01_java Lucene学习——创建索引

吐槽：

看到视频是3.5，用的jar包是4.0.源代码是4.1.。。悲哀。。

我只有4.9的源码。。。

说明：

1.用的是lucene4.0版本。

2.创建的索引是保存在硬盘上。

3.代码中对日期初始化用的是自己的工具栏，没有上传。common.DateUtil

4.lucene 4.0版本特性 http://www.cnblogs.com/ibook360/archive/2012/12/29/2839094.html

说明二：

1.搜索的过程，其实就是在索引中查找单词，进而找到包含这个单词的文档的过程。

2.查全率：搜索系统中搜索到相关文档的能力；

   查准率：搜索系统中过滤掉不相关文档的能力；

创建索引步骤：

1.创建Directory对象，指定索引类型以及索引存储位置
2.创建IndexWriter对象，用于将Document对象写入到Directory指定的存储位置 
3.创建Docment对象，包装源数据；
4.关闭IndexWriter

导入的基础包：

代码分析：

1.源数据被封装成为document对象时，不同于3.x版本，field的类型变得更加具体了；

2.之前的版本中需要需要知道field的存储域（Field.Store）和索引域（Field.Index），4.0不需要指定索引域

是因为有默认选项

如图1

doc = new Document();
doc.add(new StringField("id", ids[i], Field.Store.YES));
doc.add(new StringField("email", emails[i],Field.Store.YES));
doc.add(new TextField("content", contents[i],Field.Store.YES));
doc.add(new StringField("name", names[i], Field.Store.YES));
// 存储数字
doc.add(new IntField("attach", attachs[i],Field.Store.YES));
// 存储日期
doc.add(new LongField("date", dates[i].getTime(),Field.Store.YES));

StringField为例：

源代码

***如果不需要使用默认的选项，可考虑这种写法

代码功能，创建索引，保存的硬盘中。query方法返回建立的索引记录；

package searcher;


import java.io.File;
import java.io.IOException;
import java.util.Date;
import java.util.HashMap;
import java.util.Map;


import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
import org.apache.lucene.document.IntField;
import org.apache.lucene.document.LongField;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
import org.apache.lucene.index.CorruptIndexException;
import org.apache.lucene.index.DirectoryReader;
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.store.MMapDirectory;
import org.apache.lucene.store.NIOFSDirectory;
import org.apache.lucene.store.SimpleFSDirectory;
import org.apache.lucene.util.Version;


import common.DateUtil;


public class IndexUtil {
// 示例源数据：需要创建索引的数据---begin
private String[] ids = { "1", "2", "3", "4", "5", "6" };
private String[] emails = { "aa@163.com", "bb@163.com", "cc@mit.edu",
"dd@sina.org", "ee@mit.edu", "ff@126.com" };
private String[] contents = { "welcome to China,I like book",
"hello little two b, I like tennis", "my name is cc I like game",
"I like football", "I like football and I like basketball too",
"I like movie and swimming" };
private Date[] dates = new Date[6];
private int[] attachs = { 2, 3, 1, 4, 5, 5 };
private String[] names = { "adele", "betty", "kitty", "jetty", "jack",
"rose" };
// 示例源数据：需要创建索引的数据---end


private static Directory directory = null;


public IndexUtil() {
initDates();


// 创建directory对象
try {
directory = FSDirectory.open(new File("D:/test/luceneIndex"));
// 判断当前directory具体的实例化对象类型
if (directory instanceof MMapDirectory) {
System.out.println("directory belongs to  MMapDirectory");
} else if (directory instanceof SimpleFSDirectory) {
System.out.println("directory belongs to SimpleFSDirectory");
} else if (directory instanceof NIOFSDirectory) {
System.out.println("directory belongs to NIOFSDirectory");
}


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


// 创建索引
index();
}


/**
* 初始化日期数据
*/
private void initDates() {
Date date = new Date();
for (int i = 1; i <= 6; i++) {
dates[i - 1] = DateUtil.getRelativeDate(date, -i);
}
}


/**
* 创建索引基本步骤： 
* 1.创建Directory对象，指定索引类型以及索引存储位置
* 2.创建IndexWriter对象，用于将Document对象写入到Directory指定的存储位置 
* 3.创建Docment对象，包装源数据；
* 4.关闭IndexWriter
* 
*/
public void index() {
IndexWriter writer = null;
try {
// 创建writer对象
writer = getWriter(directory);

if (writer != null) {

// 删除原来的索引，若存在
writer.deleteAll();
// 删除后，commit可以立即生效
//writer.commit();

// 创建document对象
Document doc = null;
for (int i = 0; i < ids.length; i++) {
doc = new Document();

// 写法一
//FieldType fileType = new FieldType();
//fileType.setIndexed(false); // 不需要索引
//fileType.setStored(true);
//doc.add(new Field("id", ids[i], fileType));

// StringField默认需要索引
doc.add(new StringField("id", ids[i], Field.Store.YES));
doc.add(new StringField("email", emails[i],Field.Store.YES));
doc.add(new TextField("content", contents[i],Field.Store.YES));
doc.add(new StringField("name", names[i], Field.Store.YES));
// 存储数字
doc.add(new IntField("attach", attachs[i],Field.Store.YES));
// 存储日期
doc.add(new LongField("date", dates[i].getTime(),Field.Store.YES));
writer.addDocument(doc);
}
}
} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (LockObtainFailedException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
} finally {
try {
closeWriter(writer);
} catch (IOException e) {
e.printStackTrace();
}
}
}


/**
* 创建IndexWriter对象
* @param directory
* @return
* @throws IOException
*/
public IndexWriter getWriter(Directory directory) throws IOException {
if (directory == null) {
return null;
}
IndexWriter writer = new IndexWriter(directory, new IndexWriterConfig(
Version.LUCENE_40, new StandardAnalyzer(Version.LUCENE_40)));
return writer;
}


/**
* 关闭Writer
* @param writer
* @throws IOException
*/
public void closeWriter(IndexWriter writer) throws IOException {
if (writer != null) {
writer.close();
}
}

public void query() {
try {
// 获取reader对象
IndexReader reader = DirectoryReader.open(directory);

// 通过reader可以有效的获取到文档的数量
System.out.println("numDocs:" + reader.numDocs());
System.out.println("maxDocs:" + reader.maxDoc());
System.out.println("deleteDocs:" + reader.numDeletedDocs());

reader.close();

} catch (CorruptIndexException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}

}