Browse Source

Merge branch 'upstream' into development

Conflicts:
	dictsource/dict_phonemes
	phsource/compile_report
master
Reece H. Dunn 11 years ago
parent
commit
fd3742fb64

+ 24
- 21
dictsource/an_rules View File

@@ -75,9 +75,9 @@
i) e E
u) e E
y) e E
L06_) e (CC e# // unstressed 'e' silent at start of word after a,e,o
L06_h) e (CC e# // unstressed 'e' silent at start of word after a,e,o
L06_) e (CC e# // unstressed 'e' silent at start of word after a,e,o
L06_h) e (CC e# // unstressed 'e' silent at start of word after a,e,o

_) ent' (AP4 ent
_) enta' ,ent%a
@@ -109,13 +109,13 @@
.group h
h // silent
hu (Y gw

.group i
i i
i (u_ i
i (A j


.group j
@@ -142,7 +142,7 @@
n n
n (L04 m
n (_L04 m
ny n^
ny (A n^


.group ñ
@@ -173,13 +173,14 @@


.group q
q k
q k
qu (A kw
qü kw
qu (e k
qu (i k
qu (é k
qu (í k
qu ('A k

.group r
r r
@@ -214,9 +215,9 @@ q k
u) t (_ t#
ei) t (_ t#
n) t (_ = // silent, but stress on last vowel
n) t (m // Silent
_pos) t (h t
_pos) t (C // Silent
n) t (m // Silent
_pos) t (h t
_pos) t (C // Silent
tz T
ue) t (_ t#
ui) t (_ t#
@@ -234,16 +235,17 @@ q k
u (i u
r) uix uS
r) u (A u
A) u (Y gw
A) u (Y gw
u (A w
_) u (u u
_) u (u u
_) u (A gw
//Ar) u (Y gw
_des) u (Y gw
_es) u (Y gw
_des) u (Y gw
_es) u (Y gw

_cir) ue (ll gwe
_esquir) ue (l gwe
// Some exception
_esquir) u (el Qw // esquiruelo, esquiruelos
_cir) u (ell Qw // Ciruello, ciruella, ciruellos, ciruellas

.group v // same as 'b'
v b
@@ -266,24 +268,25 @@ _esquir) ue (l gwe
x ks
_) x S
i) x S
C) x S
C) x S

.group y
y j
y (_ i
C) y (C i

.group z
z T


.group
'
'
á ''a
é ''e
í ''i
ó ''o
ú ''u

__) - (_D m'enos
D_) - (_D m'enos
__) - (_D m'enos
D_) - (_D m'enos

+ 83
- 24
dictsource/en_list View File

@@ -16,8 +16,8 @@
// ?7 Scottish
// ?8 Use full vowel, not schwa in some word endings

// $alt1 use strong ending (-an, -ance, -ative, -table, -eria, -inal, -ier -or -ored, -s)
// $alt2 use weak ending (ace, ain, ard, ate, ery, ess, ile, men, on, ot)
// $alt1 use strong ending (-an, -ance, -ative, -table, -eria, -et, -inal, -ier -or -ored, -s)
// $alt2 use weak ending (ace, ain, an, ard, ate, ery, ess, ile, men, on, ot)
// $alt3 use weak first vowel, a->[a#], e->[@], o->[0#]
// $alt4 separate 'h', not 'th' 'ph'; [t2] not [t]
// $alt5 remove only 's' from plural (-ies)
@@ -601,6 +601,7 @@ lotr $abbrev
ltd lImI2tI2d
//mc m@k $combine // combine with the following word
mhz mEg@h3:ts
mit $abbrev $allcaps
motd $abbrev
mpaa $abbrev
msaa $abbrev
@@ -617,6 +618,7 @@ ocr $abbrev
odf $abbrev
oecd $abbrev
oem $abbrev
oic $abbrev
ok $abbrev
olpc $abbrev
omg $abbrev
@@ -625,10 +627,12 @@ osx $abbrev
otoh $abbrev
pcie $abbrev
pcmcia $abbrev
psa $abbrev
psu $abbrev
riaa $abbrev
riscos rIskoUEs
rnib $abbrev
rtos $abbrev
sae $abbrev
sla $abbrev
scsi skVzi
@@ -657,6 +661,7 @@ uucp $abbrev
uv $abbrev
VI $abbrev
wwii dVb@Lju:dVb@Lju:t'u:
xaml $abbrev
xl $abbrev // not roman 40
xxx $abbrev // not roman 30
xy $abbrev
@@ -717,6 +722,7 @@ acetylene a#sEt@li:n
accurate $alt2
accursed a#k3:sI#d
?5 accursed a#kVRsI#d
accuses a#kju:zI#z
ached eIkt
achille a#kIli:
aching eIkIN
@@ -870,11 +876,13 @@ anxious aNS@s
anymore $3
anything EnI2TIN
apache a#patSi
aperitif a#pEr@t'i:f
apneoa apni@
apostle a#p0s@L
apron eIpr@n
apropos apr@p'oU
appal a#pO:l
apparal $alt3
apparatus ap@r'eIt@s
?3 apparatus ap@r'at@s
appellate a#pEl@t
@@ -885,6 +893,7 @@ approximately a#pr0ksIm@tli
aqueduct akwI#dVkt
arab ar@b
arabic $1
arabica $alt3
arable ara#b@L
arc A@k // arcing
arcade $2
@@ -914,6 +923,7 @@ askance a#skaans
askew a#skju:
ass as
assess a#sEs
astride $alt3
asus eIs@s
atlas atl@s
atop a#t0p
@@ -1045,6 +1055,7 @@ bonhomie b0n@mi:
bonjour bO:nZ'U@
booger bUg3
boogie bu:gi
?3 boogey bUgi
?3 boogie bUgi
borealis bo@rI'alIs
bosun boUs@n
@@ -1194,6 +1205,7 @@ chassis Sasi
chateau SatoU
chemise S@mi:z
chevrolet SEvr@l'eI
chianti kjanti
chic Si:k
chiffron SIfr0n
chihuahua tSI2wA:w@
@@ -1216,7 +1228,6 @@ ciao tSaU
cigar sI2gA@
cigarette sIg@'rEt
cinema sIn@m@
cinnamon sIn@m@n
circumference s3:k'Vmfr@ns
circumstance $alt1
circumvent s3:k@mvEnt
@@ -1372,15 +1383,18 @@ cosmos k0zm0s
cougar ku:g3
counteract $3
countered kaUnt3d
(coup de grace) ku:d@||gr'A:
(coup de grâce) ku:d@||gr'A:
coupon ku:p0n
couscous ku:sku:s
couture ku:t'U@
covert koUv'3:t
covetous kVv@t@s
coworker koUw3:k3
coyote kaI'oUti
creature kri:tS3
?3 cremate kri:meIt
crescendo kr@SEndoU
crevasse kr@vas
crisis kraIsIs
crises kraIsi:z
@@ -1422,6 +1436,7 @@ decaf di:kaf
decent di:s@nt
decibel dEsI#b@L
declaration dEkl@'reIS@n
deco dEkoU
decolletage deIk0lt'A:Z
décolletage deIk0lt'A:Z
decor deIkO@
@@ -1466,6 +1481,7 @@ desperate $alt2
detante deIt'0nt
detente deIt'0nt
détente deIt'0nt
detestation dIt,Est'eIS@n
detour di:t2U@
detritus dI2traIt@s
deus deIUs
@@ -1487,6 +1503,7 @@ dieback daIbak
diehard daIhA@d
dielectric daI@l'EktrIk
diesel di:z@L
dieu _^_FR
dilatory dIl@t@rI
?3 dilatory dIlato:rI
dilemma daIl'Em@
@@ -1529,6 +1546,7 @@ dose doUs
dosage doUsI2dZ
dossier d0sIeI
dotage doUtI2dZ
dragnet $alt1
dramatic dr@matIk
drawer drO@
dreamt drEmpt
@@ -1547,6 +1565,7 @@ earlobe i@3loUb
early 3:lI
eavesdrop i:vzdr0p
ebay $alt6
ebola $alt6
ebook $alt6
echelon ES@l0n
ecole Ik'oUl
@@ -1560,7 +1579,7 @@ edwardian Edw'O@di@n
efile $alt6
egg Eg // egging
egregious Igr'i:dZ@s
?!3 egret i:gr@t
egret i:gr@t
eh eI
eid i:d
eke i:k
@@ -1643,6 +1662,7 @@ evenings i:vnINz
evit EvI2t // inevitable
exactement Egzakt@m'A~
exalt Egz'0lt
excuses Ekskj'u:sI#z
execute EksI2kju:t // not $2
executable $3
exile $1
@@ -1712,7 +1732,7 @@ finance $verb
finess fI2nEs // for finessed
finesse fI2nEs
finite faInaIt
fishnet fISnEt
fishnet $alt1
fiord fi:O@d
fix fIks // for fixer
flaccid flasId
@@ -1736,8 +1756,7 @@ forewarn $2
formid fO@m'Id // formidable
formica fO@m'aIk@
fortunate fO@tS@n@t
fortune fO@tSu:n
?3 fortune fO@tS@n
!?3 fortune fO@tSu:n
foyer fOIeI
freelance fri:laans
freer fri:3
@@ -1762,7 +1781,7 @@ fuscia fju:S@
fuselage fju:z@lA:Z
futon fu:t0n

gala gA:l@
?3 gala geIl@
galactic $alt3
galaga gal@g@
galaxy gala#ksi
@@ -1787,12 +1806,12 @@ gazebo $alt3
geese gi:s
geezer gi:z3
gemini dZEmI2naI
generic dZ@nErIk
geni dZi:ni
genome dZi:noUm
genre Z0nr@
gentlemen dZEnt@Lm@n
genuine dZEnju:I#n
geo dZi:oU
geode dZi:oUd
geologist $2
geyser gi:z3
@@ -1845,6 +1864,7 @@ haggis hagIs
haha hA:h'A:
haiku haIku:
hairdo he@du:
hairnet $alt1
halation $alt3 // in-
halberdier $alt1
halleluiah halI2'lu:j@
@@ -1852,6 +1872,7 @@ hallelujah halI2'lu:j@
halloween $3
halogen hal@dZ@n
hanged haNd
hardcopy hA@dk0pi
harem hA:r'i:m
harness hA@nI#s
havoc hav@k
@@ -2025,7 +2046,7 @@ ipad $alt6
iphone $alt6
iplayer $alt6
irate aIr'eIt
iris $alt6
iris aIrIs // es
iron aI3n
isosceles aIs'0s@li:z
?3 issuance ISu:@ns
@@ -2047,6 +2068,7 @@ jour ZU@ // french
journal dZ3:n@L // journing
jukebox dZu:kb0ks
july dZu:l'aI
jumbalaya dZVmb@l'aI|@

kaput $alt3
karaoke karI'oUki
@@ -2119,7 +2141,7 @@ leprechaun lEpr@kO:n
lesion li:Z@n
(les misérables) leImIzEr'A:bl@-
lethal li:T@L
lethargy lET@dZi
lethargy lET3dZi
liaison li:'eIz0n
lichen laIk@n
lien li:@n
@@ -2153,7 +2175,6 @@ loch l0x
login l0gIn
logon l0g'0n
longago l0Ng@goU
london lVnd@n
looser lu:z3
lorenz l0r@nts
los ,l0s $only
@@ -2230,14 +2251,13 @@ medicine mEds@n
meh mE
melee mEleI
?3 melee meIleI
melon mEl@n
memento $alt3
memo mEmoU
memorial $alt3
memoriam $alt3
menagerie m@n'adZj@ri
ménage meIn'A:Z
menus mEnju:z
meow mi'aU
mercedes m3:s'eIdi:z
//mercenary m3:s@n@rI
merest mi@r@st
@@ -2256,7 +2276,8 @@ mica maIk@
microorganism maIkroU'O@g@nIz@m
midair $2
midday m,Idd'eI
mideast mId'i:st
middleman $alt1
mideven m,Id'i:vn // ing
midterm m'Idt,3:m
mildew mIldju:
mileage maIlI2dZ
@@ -2273,6 +2294,7 @@ minut mInIt // minuted
mir mi@3
mirage mIrA:Z
?3 mirage m3rA:Z
mirandize $2
mischief mIstSI#f
misery mIz@rI
misled mIsl'Ed
@@ -2286,7 +2308,6 @@ mister mIst3
mitre maIt3
mixer mIks3
moccasin m0k@sI#n
mocha moUk@
modem moUdEm
?3 modem moUd@m
moderate m0d@reIt $verb
@@ -2398,7 +2419,7 @@ ocelot 0s@l0t
ochre oUk3
o'clock @kl0k
octave 0ktIv
october $2
october 0kt'oUb3
oeuvre 3:vr@
?5 oeuvre VRvr@
offer 0f3
@@ -2428,6 +2449,7 @@ orion 0r'aI@n
ornate $2
orphan O@f@n // orphaned
ottoman 0t@m@n
oui wi:
ouija wi:dZ@
outage aUtI2dZ
outback $1
@@ -2487,7 +2509,8 @@ parabola p@rab@l@
paralysis p@ral@sIs
parameter p@ramI2t3
parasite par@saIt
paren pa#rEn // "parenthesis"
paren $alt3 // "parenthesis"
parental $alt3
pariah p@raI@
parole $alt3
passenger pasI2ndZ3
@@ -2512,13 +2535,14 @@ pearly p3:li
pecan pi:k@n
pedalo pEd@loU
pedestal pEdI2st@L
pedestrian $alt3
pedestria $alt3 // n
pegasus pEg@s@s
pejorative p@dZ0r@tIv
pekinese pi:kI#n'i:z
penal pi:n@L
penchant p0nS0n
?3 penchant pEnS@nt
pencil pEns@L // ed
peninsula p@n'InsjUl@
penis pi:nI2s
peon pi:@n
@@ -2864,6 +2888,7 @@ salmon sam@n
saloon $alt3
san ,san $only
sardine $2
sassafras sasa#fras
satanic $alt3
satiric $alt3
saucepan sO:sp@n
@@ -2939,6 +2964,7 @@ severest s@vi@r@st
shallow SaloU
shampoo $2
shareable Se@@b@L
shazam $alt3
shebang SI#baN
shenanigan SI#nanIg@n
shepherd SEp@d
@@ -3005,6 +3031,7 @@ sooth su:D
souffle su:fl'eI
soundbite saUndbaIt
souvenir su:v@n'i@3
sopapilla soUp@p'i:@
sorbet sO@beI
soyabean sOI@bi:n
spaghetti spa#gEti
@@ -3019,19 +3046,19 @@ staccato $alt3
stasis steIsI#s
standby standbaI
stagnate $2
?3 stalactite $alt3
?3 stalagmite $alt3
stampede $2
starboard stA@b3d
starry stA:rI
statistic $alt3
stencil stEns@L // ed
stiletto stI2lEtoU
stingy stIndZi
streambed stri:mbEd
strychnine str'Ikni:n
sterile stEraIl
stomata stoUm@t@
storytell stO:rItEl
storytelling stO:rItElIN
stringed strINgd
stripy straIpI
stygian stIdZi@n
suave swA:v
@@ -3050,6 +3077,7 @@ suerte swe@rteI // -ed, -es
suet su:I2t
suffice s@faIs
suffuse $2
sulphurous sVlf3r@s
summonse sVm@nz
sundae sVndeI
sundial sVndaI@l
@@ -3063,6 +3091,7 @@ supplier s@plaI3
suppose $2
suprise $2 // misspell
surest SU@@st
surety SU@@ti
?3 surplus s3:plVs
surrogate sVr@geIt
?3 surrogate s3:@g@t
@@ -3118,6 +3147,7 @@ telepathy t@lEp@Ti
telephony t@l'Ef@ni
telephonist t@l'Ef@nIst
ten tEn // untenable
tendril tEndr@L // ed
tennis tEnI#s
tepee ti:pi:
tequila t@ki:l@
@@ -3133,10 +3163,12 @@ tetanus tEt@n@s
thereabout $3
therefore $1
thereof De@r'0v
thereto De@t'u:
thermos T3:m@s
thermostable $alt1
thesis Ti:sIs
theta Ti:t@
thingumajig TIN@m@dZIg
tho DoU $only
throughout $2
thursday T3:zdeI
@@ -3327,6 +3359,7 @@ wannabe w0na#bi:
warred wO@d
warring wO@rIN
warthog $alt4
wasabi wa#sA:bi
wastage weIstI2dZ
wast weIst // wasted
watershed wO:t3SEd
@@ -3395,6 +3428,7 @@ yoyo joUjoU
zavala $alt3
zealot $alt2
?3 zebra zi:br@
zeppole zEp@li
zulus zu:lu:z


@@ -3433,6 +3467,7 @@ Greenwich grEnItS
Harwich harIdZ
Hasting heIstIN
Inverness Inv3n'Es
Killeen $2
Kirkcaldy kIRk'0di
Lambeth lamb@T
Leven li:v@n
@@ -3501,6 +3536,7 @@ Beirut beIr'u:t
Belgrade $2
Belize bEl'i:z
Bengal b,Eng'O:l
Benevente bEnIv'EnteI
Benin bEnIn
Berkeley b3:kli
Bethesda $alt3
@@ -3533,6 +3569,7 @@ Chile tSIli
?3 Chilean tSIl'i:@n
Cincinnati sInsIn'ati
Cologne k@loUn
Coloradan k0l3r'A:d@n
Colorado k0l3r'A:doU
Colombia k@lVmbi@
Columbus $alt3
@@ -3620,6 +3657,7 @@ Kosovo k0s@voU
Kuala kwA:la#
Kyrgyz k3:rgIz
Kyrgyzstan k3:rgIst'A:n
Lafitte la#fi:t
(La jolla) la#hOI@
Lagos leIg0s
Lahore $alt3
@@ -3640,6 +3678,7 @@ Lvov l@-v0v
Madagascar mad@g'ask3
Madras m@draas
Madrid m@drId
Makassar $alt3
Malawi $alt3
Malayalam maleI'A:l@m
Maldives mO:ld'i:v
@@ -3783,6 +3822,7 @@ Vermont $2
Vienna vI'En@
Viennese vi:@n'i:z
Vietnamese vi:Etn@m'i:z
Waco weIkoU
Wichita wItSI2tA@
Winnipeg wInI2pEg
Wisconsin wI2sk'0nsI2n
@@ -3860,6 +3900,7 @@ Bremen brEm@n
Brianna brI'an@
Brien braI@n
Caiseal kaS@L
Camille ka#mi:l
Candace kandIs
Carol kar@L
Caroline kar@laIn
@@ -4017,7 +4058,7 @@ Leanne li:'an
(Le ann) li:'an
Lenore lEn'o@
Leon li:0n
Leonard lEn@d
Leonard lEn3d
Leroy li:rOI
Liam li:@m
Lindsay lInzi
@@ -4031,7 +4072,6 @@ Louise lu:w'i:z
Luigi lu:'i:dZi
Luis lu:Is
Lupe lu:peI
Luther lu:T3
Madeleine mad@lI2n
Madeline mad@lI2n
Maeve meIv
@@ -4135,6 +4175,7 @@ Sarisa $alt3
Seamus SeIm@s
Sean SO:n
Sebastian $alt3
Seumus Su:m@s
Sheila Si:l@
Simon saIm@n
Sinead SI2neId
@@ -4170,6 +4211,7 @@ Trina tri:n@
Tricia trIS@
Trudy tru:di
Vanessa $alt3
Vernon $alt2
Wallace w0lI#s
Wally w0li
?3 William wIlj@m
@@ -4220,10 +4262,13 @@ Emory Em3ri
Ferguson f3:g@s@n
Fleming flEmIN
Folger foUldZ3
Forrester f0rI#st3
Foushee fu:S'eI
Gaia gaI|@
Gallagher gal@g3
Genghis dZENgIs
Gibson gIbs@n
Godzilla g0dz'Il@
Goliath $alt3
Guinness gInIs
Gutierrez gu:tj'ErEz
@@ -4235,6 +4280,7 @@ Hormel ho@m'El
Hoosier hu:Z3
Iscariot $2
Jacobi dZa#koUbi
Jerrard dZ3rA@d
Jimenez hIm'EnEz
Kawasaki kaU|@s'A:ki
Kendell kEnd@L
@@ -4244,22 +4290,27 @@ Kroger kroUg3
Kyocera kaI|@s'i@r@
Lamaze la#mA:z
Laurell $2
Lussier lVsIeI
Mackenna m@kEn@
Mackenzie m@kEnzi
Maguire m@gwaI3
Medusa $alt3
Michelangelo maIk@L'andZ@loU
Microsoft maIkr@s0ft
Monet moUn'eI
Montague m0nt2@gju:
Mossad moUs'A:d
Mozart moUtsA@t
Munoz mu:njoUz
Navasca $alt3
Nichol nIk@L
Nietzsche ni:tSi
Niro ni@roU
Nobel noUb'El
Otis oUtIs
Patel $alt3
Perez p3rEz
Pérez pErEz
Perrier pErI'eI
Pokemon poUkeIm0n
Pompadour p0mpa#do@
@@ -4286,6 +4337,8 @@ Sanchez santSEz
Shakur Sa#kU@
Sturgis st3:dZIs
Subaru su:b3u:
Sullivan $alt2
symantec $2
Thoreau $alt3
Truphone tru:foUn
Tzu tsu:
@@ -4298,6 +4351,7 @@ xeon zi:0n
Yaesu jeIsu:
Yamaha jam@hA:
?3 Yamaha jA:m@hA:
Yeo joU
Younge jVN
zeus zju:s
?3 zeus zu:s
@@ -4526,6 +4580,9 @@ had ,had $atend
(had been) %ha#d%bIn $pastf
(had it) h,adI2t
(had them) h,adDEm
(had one) hadwVn
(had any) h,ad||Eni
(had some) h,ad||sVm
having ,havIN $strend2 $pastf $only
haven't hav@-nt $pastf
hadn't had@-nt $pastf
@@ -4725,7 +4782,9 @@ those DoUz $u $nounf $strend2 $only
there De@ $u $strend2 $only
there've De@v $u
(there are) D%e@,A@ $strend
(there is) De@'Iz $atend
(there be) De@b'i:
(there was) D%e@w,0z $strend
(there were) D%e@,w3: $strend

than Da#n $u $only

+ 6203
- 6141
dictsource/en_rules
File diff suppressed because it is too large
View File


+ 15
- 17
dictsource/gu_rules View File

@@ -70,9 +70,9 @@

.group ઐ
ઐ aI // ?? [aI] [E:] [&:]
ઐં E~
ઐઁ (_ E~
?2 ઐ aI // ?? [aI] [E:] [&:]
ઐં aI~
ઐઁ (_ aI~

.group ઑ
@@ -86,10 +86,10 @@
ા) ઓઁ (_ w
.group ઔ
O: // ?? [aU] [O:]
ઔં O~ // +anusvara
ઔઁ (_ O~ // +candrabindu
?3 ઔ aU // ?? [aU] [O:]
aU // ?? [aU] [O:]
ઔં aU~ // +anusvara
ઔઁ (_ aU~ // +candrabindu


// Vowel Signs
@@ -141,11 +141,10 @@
ેઁ (_ e~:

.group ૈ
ૈ E: // ?? [aI] [E:] [&:]
ૈં E~
ૈ (ઁ E~
ૈઁ (_ E~
?2 ૈ aI // ?? [aI] [E:] [&:]
ૈ aI // ?? [aI] [E:] [&:]
ૈં aI~
ૈ (ઁ aI~
ૈઁ (_ aI~

.group ૉ
ૉ O
@@ -157,11 +156,10 @@
ોઁ (_ o~

.group ૌ
ૌ O: // [O:] or [aU] ??
ૌ (ઁ O~ // [O:] or [aU] ??
ૌં O~
ૌઁ (_ O~
?3 ૌ aU // [O:] or [aU] ??
ૌ aU // [O:] or [aU] ??
ૌ (ઁ aU~ // [O:] or [aU] ??
ૌં aU~
ૌઁ (_ aU~

.group ૢ // vowel sign l
ૢ l-

+ 288
- 189
dictsource/it_list
File diff suppressed because it is too large
View File


+ 64
- 27
dictsource/it_listx View File

@@ -20,6 +20,7 @@ accadia $3
accegli $alt
accenn $alt2
accett $alt2
accetto $alt
accipiter $2
accolit $2
accredit $2 $alt2
@@ -69,6 +70,7 @@ agora $3
agorafobia $5
agord $1
agost $alt2
agosta $1
agrifogli $alt
agrosistem $alt
aho $2
@@ -118,6 +120,7 @@ alleluia allEl'uia
allobrogi $2
allodol $2
alloggi $alt
allora $alt2
alluce $1
almen $alt2
alo $2 $alt
@@ -200,6 +203,7 @@ annibale $2
anoa $alt
anofele $2
anomalia $4
anomalo $2 $alt
anomei $3
anoressia $4
anosmia $3
@@ -209,6 +213,7 @@ antemi $alt
antenn $alt2
antenne $alt2
anter $1
antera $2
anteros $1
anthemis $1
antiaerea $3
@@ -372,13 +377,13 @@ atenolf $alt
ateo $1
atlet $alt
atom $1
aton $2
aton $1
atrofia $3
attendol $alt
attimis $1
attivita $4
attorn $alt2
audace $3
audac $3
augure $1
aulos $3
aureol $3
@@ -424,6 +429,7 @@ bachec $alt
badia $2
badile $2
bage $2
bagli $2 $only
bagnol $2
bagnoli $2
bagnoregi $alt
@@ -445,6 +451,7 @@ baratr $1
barbabietol $3 $alt
barbaner $alt2
barbar $1
barbera $2
baricentr $alt
barile $2
bariton $2
@@ -530,6 +537,7 @@ boa $alt
boabdil $3
bob $alt
bobbi $alt
bocca $alt2
boccaner $alt2
boccett $alt2
boccia $alt
@@ -563,6 +571,7 @@ borgosatoll $alt2
borgosesia $3 $alt
born $alt2
borneo $1
borro $alt2
bors $alt2
bos $alt
bosc $alt
@@ -633,7 +642,6 @@ caffar $1
caffe $2 $alt
cagno $2 $alt
calabr $1
calamita $4
calao $2
calasett $alt
calcaree $2
@@ -692,6 +700,7 @@ cantu $2
caorle $1
capace $2
capannori $2
capello $alt2
capiner $alt2
capitaneo $3
capocchia $alt
@@ -782,6 +791,7 @@ cavea $1
cavedine $alt2
cazzol $2
ceb $alt
ceca $alt
cecc $alt2
cecrope $1 $alt
cedol $1 $alt
@@ -802,7 +812,7 @@ cenerentol $alt
cenn $alt2
cenobi $alt
cenomani $2
centesim $alt
centesim $2 $alt
centimetr $2
centin $1 $alt
centocchi $alt
@@ -850,7 +860,6 @@ chies $alt
chiesanuov $alt
chiese $alt
chiliagon $3
chine $2
chio $2 $alt
chiod $2 $alt
chirogaleo $3
@@ -949,7 +958,7 @@ coller $alt
collett $alt
collevecchi $alt
colli $alt
collodi $alt
collodi $2 $alt $only
colloqui $alt
colob $1
cologn $alt
@@ -1044,12 +1053,14 @@ corneo $1
cornice $2
cornucopia $alt
corone $alt
corporeo $2
corporea $2
corporeo $2
corred $alt
correr $2
corrett $alt
corrid $2
corrott $alt2
corsa $alt2
cort $alt2
corte $alt2
cortenuov $alt
@@ -1068,8 +1079,6 @@ cosmogonia $4
cospett $alt
cosseria $2
cossov $1
costa $2
costi $2
cot $alt
cot $alt
cote $alt
@@ -1185,9 +1194,9 @@ diadem $alt
diagnosi $2
dialett $alt
dialisi $2
dialog $2
diametr $2
diapason $2
dialog $1
diametr $1
diapason $1
diarchia $3
diaspor $2
diatesi $2
@@ -1265,6 +1274,7 @@ dollar $1 $alt
dolman $alt
dolmen $alt
dolomia $2 $alt
doma $alt
domenic $alt2
domin $1
domusnovas $alt
@@ -1330,6 +1340,7 @@ egeria $2
egocentric $alt
egumen $2
eh $alt2
ei eI
el $alt2
elegiac $3
elemosin $3
@@ -1404,8 +1415,9 @@ enschede $3
entalpia $3
enteric $alt2
entropia $3
entusiasm $4
entusiasm $3
entusiast $4
epa $alt
epagneul $1
eparchia $3
epicentr $alt
@@ -1473,14 +1485,15 @@ esoner $2
esop $alt
esoscheletr $3
esotropia $4
esper $1 $alt
esperia $2
esplicit $2
esposimetr $3
ess $alt2
esserci $1 $alt
essere $alt
est $alt2
estasi $1
est $alt2 $only
estasi 'Estazi
estensimetr $3
ester $1
estet $alt
@@ -1588,6 +1601,7 @@ fet $alt
feud $1
ficarol $3
fienile $2
fieri fi'eRi
fiesole $1 $alt
figar $1
filantrop $2
@@ -1640,9 +1654,11 @@ foppol $alt
for $alt2
foraminiferi $4
foraneo $2
forca $alt2
forcol $alt2
forfor $1 $alt2
forgia $1
fori $alt $only
fori $2
formic $2
forn $alt2
@@ -1711,11 +1727,11 @@ gebel $alt
gec $alt
gemin $1
gemit $1
gener $1
generazione $alt
genesi $alt
genes $1 $alt
geneve $alt
geni $alt
gentile $2
geocentric $alt
geode $alt
geometr $2 $alt
@@ -1785,10 +1801,12 @@ gonars $2
goni $alt
gonn $alt2
gonnes $alt
gorga $alt2
gorgia $1
gorgonzol $3
got $alt
goti $alt
gotta $alt2
gottasecc $alt2
gozz $alt2
gradoli $1
@@ -1873,6 +1891,7 @@ incub $1
incursione $alt
indebit $2 $alt2
indirett $alt
indolo $2
indomit $2
inedia $alt
inedit $2
@@ -2013,10 +2032,11 @@ lecit $1 $alt2
legatoria $4
legazia $3
legge $alt2
leggere $alt
leggi l'edZ:,i
lemn $alt
lemure $1 $alt
lemuri $1 $alt
lena $alt2
leo $alt2
leon $alt2
leonzi $alt
@@ -2076,7 +2096,7 @@ litania $3
litoraneo $3
lob $alt
lod $alt
lode $2 $alt
lode $alt
lodol $1
lodz $alt2
log $alt
@@ -2470,6 +2490,7 @@ nippur $2
niscemi $alt
niteroi $alt2
nocciol $alt
nocciola $2
nod $alt
noe $alt
noe $2
@@ -2569,7 +2590,6 @@ ongar $1
onicofori $3
ontogenesi $3
opac $2
oper $alt2
opistodom $3
oppi $alt
oppost $alt2
@@ -2577,6 +2597,7 @@ opprimente $alt
oraf $1
oramai $3
orbit $1
orca $alt2
orchidacee $3
orcia $alt2
ordin $1 $alt2
@@ -2617,13 +2638,15 @@ oscar $alt
osmi $alt
ospite $alt
osroe $1
ossa $alt2
osseo $1
ossequi $alt
osset $alt
ossia $2
ossidoreduttasi $1
osteogenesi $4
ostia $1
ostia $1
ostie $1
ostile $2
ostrogot $alt
ostrogoti $alt
@@ -2693,7 +2716,7 @@ paravia $3
parenchim $alt
parentesi $2 $alt
parere $2 $alt2
parestesie $4
// ò parestesie $4
parghelia $3
paria $2
parnassos $3
@@ -2740,6 +2763,7 @@ peloponnes $alt
pelosi $alt2
pelot $alt
pemfig $alt
pena $alt2
pend $alt2
pendi $2
pendol $alt
@@ -2757,6 +2781,7 @@ pentatl $alt
pentatl $1
pentatlet $alt
pentod $alt
peoni $1 $only
pepi $alt
pepoli $1 $alt
peptidi $alt
@@ -2779,7 +2804,6 @@ perimetr $2
period $2
peripl $1
peristasi $2
perle $2
perlomen $alt2
permafrost $1
permut $1
@@ -2797,22 +2821,24 @@ perun $2
pesc $alt
pesc $alt
pescasseroli $3
pesce $alt2
pesche $alt
peschici $alt
pesi $alt
pessim $alt
pest $alt2
peste $alt
petal $1 $alt
pett $alt
pettineo $2
pezz $alt
phon $alt
piacere $3 $alt2
piacere $2 $alt2
piaden $2
pianterren $alt2
piastrinopenia $6
piastrinopenia $5
piazzatorre $alt2
piazzol $3
piazzol $2
piccardia $3
piccolomini $3
picnic $2
@@ -2921,6 +2947,7 @@ ponce $alt
pontassieve $alt
pontefice $alt2
pontelandolf $alt
ponto $alt
pontremoli $2
pop $alt
pope $alt
@@ -3021,6 +3048,7 @@ prospett $alt
prostaferesi $3
prostat $1
prot $alt
protas $1
proteo $1 $alt
protesi $1
protett $alt
@@ -3086,6 +3114,8 @@ rapsod $2
rapsodia $3
rateo $1
razzia $2
re @-*'E $capital
re @-*e
rebbi $alt2
recapit $2
recared $alt
@@ -3109,6 +3139,7 @@ remot $alt
ren $alt2
rendin $1
rendit $1
rene $alt2
reni $alt2
reostat $2
res $alt2
@@ -3255,7 +3286,6 @@ samosat $2
samovar $3
sampeyre $2
sampierdaren $alt2
samurai $3
sandal $1
sande $2
sandia $2
@@ -3312,6 +3342,7 @@ sciovia $2
sclerodermia $4
scogli $alt
scol $alt2
scopa $alt2
scorci $alt2
scorciatoia $alt2
scordia $2
@@ -3377,6 +3408,7 @@ sepri $alt
sepsi $alt
sequals $2
sequani $1 $alt
sera $alt2
seren $alt2
seriol $2
serval $2
@@ -3635,6 +3667,7 @@ teck $alt
tecl $alt
tecnic $alt
tecnocrazia $4
teco $alt2
tedofor $2
teetet $alt
tegol $1
@@ -3960,6 +3993,8 @@ vetr $alt2
vezzen $1
viadott $alt2
vibrafon $2
vicari $2 $only
vicaria $2
video $1
videoclip $4
videotec $alt
@@ -4001,6 +4036,7 @@ voll $alt2
volsci $alt
voltametr $2
voltmetr $1
volto $alt2
voltri $alt2
volv $alt
vomer $1
@@ -4053,6 +4089,7 @@ zingari $1
zoccol $alt
zoe $alt
zon $alt
zone $alt2
zoofilia $4
zoppia $2
zoppol $alt

+ 83
- 31
dictsource/it_rules View File

@@ -31,12 +31,13 @@
@) a (ggine_ 'a

_) ae (r aE
// @) a (no_ =a //ByFilo, this seems to make it_listx longer
@) avano (_S5 'avano
a (tterA_ 'a
_) all' (P4t all
_) anch' (P5t ank
@) amo (L04_ 'amo
@) ander (L04_ 'andE@-*
ate (L04_ 'ate

.group à
à ''a
@@ -61,7 +62,8 @@
ci (A tS // or L01 ?
cci (A tS: // or L01 ?
@) co (lA_ =ko
_) c' (P2t tS

.group d
d d
dd d:
@@ -69,16 +71,15 @@

_) dall' (P5t dall
_) dell' (P5t dell
_) d' (P2t d
decider (L04 detS'ide@-*

.group e
e e
ei (K Ej
r) ei (_ 'ei
@C) e (_ e
@C) e (_S1q e // lookup it_list without suffix
@Ar) e (_ e

// ò @Ar) e (_ e
e (C_ E
e (A E
e (C%A_ E // doubled consonant
@@ -113,21 +114,23 @@
gg) e (ro_ E
f) e (rm e
@) e (rrimo_ 'E
@) e (simo_ 'e
@) e (simA_ 'e
h) e (ss e
m) e (ss e
_sC) e (ss e
e (ssa_ e
e (tr E
e (ti E

e (vi_ E
e (vo_ E
@) e (volA_ 'e
e (zA E
CC) eggia (no_ 'EdZ:a
C) ender (L04_ 'ende@-*
C) erder (L04_ 'E@-*de@-*
esser (L04_ 'es:eR
_) ecco (L04 'Ek:o
ete (L04_ 'ete

.group f
f f
@@ -143,20 +146,22 @@
gi (A dZ // any vowel, or L01 ?
gi (a_ dZ'i# // [i] only if stressed
gì (a_ dZ'i# // [i] only if stressed
lo) gi (e_ dZ'i#
n) gi (a_ dZ
gg (Y dZ:
ggi (A dZ: // or L01 ?
@) gger (lo_ =dZ:eR
@) gger (L04_ =dZ:e@-*
gl (i l^
gl (ì l^
gli (A l^
_) gl gl
@) glier (L04_ =l^E@-*
@) guer (L04_ =gUe@-*
gn n^
@) gn (A_ n^;
a) gn (A_ n^:
gu (A gw

.group h
h
_) ha h'a
@@ -167,8 +172,6 @@
i (A j
l) i (A %i
r) i (A %i
_C) i (a i
_C) i (à i
_C) ie (_ 'ie
i (o i
i (ò i
@@ -186,6 +189,7 @@
metr) ia (_ 'ia
metr) ie (_ 'ie
t) ia (_ 'ia
t) ie (_ 'ie
@) io (_S1q =i%o
a) i (+ j
à) i (+ j
@@ -199,13 +203,13 @@
i (asi_ 'i
@) i (bile_ 'i
@) i (cA_ =i
tr) i (ce_ i
tr) i (cY_ i
@) i (chA_ =i
@) i (dA_ =i
@) i (dere_ 'i
@) ie (rA_ i'E
@) ié (rA_ i'E
@) iè (rA_ i'E
// [ @) iè (rA_ i'E
@) i (gA_ =i
i (genA_ 'i
c) i (lA_ =i
@@ -227,6 +231,7 @@
p) i (te_ =i
@) iono (_ =iono
issano (_ 'is:ano
ite (L04_ 'ite

.group j

@@ -243,8 +248,8 @@
ll (C l_
ll (_ l
_) l' (P2t l
A) l (bA l:
A) l (bA l:
A) l (vA l:

.group m
m m
@@ -259,6 +264,7 @@
n (k N
_) nell' (P5t nell
ndo (L04_ =ndo // for pronominal verbs
_zA) nz (A n|dz

.group o
o o
@@ -316,7 +322,7 @@
o (polA_ 'O
sc) o (p O
o (r O
o (re_ o
o (rY_ o
f) o (rmA_ o
o (si_ O
o (ss O
@@ -326,7 +332,7 @@
o (ttol O
o (zA O
osano (_ 'ozano
C) onder (L04_ 'ondE@-*
.group p
p p
pp p:
@@ -348,6 +354,9 @@
rr R*
A) r (A R
@) r (L04_ =@-* // for Italian pronominal verbs and reflexive verbs
C) rai (_ @-*'aI
A) rai (_ R'aI
rrai (_ R*'aI

.group s
s s
@@ -374,11 +383,13 @@
sh (K S // foreign words
K) sh S // foreign words
A) sh (A S
@) sia z'ia
@) sia (_ z'i#a
@) sie (_ z'i#e
@C) sia s'ia
@) sià zi'a
@) s (_S1 s
_) sull' (P5t sull
_) sotto (P5t sot:o
scriver (L04_ sk@-*'iv%E@-*

.group t
@@ -415,23 +426,66 @@
.group y
y j
y (K i // foreign words

.group z
z ts
A) zz ts:
A) z (A ts
_) z (AC |dz|
_) z (i dz
_) z (ì dz
A) zz (A ts:
_A) z (A dz
_) z (AC dz
_) z (Y dz
z (L01A dz
_A) zz (A |dz:
@li) zz (A dz:
@) zz (ano_ =ts:
ziono (_ tsi'Ono
i) zza (no_ =dz:a
@@) zza (L04_ =dz:a
@) zza (ti_ dz:'a
zion (A_ tsi'On

.group 0xce // Greek letters
// 0xce is the first byte of the utf-8 code for these characters

α 'alfa_
ά 'alfa_
β b'eta_
γ g'am:a_
δ d'Elta_
ε 'EpsIlon
έ 'EpsIlon_
ζ dz'eta||g@-*'eka
η 'e:ta||g@-*'eka
ή 'e:ta||g@-*'eka_
θ t'e:ta||g@-*'eka_
ι I'ota_
ί I'ota_
κ k'ap:a||g@-*'eka_
λ l'ambda_
μ m'ju:_
ν n'ju:_
ξ ks'I||g@-*'eka_
ο 'omIk@-*on_

.group 0xcf // Greek letters

π p'I||g@-*'eka_
ρ @-*'O||g@-*'eka_
σ s'Igma_
ς s'Igma_
τ t'au_
υ 'IpsIlon_
ύ 'IpsIlon_
φ f'I||g@-*'eka_
χ k'I||g@-*'eka_
ψ ps'I||g@-*'eka_
ω om'ega_
ώ om'ega_
ό 'omIk@-*on_

.group

gn n^
ñ n^
_L16_) : (_L17D_ ||%E_|| // Say time
_L16_) : (_L17D_ _%%E_ // Say time

è ''E
èi (K ''Ej
@@ -448,17 +502,15 @@ _L16_) : (_L17D_ ||%E_|| // Say time

ù ''u

$ dollaro
$ d'ollaRo
, (D v'irgola
! _p'untoesklamat'ivo_
!) !
? _p'untointeRogat'ivo_
?) ?

__) - (_D meno
A_) - (_D _
C_) - (_D _

§ setsi'one

+ 3
- 2
dictsource/pt_rules View File

@@ -996,11 +996,12 @@ _pormen) o (L05_ O
ese) qu (ív kw
_e) qu (in kw
fre) qu (ent kw
li) qu (id kw
lí) qu (id kw
?2 li) qu (id kw
?2 lí) qu (id kw
lo) qu (en kw
n) qu (en kw
_) qu (inqu kw
_se) qu (el kw
se) qu (en kw
tran) qu (il kw
?1 queç kes // esqueça.

+ 18
- 3
dictsource/ta_list View File

@@ -112,6 +112,22 @@ U+bf9 ru:ba:j
¼ ka:l
½ araI
¾ mukka:l
® pVdivU
© p'VdippUrimaI
• t'o:t.t.a:
… v'id.UnilaI
¡ t'VlaIki:z.||v'ijVppU
¿ t'VlaIki:z.||k'e:l.vi
× d'Vd.VvaI
± k'u:t.t.Vl||k'Vz.ittVl
™ v'Vn.igVm
§ p'irivU
➔ v'VlVdVmbU
→ v'VlVdVmbU
■ k'VrUn^dZVdU*Vm
● v'Vt.t.Vm

_sup m'e:lez.UttU

// alphabet names
_ar arVbU
@@ -215,7 +231,7 @@ _5o aInd
_6o a:R
_7o ;e:z.
_8o ;et.t.
_9o onbVd.
_9o onbVd
_10o patt
_11o patinonR
_12o pVnnirVn.d.
@@ -278,7 +294,6 @@ tamil தமிழ் $text
பண்தம் $alt
பவனி $alt
பாபா $alt
பாதாம் $alt
போகம் $alt
போதனை $alt
பூகம்பம் $alt
@@ -504,7 +519,6 @@ tamil தமிழ் $text
காந்தி $alt
கிரி $alt
கயா $alt
காயத்ரி $alt
கட $alt
கதி $alt
கோபி $alt
@@ -587,3 +601,4 @@ tamil தமிழ் $text
புட் fud.
உப்ப ubbV
ஜென் zen


+ 80
- 6
dictsource/ta_rules View File

@@ -66,8 +66,8 @@
// i or i:
.L08 ி ீ

// n or n
.L09 ந ன
// n or n or n.
.L09 ந ன

// l or l.
.L10 ல ள
@@ -76,7 +76,7 @@
.L11 ப த க

// words before "bottle"
.L12 பீர் கலர் சாராய சோடா தண்ணி தண்ணீர் பிராந்தி வாட்டர் விஸ்கி பிளாஸ்டிக் ப்ளாஸ்டிக் கண்ணாடி கிளாஸ் க்ளாஸ் மது மருந்து ஊறுகா ஊறுகாய்
.L12 பீர் கலர் சாராய சோடா தண்ணி தண்ணீர் பிராந்தி வாட்டர் விஸ்கி பிளாஸ்டிக் ப்ளாஸ்டிக் கண்ணாடி கிளாஸ் க்ளாஸ் மது மருந்து ஊறுகா ஊறுகாய் குடிநீர்

// words after "booga"
.L13 வாழ்க்கை பூமி விருந்த மனிதன
@@ -619,9 +619,16 @@ _மன்மதக்) க (ுகை g
_) க் (ளாஸ்_ g
_) க்வ (A kw
_) க் (வாலியர g
_) க (னஜோர gV
_) க (ோரத்தாண்டவ g
_) காஜ (ியாபாத ga:z
_) க (ிலானி g
_) க (ாயத்ரி g
//endsort

//sort
_தலை) க (ீழ் g
_காட்டுமன்னார்) க (ோயில k
_கோபி) க kV#
_ஸ்டா) க kV#
_ஜமாய்) க kV#
@@ -1384,6 +1391,11 @@ _வெனி) ச (ுவேல z
_) ச (ௌஹான tS
_ந) ச் (னு tS
_கா) ச்மூச tSmu:tSV#
_) ச (ிட்டகாங் tS
_) ச (ெப்பல tS
_) சாருக (ேசி tSa:rUk
அஜாத) ச (த்துரு tSV
இமா) ச (ல tSV
//endsort


@@ -1409,7 +1421,7 @@ _வெனி) ச (ுவேல z
_ப) ஜ (ார z
அ) ஜ (ாருதீன z
_நா) ஜ (ி z
_) ஜ (ிந்தாபாத z
_) ஜிந்தாப (ாத zinda:b
_) ஜிப்(_ zip
_) ஜ (ிப்ப z
_) ஜ (ிப்பா dZ
@@ -1438,7 +1450,7 @@ _வெனி) ச (ுவேல z
_வி) ஞ்ச் ntS
_ப) ஞ்ச (ர ntSV
_ல) ஞ்ச (B ntS
_ம) ஞ்ச (ூரிய ntS

.group ட
ட d.V
@@ -1533,7 +1545,6 @@ _ஷிஃப்) ட t.V#
_) ட (ான்ஜானிய t.
_) டாபிக் t.a:pik
_) டாப் t.a:p
_) ட (ாமி t.
_) டாய்லட் t.a:jlVt.
_) டாய்லெட் t.a:jlet.
_) ட (ார்ச்சர t.
@@ -1828,6 +1839,8 @@ _நடுரோ) ட் (ல t.
அ) ட்லாண்ட t.la:n.t.V# // atlant
_) ட்விங்க (ிள t.wiNk
_) ட்வ (ிட்டர t.w
_) ட (ாமிய t.
_) ட (ாமி_ t.
//endsort


@@ -2253,9 +2266,21 @@ _) தீர்க்க (_சுமங்கலி di:rggV
_) த (ோஹா d
_) தௌலதாப (ாத daUlVd.a:b
_) த (்ராட்சை d
_) தர்ப்ப (த்த dVrbbV
_) த (ாதர d
_) த (டிக்கின dV
_) த (டிக்கிற dV
_) த (ன்வந்திரி dV
_) த (ேவ்டியா t
//endsort

//sort
_ஆஸ்) தி (ர t
_கபூர்) த (லா tV
அகர்) த (லா tV
_ரஞ்சி) த (ா t
_லி) த (ிய t
அஜா) தச (த்ரு tVtSV
_நிசப்) த dV#
அனந்) த tV#
_வசந்) த tV#
@@ -3245,6 +3270,8 @@ _விளையாடு_) ப (ாம்பே p
_) பி (ரியம p
_) பி (ரியர p
_) பி (ரியா_ p
_) பி (ரியா_விடை pi
இணைப்_) பி (ரியா_ pi
_) ப (ிரியாணி b
_) பி (ரியாமணி p
_) பி (ரியாவிடம p
@@ -3699,9 +3726,52 @@ _பெனசீர்_) ப (ுட்டோ b
_) ப் (ளூஸ b
_) ப் (ளோரிடா f
_) ப் (ளௌஸ b
_) ப் (ரெஸ்ட b
_) ப (லமோ bV
_) ப (ோட்ஸ்வான b
_) பூப (ால bu:p
_) ப (ாதிப்புற b
_) ப (ந்திப்பூர bV
_) ப (ண்டிப்பூர bV
_) ப (ாஸ்டர்ட b
_) ப (லமடைய bV
_) ப (லமடைந்த bV
_) பாப (ாக்கள ba:b
_) ப (லமிருக்க bV
_) ப (ாலயோக b
_) ப (ௌண்டரி b
_) ப (வுண்டரி bV
_) ப (ிக்ஷ b
_) ப (ுல்_ஷிட் b
_) ப (ாதாம b
//endsort

//sort
_) ப் (ளோர f
_) பு (ளோர f
_) பயர்ப (ாக்ஸ fVjVrf
_லை) ப் (_ f
_லை) ப் (ல f
_சிம்) ப (னி fV
_வடை) ப்பி (ரிய pp
இசை) ப்பி (ரிய pp
_கம்) ப (ூச்சிய p
_பகு) ப (த bV
_வாஜ்) ப (ாய p
_லி) ப (ி_ p
_லி) ப (ியை p
_லி) ப (ியு p
_லி) ப (ியி p
அ) ப் (ரோ p
_நுண்) ப (ுல p
_வால்) ப (ாறை p
_மீள்) ப (ார p
_சாஹி) ப்ப bbV#
_சாகி) ப்ப bbV#
_நற்) ப (ூமி b
_முழு) ப்ப (ல bb
_மன) ப்ப (ிம்ப bb
_மர) ப்ப (ொம்மை bb
_நீர்) ப pV#
_ப்ரூ) ப fV#
இடர்) ப pV#
@@ -4548,6 +4618,10 @@ _சந்தேக) ப்ப (ுத்தி bb
அரி) ஸ (ோன z
_சூய) ஸ zV#
_ஹி) ஸ்ப (ுல்லா zb
_மி) ஸ (ோரம z
_மி) ஸாப (ர்பூர za:fV
_மி) ஸ (ாஃபர்பூர z


.group ஹ
ஹ HV

+ 3
- 1
espeak-data/voices/europe/it View File

@@ -1,6 +1,8 @@
name italian
language it
gender male

replace 03 i I
tunes s4 c4 q4 e4

replace 03 i I

+ 1
- 1
phsource/ph_english_us View File

@@ -361,7 +361,7 @@ phoneme t

IF nextPhW(isVowel) AND nextPh(isUnstressed) THEN
IF NOT next2PhW(n) OR nextPhW(3:) THEN
IF prevPhW(isVowel) AND NOT prevPhW(aI@) THEN
IF prevPhW(isVowel) THEN
ChangePhoneme(t#)
ELIF prevPhW(n) THEN
WAV(ustop/t, 60)

+ 15
- 0
phsource/ph_gujarati View File

@@ -9,6 +9,14 @@ phoneme aI
FMT(vdiph/@i_4)
endphoneme

phoneme aI~
vowel long starttype #@ endtype #i
length 270
long
FMT(vnasal/ai_n)
endphoneme


phoneme aU
vowel long starttype #a endtype #u
length 240
@@ -16,4 +24,11 @@ phoneme aU
FMT(vdiph/a#u)
endphoneme

phoneme aU~
vowel long starttype #a endtype #u
length 300
long
FMT(vnasal/au_n)
endphoneme



+ 26
- 15
phsource/ph_italian View File

@@ -1,4 +1,3 @@

//====================================================
// Italian
//====================================================
@@ -11,7 +10,7 @@ endphoneme

phoneme a
vowel starttype #a endtype #a
length 180
length 160
ChangeIfNotStressed(a/)
FMT(vowel/a)
endphoneme
@@ -19,7 +18,7 @@ endphoneme

phoneme a/
vowel starttype #@ endtype #@
length 180
length 140
IF thisPh(isWordEnd) THEN
FMT(vowel/a#_4)
ENDIF
@@ -29,14 +28,14 @@ endphoneme

phoneme e
vowel starttype #e endtype #e
length 170
length 150
ChangeIfNotStressed(e/)
FMT(vowel/e_2)
endphoneme

phoneme e/
vowel starttype #e endtype #e
length 170
length 140
IF nextPhW(isNasal) OR nextPhW(isLiquid) THEN
FMT(vowel/e_mid2)
ELSE
@@ -48,7 +47,7 @@ endphoneme

phoneme E
vowel starttype #e endtype #e
length 170
length 145
ChangeIfUnstressed(e/) // [E] only in stressed syllables ?
FMT(vowel/e_mid)
endphoneme
@@ -64,7 +63,7 @@ endphoneme

phoneme i# // Used for 'gia_' where [i] is only spoken if stressed
vowel starttype #i endtype #i
length 140
length 145
ChangeIfNotStressed(NULL)
ChangePhoneme(i)
endphoneme
@@ -72,7 +71,7 @@ endphoneme

phoneme I
vowel starttype #i endtype #i
length 150
length 140
IfNextVowelAppend(;)
FMT(vowel/i_4)
endphoneme
@@ -81,14 +80,14 @@ endphoneme

phoneme o
vowel starttype #o endtype #o
length 170
length 150
ChangeIfNotStressed(o/)
FMT(vowel/o)
endphoneme

phoneme o/
vowel starttype #o endtype #o
length 170
length 140
IF nextPhW(isNasal) OR nextPhW(isLiquid) THEN
FMT(vowel/oo_1)
ELSE
@@ -99,7 +98,7 @@ endphoneme

phoneme O
vowel starttype #o endtype #o
length 170
length 150
ChangeIfUnstressed(o/) // [O] only in stressed syllables ?
FMT(vowel/oo_4)
endphoneme
@@ -107,21 +106,21 @@ endphoneme

phoneme u
vowel starttype #u endtype #u
length 160
length 150
ChangeIfNotStressed(U)
FMT(vowel/u_bck)
endphoneme

phoneme U
vowel starttype #u endtype #u
length 160
length 140
FMT(vowel/u_bck)
endphoneme


phoneme aU
vowel starttype #a endtype #o
length 270
length 300
FMT(vdiph/aoo)
endphoneme

@@ -147,5 +146,17 @@ endphoneme

phoneme l^
import_phoneme base/l^
Length 140
Length 130
endphoneme

phoneme ts
import_phoneme consonants/ts
voicingswitch ts
endphoneme

phoneme dz
import_phoneme consonants/dz
voicingswitch z
lengthmod 3
endphoneme


BIN
phsource/vnasal/ai_n View File


BIN
phsource/vnasal/au_n View File


+ 1
- 1
src/compiledict.cpp View File

@@ -1932,7 +1932,7 @@ int CompileDictionary(const char *dsource, const char *dict_name, FILE *log, cha
if((f_out = fopen_log(fname_out,"wb+")) == NULL)
{
if(fname_err)
strcpy(fname_err,fname_in);
strcpy(fname_err,fname_out);
return(-1);
}
sprintf(fname_temp,"%s%ctemp",path_home,PATHSEP);

+ 7
- 0
src/dictionary.cpp View File

@@ -905,6 +905,7 @@ int Unpronouncable(Translator *tr, char *word, int posn)
int vowel_posn=9;
int index;
int count;
ALPHABET *alphabet;

utf8_in(&c,word);
if((tr->letter_bits_offset > 0) && (c < 0x241))
@@ -913,6 +914,12 @@ int Unpronouncable(Translator *tr, char *word, int posn)
return(0); // so we can re-translate the word as English
}

if(((alphabet = AlphabetFromChar(c)) != NULL) && (alphabet->offset != tr->letter_bits_offset))
{
// Character is not in our alphabet
return(0);
}

if(tr->langopts.param[LOPT_UNPRONOUNCABLE] == 1)
return(0);


+ 35
- 21
src/numbers.cpp View File

@@ -676,6 +676,25 @@ static unsigned short derived_letters[] = {

static const char *hex_letters[] = {"'e:j","b'i:","s'i:","d'i:","'i:","'ef"}; // names, using phonemes available to all languages


int IsSuperscript(int letter)
{//===========================
// is this a subscript or superscript letter ?
int ix;
int c;

for(ix=0; (c = derived_letters[ix]) != 0; ix+=2)
{
if(c > letter)
break;
if(c == letter)
return(derived_letters[ix+1]);
}
return(0);
}



int TranslateLetter(Translator *tr, char *word, char *phonemes, int control)
{//=========================================================================
// get pronunciation for an isolated letter
@@ -732,30 +751,25 @@ int TranslateLetter(Translator *tr, char *word, char *phonemes, int control)
if(ph_buf[0] == 0)
{
// is this a subscript or superscript letter ?
for(ix=0; (c = derived_letters[ix]) != 0; ix+=2)
if((c = IsSuperscript(letter)) != 0)
{
if(c > letter)
break;
if(c == letter)
letter = c & 0x3fff;
if((control & 4 ) && ((modifier = modifiers[c >> 14]) != NULL))
{
c = derived_letters[ix+1];
letter = c & 0x3fff;
if((modifier = modifiers[c >> 14]) != NULL)
// don't say "superscript" during normal text reading
Lookup(tr, modifier, capital);
if(capital[0] == 0)
{
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[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;
}
capital[0] = phonPAUSE;
capital[1] = phonSWITCH;
len = strlen(&capital[3]);
capital[len+3] = phonSWITCH;
capital[len+4] = phontab_1;
capital[len+5] = 0;
}
}
}
@@ -1209,7 +1223,7 @@ int TranslateRoman(Translator *tr, char *word, char *ph_out, WORD_TAB *wtab)
p = &ph_out[strlen(ph_roman)];
}

sprintf(number_chars," %d ",acc);
sprintf(number_chars," %d %s ",acc, tr->langopts.roman_suffix);

if(word[0] == '.')
{

+ 1
- 1
src/synthdata.cpp View File

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

const char *version_string = "1.47.14 29.Nov.13";
const char *version_string = "1.47.15 22.Dec.13";
const int version_phdata = 0x014709;

int option_device_number = -1;

+ 18
- 10
src/tr_languages.cpp View File

@@ -193,10 +193,13 @@ static const unsigned short chars_ignore_default[] = {
// alternatively, ignore characters but allow zero-width-non-joiner (lang-fa)
static const unsigned short chars_ignore_zwnj_hyphen[] = {
0xad, 1, // soft hyphen
0x640, 1, // igniore Arabic Tatweel (lang=FA)
0x200c, '-', // zero width non-joiner, replace with hyphen
0x200d, 1, // zero width joiner
0, 0 };

const char string_ordinal[] = {0xc2,0xba,0}; // masculine ordinal character, UTF-8


static Translator* NewTranslator(void)
{//===================================
@@ -293,6 +296,7 @@ static const char transpose_map_latin[] = {
tr->langopts.replace_chars = NULL;
tr->langopts.ascii_language[0] = 0; // Non-Latin alphabet languages, use this language to speak Latin words, default is English
tr->langopts.alt_alphabet_lang = L('e','n');
tr->langopts.roman_suffix = "";

SetLengthMods(tr,201);
// tr->langopts.length_mods = length_mods_en;
@@ -752,7 +756,9 @@ Translator *SelectTranslator(const char *name)
if(name2 == L('a','n'))
{
tr->langopts.stress_flags = S_FINAL_SPANISH | S_FINAL_DIM_ONLY | S_FINAL_NO_2;
tr->langopts.numbers = NUM_SINGLE_STRESS | NUM_DECIMAL_COMMA | NUM_AND_UNITS | NUM_OMIT_1_HUNDRED | NUM_OMIT_1_THOUSAND | NUM_ROMAN | NUM_ROMAN_ORDINAL;
tr->langopts.numbers2 = NUM2_ORDINAL_NO_AND;
tr->langopts.roman_suffix = string_ordinal;
}
else
if(name2 == L_pap)
@@ -1657,21 +1663,23 @@ SetLengthMods(tr,3); // all equal

tr->translator_name = name2;

if(tr->langopts.numbers & NUM_DECIMAL_COMMA)
return(tr);
} // end of SelectTranslator


void ProcessLanguageOptions(LANGUAGE_OPTIONS *langopts)
{//=====================================================
if(langopts->numbers & NUM_DECIMAL_COMMA)
{
// use . and ; for thousands and decimal separators
tr->langopts.thousands_sep = '.';
tr->langopts.decimal_sep = ',';
langopts->thousands_sep = '.';
langopts->decimal_sep = ',';
}
if(tr->langopts.numbers & NUM_THOUS_SPACE)
if(langopts->numbers & NUM_THOUS_SPACE)
{
tr->langopts.thousands_sep = 0; // don't allow thousands separator, except space
langopts->thousands_sep = 0; // don't allow thousands separator, except space
}

return(tr);
} // end of SelectTranslator


}

//**********************************************************************************************************


+ 2
- 2
src/translate.cpp View File

@@ -1180,9 +1180,9 @@ if(end_type & SUFX_UNPRON)
{
int wc;
// characters not recognised, speak them individually
// ?? should we say super/sub-script numbers and letters here?
utf8_in(&wc, wordx);
if((word_length == 1) && IsAlpha(wc))
if((word_length == 1) && (IsAlpha(wc) || IsSuperscript(wc)))
{
if((wordx = SpeakIndividualLetters(tr, wordx, phonemes, spell_word)) == NULL)
{

+ 3
- 0
src/translate.h View File

@@ -533,6 +533,7 @@ typedef struct {
int decimal_sep;
int max_digits; // max number of digits which can be spoken as an integer number (rather than individual digits)
const char *ordinal_indicator; // UTF-8 string
const char *roman_suffix; // add this (ordinal) suffix to Roman numbers (LANG=an)

// bit 0, accent name before the letter name, bit 1 "capital" after letter name
int accents;
@@ -722,6 +723,7 @@ int IsDigit(unsigned int c);
int IsDigit09(unsigned int c);
int IsAlpha(unsigned int c);
int IsVowel(Translator *tr, int c);
int IsSuperscript(int letter);
int iswalpha2(int c);
int isspace2(unsigned int c);
int iswlower2(int c);
@@ -736,6 +738,7 @@ ALPHABET *AlphabetFromName(const char *name);
Translator *SelectTranslator(const char *name);
int SetTranslator2(const char *name);
void DeleteTranslator(Translator *tr);
void ProcessLanguageOptions(LANGUAGE_OPTIONS *langopts);
int Lookup(Translator *tr, const char *word, char *ph_out);
int LookupFlags(Translator *tr, const char *word);


+ 1
- 0
src/voices.cpp View File

@@ -881,6 +881,7 @@ voice_t *LoadVoice(const char *vname, int control)
}
while(isalnum(*p)) p++;
}
ProcessLanguageOptions(langopts);
break;

case V_REPLACE:

Loading…
Cancel
Save