RegexWord.java revision 816:f868402f8d7b 
1/*
2 * Copyright (c) 2015, Oracle and/or its affiliates. All rights reserved.
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
4 *
5 * This code is free software; you can redistribute it and/or modify it
6 * under the terms of the GNU General Public License version 2 only, as
7 * published by the Free Software Foundation.
8 *
9 * This code is distributed in the hope that it will be useful, but WITHOUT
10 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
11 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
12 * version 2 for more details (a copy is included in the LICENSE file that
13 * accompanied this code).
14 *
15 * You should have received a copy of the GNU General Public License version
16 * 2 along with this work; if not, write to the Free Software Foundation,
17 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
18 *
19 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
20 * or visit www.oracle.com if you need additional information or have any
21 * questions.
22 */
23package validation.tck;
24
25import java.io.IOException;
26import javax.xml.XMLConstants;
27import javax.xml.transform.stream.StreamSource;
28import javax.xml.validation.Schema;
29import javax.xml.validation.SchemaFactory;
30import javax.xml.validation.Validator;
31import org.testng.annotations.Test;
32import org.xml.sax.SAXException;
33
34/*
35 * @bug 8142900
36 * @summary Verifies that all characters except the set of "punctuation",
37 * "separator" and "other" characters are accepted by \w [#x0000-#x10FFFF]-[\p{P}\p{Z}\p{C}]
38 * @author Joe Wang
39 */
40public class RegexWord {
41    static final String SCHEMA_LANGUAGE = "http://java.sun.com/xml/jaxp/properties/schemaLanguage";
42    static final String SCHEMA_SOURCE = "http://java.sun.com/xml/jaxp/properties/schemaSource";
43
44    /*
45    The original reZ003v.xml contains a full list of word characters that \w should accept.
46    However, U+2308..U+230B were changed from Sm to either Ps or Pe in Unicode 7.0.
47    They are therefore excluded from the test.
48
49    The test throws an Exception (and fails) if it fails to recognize any of characters.
50    */
51    @Test
52    public void test() throws SAXException, IOException {
53        SchemaFactory schemaFactory = SchemaFactory.newInstance(XMLConstants.W3C_XML_SCHEMA_NS_URI);
54        Schema schema = schemaFactory.newSchema(new StreamSource(RegexWord.class.getResourceAsStream("reZ003.xsd")));
55        Validator validator = schema.newValidator();
56
57        validator.validate(new StreamSource(RegexWord.class.getResourceAsStream("reZ003vExc23082309.xml")));
58    }
59}
60