hbase使用MapReduce操作4（实现将 HDFS 中的数据写入到 HBase 表中）

package com.yjsj.hbase_mr2; import com.yjsj.hbase_mr2.ReadFruitFromHDFSMapper;
import com.yjsj.hbase_mr2.WriteFruitMRFromTxtReducer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner; import java.io.IOException; class Txt2FruitRunner extends Configured implements Tool {
public int run(String[] args) throws Exception {
//得到 Configuration
Configuration conf = this.getConf();
//创建 Job 任务
Job job = Job.getInstance(conf, this.getClass().getSimpleName());
job.setJarByClass(Txt2FruitRunner.class);
Path inPath = new Path("hdfs://master:9000/input_fruit/fruit.tsv"); FileInputFormat.addInputPath(job, inPath);
//设置 Mapper
job.setMapperClass(ReadFruitFromHDFSMapper.class);
job.setMapOutputKeyClass(ImmutableBytesWritable.class);
job.setMapOutputValueClass(Put.class);
//设置 Reducer
TableMapReduceUtil.initTableReducerJob("fruit_hdfs", WriteFruitMRFromTxtReducer.class, job);
//设置 Reduce 数量，最少 1 个
job.setNumReduceTasks(1);
boolean isSuccess = job.waitForCompletion(true);
if (!isSuccess) {
throw new IOException("Job running with error");
}
return isSuccess ? 0 : 1;
} public static void main(String[] args) throws Exception {
Configuration conf = HBaseConfiguration.create();
conf = HBaseConfiguration.create();
conf.set("hbase.zookeeper.quorum", "master,node1,node2");
conf.set("hbase.zookeeper.property.clientPort", "2181");
conf.set("hbase.master", "master:60000");
int status = ToolRunner.run(conf, new Txt2FruitRunner(), args);
System.exit(status);
}
}

package com.yjsj.hbase_mr2; import java.io.IOException; import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper; public class ReadFruitFromHDFSMapper extends Mapper<LongWritable, Text, ImmutableBytesWritable, Put> {
@Override
protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
//从 HDFS 中读取的数据
String lineValue = value.toString();
//读取出来的每行数据使用\t 进行分割，存于 String 数组
String[] values = lineValue.split("\t");
//根据数据中值的含义取值
String rowKey = values[0];
String name = values[1];
String color = values[2];
//初始化 rowKey
ImmutableBytesWritable rowKeyWritable = new ImmutableBytesWritable(Bytes.toBytes(rowKey));
//初始化 put 对象
Put put = new Put(Bytes.toBytes(rowKey));
//参数分别:列族、列、值
put.add(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes(name));
put.add(Bytes.toBytes("info"), Bytes.toBytes("color"), Bytes.toBytes(color));
context.write(rowKeyWritable, put);
}
}

package com.yjsj.hbase_mr2;import java.io.IOException;import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.io.NullWritable;public class WriteFruitMRFromTxtReducer extends TableReducer<ImmutableBytesWritable, Put, NullWritable> {
@Override
protected void reduce(ImmutableBytesWritable key, Iterable<Put> values, Context context) throws IOException, InterruptedException {
//读出来的每一行数据写入到 fruit_hdfs 表中
for (Put put : values) {
context.write(NullWritable.get(), put);
}
}
}