A very simple mechanism for importing per-country language lists from CLDR to ULS' langdb. If I understand correctly, we only need languages spoken in a country ordered by number of speakers. The CLDR data already has it and it should be mostly useful. Also added a utility function and a test. Some tweaks to override the CLDR data are still needed: * The data as it is omits some useful languages. For example, Amharic is not listed in Eritrea. * Some countries have a very large number of languages. Ideally it's right, but is not practical currently, for example India with 75. Maybe hand-picking or limiting the choice to top X languages can be useful, but requires thought. * Some language codes are standard, but different from Wikipedia practice, for example "pa_Guru" (we just write "pa"). Maybe a mapping of codes is needed. Change-Id: I3c0cd5a9118997ba39a4f3695978e359f3de6956
81 lines
2.8 KiB
PHP
81 lines
2.8 KiB
PHP
<?php
|
|
/**
|
|
* Script to create the language data in JSON format for ULS.
|
|
*
|
|
* Copyright (C) 2012 Alolita Sharma, Amir Aharoni, Arun Ganesh, Brandon Harris,
|
|
* Niklas Laxström, Pau Giner, Santhosh Thottingal, Siebrand Mazeland and other
|
|
* contributors. See CREDITS for a list.
|
|
*
|
|
* UniversalLanguageSelector is dual licensed GPLv2 or later and MIT. You don't
|
|
* have to do anything special to choose one license or the other and you don't
|
|
* have to notify anyone which license you are using. You are free to use
|
|
* UniversalLanguageSelector in commercial projects as long as the copyright
|
|
* header is left intact. See files GPL-LICENSE and MIT-LICENSE for details.
|
|
*
|
|
* @file
|
|
* @ingroup Extensions
|
|
* @licence GNU General Public Licence 2.0 or later
|
|
* @licence MIT License
|
|
*/
|
|
|
|
include __DIR__ . '/spyc.php';
|
|
|
|
print( "Reading langdb.yaml...\n" );
|
|
$yamlLangdb = file_get_contents( 'langdb.yaml' );
|
|
$parsedLangdb = spyc_load( $yamlLangdb );
|
|
|
|
$supplementalDataFilename = 'supplementalData.xml';
|
|
$supplementalDataUrl = "http://unicode.org/repos/cldr/trunk/common/supplemental/$supplementalDataFilename";
|
|
|
|
$curl = curl_init( $supplementalDataUrl );
|
|
$supplementalDataFile = fopen( $supplementalDataFilename, 'w' );
|
|
|
|
curl_setopt( $curl, CURLOPT_FILE, $supplementalDataFile );
|
|
curl_setopt( $curl, CURLOPT_HEADER, 0 );
|
|
|
|
print( "Trying to download $supplementalDataUrl...\n" );
|
|
$curlSuccess = curl_exec( $curl );
|
|
curl_close( $curl );
|
|
fclose( $supplementalDataFile );
|
|
|
|
if ( !$curlSuccess ) {
|
|
die( "Failed to download CLDR data from $supplementalDataUrl.\n" );
|
|
}
|
|
print( "Downloaded $supplementalDataFilename, trying to parse...\n" );
|
|
|
|
$supplementalData = simplexml_load_file( $supplementalDataFilename );
|
|
|
|
if ( !( $supplementalData instanceof SimpleXMLElement ) ) {
|
|
die( "Attempt to load CLDR data from $supplementalDataFilename failed.\n" );
|
|
}
|
|
|
|
print( "CLDR supplemental data parsed successfully, reading territories info...\n" );
|
|
$parsedLangdb['territories'] = array();
|
|
|
|
foreach ( $supplementalData->territoryInfo->territory as $territoryRecord ) {
|
|
$territoryAtributes = $territoryRecord->attributes();
|
|
$territoryCodeAttr = $territoryAtributes['type'];
|
|
$territoryCode = "$territoryCodeAttr[0]";
|
|
$parsedLangdb['territories'][$territoryCode] = array();
|
|
|
|
foreach ( $territoryRecord->languagePopulation as $languageRecord ) {
|
|
$languageAttributes = $languageRecord->attributes();
|
|
$languageCodeAttr = $languageAttributes['type'];
|
|
$parsedLangdb['territories'][$territoryCode][] = "$languageCodeAttr[0]";
|
|
}
|
|
}
|
|
|
|
print( "Writing JSON langdb...\n" );
|
|
$json = json_encode( $parsedLangdb );
|
|
$js = <<<JAVASCRIPT
|
|
// Please do not edit. This file is generated from data/langdb.yaml by ulsdata2json.php
|
|
( function ( $ ) {
|
|
$.uls = $.uls || {};
|
|
$.uls.data = $json;
|
|
} )( jQuery );
|
|
|
|
JAVASCRIPT;
|
|
file_put_contents( '../src/jquery.uls.data.js', $js );
|
|
|
|
print( "Done.\n" );
|