Java Word类代码示例

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
@Test
public void testIsLexical() throws JWNLException {
    Synset s1 = new Synset(null, POS.NOUN);
    PointerTargetNode p1 = new PointerTargetNode(s1, PointerType.ANTONYM);
    Synset s2 = new Synset(null, POS.NOUN);
    Word w2 = new Word(null, s2, "test");
    PointerTargetNode p2 = new PointerTargetNode(w2, PointerType.ANTONYM);

    Assert.assertFalse(p1.isLexical());
    Assert.assertTrue(p2.isLexical());

    Assert.assertEquals(s1, p1.getSynset());
    Assert.assertEquals(s2, p2.getSynset());

    Assert.assertEquals(s1, p1.getPointerTarget());
    Assert.assertEquals(w2, p2.getPointerTarget());

    Assert.assertNull(p1.getWord());
    Assert.assertEquals(w2, p2.getWord());

    Assert.assertFalse(p1.equals(p2));
    Assert.assertFalse(p1.hashCode() == p2.hashCode());

    Assert.assertNotNull(p1.toString());
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
/**
* Returns the infinitive form for a given word.
* 
* @param word the word
* @return the infinitive form
*/
  public String getInfinitiveForm(String word) {
  	//System.out.println("Word: " + word);
      String[] split = word.split(" ");
      String verb = split[0];

      if(verb.endsWith("ed") && split.length == 1) { 
      	// probably past tense
      	
      } else if (verb.endsWith("do")) { // termina com participio
      	
      	// check for past construction that simply need an auxiliary
      	return "ser " + word;
      }

      try {
	IndexWord iw = database.getIndexWord(POS.VERB, word);
	if(iw != null) {
		List<Synset> synsets = iw.getSenses();
		//double min = verb.length();
		String result = verb;
		for (Synset synset : synsets) {
		    for (Word w : synset.getWords()) {
		        if (verb.contains(w.getLemma())) {
		            result = w.getLemma();
		            if (split.length > 1) {
		                for (int k = 1; k < split.length; k++) {
		                    result = result + " " + split[k];
		                }
		            }
		            return result;
		        }
		    }
		}
	}
} catch (JWNLException e) {
	logger.error("WordNet lookup failed.", e);
}
      return word;
  }
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
@Override
public Optional<Word> lookup(String id) {
    try {
        return Optional.ofNullable(dictionary.getWordBySenseKey(id));
    } catch (JWNLException e) {
        log.warn("Error looking up word for sense key: {}", id);
    }
    return Optional.empty();
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
@Override
public Optional<String> mfs(String lemma, String pos) {
    List<Synset> senses = getSynsets(lemma, pos);
    if (senses.size() == 0) {
        return Optional.empty();
    }
    Synset synset = senses.get(0);
    int index = synset.indexOfWord(getLemmaString(lemma));
    Word word = synset.getWords().get(index);
    return getSenseKey(word);
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
private static Optional<String> getSenseKey(Word word) {
    String result = null;
    try {
        result = word.getSenseKey();
    } catch (JWNLException e) {
        log.warn("Error retrieving sense key for word", word, e);
    }
    return Optional.ofNullable(result);
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
/**
 * Returns the infinitive form for a given word.
 * 
 * @param word
 *            the word
 * @return the infinitive form
 */
public String getInfinitiveForm(String word) {

	String[] split = word.split(" ");
	String verb = split[0];

	if (verb.endsWith("ed") && split.length == 1) {
		// probably past tense

	} else if (verb.endsWith("ed") || verb.endsWith("un") || verb.endsWith("wn") || verb.endsWith("en")) {
		// check for past construction that simply need an auxiliary
		return "be " + word;
	}

	try {
		IndexWord iw = database.getIndexWord(POS.VERB, word);
		if (iw != null) {
			List<Synset> synsets = iw.getSenses();
			double min = verb.length();
			String result = verb;
			for (Synset synset : synsets) {
				for (Word w : synset.getWords()) {
					if (verb.contains(w.getLemma())) {
						result = w.getLemma();
						if (split.length > 1) {
							for (int k = 1; k < split.length; k++) {
								result = result + " " + split[k];
							}
						}
						return result;
					}
				}
			}
		}
	} catch (JWNLException e) {
		logger.error("WordNet lookup failed.", e);
	}
	return word;
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
public static List<String> getStrictExpansion(String inputWord) {
    List<String> expansion = null;
    try {
        IndexWordSet wordSet = dictionary.lookupAllIndexWords(inputWord);
        if (wordSet.size() == 1) {
            IndexWord indexWord = wordSet.getIndexWordCollection().iterator().next();
            String lemma = indexWord.getLemma();
            List<Synset> senses = indexWord.getSenses();
            if (senses.size() == 1) {
                List<Word> words = senses.get(0).getWords();
                if (words.size() > 1) {
                    expansion = new ArrayList<>();
                    for (Word word : words) {
                        if (!word.getLemma().equals(lemma)) {
                            expansion.add(word.getLemma());
                        }
                    }
                }
            }
        }
    } catch (JWNLException e) {
        e.printStackTrace();
    }
    return expansion;
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
/**
 * Ctor that takes a synset and a word. It verifies that the word indeed belongs to the synset.
 * <p>
 * <b>NOTE</b> ExtJwnl <i>lowercases</i> the words it is queried about. But the words it retrieves in methods like <code>realSynset.getWords()</code> 
 * are case sensitive!
 * 
 * @param synset
 * @param strWord
 * @throws WordNetException 
 */
public ExtJwnlSensedWord(ExtJwnlSynset synset, String strWord) throws WordNetException {
	this.synset = synset;
	this.word = strWord;
	
	String wordToLookup = strWord.replace(' ', '_');	// mimic jwnl, which replaces underscores with spaces when looking up
 	List<Word> words = synset.realSynset.getWords();
 	Word wordObj = lookupWordInWords(words, wordToLookup);
 	if (wordObj == null)
 		throw new WordNetException("\""+ strWord + "\" is not a memeber of the given synset " + synset);
 	this.wordObj = wordObj;
 	dictionary = synset.extJwnlDictionary;
 	this.pos = ExtJwnlUtils.getWordNetPartOfSpeech( wordObj.getPOS());
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
public Set<SensedWord> getNeighborSensedWords(WordNetRelation relation) throws WordNetException {

		Set<SensedWord> sensedWords = new LinkedHashSet<SensedWord>();
		if (relation.isLexical())
		{
			List<Pointer> pointers = wordObj.getPointers(ExtJwnlUtils.wordNetRelationToPointerType(relation));
			for (Pointer pointer : pointers)
				// add a new SensedWord made of the Word-cast of this pointer 
				sensedWords.add( new ExtJwnlSensedWord(((Word) pointer.getTarget()), dictionary));
		}
		return sensedWords;
	}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
/**
 * @param words
 * @param wordToLookup 
 * @return
 */
private Word lookupWordInWords(List<Word> words, String wordToLookup) {
 	boolean found = false;
 	Word someWord = null;
	for (int i = 0; i < words.size() && !found; i++)
 	{
		someWord = words.get(i);
		found = someWord.getLemma().equalsIgnoreCase(wordToLookup);
 	}

	return someWord;
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
public Set<String> getWords() throws WordNetException
{
	if (words == null)
	{
		words = new LinkedHashSet<String>();
		for (Word word : this.realSynset.getWords())
		{
			String lemma = word.getLemma();
			lemma = lemma.replaceAll("_", " ");	// clean
			words.add(lemma);
		}
	}
	return new LinkedHashSet<String>(words);	// return a copy
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
public List<WordAndUsage> getWordsAndUsages() throws WordNetException
{
	List<WordAndUsage> ret = null;
	List<Word> words = this.realSynset.getWords();
	ret = new ArrayList<WordAndUsage>(words.size());
	for (Word word : words)
	{
		// TODO handle this better
		try
		{
			ret.add(new WordAndUsage(word.getLemma(), word.getUseCount()));
		}
		catch(NoSuchElementException e){} // a JWNL bug
	}
	Collections.sort(ret,
			Collections.reverseOrder( // I'm preferring correctness to performance (in this case)
					new Comparator<WordAndUsage>()
					{
						public int compare(WordAndUsage o1, WordAndUsage o2)
						{
							if (o1.getUsage()<o2.getUsage())return -1;
							else if (o1.getUsage()==o2.getUsage()) return 0;
							else return 1;
						}

					} // end of anonymous class Comparator
			) // end of reverseOrder function (which returns the reverse of the defined comparator)
	);
	
	return ret;
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
@Override
public List<SensedWord> getAllSensedWords() throws WordNetException {
	List<Word> objWords = realSynset.getWords();
	List<SensedWord> sensedWords = new ArrayList<SensedWord>(objWords.size());
	for ( Word word : objWords)
		sensedWords.add( new ExtJwnlSensedWord(word, this.extJwnlDictionary));
	return sensedWords;
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
/**
 * If the target is a word, return it, otherwise return null.
 *
 * @return if the target is a word, return it, otherwise return null
 */
public Word getWord() {
    if (isLexical()) {
        return (Word) target;
    } else {
        return null;
    }
}
 

import net.sf.extjwnl.data.Word; //导入依赖的package包/类
@Override public IndexResultSet getResourcesWithScores(String queryString, int limit)
	{
		IndexResultSet resources = index.getResourcesWithScores(queryString, limit);
		if(resources.size()>=limit&&resources.last().getScore()==1f) return resources; // already perfect, no wordnet necessary
		int MAX_ADDITIONS = resources.tailSet(new IndexItem("","",WORDNET_PENALTY_FACTOR)).size();

//		(new Comparator<IndexItem>(){public int compare(IndexItem i1, IndexItem i2)
//		{return i1.getUri().compareTo(i2.getUri());};});
//		itemsByUri.addAll(resources);

		try
		{
			Set<Synset> synsets = new HashSet<>();

			for(IndexWord iw: d.lookupAllIndexWords(queryString).getIndexWordArray())
			{
				synsets.addAll(iw.getSenses());
			}

			Set<String> lemmas = new HashSet<>();

			for(Synset synset: synsets)
			{
				for(Word word: synset.getWords()) {lemmas.add(word.getLemma());}
			}

			for(String lemma: lemmas) {resources.addAll(index.getResourcesWithScores(lemma, MAX_ADDITIONS));}

			resources.retainBest(limit);
			return resources;
		}
		catch (JWNLException e) {throw new RuntimeException(e);}
	}