下面是一个简单的 MapReduce 程序的示例代码,用于统计 HBase 中的成绩表中的单科排名和总分排名,并将结果上传到 HDFS 中:
``` import java.io.IOException;
import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.hbase.HBaseConfiguration; import org.apache.hadoop.hbase.client.Result; import org.apache.hadoop.hbase.client.Scan; import org.apache.hadoop.hbase.io.ImmutableBytesWritable; import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil; import org.apache.hadoop.hbase.mapreduce.TableMapper; import org.apache.hadoop.hbase.util.Bytes; import org.apache.hadoop.io.IntWritable; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.Job; import org.apache.hadoop.mapreduce.Reducer;
public class RankCalculator {
public static class RankMapper extends TableMapper<Text, IntWritable> {
private Text subject = new Text();
private final static IntWritable score = new IntWritable(1);
public void map(ImmutableBytesWritable row, Result value, Context context)
throws IOException, InterruptedException {
String subjectStr = Bytes.toString(value.getValue(Bytes.toBytes("grades"),
Bytes.toBytes("subject")));
subject.set(subjectStr);
int scoreInt = Bytes.toInt(value.getValue(Bytes.toBytes("grades"),
Bytes.toBytes("score")));
score.set(scoreInt);
context.write(subject, score);
}
}
public static class RankReducer extends Reducer<Text, IntWritable, Text, IntWritable> {
private IntWritable result =new IntWritable();
public void reduce(Text key, Iterable<IntWritable> values,
Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val : values) {
sum += val.get();
}
result.set(sum);
context.write(key, result);
}
}
public static void main(String[] args) throws Exception { Configuration conf = HBaseConfiguration.create(); Job job = Job.getInstance(conf, "rank calculator"); job.setJarByClass(RankCalculator.class); Scan scan = new Scan(); scan.setCaching(500); scan.setCacheBlocks(false); TableMapReduceUtil.initTableMapperJob("grades", scan, RankMapper.class, Text.class, IntWritable.