Debian Codegraph @

tests/org.eclipse.emf.test.xml/src/org/eclipse/emf/test/xml/encoding/UnicodeEncodingTest.java

raw
1 /**
2 * Copyright (c) 2006 Jesper Steen M�ller
3 *
4 * All rights reserved. This program and the accompanying materials
5 * are made available under the terms of the Eclipse Public License v2.0
6 * which accompanies this distribution, and is available at
7 * http://www.eclipse.org/legal/epl-v20.html
8 *
9 * Contributors:
10 * IBM - Initial API and implementation
11 */
12
13 package org.eclipse.emf.test.xml.encoding;
14
15
16 import static org.junit.Assert.assertEquals;
17 import static org.junit.Assert.assertTrue;
18
19 import java.io.File;
20 import java.io.IOException;
21 import java.util.Arrays;
22 import java.util.Collection;
23 import java.util.HashMap;
24
25 import org.eclipse.emf.common.util.URI;
26 import org.eclipse.emf.ecore.EAnnotation;
27 import org.eclipse.emf.ecore.EcoreFactory;
28 import org.eclipse.emf.ecore.xmi.XMIResource;
29 import org.eclipse.emf.ecore.xmi.impl.XMIResourceImpl;
30 import org.junit.After;
31 import org.junit.Before;
32 import org.junit.Test;
33 import org.junit.runner.RunWith;
34 import org.junit.runners.Parameterized;
35
36
37 /**
38 * @author jsm
39 */
40 @RunWith(Parameterized.class)
41 public class UnicodeEncodingTest
42 {
43 // From the Unicode spec
44 public static final int MIN_SUPPLEMENTARY_CODE_POINT = 0x010000;
45
46 public static final int MIN_CODE_POINT = 0x000000;
47
48 public static final int MAX_CODE_POINT = 0x10ffff;
49
50 public static final char MIN_HIGH_SURROGATE = '\uD800';
51
52 public static final char MAX_HIGH_SURROGATE = '\uDBFF';
53
54 public static final char MIN_LOW_SURROGATE = '\uDC00';
55
56 public static final char MAX_LOW_SURROGATE = '\uDFFF';
57
58 public static char[] toSurrogatePair(int codePoint)
59 {
60 if (codePoint < 0 || codePoint > MAX_CODE_POINT)
61 {
62 throw new IllegalArgumentException();
63 }
64 if (codePoint < MIN_SUPPLEMENTARY_CODE_POINT)
65 {
66 return new char []{ (char)codePoint };
67 }
68 char[] result = new char [2];
69
70 int offset = codePoint - MIN_SUPPLEMENTARY_CODE_POINT;
71 result[0] = (char)((offset >>> 10) + MIN_HIGH_SURROGATE);
72 result[1] = (char)((offset & 0x3ff) + MIN_LOW_SURROGATE);
73
74 return result;
75 }
76
77 protected File tempFile;
78 protected final String encodingName;
79 protected final String xmlVersion;
80
81 public UnicodeEncodingTest(String encoding, String xmlVersion)
82 {
83 encodingName = encoding;
84 this.xmlVersion = xmlVersion;
85 }
86
87 @Parameterized.Parameters(name="Encoding {0} for XML {1}")
88 public static Collection<Object[]> parameters()
89 {
90 return
91 Arrays.asList
92 (new Object[][]
93 {
94 { "UTF-8", "1.0" },
95 { "UTF-16BE", "1.0" },
96 { "UTF-16LE", "1.0" },
97 { "ASCII", "1.0" },
98 { "ISO-8859-1", "1.0" },
99 // { "ISO-8859-5", "1.0" },
100 { "ASCII", "1.1" },
101 });
102 }
103
104 @Before
105 public void setUp() throws Exception
106 {
107 tempFile = File.createTempFile("EMF-encoding-test-" + encodingName, ".tmp.xml");
108 }
109
110 @After
111 public void tearDown() throws Exception
112 {
113 tempFile.delete();
114 }
115
116 public void doEMFSaveAndLoad(String testString) throws IOException
117 {
118 URI fileURI = URI.createFileURI(tempFile.toString());
119 String sourceValue = testString + " represented as XML in " + encodingName;
120 EAnnotation eObject = EcoreFactory.eINSTANCE.createEAnnotation();
121
122 eObject.setSource(sourceValue); // Including international characters
123
124 XMIResource resource = new XMIResourceImpl();
125 resource.getContents().add(eObject);
126 resource.setEncoding(encodingName);
127 resource.setXMLVersion(xmlVersion);
128 resource.setURI(fileURI);
129 resource.save(new HashMap<String, Object>());
130
131 XMIResource loadedResource = new XMIResourceImpl();
132 loadedResource.setURI(fileURI);
133 loadedResource.load(new HashMap<String, Object>());
134 assertTrue("No errors should occur while loading", loadedResource.getErrors().isEmpty());
135
136 EAnnotation loadedAnnotation = (EAnnotation)loadedResource.getContents().get(0);
137 assertEquals("String read back by EMF was different from the one being saved", sourceValue, loadedAnnotation.getSource());
138 }
139
140
141 @Test
142 public void testStraightASCII() throws Exception
143 {
144 // Test in the ASCII range
145 doEMFSaveAndLoad("Just straight ASCII small < and (&) big >");
146 }
147
148 @Test
149 public void testCharactersIn8bit() throws Exception
150 {
151 // Test in the 8 bit range of Unicode
152 doEMFSaveAndLoad("A name in Western Europe: Jesper Steen M\u00F8ller");
153 }
154
155 // Test outside the 8 bit range of Unicode
156 @Test
157 public void testArabicLetter() throws Exception
158 {
159 // Test in the 16 bit range of Unicode
160 doEMFSaveAndLoad("This is an arabic glyph: \uFECE. ");
161 }
162
163 // Test beyond the 16 bit range of Unicode
164 @Test
165 public void testSupplementaryContent() throws Exception
166 {
167 /**
168 * Test in the supplementary code point area (this will get tricky)
169 * See <http://www.unicode.org/charts/PDF/U10330.pdf>
170 */
171 char kusma[] = toSurrogatePair(0x1033A); // GOTHIC LETTER KUSMA
172 doEMFSaveAndLoad("This is a gothic letter: " + new String(kusma) + ". ");
173
174 // XML saving and loading has errors, too!
175 }
176
177 @Test
178 public void testControlCharacters() throws Exception
179 {
180 if ("1.1".equals(xmlVersion))
181 {
182 StringBuffer text = new StringBuffer();
183 for (char i = 1; i <= 0x1F; ++i)
184 {
185 text.append(i);
186 }
187 doEMFSaveAndLoad("These are control characters: " + text + ". ");
188 }
189 }
190 }