Java 类org.apache.lucene.search.highlight.SimpleHTMLFormatter 实例源码

项目:DEM    文件:TextHighlighter.java   
public static String getHighlightString (String text, String keyword) throws IOException {
       TermQuery query = new TermQuery(new Term("f", keyword));
QueryScorer scorer = new QueryScorer(query);
SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<span class=\"highlight\">","</span>");
Highlighter highlighter = new Highlighter(formatter, scorer);
Fragmenter fragmenter = new SimpleFragmenter(50);
highlighter.setTextFragmenter(fragmenter);
TokenStream tokenStream = new StandardAnalyzer(Version.LUCENE_20).tokenStream("f", new StringReader(text));
//String result = highlighter.getBestFragments(tokenStream, text, 30, "...");

StringBuilder writer = new StringBuilder("");
writer.append("<html>");
writer.append("<style>\n" +
    ".highlight {\n" +
    " background: yellow;\n" +
    "}\n" +
    "</style>");
writer.append("<body>");
writer.append("");
writer.append("</body></html>");

return ( writer.toString() );
   }
项目:Rearchor    文件:TestHighLight.java   
/**
 * ����
 * @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);
       }  
   }
项目:miru    文件:LuceneBackedQueryParser.java   
@Override
public String highlight(String locale, boolean useStopWords, String query, String content, String pre, String post, int preview) {
    Analyzer analyzer = termAnalyzers.findAnalyzer(locale, useStopWords);
    QueryParser parser = new QueryParser(defaultField, analyzer);

    String summary = null;
    try {
        SimpleHTMLFormatter formatter = new SimpleHTMLFormatter(pre, post);
        Highlighter hg = new Highlighter(formatter, new QueryTermScorer(parser.parse(query)));
        hg.setMaxDocCharsToAnalyze(preview);
        hg.setTextFragmenter(new SimpleFragmenter(100));

        TokenStream tokens = TokenSources.getTokenStream(defaultField, content, analyzer);
        summary = hg.getBestFragments(tokens, content, 4, " ... ");
    } catch (InvalidTokenOffsetsException | IOException | ParseException ex) {
        LOG.error("Failed to highlight", ex);
    }

    return StringUtils.isBlank(summary) ? null : summary;
}
项目:NYBC    文件:HighlightCustomQueryTest.java   
/**
 * This method intended for use with
 * <tt>testHighlightingWithDefaultField()</tt>
 */
private String highlightField(Query query, String fieldName,
    String text) throws IOException, InvalidTokenOffsetsException {
  TokenStream tokenStream = new MockAnalyzer(random(), MockTokenizer.SIMPLE,
      true, MockTokenFilter.ENGLISH_STOPSET, true).tokenStream(fieldName,
      new StringReader(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;
}
项目:lumongo    文件:LumongoSegment.java   
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;
    }
项目:Tedyli-Searcher    文件:Searcher.java   
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);
}
项目:cjs_ssms    文件:SearcherTest.java   
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();
}
项目:mblog    文件:PostDaoImpl.java   
@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;
}
项目:lucenestudy    文件:HighlightingHelper.java   
HighlightingHelper(Query query, Analyzer analyzer) {
  this.analyzer = analyzer;

  Formatter formatter = new SimpleHTMLFormatter();
  Encoder encoder = new MinimalHTMLEncoder();
  scorer = new QueryScorer(query);
  highlighter = new Highlighter(formatter, encoder, scorer);

  fragmentLength = DEFAULT_FRAGMENT_LENGTH;
  Fragmenter fragmenter = new SimpleSpanFragmenter(scorer, fragmentLength);
  highlighter.setTextFragmenter(fragmenter);
}
项目:search    文件:HighlightCustomQueryTest.java   
/**
 * This method intended for use with
 * <tt>testHighlightingWithDefaultField()</tt>
 */
private String highlightField(Query query, String fieldName,
    String text) throws IOException, InvalidTokenOffsetsException {
  TokenStream tokenStream = new MockAnalyzer(random(), MockTokenizer.SIMPLE,
      true, MockTokenFilter.ENGLISH_STOPSET).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;
}
项目:search    文件:SearchTravRetHighlightTask.java   
@Override
protected BenchmarkHighlighter getBenchmarkHighlighter(Query q){
  highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(q));
  highlighter.setMaxDocCharsToAnalyze(maxDocCharsToAnalyze);
  return new BenchmarkHighlighter(){
    @Override
    public int doHighlight(IndexReader reader, int doc, String field,
        Document document, Analyzer analyzer, String text) throws Exception {
      TokenStream ts = TokenSources.getAnyTokenStream(reader, doc, field, document, analyzer);
      TextFragment[] frag = highlighter.getBestTextFragments(ts, text, mergeContiguous, maxFrags);
      return frag != null ? frag.length : 0;
    }
  };
}
项目:search    文件:CountingHighlighterTestTask.java   
@Override
public BenchmarkHighlighter getBenchmarkHighlighter(Query q) {
  highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(q));
  return new BenchmarkHighlighter() {
    @Override
    public int doHighlight(IndexReader reader, int doc, String field, Document document, Analyzer analyzer, String text) throws Exception {
      TokenStream ts = TokenSources.getAnyTokenStream(reader, doc, field, document, analyzer);
      TextFragment[] frag = highlighter.getBestTextFragments(ts, text, mergeContiguous, maxFrags);
      numHighlightedResults += frag != null ? frag.length : 0;
      return frag != null ? frag.length : 0;
    }
  };
}
项目:search    文件:HtmlFormatter.java   
@Override
public Formatter getFormatter(String fieldName, SolrParams params ) 
{
  numRequests++;
  params = SolrParams.wrapDefaults(params, defaults);

  return new SimpleHTMLFormatter(
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_PRE,  "<em>" ), 
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_POST, "</em>"));
}
项目:Lucee4    文件:_Highlight.java   
public static Object createHighlighter(Query query,String highlightBegin,String highlightEnd) {

        return new Highlighter(
                //new SimpleHTMLFormatter("<span class=\"matching-term\">","</span>"),
                new SimpleHTMLFormatter(highlightBegin,highlightEnd),
                new QueryScorer(query));

}
项目:openyu-commons    文件:CommonDaoSupporter.java   
protected Highlighter createHighlighter(org.apache.lucene.search.Query luceneQuery) {
    SimpleHTMLFormatter format = new SimpleHTMLFormatter("<b><font color='red'>", "</font></b>");
    Highlighter highlighter = new Highlighter(format, new QueryScorer(luceneQuery));// 高亮
    // highlighter.setTextFragmenter(new
    // SimpleFragmenter(Integer.MAX_VALUE));
    highlighter.setTextFragmenter(new SimpleFragmenter(200));
    return highlighter;
}
项目:olat    文件:SearchResultsImpl.java   
/**
 * 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);
    }
}
项目:olat    文件:SearchResultsImpl.java   
/**
 * 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);
    }
}
项目:NYBC    文件:SearchTravRetHighlightTask.java   
@Override
protected BenchmarkHighlighter getBenchmarkHighlighter(Query q){
  highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(q));
  highlighter.setMaxDocCharsToAnalyze(maxDocCharsToAnalyze);
  return new BenchmarkHighlighter(){
    @Override
    public int doHighlight(IndexReader reader, int doc, String field,
        Document document, Analyzer analyzer, String text) throws Exception {
      TokenStream ts = TokenSources.getAnyTokenStream(reader, doc, field, document, analyzer);
      TextFragment[] frag = highlighter.getBestTextFragments(ts, text, mergeContiguous, maxFrags);
      return frag != null ? frag.length : 0;
    }
  };
}
项目:NYBC    文件:CountingHighlighterTestTask.java   
@Override
public BenchmarkHighlighter getBenchmarkHighlighter(Query q) {
  highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(q));
  return new BenchmarkHighlighter() {
    @Override
    public int doHighlight(IndexReader reader, int doc, String field, Document document, Analyzer analyzer, String text) throws Exception {
      TokenStream ts = TokenSources.getAnyTokenStream(reader, doc, field, document, analyzer);
      TextFragment[] frag = highlighter.getBestTextFragments(ts, text, mergeContiguous, maxFrags);
      numHighlightedResults += frag != null ? frag.length : 0;
      return frag != null ? frag.length : 0;
    }
  };
}
项目:NYBC    文件:HtmlFormatter.java   
@Override
public Formatter getFormatter(String fieldName, SolrParams params ) 
{
  numRequests++;
  params = SolrParams.wrapDefaults(params, defaults);

  return new SimpleHTMLFormatter(
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_PRE,  "<em>" ), 
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_POST, "</em>"));
}
项目:search-core    文件:HtmlFormatter.java   
@Override
public Formatter getFormatter(String fieldName, SolrParams params ) 
{
  numRequests++;
  params = SolrParams.wrapDefaults(params, defaults);

  return new SimpleHTMLFormatter(
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_PRE,  "<em>" ), 
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_POST, "</em>"));
}
项目:read-open-source-code    文件:SearchTravRetHighlightTask.java   
@Override
protected BenchmarkHighlighter getBenchmarkHighlighter(Query q){
  highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(q));
  highlighter.setMaxDocCharsToAnalyze(maxDocCharsToAnalyze);
  return new BenchmarkHighlighter(){
    @Override
    public int doHighlight(IndexReader reader, int doc, String field,
        Document document, Analyzer analyzer, String text) throws Exception {
      TokenStream ts = TokenSources.getAnyTokenStream(reader, doc, field, document, analyzer);
      TextFragment[] frag = highlighter.getBestTextFragments(ts, text, mergeContiguous, maxFrags);
      return frag != null ? frag.length : 0;
    }
  };
}
项目:read-open-source-code    文件:HtmlFormatter.java   
@Override
public Formatter getFormatter(String fieldName, SolrParams params ) 
{
  numRequests++;
  params = SolrParams.wrapDefaults(params, defaults);

  return new SimpleHTMLFormatter(
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_PRE,  "<em>" ), 
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_POST, "</em>"));
}
项目:read-open-source-code    文件:SearchTravRetHighlightTask.java   
@Override
protected BenchmarkHighlighter getBenchmarkHighlighter(Query q){
  highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(q));
  highlighter.setMaxDocCharsToAnalyze(maxDocCharsToAnalyze);
  return new BenchmarkHighlighter(){
    @Override
    public int doHighlight(IndexReader reader, int doc, String field,
        Document document, Analyzer analyzer, String text) throws Exception {
      TokenStream ts = TokenSources.getAnyTokenStream(reader, doc, field, document, analyzer);
      TextFragment[] frag = highlighter.getBestTextFragments(ts, text, mergeContiguous, maxFrags);
      return frag != null ? frag.length : 0;
    }
  };
}
项目:read-open-source-code    文件:HtmlFormatter.java   
@Override
public Formatter getFormatter(String fieldName, SolrParams params ) 
{
  numRequests++;
  params = SolrParams.wrapDefaults(params, defaults);

  return new SimpleHTMLFormatter(
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_PRE,  "<em>" ), 
      params.getFieldParam(fieldName, HighlightParams.SIMPLE_POST, "</em>"));
}
项目:Maskana-Gestor-de-Conocimiento    文件:HighlightCustomQueryTest.java   
/**
 * This method intended for use with
 * <tt>testHighlightingWithDefaultField()</tt>
 */
private String highlightField(Query query, String fieldName,
    String text) throws IOException, InvalidTokenOffsetsException {
  TokenStream tokenStream = new MockAnalyzer(random(), MockTokenizer.SIMPLE,
      true, MockTokenFilter.ENGLISH_STOPSET).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;
}
项目:Maskana-Gestor-de-Conocimiento    文件:SearchTravRetHighlightTask.java   
@Override
protected BenchmarkHighlighter getBenchmarkHighlighter(Query q){
  highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(q));
  highlighter.setMaxDocCharsToAnalyze(maxDocCharsToAnalyze);
  return new BenchmarkHighlighter(){
    @Override
    public int doHighlight(IndexReader reader, int doc, String field,
        Document document, Analyzer analyzer, String text) throws Exception {
      TokenStream ts = TokenSources.getAnyTokenStream(reader, doc, field, document, analyzer);
      TextFragment[] frag = highlighter.getBestTextFragments(ts, text, mergeContiguous, maxFrags);
      return frag != null ? frag.length : 0;
    }
  };
}
项目:Maskana-Gestor-de-Conocimiento    文件:CountingHighlighterTestTask.java   
@Override
public BenchmarkHighlighter getBenchmarkHighlighter(Query q) {
  highlighter = new Highlighter(new SimpleHTMLFormatter(), new QueryScorer(q));
  return new BenchmarkHighlighter() {
    @Override
    public int doHighlight(IndexReader reader, int doc, String field, Document document, Analyzer analyzer, String text) throws Exception {
      TokenStream ts = TokenSources.getAnyTokenStream(reader, doc, field, document, analyzer);
      TextFragment[] frag = highlighter.getBestTextFragments(ts, text, mergeContiguous, maxFrags);
      numHighlightedResults += frag != null ? frag.length : 0;
      return frag != null ? frag.length : 0;
    }
  };
}
项目:incubator-blur    文件:HighlightHelper.java   
/**
 * 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;
}
项目:maven-framework-project    文件:SearchManager.java   
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();

    }
项目:maven-framework-project    文件:BookDaoImpl.java   
@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;
}
项目:maven-framework-project    文件:SearchManager.java   
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();

    }
项目:maven-framework-project    文件:BookDaoImpl.java   
@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;
}
项目:t4f-data    文件:HighlightIt.java   
public static void main(String[] args) throws Exception {

        if (args.length != 1) {
            System.err.println("Usage: HighlightIt <filename-out>");
            System.exit(-1);
        }

        String filename = args[0];

        String searchText = "term"; //
        QueryParser parser = new QueryParser(Version.LUCENE_41, //
                "f", //
                new StandardAnalyzer(Version.LUCENE_41));// #1
        Query query = parser.parse(searchText); //

        SimpleHTMLFormatter formatter = //
        new SimpleHTMLFormatter("<span class=\"highlight\">", //
                "</span>"); //

        TokenStream tokens = new StandardAnalyzer(Version.LUCENE_41) //
                .tokenStream("f", new StringReader(text)); //

        QueryScorer scorer = new QueryScorer(query, "f"); //

        Highlighter highlighter = new Highlighter(formatter, scorer); //
        highlighter.setTextFragmenter( //
                new SimpleSpanFragmenter(scorer)); //

        String result = //
        highlighter.getBestFragments(tokens, text, 3, "..."); //

        FileWriter writer = new FileWriter(filename); //
        writer.write("<html>"); //
        writer.write("<style>\n" + //
                ".highlight {\n" + //
                " background: yellow;\n" + //
                "}\n" + //
                "</style>"); //
        writer.write("<body>"); //
        writer.write(result); //
        writer.write("</body></html>"); //
        writer.close(); //
    }
项目:OCRaptor    文件:COF.java   
/**
 *
 *
 * @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);
}