org.apache.lucene.search.highlight.SimpleHTMLFormatter Java Exaples

Source File: HighlightCustomQueryTest.java From lucene-solr with Apache License 2.0

6 votes

/**
 * This method intended for use with
 * <code>testHighlightingWithDefaultField()</code>
 */
private String highlightField(Query query, String fieldName,
    String text) throws IOException, InvalidTokenOffsetsException {
  try (MockAnalyzer mockAnalyzer = new MockAnalyzer(random(), MockTokenizer.SIMPLE,true,
      MockTokenFilter.ENGLISH_STOPSET); TokenStream tokenStream = mockAnalyzer.tokenStream(fieldName, text)) {
    // Assuming "<B>", "</B>" used to highlight
    SimpleHTMLFormatter formatter = new SimpleHTMLFormatter();
    MyQueryScorer scorer = new MyQueryScorer(query, fieldName, FIELD_NAME);
    Highlighter highlighter = new Highlighter(formatter, scorer);
    highlighter.setTextFragmenter(new SimpleFragmenter(Integer.MAX_VALUE));

    String rv = highlighter.getBestFragments(tokenStream, text, 1,
        "(FIELD TEXT TRUNCATED)");
    return rv.length() == 0 ? text : rv;
  }
}

Source File: LumongoSegment.java From lumongo with Apache License 2.0

6 votes

private List<LumongoHighlighter> getHighlighterList(List<HighlightRequest> highlightRequests, Query q) {

		if (highlightRequests.isEmpty()) {
			return Collections.emptyList();
		}

		List<LumongoHighlighter> highlighterList = new ArrayList<>();

		for (HighlightRequest highlight : highlightRequests) {
			QueryScorer queryScorer = new QueryScorer(q, highlight.getField());
			queryScorer.setExpandMultiTermQuery(true);
			Fragmenter fragmenter = new SimpleSpanFragmenter(queryScorer, highlight.getFragmentLength());
			SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter(highlight.getPreTag(), highlight.getPostTag());
			LumongoHighlighter highlighter = new LumongoHighlighter(simpleHTMLFormatter, queryScorer, highlight);
			highlighter.setTextFragmenter(fragmenter);
			highlighterList.add(highlighter);
		}
		return highlighterList;
	}

Source File: SearcherTest.java From cjs_ssms with GNU General Public License v2.0

5 votes

public static void search(String indexDir, String q) throws Exception {
  Directory dir = FSDirectory.open(Paths.get(indexDir));
  IndexReader reader = DirectoryReader.open(dir);
  IndexSearcher is = new IndexSearcher(reader);
  // Analyzer analyzer=new StandardAnalyzer(); // 标准分词器
  SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();
  QueryParser parser = new QueryParser("desc", analyzer);
  Query query = parser.parse(q);

  long start = System.currentTimeMillis();
  TopDocs hits = is.search(query, 10);
  long end = System.currentTimeMillis();
  System.out.println("匹配 " + q + " ，总共花费" + (end - start) + "毫秒" + "查询到" + hits.totalHits + "个记录");

  QueryScorer scorer = new QueryScorer(query);
  Fragmenter fragmenter = new SimpleSpanFragmenter(scorer);
  SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<b><font color='red'>", "</font></b>");
  Highlighter highlighter = new Highlighter(simpleHTMLFormatter, scorer);
  highlighter.setTextFragmenter(fragmenter);
  for (ScoreDoc scoreDoc : hits.scoreDocs) {
    Document doc = is.doc(scoreDoc.doc);
    System.out.println(doc.get("city"));
    System.out.println(doc.get("desc"));
    String desc = doc.get("desc");
    if (desc != null) {
      TokenStream tokenStream = analyzer.tokenStream("desc", new StringReader(desc));
      System.out.println(highlighter.getBestFragment(tokenStream, desc));
    }
  }
  reader.close();
}

Source File: LuceneQuery.java From rdf4j with BSD 3-Clause "New" or "Revised" License

5 votes

@Override
@Deprecated
public void highlight(IRI property) {
	Formatter formatter = new SimpleHTMLFormatter(SearchFields.HIGHLIGHTER_PRE_TAG,
			SearchFields.HIGHLIGHTER_POST_TAG);
	highlighter = new Highlighter(formatter, new QueryScorer(query));
}

Source File: HtmlFormatter.java From lucene-solr with Apache License 2.0

5 votes

@Override
public Formatter getFormatter(String fieldName, SolrParams params ) 
{
  numRequests.inc();
  params = SolrParams.wrapDefaults(params, defaults);

  return new SimpleHTMLFormatter(
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_PRE,  "<em>" ), 
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_POST, "</em>"));
}

Source File: SearchResultsImpl.java From olat with Apache License 2.0

5 votes

/**
 * Highlight (bold,color) query words in result-document. Set HighlightResult for content or description.
 * 
 * @param query
 * @param analyzer
 * @param doc
 * @param resultDocument
 * @throws IOException
 */
private void doHighlight(final Query query, final Analyzer analyzer, final Document doc, final ResultDocument resultDocument) throws IOException {
    final Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(HIGHLIGHT_PRE_TAG, HIGHLIGHT_POST_TAG), new QueryScorer(query));
    // Get 3 best fragments of content and seperate with a "..."
    try {
        // highlight content
        final String content = doc.get(AbstractOlatDocument.CONTENT_FIELD_NAME);
        TokenStream tokenStream = analyzer.tokenStream(AbstractOlatDocument.CONTENT_FIELD_NAME, new StringReader(content));
        String highlightResult = highlighter.getBestFragments(tokenStream, content, 3, HIGHLIGHT_SEPARATOR);

        // if no highlightResult is in content => look in description
        if (highlightResult.length() == 0) {
            final String description = doc.get(AbstractOlatDocument.DESCRIPTION_FIELD_NAME);
            tokenStream = analyzer.tokenStream(AbstractOlatDocument.DESCRIPTION_FIELD_NAME, new StringReader(description));
            highlightResult = highlighter.getBestFragments(tokenStream, description, 3, HIGHLIGHT_SEPARATOR);
            resultDocument.setHighlightingDescription(true);
        }
        resultDocument.setHighlightResult(highlightResult);

        // highlight title
        final String title = doc.get(AbstractOlatDocument.TITLE_FIELD_NAME);
        tokenStream = analyzer.tokenStream(AbstractOlatDocument.TITLE_FIELD_NAME, new StringReader(title));
        final String highlightTitle = highlighter.getBestFragments(tokenStream, title, 3, " ");
        resultDocument.setHighlightTitle(highlightTitle);
    } catch (final InvalidTokenOffsetsException e) {
        log.warn("", e);
    }
}

Source File: SearchResultsImpl.java From olat with Apache License 2.0

5 votes

/**
 * Highlight (bold,color) query words in result-document. Set HighlightResult for content or description.
 * 
 * @param query
 * @param analyzer
 * @param doc
 * @param resultDocument
 * @throws IOException
 */
private void doHighlight(final Query query, final Analyzer analyzer, final Document doc, final ResultDocument resultDocument) throws IOException {
    final Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter(HIGHLIGHT_PRE_TAG, HIGHLIGHT_POST_TAG), new QueryScorer(query));
    // Get 3 best fragments of content and seperate with a "..."
    try {
        // highlight content
        final String content = doc.get(AbstractOlatDocument.CONTENT_FIELD_NAME);
        TokenStream tokenStream = analyzer.tokenStream(AbstractOlatDocument.CONTENT_FIELD_NAME, new StringReader(content));
        String highlightResult = highlighter.getBestFragments(tokenStream, content, 3, HIGHLIGHT_SEPARATOR);

        // if no highlightResult is in content => look in description
        if (highlightResult.length() == 0) {
            final String description = doc.get(AbstractOlatDocument.DESCRIPTION_FIELD_NAME);
            tokenStream = analyzer.tokenStream(AbstractOlatDocument.DESCRIPTION_FIELD_NAME, new StringReader(description));
            highlightResult = highlighter.getBestFragments(tokenStream, description, 3, HIGHLIGHT_SEPARATOR);
            resultDocument.setHighlightingDescription(true);
        }
        resultDocument.setHighlightResult(highlightResult);

        // highlight title
        final String title = doc.get(AbstractOlatDocument.TITLE_FIELD_NAME);
        tokenStream = analyzer.tokenStream(AbstractOlatDocument.TITLE_FIELD_NAME, new StringReader(title));
        final String highlightTitle = highlighter.getBestFragments(tokenStream, title, 3, " ");
        resultDocument.setHighlightTitle(highlightTitle);
    } catch (final InvalidTokenOffsetsException e) {
        log.warn("", e);
    }
}

Source File: HighlightHelper.java From incubator-retired-blur with Apache License 2.0

4 votes

/**
 * NOTE: This method will not preserve the correct field types.
 * 
 * @param preTag
 * @param postTag
 */
public static Document highlight(int docId, Document document, Query query, FieldManager fieldManager,
    IndexReader reader, String preTag, String postTag) throws IOException, InvalidTokenOffsetsException {

  String fieldLessFieldName = fieldManager.getFieldLessFieldName();

  Query fixedQuery = fixSuperQuery(query, null, fieldLessFieldName);

  Analyzer analyzer = fieldManager.getAnalyzerForQuery();

  SimpleHTMLFormatter htmlFormatter = new SimpleHTMLFormatter(preTag, postTag);
  Document result = new Document();
  for (IndexableField f : document) {
    String name = f.name();
    if (fieldLessFieldName.equals(name) || FIELDS_NOT_TO_HIGHLIGHT.contains(name)) {
      result.add(f);
      continue;
    }
    String text = f.stringValue();
    Number numericValue = f.numericValue();

    Query fieldFixedQuery;
    if (fieldManager.isFieldLessIndexed(name)) {
      fieldFixedQuery = fixSuperQuery(query, name, fieldLessFieldName);
    } else {
      fieldFixedQuery = fixedQuery;
    }

    if (numericValue != null) {
      if (shouldNumberBeHighlighted(name, numericValue, fieldFixedQuery)) {
        String numberHighlight = preTag + text + postTag;
        result.add(new StringField(name, numberHighlight, Store.YES));
      }
    } else {
      Highlighter highlighter = new Highlighter(htmlFormatter, new QueryScorer(fieldFixedQuery, name));
      TokenStream tokenStream = TokenSources.getAnyTokenStream(reader, docId, name, analyzer);
      TextFragment[] frag = highlighter.getBestTextFragments(tokenStream, text, false, 10);
      for (int j = 0; j < frag.length; j++) {
        if ((frag[j] != null) && (frag[j].getScore() > 0)) {
          result.add(new StringField(name, frag[j].toString(), Store.YES));
        }
      }
    }
  }
  return result;
}

Source File: PostSearchServiceImpl.java From mblog with GNU General Public License v3.0

4 votes

@Override
@PostStatusFilter
public Page<PostVO> search(Pageable pageable, String term) throws Exception {
    FullTextEntityManager fullTextEntityManager = Search.getFullTextEntityManager(entityManager);
    QueryBuilder builder = fullTextEntityManager.getSearchFactory().buildQueryBuilder().forEntity(Post.class).get();

    Query luceneQuery = builder
            .keyword()
            .fuzzy()
            .withEditDistanceUpTo(1)
            .withPrefixLength(1)
            .onFields("title", "summary", "tags")
            .matching(term).createQuery();

    FullTextQuery query = fullTextEntityManager.createFullTextQuery(luceneQuery, Post.class);
    query.setFirstResult((int) pageable.getOffset());
    query.setMaxResults(pageable.getPageSize());

    SmartChineseAnalyzer analyzer = new SmartChineseAnalyzer();
    SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span style='color:red;'>", "</span>");
    QueryScorer scorer = new QueryScorer(luceneQuery);
    Highlighter highlighter = new Highlighter(formatter, scorer);

    List<Post> list = query.getResultList();
    List<PostVO> rets = list.stream().map(po -> {
        PostVO post = BeanMapUtils.copy(po);

        try {
            // 处理高亮
            String title = highlighter.getBestFragment(analyzer, "title", post.getTitle());
            String summary = highlighter.getBestFragment(analyzer, "summary", post.getSummary());

            if (StringUtils.isNotEmpty(title)) {
                post.setTitle(title);
            }
            if (StringUtils.isNotEmpty(summary)) {
                post.setSummary(summary);
            }
        } catch (Exception e) {
            log.error(e.getMessage(), e);
        }
        return post;
    }).collect(Collectors.toList());
    buildUsers(rets);
    return new PageImpl<>(rets, pageable, query.getResultSize());
}

Source File: SearchManager.java From maven-framework-project with MIT License

4 votes

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();
		
	}

Source File: BookDaoImpl.java From maven-framework-project with MIT License

4 votes

@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;
}

Source File: SearchManager.java From maven-framework-project with MIT License

4 votes

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();
		
	}

Source File: BookDaoImpl.java From maven-framework-project with MIT License

4 votes

@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;
}

org.apache.lucene.search.highlight.SimpleHTMLFormatter Java Examples