Make all autonyms unique and add a test for this

In a list of languages to select autonyms must be unique so that
every user would know what to select.

* Batak Toba language in the Batak writing variant (bbc-batk) has
  an autonum in the right script now. This is taken from the Indonesian
  Wikipedia article "Surat Batak".
* Similarly to the practice with pa -> pa-guru:
  * iu for Inuktitut in the Canadian script redirects to ike-cans.
  * ks for Kashmiri in the Arabic writing redirects to ks-arab.
  * tg for Tajik in the Cyrillic script redirects to tg-cyrl.
* zgh has an updated autonym, taken from Ethologue.
* zh-classical redirects to lzh, similarly to zh-yue -> yue.

data/generated-langdb.json

@@ -316,14 +316,10 @@
             [
                 "AS"
             ],
-            "Batak Toba"
+            "ᯅᯖᯂ᯲ ᯖᯬᯅ"
         ],
         "bbc": [
-            "Latn",
+            "bbc-latn"
-            [
-                "AS"
-            ],
-            "Batak Toba"
         ],
         "bcc": [
             "Arab",
@@ -1445,11 +1441,7 @@
             "italiano"
         ],
         "iu": [
-            "Cans",
+            "ike-cans"
-            [
-                "AM"
-            ],
-            "ᐃᓄᒃᑎᑐᑦ"
         ],
         "ja": [
             "Jpan",
@@ -1756,11 +1748,7 @@
             "कॉशुर"
         ],
         "ks": [
-            "Arab",
+            "ks-arab"
-            [
-                "AS"
-            ],
-            "کٲشُر"
         ],
         "ksf": [
             "Latn",
@@ -3239,11 +3227,7 @@
             "tojikī"
         ],
         "tg": [
-            "Cyrl",
+            "tg-cyrl"
-            [
-                "AS"
-            ],
-            "тоҷикӣ"
         ],
         "th": [
             "Thai",
@@ -3700,7 +3684,7 @@
             [
                 "AF"
             ],
-            "ⵜⴰⵎⴰⵣⵉⵖⵜ"
+            "ⵜⴰⵎⴰⵣⵉⵖⵜ ⵜⴰⵏⴰⵡⴰⵢⵜ"
         ],
         "zh": [
             "Hans",
@@ -3710,11 +3694,7 @@
             "中文"
         ],
         "zh-classical": [
-            "Hant",
+            "lzh"
-            [
-                "AS"
-            ],
-            "文言"
         ],
         "zh-cn": [
             "Hans",
@@ -4076,7 +4056,7 @@
             "pdt",
             "cr",
             "yi",
-            "iu",
+            "ike-cans",
             "atj"
         ],
         "CC": [
@@ -4356,7 +4336,7 @@
             "zh",
             "el",
             "it",
-            "ks",
+            "ks-arab",
             "gd",
             "yi",
             "ml",
@@ -4483,7 +4463,7 @@
             "bug",
             "bjn",
             "ace",
-            "bbc",
+            "bbc-latn",
             "zh-hant",
             "zh",
             "sly",
@@ -4531,7 +4511,7 @@
             "hne",
             "ne",
             "sat",
-            "ks",
+            "ks-arab",
             "gom-deva",
             "sd",
             "doi",
@@ -4984,10 +4964,10 @@
             "brh",
             "fa",
             "bgn",
-            "tg",
+            "tg-cyrl",
             "bft",
             "khw",
-            "ks"
+            "ks-arab"
         ],
         "PL": [
             "pl",
@@ -5242,7 +5222,7 @@
             "shn"
         ],
         "TJ": [
-            "tg",
+            "tg-cyrl",
             "ru",
             "fa",
             "ar"

data/langdb.yaml

@@ -51,9 +51,8 @@ languages:
   bar: [Latn, [EU], Boarisch]
   bat-smg: [sgs]
   bbc-latn: [Latn, [AS], Batak Toba]
- # FIXME - autonym in the Batak script is unknown
+  bbc-batk: [Batk, [AS], ᯅᯖᯂ᯲ ᯖᯬᯅ]
-  bbc-batk: [Batk, [AS], Batak Toba]
+  bbc: [bbc-latn]
-  bbc: [Latn, [AS], Batak Toba]
   bcc: [Arab, [AS, ME], جهلسری بلوچی]
   bcl: [Latn, [AS], Bikol Central]
   be-tarask: [Cyrl, [EU], беларуская (тарашкевіца)]
@@ -228,8 +227,7 @@ languages:
   io: [Latn, [WW], Ido]
   is: [Latn, [EU], íslenska]
   it: [Latn, [EU], italiano]
- # For variants ike-* is used
+  iu: [ike-cans]
-  iu: [Cans, [AM], ᐃᓄᒃᑎᑐᑦ]
   ja: [Jpan, [AS], 日本語]
   jam: [Latn, [AM], Patois]
   jbo: [Latn, [WW], lojban]
@@ -279,7 +277,7 @@ languages:
   krl: [Latn, [EU], Karjala]
   ks-arab: [Arab, [AS], کٲشُر]
   ks-deva: [Deva, [AS], कॉशुर]
-  ks: [Arab, [AS], کٲشُر]
+  ks: [ks-arab]
   ksf: [Latn, [AF], Bafia]
   ksh: [Latn, [EU], Ripoarisch]
  # CLDR uses ku-latn and ku-arab. Latin is more common and is used in Wikipedia.
@@ -502,7 +500,7 @@ languages:
   tet: [Latn, [AS, PA], tetun]
   tg-cyrl: [Cyrl, [AS], тоҷикӣ]
   tg-latn: [Latn, [AS], tojikī]
-  tg: [Cyrl, [AS], тоҷикӣ]
+  tg: [tg-cyrl]
   th: [Thai, [AS], ไทย]
   ti: [Ethi, [AF], ትግርኛ]
   tig: [Ethi, [AF], ትግረ]
@@ -570,10 +568,10 @@ languages:
   yue: [Hant, [AS], 粵語]
   za: [Latn, [AS], Vahcuengh]
   zea: [Latn, [EU], Zeêuws]
-  zgh: [Tfng, [AF], ⵜⴰⵎⴰⵣⵉⵖⵜ]
+  zgh: [Tfng, [AF], ⵜⴰⵎⴰⵣⵉⵖⵜ ⵜⴰⵏⴰⵡⴰⵢⵜ]
  # world? (may apply to many varieties of Chinese)
   zh: [Hans, [AS], 中文]
-  zh-classical: [Hant, [AS], 文言]
+  zh-classical: [lzh]
   zh-cn: [Hans, [AS], 中文（中国大陆）]
   zh-hans: [Hans, [AS], 中文（简体）]
   zh-hant: [Hant, [AS], 中文（繁體）]

src/jquery.uls.data.js

@@ -3,5 +3,5 @@
 	'use strict';
 	$.uls = $.uls || {};
 	//noinspection JSHint
-	$.uls.data = {"languages":{"aa":["Latn",["AF"],"Qafár af"],"ab":["Cyrl",["EU"],"Аҧсшәа"],"abs":["Latn",["AS"],"Bahasa Ambon"],"ace":["Latn",["AS","PA"],"Acèh"],"acf":["Latn",["AM"],"kwéyòl"],"ady":["Cyrl",["EU","ME"],"Адыгабзэ"],"ady-cyrl":["ady"],"ady-latn":["Latn",["EU","ME"],"Adygabze"],"aeb":["aeb-arab"],"aeb-arab":["Arab",["AF"],"تونسي"],"aeb-latn":["Latn",["AF"],"Tûnsî"],"af":["Latn",["AF"],"Afrikaans"],"ahr":["Deva",["AS"],"अहिराणी"],"ais":["Latn",["AS"],"Sakizaya"],"ak":["Latn",["AF"],"Akan"],"akz":["Latn",["AM"],"Albaamo innaaɬiilka"],"aln":["Latn",["EU"],"Gegë"],"am":["Ethi",["AF"],"አማርኛ"],"ami":["Latn",["AS"],"Pangcah"],"an":["Latn",["EU"],"aragonés"],"ang":["Latn",["EU"],"Ænglisc"],"anp":["Deva",["AS"],"अङ्गिका"],"ar":["Arab",["ME"],"العربية"],"arc":["Syrc",["ME"],"ܐܪܡܝܐ"],"arn":["Latn",["AM"],"mapudungun"],"aro":["Latn",["AM"],"Araona"],"arq":["Arab",["AF"],"جازايرية"],"ary":["Latn",["ME"],"Maġribi"],"arz":["Arab",["ME"],"مصرى"],"as":["Beng",["AS"],"অসমীয়া"],"ase":["Sgnw",["AM"],"American sign language"],"ast":["Latn",["EU"],"asturianu"],"atj":["Latn",["AM"],"atikamekw"],"av":["Cyrl",["EU"],"авар"],"avk":["Latn",["WW"],"Kotava"],"ay":["Latn",["AM"],"Aymar aru"],"az":["az-latn"],"az-arab":["Arab",["AS","ME"],"تۆرکجه"],"az-latn":["Latn",["EU","ME"],"azərbaycanca"],"az-cyrl":["Cyrl",["EU","ME"],"азәрбајҹанҹа"],"azb":["az-arab"],"azj":["az-latn"],"ba":["Cyrl",["EU"],"башҡортса"],"ban":["Bali",["AS"],"ᬩᬲᬩᬮᬶ"],"bar":["Latn",["EU"],"Boarisch"],"bat-smg":["sgs"],"bbc-latn":["Latn",["AS"],"Batak Toba"],"bbc-batk":["Batk",["AS"],"Batak Toba"],"bbc":["Latn",["AS"],"Batak Toba"],"bcc":["Arab",["AS","ME"],"جهلسری بلوچی"],"bcl":["Latn",["AS"],"Bikol Central"],"be-tarask":["Cyrl",["EU"],"беларуская (тарашкевіца)"],"be-x-old":["be-tarask"],"be":["Cyrl",["EU"],"беларуская"],"bew":["Latn",["AS"],"Bahasa Betawi"],"bfa":["Latn",["AF"],"Bari"],"bft":["Arab",["AS"],"بلتی"],"bfq":["Taml",["AS"],"படகா"],"bg":["Cyrl",["EU"],"български"],"bgn":["Arab",["AS","ME"],"روچ کپتین بلوچی"],"bh":["bho"],"bho":["Deva",["AS"],"भोजपुरी"],"bi":["Latn",["PA"],"Bislama"],"bjn":["Latn",["AS"],"Bahasa Banjar"],"bm":["Latn",["AF"],"bamanankan"],"bn":["Beng",["AS"],"বাংলা"],"bo":["Tibt",["AS"],"བོད་ཡིག"],"bpy":["Beng",["AS"],"বিষ্ণুপ্রিয়া মণিপুরী"],"bqi":["Arab",["AS","ME"],"بختیاری"],"br":["Latn",["EU"],"brezhoneg"],"brh":["Latn",["ME","AS"],"Bráhuí"],"brx":["Deva",["AS"],"बड़ो"],"bs":["Latn",["EU"],"bosanski"],"bto":["Latn",["AS"],"Iriga Bicolano"],"bug":["Bugi",["AS"],"ᨅᨔ ᨕᨘᨁᨗ"],"bxr":["Cyrl",["AS"],"буряад"],"byn":["Ethi",["AF"],"ብሊን"],"ca":["Latn",["EU"],"català"],"cbk-zam":["Latn",["AS"],"Chavacano de Zamboanga"],"cdo":["Latn",["AS"],"Mìng-dĕ̤ng-ngṳ̄"],"ce":["Cyrl",["EU"],"нохчийн"],"ceb":["Latn",["AS"],"Cebuano"],"ch":["Latn",["PA"],"Chamoru"],"chm":["mhr"],"cho":["Latn",["AM"],"Choctaw"],"chr":["Cher",["AM"],"ᏣᎳᎩ"],"chy":["Latn",["AM"],"Tsetsêhestâhese"],"ciw":["Latn",["AM"],"Ojibwemowin"],"cjy":["cjy-hant"],"cjy-hans":["Hans",["AS"],"晋语（简化字)"],"cjy-hant":["Hant",["AS"],"晉語"],"ckb":["Arab",["ME"],"کوردیی ناوەندی"],"cnh":["Latn",["AS"],"Lai holh"],"co":["Latn",["EU"],"corsu"],"cps":["Latn",["AS"],"Capiceño"],"cr":["Cans",["AM"],"ᓀᐦᐃᔭᐍᐏᐣ"],"cr-cans":["cr"],"cr-latn":["Latn",["AM"],"Nēhiyawēwin"],"crh":["Latn",["EU"],"qırımtatarca"],"crh-cyrl":["Cyrl",["EU"],"къырымтатарджа"],"crh-latn":["crh"],"cs":["Latn",["EU"],"čeština"],"csb":["Latn",["EU"],"kaszëbsczi"],"cu":["Cyrl",["EU"],"словѣньскъ \/ ⰔⰎⰑⰂⰡⰐⰠⰔⰍⰟ"],"cv":["Cyrl",["EU"],"Чӑвашла"],"cy":["Latn",["EU"],"Cymraeg"],"da":["Latn",["EU"],"dansk"],"dag":["Latn",["AF"],"dagbanli"],"de-at":["Latn",["EU"],"Österreichisches Deutsch"],"de-ch":["Latn",["EU"],"Schweizer Hochdeutsch"],"de-formal":["Latn",["EU"],"Deutsch (Sie-Form)"],"de":["Latn",["EU"],"Deutsch"],"din":["Latn",["AF"],"Thuɔŋjäŋ"],"diq":["Latn",["EU","AS"],"Zazaki"],"doi":["Deva",["AS"],"डोगरी"],"dsb":["Latn",["EU"],"dolnoserbski"],"dtp":["Latn",["AS"],"Dusun Bundu-liwan"],"dty":["Deva",["AS"],"डोटेली"],"dv":["Thaa",["AS"],"ދިވެހިބަސް"],"dz":["Tibt",["AS"],"ཇོང་ཁ"],"ee":["Latn",["AF"],"eʋegbe"],"egl":["Latn",["EU"],"Emiliàn"],"el":["Grek",["EU"],"Ελληνικά"],"eml":["Latn",["EU"],"emiliàn e rumagnòl"],"en-ca":["Latn",["AM"],"Canadian English"],"en-gb":["Latn",["EU","AS","PA"],"British English"],"en":["Latn",["EU","AM","AF","ME","AS","PA","WW"],"English"],"eo":["Latn",["WW"],"Esperanto"],"es-419":["Latn",["AM"],"español de America Latina"],"es-formal":["Latn",["EU","AM","AF","WW"],"español (formal)"],"es":["LatnLine truncated
+	$.uls.data = {"languages":{"aa":["Latn",["AF"],"Qafár af"],"ab":["Cyrl",["EU"],"Аҧсшәа"],"abs":["Latn",["AS"],"Bahasa Ambon"],"ace":["Latn",["AS","PA"],"Acèh"],"acf":["Latn",["AM"],"kwéyòl"],"ady":["Cyrl",["EU","ME"],"Адыгабзэ"],"ady-cyrl":["ady"],"ady-latn":["Latn",["EU","ME"],"Adygabze"],"aeb":["aeb-arab"],"aeb-arab":["Arab",["AF"],"تونسي"],"aeb-latn":["Latn",["AF"],"Tûnsî"],"af":["Latn",["AF"],"Afrikaans"],"ahr":["Deva",["AS"],"अहिराणी"],"ais":["Latn",["AS"],"Sakizaya"],"ak":["Latn",["AF"],"Akan"],"akz":["Latn",["AM"],"Albaamo innaaɬiilka"],"aln":["Latn",["EU"],"Gegë"],"am":["Ethi",["AF"],"አማርኛ"],"ami":["Latn",["AS"],"Pangcah"],"an":["Latn",["EU"],"aragonés"],"ang":["Latn",["EU"],"Ænglisc"],"anp":["Deva",["AS"],"अङ्गिका"],"ar":["Arab",["ME"],"العربية"],"arc":["Syrc",["ME"],"ܐܪܡܝܐ"],"arn":["Latn",["AM"],"mapudungun"],"aro":["Latn",["AM"],"Araona"],"arq":["Arab",["AF"],"جازايرية"],"ary":["Latn",["ME"],"Maġribi"],"arz":["Arab",["ME"],"مصرى"],"as":["Beng",["AS"],"অসমীয়া"],"ase":["Sgnw",["AM"],"American sign language"],"ast":["Latn",["EU"],"asturianu"],"atj":["Latn",["AM"],"atikamekw"],"av":["Cyrl",["EU"],"авар"],"avk":["Latn",["WW"],"Kotava"],"ay":["Latn",["AM"],"Aymar aru"],"az":["az-latn"],"az-arab":["Arab",["AS","ME"],"تۆرکجه"],"az-latn":["Latn",["EU","ME"],"azərbaycanca"],"az-cyrl":["Cyrl",["EU","ME"],"азәрбајҹанҹа"],"azb":["az-arab"],"azj":["az-latn"],"ba":["Cyrl",["EU"],"башҡортса"],"ban":["Bali",["AS"],"ᬩᬲᬩᬮᬶ"],"bar":["Latn",["EU"],"Boarisch"],"bat-smg":["sgs"],"bbc-latn":["Latn",["AS"],"Batak Toba"],"bbc-batk":["Batk",["AS"],"ᯅᯖᯂ᯲ ᯖᯬᯅ"],"bbc":["bbc-latn"],"bcc":["Arab",["AS","ME"],"جهلسری بلوچی"],"bcl":["Latn",["AS"],"Bikol Central"],"be-tarask":["Cyrl",["EU"],"беларуская (тарашкевіца)"],"be-x-old":["be-tarask"],"be":["Cyrl",["EU"],"беларуская"],"bew":["Latn",["AS"],"Bahasa Betawi"],"bfa":["Latn",["AF"],"Bari"],"bft":["Arab",["AS"],"بلتی"],"bfq":["Taml",["AS"],"படகா"],"bg":["Cyrl",["EU"],"български"],"bgn":["Arab",["AS","ME"],"روچ کپتین بلوچی"],"bh":["bho"],"bho":["Deva",["AS"],"भोजपुरी"],"bi":["Latn",["PA"],"Bislama"],"bjn":["Latn",["AS"],"Bahasa Banjar"],"bm":["Latn",["AF"],"bamanankan"],"bn":["Beng",["AS"],"বাংলা"],"bo":["Tibt",["AS"],"བོད་ཡིག"],"bpy":["Beng",["AS"],"বিষ্ণুপ্রিয়া মণিপুরী"],"bqi":["Arab",["AS","ME"],"بختیاری"],"br":["Latn",["EU"],"brezhoneg"],"brh":["Latn",["ME","AS"],"Bráhuí"],"brx":["Deva",["AS"],"बड़ो"],"bs":["Latn",["EU"],"bosanski"],"bto":["Latn",["AS"],"Iriga Bicolano"],"bug":["Bugi",["AS"],"ᨅᨔ ᨕᨘᨁᨗ"],"bxr":["Cyrl",["AS"],"буряад"],"byn":["Ethi",["AF"],"ብሊን"],"ca":["Latn",["EU"],"català"],"cbk-zam":["Latn",["AS"],"Chavacano de Zamboanga"],"cdo":["Latn",["AS"],"Mìng-dĕ̤ng-ngṳ̄"],"ce":["Cyrl",["EU"],"нохчийн"],"ceb":["Latn",["AS"],"Cebuano"],"ch":["Latn",["PA"],"Chamoru"],"chm":["mhr"],"cho":["Latn",["AM"],"Choctaw"],"chr":["Cher",["AM"],"ᏣᎳᎩ"],"chy":["Latn",["AM"],"Tsetsêhestâhese"],"ciw":["Latn",["AM"],"Ojibwemowin"],"cjy":["cjy-hant"],"cjy-hans":["Hans",["AS"],"晋语（简化字)"],"cjy-hant":["Hant",["AS"],"晉語"],"ckb":["Arab",["ME"],"کوردیی ناوەندی"],"cnh":["Latn",["AS"],"Lai holh"],"co":["Latn",["EU"],"corsu"],"cps":["Latn",["AS"],"Capiceño"],"cr":["Cans",["AM"],"ᓀᐦᐃᔭᐍᐏᐣ"],"cr-cans":["cr"],"cr-latn":["Latn",["AM"],"Nēhiyawēwin"],"crh":["Latn",["EU"],"qırımtatarca"],"crh-cyrl":["Cyrl",["EU"],"къырымтатарджа"],"crh-latn":["crh"],"cs":["Latn",["EU"],"čeština"],"csb":["Latn",["EU"],"kaszëbsczi"],"cu":["Cyrl",["EU"],"словѣньскъ \/ ⰔⰎⰑⰂⰡⰐⰠⰔⰍⰟ"],"cv":["Cyrl",["EU"],"Чӑвашла"],"cy":["Latn",["EU"],"Cymraeg"],"da":["Latn",["EU"],"dansk"],"dag":["Latn",["AF"],"dagbanli"],"de-at":["Latn",["EU"],"Österreichisches Deutsch"],"de-ch":["Latn",["EU"],"Schweizer Hochdeutsch"],"de-formal":["Latn",["EU"],"Deutsch (Sie-Form)"],"de":["Latn",["EU"],"Deutsch"],"din":["Latn",["AF"],"Thuɔŋjäŋ"],"diq":["Latn",["EU","AS"],"Zazaki"],"doi":["Deva",["AS"],"डोगरी"],"dsb":["Latn",["EU"],"dolnoserbski"],"dtp":["Latn",["AS"],"Dusun Bundu-liwan"],"dty":["Deva",["AS"],"डोटेली"],"dv":["Thaa",["AS"],"ދިވެހިބަސް"],"dz":["Tibt",["AS"],"ཇོང་ཁ"],"ee":["Latn",["AF"],"eʋegbe"],"egl":["Latn",["EU"],"Emiliàn"],"el":["Grek",["EU"],"Ελληνικά"],"eml":["Latn",["EU"],"emiliàn e rumagnòl"],"en-ca":["Latn",["AM"],"Canadian English"],"en-gb":["Latn",["EU","AS","PA"],"British English"],"en":["Latn",["EU","AM","AF","ME","AS","PA","WW"],"English"],"eo":["Latn",["WW"],"Esperanto"],"es-419":["Latn",["AM"],"español de America Latina"],"es-formal":["Latn",["EU","AM","AF","WW"],"español (formal)"],"es":["Latn",["Line truncated
 } ( jQuery ) );

test/jquery.uls.test.js

@@ -20,7 +20,7 @@
 
 	module( 'jquery.uls' );
 
-	var orphanScripts, badRedirects, doubleRedirects, languagesWithoutAutonym;
+	var orphanScripts, badRedirects, doubleRedirects, doubleAutonyms, languagesWithoutAutonym;
 
 	/*
 	 * Runs over all script codes mentioned in langdb and checks whether
@@ -59,6 +59,31 @@
 		return result;
 	};
 
+	/*
+	 * Runs over all languages and checks that all autonyms are unique.
+	 */
+	doubleAutonyms = function () {
+		var language, autonym,
+			autonyms = [],
+			duplicateAutonyms = [];
+
+		for ( language in $.uls.data.languages ) {
+			if ( $.uls.data.isRedirect( language ) ) {
+				continue;
+			}
+
+			autonym = $.uls.data.getAutonym( language );
+
+			if ( $.inArray( autonym, autonyms ) > -1 ) {
+				duplicateAutonyms.push( language );
+			}
+
+			autonyms.push( autonym );
+		}
+
+		return duplicateAutonyms;
+	};
+
 	/*
 	 * Runs over all languages and checks that all redirects point to a language.
 	 * There's no reason to have double redirects.
@@ -99,7 +124,7 @@
 		assert.ok( $.fn.uls, '$.fn.uls is defined' );
 	} );
 
-	test( '-- $.uls.data testing', 30, function ( assert ) {
+	test( '-- $.uls.data testing', 31, function ( assert ) {
 		var autonyms,
 			languagesToGroup, groupedLanguages;
 
@@ -126,6 +151,7 @@
 		assert.deepEqual( badRedirects(), [], 'All redirects have valid targets.' );
 		assert.deepEqual( doubleRedirects(), [], 'There are no double redirects.' );
 		assert.deepEqual( languagesWithoutAutonym(), [], 'All languages have autonyms.' );
+		assert.deepEqual( doubleAutonyms(), [], 'All languages have distinct autonyms.' );
 
 		assert.strictEqual(
 			$.uls.data.getGroupOfScript( 'Beng' ),