scriptshifter/data/AsianCyrillicRomanization.cfg

# Original table by Randall K. Barry, 23 February 2021

[General]
Name=AsianCyrillic

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

# Due to the the large number of Cyrillic characters used by the languages of Asia and the former Soviet Union,
# as well as variations in the romanization of certain characters depending upon the languages,
# the transliterations produced by this conversion configuration file do not always match flawlessly
# the transliterations specified by the "ALA-LC Romanization Tables" for each language.
# Mappings of each character have been made to the correspondence that is correct
# for the largest number of languages. The Roman-To-Script conversion is not identical to the 
# Script-To-Roman conversion. Improvements and standardization of the transliteration of specific
# Cyrillic characters is needed. NOTE: Roundtrip conversion for many languages is lossless. :)

[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

# CONVERSION OF "A/a" WITH BREVE (0306)
AU+0306=U+04D8
aU+0306=U+04D9

# DE-ACTIVATED CONVERSION OF GAGAUZ AND MARI LETTER "A/a" WITH BREVE DUE TO CONFLICTING ROMANIZATION
# AU+0306=U+04D2
# DE-ACTIVATED CONVERSION OF GAGAUZ AND MARC LETTER "A/a" WITH BREVE DUE TO CONFLICTING ROMANIZATION
# aU+0306=U+04D3

# 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

Gh=U+0492
GH=U+0492
gH=U=0493
gh=U=0493

# DE-ACTIVATED CONVERSION OF YAKUT "A" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
# Gh=U+0494
# DE-ACTIVATED CONVERSION OF YAKUT "A" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
# GH=U+0494
# DE-ACTIVATED CONVERSION OF YAKUT "a" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
# gH=U+0495
# DE-ACTIVATED CONVERSION OF YAKUT "a" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
# gh=U+0495

GU+0301=U+0494
gU+0301=U+0495
GU+0307=U+049C
gU+0307=U+049D
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

# CONVERSION OF "T/t" LIGATED OR BLENDED WITH "H/h" (all capitalization patterns)
TU+FE20HU+FE21=U+0498
TU+FE20hU+FE21=U+0498
tU+FE20HU+FE21=U+0499
tU+FE20hU+FE21=U+0499
Th=U+04AA
TH=U+04AA
tH=U+04AB
th=U+04AB

# 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), BREVE (0306), AND CANDRABINDU (0310)
IU+0304=U+0406
IU+0306=U+0419
IU+0310=U+0408
iU+0304=U+0456
iU+0306=U+0439
iU+0310=U+0458

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

J=U+0496
j=U+0497

# DE-ACTIVATED CONVERSION OF AZERI "J" DUE TO CONFLICTING ROMANIZATION
# J=U+04B8
# DE-ACTIVATED CONVERSION OF AZERI "j" DUE TO CONFLICTING ROMANIZATION
# J=u+04B9
# DE-ACTIVATED CONVERSION OF TAJIK "J" DUE TO CONFLICTING ROMANIZATION
# J=U+04B6
# DE-ACTIVATED CONVERSION OF TAJIK "j" DUE TO CONFLICTING ROMANIZATION
# J=u+04B7

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
Q=U+04A0
q=U+04A1

# DE-ACTIVATED CONVERSION OF KHANTY "Q" DUE TO CONFLICTING ROMANIZATION
# Q=U+04C3
# DE-ACTIVATED CONVERSION OF KHANTY "q" DUE TO CONFLICTING ROMANIZATION
# q=u+04C4

K=U+041A
k=U+043A

L=U+041B
l=U+043B
M=U+041C
m=U+043C

NU+FE20GU+FE21=U+04A2
NU+FE20gU+FE21=U+04A2
nU+FE20GU+FE21=U+04A3
nU+FE20gU+FE21=U+04A3

# DE-ACTIVATED CONVERSION OF YAKUT "NG/ng" DUE TO CONFLICTING ROMANIZATION
# NU+FE20GU+FE21=U+04A4
# NU+FE20gU+FE21=U+04A4
# nU+FE20GU+FE21=U+04A5
# nU+FE20gU+FE21=U+04A5

# DE-ACTIVATED CONVERSION OF CHUKCHI AND EVENKI "NG/ng" DUE TO CONFLICTING ROMANIZATION
# NU+FE20GU+FE21=U+04C7
# NU+FE20gU+FE21=U+04C7
# nU+FE20GU+FE21=U+04C8
# nU+FE20gU+FE21=U+04C8

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)
OU+0304=U+04EA
oU+0304=U+04EB
# CONVERSION OF "O/o" WITH DOT ABOVE (0307) USED IN MOST CENTRAL ASIAN LANGUAGES
OU+0307=U+04E8
oU+0307=U+04E9

# DE-ACTIVATED CONVERSION OF GAGAUZ, KOMI, AND MARI "O" WITH DOT ABOVE (0307)DUE TO CONFLICTING ROMANIZATION
# OU+0307=U+04E6
# oU+0307=U+04E7

# 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

SHCH=U+0429
SHCh=U+0429
SHch=U+0429
Shch=U+0429
sHCH=U+0449
shCH=U+0449
shcH=U+0449
shch=U+0449

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

TU+FE20SU+FE21U+0307=U+04B4
TU+FE20SU+0307U+FE21=U+04B4
TU+FE20sU+FE21U+0307=U+04B4
TU+FE20sU+0307U+FE21=U+04B4
tU+FE20SU+FE21U+0307=U+04B5
tU+FE20SU+0307U+FE21=U+04B5
tU+FE20sU+FE21U+0307=U+04B5
tU+FE20sU+0307U+FE21=U+04B5

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

# CONVERSION OF "U/u" WITH MACRON(0304), BREVE (0306), AND DOT ABOVE (0307)
UU+0304=U+04B0
uU+0304=U+04B1

# DE-ACTIVATED CONVERSION OF TAJIK LETTER DUE TO CONFLICTING ROMANIZATION
# UU+0304=U+04EE
# DE-ACTIVATED CONVERSION OF TAJIK LETTER DUE TO CONFLICTING ROMANIZATION
# UU+0304=U+04EF

UU+0306=U+040E
uU+0306=U+0454
UU+0307=U+04AE
uU+0307=U+04AF

# DE-ACTIVATED CONVERSION OF GAGAUZ AND MARI LETTER "O/o" WITH DOT ABOVE DUE TO CONFLICTING ROMANIZATION
# UU+0307=U+04E6
# uU+0307=U+04E7

# CONVERSION OF ESKIMO AND KARAKALPAK "W/w" THAT MAPS TO THE SAME CHARACTERS AS "U/u" WITH BREVE
W=U+040E
w=U+0454

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

# CONVERSION OF CYRILLIC PALOCHKA (ASPIRATION SIGN) USED IN MANY CENTRAL ASIAN LANGUAGES (NOT NORMALLY INITIALLY)
HU+0307=U+04BA
hU+0307=U+04BB

# DE-ACTIVATED CONVERSION OF TAJIK AND UZBEK LETTER "H/h" WITH DOT ABOVE (0307) DUE TO CONFLICTING ROMANIZATION
# HU+0307=U+04B2
# hU+0307=U+04B3
# DE-ACTIVATED CONVERSION OF ARCHAIC LETTER "H/h" WITH DOT ABOVE (0307) DUE TO CONFLICTING ROMANIZATION
# HU+0307=U+04FC
# hU+0307=U+04FD

YU+0307=U+04F8
yU+0307=U+04F9

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

U+042F=IU+FE20AU+FE21
U+044F=iU+FE20aU+FE21
U+04D8=AU+0306
U+04D9=aU+0306
# DE-ACTIVATED CONVERSION OF GAGAUZ AND MARI LETTER "A/a" WITH BREVE DUE TO CONFLICTING ROMANIZATION
U+04D2=AU+0306
# DE-ACTIVATED CONVERSION OF GAGAUZ AND MARC LETTER "A/a" WITH BREVE DUE TO CONFLICTING ROMANIZATION
U+04D3=aU+0306
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+0492=Gh
U=0493=gh
# DE-ACTIVATED CONVERSION OF YAKUT "A" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
U+0494=Gh
# DE-ACTIVATED CONVERSION OF YAKUT "a" WITH DIAERSIS DUE TO CONFLICTING ROMANIZATION
U+0495=gh
U+0494=GU+0301
U+0495=gU+0301
U+049C=GU+0307
U+049D=gU+0307
U+0413=G
U+0433=g
U+0414=D
U+0434=d
# CONVERION OF "I/i" LIGATED TO "E/e", SOME WITH MACRON (0304) AND OGONEK (0328)
U+0464=IU+FE20EU+FE21U+0304
U+0468=IU+FE20EU+FE21U+0328
U+0465=iU+FE20eU+FE21U+0304
U+0469=iU+FE20eU+FE21U+0328
U+0462=IU+FE20EU+FE21
U+0463=iU+FE20eU+FE21
# CONVERSION OF "E/e" WITH MACRON (0304), DOT ABOVE (0307), DIAERESIS (0308), OGONEK (0328), & CARON (030C)
U+0404=EU+0304
U+042D=EU+0307
U+0401=EU+0308
U+0466=EU+0328
U+0454=eU+0304
U+044D=eU+0307
U+0451=eU+0308
U+0467=eU+0328
# CONVERSION OF REMAINING LONE "E/e"
U+0415=E
U+0435=e
U+0416=Zh
U+0436=zh
U+0417=Z
U+0437=z
# CONVERSION OF "T/t" LIGATED OR BLENDED WITH "H/h" (all capitalization patterns)
U+0498=TU+FE20HU+FE21
U+0499=tU+FE20hU+FE21
U+04AA=Th
U+04AB=th
# CONVERION OF "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 OF "I/i" LIGATED TO "U/u"
U+042E=IU+FE20UU+FE21
U+044E=iU+FE20uU+FE21
# CONVERSION OF "I/i" WITH MACRON (0304), BREVE (0306), AND CANDRABINDU (0310)
U+0406=IU+0304
U+0419=IU+0306
U+0408=IU+0310
U+0456=iU+0304
U+0439=iU+0306
U+0458=iU+0310
# CONVERSION OF REMAINING LONE "I/i"
U+0418=I
U+0438=i
U+0496=J
U+0497=j
# DE-ACTIVATED CONVERSION OF AZERI "J" DUE TO CONFLICTING ROMANIZATION
U+04B8=# J
# DE-ACTIVATED CONVERSION OF AZERI "j" DUE TO CONFLICTING ROMANIZATION
u+04B9=# J
# DE-ACTIVATED CONVERSION OF TAJIK "J" DUE TO CONFLICTING ROMANIZATION
U+04B6=# J
# DE-ACTIVATED CONVERSION OF TAJIK "j" DUE TO CONFLICTING ROMANIZATION
u+04B7=# J
U+0425=Kh
U+0445=kh
U+046E=KU+FE20SU+FE21
U+046F=kU+FE20sU+FE21
U+04A0=Q
U+04A1=q
# DE-ACTIVATED CONVERSION OF KHANTY "Q" DUE TO CONFLICTING ROMANIZATION
U+04C3=Q
# DE-ACTIVATED CONVERSION OF KHANTY "q" DUE TO CONFLICTING ROMANIZATION
u+04C4=q
U+041A=K
U+043A=k
U+041B=L
U+043B=l
U+041C=M
U+043C=m
U+04A2=NU+FE20GU+FE21
U+04A3=nU+FE20gU+FE21
# DE-ACTIVATED CONVERSION OF YAKUT "NG/ng" DUE TO CONFLICTING ROMANIZATION
U+04A4=# NU+FE20GU+FE21
U+04A5=# nU+FE20gU+FE21
# DE-ACTIVATED CONVERSION OF CHUKCHI AND EVENKI "NG/ng" DUE TO CONFLICTING ROMANIZATION
U+04C7=# NU+FE20GU+FE21
U+04C8=# nU+FE20gU+FE21
U+041D=N
U+043D=n
# CONVERION OF "O/o" WITH OR WITHOUT MACRON (0304), LIGATED TO "T/t"
U+047E=OU+0304U+FE20TU+FE21
U+047F=oU+0304U+FE20tU+FE21
# CONVERSION OF "O/o" WITH MACRON(0304)
U+04EA=OU+0304
U+04EB=oU+0304
# CONVERSION OF "O/o" WITH DOT ABOVE (0307) USED IN MOST CENTRAL ASIAN LANGUAGES
U+04E8=OU+0307
U+04E9=oU+0307
# DE-ACTIVATED CONVERSION OF GAGAUZ, KOMI, AND MARI "O" WITH DOT ABOVE (0307)DUE TO CONFLICTING ROMANIZATION
U+04E6=# OU+0307
U+04E7=# oU+0307
# CONVERSION OF REMAINING 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=Shch
U+0449=shch
U+0428=Sh
u+0448=sh
U+04B4=TU+FE20SU+FE21U+0307
U+04B5=tU+FE20sU+FE21U+0307
U+0426=TU+FE20SU+FE21
U+0446=tU+FE20sU+FE21
U+0421=S
U+0441=s
U+0422=T
U+0442=t
# CONVERSION OF "U/u" WITH MACRON(0304), BREVE (0306), AND DOT ABOVE (0307)
U+04B0=UU+0304
U+04B1=uU+0304
# DE-ACTIVATED CONVERSION OF TAJIK LETTER DUE TO CONFLICTING ROMANIZATION
U+04EE=# UU+0304
# DE-ACTIVATED CONVERSION OF TAJIK LETTER DUE TO CONFLICTING ROMANIZATION
U+04EF=# UU+0304
U+040E=UU+0306
U+0454=uU+0306
U+04AE=UU+0307
U+04AF=uU+0307
# DE-ACTIVATED CONVERSION OF GAGAUZ AND MARI LETTER "O/o" WITH DOT ABOVE DUE TO CONFLICTING ROMANIZATION
U+04E6=# UU+0307
U+04E7=# uU+0307
# CONVERSION OF ESKIMO AND KARAKALPAK "W/w" THAT MAPS TO THE SAME CHARACTERS AS "U/u" WITH BREVE
U+040E=W
U+0454=w
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
# CONVERSION OF CYRILLIC PALOCHKA (ASPIRATION SIGN) USED IN MANY CENTRAL ASIAN LANGUAGES (NOT NORMALLY INITIALLY)
U+04BA=HU+0307
U+04BB=hU+0307
# DE-ACTIVATED CONVERSION OF TAJIK AND UZBEK LETTER "H/h" WITH DOT ABOVE (0307) DUE TO CONFLICTING ROMANIZATION
U+04B2=HU+0307
U+04B3=hU+0307
# DE-ACTIVATED CONVERSION OF ARCHAIC LETTER "H/h" WITH DOT ABOVE (0307) DUE TO CONFLICTING ROMANIZATION
U+04FC=HU+0307
U+04FD=hU+0307
U+04F8=YU+0307
U+04F9=yU+0307
U+042B=Y
U+044B=y
# this conversion is ambiguous - U+042C is also theoretically possible
U+044C=U+02B9
# this conversion is ambiguous - U+044C is also theoretically possible
U+044A=U+02BA