一、环境说明
linux：redhat enterprise linux 5
hadoop：0.20.2
eclipse：3.4.2
jdk：1.6.21
ant：1.8.2
?
二、安装hadoop伪分布式
?
三、安装eclipse
把eclipse-SDK-3.4.2-linux-gtk.tar.gz解压到/home/hadoop/eclipse3.4.2
?
四、安装ant 1.8.2
1、把apache-ant-1.8.2-bin.tar.gz解压到/usr/apache-ant-1.8.2
2、设置/etc/profile：
export ANT_HOME=/usr/apache-ant-1.8.2
export PATH=$PATH:$ANT_HOME/bin
?
五、生成hadoop eclipse plugin
1、修改/usr/local/hadoop/hadoop-0.20.2/build.xml：
修改 <property name="version" value="0.20.2"/>
?
2、修改/usr/local/hadoop/hadoop-0.20.2/src/contrib/build-contrib.xml：
添加 <property name="eclipse.home" location="/home/hadoop/eclipse3.4.2"/>
?
3、修改 /usr/local/hadoop/hadoop-0.20.2/src/contrib/eclipse-plugin/src/java/org/apache/hadoop/eclipse/launch/HadoopApplicationLaunchShortcut.java
?
注释掉原来的//import org.eclipse.jdt.internal.debug.ui.launcher.JavaApplicationLaunchShortcut;
改为import org.eclipse.jdt.debug.ui.launchConfigurations.JavaApplicationLaunchShortcut;?
4、下载jdk-1_5_0_22-linux-i586.bin，安装到/home/hadoop/jdk1.5.0_22，不用设置环境变量。
?
5、下载apache-forrest-0.8.tar.gz，解压到/home/hadoop/apache-forrest-0.8。
?
6、编译并打包
$ cd /usr/local/haoop/hdoop-0.20.2
$ ant compile
$ ln -sf /usr/local/hadoop/hadoop-0.20.2/docs ?/usr/local/hadoop/hadoop-0.20.2/build/docs
$ ant package
????? 如果成功的话，会在/usr/local/hadoop/hadoop-0.20.2/build/contrib/eclipse-plugin
下生成hadoop-0.20.2-eclipse-plugin.jar。
?
六、设置eclipse
1、把hadoop-0.20.2-eclipse-plugin.jar复制到/home/hadoop/eclipse3.4.2/plugins下。
?
2、打开eclipse。
?
3、在eclipse中设置Window->Open Perspective->Other->Map/Reduce
?
4、新建project
File->New->Project->Map/Reduce Project
输入Project name:icas
Configure Hadoop install directory...
?
?
?
?
?
?
?
?
右键icas->properties
?
?
?
mapper类
package Sample;import java.io.IOException;import java.util.StringTokenizer;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Mapper;public class mapper 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()); while (itr.hasMoreTokens()) { word.set(itr.nextToken()); context.write(word, one); } }}
?
?
reducer类
package Sample;import java.io.IOException;import org.apache.hadoop.io.IntWritable;import org.apache.hadoop.io.Text;import org.apache.hadoop.mapreduce.Reducer;public class reducer 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); }}?
mapreduce driver类
package Sample;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.lib.input.FileInputFormat;import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;import org.apache.hadoop.util.GenericOptionsParser;public class WordCount { public static void main(String[] args) throws Exception { 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(mapper.class); job.setCombinerClass(reducer.class); job.setReducerClass(reducer.class); 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); }}?
?
Run As—>Run Configurations->Arguments中输入：/user/hadoop/input/f1 /user/hadoop/output
?
Run As—>Java Application
?
? Run As—>Run on Hadoop
?
?
结果：
?