MR代码实例-wordcount
来源:互联网 发布:电脑的网络图标不见了 编辑:程序博客网 时间:2024/05/16 10:10
package com.tiger.test;
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;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.log4j.Logger;
public class WordCountTest {
private static final Logger log = Logger.getLogger(WordCountTest.class);
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 {
log.info("Map key : " + key);
log.info("Map value : " + value);
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
String wordStr = itr.nextToken();
word.set(wordStr);
log.info("Map word : " + wordStr);
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 {
log.info("Reduce key : " + key);
log.info("Reduce value : " + values);
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
log.info("Reduce sum : " + 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.err.println("Usage: WordCountTest <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(WordCountTest.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(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
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;
import org.apache.hadoop.util.GenericOptionsParser;
import org.apache.log4j.Logger;
public class WordCountTest {
private static final Logger log = Logger.getLogger(WordCountTest.class);
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 {
log.info("Map key : " + key);
log.info("Map value : " + value);
StringTokenizer itr = new StringTokenizer(value.toString());
while (itr.hasMoreTokens()) {
String wordStr = itr.nextToken();
word.set(wordStr);
log.info("Map word : " + wordStr);
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 {
log.info("Reduce key : " + key);
log.info("Reduce value : " + values);
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
log.info("Reduce sum : " + 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.err.println("Usage: WordCountTest <in> <out>");
System.exit(2);
}
Job job = new Job(conf, "word count");
job.setJarByClass(WordCountTest.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(otherArgs[0]));
FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
System.exit(job.waitForCompletion(true) ? 0 : 1);
}
}
0 0
- MR代码实例-wordcount
- wordcount的mr java代码
- ODPS MR开发 WordCount
- MR案例之WordCount
- MR之wordcount
- 大数据之MapReduce详解(MR的运行机制及配合WordCount实例来说明运行机制)
- MR WordCount类基本解析
- WordCount 实例
- Wordcount实例
- WordCount代码
- MR英语单词频次统计案例-----wordcount
- MR--WordCount的MapReduce程序注释
- MR ADT 实例
- hadoop wordcount运行实例
- WordCount 实例分析
- hadoop-运行WordCount实例
- storm wordcount实例
- Hadoop 运行wordcount 实例
- Android 5.x之 Notification
- Java虚拟机内存模型
- 我的第一个C++程序
- 多线程 : 进程同步
- Java泛型通配符super使用Demo
- MR代码实例-wordcount
- 【HDU-1863】畅通工程(最小生成树prim)
- 深入理解JVM—JVM内存模型
- 进程和线程的区别和联系
- 为什么ES不适合做数据存储
- Info.plist与Prefix.pch修改文件位置遇到的问题及解决方法
- MTD,文件系统,存储器分区的个人理解
- 8.定制new和delete
- Java学习