用java的api将数据从HDFS上存到HBASE中

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

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.Counter;
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;

/**
 * 从HDFS批量导入数据到HBASE 
 * 
 * 示例文件是移动设备的上网信息
 */
public class BatchImport {
	static class BatchImportMapper extends Mapper{
		SimpleDateFormat dateformat1=new SimpleDateFormat("yyyyMMddHHmmss");
		Text v2 = new Text();
		
		protected void map(LongWritable key, Text value, Context context) throws java.io.IOException ,InterruptedException {
			final String[] splited = value.toString().split("\t");
			try {
				final Date date = new Date(Long.parseLong(splited[0].trim()));//上网时间
				final String dateFormat = dateformat1.format(date);
				String rowKey = splited[1]+":"+dateFormat;//将手机号和上网时间作为一个行键
				v2.set(rowKey+"\t"+value.toString());//将行键+行文本内容作为value2
				context.write(key, v2);//输出的是<偏移量,行键+行文本>
			} catch (NumberFormatException e) {
				final Counter counter = context.getCounter("BatchImport", "ErrorFormat");
				counter.increment(1L);
				System.out.println("出错了"+splited[0]+" "+e.getMessage());
			}
		};
	}
	
	/**
	 *  这边的reduce继承TableReducer
	 */
	static class BatchImportReducer extends TableReducer{
		protected void reduce(LongWritable key, java.lang.Iterable values, 	Context context) throws java.io.IOException ,InterruptedException {
			for (Text text : values) {
				final String[] splited = text.toString().split("\t");
				
				final Put put = new Put(Bytes.toBytes(splited[0]));//参数是行键
				//参数是列族,列名,值
				put.add(Bytes.toBytes("cf"), Bytes.toBytes("date"), Bytes.toBytes(splited[1]));
				put.add(Bytes.toBytes("cf"), Bytes.toBytes("msisdn"), Bytes.toBytes(splited[2]));
				//省略其他字段,调用put.add(....)即可
				context.write(NullWritable.get(), put);
			}
		};
	}
	
	public static void main(String[] args) throws Exception {
		final Configuration configuration = new Configuration();
		//设置zookeeper
		configuration.set("hbase.zookeeper.quorum", "xxc");
		//设置hbase表名称
		configuration.set(TableOutputFormat.OUTPUT_TABLE, "wlan_log");
		//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");
		
		job.setMapperClass(BatchImportMapper.class);
		job.setReducerClass(BatchImportReducer.class);
		//设置map的输出,不设置reduce的输出类型
		job.setMapOutputKeyClass(LongWritable.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);
		
		FileInputFormat.setInputPaths(job, "hdfs://xxc:9000/input");
		
		job.waitForCompletion(true);
	}
}

你可能感兴趣的:(hadoop)