Examples of com.cybozu.labs.langdetect.Detector

com.cybozu.labs.langdetect.Detector
{@link Detector} class is to detect language from specified text. Its instance is able to be constructed via the factory class {@link DetectorFactory}.
After appending a target text to the {@link Detector} instance with {@link #append(Reader)} or {@link #append(String)}, the detector provides the language detection results for target text via {@link #detect()} or {@link #getProbabilities()}. {@link #detect()} method returns a single language name which has the highest probability.{@link #getProbabilities()} methods returns a list of multiple languages and their probabilities.
The detector has some parameters for language detection. See {@link #setAlpha(double)}, {@link #setMaxTextLength(int)} and {@link #setPriorMap(HashMap)}.
```
 import java.util.ArrayList; import com.cybozu.labs.langdetect.Detector; import com.cybozu.labs.langdetect.DetectorFactory; import com.cybozu.labs.langdetect.Language; class LangDetectSample { public void init(String profileDirectory) throws LangDetectException { DetectorFactory.loadProfile(profileDirectory); } public String detect(String text) throws LangDetectException { Detector detector = DetectorFactory.create(); detector.append(text); return detector.detect(); } public ArrayList detectLangs(String text) throws LangDetectException { Detector detector = DetectorFactory.create(); detector.append(text); return detector.getProbabilities(); } } 
```
- 4x faster improvement based on Elmer Garduno's code. Thanks!
@author Nakatani Shuyo @see DetectorFactory

    public boolean hasTranslatedProperty(GraphPropertyWorkData data, String translatedTextPropertyKey) {
        return data.getElement().getProperty(translatedTextPropertyKey, data.getProperty().getName()) != null;
    }


    private String detectLanguage(String text) throws LangDetectException, IOException {
        Detector detector = DetectorFactory.create();
        detector.append(text);
        String lang = detector.detect();
        if (lang.length() == 0) {
            return null;
        }
        return lang;
    }

View Full Code Here

    try {
      if (!isLoadLanguageProfile) {
        DetectorFactory.loadProfile("language_detect");
        isLoadLanguageProfile = true;
      }
      Detector detector = DetectorFactory.create();
      detector.append(title);
      lang = detector.detect();
    } catch (LangDetectException e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
    }
    int type = 1;

View Full Code Here

    try {
      if (!isLoadLanguageProfile) {
        DetectorFactory.loadProfile("language_detect");
        isLoadLanguageProfile = true;
      }
      Detector detector = DetectorFactory.create();
      detector.append(title);
      lang = detector.detect();
    } catch (LangDetectException e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
    }
    int type = 1;

View Full Code Here

    try {
      if (!isLoadLanguageProfile) {
        DetectorFactory.loadProfile("language_detect");
        isLoadLanguageProfile = true;
      }
      Detector detector = DetectorFactory.create();
      detector.append(title);
      lang = detector.detect();
    } catch (LangDetectException e) {
      e.printStackTrace();
    }
    int type = 1;
    if (lang.equalsIgnoreCase("en")) {

View Full Code Here

    try {
      if (!isLoadLanguageProfile) {
        DetectorFactory.loadProfile("language_detect");
        isLoadLanguageProfile = true;
      }
      Detector detector = DetectorFactory.create();
      detector.append(title);
      lang = detector.detect();
    } catch (LangDetectException e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
    }
    int type = 1;

View Full Code Here

    try {
      if (!isLoadLanguageProfile) {
        DetectorFactory.loadProfile("language_detect");
        isLoadLanguageProfile = true;
      }
      Detector detector = DetectorFactory.create();
      detector.append(title);
      lang = detector.detect();
    } catch (LangDetectException e) {
      e.printStackTrace();
    }
    int type = 1;
    if (lang.equalsIgnoreCase("en")) {

View Full Code Here

     */
    public String detect(ServiceContext srvContext, String input) throws Exception {
        if(!LanguageDetector.languageLevelSupported) {
            throw new Exception(LanguageDetector.upgradeMessage);
        }
        Detector detector = DetectorFactory.create();
        detector.append(input);
        String detectedLanguage = detector.detect();  
        // this is to deal with zh-cn and zh-tw in languageprofiles. All other files have a 639-1 2-char filename.
        if(detectedLanguage.length() > 2) {
            detectedLanguage = detectedLanguage.substring(0, 2);
        }
        String iso639_2 = srvContext.getBean(IsoLanguagesMapper.class).iso639_1_to_iso639_2(detectedLanguage);

View Full Code Here

    try {
      if (!isLoadLanguageProfile) {
        DetectorFactory.loadProfile("language_detect");
        isLoadLanguageProfile = true;
      }
      Detector detector = DetectorFactory.create();
      detector.append(title);
      lang = detector.detect();
    } catch (LangDetectException e) {
      // TODO Auto-generated catch block
      e.printStackTrace();
    }
    int type = 1;

View Full Code Here

        DetectorFactory.loadProfile(profileDirectory);
    }
    
    // isLanguage("The quick brown fox.", "en")
    public boolean isLanguage(String text, String langAbbr) {
        Detector detector;
        boolean isLang = false;
        try {
            detector = DetectorFactory.create();
            detector.append(text);
            isLang = detector.detect().startsWith(langAbbr);
        } catch (LangDetectException e) {
            //System.out.println("Could not detect language on: " + text);
        }

View Full Code Here

        }
        return profiles;
    }
    
    public String getLanguage(String text) throws LangDetectException {
        Detector detector = DetectorFactory.create();
        detector.append(text);
        return detector.detect();
    }

View Full Code Here

0 1

TOP

Related Classes of com.cybozu.labs.langdetect.Detector

com.cybozu.labs.langdetect.util.NGram

com.digitalpebble.behemoth.languageidentification.LanguageIdProcessor

com.mozilla.grouperfish.text.filter.LanguageFilter

com.multysite.util.StringHelper

com.tubeilike.util.StringHelper

com.tubemostwanted.util.StringHelper

com.tubeonfire.util.StringHelper

io.lumify.translate.TranslateGraphPropertyWorker

org.apache.stanbol.enhancer.engines.langdetect.LanguageIdentifier

org.fao.geonet.languages.LanguageDetector

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.