D-Net

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

import static org.junit.Assert.assertTrue;

import java.io.IOException;

import java.io.StringReader;

import java.util.Collection;

import java.util.List;

import org.apache.commons.io.IOUtils;

import org.dom4j.Document;

import org.dom4j.DocumentException;

import org.dom4j.io.SAXReader;

import org.junit.Before;

import org.junit.Test;

import com.google.common.collect.Lists;

import eu.dnetlib.data.mapreduce.hbase.oai.utils.RecordFieldsExtractor;

public class RecordFieldsExtractorTest {

	private String record = "representativeRecord.xml";

	private String record2 = "dedupedRecord.xml";

	private String record3 = "originalRecord.xml";

	private RecordFieldsExtractor fieldExtractor;

	private List<String> enrichmentXPaths = Lists.newArrayList("//subject[./@inferred='true']", "//result/datainfo[./inferenceprovenance='dedup']",

			"//rel[./@inferred='true' and ./@inferenceprovenance != 'dedup']");

	@Before

	public void setUp() throws Exception {

		fieldExtractor = new RecordFieldsExtractor();

	}

	@Test

	public void testEnhanced() throws IOException, DocumentException {

		String recordString = IOUtils.toString(this.getClass().getResourceAsStream(record));

		Document doc = new SAXReader().read(new StringReader(recordString));

		Collection<String> sets = fieldExtractor.getEnrichedSets(doc, enrichmentXPaths, Lists.newArrayList("set1", "set2"));

		System.out.println(sets);

		assertTrue(sets.contains("set1_enriched") && sets.contains("set2_enriched"));

	}

	@Test

	public void testEnhancedDeduped() throws IOException, DocumentException {

		String recordString = IOUtils.toString(this.getClass().getResourceAsStream(record2));

		Document doc = new SAXReader().read(new StringReader(recordString));

		Collection<String> sets = fieldExtractor.getEnrichedSets(doc, enrichmentXPaths, Lists.newArrayList("set1", "set2"));

		System.out.println(sets);

		assertTrue(sets.contains("set1_enriched") && sets.contains("set2_enriched"));

	}

	@Test

	public void testNotEnhanced() throws IOException, DocumentException {

		String recordString = IOUtils.toString(this.getClass().getResourceAsStream(record3));

		Document doc = new SAXReader().read(new StringReader(recordString));

		Collection<String> sets = fieldExtractor.getEnrichedSets(doc, enrichmentXPaths, Lists.newArrayList("set1", "set2"));

		System.out.println(sets);

		assertTrue(sets.isEmpty());

	}

}