lucene4.0入门实例

1:以前用3.5的时候，到现在也差不多忘了，重新看了下文档，写个简单的例子

lucene4.0中有很多新的东西，其中Field类主要不能new Field()要通过其子类去实现比如new StringField()等，对分词等参数也有部分变化。

创建索引的代码如下：

Java代码







package com.search.lucene;

import java.io.File;

import org.apache.lucene.analysis.Analyzer;

import org.apache.lucene.analysis.standard.StandardAnalyzer;

import org.apache.lucene.document.Document;

import org.apache.lucene.document.Field.Store;

import org.apache.lucene.document.StringField;

import org.apache.lucene.document.TextField;

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.util.Version;

import org.junit.Before;
import org.junit.Test;

public class IndexFile {

protected String[] ids={"1",
"2"};

protected String[] content={"Amsterdam has lost of add cancals",
"i love add this girl"};

protected String[] city={"Amsterdam",
"Venice"};

private Directory dir;

/**
* 初始添加文档
* @throws Exception
*/
@Test
public void init()
throws Exception {
String pathFile="D://lucene/index";

dir=FSDirectory.open(new File(pathFile));

IndexWriter writer=getWriter();
for(int i=0; i < ids.length; i++) {

Document doc=new Document();

doc.add(new StringField("id", ids[i], Store.YES));

doc.add(new TextField("content", content[i], Store.YES));

doc.add(new StringField("city", city[i], Store.YES));

writer.addDocument(doc);
}
System.out.println("init ok?");

writer.close();
}

/**
* 获得IndexWriter对象
* @return
* @throws Exception
*/
public IndexWriter getWriter()
throws Exception {
Analyzer analyzer=new StandardAnalyzer(Version.LUCENE_40);

IndexWriterConfig iwc=new IndexWriterConfig(Version.LUCENE_40, analyzer);

return new IndexWriter(dir, iwc);

}

}

package com.search.lucene;

import java.io.File;

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.standard.StandardAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.document.StringField;
import org.apache.lucene.document.TextField;
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.util.Version;
import org.junit.Before;
import org.junit.Test;

public class IndexFile {

protected String[] ids={"1", "2"};

protected String[] content={"Amsterdam has lost of add  cancals", "i love  add this girl"};

protected String[] city={"Amsterdam", "Venice"};

private Directory dir;

/**
* 初始添加文档
* @throws Exception
*/
@Test
public void init() throws Exception {
String pathFile="D://lucene/index";
dir=FSDirectory.open(new File(pathFile));
IndexWriter writer=getWriter();
for(int i=0; i < ids.length; i++) {
Document doc=new Document();
doc.add(new StringField("id", ids[i], Store.YES));
doc.add(new TextField("content", content[i], Store.YES));
doc.add(new StringField("city", city[i], Store.YES));
writer.addDocument(doc);
}
System.out.println("init ok?");
writer.close();
}

/**
* 获得IndexWriter对象
* @return
* @throws Exception
*/
public IndexWriter getWriter() throws Exception {
Analyzer analyzer=new StandardAnalyzer(Version.LUCENE_40);
IndexWriterConfig iwc=new IndexWriterConfig(Version.LUCENE_40, analyzer);
return new IndexWriter(dir, iwc);
}

}

说明下：lucene4.0中有核心包和其他包:我导入



Java代码







package com.search.lucene;

import java.io.File;

import org.apache.lucene.document.Document;

import org.apache.lucene.index.DirectoryReader;

import org.apache.lucene.index.IndexReader;

import org.apache.lucene.index.Term;

import org.apache.lucene.search.IndexSearcher;

import org.apache.lucene.search.ScoreDoc;

import org.apache.lucene.search.TermQuery;

import org.apache.lucene.search.TopDocs;

import org.apache.lucene.store.Directory;

import org.apache.lucene.store.FSDirectory;

import org.junit.Test;

public class IndexSearch {

/**
* 查询
* @throws Exception
*/
@Test
public void search()
throws Exception {
String filePath="D://lucene/index";

Directory dir=FSDirectory.open(new File(filePath));

IndexReader reader=DirectoryReader.open(dir);
IndexSearcher searcher=new IndexSearcher(reader);

Term term=new Term("content",
"add");
TermQuery query=new TermQuery(term);

TopDocs topdocs=searcher.search(query, 5);

ScoreDoc[] scoreDocs=topdocs.scoreDocs;
System.out.println("查询结果总数---" + topdocs.totalHits+"最大的评分--"+topdocs.getMaxScore());

for(int i=0; i < scoreDocs.length; i++) {

int doc = scoreDocs[i].doc;

Document document = searcher.doc(doc);
System.out.println("content===="+document.get("content"));

System.out.println("id--" + scoreDocs[i].doc +
"---scors--" + scoreDocs[i].score+"---index--"+scoreDocs[i].shardIndex);

}
reader.close();
}
}

package com.search.lucene;

import java.io.File;

import org.apache.lucene.document.Document;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexReader;
import org.apache.lucene.index.Term;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.FSDirectory;
import org.junit.Test;

public class IndexSearch {

/**
* 查询
* @throws Exception
*/
@Test
public void search() throws Exception {
String filePath="D://lucene/index";
Directory dir=FSDirectory.open(new File(filePath));
IndexReader reader=DirectoryReader.open(dir);
IndexSearcher searcher=new IndexSearcher(reader);
Term term=new Term("content", "add");
TermQuery query=new TermQuery(term);
TopDocs topdocs=searcher.search(query, 5);
ScoreDoc[] scoreDocs=topdocs.scoreDocs;
System.out.println("查询结果总数---" + topdocs.totalHits+"最大的评分--"+topdocs.getMaxScore());
for(int i=0; i < scoreDocs.length; i++) {
int doc = scoreDocs[i].doc;
Document document = searcher.doc(doc);
System.out.println("content===="+document.get("content"));
System.out.println("id--" + scoreDocs[i].doc + "---scors--" + scoreDocs[i].score+"---index--"+scoreDocs[i].shardIndex);
}
reader.close();
}
}

result:

查询结果总数---2最大的评分--0.2972674

Java代码







content====i love add this girl

id--1---scors--0.2972674---index---1

content====Amsterdam has lost of add cancals
id--0---scors--0.26010898---index---1

content====i love  add this girl
id--1---scors--0.2972674---index---1
content====Amsterdam has lost of add  cancals
id--0---scors--0.26010898---index---1

大小: 7 KB

查看图片附件