source: gs3-extensions/maori-lang-detection/src/MaoriDetector.java@ 33335

/**
 * http://opennlp.apache.org/news/model-langdetect-183.html
 * language detector model: http://opennlp.apache.org/models.html
 * Use of Apache OpenNLP in general:
 *   http://opennlp.apache.org/docs/1.9.1/manual/opennlp.html#intro.api
 * Use of OpenNLP for language detection:
 * http://opennlp.apache.org/docs/1.9.1/manual/opennlp.html#tools.langdetect
 * 
 * This code was based on the information and sample code at the above links and the links dispersed throughout this file.
 */

import java.io.*;
import opennlp.tools.langdetect.*;
import opennlp.tools.util.*;

/**
 * Run as:
 *    wharariki:[115]/Scratch/ak19/openNLP-lang-detect/src>javac -cp ".:$OPENNLP_HOME/lib/*" MaoriDetector.java
 *    wharariki:[116]/Scratch/ak19/openNLP-lang-detect/src>java -cp ".:$OPENNLP_HOME/lib/*" MaoriDetector
 *
 * https://stackoverflow.com/questions/219585/including-all-the-jars-in-a-directory-within-the-java-classpath
 * Also has information on how to run this class if it's in a Java package.
 */
public class MaoriDetector {

    /** 
     * Taken from our university website
     * https://www.waikato.ac.nz/maori/
     */
    public static final String TEST_INPUT_TEXT = "Ko tēnei te Whare Wānanga o Waikato e whakatau nei i ngā iwi o te ao, ki roto i te riu o te awa e rere nei, ki runga i te whenua e hora nei, ki raro i te taumaru o ngā maunga whakaruru e tau awhi nei.";
    
    public static void main(String args[]) {
    // http://opennlp.apache.org/docs/1.9.1/manual/opennlp.html#intro.api
    // https://docs.oracle.com/javase/tutorial/essential/exceptions/tryResourceClose.html
    try (InputStream modelIn = new FileInputStream("/Scratch/ak19/openNLP-lang-detect/langdetect-183.bin")) {

        LanguageDetectorModel model = new LanguageDetectorModel(modelIn);

        // http://opennlp.apache.org/docs/1.9.1/manual/opennlp.html#tools.langdetect
        LanguageDetector myCategorizer = new LanguageDetectorME(model);

        // Get the most probable language
        Language bestLanguage = myCategorizer.predictLanguage(TEST_INPUT_TEXT);
        System.out.println("Best language: " + bestLanguage.getLang());
        System.out.println("Best language confidence: " + bestLanguage.getConfidence());

        
        // Get an array with the most probable languages
        Language[] languages = myCategorizer.predictLanguages(TEST_INPUT_TEXT);
        /*
        if(languages == null || languages.length <= 0) {
        System.err.println("No languages predicted for the input text");
        } else {
        for(int i = 0; i < languages.length; i++) {
            System.out.println("Language prediction " + i + ": " + languages[i]);
        }
        }*/
        
    } catch(Exception e) {
        e.printStackTrace();
    }
    
    System.err.println("Exitting program...\n");
    System.exit(0);
    }
}