dnet-core/dnet-core-components/src/test/java/eu/dnetlib/miscutils/functional/string/SanitizerTest.java

44 lines
1.5 KiB
Java
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

package eu.dnetlib.miscutils.functional.string;
import static org.junit.Assert.assertEquals;
import static org.junit.Assert.assertFalse;
import java.io.StringWriter;
import org.apache.commons.io.IOUtils;
import org.junit.Test;
public class SanitizerTest {
@Test
public void testIdentity() {
verifyIdentity("+-@°#()!$%&/()?' ");
verifyIdentity("asça");
verifyIdentity("qwéèrtç°§");
verifyIdentity("AÁaáCĆcćEÉeéIÍiíLĹlĺNŃnńOÓoóRŔrŕSŚsśUÚuúYÝyýZŹzź");
verifyIdentity("AÂaâCĈcĉEÊeêGĜgĝHĤhĥIÎiîJĴjĵOÔoôSŜsŝUÛuûWŴwŵYŶyŷ");
verifyIdentity("CÇcçGĢgģKĶkķLĻlļNŅnņRŖrŗSŞsşTŢtţ");
verifyIdentity("ΑΒΓΔΕΖΗΘΙΚΛΜΝΞΟΠΡΣΤΥΦΧΨΩΆΈΉΊΌΎΏΪΫαβγδεζηθικλμνξοπρσςτυφχψωάέήίόύώΐΰ");
verifyIdentity("АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ");
verifyIdentity("абвгдеёжзийклмнопрстуфхцчшщъыьэюя");
verifyIdentity("ـآ آ ـا ا بـبـب ب تـتـت ت ثـثـث ث جـجـج ج حـحـح ح خـخـخ خ ـد د ـذ ذ ـر ر ـز ز سـسـس س");
}
@Test
public void testInvalid() throws Exception {
StringWriter sw = new StringWriter();
IOUtils.copy(getClass().getResourceAsStream("invalid.txt"), sw);
String pre = sw.toString();
String post = Sanitizer.sanitize(pre);
assertFalse(pre.equals(post));
}
private void verifyIdentity(String s) {
assertEquals(s, Sanitizer.sanitize(s));
}
}