lucene3.6 mysql_lucene3.6.1 经典案例 入门教程

package lucene;

import java.io.BufferedReader;

import java.io.File;

import java.io.FileInputStream;

import java.io.IOException;

import java.io.InputStreamReader;

import java.util.Date;

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;

import org.apache.lucene.index.IndexWriter;

import org.apache.lucene.index.IndexWriterConfig;

import org.apache.lucene.index.IndexWriterConfig.OpenMode;

import org.apache.lucene.store.Directory;

import org.apache.lucene.store.FSDirectory;

import org.apache.lucene.util.Version;

public class TextFileIndexer {

public static void main(String[] args) throws Exception {

/* 指明要索引文件夹的位置,这里是C盘的source文件夹下 */

File fileDir = new File("c:\\source");

/* 这里放索引文件的位置 */

File indexDir = new File("c:\\index");

Directory dir = FSDirectory.open(indexDir);

Analyzer lunAnalyzer = new StandardAnalyzer(Version.LUCENE_36);

IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_36, lunAnalyzer);

iwc.setOpenMode(OpenMode.CREATE);

IndexWriter indexWriter = new IndexWriter(dir, iwc);

File[] textFiles = fileDir.listFiles();

//开始时间

long startTime = new Date().getTime();

//增加document到索引去

for(int i=0; i

if(textFiles[i].isFile() && textFiles[i].getName().endsWith(".txt")){

System.out.println("File:"+textFiles[i].getCanonicalPath()+" 正在被索引....");

//读取文件内容

String tmp = FileReaderAll(textFiles[i].getCanonicalPath(), "GBK");

System.out.println("文件内容：");

System.out.println(tmp);

System.out.println("文件内容结束");

Document document = new Document();

Field FieldPath = new Field("path", textFiles[i].getPath(),

Field.Store.YES, Field.Index.NO);

Field FieldBody = new Field("body", tmp, Field.Store.YES,

Field.Index.ANALYZED,

Field.TermVector.WITH_POSITIONS_OFFSETS);

document.add(FieldPath);

document.add(FieldBody);

indexWriter.addDocument(document);

}

}

indexWriter.close();

//测试索引时间

long endTime = new Date().getTime();

System.out.println("建立索引总花费了："+(endTime-startTime)+"毫秒值");

}

//读取文件内容

public static String FileReaderAll(String FileName, String charset)

throws IOException {

BufferedReader reader = new BufferedReader(new InputStreamReader(

new FileInputStream(FileName), charset));

String line = new String();

String temp = new String();

while ((line = reader.readLine()) != null) {

temp += line;

}

reader.close();

return temp;

}

}

输出结果为：

File:C:\source\test1.txt 正在被索引....

文件内容：

欢迎来到绝对秋香的博客。

文件内容结束

File:C:\source\test2.txt 正在被索引....

文件内容：

绝对秋香引领你走向潮流。

文件内容结束

建立索引总花费了：406毫秒值

第四步，建立测试类TestQuery，并运行主函数，输出测试结果，查找索引值

package lucene;

import java.io.File;

import org.apache.lucene.analysis.Analyzer;

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

import org.apache.lucene.index.IndexReader;

import org.apache.lucene.queryParser.QueryParser;

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.apache.lucene.store.FSDirectory;

import org.apache.lucene.util.Version;

public class TestQuery {

public static void main(String[] args) throws Exception{

//搜索的索引路径

String index = "c:\\index";

IndexReader indexReader = IndexReader.open(FSDirectory.open(new File(index)));

IndexSearcher searcher = new IndexSearcher(indexReader);

ScoreDoc[] hits = null;

//搜索的关键字

String queryString = "绝对";

Query query = null;

Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_36);

try {

QueryParser qp = new QueryParser(Version.LUCENE_36, "body", analyzer);

query = qp.parse(queryString);

} catch (Exception e) {

// TODO: handle exception

}

if(searcher != null){

//返回最多10条记录

TopDocs results = searcher.search(query, 10);

hits = results.scoreDocs;

if(hits.length > 0){

System.out.println("找到"+hits.length+"个结果！");

System.out.println(hits[0].toString());

}

searcher.close();

}

}

}

结果：

找到2个结果！

doc=0 score=0.21019982 shardIndex=-1

给个参加网站：