import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
public static void main(String[] args) throws Exception 
{
	
	BabelMorph bm = BabelMorph.getInstance();
	
	System.out.println(bm.getBabelMorphVersion());
	//retrieve all the available languages
	Set<Language> languages = bm.getBabelMorphLanguages();
	System.out.println("available languages:\n"+languages.toString());
	//retrieve all the available part-of-speech
	Set<POS> pos = bm.getBabelMorphPoS();
    System.out.println("available parts-of-speech:\n"+pos.toString());
	System.out.println("word stats:");
	countAllWordsByPOS(bm);
	System.out.println("lemma stats:");
	countAllLemmasByPOS(bm);
  
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * returns 
 * @param sentence
 * 			input sentence, space delimited
 * @param discardStopWords
 * 			true if stopwords are to be discarded from the sentence 			
 * @return
 * 		a pair containing <list of word-pos, remaining not-handled terms>  
 * 		
 */
public Pair<List<String>, List<String>> getStanfordSentence(String sentence)
{
	List<WordLemmaTag> wlts = SentenceProcessor.getInstance().processSentence(sentence, false);
	
	List<String> terms = null;
	StanfordSentence sSentence = StanfordSentence.fromLine(Strings.join(wlts," "));
	
	try
	{
		 terms = sSentence.getTerms(TAGS, 
				 Language.EN, 
				 null, 
				 MultiwordBelongingTo.WORDNET, 
				 CompoundingParameter.ALLOW_MULTIWORD_EXPRESSIONS,
				 CompoundingParameter.APPEND_POS);	 
	}
	catch(Exception e)
	{
		e.printStackTrace();
	}

	//discards OOVs, and tries to map incorrect pos-tags to the correct ones
	return fixTerms(terms, discardStopwords);
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * A demo to see the translations of a word.
 * 
 * @param lemma
 * @param languageToSearch
 * @param languagesToPrint
 * @throws IOException
 */
public static void testTranslations(String lemma, Language languageToSearch,
                                    Language... languagesToPrint) throws IOException {
    BabelNet bn = BabelNet.getInstance();
    
    List<Language> allowedLanguages = Arrays.asList(languagesToPrint);
    Multimap<Language, ScoredItem<String>> translations =
        bn.getTranslations(languageToSearch, lemma);
    
    for (Language language : translations.keySet()) {
        if (allowedLanguages.contains(language)) {
            System.out.print(""+language);
            for (ScoredItem<String> item : translations.get(language)) {
                System.out.print("\t"+item);
            }
            System.out.println();
        }
    }
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * Get the DBPedia URIs of the {@link BabelSense}s in a specific language
 * found in <b>this</b> {@link BabelSynset}.
 * 
 * @param languages
 * @return the DBPedia URIs of the {@link BabelSense}s in this synset.
 * @see BabelSense#getDBPediaURI()
 */
public List<String> getDBPediaURIs(Language... languages)
{
	List<String> uris = new ArrayList<String>();
	List<Language> langs = Arrays.asList(languages);
	
	for (BabelSense sense : senses)
	{
		if (sense.getSource() != BabelSenseSource.WIKIRED
				&&
				(langs.isEmpty() || langs.contains(sense.getLanguage())))
		{
			String dBPediaURI = sense.getDBPediaURI();
			if (dBPediaURI != null) uris.add(dBPediaURI);
		}
	}
	
	return uris;
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * Gets the {@link BabelSense} for the input word in the given language
 * 
 * @param language language of the sense
 * @param lemma lemma of the sense
 * @param sources possible sources for the sense 
 * @return the {@link BabelSense} for the input word in the given language
 */
public List<BabelSense> getSenses(Language language, String lemma, BabelSenseSource... sources)
{
	List<BabelSenseSource> sourceList = sources.length == 0 ? null : Arrays.asList(sources);
	
	List<BabelSense> result = new ArrayList<BabelSense>();
	for (BabelSense sense : senses)
	{
		if (sense.getSimpleLemma().equalsIgnoreCase(lemma) 
				&& sense.getLanguage().equals(language) 
				&& (sourceList == null || sourceList.contains(sense.getSource())))
		{
			result.add(sense);
		}
	}
	return result;
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * Prints the {@link BabelSense}s of <b>this</b> {@link BabelSynset} only
 * for a specific set of languages.
 * 
 * @param languages
 * @return a stringified representation of <b>this</b> Babel synset using
 *         only the senses in a specific set of languages
 */
public String toString(Language... languages)
{
	StringBuffer sb = new StringBuffer("{");
	Set<Language> languageSet = new HashSet<Language>(Arrays.asList(languages));
	
	for (BabelSense sense : senses)
	{
		if (!languageSet.isEmpty() && !languageSet.contains(sense.getLanguage())) continue;
		
		if (sb.length() > 1) sb.append(",");
		sb.append(" ").append(sense.toString());
	}
	sb.append(" }");
	
	return sb.toString();
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * A demo to explore the BabelNet graph.
 * 
 * 
 * @param synset
 * @throws IOException
 */
public static void testGraph(BabelSynset synset) throws IOException
{
	BabelNet bn = BabelNet.getInstance();
	List<BabelNetGraphEdge> successorsEdges = bn.getSuccessorEdges(synset.getId());

	System.out.println("SYNSET ID:" + synset.getId());
	System.out.println("# OUTGOING EDGES: " + successorsEdges.size());
	
	for (BabelNetGraphEdge edge : successorsEdges)
	{
		System.out.println("\tEDGE " + edge);
		System.out.println("\t" + bn.getSynsetFromId(edge.getTarget()).toString(Language.EN));
		System.out.println();
	}
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * A demo to see the translations of a word.
 * 
 * @param lemma
 * @param languageToSearch
 * @param languagesToPrint
 * @throws IOException
 */
public static void testTranslations(String lemma, Language languageToSearch,
		  							Language... languagesToPrint) throws IOException
{
	BabelNet bn = BabelNet.getInstance();
	
	List<Language> allowedLanguages = Arrays.asList(languagesToPrint);
	Multimap<Language, ScoredItem<String>> translations =
		bn.getTranslations(languageToSearch, lemma);
	
	System.out.println("TRANSLATIONS FOR " + lemma);
	for (Language language : translations.keySet())
	{
		if (allowedLanguages.contains(language))
			System.out.println("\t"+language+"=>"+translations.get(language)); 
	}
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
public static void testImages(String lemma, Language language) throws IOException
{
	BabelNet bn = BabelNet.getInstance();
	System.out.println("SYNSETS WITH word: \""+ lemma + "\"");
	List<BabelSynset> synsets = bn.getSynsets(language, lemma);
	Collections.sort(synsets, new BabelSynsetComparator(lemma));
	for (BabelSynset synset : synsets)
	{
		System.out.println("  =>(" + synset.getId() + ")" +
						 "  MAIN LEMMA: " + synset.getMainSense());
		for (BabelImage img : synset.getImages())
		{
			System.out.println("\tIMAGE URL:" + img.getURL());
			System.out.println("\tIMAGE VALIDATED URL:" + img.getValidatedURL());
			System.out.println("\t==");
		}
		System.out.println("  -----");
	}
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * 
 * @return the available languages 
 */
public Set<Language> getBabelMorphLanguages()throws IOException
{
	Set<Language> languages = new HashSet<>();
	
	Terms terms = SlowCompositeReaderWrapper.wrap(morphologicalDictionary.getIndexReader()).terms(BabelMorphIndexField.LANGUAGE.toString()); 
	TermsEnum termsEnum = terms.iterator();
	BytesRef text;
	while((text = termsEnum.next()) != null) {
	     languages.add(Language.valueOf(text.utf8ToString()));
	}
	return languages;
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * Gets a {@link BabelMorphWord} from a {@link Document}
 * 
 * @param doc
 *            a Lucene {@link Document} record for a certain WktMorphWord
 * @return an instance of a {@link BabelMorphWord} from a {@link Document}
 */
public static BabelMorphWord getBabelMorphFromDocument(Document doc)
{
	try
	{
		String queryLanguage = doc.get(BabelMorphIndexField.LANGUAGE.toString());
		Language lang = Language.valueOf(queryLanguage);
		String queryLemma = doc.get(BabelMorphIndexField.LEMMA.toString());
		String queryPos = doc.get(BabelMorphIndexField.POS.toString());
		POS p = POS.valueOf(queryPos);
		String[] queryForms = doc.getValues(BabelMorphIndexField.FORM.toString());
		String[] queryInfos = doc.getValues(BabelMorphIndexField.INFO.toString());
		
		if( lang == null || queryLemma == null || 
				queryPos == null || p == null || queryForms == null ) return null;
			
		HashMultimap<String, String> multimap =  HashMultimap.create();
		for(int i=0;i<queryForms.length;i++)
			multimap.put(queryForms[i], queryInfos[i]);
		
		BabelMorphWord bmw = new BabelMorphWord(queryLemma, lang, p, multimap);
		return bmw;
	
	}
    catch (Exception e)
    {
		e.printStackTrace();
	}
    
    return null;
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * Initialize the action.
 *
 * @param babelnet        the BabelNet instance.
 * @param language        the language.
 * @param synsetsFilename the synsets input file.
 * @param sensesFilename  the senses output file.
 * @param logger          the logger instance.
 */
public SensesAction(BabelNet babelnet, Language language, String synsetsFilename, String sensesFilename, Logger logger) {
    this.babelnet = babelnet;
    this.language = language;
    this.synsetsFilename = synsetsFilename;
    this.sensesFilename = sensesFilename;
    this.logger = logger;
    logger.log(Level.INFO, "Reading synsets from \"{0}\"", synsetsFilename);
    logger.log(Level.INFO, "Writing senses to \"{0}\"", sensesFilename);
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * Initialize the action.
 *
 * @param babelnet         the BabelNet instance.
 * @param language         the language.
 * @param pos              the part of speech.
 * @param clustersFilename the clusters input file.
 * @param wordsFilename    the words output file.
 * @param synsetsFilename  the synsets output file.
 * @param logger           the logger instance.
 */
public ClustersAction(BabelNet babelnet, Language language, BabelPOS pos, String clustersFilename, String wordsFilename, String synsetsFilename, Logger logger) {
    this.babelnet = babelnet;
    this.language = language;
    this.pos = pos;
    this.clustersFilename = clustersFilename;
    this.wordsFilename = wordsFilename;
    this.synsetsFilename = synsetsFilename;
    this.logger = logger;
    logger.log(Level.INFO, "Reading clusters from \"{0}\"", clustersFilename);
    logger.log(Level.INFO, "Writing words to \"{0}\"", wordsFilename);
    logger.log(Level.INFO, "Writing synsets to \"{0}\"", synsetsFilename);
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
@Test
public void bankBonusPayStock() throws IOException {
	List<Word> sentence = Arrays.asList(
			new Word[]{new Word("bank", "n", Language.EN), new Word("bonus", "n", Language.EN),
					new Word("pay", "v", Language.EN), new Word("stock", "n", Language.EN)});
	disambiguate(sentence, babelnetKb, degreeScorer);
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
private SnowballStemmer getStemmer(Language language) {
    if (language.equals(Language.EN)) {
        return new porterStemmer();
    } else if (language.equals(Language.ES)) {
        return new spanishStemmer();
    } else if (language.equals(Language.FR)) {
        return new frenchStemmer();
    } else if (language.equals(Language.DE)) {
        return new germanStemmer();
    } else if (language.equals(Language.IT)) {
        return new italianStemmer();
    } else {
        return null;
    }
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
private List<BabelSense> lookupSense(Language language, String lemma, POS postag) throws IOException {
    List<BabelSense> senses = babelNet.getSenses(language, lemma, postag, BabelSenseSource.WN);
    if (senses == null || senses.isEmpty()) {
        senses = babelNet.getSenses(language, lemma.replace(" ", "_"), postag, BabelSenseSource.WN);
    }
    if (senses == null || senses.isEmpty()) {
        senses = babelNet.getSenses(language, lemma, postag, BabelSenseSource.WNTR);
    }
    if (senses == null || senses.isEmpty()) {
        senses = babelNet.getSenses(language, lemma.replace(" ", "_"), postag, BabelSenseSource.WNTR);
    }
    if (senses == null || senses.isEmpty()) {
        senses = babelNet.getSenses(language, lemma, postag);
    }
    if (senses == null || senses.isEmpty()) {
        senses = babelNet.getSenses(language, lemma.replace(" ", "_"), postag);
    }
    /*
     if (senses == null || senses.isEmpty()) {
     senses = babelNet.getSenses(language, lemma);
     }
     if (senses == null || senses.isEmpty()) {
     senses = babelNet.getSenses(language, lemma.replace(" ", "_"));
     }
     */
    if (senses == null || senses.isEmpty()) {
        Logger.getLogger(RevisedLesk.class.getName()).log(Level.WARNING, "No senses for {0}, pos-tag {1}", new Object[]{lemma, postag});
    }
    //remove duplicate senses
    if (senses != null && !senses.isEmpty()) {
        Set<String> ids = new HashSet<>();
        for (int i = senses.size() - 1; i >= 0; i--) {
            if (!ids.add(senses.get(i).getSynset().getId())) {
                senses.remove(i);
            }
        }
    }
    return senses;
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * @param args the command line arguments
 */
public static void main(String[] args) {
    try {
        BabelNet babelNet = BabelNet.getInstance();
        List<BabelSense> senses = babelNet.getSenses(Language.IT, args[0],POS.NOUN,BabelSenseSource.WNTR);
        for (BabelSense sense:senses) {
            System.out.println(sense.getSynset().getId()+"\t"+sense.getPosition());
        }
    } catch (IOException ex) {
        Logger.getLogger(TestBabelNet.class.getName()).log(Level.SEVERE, null, ex);
    }
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * Gets a verified version of the full input URL <b>this</b> image. Checks
 * whether possible URLs of this image exist or return 404.
 * 
 * @return a validated, known-to-exists, URL from which an image can be
 *         retrieved.
 */
private static String getValidatedURL(String url, Language language)
{
		String validated = "";
	if (testURLexists(url))
	{
		validated = url;
	}
	else
	{
		String alternateUrl =
			BACKOFF_URL_PREFIX + language.name().toLowerCase() + "/" +
			url.substring(URL_PREFIX.length());
		if (testURLexists(alternateUrl)) validated = alternateUrl;
	}
	
	// not much to do here...
	if (validated.isEmpty()) return null;

	// check that it is not already URL encoded
	if (isURLEncoded(validated)) return validated;

	try
	{
		// encode the URL in an appropriate way
		int idx = validated.indexOf("/", 7);
		String host = validated.substring(7, idx);
		String path = validated.substring(idx);
		URI uri = new URI("http", host,  path, null);
		return uri.toASCIIString();

	}
	catch (URISyntaxException e) { return null; }
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
public static void main(String[] args) {
    if (args.length < 1) {
        System.err.println("Please specify a word to look up on the command line.");
        return;
    }
    try
    {
        String word = args[1];
        Set<Language> languages = new HashSet<Language>();
        // = BabelNetConfiguration.getInstance().getBabelLanguages();

        languages.add(Language.ES);
        languages.add(Language.DE);
        languages.add(Language.EN);

        Language source;
        if (args[0].equals("en")) {
            source = Language.EN;
        } else if (args[0].equals("fr")) {
            source = Language.FR;
        } else if (args[0].equals("nl")) {
            source = Language.NL;
        } else {
            throw new Exception();
        }
        testTranslations(word, source, languages.toArray(new Language[languages.size()]));
    }
    catch (Exception e)
    {
        e.printStackTrace();
    }
}
 

import it.uniroma1.lcl.jlt.util.Language; //导入依赖的package包/类
/**
 * Gets the categories ({@link BabelCategory}s) of <b>this</b>
 * {@link BabelSynset} in a specific language.
 * 
 * @return the categories ({@link BabelCategory}s) of <b>this</b>
 *         {@link BabelSynset} in a certain language.
 */	
public List<BabelCategory> getCategories(Language... languages)
{
	List<Language> langs = Arrays.asList(languages);
	List<BabelCategory> languageCategories = new ArrayList<BabelCategory>();

	for (BabelCategory category : categories)
		if (langs.contains(category.getLanguage()))
			languageCategories.add(category);

	return languageCategories;
}