Hbase 批量插入(mapReduce)

 如果用Hbase提供的APi只能做少量的数据的Put，如果数据量很大10W以上用MapReudce还是很方便，单机测试10W数据插入Hbase不到1秒

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.mapreduce.TableOutputFormat;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.NullWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;

import java.io.IOException;
import java.text.SimpleDateFormat;
import java.util.Date;

/**
 */
public class HbaseBatchImport {

    static class BatchMapper extends Mapper<LongWritable, Text, Text, Text> {
        SimpleDateFormat simpleDateFormat = new SimpleDateFormat("yyyyMMddHHmmssSS");
        Text text = new Text();

        protected void map(LongWritable key, Text value, Context context) {
            try {
                final String[] spliteds = value.toString().split("::");
                Date date = new Date();
                String dateFormat = simpleDateFormat.format(date);
                final String rowKey = spliteds[0] + "_" + dateFormat;
                text.set(rowKey);
                context.write(text, value);
            } catch (IOException e) {
                e.printStackTrace();
            } catch (InterruptedException e) {
                e.printStackTrace();
            }
        }


    }

    static class BatchReducer extends TableReducer<Text, Text, NullWritable> {

        protected void reduce(Text key, Iterable<Text> values, Context context) {

            for (Text tx : values) {
                try {
                    final String[] arrays = tx.toString().split("::");
                    Put put = new Put(key.getBytes());
                    put.addColumn("info".getBytes(), "name".getBytes(), arrays[1].getBytes());
                    put.addColumn("info".getBytes(), "address".getBytes(), arrays[2].getBytes());
                    put.addColumn("info".getBytes(), Bytes.toBytes("age"), arrays[3].getBytes());
                    context.write(NullWritable.get(), put);
                } catch (IOException e) {
                    e.printStackTrace();
                } catch (InterruptedException e) {
                    e.printStackTrace();
                }
            }
        }
    }


    public static void main(String[] args) throws Exception {


        final Configuration configuration = new Configuration();
        //设置zookeeper
        configuration.set("hbase.zookeeper.quorum", "127.0.0.1");
        configuration.set("hbase.zookeeper.property.clientPort", "2181");
        //设置hbase表名称
        configuration.set(TableOutputFormat.OUTPUT_TABLE, "students");
        //将该值改大，防止hbase超时退出
        configuration.set("dfs.socket.timeout", "180000");

        final Job job = new Job(configuration, "HBaseBatchImport");
        //设置reduce的个数
        job.setNumReduceTasks(3);
        job.setMapperClass(BatchMapper.class);
        job.setReducerClass(BatchReducer.class);
        //设置map的输出，不设置reduce的输出类型
        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(Text.class);

        job.setInputFormatClass(TextInputFormat.class);
        //不再设置输出路径，而是设置输出格式类型
        job.setOutputFormatClass(TableOutputFormat.class);
        //设置数据的输入路径
        FileInputFormat.setInputPaths(job, "hdfs://MacBook-Pro.local:9000/input");

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}