MapReduce程序打jar要注意的事项

package cmd;

import java.io.IOException;
import java.net.URI;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
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.Mapper.Context;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
import org.apache.hadoop.mapreduce.lib.partition.HashPartitioner;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCountApp extends Configured implements Tool{

public static String FILE_PATH="";
public static String OUT_PATH="";

public int run(String[] args) throws Exception {
FILE_PATH = args[0];
OUT_PATH = args[1];

Job job = new Job(new Configuration(), WordCountApp.class.getSimpleName());
job.setJarByClass(WordCountApp.class);

final Configuration conf = new Configuration();
final FileSystem fileSystem = FileSystem.get(new URI(OUT_PATH), conf);
if(fileSystem.exists(new Path(OUT_PATH))){
fileSystem.delete(new Path(OUT_PATH), true);
}
//1.1从哪里读取数据
FileInputFormat.setInputPaths(job, FILE_PATH);
//把每一行数据解析成一个键值对
job.setInputFormatClass(TextInputFormat.class);

//1.2自定义函数
job.setMapperClass(MyMapReduce.class);
job.setMapOutputKeyClass(Text.class);
job.setPartitionerClass(HashPartitioner.class);

//1.3分区
job.setPartitionerClass(HashPartitioner.class);
job.setNumReduceTasks(1);

//1.4排序，分组
//1.5归约

//2.1框架自己完成
//2.2自定义reduce函数
job.setReducerClass(MyReduce.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(LongWritable.class);

//2.3写入hdfs中去
FileOutputFormat.setOutputPath(job, new Path(OUT_PATH));

job.setOutputFormatClass(TextOutputFormat.class);

job.waitForCompletion(true);
return 0;
}

public static void main(String[] args) throws Exception {
ToolRunner.run(new WordCountApp(), args);
}

static class MyMapReduce extends Mapper<LongWritable, Text, Text, LongWritable>{
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
String line = value.toString();
String[] splits = line.split("\t");
for(String word:splits){
context.write(new Text(word),new LongWritable(1));
}
}
}

static class MyReduce extends Reducer<Text, LongWritable, Text, LongWritable>{
protected void reduce(Text key, Iterable<LongWritable> values, Context context
) throws IOException, InterruptedException {
long sum = 0L;
for(LongWritable value: values) {
sum+=value.get();
}
context.write(key, new LongWritable(sum));
}
}

}

如上图所示

1，继承Configured类

2，实现Tool接口

3，重写run方法并把输入，输出路径作为参数（数组）给传进来

4，job.setJarByClass(WordCountApp.class);这句一定要写，否则会报错

cmd

hadoopfs jar jar包名。后戳  输入路径   输出路径

见图如下：

[root@simon Downloads]# hadoop jar jar.jar hdfs://simon:9000/hello hdfs://simon:9000/out

然后回车就OK了