|
1
|
package eu.dnetlib.iis.metadataextraction;
|
|
2
|
|
|
3
|
import java.io.IOException;
|
|
4
|
import java.nio.ByteBuffer;
|
|
5
|
|
|
6
|
import org.apache.avro.mapred.AvroKey;
|
|
7
|
import org.apache.hadoop.io.NullWritable;
|
|
8
|
import org.apache.zookeeper.server.ByteBufferInputStream;
|
|
9
|
|
|
10
|
import eu.dnetlib.iis.importer.schemas.DocumentContent;
|
|
11
|
|
|
12
|
/**
|
|
13
|
* Metadata extractor module.
|
|
14
|
* @author Mateusz Kobos
|
|
15
|
* @author mhorst
|
|
16
|
*
|
|
17
|
*/
|
|
18
|
public class MetadataExtractorMapper extends AbstractMetadataExtractorMapper<DocumentContent> {
|
|
19
|
|
|
20
|
/* (non-Javadoc)
|
|
21
|
* @see org.apache.hadoop.mapreduce.Mapper#map(KEYIN, VALUEIN, org.apache.hadoop.mapreduce.Mapper.Context)
|
|
22
|
*/
|
|
23
|
@Override
|
|
24
|
public void map(AvroKey<DocumentContent> key, NullWritable ignore, Context context)
|
|
25
|
throws IOException, InterruptedException {
|
|
26
|
DocumentContent content = key.datum();
|
|
27
|
if (content.getPdf()!=null) {
|
|
28
|
ByteBuffer byteBuffer = content.getPdf();
|
|
29
|
processStream(content.getId(),
|
|
30
|
new ByteBufferInputStream(byteBuffer), 0);
|
|
31
|
} else {
|
|
32
|
log.warn("no byte data found for id: " + content.getId());
|
|
33
|
}
|
|
34
|
}
|
|
35
|
|
|
36
|
}
|