lucene与庖丁解牛简单示例

首先是建立索引的类文件:

 

 

package com.jereh.lucene;

import java.io.*;
import java.util.Date;
import net.paoding.analysis.analyzer.PaodingAnalyzer;
import org.apache.lucene.document.DateTools;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;

/**
 * 创建索引 Lucene 3.0+
 * 
 * @author Administrator
 * 
 */
public class Indexer {

	/**
	 * @param args
	 * @throws IOException
	 */
	public static void index(String dateDir, String indexDir)
			throws IOException {
		IndexWriter indexWriter = null;
		// 创建Directory对象
		Directory dir = FSDirectory.getDirectory(new File(indexDir)); 
		// 创建IndexWriter对象,第一个参数是Directory,第二个是分词器,第三个表示是否是创建,如果为false为在此基础上面修改,第四表示表示分词的最大值，比如说new
		// MaxFieldLength(2)，就表示两个字一分，一般用IndexWriter.MaxFieldLength.LIMITED
		indexWriter = new IndexWriter(dir,new PaodingAnalyzer());
		File[] files = new File(dateDir).listFiles();
		for (int i = 0; i < files.length; i++) {
			Document doc = new Document();
			// 创建Field对象，并放入doc对象中
			doc.add(new Field("contents", readContents(files[i], "UTF-8"),
					Field.Store.YES, Field.Index.UN_TOKENIZED));
			doc.add(new Field("filename", files[i].getName(), Field.Store.YES,
					Field.Index.TOKENIZED));
			doc.add(new Field("indexDate", DateTools.dateToString(new Date(),
					DateTools.Resolution.DAY), Field.Store.YES,
					Field.Index.TOKENIZED));
			// 写入IndexWriter
			indexWriter.addDocument(doc);
		}
		// 查看IndexWriter里面有多少个索引
		System.out.println("numDocs:" + indexWriter.numRamDocs());
		indexWriter.optimize();
		indexWriter.close();
	}

	public static String readContents(File file, String charset)
			throws IOException {
		BufferedReader reader = new BufferedReader(new InputStreamReader(
				new FileInputStream(file), charset));
		String line = new String();
		String temp = new String();

		while ((line = reader.readLine()) != null) {
			temp += line;
		}
		reader.close();
		return temp;
	}

}

 

 其次是进行搜索的类:

 

package com.jereh.lucene;

import java.io.File;
import java.io.IOException;
import net.paoding.analysis.analyzer.PaodingAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.queryParser.ParseException;
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.store.Directory;
import org.apache.lucene.store.FSDirectory;
/**
 * 搜索索引 Lucene 3.0+
 * 
 * @author Administrator
 * 
 */
public class Searcher {

	public static void search(String indexDir) throws IOException,
			ParseException {
		Directory dir = FSDirectory.getDirectory(new File(indexDir));
		// 创建 IndexSearcher对象，相比IndexWriter对象，这个参数就要提供一个索引的目录就行了
		IndexSearcher indexSearch = new IndexSearcher(dir);
		// 创建QueryParser对象,第一个参数表示Lucene的版本,第二个表示搜索Field的字段,第三个表示搜索使用分词器
		QueryParser queryParser = new QueryParser("filename",new PaodingAnalyzer());
		// 生成Query对象
		Query query = queryParser.parse("滑移装载机");
		// 搜索结果 TopDocs里面有scoreDocs[]数组，里面保存着索引值
		//TopDocs hits = indexSearch.search(query, 10);
		Hits hits = indexSearch.search(query);
		// hits.totalHits表示一共搜到多少个
		System.out.println("找到了" + hits.length() + "个");
		// 循环hits.scoreDocs数据，并使用indexSearch.doc方法把Document还原，再拿出对应的字段的值
		Document doc = null;
		for(int i=0;i<hits.length();i++){
			doc = hits.doc(i);
			System.out.print(doc.get("filename"));
		}
		indexSearch.close();
	}
}

 

最后是运行的类:

 

package com.jereh.lucene;

import java.io.File;
import java.io.IOException;

import net.paoding.analysis.analyzer.PaodingAnalyzer;
import net.paoding.analysis.examples.gettingstarted.BoldFormatter;
import org.apache.lucene.analysis.Analyzer;
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.ParseException;
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.search.highlight.Highlighter;
import org.apache.lucene.search.highlight.QueryScorer;
import org.apache.lucene.search.highlight.SimpleFragmenter;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;

public class Test {

	public static void main(String[] args) throws IOException, ParseException {
		// try {
		// //Indexer.index("E:/code/jrcms_liugong/website/products/",
		// "F:/workspace/spring-mvc/WebRoot/WEB-INF/index/");
		// Searcher.search("F:/workspace/spring-mvc/WebRoot/WEB-INF/index/");
		// } catch (Exception e) {
		// e.printStackTrace();
		// }
		// 将庖丁封装成符合Lucene要求的Analyzer规范
		String dateDir = "E:/code/jrcms_liugong/website/about/";
		Analyzer analyzer = new PaodingAnalyzer();
		File[] files = new File(dateDir).listFiles();
		for (File f : files) {
			// 读取本类目录下的text.txt文件
			String content = Indexer.readContents(f, "UTF-8");
			// 接下来是标准的Lucene建立索引和检索的代码
			Directory ramDir = new RAMDirectory();
			IndexWriter writer = new IndexWriter(ramDir, analyzer);
			Document doc = new Document();
			Field fname = new Field("filename",f.getName(),Field.Store.YES,Field.Index.UN_TOKENIZED);
			Field fd = new Field("contents", content, Field.Store.YES,
					Field.Index.TOKENIZED,
					Field.TermVector.WITH_POSITIONS_OFFSETS);
			doc.add(fname);
			doc.add(fd);
			writer.addDocument(doc);
			writer.optimize();
			writer.close();
			IndexReader reader = IndexReader.open(ramDir);
			String queryString = "国家级企业技术中心";
			QueryParser parser = new QueryParser("contents", analyzer);
			Query query = parser.parse(queryString);
			Searcher searcher = new IndexSearcher(ramDir);
			query = query.rewrite(reader);
			//System.out.println("Searching for: " + query.toString("contents"));
			Hits hits = searcher.search(query);
			BoldFormatter formatter = new BoldFormatter();
			Highlighter highlighter = new Highlighter(formatter,
					new QueryScorer(query));
			highlighter.setTextFragmenter(new SimpleFragmenter(50));
			for (int i = 0; i < hits.length(); i++) {
				String text = hits.doc(i).get("filename");
//				int maxNumFragmentsRequired = 5;
//				String fragmentSeparator = "...";
//				TermPositionVector tpv = (TermPositionVector) reader.getTermFreqVector(hits.id(i), "contents");
//				TokenStream tokenStream = TokenSources.getTokenStream(tpv);
//				String result = highlighter.getBestFragments(tokenStream, text,
//						maxNumFragmentsRequired, fragmentSeparator);
//				System.out.println("\n" + result);
				System.out.println(text);
			}
			reader.close();
		}

	}
}