Files
mediawiki-extensions-Univer…/data/langdb.yaml
Amir E. Aharoni 58bc495d6f Reorder regions in region groups
The order of the regions in each group was random and confusing.
Now it's reordered so it corresponds to the map.

Change-Id: I6fcf34dd97808f26eabbef51665e7d2743a6cd85
2012-07-10 10:58:43 -04:00

549 lines
12 KiB
YAML

languages:
aa: [Latn, [AF]]
ab: [Cyrl, [EU]]
ace: [Latn, [AS, PA]]
ady-cyrl: [Cyrl, [EU]]
ady-latn: [Latn, [EU]]
ady: [Cyrl, [EU]]
aeb: [Arab, [AF]]
af: [Latn, [AF]]
ahr: [Deva, [AS]]
ak: [Latn, [AF]]
akz: [Latn, [NA]]
aln: [Latn, [EU]]
am: [Ethi, [AF]]
an: [Latn, [EU]]
ang: [Latn, [EU]]
anp: [Deva, [AS]]
ar: [Arab, [ME]]
arc: [Syrc, [ME]]
arn: [Latn, [SA]]
aro: [Latn, [LA]]
arq: [Latn, [AF]]
ary: [Latn, [ME]]
arz: [Arab, [ME]]
as: [Beng, [AS]]
ase: [Sgnw, [NA]]
ast: [Latn, [EU]]
av: [Cyrl, [EU]]
avk: [Latn, [WW]]
ay: [Latn, [SA]]
# also Arab, and in the past - Cyrl
az: [Latn, [EU, ME]]
ba: [Cyrl, [EU]]
bar: [Latn, [EU]]
bbc-latn: [Latn, [AS]]
bbc: [Batk, [AS]]
bcc: [Arab, [AS, ME]]
bcl: [Latn, [AS]]
be-tarask: [Cyrl, [EU]]
be-x-old: [Cyrl, [EU]]
be: [Cyrl, [EU]]
bew: [Latn, [AS]]
bfq: [Taml, [AS]]
bg: [Cyrl, [EU]]
bh: [Deva, [AS]]
bho: [Deva, [AS]]
bi: [Latn, [PA]]
bjn: [Latn, [AS]]
bm: [Latn, [AF]]
bn: [Beng, [AS]]
bo: [Tibt, [AS]]
bpy: [Beng, [AS]]
bqi: [Arab, [ME]]
br: [Latn, [EU]]
brh: [Latn, [ME, AS]]
bs: [Latn, [EU]]
bto: [Latn, [AS]]
bug: [Bugi, [AS]]
bxr: [Cyrl, [AS]]
ca: [Latn, [EU]]
cbk-zam: [Latn, [AS]]
cdo: [Latn, [AS]]
ce: [Cyrl, [EU]]
ceb: [Latn, [AS]]
ch: [Latn, [PA]]
cho: [Latn, [NA]]
chr: [Cher, [NA]]
chy: [Latn, [NA]]
ckb: [Arab, [ME]]
co: [Latn, [EU]]
cps: [Latn, [AS]]
# Also Latn
cr: [Cans, [NA]]
crh-cyrl: [Cyrl, [EU]]
crh-latn: [Latn, [EU]]
# Latn is default, Cyrl is common IRL
crh: [Latn, [EU]]
cs: [Latn, [EU]]
csb: [Latn, [EU]]
cu: [Cyrl, [EU]]
cv: [Cyrl, [EU]]
cy: [Latn, [EU]]
da: [Latn, [EU]]
de-at: [Latn, [EU]]
de-ch: [Latn, [EU]]
de-formal: [Latn, [EU]]
de: [Latn, [EU]]
diq: [Latn, [EU, AS]]
dsb: [Latn, [EU]]
dtp: [Latn, [AS]]
dv: [Thaa, [AS]]
dz: [Tibt, [AS]]
ee: [Latn, [AF]]
egl: [Latn, [EU]]
el: [Grek, [EU]]
eml: [Latn, [EU]]
en-ca: [Latn, [NA]]
en-gb: [Latn, [EU, AS, AU]]
# world?
en: [Latn, [EU, NA, AU, AF, ME, AS, PA, WW]]
eo: [Latn, [WW]]
es-419: [Latn, [LA]]
# world?
es-formal: [Latn, [EU, NA, LA, SA, AF, WW]]
# world?
es: [Latn, [EU, NA, LA, SA, AF, WW]]
esu: [Latn, [NA]]
et: [Latn, [EU]]
eu: [Latn, [EU]]
ext: [Latn, [EU]]
fa: [Arab, [ME]]
ff: [Latn, [AF]]
fi: [Latn, [EU]]
fit: [Latn, [EU]]
fj: [Latn, [PA]]
fo: [Latn, [EU]]
fr: [Latn, [EU]]
frc: [Latn, [EU]]
frp: [Latn, [EU]]
frr: [Latn, [EU]]
fur: [Latn, [EU]]
fy: [Latn, [EU]]
ga: [Latn, [EU]]
gag: [Latn, [EU]]
gah: [Latn, [AS]]
gan-hans: [Hans, [AS]]
gan-hant: [Hant, [AS]]
gan: [Hant, [AS]]
gbz: [Latn, [AS]]
gcf: [Latn, [LA]]
gd: [Latn, [EU]]
gl: [Latn, [EU]]
glk: [Arab, [ME]]
gn: [Latn, [LA]]
gom-deva: [Deva, [AS]]
gom-latn: [Latn, [AS]]
gom: [Deva, [AS]]
# hmph
got: [Goth, [EU]]
grc: [Grek, [EU]]
gsw: [Latn, [EU]]
gu: [Gujr, [AS]]
guc: [Latn, [LA]]
gur: [Latn, [AF]]
gv: [Latn, [EU]]
# The name in Names.php is Arabic, but everything else is Latn
ha: [Latn, [AF]]
hak: [Latn, [AS]]
haw: [Latn, [NA, PA]]
he: [Hebr, [ME]]
# Or maybe world?
hi: [Deva, [AS]]
hif-deva: [Deva, [AS]]
hif-latn: [Latn, [PA, AU, AS]]
hif: [Latn, [PA, AU, AS]]
hil: [Latn, [AS]]
hne: [Deva, [AS]]
ho: [Latn, [PA]]
hr: [Latn, [EU]]
hsb: [Latn, [EU]]
hsn: [Hans, [AS]]
# Haitian Creole. North America, right?
ht: [Latn, [NA]]
hu-formal: [Latn, [EU]]
hu: [Latn, [EU]]
hy: [Armn, [EU, ME]]
hz: [Latn, [AF]]
ia: [Latn, [WW]]
id: [Latn, [AS]]
ie: [Latn, [WW]]
ig: [Latn, [AF]]
ii: [Yiii, [AS]]
ik: [Latn, [NA]]
ike-cans: [Cans, [NA]]
ike-latn: [Latn, [NA]]
ike: [Latn, [NA]]
ilo: [Latn, [AS]]
inh: [Cyrl, [EU]]
io: [Latn, [WW]]
is: [Latn, [EU]]
it: [Latn, [EU]]
iu: [Cans, [NA]]
ja: [Jpan, [AS]]
jam: [Latn, [NA]]
jbo: [Latn, [WW]]
jut: [Latn, [EU]]
# also in the Javanese script (Java), but the Wikipedia is in Latn
jv: [Latn, [AS, PA]]
ka: [Geor, [EU]]
kaa: [Latn, [AS]]
# Can also be Tfng, but the Wikipedia is mostly Latn
kab: [Latn, [AF, EU]]
kbd-cyrl: [Cyrl, [EU, ME]]
kbd-latn: [Latn, [EU]]
kbd: [Cyrl, [EU, ME]]
kea: [Latn, [AF]]
kg: [Latn, [AF]]
kgp: [Latn, [LA]]
khw: [Arab, [ME, AS]]
ki: [Latn, [AF]]
kiu: [Latn, [EU, ME]]
kj: [Latn, [AF]]
kk-arab: [Arab, [EU, AS]]
kk-cn: [Arab, [EU, AS, ME]]
kk-cyrl: [Cyrl, [EU, AS]]
kk-kz: [Cyrl, [EU, AS]]
kk-latn: [Latn, [EU, AS, ME]]
kk-tr: [Latn, [EU, AS, ME]]
kk: [Cyrl, [EU, AS]]
kl: [Latn, [NA, EU]]
km: [Khmr, [AS]]
kn: [Knda, [AS]]
# Here Hang may be even more appropriate, because kp has more resistance to Han
ko-kp: [Kore, [AS]]
# Kore is an alias for Hangul+Han. Maybe Hang is more appropriate?
ko: [Kore, [AS]]
koi: [Cyrl, [EU]]
kr: [Latn, [AF]]
krc: [Cyrl, [EU]]
kri: [Latn, [AF]]
krj: [Latn, [ME, EU]]
krl: [Latn, [EU]]
ks-arab: [Arab, [AS]]
ks-deva: [Deva, [AS]]
# Just because it's the current default in the Wikipedia. Deva may be needed, too.
ks: [Arab, [AS]]
ksf: [Latn, [AF]]
ksh: [Latn, [EU]]
ku-arab: [Arab, [EU, ME]]
ku-latn: [Latn, [EU, ME]]
ku: [Latn, [EU, ME]]
kv: [Cyrl, [EU]]
kw: [Latn, [EU]]
ky: [Cyrl, [AS]]
la: [Latn, [EU]]
# Most identified with Turkey, Bulgaria, Greece, Spain and Israel,
# but also spoken in Latin America and elsewhere.
# Wikipedia is mostly in Latn, but also in Hebr. (Comparable to az.)
lad: [Latn, [ME, EU, LA]]
lb: [Latn, [EU]]
lbe: [Cyrl, [EU]]
lez: [Cyrl, [EU]]
lfn: [Latn, [WW]]
lg: [Latn, [AF]]
li: [Latn, [EU]]
lij: [Latn, [EU]]
liv: [Latn, [EU]]
lld: [Latn, [EU]]
lmo: [Latn, [EU]]
ln: [Latn, [AF]]
lo: [Laoo, [AS]]
loz: [Latn, [AF]]
lt: [Latn, [EU]]
ltg: [Latn, [EU]]
lus: [Latn, [AS]]
lv: [Latn, [EU]]
lzh: [Hant, [AS]]
# Also Geor, but the incubator is in Latn
lzz: [Latn, [EU, ME]]
mai: [Deva, [AS]]
map-bms: [Latn, [AS]]
mdf: [Cyrl, [EU]]
mfe: [Latn, [LA]]
mg: [Latn, [AF]]
mh: [Latn, [PA]]
mhr: [Cyrl, [EU]]
mi: [Latn, [PA, AU]]
mic: [Latn, [NA]]
min: [Latn, [AS]]
mk: [Cyrl, [EU]]
ml: [Mlym, [AS, ME]]
# Hmm, can also have Mong some day in some way
mn: [Cyrl, [AS]]
mnc: [Mong, [AS]]
mni: [Beng, [AS]]
mnw: [Mymr, [AS]]
mo: [Cyrl, [EU]]
mr: [Deva, [AS, ME]]
mrj: [Cyrl, [EU]]
ms: [Latn, [AS]]
mt: [Latn, [EU]]
mui: [Latn, [AS]]
mus: [Latn, [NA]]
mwl: [Latn, [EU]]
mwv: [Latn, [AS]]
my: [Mymr, [AS]]
myv: [Cyrl, [EU]]
mzn: [Arab, [ME, AS]]
na: [Latn, [PA, AU]]
nah: [Latn, [NA, LA]]
nan: [Latn, [AS]]
nap: [Latn, [EU]]
nb: [Latn, [EU]]
nds-nl: [Latn, [EU]]
nds: [Latn, [EU]]
ne: [Deva, [AS]]
new: [Deva, [AS]]
ng: [Latn, [AF]]
niu: [Latn, [PA]]
njo: [Latn, [AS]]
nl-informal: [Latn, [EU, SA]]
nl: [Latn, [EU, SA]]
nn: [Latn, [EU]]
"no": [Latn, [EU]]
nov: [Latn, [WW]]
nqo: [Nkoo, [AF]]
nrm: [Latn, [EU]]
nso: [Latn, [AF]]
nv: [Latn, [NA]]
ny: [Latn, [AF]]
oc: [Latn, [EU]]
om: [Latn, [AF]]
or: [Orya, [AS]]
os: [Cyrl, [EU]]
pa: [Guru, [AS]]
pag: [Latn, [AS]]
pam: [Latn, [AS]]
pap: [Latn, [LA]]
pcd: [Latn, [EU]]
pdc: [Latn, [EU, NA, SA]]
pdt: [Latn, [EU, NA, SA]]
pfl: [Latn, [EU]]
pi: [Deva, [AS]]
pih: [Latn, [PA]]
pis: [Latn, [PA]]
pko: [Latn, [AF]]
pl: [Latn, [EU]]
pms: [Latn, [EU]]
pnb: [Arab, [AS, ME]]
pnt: [Grek, [EU]]
ppl: [Latn, [LA]]
prg: [Latn, [EU]]
pru: [Latn, [EU]]
ps: [Arab, [AS, ME]]
pt-br: [Latn, [SA, LA]]
# world?
pt: [Latn, [EU, LA, AS, PA, AF]]
qu: [Latn, [SA]]
qug: [Latn, [SA]]
rap: [Latn, [LA]]
rgn: [Latn, [EU]]
rif: [Latn, [AF]]
rki: [Mymr, [AS]]
rm: [Latn, [EU]]
rmy: [Latn, [EU]]
rn: [Latn, [AF]]
ro: [Latn, [EU]]
roa-rup: [Latn, [EU]]
roa-tara: [Latn, [EU]]
rtm: [Latn, [PA]]
# world?
ru: [Cyrl, [EU, AS, ME]]
rue: [Cyrl, [EU]]
rup: [Latn, [EU]]
ruq: [Latn, [EU]]
ruq-cyrl: [Cyrl, [EU]]
ruq-grek: [Grek, [EU]]
ruq-latn: [Latn, [EU]]
rw: [Latn, [AF]]
ryu: [Kana, [AS]]
sa: [Deva, [AS]]
# Russian Far East - Europe, Asia, or both?
sah: [Cyrl, [EU, AS]]
# Currently Latn, potentially Olck
sat: [Latn, [AS]]
saz: [Saur, [AS]]
sc: [Latn, [EU]]
scn: [Latn, [EU]]
sco: [Latn, [EU]]
sd: [Arab, [AS]]
sdc: [Latn, [EU]]
se: [Latn, [EU]]
sei: [Latn, [NA, LA]]
sg: [Latn, [AF]]
sgs: [Latn, [EU]]
sh: [Latn, [EU]]
shi-latn: [Latn, [AF]]
shi-tfng: [Tfng, [AF]]
shi: [Latn, [AF]]
shn: [Mymr, [AS]]
si: [Sinh, [AS]]
simple: [Latn, [WW]]
sk: [Latn, [EU]]
sl: [Latn, [EU]]
sli: [Latn, [EU]]
slr: [Latn, [AS]]
sly: [Latn, [AS]]
sm: [Latn, [PA]]
sma: [Latn, [EU]]
sn: [Latn, [AF]]
so: [Latn, [AF]]
sq: [Latn, [EU]]
sr-ec: [Cyrl, [EU]]
sr-el: [Latn, [EU]]
sr: [Cyrl, [EU]]
srn: [Latn, [SA, NA, EU]]
ss: [Latn, [AF]]
st: [Latn, [AF]]
stq: [Latn, [EU]]
su: [Latn, [AS]]
sv: [Latn, [EU]]
sw: [Latn, [AF]]
swb: [Latn, [AF]]
sxu: [Latn, [EU]]
szl: [Latn, [EU]]
ta: [Taml, [AS]]
tcy: [Knda, [AS]]
te: [Telu, [AS]]
tet: [Latn, [AS, PA]]
tg-cyrl: [Cyrl, [AS]]
tg-latn: [Latn, [AS]]
tg: [Cyrl, [AS]]
th: [Thai, [AS]]
ti: [Ethi, [AF]]
tk: [Latn, [AS]]
tkr: [Cyrl, [AS]]
tl: [Latn, [AS]]
# A very complicated case. Names.php is Cyrl. In TWN they argue about Cyrl, Latn, and Arab. I can't find reliable external sources. --Amir
tly: [Cyrl, [EU, AS, ME]]
tn: [Latn, [AF]]
to: [Latn, [PA]]
tokipona: [Latn, [WW]]
tpi: [Latn, [PA, AS]]
tr: [Latn, [EU, ME]]
trp: [Latn, [AS]]
tru: [Latn, [AS]]
ts: [Latn, [AF]]
tsd: [Grek, [EU]]
tt-cyrl: [Cyrl, [EU]]
tt-latn: [Latn, [EU]]
tt: [Cyrl, [EU]]
ttt: [Cyrl, [AS]]
tum: [Latn, [AF]]
tw: [Latn, [AF]]
twd: [Latn, [EU]]
ty: [Latn, [PA]]
tyv: [Cyrl, [AS]]
tzm: [Tfng, [AF]]
udm: [Cyrl, [EU]]
ug-arab: [Arab, [AS]]
ug-latn: [Latn, [AS]]
ug: [Arab, [AS]]
uk: [Cyrl, [EU]]
ur: [Arab, [AS, ME]]
uz: [Latn, [AS]]
ve: [Latn, [AF]]
vec: [Latn, [EU]]
vep: [Latn, [EU]]
vi: [Latn, [AS]]
vls: [Latn, [EU]]
vmf: [Latn, [EU]]
vo: [Latn, [WW]]
vot: [Latn, [EU]]
vro: [Latn, [EU]]
wa: [Latn, [EU]]
war: [Latn, [AS]]
wls: [Latn, [PA]]
wo: [Latn, [AF]]
wuu: [Hans, [EU]]
xal: [Cyrl, [EU]]
xh: [Latn, [AF]]
xmf: [Geor, [EU]]
ydd: [Hebr, [AS, EU]]
yi: [Hebr, [ME, EU, NA, SA]]
yo: [Latn, [AF]]
yrk: [Cyrl, [AS]]
yrl: [Latn, [LA]]
yua: [Latn, [NA, LA]]
# world?
yue: [Hant, [AS]]
za: [Latn, [AS]]
zea: [Latn, [EU]]
zh-classical: [Hant, [AS]]
zh-cn: [Hans, [AS]]
zh-hans: [Hans, [AS]]
zh-hant: [Hant, [AS]]
zh-hk: [Hant, [AS]]
zh-min-nan: [Latn, [AS]]
zh-mo: [Hant, [AS]]
zh-my: [Hans, [AS]]
zh-sg: [Hans, [AS]]
zh-tw: [Hant, [AS]]
zh-yue: [Hans, [AS]]
zh: [Hans, [AS]]
zu: [Latn, [AF]]
# The codes are taken from http://unicode.org/iso15924/iso15924-codes.html .
#
# The classification is roughly based on http://www.unicode.org/charts/
# with some practical corrections.
scriptgroups:
# Other is reserved
# Large groups, one script in each
Cyrillic: [Cyrl]
Arabic: [Arab]
# It's probalby different enough from Latin and Cyrillic, but user testing
# may prove otherwise.
Greek: [Grek]
# Couldn't find a better place for Goth.
Latin: [Latn, Goth]
WestCaucasian: [Armn, Geor]
# Maybe it can be unified with Arabic.
# Maybe Thaana can be moved here from SouthAsian.
# Maybe it can be unified with African.
MiddleEastern: [Hebr, Syrc]
African: [Ethi, Nkoo, Tfng]
# India, Nepal, Bangladesh, Sri-Lanka, Bhutan, Maldives.
#
# Thaana (Thaa, the script of Maldives) is here, even though it's RTL,
# because it's closer geographically to India. Maybe it should be moved
# to MiddleEastern or to Arabic, if that would be easier to users.
#
# Tibetan (Tibt) is here, even though it's classified as "Central Asian" by
# Unicode, because linguistically and geographically it's closely related to
# the Brahmic family.
SouthAsian: [Beng, Deva, Gujr, Guru, Knda, Mlym, Orya, Saur, Sinh, Taml, Telu, Tibt, Thaa]
SouthEastAsian: [Batk, Bugi, Java, Khmr, Laoo, Mymr, Thai]
Mongolian: [Mong]
SignWriting: [Sgnw]
CJK: [Hans, Hant, Kana, Kore, Jpan, Yiii]
NativeAmerican: [Cher, Cans]
regiongroups:
# north-america
NA: 1
# latin-america
LA: 1
# south-america
SA: 1
# europe
EU: 2
# middle-east
ME: 2
# africa
AF: 2
# asia
AS: 3
# pacific
PA: 3
# australia
AU: 3
# world wide, international
WW: 4
# Importance in the region, 100 = official language or everybody knows it
importanceInRegions:
fi: { FI: 100, SE: 10 }
ru: { RU: 100, FI: 40 }