Java Code Examples for org.apache.lucene.search.highlight.Highlighter#setTextFragmenter()

@Override
protected Highlighter getHighlighter(Query query, String requestFieldname, SolrQueryRequest request)
{
	String schemaFieldName =
			AlfrescoSolrDataModel.getInstance()
				.mapProperty(requestFieldname, FieldUse.HIGHLIGHT, request);

	Highlighter highlighter =
			new Highlighter(
					getFormatter(requestFieldname, request.getParams()),
					getEncoder(requestFieldname, request.getParams()),
					getQueryScorer(query,schemaFieldName, request));

	highlighter.setTextFragmenter(getFragmenter(requestFieldname, request.getParams()));
	return highlighter;
}
 

/**
 * 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;
  }
}
 

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();
}
 

/**
 * Return a phrase {@link org.apache.lucene.search.highlight.Highlighter} appropriate for this field.
 *
 * @param query       The current Query
 * @param fieldName   The name of the field
 * @param request     The current SolrQueryRequest
 * @param tokenStream document text tokenStream that implements reset() efficiently (e.g. CachingTokenFilter).
 *                    If it's used, call reset() first.
 * @throws IOException If there is a low-level I/O error.
 */
protected Highlighter getPhraseHighlighter(Query query, String fieldName, SolrQueryRequest request, TokenStream tokenStream) throws IOException {
  SolrParams params = request.getParams();
  Highlighter highlighter = new Highlighter(
          getFormatter(fieldName, params),
          getEncoder(fieldName, params),
          getSpanQueryScorer(query, fieldName, tokenStream, request));

  highlighter.setTextFragmenter(getFragmenter(fieldName, params));

  return highlighter;
}
 

/**
 * Return a {@link org.apache.lucene.search.highlight.Highlighter} appropriate for this field.
 *
 * @param query     The current Query
 * @param fieldName The name of the field
 * @param request   The current SolrQueryRequest
 */
protected Highlighter getHighlighter(Query query, String fieldName, SolrQueryRequest request) {
  SolrParams params = request.getParams();
  Highlighter highlighter = new Highlighter(
          getFormatter(fieldName, params),
          getEncoder(fieldName, params),
          getQueryScorer(query, fieldName, request));
  highlighter.setTextFragmenter(getFragmenter(fieldName, params));
  return highlighter;
}