Highlighter高亮

package com.bjsxt.indexsearch;

import jeasy.analysis.MMAnalyzer;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriter.MaxFieldLength;
import org.apache.lucene.queryParser.MultiFieldQueryParser;
import org.apache.lucene.queryParser.QueryParser;
import org.apache.lucene.search.Filter;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.highlight.Formatter;
import org.apache.lucene.search.highlight.Fragmenter;
import org.apache.lucene.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.Scorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.RAMDirectory;

import com.bjsxt.utils.File2DocumentUtil;

public class IndexAndSearch {

	/**
	 * @param args
	 */
	String filePath = "D:\\flexWorkespace\\LuceneDemo\\luceneDataSource\\小笑话_总统的房间 Room .txt";
	String indexPath = "D:\\flexWorkespace\\LuceneDemo\\indexPath";

//	Analyzer analyzer = new StandardAnalyzer();
	Analyzer analyzer = new MMAnalyzer();	

	public static void main(String[] args) throws Exception {
//		new IndexAndSearch().createIndexByDir();
		new IndexAndSearch().search("房间");
	}

	public void createIndex() throws Exception {
		// File file = new File(filePath);
		Document doc = File2DocumentUtil.file2Document(filePath);

		// IndexWriter 是用来操作（增删改）索引库的
		IndexWriter iw = new IndexWriter(indexPath, analyzer, true,
				MaxFieldLength.LIMITED);
		iw.addDocument(doc);
		iw.close();
	}

	public void createIndexByDir()throws Exception {

		//1.创建时候载入文件系统里的索引
		Directory fsDir = FSDirectory.getDirectory(indexPath);
		Directory ramDir = new RAMDirectory(fsDir);
		//new ramIndexWriter时不需要重新创建
		IndexWriter ramIndexWriter = new IndexWriter(ramDir, analyzer, MaxFieldLength.LIMITED);
		//添加document
		Document doc = File2DocumentUtil.file2Document(filePath);
		ramIndexWriter.addDocument(doc);
		ramIndexWriter.close();

		//2.退出时保存内存里的索引
		//new fsIndexWriter时需要重新创建，即删除原来的索引文件
		IndexWriter fsIndexWriter = new IndexWriter(fsDir, analyzer, true, MaxFieldLength.LIMITED);
//		Directory[] dir = {ramDir};
		//保存内存里的索引
		fsIndexWriter.addIndexesNoOptimize(new Directory[]{ramDir});
		//把内存里的东西提交后才优化
		fsIndexWriter.commit();
		// 优化索引文件，把多个cfs文件合并成一个 
		fsIndexWriter.optimize();
		fsIndexWriter.close();
	}

	public void search(String queryStr) throws Exception {
		String[] fields = { "content","name" };
		QueryParser queryParser = new MultiFieldQueryParser(fields, analyzer);
		Query query = null;
		Filter filter = null;
		query = queryParser.parse(queryStr);
		IndexSearcher indexSearcher = null;
		indexSearcher = new IndexSearcher(indexPath);
		TopDocs topDocs = indexSearcher.search(query, filter, 1000);
		System.out.println("总共有" + topDocs.totalHits + "条记录：");
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			int docNum = scoreDoc.doc;
			Document doc = indexSearcher.doc(docNum);
			//---------------------------准备高亮器
			Formatter formatter = new SimpleHTMLFormatter("<font color='red'>","</font>");
			Scorer scorer = new QueryScorer(query);
			Highlighter highlighter = new Highlighter(formatter,scorer);
			Fragmenter fragmenter = new SimpleFragmenter(50);
			highlighter.setTextFragmenter(fragmenter);
			//---------------------------

			//--------------------------高亮
			//将高亮后的结果返回，如果当前属性值中没有出现关键字，则返回空
			String hc = highlighter.getBestFragment(analyzer, "content", doc.get("content"));
			if(hc == null){
				String content = doc.get("content");
				int endIndex = Math.min(50,content.length());System.out.println(content.length());
				hc = content.substring(0,endIndex);
			}
			doc.getField("content").setValue(hc);
			//--------------------------


			File2DocumentUtil.printDocumentInfo(doc);
		}
	}

	public void searchByDir(String queryStr) throws Exception {
		String[] fields = { "name", "content" };
		QueryParser queryParser = new MultiFieldQueryParser(fields, analyzer);
		Query query = null;
		Filter filter = null;
		query = queryParser.parse(queryStr);
		IndexSearcher indexSearcher = null;
		Directory fsDir = FSDirectory.getDirectory(indexPath);
		indexSearcher = new IndexSearcher(fsDir);
		TopDocs topDocs = indexSearcher.search(query, filter, 1000);
		System.out.println("总共有" + topDocs.totalHits + "条记录：");
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			int docNum = scoreDoc.doc;
			Document doc = indexSearcher.doc(docNum);
			File2DocumentUtil.printDocumentInfo(doc);
		}
	}
}