dd>True if this phoneme is after the stressed vowel in a word.

+ 40
- 2
phsource/mbrola/id1 View File

@@ -1,6 +1,5 @@

// CR1 doesn't like same phonemes twice
0 e E 5 e _
// ID1 and MS1 don't like same phonemes twice
0 s s 5 s _
0 ? k 5 k _
0 t t 5 t _
@@ -8,6 +7,10 @@
0 n n 5 n _
0 p p 5 p _
0 l/ l 5 l _
0 h h 5 h _
0 k k 5 k _
0 z z 5 z _
0 D D 5 z _

0 l/2 NULL 0 l
0 l/ NULL 0 l
@@ -28,10 +31,13 @@

0 a NULL 0 V
0 E NULL 0 e
0 E2 NULL 0 e
0 i NULL 0 I
0 o NULL 0 Q
0 O NULL 0 Q
0 u NULL 0 U
// 'id1' has phonemes OI aI aU


0 n^ NULL 0 nY
0 ? NULL 0 k
@@ -40,3 +46,35 @@
0 R NULL 0 r
0 x NULL 0 h

// some English phonemes
0 A: NULL 60 V r
0 A@ NULL 60 V r
0 eI NULL 0 e
0 oU NULL 60 Q U
0 u: NULL 0 U
0 i: NULL 0 I
0 I2 NULL 0 I
0 I# NULL 0 I
0 3 NULL 0 @
0 3: NULL 0 @
0 e@ NULL 0 e
0 i@ NULL 60 I @
0 i@3 NULL 60 I r
0 o@ NULL 60 Q @
0 O@ NULL 60 Q @
0 O: NULL 80 Q @
0 U@ NULL 60 U @
0 0 NULL 0 Q
0 a# NULL 0 @
0 aa NULL 0 V
0 @L NULL 50 @ l
0 aI @ 5 aI _
0 aI 3 5 aI _
0 aU @ 5 aU _
0 aI@ NULL 75 V @
0 aI3 NULL 75 V r
0 aU@ NULL 75 V @

0 Z NULL 60 z j
0 T NULL 0 t
0 D NULL 0 z

+ 4
- 0
phsource/ph_bengali View File

@@ -8,6 +8,10 @@ phoneme V // inherent vowel, can be [O] or [o]
vowel flag1 starttype #o endtype #o
length 200

IF thisPh(isWordEnd) AND prevPhW(isNotVowel) AND prev2PhW(isNotVowel) THEN
ChangePhoneme(NULL)
ENDIF

IF thisPh(isFirstVowel) THEN
IF nextVowel(i) OR nextVowel(u) THEN
ChangePhoneme(o)

+ 51
- 1
phsource/ph_indonesian View File

@@ -3,6 +3,9 @@ phoneme @
vowel starttype #@ endtype #@
unstressed
length 140
IF prevPh(@) THEN
InsertPhoneme(_|)
ENDIF
FMT(vowel/@_low)
endphoneme

@@ -11,6 +14,9 @@ endphoneme
phoneme a
vowel starttype #a endtype #a
length 180
IF prevPh(a) THEN
InsertPhoneme(_|)
ENDIF
ChangeIfUnstressed(a/)
FMT(vowel/a)
endphoneme
@@ -19,6 +25,9 @@ endphoneme
phoneme E
vowel starttype #e endtype #e
length 180
IF prevPh(#e) THEN
InsertPhoneme(_|)
ENDIF
ChangeIfUnstressed(@)
FMT(vowel/e_mid)
endphoneme
@@ -26,6 +35,9 @@ endphoneme
phoneme E2 // as [E] but don't reduce to [@]
vowel starttype #e endtype #e
length 180
IF prevPh(#e) THEN
InsertPhoneme(_|)
ENDIF
FMT(vowel/e_mid)
endphoneme

@@ -33,6 +45,9 @@ endphoneme
phoneme e
vowel starttype #e endtype #e
length 180
IF prevPh(#e) THEN
InsertPhoneme(_|)
ENDIF
FMT(vowel/e)
endphoneme

@@ -40,7 +55,9 @@ endphoneme
phoneme i
vowel starttype #i endtype #i
length 180
IfNextVowelAppend(;)
IF prevPh(i) THEN
InsertPhoneme(_|)
ENDIF
FMT(vowel/i_6)
endphoneme

@@ -48,6 +65,9 @@ endphoneme
phoneme O
vowel starttype #o endtype #o
length 180
IF prevPh(#o) THEN
InsertPhoneme(_|)
ENDIF
FMT(vowel/oo)
endphoneme

@@ -55,6 +75,9 @@ endphoneme
phoneme o
vowel starttype #o endtype #o
length 180
IF prevPh(#o) THEN
InsertPhoneme(_|)
ENDIF
FMT(vowel/o)
endphoneme

@@ -62,6 +85,9 @@ endphoneme
phoneme u
vowel starttype #u endtype #u
length 180
IF prevPh(u) THEN
InsertPhoneme(_|)
ENDIF
FMT(vowel/u)
endphoneme

@@ -69,6 +95,12 @@ endphoneme
phoneme aI
vowel starttype #a endtype #i
length 240
IF prevPh(isVowel) THEN
InsertPhoneme(_|)
ENDIF
IF nextPh(isVowel) THEN
AppendPhoneme(_|)
ENDIF
FMT(vdiph/ai)
endphoneme

@@ -78,9 +110,27 @@ phoneme eI
FMT(vdiph/eei_2)
endphoneme

phoneme OI
vowel starttype #o endtype #i
length 240
IF prevPh(isVowel) THEN
InsertPhoneme(_|)
ENDIF
IF nextPh(isVowel) THEN
AppendPhoneme(_|)
ENDIF
FMT(vdiph/ooi)
endphoneme

phoneme aU
vowel starttype #a endtype #u
length 240
IF prevPh(isVowel) THEN
InsertPhoneme(_|)
ENDIF
IF nextPh(isVowel) THEN
AppendPhoneme(_|)
ENDIF
FMT(vdiph/au_4)
endphoneme


+ 42
- 40
phsource/phonemes View File

@@ -1864,6 +1864,20 @@ include ph_georgian
phonemetable fa base
include ph_farsi

// experimental

phonemetable ko base
include ph_korean

phonemetable kl base
include ph_greenlandic

phonemetable am base
include ph_amhari

phonemetable si hi
include ph_sinhala


//**************************************************************************************
// The following lines are experimental, for future additions.
@@ -1882,61 +1896,49 @@ include ph_kinyarwanda
//phonemetable mn base
//include ph_mongolian

phonemetable prs base
include ph_dari
//phonemetable prs base
//include ph_dari

phonemetable sl sk
include ph_slovenian

phonemetable gd base
include ph_s_gaelic
//phonemetable gd base
//include ph_s_gaelic

phonemetable nso base
include ph_northern-sotho
//phonemetable nso base
//include ph_northern-sotho

phonemetable ht fr
include ph_haitian
//phonemetable ht fr
//include ph_haitian

phonemetable az tr
include ph_azerbaijani
//phonemetable az tr
//include ph_azerbaijani

phonemetable ak base
include ph_akan
//phonemetable ak base
//include ph_akan

phonemetable am base
include ph_amhari

phonemetable wo base
include ph_wolof

phonemetable dv hi
include ph_divehi

phonemetable te hi
include ph_telugu

phonemetable si hi
include ph_sinhala
//phonemetable wo base
//include ph_wolof

phonemetable tn base
include ph_setswana
//phonemetable dv hi
//include ph_divehi

//phonemetable te hi
//include ph_telugu

phonemetable mt base
include ph_maltese
//phonemetable tn base
//include ph_setswana

phonemetable bo hi
include ph_tibetan

phonemetable kk base
include ph_kazakh
//phonemetable mt base
//include ph_maltese

phonemetable tt base
include ph_tatar
//phonemetable bo hi
//include ph_tibetan

phonemetable ko base
include ph_korean
//phonemetable kk base
//include ph_kazakh

phonemetable kl base
include ph_greenlandic
//phonemetable tt base
//include ph_tatar


BIN
phsource/vwl_fr/trr View File


+ 15
- 5
src/compiledata.cpp View File

@@ -104,9 +104,8 @@ static keywtab_t k_conditions[] = {
{"next2PhW", tWHICH_PHONEME, 6},
{"nextVowel",tWHICH_PHONEME, 7},
{"prevVowel",tWHICH_PHONEME, 8},
// {"next2PhW", tWHICH_PHONEME, 0x800},

// {"numVowels", tTEST, 0x000},
{"next3PhW", tWHICH_PHONEME, 9},
{"prev2PhW", tWHICH_PHONEME, 10},

{"PreVoicing", tTEST, 0xf01},
{"KlattSynth", tTEST, 0xf02},
@@ -1051,8 +1050,13 @@ static wxString CompileAllDictionaries()
fclose(f_in);
}

LoadVoice(voicename,0);

if(LoadVoice(voicename,1) == NULL)
{
wxLogError(wxString::Format(_T("Can't find voice '%s' for dictionary '%s'"), wxString(voicename, wxConvLocal).c_str(), dictstr.c_str()));
report = report + dictstr + _T(" No Voice, ");
errors ++;
}
else
if((err = CompileDictionary(path_dsource, dictname,log,NULL,0)) > 0)
{
report = report + dictstr + wxString::Format(_T(" %d, "),err);
@@ -2742,6 +2746,7 @@ int CompilePhoneme(int compile_phoneme)
int count;
int c;
char *p;
int vowel_length_factor = 100; // for testing
char number_buf[12];
char ipa_buf[N_ITEM_STRING+1];
PHONEME_TAB phoneme_out2;
@@ -2844,6 +2849,11 @@ int CompilePhoneme(int compile_phoneme)

case i_SET_LENGTH:
value = NextItemMax(511);
if(phoneme_out->type == phVOWEL)
{
value = (value * vowel_length_factor)/100;
}

if(after_if == 0)
{
phoneme_out->std_length = value/2;

+ 5
- 5
src/compiledict.cpp View File

@@ -470,12 +470,12 @@ static int compile_line(char *linebuf, char *dict_line, int *hash)
}

ix = 0;
if(isdigit(*p))
if(IsDigit09(*p))
{
ix += (*p-'0');
p++;
}
if(isdigit(*p))
if(IsDigit09(*p))
{
ix = ix*10 + (*p-'0');
p++;
@@ -542,7 +542,7 @@ static int compile_line(char *linebuf, char *dict_line, int *hash)
case 1:
if((c == '-') && multiple_words)
{
if(isdigit(word[0]))
if(IsDigit09(word[0]))
{
multiple_numeric_hyphen = 1;
}
@@ -1156,7 +1156,7 @@ static void copy_rule_string(char *string, int &state)
sxflags |= SUFX_M;
break;
default:
if(isdigit(c))
if(IsDigit09(c))
value = (value*10) + (c - '0');
break;
}
@@ -1575,7 +1575,7 @@ static int compile_lettergroup(char *input, FILE *f_out)
char item_length[N_LETTERGP_ITEMS];

p = input;
if(!isdigit(p[0]) || !isdigit(p[1]))
if(!IsDigit09(p[0]) || !IsDigit09(p[1]))
{
fprintf(f_log,"%5d: Expected 2 digits after '.L'\n",linenum);
error_count++;

+ 2
- 2
src/dictionary.cpp View File

@@ -607,7 +607,7 @@ char *WritePhMnemonic(char *phon_out, PHONEME_TAB *ph, PHONEME_LIST *plist, int
break; // # is subscript-h, but only for consonants

// ignore digits after the first character
if(!first && isdigit(c))
if(!first && IsDigit09(c))
continue;

if((c >= 0x20) && (c < 128))
@@ -3362,7 +3362,7 @@ int LookupDictList(Translator *tr, char **wordptr, char *ph_out, unsigned int *f
if(((c = *word1++)==0) || (c == ' '))
break;

if((c=='.') && (length > 0) && (isdigit(word[length-1])))
if((c=='.') && (length > 0) && (IsDigit09(word[length-1])))
break; // needed for lang=hu, eg. "december 2.-ig"

word[length] = c;

+ 18
- 18
src/numbers.cpp View File

@@ -604,7 +604,7 @@ int TranslateLetter(Translator *tr, char *word, char *phonemes, int control)
char ph_buf[80];
char ph_buf2[80];
char ph_alphabet[80];
char hexbuf[6];
char hexbuf[12];
static char pause_string[] = {phonPAUSE, 0};

ph_buf[0] = 0;
@@ -981,7 +981,7 @@ int TranslateRoman(Translator *tr, char *word, char *ph_out, WORD_TAB *wtab)
flags[0] = 0;
flags[1] = 0;

if(((tr->langopts.numbers & NUM_ROMAN_CAPITALS) && !(wtab[0].flags & FLAG_ALL_UPPER)) || isdigit(word[-2]))
if(((tr->langopts.numbers & NUM_ROMAN_CAPITALS) && !(wtab[0].flags & FLAG_ALL_UPPER)) || IsDigit09(word[-2]))
return(0); // not '2xx'

word_start = word;
@@ -1020,7 +1020,7 @@ int TranslateRoman(Translator *tr, char *word, char *ph_out, WORD_TAB *wtab)
n_digits++;
}

if(isdigit(word[0]))
if(IsDigit09(word[0]))
return(0); // eg. 'xx2'

acc += prev;
@@ -1756,12 +1756,12 @@ bool CheckThousandsGroup(char *word, int group_len)
// Is this a group of 3 digits which looks like a thousands group?
int ix;

if(isdigit(word[group_len]) || isdigit(-1))
if(IsDigit09(word[group_len]) || IsDigit09(-1))
return(false);

for(ix=0; ix < group_len; ix++)
{
if(!isdigit(word[ix]))
if(!IsDigit09(word[ix]))
return(false);
}
return(true);
@@ -1812,7 +1812,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned
digit_lookup = buf_digit_lookup;
number_control = control;

for(ix=0; isdigit(word[ix]); ix++) ;
for(ix=0; IsDigit09(word[ix]); ix++) ;
n_digits = ix;
value = this_value = atoi(word);

@@ -1821,14 +1821,14 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned
group_len = 4;

// is there a previous thousands part (as a previous "word") ?
if((n_digits == group_len) && (word[-2] == tr->langopts.thousands_sep) && isdigit(word[-3]))
if((n_digits == group_len) && (word[-2] == tr->langopts.thousands_sep) && IsDigit09(word[-3]))
{
prev_thousands = 1;
}
else if((tr->langopts.thousands_sep == ' ') || (tr->langopts.numbers & NUM_ALLOW_SPACE))
{
// thousands groups can be separated by spaces
if((n_digits == 3) && !(wtab->flags & FLAG_MULTIPLE_SPACES) && isdigit(word[-2]))
if((n_digits == 3) && !(wtab->flags & FLAG_MULTIPLE_SPACES) && IsDigit09(word[-2]))
{
prev_thousands = 1;
}
@@ -1850,7 +1850,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned
}
}

if((word[ix] == '.') && !isdigit(word[ix+1]) && !isdigit(word[ix+2]) && !(wtab[1].flags & FLAG_NOSPACE))
if((word[ix] == '.') && !IsDigit09(word[ix+1]) && !IsDigit09(word[ix+2]) && !(wtab[1].flags & FLAG_NOSPACE))
{
// remove dot unless followed by another number
word[ix] = 0;
@@ -1879,7 +1879,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned
{
ordinal = 2;
}
else if(!isdigit(suffix[0])) // not _#9 (tab)
else if(!IsDigit09(suffix[0])) // not _#9 (tab)
{
sprintf(string,"_#%s",suffix);
if(Lookup(tr, string, ph_ordinal2))
@@ -1904,7 +1904,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned

if((word[0] == '0') && (prev_thousands == 0) && (word[1] != ' ') && (word[1] != tr->langopts.decimal_sep))
{
if((n_digits == 2) && (word[3] == ':') && isdigit(word[5]) && isspace(word[7]))
if((n_digits == 2) && (word[3] == ':') && IsDigit09(word[5]) && isspace(word[7]))
{
// looks like a time 02:30, omit the leading zero
}
@@ -1973,7 +1973,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned
}
}

if((word[n_digits] == tr->langopts.decimal_sep) && isdigit(word[n_digits+1]))
if((word[n_digits] == tr->langopts.decimal_sep) && IsDigit09(word[n_digits+1]))
{
// this "word" ends with a decimal point
Lookup(tr, "_dpt", ph_append);
@@ -2018,8 +2018,8 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned
char *p2;
// look for combinations of the number with the next word
p = word;
while(isdigit(p[1])) p++; // just use the last digit
if(isdigit(p[-1]))
while(IsDigit09(p[1])) p++; // just use the last digit
if(IsDigit09(p[-1]))
{
p2 = p - 1;
if(LookupDictList(tr, &p2, buf_digit_lookup, flags, FLAG_SUFX, wtab)) // lookup 2 digits
@@ -2082,7 +2082,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned
n_digits++;

decimal_count = 0;
while(isdigit(word[n_digits+decimal_count]))
while(IsDigit09(word[n_digits+decimal_count]))
decimal_count++;

// if(decimal_count > 1)
@@ -2101,7 +2101,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned
decimal_count--;
n_digits++;
}
if((decimal_count <= max_decimal_count) && isdigit(word[n_digits]))
if((decimal_count <= max_decimal_count) && IsDigit09(word[n_digits]))
{
LookupNum3(tr, atoi(&word[n_digits]), buf1, 0,0,0);
strcat(ph_out,buf1);
@@ -2152,7 +2152,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned
}
}

while(isdigit(c = word[n_digits]) && (strlen(ph_out) < (N_WORD_PHONEMES - 10)))
while(IsDigit09(c = word[n_digits]) && (strlen(ph_out) < (N_WORD_PHONEMES - 10)))
{
// speak any remaining decimal fraction digits individually
value = word[n_digits++] - '0';
@@ -2165,7 +2165,7 @@ static int TranslateNumber_1(Translator *tr, char *word, char *ph_out, unsigned
if(Lookup(tr, "_dpt2", buf1))
strcat(ph_out,buf1);

if((c == tr->langopts.decimal_sep) && isdigit(word[n_digits+1]))
if((c == tr->langopts.decimal_sep) && IsDigit09(word[n_digits+1]))
{
Lookup(tr, "_dpt", buf1);
strcat(ph_out,buf1);

+ 2
- 2
src/readclause.cpp View File

@@ -1287,10 +1287,10 @@ static int attrnumber(const wchar_t *pw, int default_value, int type)
{//==================================================================
int value = 0;

if((pw == NULL) || !isdigit(*pw))
if((pw == NULL) || !IsDigit09(*pw))
return(default_value);

while(isdigit(*pw))
while(IsDigit09(*pw))
{
value = value*10 + *pw++ - '0';
}

+ 17
- 1
src/synthdata.cpp View File

@@ -35,7 +35,7 @@
#include "translate.h"
#include "wave.h"

const char *version_string = "1.47.03b 22.Mar.13";
const char *version_string = "1.47.03c 23.Mar.13";
const int version_phdata = 0x014701;

int option_device_number = -1;
@@ -615,6 +615,7 @@ static int CountVowelPosition(PHONEME_LIST *plist)
static bool InterpretCondition(Translator *tr, int control, PHONEME_LIST *plist, USHORT *p_prog, WORD_PH_DATA *worddata)
{//========================================================================================================================
int which;
int ix;
unsigned int data;
int instn;
int instn2;
@@ -705,6 +706,21 @@ static bool InterpretCondition(Translator *tr, int control, PHONEME_LIST *plist,
return(false); // no previous vowel
plist = &(worddata->prev_vowel);
break;

case 9: // next3PhW
for(ix=1; ix<=3; ix++)
{
if(plist[ix].sourceix)
return(false);
}
plist = &plist[3];
break;

case 10: // prev2PhW
if((plist[0].sourceix) || (plist[-1].sourceix))
return(false);
plist-=2;
break;
}

if((which == 0) || (which == 5))

+ 4
- 1
src/tr_languages.cpp View File

@@ -975,6 +975,7 @@ SetLengthMods(tr,3); // all equal
break;

case L('i','d'): // Indonesian
case L('m','s'): // Malay
{
static const short stress_lengths_id[8] = {160, 200, 180, 180, 0, 0, 220, 240};
static const unsigned char stress_amps_id[8] = {16,18, 18,18, 20,22, 22,21 };
@@ -1312,7 +1313,7 @@ SetLengthMods(tr,3); // all equal
tr->langopts.stress_rule = STRESSPOSN_2R;
tr->langopts.stress_flags = S_FINAL_DIM_ONLY | S_FINAL_NO_2;
tr->langopts.length_mods0 = tr->langopts.length_mods; // don't lengthen vowels in the last syllable
tr->langopts.param[LOPT_UNPRONOUNCABLE] = 1; // disable check for unpronouncable words. Need to allow "bw'" prefix
tr->langopts.numbers = NUM_HUNDRED_AND | NUM_AND_UNITS | NUM_DFRACTION_2 | NUM_AND_HUNDRED;
tr->langopts.numbers2 = 0x200; // say "thousands" before its number
}
@@ -1429,6 +1430,8 @@ SetLengthMods(tr,3); // all equal
tr->langopts.vowel_pause = 1;
tr->langopts.stress_rule = STRESSPOSN_2R;
tr->langopts.stress_flags = S_FINAL_DIM_ONLY | S_FINAL_NO_2;
tr->langopts.max_initial_consonants = 4; // for example: mwngi


tr->langopts.numbers = NUM_AND_UNITS | NUM_HUNDRED_AND | NUM_SINGLE_AND | NUM_OMIT_1_HUNDRED;
tr->langopts.break_numbers = 0x49249268; // for languages which have numbers for 100,000 and 1,000,000

+ 6
- 5
src/translate.cpp View File

@@ -374,6 +374,7 @@ void SetLengthMods(Translator *tr, int value)
}



int IsAlpha(unsigned int c)
{//========================
// Replacement for iswalph() which also checks for some in-word symbols
@@ -429,8 +430,8 @@ int IsAlpha(unsigned int c)
return(0);
}

static int IsDigit09(unsigned int c)
{//=========================
int IsDigit09(unsigned int c)
{//============================
if((c >= '0') && (c <= '9'))
return(1);
return(0);
@@ -2311,10 +2312,10 @@ static int EmbeddedCommand(unsigned int &source_index)
source_index++;
}

if(isdigit(source[source_index]))
if(IsDigit09(source[source_index]))
{
value = atoi(&source[source_index]);
while(isdigit(source[source_index]))
while(IsDigit09(source[source_index]))
source_index++;
}

@@ -3331,7 +3332,7 @@ if((c == '/') && (tr->langopts.testing & 2) && IsDigit09(next_in) && IsAlpha(pre

while(pn < &number_buf[sizeof(number_buf)-20])
{
if(!isdigit(c = *pw++) && (c != tr->langopts.decimal_sep))
if(!IsDigit09(c = *pw++) && (c != tr->langopts.decimal_sep))
break;

*pn++ = c;

+ 1
- 0
src/translate.h View File

@@ -709,6 +709,7 @@ void InitNamedata(void);
void InitText(int flags);
void InitText2(void);
int IsDigit(unsigned int c);
int IsDigit09(unsigned int c);
int IsAlpha(unsigned int c);
int IsVowel(Translator *tr, int c);
int isspace2(unsigned int c);

+ 2
- 2
src/voices.cpp View File

@@ -601,7 +601,7 @@ voice_t *LoadVoice(const char *vname, int control)

// which directory to look for a named voice. List of voice names, must end in a space.
static const char *voices_asia =
"fa fa-pin hi hy hy-west id ka kn ku ml ne pa ta tr vi vi-hue zh zh-yue ";
"fa fa-pin hi hy hy-west id ka kn ku ml ms ne pa ta tr vi vi-hue 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 ";

@@ -1134,7 +1134,7 @@ static char *ExtractVoiceVariantName(char *vname, int variant_num, int add_dir)
// The voice name has a +variant suffix
variant_num = 0;
*p++ = 0; // delete the suffix from the voice name
if(isdigit(*p))
if(IsDigit09(*p))
{
variant_num = atoi(p); // variant number
}

Write Preview
Loading…
Cancel
Save