scriptshifter/legacy/data/MongolianRomanization.cfg

# Original table by Randall K. Barry, 14 February 2021
# Revised by Randall K. Barry to correct "ng" conversion, 10 August 2021
# Revised by Randall K. Barry to correct "e+dot" conversion, 18 August 2021
# Revised by Randall K. Barry to correct "-e" (non-joining "e") conversion, 19 November 2021
# Revised by Randall K. Barry to add roman numeral handling, 13 May 2022

[General]
Name=Mongolian

# UNICODE MONGOLIAN CHARACTER RANGE: U+1800-U+18AF

[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 AND SPECIAL CHARACTERS USED WITH MONGOLIAN SCRIPT: 

# hyphen (spacing) U+002D
# combining acute U+0301
# combining dot above U+0307
# combining tilde U+0303
# combining macron U+0304
# combining dot below U+0323
# combining ring below U+0325
# Mongolian vowel separator (spacing) U+180E
# narrow no-break space U+202F

U+002DA=U+180EU+1820
U+002Da=U+180EU+1820
A=U+1820
a=U+1820
U+002DE=U+180EU+1821
U+002De=U+180EU+1821
U+002D=U+202F
EU+0307=U+1827
eU+0307=U+1827
E=U+1821
e=U+1821
I=U+1822
i=U+1822
OU+0307=U+1825
oU+0307=U+1825
O=U+1823
o=U+1823
UU+0307=U+1826
uU+0307=U+1826
U=U+1824
u=U+1824
NG=U+1829
# this conversion shouldn't be needed, but does no harm
nG=U+1829
ng=U+1829
N=U+1828
n=U+1828
B=U+182A
b=U+182A
P=U+182B
p=U+182B
Q=U+182C
q=U+182C
KH=U+183B
Kh=U+183B
# this conversion shouldn't be needed, but does no harm
kH=U+183B
kh=U+183B
KU+0307=U+183A
kU+0307=U+183A
K=U+182C
k=U+182C
GU+0307=U+182D
gU+0307=U+182D
G=U+182D
g=U+182D
M=U+182E
m=U+182E
LH=U+1840
Lh=U+1840
# this conversion shouldn't be needed, but does no harm
lH=U+1840
lh=U+1840
L=U+182F
l=U+182F
TSU+0307=U+183C
# this conversion shouldn't be needed, but does no harm
TsU+0307=U+183C
# this conversion shouldn't be needed, but does no harm
tSU+0307=U+183C
tsU+0307=U+183C
SU+0301=U+1831
sU+0301=U+1831
S=U+1830
s=U+1830
T=U+1832
t=U+1832
D=U+1833
d=U+1833
C=U+1834
c=U+1834
J=U+1835
j=U+1835
Y=U+1836
y=U+1836
R=U+1837
r=U+1837
V=U+1838
v=U+1838
W=U+1838
w=U+1838
F=U+1839
f=U+1839
ZR=U+183F
# this conversion shouldn't be needed, but does no harm
Zr=U+183F
# this conversion shouldn't be needed, but does no harm
zR=U+183F
zr=U+183F
ZH=U+1841
Zh=U+1841
# this conversion shouldn't be needed, but does no harm
zH=U+1841
zh=U+1841
CH=U+1842
Ch=U+1842
# this conversion shouldn't be needed, but does no harm
cH=U+1842
ch=U+1842
H=U+183E
h=U+183E
-=U+180E

[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
date of publication not identified=date of publication not identified
At head of title=At head of title

# g followed by vowel a
U+182DU+1820=gU+0307a
# g followed by vowel o
U+182DU+1823=gU+0307o
# g followed by vowel u
U+182DU+1824=gU+0307u
# g preceded by vowel a
U+1820U+182D=agU+0307
# g preceded by vowel o
U+1823U+182D=ogU+0307
# g preceded by vowel u
U+1824U+182D=ugU+0307

# g followed by vowel e
U+182DU+1821=ge
# g followed by vowel i
U+182DU+1822=gi
# g followed by vowel oe
U+182DU+1825=goU+0307
# g followed by vowel ue
U+182DU+1826=guU+0307
# g followed by vowel ee
U+182DU+1827=geU+0307
# g preceded by vowel e
U+1821U+182D=eg
# g preceded by vowel i
U+1822U+182D=ig
# g preceded by vowel oe
U+1825U+182D=oU+0307g
# g preceded by vowel ue
U+1826U+182D=uU+0307g
# g preceded by vowel ee
U+1827U+182D=eU+0307g

# q followed by vowel a
U+182CU+1820=qU+0307a
# q followed by vowel o
U+182CU+1823=qU+0307o
# q followed by vowel u
U+182CU+1824=qU+0307u
# q preceded by vowel a (should not occur)
U+1820U+182C=qU+0307a
# q preceded by vowel o (should not occur)
U+1823U+182C=qU+0307o
# q preceded by vowel u (should not occur)
U+1824U+182C=qU+0307u

# k followed by vowel e
U+182CU+1821=ke
# k followed by vowel i
U+182CU+1822=ki
# k followed by vowel oe
U+182CU+1825=koU+0307
# k followed by vowel ue
U+182CU+1826=koU+0307
# k followed by vowel ee
U+182CU+1827=keU+0307
# k preceded by vowel e (should not occur)
U+1821U+182C=ke
# k preceded by vowel i (should not occur)
U+1822U+182C=ki
# k preceded by vowel oe (should not occur)
U+1825U+182C=koU+0307
# k preceded by vowel ue (should not occur)
U+1826U+182C=koU+0307
# k preceded by vowel ee (should not occur)
U+1827U+182C=keU+0307

# non-connecting vowel a
U+180EU+1820=U+002Da

# non-connecting vowel e
U+180EU+1821=U+002De

# Other Mongolian vowel separators to hyphen
U+180E=U+002De

# Narrow no-break space to hyphen
U+202F=U+002D

# Other Mongolian vowel NOT associated with g or k/q
U+1820=a
U+1823=o
U+1826=u
U+1821=e
U+1822=i
U+1825=oU+0307
U+1823=o
U+1824=u
U+1826=uU+0307
U+1827=eU+0307
U+1829=ng
U+1828=n
U+182A=b
U+182B=p
U+182C=q
U+183B=kh
U+183A=kU+0307
U+182C=k
U+182D=gU+0307
U+182E=m
U+1840=lh
U+182F=l
U+183C=tsU+0307
U+1831=sU+0301
U+1830=s
U+1832=t
U+1833=d
U+1834=c
U+1835=j
U+1836=y
U+1837=r
U+1838=v
U+1839=f
U+183F=zr
U+1841=zh
U+1842=ch
U+183E=hU+0307