Hadoop-wordCount实例代码编写（Hadoop学习第四天）

1.新建一个maven项目
2.pom文件中引入以下jar包
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.7.3</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>2.7.3</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-hdfs</artifactId>
<version>2.7.3</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.7.3</version>
</dependency>
3. 可以装一个hadoop-eclipse插件，不是必须，插件装成功后，可以在资源目录中查看 hadoop集群地址
4.创建mapper类WordCountMapper.java
package com.niwodai.hadoop.mapper;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class WordCountMapper extends Mapper<LongWritable, Text, Text, IntWritable>{
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {

// 1 将maptask传给我们的文本内容先转换成String
String line = value.toString();

// 2 根据空格将这一行切分成单词
String[] words = line.split(" ");

// 3 将单词输出为<单词，1>
for(String word:words){
// 将单词作为key，将次数1作为value,以便于后续的数据分发，可以根据单词分发，以便于相同单词会到相同的reducetask中
context.write(new Text(word), new IntWritable(1));
}
}
}
5.创建WordCountReducer.java 类
package com.niwodai.hadoop.reducer;

import java.io.IOException;

import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class WordCountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {

int count = 0;

// 1 汇总各个key的个数
for(IntWritable value:values){
count +=value.get();
}

// 2输出该key的总次数
context.write(key, new IntWritable(count));
}
}

6.创建job WordCountJob
/**
*
*/
/**
* @ClassName:
* @Description:
* @Author: wangwei9
* @Date: 2020年5月7日 下午4:07:26
* @Copyright © 2018 你我贷（www.niwodai.com）
*/

package com.niwodai.hadoop.main;

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.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

import com.niwodai.hadoop.mapper.WordCountMapper;
import com.niwodai.hadoop.reducer.WordCountReducer;

public class WordCountJob{
public static void main(String[] args) throws Exception{
// 1 获取配置信息，或者job对象实例
Configuration configuration = new Configuration();
//8 配置提交到yarn上运行,windows和Linux变量不一致(参考mapred-site.xml 该配置的名字)
//configuration.set("mapreduce.framework.name", "yarn");
//configuration.set("yarn.resourcemanager.hostname", "yarn-rm-cluster");
Job job = Job.getInstance(configuration);
// 6 指定本程序的jar包所在的本地路径
job.setJarByClass(WordCountJob.class);
// 2 指定本业务job要使用的mapper/Reducer业务类
job.setMapperClass(WordCountMapper.class);
job.setReducerClass(WordCountReducer.class);
// 3 指定mapper输出数据的kv类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
// 4 指定最终输出的数据的kv类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
// 5 指定job的输入原始文件所在目录
FileInputFormat.setInputPaths(job, new Path(args[0]));
FileOutputFormat.setOutputPath(job, new Path(args[1]));
// 7 将job中配置的相关参数，以及job所用的java类所在的jar包， 提交给yarn去运行
// job.submit();
boolean result = job.waitForCompletion(true);
System.exit(result?0:1);
}
}

7.将这个maven项目打包成jar放入hadoop集群
执行命令：hadoop jar hadoop-wordcount.jar com.niwodai.hadoop.main.WordCountJob /input /output88

8.查看输出结果 ，执行命令 hdfs dfs -cat /output88/part-r-00000
China... 1
hello 3
wangwei... 1
world... 1

9.本地测试
（1）在windows环境上配置HADOOP_HOME环境变量。

（2）在eclipse上运行程序

（3）注意：如果eclipse打印不出日志，在控制台上只显示

9.其他异常解决：
当出现以下错误时，是nameNode和dataNode 时间没有同步
解决方法：
在没台节点上执行以下两个命令：
1）输入“cp /usr/share/zoneinfo/Asia/Shanghai /etc/localtime”
2）输入“ntpdate pool.ntp.org”

2020-05-07 16:57:19,233 INFO mapreduce.Job: Task Id : attempt_1588835901055_0001_r_000000_1000, Status : FAILED
Container launch failed for container_e09_1588835901055_0001_02_000006 : org.apache.hadoop.yarn.exceptions.YarnException: Unauthorized request to start container.
This token is expired. current time is 1588870485646 found 1588842438408
Note: System times on machines may be out of sync. Check system time and time zones.
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:422)
at org.apache.hadoop.yarn.api.records.impl.pb.SerializedExceptionPBImpl.instantiateExceptionImpl(SerializedExceptionPBImpl.java:171)
at org.apache.hadoop.yarn.api.records.impl.pb.SerializedExceptionPBImpl.instantiateException(SerializedExceptionPBImpl.java:182)
at org.apache.hadoop.yarn.api.records.impl.pb.SerializedExceptionPBImpl.deSerialize(SerializedExceptionPBImpl.java:106)
at org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl$Container.launch(ContainerLauncherImpl.java:163)
at org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl$EventProcessor.run(ContainerLauncherImpl.java:394)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)

2020-05-07 16:57:22,265 INFO mapreduce.Job: Task Id : attempt_1588835901055_0001_r_000000_1001, Status : FAILED
Container launch failed for container_e09_1588835901055_0001_02_000007 : org.apache.hadoop.yarn.exceptions.YarnException: Unauthorized request to start container.
This token is expired. current time is 1588870488602 found 1588842441430
Note: System times on machines may be out of sync. Check system time and time zones.
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:422)
at org.apache.hadoop.yarn.api.records.impl.pb.SerializedExceptionPBImpl.instantiateExceptionImpl(SerializedExceptionPBImpl.java:171)
at org.apache.hadoop.yarn.api.records.impl.pb.SerializedExceptionPBImpl.instantiateException(SerializedExceptionPBImpl.java:182)
at org.apache.hadoop.yarn.api.records.impl.pb.SerializedExceptionPBImpl.deSerialize(SerializedExceptionPBImpl.java:106)
at org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl$Container.launch(ContainerLauncherImpl.java:163)
at org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl$EventProcessor.run(ContainerLauncherImpl.java:394)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)

2020-05-07 16:57:25,308 INFO mapreduce.Job: Task Id : attempt_1588835901055_0001_r_000000_1002, Status : FAILED
Container launch failed for container_e09_1588835901055_0001_02_000008 : org.apache.hadoop.yarn.exceptions.YarnException: Unauthorized request to start container.
This token is expired. current time is 1588870491638 found 1588842444455
Note: System times on machines may be out of sync. Check system time and time zones.
at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:62)
at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
at java.lang.reflect.Constructor.newInstance(Constructor.java:422)
at org.apache.hadoop.yarn.api.records.impl.pb.SerializedExceptionPBImpl.instantiateExceptionImpl(SerializedExceptionPBImpl.java:171)
at org.apache.hadoop.yarn.api.records.impl.pb.SerializedExceptionPBImpl.instantiateException(SerializedExceptionPBImpl.java:182)
at org.apache.hadoop.yarn.api.records.impl.pb.SerializedExceptionPBImpl.deSerialize(SerializedExceptionPBImpl.java:106)
at org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl$Container.launch(ContainerLauncherImpl.java:163)
at org.apache.hadoop.mapreduce.v2.app.launcher.ContainerLauncherImpl$EventProcessor.run(ContainerLauncherImpl.java:394)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)