Hadoop基本开发环境搭建（原创，已实践）

软件包：

　　hadoop-2.7.2.tar.gz

　　hadoop-eclipse-plugin-2.7.2.jar

　　hadoop-common-2.7.1-bin.zip

　　eclipse

　 jdk1.8.45

　　hadoop-2.7.2（linux和windows各一份）

　　Linux系统（centos或其它）

　　Hadoop安装环境

准备环境：

　　安装Hadoop，安装步骤参见Hadoop安装章节。

　　安装eclipse。

搭建过程如下：

1. 将hadoop-eclipse-plugin-2.7.2.jar拷贝到eclipse/dropins目录下。

2. 解压hadoop-2.7.2.tar.gz到E盘下。

3. 下载或者编译hadoop-common-2.7.2（由于hadoop-common-2.7.1可以兼容hadoop-common-2.7.2，因此这里使用hadoop-common-2.7.1），如果想编译可参考相关文章。

4. 将hadoop-common-2.7.1下的文件全部拷贝到E:\hadoop-2.7.2\bin下面，hadoop.dll在system32下面也要放一个，否则会报下图的错误：

并配置系统环境变量HADOOP_HOME：

5. 启动eclipse,打开windows->Preferences的Hadoop Map/Reduce中设置安装目录:

6. 打开Windows->Open Perspective中的Map/Reduce，在此perspective下进行hadoop程序开发。

7. 打开Windows->Show View中的Map/Reduce Locations，如下图右键选择New Hadoop location…新建hadoop连接。

9. 新建工程并添加WordCount类：

10. 把log4j.properties和hadoop集群中的core-site.xml加入到classpath中。我的示例工程是maven组织，因此放到src/main/resources目录。

11. log4j.properties文件内容如下：

log4j.rootLogger=debug,stdout,R 
log4j.appender.stdout=org.apache.log4j.ConsoleAppender 
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout 
log4j.appender.stdout.layout.ConversionPattern=%5p - %m%n 
log4j.appender.R=org.apache.log4j.RollingFileAppender 
log4j.appender.R.File=mapreduce_test.log 
log4j.appender.R.MaxFileSize=1MB 
log4j.appender.R.MaxBackupIndex=1 
log4j.appender.R.layout=org.apache.log4j.PatternLayout 
log4j.appender.R.layout.ConversionPattern=%p %t %c - %m%n 
log4j.logger.com.codefutures=DEBUG

12. 在HDFS上创建目录input

　　hadoop dfs -mkdir input

13. 拷贝本地README.txt到HDFS的input里

　　 hadoop dfs -copyFromLocal /usr/local/hadoop/README.txt input

14. hadoop集群中hdfs-site.xml中要添加下面的配置，否则在eclipse中无法向hdfs中上传文件：

<property>
     <name>dfs.permissions</name>
     <value>false</value>
</property>

15. 若碰到Cannot connect to VM com.sun.jdi.connect.TransportTimeoutException，则关闭防火墙。

16. 书写代码如下：

package com.hadoop.example;

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;

public class WordCount {
    public static class TokenizerMapper extends
            Mapper<Object, Text, Text, IntWritable> {

        private final static IntWritable one = new IntWritable(1);
        private Text word = new Text();

        public void map(Object key, Text value, Context context)
                throws IOException, InterruptedException {

            StringTokenizer itr = new StringTokenizer(value.toString());

            System.out.print("--map: " + value.toString() + "\n");
            while (itr.hasMoreTokens()) {
                word.set(itr.nextToken());
                System.out.print("--map token: " + word.toString() + "\n");
                context.write(word, one);
                
                System.out.print("--context: " + word.toString() + "," + one.toString() + "\n");
            }
        }
    }

    public static class IntSumReducer extends
            Reducer<Text, IntWritable, Text, IntWritable> {

        private IntWritable result = new IntWritable();

        public void reduce(Text key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {

            int sum = 0;
            for (IntWritable val : values) {
                sum += val.get();
            }
            result.set(sum);
            context.write(key, result);
            
            System.out.print("--reduce: " + key.toString() + "," + result.toString() + "\n");
        }
    }

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

        System.setProperty("hadoop.home.dir", "E:\\hadoop-2.7.2");
        
        Configuration conf = new Configuration();

        String[] otherArgs = new GenericOptionsParser(conf, args)
                .getRemainingArgs();

        if (otherArgs.length != 2) {
            System.err.println("Usage: wordcount <in> <out>");
            System.exit(2);
        }

    
        Job job = new Job(conf, "word count");
        job.setJarByClass(WordCount.class);
        job.setMapperClass(TokenizerMapper.class);
        job.setCombinerClass(IntSumReducer.class);
        job.setReducerClass(IntSumReducer.class);
        job.setNumReduceTasks(2);
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);
        FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
        FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}