lucene最新版本為1.9，從apache svn中checkout 出來已經(jīng)包括了Highlighter
測(cè)試一下：
package org.apache.lucene.search.highlight;
import junit.framework.TestCase;
import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.TokenStream;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Hits;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.Searcher;
import org.apache.lucene.store.RAMDirectory;
import java.io.IOException;
import java.io.StringReader;
/** *//**
* @author martin
*/
public class WordsHighlighterTest extends TestCase 
{
private IndexReader reader;
RAMDirectory ramDirectory;
final private static String FIELD_NAME = "contents";
final private static String queryString = "索引";
String [] words = {
"1:索引內(nèi)容結(jié)構(gòu)：Document，以及包含于Document的多個(gè)Field索",
"2:索引內(nèi)容優(yōu)先性調(diào)整因子,boost(可對(duì)整個(gè)Document或Field指定).",
"3:索引的寫入IndexWriter,索引的寫入目標(biāo)Directory,實(shí)現(xiàn)包括FsDirectory跟RamDirectory等",
"4:索引創(chuàng)建速度的調(diào)整"
};
protected void setUp() throws Exception {
ramDirectory = new RAMDirectory();
IndexWriter indexWriter = new IndexWriter(ramDirectory, new StandardAnalyzer(), true);
for (String s : words) {
addDoc(indexWriter, s);
}
indexWriter.optimize();
indexWriter.close();
reader = IndexReader.open(ramDirectory);
}
private void addDoc(IndexWriter indexWriter, String s) throws IOException {
Document doc = new Document();
doc.add(new Field(FIELD_NAME, s, Field.Store.YES, Field.Index.TOKENIZED, Field.TermVector.YES));
indexWriter.addDocument(doc);
}
public void testSimpleWords() throws Exception {
Query query = new QueryParser(FIELD_NAME, new StandardAnalyzer()).parse(queryString);
query = query.rewrite(reader);
System.out.println("Searching for: " + query.toString(FIELD_NAME));
Searcher searcher = new IndexSearcher(ramDirectory);
Hits hits = searcher.search(query);
Highlighter highlighter = new Highlighter(new SimpleHTMLFormatter("<font color=\"red\">", "</font>"), new QueryScorer(query));
highlighter.setTextFragmenter(new SimpleFragmenter(20));
Analyzer analyzer = new StandardAnalyzer();
for (int i = 0; i < hits.length(); i++) {
String text = hits.doc(i).get(FIELD_NAME);
TokenStream tokenStream = analyzer.tokenStream(FIELD_NAME, new StringReader(text));
String result = highlighter.getBestFragments(tokenStream, text, 2, "");
System.out.println("\t" + result);
}
}
protected void tearDown() throws Exception {
super.tearDown();
}
}輸出：
Searching for: "索 引"
4:
索引創(chuàng)建速度的調(diào)整
3:
索引的寫入IndexWriter,
索引的寫入目標(biāo)Directory,實(shí)現(xiàn)包
1:
索引內(nèi)容結(jié)構(gòu)：Document，以
索
2:
索引內(nèi)容優(yōu)先性調(diào)整因子,boost(可對(duì)整個(gè)Document或Field指