scriptshifter/legacy/data/RussianRomanization.cfg

# Original table by Gary L. Strawn
# Updated by Hugh Taylor, 12 December 2006, 10.50 GMT
# Added fields to FieldsIncluded 19 July 2007
# Updated 30 May 2013 for RDA
# Updated 15 Jan 2015 fixed incorrect i-kratkoe
# Updated by Randall K. Barry, 14 February 2021, to add six Cyrillic characters used in Mongolian & Buriat
# Updates by Randall K. Barry, 13 May 2022, to add Roman numeral conversion blocking

[General]
Name=Russian

[RomanToScript]
FieldsIncluded=100 110 111 130 240 245 246 250 260 264 440 490 600 610 611 630 651 700 710 711 730 740 800 830
SubfieldsAlwaysExcluded=uvxy0123456789
OtherSubfieldsExcludedByTag=100/e 110/e 111/j 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
and others=and others
and one other=and one other
and two others=and two others
and three others=and three others
and four others=and four others
and five others=and five others
and six others=and six others
and seven others=and seven others
and eight others=and eight others
and nine others=and nine others
and ten others=and ten others
and eleven others=and eleven others
and twelve others=and twelve others
and thirteen others=and thirteen others
and fourteen others=and fourteen others
and fifteen others=and fifteen others
and sixteen others=and sixteen others
and seventeen others=and seventeen others
and eighteen others=and eighteen others
and nineteen others=and nineteen others
et al.=et al.
XLIX=XLIX
XLIV=XLIV
XLIII=XLIII
XLII=XLII
XLI=XLI
XLVIII-XLVIII
XLVII=XLVII
XLVI=XLVI
XLV=XLV
XL=XL
LXXXIX=LXXXIX
LXXXIV=LXXXIV
LXXXIII=LXXXIII
LXXXII=LXXXII
LXXXI=LXXXI
LXXXVIII=LXXXVIII
LXXXVII=LXXXVII
LXXXVI=LXXXVI
LXXXV=LXXXV
LXXX=LXXX
LXXIX=LXXIX
LXXIV=LXXIV
LXXIII=LXXIII
LXXII=LXXII
LXXI=LXXI
LXXVIII=LXXVIII
LXXVII=LXXVII
LXXVI=LXXVI
LXXV=LXXV
LXX=LXX
LXIX=XIX
LXIV=LXIV
LXIII=LXIII
LXII=LXII
LXI=LXI
LXVIII=LXVIII
LXVII=LXVII
LXVI=LXVI
LXV=LXV
LX=LX
LIX=LIX
LIV=LIV
LIII=LIII
LII=LII
LI=LI
LVIII=LVIII
LVII=LVII
LVI=LVI
LV=LV
XXXIX=XXXIX
XXXIV=XXXIV
XXXIII=XXXIII
XXXII=XXXII
XXXI=XXXI
XXXVIII=XXXVIII
XXXVII=XXXVII
XXXVI=XXXVI
XXXV=XXXV
XXX=XXX
XXIX=XXIX
XXIV=XXIV
XXIII=XXIII
XXII=XXII
XXI=XXI
XXVIII=XXVIII
XXVII=XXVII
XXVI=XXVI
XXV=XXV
XX=XX
XIX=XIX
XIV=XIV
XIII=XIII
XII=XII
XI=XI
XVIII=XVIII
XVII=XVII
XVI=XVI
XV=XV
IV=IV
VIII=VIII
VII=VII
VI=VI
IX=IX
III=III
II=II

# COMMON COMBINING CHARACTERS (always follow a base letter): 
# combining macron U+0304
# combining breve U+0306
# combining dot above U+0307
# combining diaeresis U+0308
# 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)

A=U+0410
a=U+0430
B=U+0411
b=U+0431
V=U+0412
v=U+0432
G=U+0413
g=U+0433
D=U+0414
d=U+0434
EU+0307=U+042D
EU+0308=U+0401
# conversion results in a non-MARC-8 character
EU+0328=U+0466
E=U+0415
eU+0307=U+044D
eU+0308=U+0451
# conversion results in a non-MARC-8 character
eU+0328=U+0467
e=U+0435
# this conversion shouldn't be needed, but does no harm
ZH=U+0416
Zh=U+0416
Z=U+0417
zh=U+0436
z=U+0437
IU+0304=U+0406
IU+0306=U+0419
IU+FE20EU+FE21=U+0462
# this conversion shouldn't be needed, but does no harm
IU+FE20eU+FE21=U+0462
IU+FE20UU+FE21=U+042E
# this conversion shouldn't be needed, but does no harm
IU+FE20uU+FE21=U+042E
IU+FE20AU+FE21=U+042F
# this conversion shouldn't be needed, but does no harm
IU+FE20aU+FE21=U+042F
I=U+0418
iU+0304=U+0456
iU+0306=U+0439
iU+FE20eU+FE21=U+0463
iU+FE20uU+FE21=U+044E
iU+FE20aU+FE21=U+044F
i=U+0438
# this conversion shouldn't be needed, but does no harm
KH=U+0425
Kh=U+0425
K=U+041A
kh=U+0445
k=U+043A
L=U+041B
l=U+043B
M=U+041C
m=U+043C
N=U+041D
n=U+043D
# conversion results in a non-MARC-8 character
OU+0307=U+04E8
O=U+041E
# conversion results in a non-MARC-8 character
oU+0307=U+04E9
o=U+043E
P=U+041F
p=U+043F
R=U+0420
r=U+0440
# this conversion shouldn't be needed, but does no harm
SHCH=U+0429
Shch=U+0429
# this conversion shouldn't be needed, but does no harm
SH=U+0428
Sh=U+0428
S=U+0421
shch=U+0449
sh=U+0448
s=U+0441
TU+FE20SU+FE21=U+0426
# this conversion shouldn't be needed, but does no harm
TU+FE20sU+FE21=U+0426
T=U+0422
tU+FE20sU+FE21=U+0446
t=U+0442
# conversion results in a non-MARC-8 character
UU+0307=U+04AE
U=U+0423
# conversion results in a non-MARC-8 character
uU+0307=U+04AF
u=U+0443
FU+0307=U+0472
F=U+0424
fU+0307=U+0473
f=U+0444
# this conversion shouldn't be needed, but does no harm
CH=U+0427
Ch=U+0427
ch=U+0447
# conversion results in a non-MARC-8 character
HU+0307=U+04BA
# conversion results in a non-MARC-8 character
hU+0307=U+04BB
YU+0307=U+0474
Y=U+042B
yU+0307=U+0475
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=100 110 111 130 240 245 246 250 260 264 440 490 600 610 611 630 651 700 710 711 730 740 800 830
SubfieldsAlwaysExcluded=uvxy0123456789
OtherSubfieldsExcludedByTag=100/e 110/e 111/j 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

U+0401=EU+0308
U+0451=eU+0308
U+044C=U+02B9
U+042C=U+02B9
U+044A=U+02BA
U+042A=U+02BA
U+0410=A
U+0430=a
U+0411=B
U+0431=b
U+0412=V
U+0432=v
U+0413=G
U+0433=g
U+0414=D
U+0434=d
U+042D=EU+0307
# this Unicode character shouldn't occur in MARC-8 data
U+0466=EU+0328
U+0415=E
U+044D=eU+0307
# this Unicode character shouldn't occur in MARC-8 data
U+0467=eU+0328
U+0435=e
U+0416=Zh
U+0417=Z
U+0436=zh
U+0437=z
U+0406=IU+0304
U+0419=IU+0306
U+0462=IU+FE20EU+FE21
U+042E=IU+FE20UU+FE21
U+042F=IU+FE20AU+FE21
U+0418=I
U+0456=iU+0304
U+0439=iU+0306
U+0463=iU+FE20eU+FE21
U+044E=iU+FE20uU+FE21
U+044F=iU+FE20aU+FE21
U+0438=i
U+0425=Kh
U+041A=K
U+0445=kh
U+043A=k
U+041B=L
U+043B=l
U+041C=M
U+043C=m
U+041D=N
U+043D=n
# this Unicode character shouldn't occur in MARC-8 data
U+04E8=OU+0307
U+041E=O
# this Unicode character shouldn't occur in MARC-8 data
U+04E9=oU+0307
U+043E=o
U+041F=P
U+043F=p
U+0420=R
U+0440=r
U+0429=Shch
U+0428=Sh
U+0421=S
U+0449=shch
U+0448=sh
U+0441=s
U+0426=TU+FE20SU+FE21
U+0422=T
U+0446=tU+FE20sU+FE21
U+0442=t
# this Unicode character shouldn't occur in MARC-8 data
U+04AE=UU+0307
U+0423=U
# this Unicode character shouldn't occur in MARC-8 data
U+04AF=uU+0307
U+0443=u
U+0472=FU+0307
U+0424=F
U+0473=fU+0307
U+0444=f
U+0427=Ch
# this Unicode character shouldn't occur in MARC-8 data
U+04BA=HU+0307
U+0447=ch
# this Unicode character shouldn't occur in MARC-8 data
U+04BB=hU+0307
U+0474=YU+0307
U+042B=Y
U+0475=yU+0307
U+044B=y