1
|
package eu.dnetlib.data.mapreduce.hbase.statsExport;
|
2
|
|
3
|
import java.io.IOException;
|
4
|
import java.util.Iterator;
|
5
|
|
6
|
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
|
7
|
import org.apache.hadoop.io.Text;
|
8
|
import org.apache.hadoop.mapreduce.Reducer;
|
9
|
import org.apache.hadoop.mapreduce.TaskInputOutputContext;
|
10
|
import org.apache.hadoop.mapreduce.lib.output.MultipleOutputs;
|
11
|
import org.apache.log4j.Logger;
|
12
|
|
13
|
public class StatsReducer extends Reducer<Text, ImmutableBytesWritable, Text, Text> {
|
14
|
|
15
|
private Logger log = Logger.getLogger(StatsReducer.class);
|
16
|
private MultipleOutputs MultipleOutputWriter;
|
17
|
private long counter = 0;
|
18
|
|
19
|
/**
|
20
|
* Reducer that splits input according to their Type ( datasource, results
|
21
|
* etc..) and writes each kind to a seperate output
|
22
|
*/
|
23
|
@Override
|
24
|
protected void setup(Context context) throws IOException, InterruptedException {
|
25
|
|
26
|
MultipleOutputWriter = new MultipleOutputs((TaskInputOutputContext) context);
|
27
|
};
|
28
|
|
29
|
@Override
|
30
|
protected void reduce(final Text key, final Iterable<ImmutableBytesWritable> values, final Context context) throws IOException, InterruptedException {
|
31
|
|
32
|
Iterator<ImmutableBytesWritable> it = values.iterator();
|
33
|
while (it.hasNext()) {
|
34
|
String[] split = key.toString().split(",");
|
35
|
String type = split[0];
|
36
|
String id = split[1];
|
37
|
String value = new String(it.next().copyBytes());
|
38
|
counter++;
|
39
|
|
40
|
value = value.trim();
|
41
|
MultipleOutputWriter.write(type, " " + new Text(id), new Text(context.getConfiguration().get("stats.delim") + value), type.toString());
|
42
|
}
|
43
|
|
44
|
}
|
45
|
|
46
|
@Override
|
47
|
protected void cleanup(Context context) throws IOException, InterruptedException {
|
48
|
|
49
|
log.info("******************************* TOTAL RECORDS " + counter);
|
50
|
MultipleOutputWriter.close();
|
51
|
}
|
52
|
}
|