hadoop2.0 MapReduce编程（java客户端）

来源：互联网发布：linux服务器开发 epub 编辑：程序博客网时间：2024/06/05 11:08

1 通用开发步骤

创建java工程

引入相应的hadoop相关jar

               share/hadoop/mapreduce下面的全部jar
               share/hadoop/common/hadoop-common-2.7.1.jar
               share/hadoop/common/lib全部jar

编写mapreduce程序

导出为jar包

将jar包拷贝到hadoop集群环境上

2 wordcount案例

用pig客户端将文件上传到HDFS

grunt> copyFromLocal /usr/local/input.txt /inputgrunt> cat /inputhelloworldhadoophbasehivehadoop

import java.io.IOException;import java.util.StringTokenizer;import org.apache.hadoop.conf.Configuration;import org.apache.hadoop.examples.WordCount.IntSumReducer;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 WordCountMapper extends Mapper<Object, Text, Text, IntWritable>{private final static IntWritable one = new IntWritable(1);private Text word = new Text();@Overrideprotected void map(Object key, Text value, Mapper<Object, Text, Text, IntWritable>.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 WordCountReduceextends Reducer<Text, IntWritable, Text, IntWritable>{private IntWritable result = new IntWritable();@Overrideprotected void reduce(Text key, Iterable<IntWritable> values,Reducer<Text, IntWritable, Text, IntWritable>.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();String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();if(otherArgs.length != 2){System.out.println("Usage:wordcount <in> <out>");System.exit(2);}Job job = new Job(conf,"wodr count");job.setJarByClass(WordCount.class);job.setMapperClass(WordCountMapper.class);job.setCombinerClass(IntSumReducer.class);job.setReducerClass(IntSumReducer.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);}}

运行并查看结果

root@localhost hadoop-2.7.1]# bin/hadoop jar /usr/local/wordcount.jar WordCount /input /outputgrunt> cat /outputhadoop2hbase1hello1hive1world1

0 0