Java Highlighter.getBestFragment方法代码示例

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
/**
 * ����
 * @param analyzer
 * @param searcher
 * @throws IOException
 * @throws InvalidTokenOffsetsException
 */
public void searToHighlighterCss(Analyzer analyzer,IndexSearcher searcher) throws IOException, InvalidTokenOffsetsException{  
       Term term =new Term("Content", new String("免费".getBytes(),"GBK"));//��ѯ��������˼����Ҫ�����Ա�Ϊ���������  
       TermQuery query =new TermQuery(term);  
       TopDocs docs =searcher.search(query, 10);//����  
         
       /**�Զ����ע�����ı���ǩ*/  
       SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span class=\"hightlighterCss\">","</span>");  
       /**����QueryScorer*/  
       QueryScorer scorer=new QueryScorer(query);  
       /**����Fragmenter*/  
       Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);  
       Highlighter highlight=new Highlighter(formatter,scorer);  
       highlight.setTextFragmenter(fragmenter);  
       
       for(ScoreDoc doc:docs.scoreDocs){//��ȡ���ҵ��ĵ����������
           Document document =searcher.doc(doc.doc);
           String value = document.getField("Content").toString();
           TokenStream tokenStream = analyzer.tokenStream("Content", new StringReader(value));    
           String str1 = highlight.getBestFragment(tokenStream, value);    
           System.out.println(str1);
       }  
   }
 

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
public void testHits() throws Exception {
    IndexSearcher searcher = new IndexSearcher(TestUtil.getBookIndexDirectory());
    TermQuery query = new TermQuery(new Term("title", "action"));
    TopDocs hits = searcher.search(query, 10);

    QueryScorer scorer = new QueryScorer(query, "title");
    Highlighter highlighter = new Highlighter(scorer);
    highlighter.setTextFragmenter(new SimpleSpanFragmenter(scorer));

    Analyzer analyzer = new SimpleAnalyzer();

    for (ScoreDoc sd : hits.scoreDocs) {
        StoredDocument doc = searcher.doc(sd.doc);
        String title = doc.get("title");

        TokenStream stream = TokenSources.getAnyTokenStream(searcher.getIndexReader(), sd.doc, "title", doc,
                analyzer);
        String fragment = highlighter.getBestFragment(stream, title);

        LOGGER.info(fragment);
    }
}
 

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
static String displayHtmlHighlight(Query query, Analyzer analyzer, String fieldName, String fieldContent,
		int fragmentSize) throws IOException, InvalidTokenOffsetsException {
	Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter("<font color='red'>", "</font>"),
			new QueryScorer(query));
	Fragmenter fragmenter = new SimpleFragmenter(fragmentSize);
	highlighter.setTextFragmenter(fragmenter);
	return highlighter.getBestFragment(analyzer, fieldName, fieldContent);
}
 

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
@Override
@SuppressWarnings("unchecked")
public List<Post> search(Paging paging, String q) throws Exception {
	FullTextSession fullTextSession = Search.getFullTextSession(super.session());
    SearchFactory sf = fullTextSession.getSearchFactory();
    QueryBuilder qb = sf.buildQueryBuilder().forEntity(PostPO.class).get();

	org.apache.lucene.search.Query luceneQuery  = qb.keyword().onFields("title","summary","tags").matching(q).createQuery();

	FullTextQuery query = fullTextSession.createFullTextQuery(luceneQuery);
    query.setFirstResult(paging.getFirstResult());
    query.setMaxResults(paging.getMaxResults());

    StandardAnalyzer standardAnalyzer = new StandardAnalyzer();
    SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span style='color:red;'>", "</span>");
       QueryScorer queryScorer = new QueryScorer(luceneQuery);
       Highlighter highlighter = new Highlighter(formatter, queryScorer);
       
	List<PostPO> list = query.list();
    List<Post> rets = new ArrayList<>(list.size());

    for (PostPO po : list) {
		Post m = BeanMapUtils.copy(po, 0);

		// 处理高亮
		String title = highlighter.getBestFragment(standardAnalyzer, "title", m.getTitle());
		String summary = highlighter.getBestFragment(standardAnalyzer, "summary", m.getSummary());

		if (StringUtils.isNotEmpty(title)) {
			m.setTitle(title);
		}
		if (StringUtils.isNotEmpty(summary)) {
			m.setSummary(summary);
		}
		rets.add(m);
	}

	paging.setTotalCount(query.getResultSize());
	return rets;
}
 

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
/**
 * Searches the current corpus using the search terms in the search field.
 */
private void searchCorpus() {
    if (search.getText().trim().equals("")) return;
    try {
        indexSearcher = guess.getSelected() != null ?
            getIndex(getDiffCorpus(gold.getSelected(), guess.getSelected())) :
            getIndex(gold.getSelected());
        //System.out.println("Searching...");
        QueryParser parser = new QueryParser("Word", analyzer);
        Query query = parser.parse(search.getText());
        Hits hits = indexSearcher.search(query);
        Highlighter highlighter = new Highlighter(new QueryScorer(query));
        DefaultListModel model = new DefaultListModel();
        for (int i = 0; i < hits.length(); i++) {
            Document hitDoc = hits.doc(i);
            int nr = Integer.parseInt(hitDoc.get("<nr>"));
            //System.out.println(hitDoc.get("<nr>"));
            String best = null;
            for (Object field : hitDoc.getFields()) {
                Field f = (Field) field;
                best = highlighter.getBestFragment(analyzer, f.name(), hitDoc.get(f.name()));
                if (best != null) break;
            }
            if (best != null)
                model.addElement(new Result(nr, "<html>" + nr + ":" + best + "</html>"));
            //System.out.println(highlighter.getBestFragment(analyzer, "Word", hitDoc.get("Word")));
            //assertEquals("This is the text to be indexed.", hitDoc.get("fieldname"));
        }
        results.setModel(model);
        repaint();
    } catch (Exception ex) {
        ex.printStackTrace();
    }
}
 

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception{
		ApplicationContext applicationContext=new ClassPathXmlApplicationContext("applicationContext.xml");
		SessionFactory sessionFactory = applicationContext.getBean("hibernate4sessionFactory",SessionFactory.class);
		FullTextSession fullTextSession = Search.getFullTextSession(sessionFactory.openSession());
		
		//使用Hibernate Search api查询 从多个字段匹配 name、description、authors.name
//		QueryBuilder qb = fullTextEntityManager.getSearchFactory().buildQueryBuilder().forEntity(Book.class ).get();
//		Query luceneQuery = qb.keyword().onFields("name","description","authors.name").matching("移动互联网").createQuery();
		
		//使用lucene api查询 从多个字段匹配 name、description、authors.name
		//使用庖丁分词器
		MultiFieldQueryParser queryParser=new MultiFieldQueryParser(Version.LUCENE_36, new String[]{"name","description","authors.name"}, new PaodingAnalyzer());
		Query luceneQuery=queryParser.parse("实战");
		
		FullTextQuery fullTextQuery =fullTextSession.createFullTextQuery(luceneQuery, Book.class);
		//设置每页显示多少条
		fullTextQuery.setMaxResults(5);
		//设置当前页
		fullTextQuery.setFirstResult(0);
		
		//高亮设置
		SimpleHTMLFormatter formatter=new SimpleHTMLFormatter("<b><font color='red'>", "<font/></b>");
		QueryScorer queryScorer=new QueryScorer(luceneQuery);
		Highlighter highlighter=new Highlighter(formatter, queryScorer);

		@SuppressWarnings("unchecked")
		List<Book> resultList = fullTextQuery.list();
		System.out.println("共查找到["+resultList.size()+"]条记录");
		for (Book book : resultList) {
			String highlighterString=null;
			Analyzer analyzer=new PaodingAnalyzer();
			try {
				//高亮name
				highlighterString=highlighter.getBestFragment(analyzer, "name", book.getName());
				if(highlighterString!=null){
					book.setName(highlighterString);
				}
				//高亮authors.name
				Set<Author> authors = book.getAuthors();
				for (Author author : authors) {
					highlighterString=highlighter.getBestFragment(analyzer, "authors.name", author.getName());
					if(highlighterString!=null){
						author.setName(highlighterString);
					}
				}
				//高亮description
				highlighterString=highlighter.getBestFragment(analyzer, "description", book.getDescription());
				if(highlighterString!=null){
					book.setDescription(highlighterString);
				}
			} catch (Exception e) {
			}
			
			System.out.println("书名:"+book.getName()+"\n描述:"+book.getDescription()+"\n出版日期:"+book.getPublicationDate());
			System.out.println("----------------------------------------------------------");
		}
		
		fullTextSession.close();
		sessionFactory.close();
		
	}
 

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
@Override
public QueryResult<Book> query(String keyword, int start, int pagesize,Analyzer analyzer,String...field) throws Exception{
	
	QueryResult<Book> queryResult=new QueryResult<Book>();
	
	List<Book> books=new ArrayList<Book>();
	
	FullTextSession fullTextSession = Search.getFullTextSession(getSession());
	
	//使用Hibernate Search api查询 从多个字段匹配 name、description、authors.name
	//QueryBuilder qb = fullTextSession.getSearchFactory().buildQueryBuilder().forEntity(Book.class ).get();
	//Query luceneQuery = qb.keyword().onFields(field).matching(keyword).createQuery();

	//使用lucene api查询 从多个字段匹配 name、description、authors.name
	
	MultiFieldQueryParser queryParser=new MultiFieldQueryParser(Version.LUCENE_36,new String[]{"name","description","authors.name"}, analyzer);
	Query luceneQuery=queryParser.parse(keyword);
	
	FullTextQuery fullTextQuery = fullTextSession.createFullTextQuery(luceneQuery);
	int searchresultsize = fullTextQuery.getResultSize();
	queryResult.setSearchresultsize(searchresultsize);
	System.out.println("共查找到["+searchresultsize+"]条记录");
	
	fullTextQuery.setFirstResult(start);
	fullTextQuery.setMaxResults(pagesize);
	
	//设置按id排序
	fullTextQuery.setSort(new Sort(new SortField("id", SortField.INT ,true)));
	
	//高亮设置
	SimpleHTMLFormatter formatter=new SimpleHTMLFormatter("<b><font color='red'>", "</font></b>");
	QueryScorer queryScorer=new QueryScorer(luceneQuery);
	Highlighter highlighter=new Highlighter(formatter, queryScorer);

	@SuppressWarnings("unchecked")
	List<Book> tempresult = fullTextQuery.list();
	for (Book book : tempresult) {
		String highlighterString=null;
		try {
			//高亮name
			highlighterString=highlighter.getBestFragment(analyzer, "name", book.getName());
			if(highlighterString!=null){
				book.setName(highlighterString);
			}
			//高亮authors.name
			Set<Author> authors = book.getAuthors();
			for (Author author : authors) {
				highlighterString=highlighter.getBestFragment(analyzer, "authors.name", author.getName());
				if(highlighterString!=null){
					author.setName(highlighterString);
				}
			}
			//高亮description
			highlighterString=highlighter.getBestFragment(analyzer, "description", book.getDescription());
			if(highlighterString!=null){
				book.setDescription(highlighterString);
			}
		} catch (Exception e) {
		}
		
		books.add(book);
		
		
		System.out.println("书名:"+book.getName()+"\n描述:"+book.getDescription()+"\n出版日期:"+book.getPublicationDate());
		System.out.println("----------------------------------------------------------");
	}
	
	queryResult.setSearchresult(books);
	
	return queryResult;
}
 

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
public static void main(String[] args) throws Exception{
		ApplicationContext applicationContext=new ClassPathXmlApplicationContext("applicationContext.xml");
		EntityManagerFactory entityManagerFactory = applicationContext.getBean("entityManagerFactory",EntityManagerFactory.class);
		FullTextEntityManager fullTextEntityManager = Search.getFullTextEntityManager(entityManagerFactory.createEntityManager());
		
		//使用Hibernate Search api查询 从多个字段匹配 name、description、authors.name
//		QueryBuilder qb = fullTextEntityManager.getSearchFactory().buildQueryBuilder().forEntity(Book.class ).get();
//		Query luceneQuery = qb.keyword().onFields("name","description","authors.name").matching("移动互联网").createQuery();
		
		//使用lucene api查询 从多个字段匹配 name、description、authors.name
		//使用庖丁分词器
		MultiFieldQueryParser queryParser=new MultiFieldQueryParser(Version.LUCENE_36, new String[]{"name","description","authors.name"}, new PaodingAnalyzer());
		Query luceneQuery=queryParser.parse("实战");
		
		FullTextQuery fullTextQuery =fullTextEntityManager.createFullTextQuery(luceneQuery, Book.class);
		//设置每页显示多少条
		fullTextQuery.setMaxResults(5);
		//设置当前页
		fullTextQuery.setFirstResult(0);
		
		//高亮设置
		SimpleHTMLFormatter formatter=new SimpleHTMLFormatter("<b><font color='red'>", "<font/></b>");
		QueryScorer queryScorer=new QueryScorer(luceneQuery);
		Highlighter highlighter=new Highlighter(formatter, queryScorer);

		@SuppressWarnings("unchecked")
		List<Book> resultList = fullTextQuery.getResultList();
		
		for (Book book : resultList) {
			String highlighterString=null;
			Analyzer analyzer=new PaodingAnalyzer();
			try {
				//高亮name
				highlighterString=highlighter.getBestFragment(analyzer, "name", book.getName());
				if(highlighterString!=null){
					book.setName(highlighterString);
				}
				//高亮authors.name
				Set<Author> authors = book.getAuthors();
				for (Author author : authors) {
					highlighterString=highlighter.getBestFragment(analyzer, "authors.name", author.getName());
					if(highlighterString!=null){
						author.setName(highlighterString);
					}
				}
				//高亮description
				highlighterString=highlighter.getBestFragment(analyzer, "description", book.getDescription());
				if(highlighterString!=null){
					book.setDescription(highlighterString);
				}
			} catch (Exception e) {
			}
			
		}
		
		fullTextEntityManager.close();
		entityManagerFactory.close();
		
	}
 

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
@Override
public QueryResult<Book> query(String keyword, int start, int pagesize,Analyzer analyzer,String...field) throws Exception{
	
	QueryResult<Book> queryResult=new QueryResult<Book>();
	
	List<Book> books=new ArrayList<Book>();
	
	FullTextEntityManager fullTextEntityManager = Search.getFullTextEntityManager(em);
	
	//使用Hibernate Search api查询 从多个字段匹配 name、description、authors.name
	//QueryBuilder qb = fullTextSession.getSearchFactory().buildQueryBuilder().forEntity(Book.class ).get();
	//Query luceneQuery = qb.keyword().onFields(field).matching(keyword).createQuery();

	//使用lucene api查询 从多个字段匹配 name、description、authors.name
	
	MultiFieldQueryParser queryParser=new MultiFieldQueryParser(Version.LUCENE_36,new String[]{"name","description","authors.name"}, analyzer);
	Query luceneQuery=queryParser.parse(keyword);
	
	FullTextQuery fullTextQuery = fullTextEntityManager.createFullTextQuery(luceneQuery);
	int searchresultsize = fullTextQuery.getResultSize();
	queryResult.setSearchresultsize(searchresultsize);
			
	fullTextQuery.setFirstResult(start);
	fullTextQuery.setMaxResults(pagesize);
	
	//设置按id排序
	fullTextQuery.setSort(new Sort(new SortField("id", SortField.INT ,true)));
	
	//高亮设置
	SimpleHTMLFormatter formatter=new SimpleHTMLFormatter("<b><font color='red'>", "</font></b>");
	QueryScorer queryScorer=new QueryScorer(luceneQuery);
	Highlighter highlighter=new Highlighter(formatter, queryScorer);

	@SuppressWarnings("unchecked")
	List<Book> tempresult = fullTextQuery.getResultList();
	for (Book book : tempresult) {
		String highlighterString=null;
		try {
			//高亮name
			highlighterString=highlighter.getBestFragment(analyzer, "name", book.getName());
			if(highlighterString!=null){
				book.setName(highlighterString);
			}
			//高亮authors.name
			Set<Author> authors = book.getAuthors();
			for (Author author : authors) {
				highlighterString=highlighter.getBestFragment(analyzer, "authors.name", author.getName());
				if(highlighterString!=null){
					author.setName(highlighterString);
				}
			}
			//高亮description
			highlighterString=highlighter.getBestFragment(analyzer, "description", book.getDescription());
			if(highlighterString!=null){
				book.setDescription(highlighterString);
			}
		} catch (Exception e) {
		}
		
		books.add(book);	
		
	}
	
	queryResult.setSearchresult(books);
	
	return queryResult;
}
 

import org.apache.lucene.search.highlight.Highlighter; //导入方法依赖的package包/类
/**
 *
 *
 * @param query
 * @param analyzer
 * @param fieldName
 * @param fulltext
 * @param startDelimiter
 * @param stopDelimiter
 * @return
 *
 * @throws IOException
 * @throws InvalidTokenOffsetsException
 */
public static String getHighlightedField(Query query, Analyzer analyzer, String fieldName,
    String fulltext, final String startDelimiter, final String stopDelimiter) throws IOException,
        InvalidTokenOffsetsException {

  Formatter formatter = new SimpleHTMLFormatter(startDelimiter, stopDelimiter);
  QueryScorer queryScorer = new QueryScorer(query);
  Highlighter highlighter = new Highlighter(formatter, queryScorer);
  highlighter.setTextFragmenter(new SimpleSpanFragmenter(queryScorer, Integer.MAX_VALUE));
  highlighter.setMaxDocCharsToAnalyze(Integer.MAX_VALUE);

  return highlighter.getBestFragment(analyzer, fieldName, fulltext);
}