Merge pull request #225 from wikimedia/nikerabbit-langdbterritories

Improve our languages spoken by territory data
This commit is contained in:
Santhosh Thottingal committed 2016-06-02 09:15:53 +05:30
commit 20eea5de9f
3 files changed
+5282 -5

No files matched your search

File diff suppressed because it is too large. Load diff
+48 -4
View File
@@ -64,23 +64,67 @@ foreach ( $supplementalData->territoryInfo->territory as $territoryRecord ) {
$languageCodeAttr = $languageAttributes['type'];
// Lower case is a convention for language codes in ULS.
// '_' is used in CLDR for compound codes and it's replaced with '-' here.
$parsedLangdb['territories'][$territoryCode][] =
strtr( strtolower( (string) $languageCodeAttr[0] ), '_', '-' );
$normalisedCode = strtr( strtolower( (string) $languageCodeAttr[0] ), '_', '-' );
$parsedLangdb['territories'][$territoryCode][] = $normalisedCode;
// In case of codes with variants, also add the base because ULS might consider
// them as separate languages, e.g. zh, zh-hant and zh-hans.
if ( strpos( $normalisedCode, '-' ) !== false ) {
$parts = explode( '-', $normalisedCode );
$parsedLangdb['territories'][$territoryCode][] = $parts[0];
}
}
}
foreach ( $parsedLangdb['territories'] as $territoryCode => $languages ) {
foreach ( $languages as $index => $language ) {
if ( !isset( $parsedLangdb['languages'][$language] ) ) {
echo "Unknown language $language for territory $territoryCode\n";
unset( $parsedLangdb['territories'][$territoryCode][$index] );
continue;
}
$data = $parsedLangdb['languages'][$language];
if ( count( $data ) === 1 ) {
echo "Redirect for language $language to {$data[0]} territory $territoryCode\n";
$parsedLangdb['territories'][$territoryCode][$index] = $data[0];
continue;
}
}
// Clean-up to save space
if ( count( $parsedLangdb['territories'][$territoryCode] ) === 0 ) {
unset( $parsedLangdb['territories'][$territoryCode] );
continue;
}
// Remove duplicates we might have created
$parsedLangdb['territories'][$territoryCode] =
array_unique( $parsedLangdb['territories'][$territoryCode] );
// We need to renumber or json conversion thinks these are objects
$parsedLangdb['territories'][$territoryCode] =
array_values( $parsedLangdb['territories'][$territoryCode] );
}
print "Writing JSON langdb...\n";
$json = json_encode( $parsedLangdb, JSON_UNESCAPED_UNICODE );
$jsonVerbose = json_encode( $parsedLangdb, JSON_PRETTY_PRINT | JSON_UNESCAPED_UNICODE );
$jsonSlim = json_encode( $parsedLangdb, JSON_UNESCAPED_UNICODE );
$js = <<<JAVASCRIPT
// Please do not edit. This file is generated from data/langdb.yaml by ulsdata2json.php
( function ( $ ) {
'use strict';
$.uls = $.uls || {};
//noinspection JSHint
$.uls.data = $json;
$.uls.data = $jsonSlim;
} ( jQuery ) );
JAVASCRIPT;
file_put_contents( '../src/jquery.uls.data.js', $js );
// For making diff review easier.
file_put_contents( 'generated-langdb.json', $jsonVerbose );
print "Done.\n";
+1 -1
View File
@@ -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"],"ak":["Latn",["AF"],"Akan"],"akz":["Latn",["AM"],"Albaamo innaaɬiilka"],"aln":["Latn",["EU"],"Gegë"],"am":["Ethi",["AF"],"አማርኛ"],"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"],"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"],"bfq":["Taml",["AS"],"படகா"],"bg":["Cyrl",["EU"],"български"],"bgn":["Arab",["AS","ME"],"روچ کپتین بلوچی"],"bh":["Deva",["AS"],"भोजपुरी"],"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"],"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"],"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"],"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"],"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",["EU","AM","AF","WW"],"español"],"esu":["Latn",["AM"],"Yup'ik"],"et":["Latn",["EU"],"eesti"],"eu":["Latn",["EU"],"euskara"],"ext":["Latn",["EU"],"estremeñu"],"fa":["Arab",["AS","ME"],"فارسی"],"ff":["Latn",["AF"],Line 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"],"ak":["Latn",["AF"],"Akan"],"akz":["Latn",["AM"],"Albaamo innaaɬiilka"],"aln":["Latn",["EU"],"Gegë"],"am":["Ethi",["AF"],"አማርኛ"],"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"],"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"],"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"],"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"],"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"],"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"],"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",["EU","AM","AF","WW"],"español"],"esu":["Latn",["AM"],"Yup'ik"],"et":["Latn",["EU"],"eesti"],"eu":["Latn",["EU"],"euskara"],"ext":["Latn",["EU"],"estremeñu"],"fa":["Arab",["AS","ME"],"فارسی"],"ff":["Latn",["AF"],"Fulfulde"],"fi":["Latn",["EU"],Line truncated
} ( jQuery ) );