HBase結合MapReduce批量導入（HDFS中的數據導入到HBase）

HBase結合MapReduce批量導入

package hbase;

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;

public class BatchImport {
    static class BatchImportMapper extends
            Mapper<LongWritable, Text, LongWritable, Text> {
        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()));
                final String dateFormat = dateformat1.format(date);
                String rowKey = splited[1] + ":" + dateFormat;//設置行鍵：手機號碼+日期時間
                v2.set(rowKey + "\t" + value.toString());
                context.write(key, v2);
            } catch (NumberFormatException e) {
                final Counter counter = context.getCounter("BatchImport",
                        "ErrorFormat");
                counter.increment(1L);
                System.out.println("出錯了" + splited[0] + " " + e.getMessage());
            }
        };
    }

    static class BatchImportReducer extends
            TableReducer<LongWritable, Text, NullWritable> {
        protected void reduce(LongWritable key,
                java.lang.Iterable<Text> 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]));//第一列行鍵
                put.add(Bytes.toBytes("cf"), Bytes.toBytes("date"),
                        Bytes.toBytes(splited[1]));//第二列日期
                put.add(Bytes.toBytes("cf"), Bytes.toBytes("msisdn"),
                        Bytes.toBytes(splited[2]));//第三列手機號碼
                // 省略其他字段，調用put.add(....)即可
                context.write(NullWritable.get(), put);
            }
        };
    }

    public static void main(String[] args) throws Exception {
        final Configuration configuration = new Configuration();
        // 設置zookeeper
        configuration.set("hbase.zookeeper.quorum", "hadoop0");
        // 設置hbase表名稱
        configuration.set(TableOutputFormat.OUTPUT_TABLE, "wlan_log");//先在shell下創建一個表：create 'wlan_log','cf'
        // 將該值改大，防止hbase超時退出
        configuration.set("dfs.socket.timeout", "180000");

        final Job job = new Job(configuration, "HBaseBatchImport");

        job.setMapperClass(BatchImportMapper.class);
        job.setReducerClass(BatchImportReducer.class);
        // 設置map的輸出，不設置reduce的輸出類型
        job.setMapOutputKeyClass(LongWritable.class);
        job.setMapOutputValueClass(Text.class);

        job.setInputFormatClass(TextInputFormat.class);
        // 不再設置輸出路徑，而是設置輸出格式類型
        job.setOutputFormatClass(TableOutputFormat.class);

        FileInputFormat.setInputPaths(job, "hdfs://hadoop0:9000/input");//將手機上網日志文件上傳到HDFS中的input文件中

        job.waitForCompletion(true);
    }
}

 

在eclipse中將上面代碼運行成功后，就可以去HBase shell中查看結果：