Lucene实现搜索结果命中关键字高亮显示

     使用lucene实现搜索结果 命中关键字高亮显示，大致流程与lucene 建立文件索引和针对索引进行搜索（lucene2.2版本）介绍的一致，只需在代码里稍作修改。


   1.索引生成过程：（红色为修改部分，针对需要进行高亮显示索引内容，进行分词与关键字位置索引）

package demo.example.searcher;

import java.io.*;
import java.util.*;
import org.apache.lucene.analysis.standard.*;
import org.apache.lucene.index.*;
import org.apache.lucene.document.*;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;

public class Indexer {
	private static Log log = LogFactory.getLog(Indexer.class);

	public static void main(String[] args) throws Exception {
		File indexDir = new File("C:\\index");
		File dataDir = new File("C:\\lucene\\src");

		long start = new Date().getTime();

		int numIndexed = index(indexDir, dataDir);

		long end = new Date().getTime();

		System.out.println("use:" + (end - start));
	}

	public static int index(File indexDir, File dataDir) {
		int ret = 0;
		try {
			IndexWriter writer = new IndexWriter(indexDir, new StandardAnalyzer(), true);
			writer.setUseCompoundFile(false);

			indexDirectory(writer, dataDir);

			ret = writer.docCount();
			writer.optimize();
			writer.close();

		} catch (Exception e) {
			e.printStackTrace();
		}
		return ret;
	}

	public static void indexDirectory(IndexWriter writer, File dir) {
		try {
			File[] files = dir.listFiles();

			for (File f : files) {
				if (f.isDirectory()) {
					indexDirectory(writer, f);
				} else {
					indexFile(writer, f);
				}
			}
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

	public static void indexFile(IndexWriter writer, File f) {
		try {
			System.out.println("Indexing:" + f.getCanonicalPath());
			Document doc = new Document();
			Reader txtReader = new FileReader(f);

			doc.add(new Field("contents", txtReader，Field.TermVector.WITH_POSITIONS_OFFSETS));
			doc.add(new Field("filename", f.getCanonicalPath(), Field.Store.YES, Field.Index.UN_TOKENIZED));

			writer.addDocument(doc);

		} catch (Exception e) {
			e.printStackTrace();
		}
	}
}

2.搜索过程，红色的为修改部分，需要highlight和analysis的lucene的jar文件

 

package demo.example.searcher;

import java.util.*;

import org.apache.lucene.search.highlight.*;
import org.apache.lucene.analysis.*;
import org.apache.lucene.search.*;
import org.apache.lucene.queryParser.*;
import org.apache.lucene.analysis.standard.*;
import org.apache.lucene.document.*;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;

public class Searcher {
	private static Log log = LogFactory.getLog(Searcher.class);

	public static void main(String[] args) {
		String indexDir = "C:\\index";
		String q = "查询关键字";
		search(indexDir, q);
	}

	public static void search(String indexDir, String q) {
		try {
			IndexSearcher is = new IndexSearcher(indexDir);

			QueryParser queryParser = new QueryParser("contents", new StandardAnalyzer());
			Query query = queryParser.parse(q);
			long start = new Date().getTime();

			Hits hits = is.search(query);

			long end = new Date().getTime();

			System.out.println("use:" + (end - start));
                                                

 

   SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<strong><font color='red'>", "</font></strong>");
   SimpleFragmenter fragmenter = new SimpleFragmenter(60);

 

   Highlighter highlighter = new Highlighter(formatter, new QueryScorer(q));
   highlighter.setTextFragmenter(fragmenter);

 

   int maxNumFragmentsRequired = 10;
   String fragmentSeparator = "";
   TermPositionVector tpv = null;
   TokenStream tokenstream = null;

 

			for (int i = 0; i < hits.length(); i++) {
				Document doc = hits.doc(i);

 

                                                                 int id = hits.id(i);

 

				System.out.println("The right file:" + doc.get("filename"));

 

 tpv = (TermPositionVector) is.getIndexReader().getTermFreqVector(id, "contents");     

 

 tokenstream = TokenSources.getTokenStream(tpv);

 

String result = highlighter.getBestFragments(tokenstream, doc.get("contents"),
       maxNumFragmentsRequired, fragmentSeparator)

 

 System.out.println("The right file context is :" + result);

 

			}
		} catch (Exception e) {
			e.printStackTrace();
		}
	}

}

   在输出结果中，文件内容中命中的关键字被加上了

"<strong><font color='red'>", "</font></strong>"

   在网页中显示内容，即为黑体红字显示效果。