PHP code example of nitotm / efficient-language-detector

    
        
<?php
require_once('vendor/autoload.php');

/* Start to develop here. Best regards https://php-download.com/ */

    

nitotm / efficient-language-detector example snippets

// e Nitotm\Eld\{LanguageDetector, EldDataFile, EldFormat};

// LanguageDetector(databaseFile: ?string, outputFormat: ?string)
$eld = new LanguageDetector(EldDataFile::SMALL, EldFormat::ISO639_1);
// Database files: 'small', 'medium', 'large', 'extralarge'. Check memory g, float>, isReliable() => bool )
// ( language => 'es', scores() => ['es' => 0.25, 'nl' => 0.05], isReliable() => true )

$eld->detect('Hola, cómo te llamas?')->language;
// 'es'

// It always accepts ISO 639-1 codes, as well as the selected output format if different.
// langSubset(languages: [], save: true, encode: true); Will return subset file name if saved
$eld->langSubset(['en', 'es', 'fr', 'it', 'nl', 'de']);
// Object ( success => bool, languages => ?array, error => ?string, file => ?string )
// ( success => true, languages => ['en', 'es'...], error => NULL, file => 'small_6_mfss...' )

// to remove the subset
$eld->langSubset();

// The best and fastest way to use a subset, is to load it just like a default database
$eld_subset = new Nitotm\Eld\LanguageDetector('small_6_mfss5z1t');

// if enableTextCleanup(True), detect() removes Urls, .com domains, emails, alphanumerical...
// Not recommended, as urls & domains contain hints of a language, which might help accuracy
$eld->enableTextCleanup(true); // Default is false

// If needed, we can get info of the ELD instance: languages, database type, etc.
$eld->info();

new Nitotm\Eld\Tests\TestsAutoload();

bash
$ php efficient-language-detector/tests/tests.php # Update path