eclipse配置hadoop mapreduce开发环境
环境：
Eclipse版本：MyEclipse6.5.1
Hadoop版本：hadoop-1.2.1
1.安装MyEclipse后，创建一个java项目
File->New->Java Project
输入项目名称，确定
2.导入hadoop所有包
解压hadoop-1.2.1.tar（E:\software\share\hadoop-1.2.1）
把E:\software\share\hadoop-1.2.1下
和E:\software\share\hadoop-1.2.1\lib下的jar包都导入到项目里
方法如下：
点中项目根右键->Properties->JavaPath->Libraries->Add External JARs
3.确认jre为6.0以上版本
我的MyEclipse6.5.1版本开始默认使用jre5.0版本，因hadoop-1.2.1需要jre 6.0以上版本，所执行程序时报错：
Bad version number in .class file (unableto load class ***)
更改jre版本方法
Windows->Preference->Java->InstalledJREs àadd
4.修改FileUtil.java文件
这时在创建一个测试WordCount的mapreduce程序时，同样遇到了下面的问题
13/12/13 22:58:49 WARNutil.NativeCodeLoader: Unable to load native-hadoop library for yourplatform... using builtin-java classes where applicable
13/12/13 22:58:49 ERRORsecurity.UserGroupInformation: PriviledgedActionException as:licz cause:java.io.IOException: Failed to set permissions of path:\tmp\hadoop-licz\mapred\staging\licz1853164772\.staging to 0700
Exception in thread"main" java.io.IOException: Failed to set permissions of path:\tmp\hadoop-licz\mapred\staging\licz1853164772\.staging to
......
解决办法：
修改E:\software\share\hadoop-1.2.1\src\core\org\apache\hadoop\fs\FileUtil.java文件
注释掉下面的内容
685 private static voidcheckReturnValue(boolean rv, File p,
686 FsPermission permission
687 ) throws IOException {
688 /*if (!rv) {
689 throw new IOException("Failed toset permissions of path: " + p +
690 " to " +
691 String.format("%04o", permission.toShort()));
692 }*/
693 }
然后在Mapreduce1/scr新建一个org.apache.hadoop.fs包，把FileUtil.java文件拷到这个包的下面（在eclipse里直接粘贴就可以）
再次编译WordCount.java程序没有报错
import java.io.IOException;
import java.util.Iterator;
import java.util.StringTokenizer;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
importorg.apache.hadoop.mapred.FileOutputFormat;
importorg.apache.hadoop.mapred.JobClient;
importorg.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
importorg.apache.hadoop.mapred.Mapper;
importorg.apache.hadoop.mapred.OutputCollector;
importorg.apache.hadoop.mapred.Reducer;
importorg.apache.hadoop.mapred.Reporter;
importorg.apache.hadoop.mapred.TextInputFormat;
importorg.apache.hadoop.mapred.TextOutputFormat;
public class WordCount {
public static class WordCountMapper extends MapReduceBase implementsMapper {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(Object key, Text value,OutputCollector output, Reporter reporter) throws IOException {
StringTokenizer itr = newStringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
word.set(itr.nextToken());
output.collect(word, one);
}
}
}
public static class WordCountReducer extends MapReduceBase implementsReducer {
private IntWritable result = new IntWritable();
public void reduce(Text key, Iteratorvalues, OutputCollector output, Reporter reporter) throws IOException {
int sum = 0;
while (values.hasNext()) {
sum +=values.next().get();
}
result.set(sum);
output.collect(key, result);
}
}
public static void main(String[] args) throws Exception {
String input = "hdfs://192.168.2.100:9000/user/licz/hdfs/o_t_account";
String output = "hdfs://192.168.2.100:9000/user/licz/hdfs/o_t_account/result";
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("WordCount");
conf.addResource("classpath:/hadoop/core-site.xml");
conf.addResource("classpath:/hadoop/hdfs-site.xml");
conf.addResource("classpath:/hadoop/mapred-site.xml");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(WordCountMapper.class);
conf.setCombinerClass(WordCountReducer.class);
conf.setReducerClass(WordCountReducer.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(input));
FileOutputFormat.setOutputPath(conf,new Path(output));
JobClient.runJob(conf);
System.exit(0);
}
}
注意：
在windows上使用eclipse用户要与hadoop服务器上安装hadoop的用户名一致，这样才能正常运行，否则会出现没有权限创建目录的报错。
如hadoop安装在了linux服务器的licz用户下，我必需在windows的上的licz用户下使用eclipse开发程序。
这样，我们就可以在eclipse上开发mapreduce程序了。
感谢 吕双平 同学的帮助
参考刘丹：http://blog.fens.me/hadoop-maven-eclipse/