MapReduce的根本内容介绍(附代码)
发布时间:08/01 来源:未知 浏览:
关键词:
1、WordCount程序
1.1 WordCount源程序
import java.io.IOException; import java.util.Iterator; 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; import org.apache.hadoop.util.GenericOptionsParser; public class WordCount { public 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[ ...] "); System.exit(2); } Job job = Job.getInstance(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(WordCount.TokenizerMapper.class); job.setCombinerClass(WordCount.IntSumReducer.class); job.setReducerClass(WordCount.IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); for(int i = 0; i < otherArgs.length - 1; ++i) { FileInputFormat.addInputPath(job, new Path(otherArgs[i])); } FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1])); System.exit(job.waitForCompletion(true)?0:1); } public static class TokenizerMapper extends Mapper
1.2 运转程序,Run As->Java Applicatiion
1.3 编译打包程序,发生Jar文件
Spark 2
以上就是MapReduce的根本内容介绍(附代码)的细致内容,更多请关注 百分百源码网 其它相干文章!