**主类WordCount**
package com.hadoop;
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.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
public class WordCount {
public static void main(String[] args) throws Exception
{
/**
* JobConf:map/reduce的job配置类,向hadoop框架描述map-reduce执行的工作
* 构造方法:JobConf()、JobConf(Class exampleClass)、JobConf(Configuration conf)等
*/
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordcount"); //设置一个用户定义的job名称
conf.setOutputKeyClass(Text.class); //为job的输出数据设置Key类
conf.setOutputValueClass(IntWritable.class); //为job输出设置value类
conf.setMapperClass(Map.class); //为job设置Mapper类
conf.setCombinerClass(Reduce.class); //为job设置Combiner类
conf.setReducerClass(Reduce.class); //为job设置Reduce类
conf.setInputFormat(TextInputFormat.class); //为map-reduce任务设置InputFormat实现类
conf.setOutputFormat(TextOutputFormat.class); //为map-reduce任务设置OutputFormat实现类
/**
* InputFormat描述map-reduce中对job的输入定义
* setInputPaths():为map-reduce job设置路径数组作为输入列表
* setInputPath():为map-reduce job设置路径数组作为输出列表
*/
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf); //开始运行一个job
}
}
Hadoop入门—WordCount代码分析
最新推荐文章于 2024-08-26 17:52:13 发布