lucene(全文搜索)_根据内容建立索引_源码下载

在我们的开发过程中，会遇到这样的情况：

给出下面的信息，让我们进行建立索引，并且进行搜索信息

这个时候，我们应该怎样处理呢？

要实现这样的功能，其实使用lucene会变得简单很多！！

========================================

项目结构：

运行

@Test
    public void testIndex(){
        LuceneUtil util = new LuceneUtil();
        util.index();
    }

效果：

运行

@Test
    public void testQuery(){
        LuceneUtil util = new LuceneUtil();
        util.query();
    }

效果：

=========================================================

代码部分：

=========================================================

/lucene_0200_index/src/com/b510/lucene/util/LuceneUtil.java

/**
 * 
 */
package com.b510.lucene.util;

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

import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.LockObtainFailedException;
import org.apache.lucene.util.Version;

/**
 * @author Hongten <br />
 * @date 2013-1-31
 */
public class LuceneUtil {

    /**
     * 邮件id
     */
    private String[] ids = { "1", "2", "3", "4", "5", "6" };
    /**
     * 邮箱
     */
    private String[] emails = { "aa@sina.com", "bb@foxmail.com", "cc@qq.com",
            "dd@163.com", "ee@gmail.com", "ff@sina.com" };
    /**
     * 邮件内容
     */
    private String[] contents = { "hello,aa", "hello,bb", "hello,cc",
            "hello,dd", "hello,ee", "hello,ff" };
    /**
     * 邮件的附件
     */
    private int[] attachs = { 1, 5, 3, 4, 2, 6 };
    /**
     * 收件人的名称
     */
    private String[] names = { "hongten", "hanyuan", "Devide", "Tom", "Steven",
            "Shala" };

    private Directory directory = null;

    public LuceneUtil() {
        try {
            directory = FSDirectory.open(new File(
                    "D:/WordPlace/lucene/lucene_0200_index/lucene/index"));
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

    /**
     * 创建索引
     */
    public void index() {
        IndexWriter writer = null;
        try {
            writer = new IndexWriter(directory, new IndexWriterConfig(
                    Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
            // 创建文档
            Document document = null;
            for (int i = 0; i < ids.length; i++) {
                // Field.Store.YES:将会存储域值，原始字符串的值会保存在索引，以此可以进行相应的回复操作，对于主键，标题可以是这种方式存储
                // Field.Store.NO:不会存储域值，通常与Index.ANAYLIZED和起来使用，索引一些如文章正文等不需要恢复的文档
                // ==============================
                // Field.Index.ANALYZED:进行分词和索引，适用于标题，内容等
                // Field.Index.NOT_ANALYZED:进行索引，但是不进行分词，如身份证号码，姓名，ID等，适用于精确搜索
                // Field.Index.ANALYZED_NOT_NORMS:进行分词，但是不进行存储norms信息，这个norms中包括了创建索引的时间和权值等信息
                // Field.Index.NOT_ANALYZED_NOT_NORMS:不进行分词也不进行存储norms信息(不推荐)
                // Field.Index.NO:不进行分词
                document = new Document();
                document.add(new Field("id", ids[i], Field.Store.YES,
                        Field.Index.NOT_ANALYZED_NO_NORMS));
                document.add(new Field("email", emails[i], Field.Store.YES,
                        Field.Index.NOT_ANALYZED));
                document.add(new Field("content", contents[i], Field.Store.YES,
                        Field.Index.ANALYZED));
                // document.add(new
                // Field("attach",attachs[i],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
                document.add(new Field("name", names[i], Field.Store.YES,
                        Field.Index.NOT_ANALYZED_NO_NORMS));
                writer.addDocument(document);
            }
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (LockObtainFailedException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        } finally {
            if (writer != null) {
                try {
                    writer.close();
                } catch (CorruptIndexException e) {
                    e.printStackTrace();
                } catch (IOException e) {
                    e.printStackTrace();
                }
            }
        }
    }

    /**
     * 查询索引
     */
    public void query() {
        try {
            IndexReader reader = IndexReader.open(directory);
            System.out.println("文档数目：" + reader.numDocs());
            System.out.println("文档总数：" + reader.maxDoc());
        } catch (CorruptIndexException e) {
            e.printStackTrace();
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}

/lucene_0200_index/src/com/b510/lucene/test/IndexTest.java

/**
 * 
 */
package com.b510.lucene.test;

import org.junit.Test;

import com.b510.lucene.util.LuceneUtil;

/**
 * @author Hongten <br />
 * @date 2013-1-31
 */
public class IndexTest {

    @Test
    public void testIndex(){
        LuceneUtil util = new LuceneUtil();
        util.index();
    }
    
    @Test
    public void testQuery(){
        LuceneUtil util = new LuceneUtil();
        util.query();
    }
}

 项目源码：https://files.cnblogs.com/hongten/lucene_0200_index.zip

I'm Hongten