自定义mapreduce连接hbase

遇到的问题总结：

1、map中进行数据的清洗

2、reduce中进行逻辑上的处理

3、本地连接时，必需配置本地的host和集群中的相同，不然会连接失败（本地模式）

4、在集群上运行时，一定要把依赖包打入，采用hadoop jar xxx.jar args[0] args[1] ...（集群模式）

代码详情

MAIN

	import org.apache.hadoop.conf.Configuration;
	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.lib.input.FileInputFormat;
	import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
	
	public class StartLmUserSys {

	public static void main(String[] args) throws Exception {
		String input = args[0];
		String output = args[1];
		System.out.println("input=" + input);
		Configuration conf = new Configuration();
		FileSystem fs = new Path(output).getFileSystem(conf);
		fs.delete(new Path(output), true);
		Job job = Job.getInstance(conf);
		job.setJarByClass(StartLmUserSys.class);
		job.setMapperClass(LmUserMap.class);
		job.setMapOutputKeyClass(Text.class);
		job.setMapOutputValueClass(LongWritable.class);
		FileInputFormat.addInputPath(job, new Path(input));

		job.setReducerClass(LmUserReduce.class);
		job.setOutputKeyClass(Text.class);
		job.setOutputValueClass(LongWritable.class);
		FileOutputFormat.setOutputPath(job, new Path(output));
		job.waitForCompletion(false);
		System.out.println("input=" + input);
	}
}

MAP

import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class LmUserMap extends Mapper<LongWritable, Text, Text, LongWritable> {
	@Override
	protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
		String line = value.toString();			
			System.out.println(line);		
	}
}

REDUCE

import java.io.IOException;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Reducer;

public class Reduce extends Reducer<Text, LongWritable,Text,LongWritable>{
	@Override
	protected void reduce(Text key, Iterable<LongWritable> values,
				Context context) throws IOException, InterruptedException {
		
		long counter = 0;
		for(LongWritable l : values){
			counter += l.get();
		}
		context.write(key, new LongWritable(counter));
	}
}