Partly reverting the langdb

Multiple scripts and autonyms are not currently supported by ULS utils.
I commented out the problematic lines and left the current de-facto
situation in Wikipedia.
This is a TODO item, but it needs proper specification.

Also updated the tests somewhat.

Change-Id: I8cdc6ae430f5bb5af4b1890abf6e71a91b6beb3d
This commit is contained in:
Amir E. Aharoni
2012-08-14 15:08:08 +03:00
parent a870263ad9
commit 3d2e85664f
3 changed files with 50 additions and 24 deletions

View File

@@ -4,7 +4,9 @@ languages:
ace: [Latn, [AS, PA], Acèh]
ady-cyrl: [Cyrl, [EU], Адыгэбзэ]
ady-latn: [Latn, [EU], Adygabze]
ady: [[Cyrl, Latn], [EU], [Адыгэбзэ, Adygabze]]
# XXX multiple script
# ady: [[Cyrl, Latn], [EU], [Адыгэбзэ, Adygabze]]
ady: [Cyrl, [EU], Адыгэбзэ]
aeb: [Arab, [AF], زَوُن]
af: [Latn, [AF], Afrikaans]
ahr: [Deva, [AS], अहिराणी]
@@ -73,11 +75,15 @@ languages:
cps: [Latn, [AS], Capiceño]
cr-cans: [Cans, [NA], ᓀᐦᐃᔭᐍᐏᐣ]
cr-latn: [Latn, [NA], Nēhiyawēwin]
cr: [[Latn, Cans], [NA], [Nēhiyawēwin, ᓀᐦᐃᔭᐍᐏᐣ]]
# XXX multiple script
# cr: [[Latn, Cans], [NA], [Nēhiyawēwin, ᓀᐦᐃᔭᐍᐏᐣ]]
cr: [Cans, [NA], Nēhiyawēwin / ᓀᐦᐃᔭᐍᐏᐣ]
crh-cyrl: [Cyrl, [EU], къырымтатарджа (Кирилл)]
crh-latn: [Latn, [EU], qırımtatarca (Latin)]
# Latn is default, Cyrl is common IRL
crh: [[Curl, Latn], [EU], [къырымтатарджа, qırımtatarca]]
# XXX multiple script
# Latn is default in Wikipedia, Cyrl is common IRL
# crh: [[Cyrl, Latn], [EU], [къырымтатарджа, qırımtatarca]]
crh: [Latn, [EU], къырымтатарджа / qırımtatarca]
cs: [Latn, [EU], česky]
csb: [Latn, [EU], kaszëbsczi]
# FIXME: what script?
@@ -138,8 +144,10 @@ languages:
gn: [Latn, [LA], "Avañe'ẽ"]
gom-deva: [Deva, [AS], कोंकणी]
gom-latn: [Latn, [AS], Konknni]
gom: [[Deva, Latn], [AS], [कोंकणी, Konknni]]
# hmph??
# XXX multiple script
# gom: [[Deva, Latn], [AS], [कोंकणी, Konknni]]
gom: [Deva, [AS], कोंकणी / Konknni]
# hmph?..
got: [Goth, [EU], 𐌲𐌿𐍄𐌹𐍃𐌺]
grc: [Grek, [EU], Ἀρχαία ἑλληνικὴ]
gsw: [Latn, [EU], Alemannisch]
@@ -156,7 +164,9 @@ languages:
hi: [Deva, [AS], हिन्दी]
hif-deva: [Deva, [AS], फ़ीजी हिन्दी]
hif-latn: [Latn, [PA, AU, AS], Fiji Hindi]
hif: [[Deva, Latn[, [PA, AU, AS], [फ़ीजी हिन्दी, Fiji Hindi]]
# XXX multiple script
# hif: [[Deva, Latn], [PA, AU, AS], [फ़ीजी हिन्दी, Fiji Hindi]]
hif: [Latn, [PA, AU, AS], फ़ीजी हिन्दी / Fiji Hindi]
hil: [Latn, [AS], Ilonggo]
hne: [Deva, [AS], छत्तीसगढ़ी]
ho: [Latn, [PA], Hiri Motu]
@@ -177,13 +187,12 @@ languages:
ik: [Latn, [NA], Iñupiak]
ike-cans: [Cans, [NA], ᐃᓄᒃᑎᑐᑦ]
ike-latn: [Latn, [NA], inuktitut]
ike: [[Cans, Latn], [NA], [ᐃᓄᒃᑎᑐᑦ, inuktitut]]
ilo: [Latn, [AS], Ilokano]
inh: [Cyrl, [EU], ГӀалгӀай]
io: [Latn, [WW], Ido]
is: [Latn, [EU], íslenska]
it: [Latn, [EU], italiano]
# FIXME: relation to ike?
# For variants ike-* is used
iu: [Cans, [NA], ᐃᓄᒃᑎᑐᑦ/inuktitut]
ja: [Jpan, [AS], 日本語]
jam: [Latn, [NA], Patois]
@@ -211,7 +220,9 @@ languages:
kk-kz: [Cyrl, [EU, AS], қазақша (Қазақстан)]
kk-latn: [Latn, [EU, AS, ME], qazaqşa (latın)]
kk-tr: [Latn, [EU, AS, ME], qazaqşa (Türkïya)]
kk: [[Arab, Cyrl, Latn] [EU, AS], [قازاقشا, қазақша, qazaqşa]]
# XXX multiple script
# kk: [[Arab, Cyrl, Latn] [EU, AS], [قازاقشا, қазақша, qazaqşa]]
kk: [Cyrl, [EU, AS], қазақша / قازاقشا / qazaqşa]
kl: [Latn, [NA, EU], kalaallisut]
km: [Khmr, [AS], ភាសាខ្មែរ]
kn: [Knda, [AS], ಕನ್ನಡ]
@@ -227,13 +238,17 @@ languages:
krl: [Latn, [EU], Karjala]
ks-arab: [Arab, [AS], کٲشُر]
ks-deva: [Deva, [AS], कॉशुर]
# Just because it's the current default in the Wikipedia. Deva may be needed, too.
ks: [[Deva, Arab], [AS], [कॉशुर, کٲشُر]]
# XXX multiple script
# Arab is first here just because it's the current default in the Wikipedia. Deva may be needed, too.
# ks: [[Deva, Arab], [AS], [कॉशुर, کٲشُر]]
ks: [Arab, [AS], कॉशुर / کٲشُر]
ksf: [Latn, [AF], Bafia]
ksh: [Latn, [EU], Ripoarisch]
ku-arab: [Arab, [EU, ME], كوردي (عەرەبی)]
ku-latn: [Latn, [EU, ME], Kurdî (latînî)]
ku: [[Arab, Latn], [EU, ME], [كوردي , Kurdî]]
# XXX multiple script
# ku: [[Arab, Latn], [EU, ME], [كوردي , Kurdî]]
ku: [Latn, [EU, ME], كوردي / Kurdî]
kv: [Cyrl, [EU], коми]
kw: [Latn, [EU], kernowek]
ky: [Cyrl, [AS], Кыргызча]
@@ -381,10 +396,14 @@ languages:
sgs: [Latn, [EU], žemaitėška]
sh-cyrl: [Cyrl, [EU], српскохрватски]
sh-latn: [Latn, [EU], srpskohrvatski]
sh: [[Latn, Cyrl], [EU], [srpskohrvatski, српскохрватски]]
# XXX multiple script
# sh: [[Latn, Cyrl], [EU], [srpskohrvatski, српскохрватски]]
sh: [Latn, [EU], srpskohrvatski / српскохрватски]
shi-latn: [Latn, [AF], Tašlḥiyt]
shi-tfng: [Tfng, [AF], ⵜⴰⵛⵍⵃⵉⵜ]
shi: [[Latn, Tfng], [AF], [Tašlḥiyt, ⵜⴰⵛⵍⵃⵉⵜ]]
# XXX multiple script
# shi: [[Latn, Tfng], [AF], [Tašlḥiyt, ⵜⴰⵛⵍⵃⵉⵜ]]
shi: [Latn, [AF], Tašlḥiyt / ⵜⴰⵛⵍⵃⵉⵜ]
shn: [Mymr, [AS], လိၵ်ႈတႆး]
si: [Sinh, [AS], සිංහල]
simple: [Latn, [WW], Simple English]
@@ -400,7 +419,9 @@ languages:
sq: [Latn, [EU], shqip]
sr-ec: [Cyrl, [EU], српски (ћирилица)]
sr-el: [Latn, [EU], srpski (latinica)]
sr: [[Cyrl, Latn], [EU], [српски, srpski]]
# XXX multiple script
# sr: [[Cyrl, Latn], [EU], [српски, srpski]]
sr: [Cyrl, [EU], српски / srpski]
srn: [Latn, [SA, NA, EU], Sranantongo]
ss: [Latn, [AF], SiSwati]
st: [Latn, [AF], Sesotho]
@@ -436,7 +457,9 @@ languages:
tsd: [Grek, [EU], Τσακωνικά]
tt-cyrl: [Cyrl, [EU], татарча]
tt-latn: [Latn, [EU], tatarça]
tt: [[Cyrl, Latn] [EU], [татарча, tatarça]]
# XXX multiple script
# tt: [[Cyrl, Latn] [EU], [татарча, tatarça]]
tt: [Cyrl, [EU], татарча / tatarça]
ttt: [Cyrl, [AS], Tati]
tum: [Latn, [AF], chiTumbuka]
tw: [Latn, [AF], Twi]
@@ -447,7 +470,9 @@ languages:
udm: [Cyrl, [EU], удмурт]
ug-arab: [Arab, [AS], ئۇيغۇرچە]
ug-latn: [Latn, [AS], Uyghurche]
ug: [[Arab, Latn], [AS], [ئۇيغۇرچە, Uyghurche]]
# XXX multiple script
# ug: [[Arab, Latn], [AS], [ئۇيغۇرچە, Uyghurche]]
ug: [Arab, [AS], ئۇيغۇرچە / Uyghurche ]
uk: [Cyrl, [EU], українська]
ur: [Arab, [AS, ME], اردو]
uz: [Latn, [AS], oʻzbekcha]

File diff suppressed because one or more lines are too long

View File

@@ -89,8 +89,9 @@ test( "-- $.uls.data testing", function() {
deepEqual( $.uls.data.languagesInRegion( 'AU' ), ["en-gb", "en", "hif-latn", "hif", "mi", "na"], "languages of region AU are selected correctly" );
deepEqual( $.uls.data.languagesInRegions( ['NA', 'WW'] ),
[
"akz", "ase", "avk", "cho", "chr", "chy", "cr", "en-ca", "en", "eo", "es-formal", "es", "esu",
"haw", "ht", "ia", "ie", "ik", "ike-cans", "ike-latn", "ike", "io",
"akz", "ase", "avk", "cho", "chr", "chy", "cr-cans", "cr-latn", "cr",
"en-ca", "en", "eo", "es-formal", "es", "esu",
"haw", "ht", "ia", "ie", "ik", "ike-cans", "ike-latn", "io",
"iu", "jam", "jbo", "kl", "lfn", "mic", "mus", "nah", "nov", "nv",
"pdc", "pdt", "sei", "simple", "srn", "tokipona",
"vo", "yi", "yua"
@@ -108,7 +109,7 @@ test( "-- $.uls.data testing", function() {
deepEqual( $.uls.data.regionsInGroup( 4 ), ["WW"], "regions in group 4 are selected correctly" );
var languagesByScriptInNA = $.uls.data.languagesByScriptInRegion( 'NA' );
deepEqual( languagesByScriptInNA['Cans'], ["cr", "ike-cans", "iu"], "correct languages in Cans in NA selected" );
deepEqual( languagesByScriptInNA['Cans'], ["cr-cans", "cr", "ike-cans", "iu"], "correct languages in Cans in NA selected" );
strictEqual( $.uls.data.autonym( 'pa' ), 'ਪੰਜਾਬੀ', 'Correct autonym of the Punjabi language was selected' );