D-Net

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

import java.io.IOException;

import eu.dnetlib.miscutils.functional.xml.ApplyXslt;

import org.apache.commons.codec.binary.Base64;

import org.apache.commons.lang.StringUtils;

import org.apache.commons.logging.Log;

import org.apache.commons.logging.LogFactory;

import org.apache.hadoop.io.Text;

import org.apache.hadoop.mapreduce.Mapper;

public class ExportSimplifiedRecordsMapper extends Mapper<Text, Text, Text, Text> {

	private static final Log log = LogFactory.getLog(ExportSimplifiedRecordsMapper.class); // NOPMD by marko on 11/24/08 5:02 PM

	private ApplyXslt recordSummarizer;

	private Text valueOut;

	private Text keyOut;

	@Override

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

		final String xslt = new String(Base64.decodeBase64(context.getConfiguration().get("xslt")));

		log.info("got xslt: \n" + xslt);

		recordSummarizer = new ApplyXslt(xslt);

		valueOut = new Text();

		keyOut = new Text("");

	}

	@Override

	protected void map(final Text key, final Text value, final Context context) throws IOException, InterruptedException {

		final String summary = recordSummarizer.evaluate(value.toString());

		if (StringUtils.isNotBlank(summary)) {

			valueOut.set(summary.replaceAll("\n","").replaceAll("\t",""));

			context.write(keyOut, valueOut);

		}

	}

}