50045
|
1 |
/*
|
|
2 |
* Copyright (c) 2018, 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. Oracle designates this
|
|
8 |
* particular file as subject to the "Classpath" exception as provided
|
|
9 |
* by Oracle in the LICENSE file that accompanied this code.
|
|
10 |
*
|
|
11 |
* This code is distributed in the hope that it will be useful, but WITHOUT
|
|
12 |
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
13 |
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
|
14 |
* version 2 for more details (a copy is included in the LICENSE file that
|
|
15 |
* accompanied this code).
|
|
16 |
*
|
|
17 |
* You should have received a copy of the GNU General Public License version
|
|
18 |
* 2 along with this work; if not, write to the Free Software Foundation,
|
|
19 |
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
|
20 |
*
|
|
21 |
* Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
|
|
22 |
* or visit www.oracle.com if you need additional information or have any
|
|
23 |
* questions.
|
|
24 |
*/
|
|
25 |
|
|
26 |
/*
|
|
27 |
* @test
|
|
28 |
* @bug 4397357 6565620 6959267 7070436 7198195 8041791 8032446 8072600
|
|
29 |
* @summary Confirm special case mappings are handled correctly.
|
|
30 |
*/
|
|
31 |
|
|
32 |
import java.io.BufferedReader;
|
|
33 |
import java.io.IOException;
|
|
34 |
import java.nio.file.Files;
|
|
35 |
import java.nio.file.Paths;
|
|
36 |
import java.util.ArrayList;
|
|
37 |
import java.util.List;
|
|
38 |
import java.util.Locale;
|
|
39 |
import java.util.StringTokenizer;
|
|
40 |
|
|
41 |
public class SpecialCasingTest {
|
|
42 |
|
|
43 |
private static boolean err = false;
|
|
44 |
|
|
45 |
// Locales which are used for testing
|
|
46 |
private static List<Locale> locales = new ArrayList<>();
|
|
47 |
static {
|
|
48 |
locales.add(new Locale("az", ""));
|
|
49 |
locales.addAll(java.util.Arrays.asList(Locale.getAvailableLocales()));
|
|
50 |
}
|
|
51 |
|
|
52 |
// Default locale
|
|
53 |
private static String defaultLang;
|
|
54 |
|
|
55 |
// True if the default language is az, lt, or tr which has locale-specific
|
|
56 |
// mappings.
|
|
57 |
private static boolean specificLocale;
|
|
58 |
|
|
59 |
// Additional test cases
|
|
60 |
// Pseudo-locales which are used here:
|
|
61 |
// L1: locales other than lt
|
|
62 |
// L2: locales other than az and tr
|
|
63 |
// L3: locales other than az, lt and tr
|
|
64 |
private static final String[] additionalTestData = {
|
|
65 |
// Format:
|
|
66 |
// <code>; <lower>; <title>; <upper>; (<condition_list>)
|
|
67 |
|
|
68 |
// Counterpart of Final_Sigma test case
|
|
69 |
// 03A3; 03C2; 03A3; 03A3; Final_Sigma
|
|
70 |
"03A3; 03C3; 03A3; 03A3; SunSpecific_Not_Final_Sigma1",
|
|
71 |
"03A3; 03C3; 03A3; 03A3; SunSpecific_Not_Final_Sigma2",
|
|
72 |
|
|
73 |
// Counterpart of After_Soft_Dotted test case
|
|
74 |
// 0307; 0307; ; ; lt After_Soft_Dotted
|
|
75 |
"0307; 0307; 0307; 0307; L1 After_Soft_Dotted",
|
|
76 |
"0307; 0307; 0307; 0307; lt SunSpecific_Not_After_Soft_Dotted",
|
|
77 |
"0307; 0307; 0307; 0307; L1 SunSpecific_Not_After_Soft_Dotted",
|
|
78 |
|
|
79 |
// Counterpart of More_Above test cases
|
|
80 |
// 0049; 0069 0307; 0049; 0049; lt More_Above
|
|
81 |
"0049; 0131 ; 0049; 0049; az More_Above",
|
|
82 |
"0049; 0131 ; 0049; 0049; tr More_Above",
|
|
83 |
"0049; 0069 ; 0049; 0049; L3 More_Above",
|
|
84 |
"0049; 0069 ; 0049; 0049; lt SunSpecific_Not_More_Above",
|
|
85 |
"0049; 0131 ; 0049; 0049; az SunSpecific_Not_More_Above",
|
|
86 |
"0049; 0131 ; 0049; 0049; tr SunSpecific_Not_More_Above",
|
|
87 |
"0049; 0069 ; 0049; 0049; L3 SunSpecific_Not_More_Above",
|
|
88 |
// 004A; 006A 0307; 004A; 004A; lt More_Above
|
|
89 |
"004A; 006A ; 004A; 004A; L1 More_Above",
|
|
90 |
"004A; 006A ; 004A; 004A; lt SunSpecific_Not_More_Above",
|
|
91 |
"004A; 006A ; 004A; 004A; L1 SunSpecific_Not_More_Above",
|
|
92 |
// 012E; 012F 0307; 012E; 012E; lt More_Above
|
|
93 |
"012E; 012F ; 012E; 012E; L1 More_Above",
|
|
94 |
"012E; 012F ; 012E; 012E; lt SunSpecific_Not_More_Above",
|
|
95 |
"012E; 012F ; 012E; 012E; L1 SunSpecific_Not_More_Above",
|
|
96 |
|
|
97 |
// Counterpart of After_I test cases
|
|
98 |
// 0307; ; 0307; 0307; tr After_I
|
|
99 |
// 0307; ; 0307; 0307; az After_I
|
|
100 |
"0307; 0307 0307; 0307; 0307; lt After_I",
|
|
101 |
"0307; 0307 ; 0307; 0307; L3 After_I",
|
|
102 |
"0307; 0307 ; 0307; 0307; tr SunSpecific_Not_After_I",
|
|
103 |
"0307; 0307 ; 0307; 0307; az SunSpecific_Not_After_I",
|
|
104 |
"0307; 0307 ; 0307; 0307; L2 SunSpecific_Not_After_I",
|
|
105 |
|
|
106 |
// Counterpart of Not_Before_Dot test cases
|
|
107 |
// 0049; 0131 ; 0049; 0049; tr Not_Before_Dot
|
|
108 |
// 0049; 0131 ; 0049; 0049; az Not_Before_Dot
|
|
109 |
"0049; 0069 ; 0049; 0049; L2 Not_Before_Dot",
|
|
110 |
"0049; 0069 ; 0049; 0049; tr SunSpecific_Before_Dot",
|
|
111 |
"0049; 0069 ; 0049; 0049; az SunSpecific_Before_Dot",
|
|
112 |
"0049; 0069 0307 0307; 0049; 0049; lt SunSpecific_Before_Dot",
|
|
113 |
"0049; 0069 0307 ; 0049; 0049; L3 SunSpecific_Before_Dot",
|
|
114 |
};
|
|
115 |
|
|
116 |
public static void main (String[] args) {
|
|
117 |
SpecialCasingTest specialCasingTest = new SpecialCasingTest();
|
|
118 |
specialCasingTest.test();
|
|
119 |
}
|
|
120 |
|
|
121 |
private void test () {
|
|
122 |
Locale defaultLocale = Locale.getDefault();
|
|
123 |
BufferedReader in = null;
|
|
124 |
|
|
125 |
try {
|
|
126 |
int locale_num = locales.size();
|
|
127 |
for (int l = 0; l < locale_num; l++) {
|
|
128 |
Locale locale = locales.get(l);
|
|
129 |
Locale.setDefault(locale);
|
|
130 |
System.out.println("Testing on " + locale + " locale....");
|
|
131 |
|
|
132 |
defaultLang = locale.getLanguage();
|
|
133 |
if (defaultLang.equals("az") ||
|
|
134 |
defaultLang.equals("lt") ||
|
|
135 |
defaultLang.equals("tr")) {
|
|
136 |
specificLocale = true;
|
|
137 |
} else {
|
|
138 |
specificLocale = false;
|
|
139 |
}
|
|
140 |
in = Files.newBufferedReader(Paths.get(System.getProperty("test.src.path"), "..", "/Character/SpecialCasing.txt")
|
|
141 |
.toRealPath());
|
|
142 |
String line;
|
|
143 |
while ((line = in.readLine()) != null) {
|
|
144 |
if (line.length() == 0 || line.charAt(0) == '#') {
|
|
145 |
continue;
|
|
146 |
}
|
|
147 |
test(line);
|
|
148 |
}
|
|
149 |
in.close();
|
|
150 |
in = null;
|
|
151 |
System.out.println("Testing with Sun original data....");
|
|
152 |
for (String additionalTestData1 : additionalTestData) {
|
|
153 |
test(additionalTestData1);
|
|
154 |
}
|
|
155 |
}
|
|
156 |
}
|
|
157 |
catch (IOException e) {
|
|
158 |
err = true;
|
|
159 |
e.printStackTrace();
|
|
160 |
}
|
|
161 |
finally {
|
|
162 |
if (in != null) {
|
|
163 |
try {
|
|
164 |
in.close();
|
|
165 |
}
|
|
166 |
catch (IOException e) {
|
|
167 |
}
|
|
168 |
}
|
|
169 |
Locale.setDefault(defaultLocale);
|
|
170 |
if (err) {
|
|
171 |
throw new RuntimeException("SpecialCasingTest failed.");
|
|
172 |
} else {
|
|
173 |
System.out.println("*** SpecialCasingTest passed.");
|
|
174 |
}
|
|
175 |
}
|
|
176 |
}
|
|
177 |
|
|
178 |
private void test(String line) {
|
|
179 |
int index = line.indexOf('#');
|
|
180 |
if (index != -1) {
|
|
181 |
line = line.substring(0, index);
|
|
182 |
}
|
|
183 |
|
|
184 |
String lang = null;
|
|
185 |
String condition = null;
|
|
186 |
String[] fields = line.split("; ");
|
|
187 |
|
|
188 |
for (int i = 0; i < 4; i++) {
|
|
189 |
if (fields[i].length() != 0) {
|
|
190 |
fields[i] = convert(fields[i]);
|
|
191 |
}
|
|
192 |
}
|
|
193 |
if (fields.length != 4) {
|
|
194 |
StringTokenizer st = new StringTokenizer(fields[4]);
|
|
195 |
|
|
196 |
while (st.hasMoreTokens()) {
|
|
197 |
String token = st.nextToken();
|
|
198 |
|
|
199 |
if (token.equals("Final_Sigma")) {
|
|
200 |
condition = "Final Sigma";
|
|
201 |
fields[0] = "Abc" + fields[0];
|
|
202 |
fields[1] = "abc" + fields[1];
|
|
203 |
fields[3] = "ABC" + fields[3];
|
|
204 |
} else if (token.equals("SunSpecific_Not_Final_Sigma1")) {
|
|
205 |
condition = "*Sun Specific* Not Final Sigma 1";
|
|
206 |
fields[0] = "Abc" + fields[0] + "xyz";
|
|
207 |
fields[1] = "abc" + fields[1] + "xyz";
|
|
208 |
fields[3] = "ABC" + fields[3] + "XYZ";
|
|
209 |
} else if (token.equals("SunSpecific_Not_Final_Sigma2")) {
|
|
210 |
condition = "*Sun Specific* Not Final Sigma 2";
|
|
211 |
} else if (token.equals("After_Soft_Dotted")) {
|
|
212 |
condition = "After Soft-Dotted";
|
|
213 |
fields[0] = "\u1E2D" + fields[0];
|
|
214 |
fields[1] = "\u1E2D" + fields[1];
|
|
215 |
fields[3] = "\u1E2C" + fields[3];
|
|
216 |
} else if (token.equals("SunSpecific_Not_After_Soft_Dotted")) {
|
|
217 |
condition = "*Sun Specific* Not After Soft-Dotted";
|
|
218 |
fields[0] = "Dot" + fields[0];
|
|
219 |
fields[1] = "dot" + fields[1];
|
|
220 |
fields[3] = "DOT" + fields[3];
|
|
221 |
} else if (token.equals("More_Above")) {
|
|
222 |
condition = "More Above";
|
|
223 |
fields[0] = fields[0] + "\u0306";
|
|
224 |
fields[1] = fields[1] + "\u0306";
|
|
225 |
fields[3] = fields[3] + "\u0306";
|
|
226 |
} else if (token.equals("SunSpecific_Not_More_Above")) {
|
|
227 |
condition = "*Sun Specific* Not More Above";
|
|
228 |
fields[0] = fields[0] + "breve";
|
|
229 |
fields[1] = fields[1] + "breve";
|
|
230 |
fields[3] = fields[3] + "BREVE";
|
|
231 |
} else if (token.equals("After_I")) {
|
|
232 |
condition = "After I";
|
|
233 |
fields[0] = "I" + fields[0];
|
|
234 |
fields[1] = "i" + fields[1];
|
|
235 |
fields[3] = "I" + fields[3];
|
|
236 |
} else if (token.equals("SunSpecific_Not_After_I")) {
|
|
237 |
condition = "*Sun Specific* Not After I";
|
|
238 |
fields[0] = "A" + fields[0];
|
|
239 |
fields[1] = "a" + fields[1];
|
|
240 |
fields[3] = "A" + fields[3];
|
|
241 |
} else if (token.equals("Not_Before_Dot")) {
|
|
242 |
condition = "Not Before Dot";
|
|
243 |
fields[0] = fields[0] + "Z";
|
|
244 |
fields[1] = fields[1] + "z";
|
|
245 |
fields[3] = fields[3] + "Z";
|
|
246 |
} else if (token.equals("SunSpecific_Before_Dot")) {
|
|
247 |
condition = "*Sun Specific* Before Dot";
|
|
248 |
fields[0] = fields[0] + "\u0307";
|
|
249 |
fields[3] = fields[3] + "\u0307";
|
|
250 |
} else if (token.length() == 2) {
|
|
251 |
lang = token;
|
|
252 |
|
|
253 |
if (lang.equals("L1")) {
|
|
254 |
if (defaultLang.equals("lt")) {
|
|
255 |
lang = "en";
|
|
256 |
} else {
|
|
257 |
lang = defaultLang;
|
|
258 |
}
|
|
259 |
} else if (lang.equals("L2")) {
|
|
260 |
if (defaultLang.equals("az") ||
|
|
261 |
defaultLang.equals("tr")) {
|
|
262 |
lang = "en";
|
|
263 |
} else {
|
|
264 |
lang = defaultLang;
|
|
265 |
}
|
|
266 |
} else if (lang.equals("L3")) {
|
|
267 |
if (defaultLang.equals("az") ||
|
|
268 |
defaultLang.equals("lt") ||
|
|
269 |
defaultLang.equals("tr")) {
|
|
270 |
lang = "en";
|
|
271 |
} else {
|
|
272 |
lang = defaultLang;
|
|
273 |
}
|
|
274 |
// I want to have another test case here for double-check.
|
|
275 |
// Current implementation for Character and String considers
|
|
276 |
// only az, lt, and tr locales. I want to detect if other
|
|
277 |
// locales are specified.
|
|
278 |
} else if (!lang.equals("az") &&
|
|
279 |
!lang.equals("lt") &&
|
|
280 |
!lang.equals("tr")) {
|
|
281 |
throw new RuntimeException("Unsupported locale: " +
|
|
282 |
lang + ". It may need to be considered in ConditionalSpecialCasing.java. Please confirm.");
|
|
283 |
}
|
|
284 |
} else {
|
|
285 |
throw new RuntimeException("Unknown condition: " + token);
|
|
286 |
}
|
|
287 |
}
|
|
288 |
} else if (fields[0].equals("\u0130")) {
|
|
289 |
// special case for \u0130
|
|
290 |
if (defaultLang.equals("az") ||
|
|
291 |
defaultLang.equals("tr")) {
|
|
292 |
lang = "en";
|
|
293 |
} else {
|
|
294 |
lang = defaultLang;
|
|
295 |
}
|
|
296 |
}
|
|
297 |
testLowerCase(fields[0], fields[1], lang, condition);
|
|
298 |
testUpperCase(fields[0], fields[3], lang, condition);
|
|
299 |
}
|
|
300 |
|
|
301 |
private void testLowerCase(String orig, String expected,
|
|
302 |
String lang, String condition) {
|
|
303 |
String got = (lang == null) ?
|
|
304 |
orig.toLowerCase() : orig.toLowerCase(new Locale(lang, ""));
|
|
305 |
|
|
306 |
if (!expected.equals(got)) {
|
|
307 |
err = true;
|
|
308 |
System.err.println("toLowerCase(lang=" + lang +
|
|
309 |
") failed.\n\tOriginal: " + toString(orig) +
|
|
310 |
"\n\tGot: " + toString(got) +
|
|
311 |
"\n\tExpected: " + toString(expected) +
|
|
312 |
((condition == null) ? "" : ("\n under condition(" +
|
|
313 |
condition + ")")));
|
|
314 |
}
|
|
315 |
}
|
|
316 |
|
|
317 |
private void testUpperCase(String orig, String expected,
|
|
318 |
String lang, String condition) {
|
|
319 |
String got = (lang == null) ?
|
|
320 |
orig.toUpperCase() : orig.toUpperCase(new Locale(lang, ""));
|
|
321 |
|
|
322 |
if (!expected.equals(got)) {
|
|
323 |
err = true;
|
|
324 |
System.err.println("toUpperCase(lang=" + lang +
|
|
325 |
") failed.\n\tOriginal: " + toString(orig) +
|
|
326 |
"\n\tGot: " + toString(got) +
|
|
327 |
"\n\tExpected: " + toString(expected) +
|
|
328 |
((condition == null) ? "" : ("\n under condition(" +
|
|
329 |
condition + ")")));
|
|
330 |
}
|
|
331 |
}
|
|
332 |
StringBuilder sb = new StringBuilder();
|
|
333 |
|
|
334 |
private String convert(String str) {
|
|
335 |
sb.setLength(0);
|
|
336 |
|
|
337 |
String[] tokens = str.split(" ");
|
|
338 |
for (String token : tokens) {
|
|
339 |
sb.append((char) Integer.parseInt(token, 16));
|
|
340 |
}
|
|
341 |
return sb.toString();
|
|
342 |
}
|
|
343 |
|
|
344 |
private String toString(String str) {
|
|
345 |
sb.setLength(0);
|
|
346 |
|
|
347 |
int len = str.length();
|
|
348 |
for (int i = 0; i < len; i++) {
|
|
349 |
sb.append("0x").append(Integer.toHexString(str.charAt(i)).toUpperCase()).append(" ");
|
|
350 |
}
|
|
351 |
return sb.toString();
|
|
352 |
}
|
|
353 |
|
|
354 |
}
|