hive数据文件简单合并

MR代码：

package merge;
import java.io.IOException;
import java.util.Iterator;
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.mapred.FileInputFormat;
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;

public class merge
{
    public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, Text>
    {
        private Text word=new Text("");
        public void map(LongWritable key, Text value, OutputCollector<Text, Text> output, Reporter reporter)
                throws IOException
        {
            output.collect(value,word);
        }
    }

    public static void main(String[] args) throws Exception
    {
        JobConf conf = new JobConf(merge.class);
        conf.setJobName("wordcount");
        conf.setOutputKeyClass(Text.class);
        conf.setOutputValueClass(Text.class);
        conf.setMapperClass(Map.class);
        conf.setInputFormat(TextInputFormat.class);
        conf.setOutputFormat(TextOutputFormat.class);
        FileInputFormat.setInputPaths(conf, new Path(args[0]));
        FileOutputFormat.setOutputPath(conf, new Path(args[1]));
        JobClient.runJob(conf);
    }
}

Eclipse自动生成.class文件，打包命令：

jar打包：在项目的bin目录下
Dev-Fac:bin ce-pc$ jar -cvf hive-merge.jar -C  ../ .

合并命令：

hadoop jar /tmp/hive-merge.jar merge.merge /user/hive/warehouse/table1 /user/hive/warehouse/table1/out

#merge.merge 表示merge包下的merge类