scriptshifter/legacy/data/SlavonicRomanization.cfg

# Original table by Randall K. Barry, 22 February 2021

[General]
Name=Slavonic

# UNICODE CYRILLIC CHARACTER RANGE: U+0400-U+04FF

[RomanToScript]
FieldsIncluded=100 110 111 130 240 241 243 245 246 247 250 260 264 440 490 600 610 611 630 651 700 710 711 730 740 800 830
SubfieldsAlwaysExcluded=uvxy0123456789
OtherSubfieldsExcludedByTag=100/e 110/e 111/j 240/k 240/l 240/s 246/i 260/c 264/c 650/a 700/e 700/i 710/e 710/i 711/i 711/j 730/i

# RDA boilerplate phrases not transliterated:
Place of publication not identified=Place of publication not identified
publisher not identified=publisher not identified
date of publication not identified=date of publication not identified
At head of title=At head of title
Colophon=Colophon

# COMMON COMBINING CHARACTERS (always follow a base letter): 

# combining grave U+0300
# combining acute U+0301
# combining circumflex U+0302
# combining macron U+0304
# combining breve U+0306
# combining dot above U+0307
# combining diaeresis U+0308
# combining ring above U+030A
# combining double acute U+030B
# combining caron (hachek) U+030C
# combining candrabindu U+0310
# combining dot below U+0323
# combining comma below U+0326 (Romanian, Latvian, Livonian)
# combining cedilla U+0327 (French, Turkish, Azeri)
# combining ogonek (hook) U+0328 (Polish, Lithuanian)
# combining left ligature U+FE20 (Cyrillic transliteration)
# combining right ligature U+FE21 (Cyrillic transliteration)
# soft sign/prime (spacing) U+02B9(Cyrillic transliteration)
# hard sign/double prime (spacing) U+02BA (Cyrillic transliteration)
# ayn(spacing) U+02BB (Semitic and Caucasian languages)
# alif (spacing) U+02BC (Semitic languages)
# middle dot (space) U+00B7) (Catalan)

# REGULAR LATIN ALPHABETIC CHARACTERS TO BE CONVERTED

# CONVERSION OF "I/i" LIGATED TO "A/a" (all capitalization patterns)
IU+FE20AU+FE21=U+042F
IU+FE20aU+FE21=U+042F
iU+FE20aU+FE21=U+044F
iU+FE20AU+FE21=U+044F


# REMAINING LONE "A/a"
A=U+0410
a=U+0430

B=U+0411
b=U+0431

VU+0307=U+0474
vU+0307=U+0475
V=U+0412
v=U+0432

GU+0301=U+0494
gU+0301=U+0495
G=U+0413
g=U+0433

D=U+0414
d=U+0434

# CONVERION OF "I/i" LIGATED TO "E/e", SOME WITH MACRON (0304) AND OGONEK (0328)
IU+FE20EU+FE21U+0304=U+0464
IU+FE20EU+0304U+FE21=U+0464
IU+FE20eU+FE21U+0304=U+0464
IU+FE20eU+0304U+FE21=U+0464
IU+FE20EU+FE21U+0328=U+0468
IU+FE20EU+0328U+FE21=U+0468
IU+FE20eU+FE21U+0328=U+0468
IU+FE20eU+0328U+FE21=U+0468
iU+FE20eU+FE21U+0304=U+0465
iU+FE20eU+0304U+FE21=U+0465
iU+FE20EU+FE21U+0304=U+0465
iU+FE20EU+0304U+FE21=U+0465
iU+FE20eU+FE21U+0328=U+0469
iU+FE20eU+0328U+FE21=U+0469
iU+FE20EU+FE21U+0328=U+0469
iU+FE20EU+0328U+FE21=U+0469
IU+FE20EU+FE21=U+0462
IU+FE20eU+FE21=U+0462
iU+FE20eU+FE21=U+0463
iU+FE20EU+FE21=U+0463

# CONVERSION OF "E/e" WITH MACRON (0304), DOT ABOVE (0307), DIAERESIS (0308), OGONEK (0328), & CARON (030C)
EU+030C=U+0462
EU+0304=U+0404
EU+0307=U+042D
EU+0308=U+0401
EU+0328=U+0466
eU+030C=U+0463
eU+0304=U+0454
eU+0307=U+044D
eU+0308=U+0451
eU+0328=U+0467

# CONVERSION OF REMAINING LONE "E/e"
E=U+0415
e=U+0435

ZH=U+0416
Zh=U+0416
zH=U+0436
zh=U+0436

Z=U+0417
z=U+0437

# CONVERION OF "I/i" LIGATED TO "O/o" WITH MACRON (0304) AND OGONEK (0328)
IU+FE20OU+FE21U+0328=U+046C
IU+FE20OU+0328U+FE21=U+046C
IU+FE20oU+FE21U+0328=U+046C
IU+FE20oU+0328U+FE21=U+046C
iU+FE20oU+FE21U+0328=U+046D
iU+FE20oU+0328U+FE21=U+046D
iU+FE20OU+FE21U+0328=U+046D
iU+FE20OU+0328U+FE21=U+046D


# CONVERION OF "I/i" LIGATED TO "U/u"
IU+FE20UU+FE21=U+042E
IU+FE20uU+FE21=U+042E
iU+FE20uU+FE21=U+044E
iU+FE20UU+FE21=U+044E


# CONVERSION OF "I/i" WITH MACRON (0304) AND BREVE (0306)
IU+0304=U+0406
IU+0306=U+0419
iU+0304=U+0456
iU+0306=U+0439

# CONVERSION OF REMAINING LONE "I/i"
I=U+0418
i=U+0438

KH=U+0425
Kh=U+0425
kh=U+0445
kH=U+0445

KU+FE20SU+FE21=U+046E
KU+FE20sU+FE21=U+046E
kU+FE20sU+FE21=U+046F
kU+FE20SU+FE21=U+046F
K=U+041A
k=U+043A

L=U+041B
l=U+043B
M=U+041C
m=U+043C
N=U+041D
n=U+043D

# CONVERION OF "O/o" WITH OR WITHOUT MACRON (0304), LIGATED TO "T/t"
OU+0304U+FE20TU+FE21=U+047E
OU+0304U+FE20tU+FE21=U+047E
OU+FE20U+0304TU+FE21=U+047E
OU+FE20U+0304tU+FE21=U+047E
OU+FE20TU+FE21=U+047E
OU+FE20tU+FE21=U+047E
oU+0304U+FE20tU+FE21=U+047F
oU+0304U+FE20TU+FE21=U+047F
oU+FE20U+0304tU+FE21=U+047F
oU+FE20U+0304TU+FE21=U+047F
oU+FE20tU+FE21=U+047F
oU+FE20TU+FE21=U+047F


# CONVERSION OF "O/o" WITH MACRON(0304) AND OGONEK (0328)
OU+0328=U+046A
oU+0328=U+046B
OU+0304=U+0460
oU+0304=U+0461

# CONVERSION OF REMAINING LONE "O/o"
O=U+041E
o=U+043E

PU+FE20SU+FE21=U+0470
PU+FE20sU+FE21=U+0470
pU+FE20sU+FE21=U+0471
pU+FE20SU+FE21=U+0471
P=U+041F
p=U+043F

R=U+0420
r=U+0440

SHT=U+0429
SHt=U+0429
Sht=U+0429
sHT=U+0449
shT=U+0449
sht=U+0449

SH=U+0428
Sh=U+0428
sh=U+0448
sH=U+0448

TU+FE20SU+FE21=U+0426
TU+FE20sU+FE21=U+0426
tU+FE20sU+FE21=U+0446
tU+FE20SU+FE21=U+0446

S=U+0421
s=U+0441

T=U+0422
t=U+0442

UU+0304=U+0478
uU+0304=U+0479
U=U+0423
u=U+0443

FU+0307=U+0472
fU+0307=U+0473
F=U+0424
f=U+0444

CH=U+0427
Ch=U+0427
ch=U+0447
cH=U+0447

YU+0307=U+0476
yU+0307=U+0477
Y=U+042B
y=U+044B

# this conversion shouldn't be needed, but does no harm
U+FE20=
# this conversion shouldn't be needed, but does no harm
U+FE21=
# this conversion is ambiguous - U+042C is also theoretically possible
U+0027=U+044C
# this conversion is ambiguous - U+042C is also theoretically possible
U+02B9=U+044C
# this conversion is ambiguous - U+044C is also theoretically possible
U+02BA=U+044A

[ScriptToRoman]
FieldsIncluded=100 110 111 130 240 241 242 243 245 246 250 260 264 440 490 600 610 611 630 651 700 710 711 730 740 800 830
SubfieldsAlwaysExcluded=uvxy0123456789
OtherSubfieldsExcludedByTag=100/e 110/e 111/j 240/k 240/l 240/s 246/i 260/c 264/c 650/a 700/e 700/i 710/e 710/i 711/i 711/j 730/i

# RDA boilerplate phrases not transliterated:
Place of publication not identified=Place of publication not identified
publisher not identified=publisher not identified

# CYRILLIC SCRIPT ALPHABETIC CHARACTERS TO BE CONVERTED

# CONVERSION TO "I/i" LIGATED TO "A/a"
U+042F=IU+FE20AU+FE21
U+044F=iU+FE20aU+FE21
U+0410=A
U+0430=a
U+0411=B
U+0431=b
U+0474=VU+0307
U+0475=vU+0307
U+0412=V
U+0432=v
U+0494=GU+0301
U+0495=gU+0301
U+0413=G
U+0433=g
U+0414=D
U+0434=d
# CONVERION TO "I/i" LIGATED TO "E/e" WITH DIACRITICS
U+0464=IU+FE20EU+FE21U+0304
U+0468=IU+FE20EU+FE21U+0328
U+0465=iU+FE20eU+FE21U+0304
U+0469=iU+FE20eU+FE21U+0328
# CONVERSION TO "E/e" WITH MACRON (0304), DOT ABOVE (0307), DIAERESIS (0308), OGONEK (0328), & CARON (030C)
U+0462=EU+030C
U+0404=EU+0304
U+042D=EU+0307
U+0401=EU+0308
U+0466=EU+0328
U+0463=eU+030C
U+0454=eU+0304
U+044D=eU+0307
U+0451=eU+0308
U+0467=eU+0328
U+0415=E
U+0435=e
U+0416=Zh
U+0436=zh
U+0417=Z
U+0437=z
# CONVERION T0 "I/i" LIGATED TO "O/o" WITH MACRON (0304) AND OGONEK (0328)
U+046C=IU+FE20OU+FE21U+0328
U+046D=iU+FE20oU+FE21U+0328
# CONVERION TO "I/i" LIGATED TO "U/u"
U+042E=IU+FE20UU+FE21
U+044E=iU+FE20uU+FE21
# CONVERSION TO "I/i" WITH MACRON (0304) AND BREVE (0306)
U+0406=IU+0304
U+0419=IU+0306
U+0456=iU+0304
U+0439=iU+0306
# CONVERSION TO LONE "I/i"
U+0418=I
U+0438=i
U+0425=Kh
U+0445=kh
U+046E=KU+FE20SU+FE21
U+046F=kU+FE20sU+FE21
U+041A=K
U+043A=k
U+041B=L
U+043B=l
U+041C=M
U+043C=m
U+041D=N
U+043D=n
# CONVERION TO "O/o" WITH MACRON (0304) LIGATED TO "T/t"
U+047E=OU+FE20U+0304tU+FE21
U+047F=oU+FE20U+0304tU+FE21
# CONVERSION TO "O/o" WITH MACRON(0304) AND OGONEK (0328)
U+046A=OU+0328
U+046B=oU+0328
U+0460=OU+0304
U+0461=oU+0304
# CONVERSION TO LONE "O/o"
U+041E=O
U+043E=o
U+0470=PU+FE20SU+FE21
U+0471=pU+FE20sU+FE21
U+041F=P
U+043F=p
U+0420=R
U+0440=r
U+0429=Sht
U+0449=sht
U+0428=Sh
U+0448=sh
U+0426=TU+FE20SU+FE21
U+0446=tU+FE20sU+FE21
U+0421=S
U+0441=s
U+0422=T
U+0442=t
U+0478=UU+0304
U+0479=uU+0304
U+0423=U
U+0443=u
U+0472=FU+0307
U+0473=fU+0307
U+0424=F
U+0444=f
U+0427=Ch
U+0447=ch
U+0476=YU+0307
U+0477=yU+0307
# Uppercase hard sign (ambiguously maps to one Latin character)
U+042A=U+02BA
# Lowercase hard sign (ambiguously maps to one Latin character)
U+044A=U+02BA
# Uppercase soft sign (ambiguously maps to one Latin character)
U+042C=U+02B9
# Lowercase soft sign (ambiguously maps to one Latin character)
U+044C=U+02B9
U+042B=Y
U+044B=y