D-Net

package eu.dnetlib.data.information.oai.publisher;

import java.text.Normalizer;

import org.apache.commons.lang3.StringEscapeUtils;

import org.junit.Ignore;

import org.junit.Test;

import static org.junit.Assert.assertEquals;

import static org.junit.Assert.assertFalse;

public class PublisherMiscTest {

	@Ignore

	@Test

	//FIXME: do we really need to change © into © ?

	public void test() {

		String id = "NonavCreation.filmportal.de/DIF_NonAVCreation_EUROPA_TM & © Aardman Animations, LTD";

		String newId = StringEscapeUtils.escapeXml11(id);

		assertEquals("NonavCreation.filmportal.de/DIF_NonAVCreation_EUROPA_TM & © Aardman Animations, LTD", newId);

		assertFalse(id.equals(newId));

	}

	@Test

	public void test2() {

		// Hochschulschriftenserver - Universität Frankfurt am Main

		String s = "Publikationenserver der Georg-August-Universität Göttingen";

		System.out.println("String to normalize: " + s);

		s = StringEscapeUtils.unescapeXml(s);

		System.out.println("unescaped: " + s);

		s = Normalizer.normalize(s, Normalizer.Form.NFD);

		System.out.println("normalized: " + s);

		// remove tilde, dots... over letters

		s = s.replaceAll("[\\p{InCombiningDiacriticalMarks}&&[^-_]]", "");

		// change punctuation into an underscore

		s = s.replaceAll("[\\p{Punct}&&[^-_]]", "_");

		// remove all non-word charcheters

		s = s.replaceAll("[\\W&&[^-_]]", "");

		System.out.println("Converted setSpec to: " + s);

	}

}