D-Net

package eu.dnetlib.data.mapreduce.hbase.dataexport;

import com.googlecode.protobuf.format.JsonFormat;

import eu.dnetlib.data.mapreduce.util.DedupUtils;

import eu.dnetlib.data.proto.OafProtos;

import eu.dnetlib.data.proto.TypeProtos;

import org.apache.hadoop.hbase.client.Result;

import org.apache.hadoop.hbase.io.ImmutableBytesWritable;

import org.apache.hadoop.hbase.mapreduce.TableMapper;

import org.apache.hadoop.io.Text;

import java.io.IOException;

import java.util.Map;

public class ExportDuplicatesMapper extends TableMapper<Text, Text> {

    private Text keyOut;

    private Text valueOut;

    @Override

    protected void setup(Context context) throws IOException, InterruptedException {

        keyOut = new Text("");

        valueOut = new Text();

    }

    @Override

    protected void map(ImmutableBytesWritable key, Result value, Context context) throws IOException, InterruptedException {

        final Map<byte[], byte[]> mergedInMap = value.getFamilyMap(DedupUtils.getDedupCF_mergedInBytes(TypeProtos.Type.result));

        if (mergedInMap != null && !mergedInMap.isEmpty()) {

            final byte[] body = value.getValue("result".getBytes(), DedupUtils.BODY_B);

            if (body != null) {

                OafProtos.Oaf oaf = OafProtos.Oaf.parseFrom(body);

                valueOut.set(JsonFormat.printToString(oaf));

                context.write(keyOut, valueOut);

            }

        }

    }

}