Merge pull request #59 from amire80/arrange_aliases

Aliases for all the languages that need them

data/langdb.yaml

@@ -2,9 +2,8 @@ languages:
   aa: [Latn, [AF], Qafár af]
   ab: [Cyrl, [EU], Аҧсшәа]
   ace: [Latn, [AS, PA], Acèh]
- # FIXME: alias
   ady: [Cyrl, [EU, ME], Адыгэбзэ]
-  ady-cyrl: [Cyrl, [EU, ME], Адыгэбзэ]
+  ady-cyrl: [ady]
   ady-latn: [Latn, [EU, ME], Adygabze]
   aeb: [Arab, [AF], زَوُن]
   af: [Latn, [AF], Afrikaans]
@@ -30,21 +29,23 @@ languages:
   avk: [Latn, [WW], Kotava]
   ay: [Latn, [AM], Aymar aru]
  # Latin is the default in Azerbaijani Wikipedia
- # FIXME: alias
-  az: [Latn, [EU, ME], azərbaycanca]
+ # CLDR uses az-latn and az-arab
+  az: [az-latn]
   az-latn: [Latn, [EU, ME], azərbaycanca]
   az-arab: [Arab, [EU, ME], آذربايجانجا]
   az-cyrl: [Latn, [EU, ME], азәрбајҹанҹа]
+ # CLDR uses az-arab for the Arabic-script Azerbaijani of Iran
+  azb: [az-arab]
   ba: [Cyrl, [EU], башҡортса]
   bar: [Latn, [EU], Boarisch]
   bbc-latn: [Latn, [AS], Batak Toba]
- # FIXME
-  bbc: [Batk, [AS], Batak Toba/Batak autonym unknown]
+ # FIXME - autonym in the Batak script is unknown
+  bbc-batk: [Batk, [AS], Batak Toba]
+  bbc: [Latn, [AS], Batak Toba]
   bcc: [Arab, [AS, ME], بلوچی مکرانی]
   bcl: [Latn, [AS], Bikol Central]
- # FIXME: alias
   be-tarask: [Cyrl, [EU], беларуская (тарашкевіца)]
-  be-x-old: [Cyrl, [EU], беларуская (тарашкевіца)]
+  be-x-old: [be-tarask]
   be: [Cyrl, [EU], беларуская]
   bew: [Latn, [AS], Bahasa Betawi]
   bfq: [Taml, [AS], படகா]
@@ -77,17 +78,15 @@ languages:
   ckb: [Arab, [ME], کوردی]
   co: [Latn, [EU], corsu]
   cps: [Latn, [AS], Capiceño]
- # FIXME: alias
   cr: [Cans, [AM], ᓀᐦᐃᔭᐍᐏᐣ]
-  cr-cans: [Cans, [AM], ᓀᐦᐃᔭᐍᐏᐣ]
+  cr-cans: [cr]
   cr-latn: [Latn, [AM], Nēhiyawēwin]
- # FIXME: alias
   crh: [Latn, [EU], qırımtatarca]
   crh-cyrl: [Cyrl, [EU], къырымтатарджа]
-  crh-latn: [Latn, [EU], qırımtatarca]
+  crh-latn: [crh]
   cs: [Latn, [EU], česky]
   csb: [Latn, [EU], kaszëbsczi]
- # FIXME: what script?
+ # FIXME: which script to prefer?..
   cu: [Cyrl, [EU], словѣ́ньскъ / ⰔⰎⰑⰂⰡⰐⰠⰔⰍⰟ]
   cv: [Cyrl, [EU], Чӑвашла]
   cy: [Latn, [EU], Cymraeg]
@@ -133,9 +132,8 @@ languages:
   ga: [Latn, [EU], Gaeilge]
   gag: [Latn, [EU], Gagauz]
   gah: [Latn, [AS], Alekano]
- # FIXME: alias
-  gan-hans: [Hans, [AS], 赣语（简体）]
-  gan-hant: [Hant, [AS], 贛語（繁體）]
+  gan-hans: [Hans, [AS], 赣语（简体]
+  gan-hant: [gan]
   gan: [Hant, [AS], 贛語]
   gbz: [Latn, [AS], Dari]
   gcf: [Latn, [AM], Guadeloupean Creole French]
@@ -143,9 +141,8 @@ languages:
   gl: [Latn, [EU], galego]
   glk: [Arab, [ME], گیلکی]
   gn: [Latn, [AM], "Avañe'ẽ"]
- # FIXME: alias
   gom: [Deva, [AS], कोंकणी]
-  gom-deva: [Deva, [AS], कोंकणी]
+  gom-deva: [gom]
   gom-latn: [Latn, [AS], Konknni]
   got: [Goth, [EU], 𐌲𐌿𐍄𐌹𐍃𐌺]
   grc: [Grek, [EU], Ἀρχαία ἑλληνικὴ]
@@ -154,25 +151,23 @@ languages:
   guc: [Latn, [AM], Wayúu]
   gur: [Latn, [AF], Gurenɛ]
   gv: [Latn, [EU], Gaelg]
- # FIXME: alias
+ # CLDR uses ha-latn and ha-arab. Latin is more common and is used in Wikipedia.
   ha-arab: [Arab, [AF], هَوُسَ]
   ha-latn: [Latn, [AF], Hausa]
-  ha: [Latn, [AF], Hausa]
+  ha: [ha-latn]
   hak: [Latn, [AS], Hak-kâ-fa]
   haw: [Latn, [AM, PA], Hawai`i]
   he: [Hebr, [ME], עברית]
   hi: [Deva, [AS], हिन्दी]
- # FIXME: alias
   hif: [Latn, [PA, AS], Fiji Hindi]
   hif-deva: [Deva, [AS], फ़ीजी हिन्दी]
-  hif-latn: [Latn, [PA, AS], Fiji Hindi]
+  hif-latn: [hif]
   hil: [Latn, [AS], Ilonggo]
   hne: [Deva, [AS], छत्तीसगढ़ी]
   ho: [Latn, [PA], Hiri Motu]
   hr: [Latn, [EU], hrvatski]
   hsb: [Latn, [EU], hornjoserbsce]
   hsn: [Hans, [AS], 湘语]
- # Haitian Creole. North America, right?
   ht: [Latn, [AM], Kreyòl ayisyen]
   hu-formal: [Latn, [EU], Magyar (magázó)]
   hu: [Latn, [EU], magyar]
@@ -204,7 +199,7 @@ languages:
   kaa: [Latn, [AS], Qaraqalpaqsha]
  # Can also be Tfng, but the Wikipedia is mostly Latn
   kab: [Latn, [AF, EU], Taqbaylit]
-  kbd-cyrl: [Cyrl, [EU, ME], Адыгэбзэ]
+  kbd-cyrl: [kbd]
   kbd-latn: [Latn, [EU], Qabardjajəbza]
   kbd: [Cyrl, [EU, ME], Адыгэбзэ]
   kea: [Latn, [AF], Kabuverdianu]
@@ -214,14 +209,13 @@ languages:
   ki: [Latn, [AF], Gĩkũyũ]
   kiu: [Latn, [EU, ME], Kırmancki]
   kj: [Latn, [AF], Kwanyama]
- # FIXME: alias
-  kk: [Cyrl, [EU, AS], қазақша]
+  kk: [kk-cyrl]
   kk-arab: [Arab, [EU, AS], قازاقشا (تٴوتە)]
-  kk-cn: [Arab, [EU, AS, ME], قازاقشا (جۇنگو)]
+  kk-cn: [kk-arab]
   kk-cyrl: [Cyrl, [EU, AS], қазақша]
-  kk-kz: [Cyrl, [EU, AS], қазақша (Қазақстан)]
+  kk-kz: [kk-cyrl]
   kk-latn: [Latn, [EU, AS, ME], qazaqşa]
-  kk-tr: [Latn, [EU, AS, ME], qazaqşa (Türkïya)]
+  kk-tr: [kk-latn]
   kl: [Latn, [AM, EU], kalaallisut]
   km: [Khmr, [AS], ភាសាខ្មែរ]
   kn: [Knda, [AS], ಕನ್ನಡ]
@@ -237,20 +231,18 @@ languages:
   krl: [Latn, [EU], Karjala]
   ks-arab: [Arab, [AS], کٲشُر]
   ks-deva: [Deva, [AS], कॉशुर]
- # FIXME: alias
   ks: [Arab, [AS], کٲشُر]
   ksf: [Latn, [AF], Bafia]
   ksh: [Latn, [EU], Ripoarisch]
- # FIXME: alias
-  ku: [Latn, [EU, ME], Kurdî]
+ # CLDR uses ku-latn and ku-arab. Latin is more common and is used in Wikipedia.
+  ku: [ku-latn]
   ku-arab: [Arab, [EU, ME], كوردي]
   ku-latn: [Latn, [EU, ME], Kurdî]
   kv: [Cyrl, [EU], коми]
   kw: [Latn, [EU], kernowek]
   ky: [Cyrl, [AS], Кыргызча]
   la: [Latn, [EU], Latina]
- # FIXME: alias
-  lad: [Latn, [ME, EU, AM], Ladino]
+  lad: [lad-latn]
   lad-latn: [Latn, [ME, EU, AM], Ladino]
   lad-hebr: [Hebr, [ME, EU, AM], לאדינו]
   lb: [Latn, [EU], Lëtzebuergesch]
@@ -368,15 +360,14 @@ languages:
   ru: [Cyrl, [EU, AS, ME], русский]
   rue: [Cyrl, [EU], русиньскый]
   rup: [Latn, [EU], Armãneashce]
-  ruq: [Latn, [EU], Vlăheşte]
-  ruq-cyrl: [Cyrl, [EU], Влахесте]
+  ruq: [Cyrl, [EU], Влахесте]
+  ruq-cyrl: [ruq]
  # FIXME: broken autonym
   ruq-grek: [Grek, [EU], Megleno-Romanian (Greek script)]
   ruq-latn: [Latn, [EU], Vlăheşte]
   rw: [Latn, [AF], Kinyarwanda]
   ryu: [Kana, [AS], ʔucināguci]
   sa: [Deva, [AS], संस्कृतम्]
- # Russian Far East - Europe, Asia, or both?
   sah: [Cyrl, [EU, AS], саха тыла]
  # Currently Latn, potentially Olck
   sat: [Latn, [AS], Santali]
@@ -390,14 +381,10 @@ languages:
   sei: [Latn, [AM], Cmique Itom]
   sg: [Latn, [AF], Sängö]
   sgs: [Latn, [EU], žemaitėška]
-  sh-cyrl: [Cyrl, [EU], српскохрватски]
-  sh-latn: [Latn, [EU], srpskohrvatski]
- # FIXME: alias
   sh: [Latn, [EU], srpskohrvatski]
   shi-latn: [Latn, [AF], Tašlḥiyt]
   shi-tfng: [Tfng, [AF], ⵜⴰⵛⵍⵃⵉⵜ]
- # FIXME: which one to pick and alias?
-  shi: [Latn, [AF], Tašlḥiyt / ⵜⴰⵛⵍⵃⵉⵜ]
+  shi: [shi-latn]
   shn: [Mymr, [AS], လိၵ်ႈတႆး]
   si: [Sinh, [AS], සිංහල]
   simple: [Latn, [WW], Simple English]
@@ -414,8 +401,7 @@ languages:
   sn: [Latn, [AF], chiShona]
   so: [Latn, [AF], Soomaaliga]
   sq: [Latn, [EU], shqip]
- # FIXME: do we need the double name here?
-  sr: [Cyrl, [EU], српски]
+  sr: [sr-cyrl]
   sr-ec: [sr-cyrl]
   sr-cyrl: [Cyrl, [EU], српски]
   sr-el: [sr-latn]
@@ -453,11 +439,8 @@ languages:
   tru: [Latn, [AS], Ṫuroyo]
   ts: [Latn, [AF], Xitsonga]
   tsd: [Grek, [EU], Τσακωνικά]
-  tt-cyrl: [Cyrl, [EU], татарча]
-  tt-latn: [Latn, [EU], tatarça]
- # FIXME: alias
   tt: [Cyrl, [EU], татарча]
-  tt-cyrl: [Cyrl, [EU], татарча]
+  tt-cyrl: [tt]
   tt-latn: [Latn, [EU], tatarça]
   ttt: [Cyrl, [AS], Tati]
   tum: [Latn, [AF], chiTumbuka]
@@ -467,10 +450,12 @@ languages:
   tyv: [Cyrl, [AS], тыва дыл]
   tzm: [Tfng, [AF], ⵜⴰⵎⴰⵣⵉⵖⵜ]
   udm: [Cyrl, [EU], удмурт]
- # FIXME: alias
-  ug: [Arab, [AS], ئۇيغۇرچە ]
-  ug-arab: [Arab, [AS], ئۇيغۇرچە ]
-  ug-latn: [Latn, [AS], Uyghurche ]
+ # CLDR uses ug-arab, ug-latn and ug-cyrl.
+ # Arabic seems to have the largest number of users and is the main script in the Wikipedia.
+  ug: [ug-arab]
+  ug-arab: [Arab, [AS], ئۇيغۇرچە]
+  ug-latn: [Latn, [AS], uyghurche]
+  ug-cyrl: [Cyrl, [AS], уйғурчә]
   uk: [Cyrl, [EU], українська]
   ur: [Arab, [AS, ME], اردو]
   uz: [Latn, [AS], oʻzbekcha]

test/jquery.uls.test.js

@@ -51,6 +51,24 @@
 		return result;
 	};
 
+	/*
+	 * Runs over all languages and checks that all redirects point to a language.
+	 * There's no reason to have double redirects.
+	 */
+	var doubleRedirects = function () {
+		var result = [];
+
+		for ( var language in $.uls.data.languages ) {
+			var target = $.uls.data.isRedirect( language );
+
+			if ( target && $.uls.data.isRedirect( target ) ) {
+				result.push( language );
+			}
+		}
+
+		return result;
+	};
+
 	/*
 	 * Runs over all script codes mentioned in langdb and checks whether
 	 * they have something that looks like an autonym.
@@ -71,7 +89,7 @@
 		assert.ok( $.fn.uls, "$.fn.uls is defined" );
 	} );
 
-	test( "-- $.uls.data testing", 40, function ( assert ) {
+	test( "-- $.uls.data testing", 41, function ( assert ) {
 
 		assert.strictEqual( $.uls.data.isRedirect( 'sr-ec' ), 'sr-cyrl', "'sr-ec' is a redirect to 'sr-cyrl'" );
 		var autonyms = $.uls.data.getAutonyms();
@@ -82,7 +100,9 @@
 		// This test assumes that we don't want any scripts to be in the 'Other'
 		// group. Actually, this may become wrong some day.
 		assert.deepEqual( orphanScripts(), [], 'All scripts belong to script groups.' );
+
 		assert.deepEqual( badRedirects(), [], 'All redirects have valid targets.' );
+		assert.deepEqual( doubleRedirects(), [], 'There are no double redirects.' );
 		assert.deepEqual( languagesWithoutAutonym(), [], 'All languages have autonyms.' );
 
 		assert.strictEqual(
@@ -116,17 +136,17 @@
 
 		assert.deepEqual( $.uls.data.getLanguagesInRegion( "PA" ),
 			[
-				"ace", "bi", "ch", "en-gb", "en", "fj", "haw", "hif", "hif-latn", "ho", "jv", "jv-java",
+				"ace", "bi", "ch", "en-gb", "en", "fj", "haw", "hif", "ho", "jv", "jv-java",
 				"mh", "mi", "na", "niu", "pih", "pis", "pt", "rtm", "sm", "tet",
 				"to", "tpi", "ty", "wls"
 			],
 			"languages of region PA are selected correctly" );
 		assert.deepEqual( $.uls.data.getLanguagesInRegions( ["AM", "WW"] ),
 			[
-				"akz", "arn", "aro", "ase", "avk", "ay", "cho", "chr", "chy", "cr", "cr-cans", "cr-latn",
+				"akz", "arn", "aro", "ase", "avk", "ay", "cho", "chr", "chy", "cr", "cr-latn",
 				"en-ca", "en", "eo", "es-419", "es-formal", "es", "esu", "fr", "gcf", "gn",
 				"guc", "haw", "ht", "ia", "ie", "ik", "ike-cans", "ike-latn", "io", "iu", "jam",
-				"jbo", "kgp", "kl", "lad", "lad-latn", "lad-hebr", "lfn", "mfe", "mic", "mus", "nah", "nl-informal", "nl",
+				"jbo", "kgp", "kl", "lad-latn", "lad-hebr", "lfn", "mfe", "mic", "mus", "nah", "nl-informal", "nl",
 				"nov", "nv", "pap", "pdc", "pdt", "ppl", "pt-br", "pt", "qu", "qug", "rap", "sei",
 				"simple", "srn", "tokipona", "vo", "yi", "yrl", "yua"
 			],
@@ -157,7 +177,7 @@
 
 		var languagesByScriptInAM = $.uls.data.getLanguagesByScriptInRegion( "AM" );
 		assert.deepEqual( languagesByScriptInAM['Cans'], [
-			"cr", "cr-cans", "ike-cans", "iu"
+			"cr", "ike-cans", "iu"
 		], "correct languages in Cans in AM selected" );
 
 		var languagesByScriptInEU = $.uls.data.getLanguagesByScriptInRegion( "EU" );