Lucene 全文检索

[b]1,信息检索与数据库的搜索对比 -- DB就不是为全文检索而设计的[/b]
a> 数据库的搜索不能实现我们的全文检索的要求,原因如下: 匹配效果:如搜索 ant,在 sql 中使用 like %ant%'是会搜索出 planting 的,但他不应出现.
b> 查出的结果没有相关度排序,不知道有用的结果在哪一页.
c> 搜索速度太慢,达不到毫秒级的要求

[b]2， 整体流程[/b]
[img]http://dl.iteye.com/upload/attachment/476858/6ab1048a-1920-3157-a2a6-46d453785787.jpg[/img]


[img]http://dl.iteye.com/upload/attachment/476870/080a8328-0ed7-3ef9-b462-86722279bc25.jpg[/img]


[b]3， 主要概念[/b]
索引， 分词器， 高亮器， 过滤器

[b]4， 代码[/b]

package cn.itcast.lucene.helloworld;

import jeasy.analysis.MMAnalyzer;

import org.apache.lucene.analysis.Analyzer;
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.junit.Test;

import cn.itcast.lucene.utils.File2DocumentUtils;

public class HelloWorld2 {

	String filePath = "luceneDatasource\\ch1.txt";
	String filePath2 = "luceneDatasource\\ch2.txt";
	String filePath3 = "luceneDatasource\\ch3.txt";
	String filePath4 = "luceneDatasource\\ch4.txt";

	String indexPath = "luceneIndex2";

	Analyzer analyzer = new MMAnalyzer();

	/**
	 * 创建索引
	 * 
	 * IndexWriter 是用来操作（增、删、改）索引库的
	 */
	@Test
	public void createIndex() throws Exception {
		// file --> doc
		Document doc = File2DocumentUtils.file2Document(filePath);
		Document doc2 = File2DocumentUtils.file2Document(filePath2);
		Document doc3 = File2DocumentUtils.file2Document(filePath3);
		Document doc4 = File2DocumentUtils.file2Document(filePath4);

		// 建立索引
		IndexWriter indexWriter = new IndexWriter(indexPath, analyzer, true,
				MaxFieldLength.LIMITED);
		indexWriter.addDocument(doc);
		indexWriter.addDocument(doc2);
		indexWriter.addDocument(doc3);
		indexWriter.addDocument(doc4);

		indexWriter.close();
	}

	/**
	 * 搜索
	 * 
	 * IndexSearcher 是用来在索引库中进行查询的
	 */
	@Test
	public void search() throws Exception {
//		String queryString = "document";
		String queryString = "商品";

		// 1，把要搜索的文本解析为 Query
		String[] fields = { "content" };
		QueryParser queryParser = new MultiFieldQueryParser(fields, analyzer);
		Query query = queryParser.parse(queryString);

		// 2，进行查询
		IndexSearcher indexSearcher = new IndexSearcher(indexPath);
		Filter filter = null;
		TopDocs topDocs = indexSearcher.search(query, filter, 10000);
		System.out.println("总共有【" + topDocs.totalHits + "】条匹配结果");

		// 3，打印结果
		for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
			int docSn = scoreDoc.doc; // 文档内部编号
			Document doc = indexSearcher.doc(docSn); // 根据编号取出相应的文档
			File2DocumentUtils.printDocumentInfo(doc); // 打印出文档信息
		}
	}
}

package cn.itcast.lucene.utils;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;

import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.NumberTools;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;

public class File2DocumentUtils {

	// 文件：name, content, size, path
	public static Document file2Document(String path) {
		File file = new File(path);

		Document doc = new Document();
		doc.add(new Field("name", file.getName(), Store.YES, Index.ANALYZED));
		doc.add(new Field("content", readFileContent(file), Store.YES, Index.ANALYZED));
		doc.add(new Field("size", NumberTools.longToString(file.length()), Store.YES, Index.NOT_ANALYZED));
		doc.add(new Field("path", file.getAbsolutePath(), Store.YES, Index.NOT_ANALYZED));
		return doc;
	}

	// public static void document2File(Document doc ){
	//		
	// }

	/**
	 * 读取文件内容
	 */
	public static String readFileContent(File file) {
		try {
			BufferedReader reader = new BufferedReader(new InputStreamReader(new FileInputStream(file)));
			StringBuffer content = new StringBuffer();

			for (String line = null; (line = reader.readLine()) != null;) {
				content.append(line).append("\n");
			}

			return content.toString();
		} catch (Exception e) {
			throw new RuntimeException(e);
		}
	}

	/**
	 * <pre>
	 * 获取 name 属性的值的两种方法：
	 * 1，Field f = doc.getField("name");
	 *    f.stringValue();
	 * 2，doc.get("name");
	 * </pre>
	 * 
	 * @param doc
	 */
	public static void printDocumentInfo(Document doc) {
		// Field f = doc.getField("name");
		// f.stringValue();
		System.out.println("------------------------------");
		System.out.println("name     = " + doc.get("name"));
		System.out.println("content  = " + doc.get("content"));
		System.out.println("size     = " + NumberTools.stringToLong(doc.get("size")));
		System.out.println("path     = " + doc.get("path"));
	}

}

5， 相关查询文件 & JAR包
见附件