准备
- 虚拟机 centos6.5 中分布式搭建,Hadoop 2.6.4
- Win10
- IDEA 2019
- JDK 1.8
- IDEA 对虚拟机中增删改查操作正常
配置
- HADOOP_HOME 系统环境变量添加 hadoop 文件夹的位置(文件夹的 bin 目录下需包含 hadoop.dll 和 winutils.exe)
- 上面两文件在 C:\Windows\System32 目录下也放一份
编写
import org.apache.hadoop.conf.Configuration;
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.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 java.io.IOException;
public class WordCountDemo {
public static class WordcountMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
/**
* map阶段的业务逻辑就写在自定义的map()方法中
* maptask会对每一行输入数据调用一次我们自定义的map()方法
*/
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//将maptask传给我们的文本内容先转换成String
String line = value.toString();
//根据空格将这一行切分成单词
String[] words = line.split(" ");
//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reduce task
context.write(new Text(word), new IntWritable(1));
}
}
}
public static class WordcountReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
/**
* <angelababy,1><angelababy,1><angelababy,1><angelababy,1><angelababy,1>
* <hello,1><hello,1><hello,1><hello,1><hello,1><hello,1>
* <banana,1><banana,1><banana,1><banana,1><banana,1><banana,1>
* 入参key,是一组相同单词kv对的key
*/
@Override
protected void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {
int count=0;
for(IntWritable value:values){
count += value.get();
}
context.write(key, new IntWritable(count));
}
}
public static void main(String[] args) throws Exception {
if (args == null || args.length == 0) {
args = new String[2];
args[0] = "hdfs://node01:9000/data/input/LICENSE.txt";
args[1] = "hdfs://node01:9000/data/output";
}
Configuration conf = new Configuration();
Job job = Job.getInstance(conf);
//指定本程序的jar包所在的本地路径
job.setJarByClass(WordCountDemo.class);
//指定本业务job要使用的mapper/Reducer业务类
job.setMapperClass(WordcountMapper.class);
job.setReducerClass(WordcountReducer.class);
//指定mapper输出数据的kv类型
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(IntWritable.class);
//指定最终输出的数据的kv类型
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
//指定job的输入原始文件所在目录
FileInputFormat.setInputPaths(job, new Path(args[0]));
//指定job的输出结果所在目录
FileOutputFormat.setOutputPath(job, new Path(args[1]));
//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 res = job.waitForCompletion(true);
System.exit(res?0:1);
}
}
启动 VM 参数添加 -DHADOOP_USER_NAME=hadoop,hadoop 为虚拟机中对 hdfs 有读写权限的用户名
运行结果

Idea 控制台

HDFS 查看
附
resources 下的 log4j.properties
# Global logging configuration 开发时候建议使用 debug
log4j.rootLogger=DEBUG, stdout
# Console output...
log4j.appender.stdout=org.apache.log4j.ConsoleAppender
log4j.appender.stdout.layout=org.apache.log4j.PatternLayout
log4j.appender.stdout.layout.ConversionPattern=%5p [%t] - %m%n