Java ISynset.getWords方法代码示例

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
private String getMeanings(int synset, POS pos){
	String result = "";
	ISynsetID synsetID = new SynsetID(synset, pos);
	ISynset s = dict.getSynset(synsetID);
	if(s == null) return "";
	
	int i= 1;
	
	for (IWord iword: s.getWords()){
		result += i + " - ";
		result += iword.getLemma() + "\n";
		i++;
	}
	result += "Gloss: " + s.getGloss() + "\n\n";
	return result;
}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
@Override
public List<String> getWords(int synset, String pos) {
	ArrayList<String> words = new ArrayList<String>();
	
	try {
		dict.open();
	} catch (IOException e) {
		return words;
	}
	
	IWordID wordID1 = new WordID(synset,POS.valueOf(pos),1);
	IWord word1 = dict.getWord(wordID1);
	ISynset isynset = word1.getSynset() ;
	
	for( IWord word : isynset.getWords () )
		words.add(word.getLemma());
		
	return words;
}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
public List<SynonymDomain> ExtractSynsetsSentence(String Sentence,File englishStopwordsFilePath) throws IOException, Exception
{
    List<SynonymDomain> lstSynset=new ArrayList<>();
    String sentenceKeyWords=EX.ExtractKeyword(Sentence, englishStopwordsFilePath);
    for(String str:sentenceKeyWords.split(","))
    {
    String strSynset="";
    File dicFile=new File(path);
    IDictionary dict=new Dictionary(dicFile);
    dict.open();
    WordnetStemmer stemmer=new WordnetStemmer(dict);
     try
     {
        List<String> lstStem=stemmer.findStems(str, POS.NOUN);
        IIndexWord idxWord = dict . getIndexWord (lstStem.get(0), POS.NOUN);
        IWordID wordID = idxWord . getWordIDs ().get(0);
        IWord word = dict.getWord(wordID);
        ISynset sen=word.getSynset();
         for(IWord w:sen.getWords())
         {
           strSynset+=w.getLemma()+",";
           
         }
        lstSynset.add(new SynonymDomain(str, strSynset));
     }
     catch(Exception ex)
     {
        
     }
    }
    return lstSynset;
}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
@Override
public List<String> ExtractSynonymWord(String word) throws URISyntaxException, IOException 
{
	List<String> lstSynonym=new ArrayList<>();
	java.net.URL url = getClass().getClassLoader().getResource("dict\\");
    //File dicFile = new File(url.toURI());
    String strSynset="";
       IDictionary dict=new Dictionary(new File(path));
       dict.open();
       WordnetStemmer stemmer=new WordnetStemmer(dict);
        try
        {
           List<String> lstStem=stemmer.findStems(word, POS.NOUN);
           for(int i=0;i<1000;i++)
           {
           IIndexWord idxWord = dict . getIndexWord (lstStem.get(0), POS.NOUN);
           IWordID wordID = idxWord . getWordIDs ().get(i);
           IWord words = dict.getWord(wordID);
           ISynset sen=words.getSynset();
            for(IWord w:sen.getWords())
            {
           	 
           	 lstSynonym.add(w.getLemma());
            }
            
           }
        }
        catch(Exception ex)
        {
        }
       return lstSynonym;
}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
public List<ExtractSynonym> ExtractSynonymSentence(String inputSentence) throws MalformedURLException, IOException
{
    List<ExtractSynonym> lstSynset=new ArrayList<>();
        for(String str:inputSentence.split(" "))
        {
            String strSynset="";
            File dicFile=new File(path);
            IDictionary dict=new Dictionary(dicFile);
            dict.open();
            WordnetStemmer stemmer=new WordnetStemmer(dict);
            for(int j=0;j<10;j++)
         {
              try
              {
                List<String> lstStem=stemmer.findStems(str, POS.NOUN);
                IIndexWord idxWord = dict . getIndexWord (lstStem.get(0), POS.NOUN);
                IWordID wordID = idxWord . getWordIDs ().get(j);
                IWord word = dict.getWord(wordID);
                ISynset sen=word.getSynset();
                 for(IWord w:sen.getWords())
                 {
                   strSynset+=w.getLemma()+",";
                 }
                
              }
              
              catch(Exception ex)
              {

              }
              
         }
            lstSynset.add(new ExtractSynonym(str, strSynset));
        }
    return lstSynset;
}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
/**
 * Retrieve a set of synonyms for a word. Use only the first sense if
 * useFirstSense flag is true.
 */
public static HashSet<String> getSynonyms(IDictionary iDictionary, String word, String posTag,
		boolean firstSenseOnly) {

	// need a set to avoid repeating words
	HashSet<String> synonyms = new HashSet<String>();

	POS pos = POS.getPartOfSpeech(posTag.charAt(0));
	if (pos == null) {
		return synonyms;
	}

	IIndexWord iIndexWord = iDictionary.getIndexWord(word, pos);
	if (iIndexWord == null) {
		return synonyms; // no senses found
	}

	// iterate over senses
	for (IWordID iWordId : iIndexWord.getWordIDs()) {
		IWord iWord = iDictionary.getWord(iWordId);

		ISynset iSynset = iWord.getSynset();
		for (IWord synsetMember : iSynset.getWords()) {
			synonyms.add(synsetMember.getLemma());
		}

		if (firstSenseOnly) {
			break;
		}
	}

	return synonyms;
}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
/**
 * Will return a list of synonyms for a word, given a set of permissible word classes
 * @param word
 * @param wordClass
 * @return
 */
public static List<String> getSynonyms(String word, POS... wordClass){
	
	List<String> synonyms = new ArrayList<String>();
	synonyms.add(word.toLowerCase());
	
	List<POS> acceptedWordClasses = Arrays.asList(wordClass);
	
	try{
		for(POS p : acceptedWordClasses){
			IIndexWord iw = dict.getIndexWord(word, p);
			if(iw != null){
				for(IWordID wid : iw.getWordIDs()){
					IWord wrd = dict.getWord(wid);
					ISynset synset = wrd.getSynset();
					for(IWord iwrd : synset.getWords()){
						String lemma = iwrd.getLemma().toLowerCase();
						if(!synonyms.contains(lemma))
						synonyms.add(lemma);
					}
				}
			}
			
		}
			
	}catch(IllegalArgumentException iae){
		System.out.println("Illegal argument: synonym "+word);
	}

	Collections.sort(synonyms);
	return synonyms;
	
}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
String parseSynset(ISynset synset){
	String ret = "";
	if(synset.getWords().size()==1)return ret;
	ret+="<p>Synsets:&nbsp&nbsp&nbsp";
	for(IWord word:synset.getWords()){
		String t=word.getLemma();
		if(!t.equals(wordName)){
			ret += "<a href="+t+">"+t.replaceAll("_", " ")+"</a>&nbsp&nbsp&nbsp";
		}
	}
	
	return ret;
}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
/**
 * @param iSynsets
 * @return
 */
private Set<String> getWordsOfSynsets(ISynset[] iSynsets) {
	Set<String> words = new HashSet<String>();
	for (ISynset synset : iSynsets)
		for (IWord iWord : synset.getWords())
			words.add(iWord.getLemma());
	return words;
}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
public Map<MappedString, Float> getSynonyms(IWord word, int depth, int maxDepth, List<TraceElement> trace) {
	Map<MappedString, Float> res = new HashMap<MappedString, Float>();
	if (depth > maxDepth) {
		return res;
	}
	List<IWordID> words;
	synchronized (dict) {
		words = dict.getIndexWord(word.getLemma(), word.getPOS()).getWordIDs();
	}
	for (IWordID sameWordInOtherSynset : words) {
		ISynset s;
		synchronized (dict) {
			s = dict.getWord(sameWordInOtherSynset).getSynset();
		}
		for (IWord synonym : s.getWords()) {
			float score = 1.0f - (float)depth / (maxDepth + 1);
			List<TraceElement> _trace = new LinkedList<TraceElement>(trace);
			// we don't have to mention that a word is a synonym of itself
			if (!word.getLemma().equals(synonym.getLemma())) {
				_trace.add(new TraceElement(synonym.getLemma() + " (synonym)", getWordNetUrl(synonym)));
			}
			addSynonym(res, synonym.getLemma(), _trace, score);
			addSynonyms(res, getSynonyms(synonym, depth + 1, maxDepth, _trace));
		}
	}
	return res;
}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
public Map<MappedString, Float> getRelatedWords(ISynset s, int depth, int maxDepth, IPointer relationType, boolean assignDepthPenalty, List<TraceElement> trace) {
		if (depth == maxDepth) {
			return Collections.emptyMap();
		}
		float scoreInThisDepth = 1.0f;
		if (assignDepthPenalty) {
			scoreInThisDepth -= (float)depth / maxDepth;
		}
		Map<MappedString, Float> res = new HashMap<MappedString, Float>();
//		Map foo = word.getRelatedMap();
		List<ISynsetID> sIDs = s.getRelatedSynsets(relationType);
		for (ISynsetID sID : sIDs) {
			ISynset hS;
			synchronized (dict) {
				hS = dict.getSynset(sID);
			}
			List<TraceElement> _trace = new LinkedList<TraceElement>(trace);
			_trace.add(new TraceElement(hS.getGloss() + " (" + relationType.getName() + ")", ""));
			for (IWord h : hS.getWords()) {
				List<TraceElement> __trace = new LinkedList<TraceElement>(trace);
				__trace.add(new TraceElement(h.getLemma() + " (" + relationType.getName() + ")", getWordNetUrl(h)));
				addSynonym(res, h.getLemma(), __trace, scoreInThisDepth);
			}
			addSynonyms(res, getRelatedWords(hS, depth + 1, maxDepth, relationType, assignDepthPenalty, _trace));
		}
		return res;
	}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
public List<ExtractSynonym> ExtractSynonymFile(File filePath) throws MalformedURLException, IOException
{
    List<ExtractSynonym> lstSynset=new ArrayList<>();
    BufferedReader reader=new BufferedReader(new FileReader(filePath));
    String Line="";
    List<String> lstText=new ArrayList<>();
    while((Line=reader.readLine())!=null)
    {
        lstText.add(Line);
    }
    for(String Sentence:lstText)
    {
        for(String str:Sentence.split(" "))
        {
            String strSynset="";
            File dicFile=new File(path);
            IDictionary dict=new Dictionary(dicFile);
            dict.open();
            WordnetStemmer stemmer=new WordnetStemmer(dict);
            for(int j=0;j<10;j++)
         {
             try
             {
            	List<String> lstStem=stemmer.findStems(str, POS.NOUN);
                IIndexWord idxWord = dict . getIndexWord (lstStem.get(0), POS.NOUN);
                IWordID wordID = idxWord . getWordIDs ().get(j);
                IWord word = dict.getWord(wordID);
                ISynset sen=word.getSynset();
                 for(IWord w:sen.getWords())
                 {
                   strSynset+=w.getLemma()+",";

                 }
                lstSynset.add(new ExtractSynonym(str, strSynset));
             }
             catch(Exception ex)
             {
             }
         }
        }
    }
    return lstSynset;
}
 

import edu.mit.jwi.item.ISynset; //导入方法依赖的package包/类
/**
 * 根据一定规则来获取当前词的最佳同义词
 * 2015-6-9 19:47:30 添加synchronized关键字，jwi不是线程安全的
 * @param dict
 * @param word
 * @param selectedSynonymsWords 文章中已经选择的同义词集合
 * @return
 */
public synchronized static List<Word> getSynonyms(IDictionary dict, Word word){

    List<Word> synonymsWords = new ArrayList<Word>();

    IIndexWord idxWord = null;
    if(POS_NOUN.contains(word.getPos())){
        idxWord = dict.getIndexWord(word.getLemma(), POS.NOUN);
    }else if(POS_VERB.contains(word.getPos())){
        idxWord = dict.getIndexWord(word.getLemma(), POS.VERB);
    }else if(POS_ADVERB.contains(word.getPos())){
        idxWord = dict.getIndexWord(word.getLemma(), POS.ADVERB);
    }else if(POS_ADJ.contains(word.getPos())){
        idxWord = dict.getIndexWord(word.getLemma(), POS.ADJECTIVE);
    }

    if(idxWord == null) {
        return synonymsWords;
    }

    IWordID wordID = idxWord.getWordIDs().get(0); // 1st meaning
    IWord iword = dict.getWord(wordID);
    ISynset synset = iword.getSynset (); //ISynset是一个词的同义词集的接口

    for(IWord w : synset.getWords()){

        Word synonymsWord = null;
        try {
            synonymsWord = (Word) word.clone();
            synonymsWord.setName(w.getLemma());
            synonymsWord.setLemma(w.getLemma());
        } catch (CloneNotSupportedException e) {
            log.error("Clone word[" + word + "] error!", e);
        }
        if(null != synonymsWord) {
            synonymsWords.add(synonymsWord);
        }

    }

    return synonymsWords;
}