Hadoop-2.7.3_MapReduce开发环境搭建

来源：互联网发布：蒸汽巴士推荐的淘宝店编辑：程序博客网时间：2024/06/05 01:16

在YARN配置完毕之后，尝试使用Eclipse开发MR程序。

1、打开eclipse，建立工程，并把hadoop-2.7.3/share/hadoop/mapreduce以及hadoop-2.7.3/share/hadoop/common下的jar文件加到项目的类路径。

2、新建类。

package chan.takchi.mr;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;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());      while (itr.hasMoreTokens()) {        word.set(itr.nextToken());        context.write(word, one);      }    }  }  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);    }  }  public static void main(String[] args) throws Exception {    Configuration conf = new Configuration();    Job job = Job.getInstance(conf, "word count");    job.setJarByClass(WordCount.class);    job.setMapperClass(TokenizerMapper.class);    job.setCombinerClass(IntSumReducer.class);    job.setReducerClass(IntSumReducer.class);    job.setOutputKeyClass(Text.class);    job.setOutputValueClass(IntWritable.class);    FileInputFormat.addInputPath(job, new Path(args[0]));    FileOutputFormat.setOutputPath(job, new Path(args[1]));    System.exit(job.waitForCompletion(true) ? 0 : 1);  }}

3、导出为jar包，File-->>Export-->>java-->>JAR file。

4、运行jar包。

./hadoop jar /home/takchi/Desktop/_wordcount.jar chan.takchi.mr.WordCount /tmp/input /tmp/output

0 0