很長一段時間沒有關注hadoop，忽然間有興致，因而動手又研究一下
準備的基礎以下:
下載hadoop-1.0.4,tomcat,lucene因爲關於hadoop的基礎資料也挺多的，因此這裏只寫一段關於hadoop+lucene+web小綜合的demo設計思路， 但願對初學入門者有所啓示，以下圖:
本例子會引用最初hadoop提供的wordcount例子,具體的代碼能夠經過網上獲得,而後運行.
workcount輸入文件名稱inputfile.txt 包含內容：
Hello World Bye World goole
workcount輸出的文件名稱part-00000 ，包含內容：
Bye 1
Hello 1
World 2
goole 1
Hello 1
World 2
goole 1
假設:在生成part-00000 文件以後,立刻調用lucene建立索引文件
建立索引文件的java代碼以下：
// @author minn
IndexWriter writer = new IndexWriter(PRE_PATH+ "index",new SimpleAnalyzer(),true);
FileReader read = new FileReader(PRE_PATH+"part-00000");
BufferedReader br = new BufferedReader(read);
String row;
Document document =null;
while((row = br.readLine())!=null){
String tmp[]=row.split("\\s+");
document=new Document();
document.add(new Field("name",tmp[0],Field.Store.YES,Field.Index.TOKENIZED));
document.add(new Field("count",tmp[1],Field.Store.YES,Field.Index.TOKENIZED));
writer.addDocument(document);
}
writer.optimize();
writer.close();
查找java代碼：
/**
*
* @author minn
*
*/
public static String searchWord(String word) throws Exception {
Analyzer analyzer = new StandardAnalyzer();
String result = "";
IndexSearcher indexSearcher = null;
indexSearcher = new IndexSearcher(PRE_PATH + "index");
QueryParser queryParser = new QueryParser("name", analyzer);
Query query = null;
query = queryParser.parse(word);
if (null != query && null != indexSearcher) {
Hits hits = indexSearcher.search(query);
result = hits.doc(0).get("count");
}
return result;
}
servlet調用lucene查找：
package servlet;
import java.io.IOException;
import java.io.PrintWriter;
import java.sql.Connection;
import java.sql.ResultSet;
import java.sql.SQLException;
import java.sql.Statement;
import java.util.ArrayList;
import java.util.Date;
import java.util.HashMap;
import java.util.List;
import java.util.Map;
import javax.servlet.ServletException;
import javax.servlet.http.HttpServlet;
import javax.servlet.http.HttpServletRequest;
import javax.servlet.http.HttpServletResponse;
import lucene.SearchHadoopFile;
/**
* Servlet implementation class HadoopServlet
* @author minn
*/
public class HadoopServlet extends HttpServlet {
private static final long serialVersionUID = 1L;
/**
* @see HttpServlet#HttpServlet()
*/
public HadoopServlet() {
super();
// TODO Auto-generated constructor stub
}
/**
* @see HttpServlet#doGet(HttpServletRequest request, HttpServletResponse response)
*/
protected void doGet(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
// TODO Auto-generated method stub
doPost(request,response);
}
/**
* @see HttpServlet#doPost(HttpServletRequest request, HttpServletResponse response)
*/
protected void doPost(HttpServletRequest request, HttpServletResponse response) throws ServletException, IOException {
// TODO Auto-generated method stubintl
String result="";
PrintWriter out=response.getWriter();
try {
result= SearchHadoopFile.searchWord(request.getParameter("word"));
} catch (Exception e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
out.write(result);
out.flush();
out.close();
}
}
web頁面：
寫道
<%@ page language="java" contentType="text/html; charset=UTF-8"
pageEncoding="UTF-8"%>
<%@ taglib prefix="c" uri="http://java.sun.com/jsp/jstl/core" %>
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<title>hadoop lucene test</title>
<script type="text/javascript" src="js/jquery-1.7.1.min.js"></script>
<script type="text/javascript">
function queryWord(){
var word=$('#searchWord_id').val();
$.ajax({
type: "POST",
url: "hServlet",
data: { word: word }
}).done(function( msg ) {
$('#count_id').text('結果:'+msg);
});
}
</script>
</head>
<body>
<div>關鍵字:Hello,World bye,google</div>
查找字段:<input id="searchWord_id" type="text"><input type="button" value="查找">
<div id="count_id"></div>
</body>
</html>
pageEncoding="UTF-8"%>
<%@ taglib prefix="c" uri="http://java.sun.com/jsp/jstl/core" %>
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=UTF-8">
<title>hadoop lucene test</title>
<script type="text/javascript" src="js/jquery-1.7.1.min.js"></script>
<script type="text/javascript">
function queryWord(){
var word=$('#searchWord_id').val();
$.ajax({
type: "POST",
url: "hServlet",
data: { word: word }
}).done(function( msg ) {
$('#count_id').text('結果:'+msg);
});
}
</script>
</head>
<body>
<div>關鍵字:Hello,World bye,google</div>
查找字段:<input id="searchWord_id" type="text"><input type="button" value="查找">
<div id="count_id"></div>
</body>
</html>
效果界面以下: