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

The following examples show how to use org.apache.lucene.search.highlight.SimpleSpanFragmenter. You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.

Example #1

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;
	}

Example #2

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();
}