hive load数据，使用mapreduc进行分析注意事项

直接上代码 ：

package ccindex.mapreduce;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
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.input.SequenceFileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;

public class TestMR {
    // map key => input
    public static class MMap extends
            Mapper<BytesWritable , Text, Text, IntWritable> {
        private Text key = new Text();
        private IntWritable value = new IntWritable(1);

        public void map(BytesWritable ikey, Text row, Context context)
                throws IOException, InterruptedException {
            key.set(row.toString().split("\001")[0]);
            context.write(key, value);
        }

    }

    public static class RReduce extends
            Reducer<Text, IntWritable, Text, IntWritable> {

        private IntWritable value = new IntWritable(0);

        public void reduce(Text ikey, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {
            context.write(ikey, value);
        }
    }

    public static void main(String[] args) throws Exception {
        Configuration config = new Configuration(true);
        config.set("mapred.job.queue.name", "hadmin");

        config.set("mapred.output.compression.type", "BLOCK");

        Job job = new Job(config);

        job.setInputFormatClass(SequenceFileInputFormat.class);

        String input = args[0], output = args[1]+"/1/";
        //job.setNumReduceTasks

        // map -> reducr 序列化 对象
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(IntWritable.class);

        // reduce -> HDFS 序列化 对象
        job.setOutputKeyClass(Text.class);
        job.setOutputValueClass(IntWritable.class);

        job.setMapperClass(MMap.class);
        job.setReducerClass(RReduce.class);

        job.setNumReduceTasks(1);

        job.setJarByClass(TestMR.class);

        FileInputFormat.setInputPaths(job, new Path(input));

        FileOutputFormat.setOutputPath(job, new Path(output));

        job.waitForCompletion(true);
    }
}