1 /* 2 * Copyright (c) 2000, 2003, 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 */ 23 24 /* 25 @test 26 @bug 4219630 4304573 4533872 4900935 8042589 8054307 27 @summary toUpperCase should upper-case German sharp s correctly even if 28 it's the only character in the string. should also uppercase 29 all of the 1:M char mappings correctly. Also it should handle 30 Locale specific (lt, tr, and az) uppercasings and supplementary 31 characters correctly. 32 */ 33 34 import java.util.Locale; 35 36 public class ToUpperCase { 37 main(String[] args)38 public static void main(String[] args) { 39 Locale turkish = new Locale("tr", "TR"); 40 Locale lt = new Locale("lt"); // Lithanian 41 Locale az = new Locale("az"); // Azeri 42 43 test("\u00DF", turkish, "SS"); 44 test("a\u00DF", turkish, "ASS"); 45 test("i", turkish, "\u0130"); 46 test("i", az, "\u0130"); 47 test("\u0131", turkish, "I"); 48 test("\u00DF", Locale.GERMANY, "SS"); 49 test("a\u00DF", Locale.GERMANY, "ASS"); 50 test("i", Locale.GERMANY, "I"); 51 52 // test some of the 1:M uppercase mappings 53 test("abc\u00DF", Locale.US, "ABC\u0053\u0053"); 54 test("\u0149abc", Locale.US, "\u02BC\u004EABC"); 55 test("\u0149abc", turkish, "\u02BC\u004EABC"); 56 test("\u1F52", Locale.US, "\u03A5\u0313\u0300"); 57 test("\u0149\u1F52", Locale.US, "\u02BC\u004E\u03A5\u0313\u0300"); 58 test("\u1F54ZZZ", Locale.US, "\u03A5\u0313\u0301ZZZ"); 59 test("\u1F54ZZZ", turkish, "\u03A5\u0313\u0301ZZZ"); 60 test("a\u00DF\u1F56", Locale.US, "ASS\u03A5\u0313\u0342"); 61 test("\u1FAD", turkish, "\u1F6D\u0399"); 62 test("i\u1FC7", turkish, "\u0130\u0397\u0342\u0399"); 63 test("i\u1FC7", az, "\u0130\u0397\u0342\u0399"); 64 test("i\u1FC7", Locale.US, "I\u0397\u0342\u0399"); 65 test("\uFB04", Locale.US, "\u0046\u0046\u004C"); 66 test("\uFB17AbCdEfi", turkish, "\u0544\u053DABCDEF\u0130"); 67 test("\uFB17AbCdEfi", az, "\u0544\u053DABCDEF\u0130"); 68 69 // Remove DOT ABOVE after "i" in Lithuanian 70 test("i\u0307", lt, "I"); 71 test("\u0307", lt, "\u0307"); 72 test("\u0307i", lt, "\u0307I"); 73 test("j\u0307", lt, "J"); 74 test("abci\u0307def", lt, "ABCIDEF"); 75 test("a\u0307", lt, "A\u0307"); 76 test("abc\u0307def", lt, "ABC\u0307DEF"); 77 test("i\u0307", Locale.US, "I\u0307"); 78 test("i\u0307", turkish, "\u0130\u0307"); 79 80 // Supplementary character tests 81 // 82 // U+10400 ("\uD801\uDC00"): DESERET CAPITAL LETTER LONG I 83 // U+10401 ("\uD801\uDC01"): DESERET CAPITAL LETTER LONG E 84 // U+10402 ("\uD801\uDC02"): DESERET CAPITAL LETTER LONG A 85 // U+10428 ("\uD801\uDC28"): DESERET SMALL LETTER LONG I 86 // U+10429 ("\uD801\uDC29"): DESERET SMALL LETTER LONG E 87 // U+1042A ("\uD801\uDC2A"): DESERET SMALL LETTER LONG A 88 // 89 // valid code point tests: 90 test("\uD801\uDC28\uD801\uDC29\uD801\uDC2A", Locale.US, "\uD801\uDC00\uD801\uDC01\uD801\uDC02"); 91 test("\uD801\uDC28a\uD801\uDC29b\uD801\uDC2Ac", Locale.US, "\uD801\uDC00A\uD801\uDC01B\uD801\uDC02C"); 92 // invalid code point tests: 93 test("\uD800\uD800\uD801a\uDC00\uDC00\uDC00b", Locale.US, "\uD800\uD800\uD801A\uDC00\uDC00\uDC00B"); 94 95 // lower/uppercase + surrogates 96 test("a\uD801\uDC44", Locale.ROOT, "A\uD801\uDC1c"); 97 test("A\uD801\uDC44", Locale.ROOT, "A\uD801\uDC1c"); 98 test("a\uD801\uDC28\uD801\uDC29\uD801\uDC2A", Locale.US, "A\uD801\uDC00\uD801\uDC01\uD801\uDC02"); 99 test("A\uD801\uDC28a\uD801\uDC29b\uD801\uDC2Ac", Locale.US, "A\uD801\uDC00A\uD801\uDC01B\uD801\uDC02C"); 100 101 // test latin1 only case 102 StringBuilder src = new StringBuilder(0x100); 103 StringBuilder exp = new StringBuilder(0x100); 104 for (int cp = 0; cp < 0x100; cp++) { 105 int upperCase = Character.toUpperCase(cp); 106 if (upperCase == -1) { //Character.ERROR 107 continue; 108 } 109 src.appendCodePoint(cp); 110 if (cp == '\u00df') { 111 exp.append("SS"); // need Character.toUpperCaseEx() 112 } else { 113 exp.appendCodePoint(upperCase); 114 } 115 } 116 test(src.toString(), Locale.US, exp.toString()); 117 118 // test non-latin1 -> latin1 119 src = new StringBuilder(0x100).append("ABC"); 120 exp = new StringBuilder(0x100).append("ABC"); 121 for (int cp = 0x100; cp < 0x10000; cp++) { 122 int upperCase = Character.toUpperCase(cp); 123 if (upperCase < 0x100) { 124 src.appendCodePoint(cp); 125 exp.appendCodePoint(upperCase); 126 } 127 } 128 test(src.toString(), Locale.US, exp.toString()); 129 130 } 131 test(String in, Locale locale, String expected)132 static void test(String in, Locale locale, String expected) { 133 test0(in, locale,expected); 134 // trigger different code paths 135 for (String[] ss : new String[][] { 136 new String[] {"abc", "ABC"}, 137 new String[] {"AbC", "ABC"}, 138 new String[] {"ABC", "ABC"}, 139 new String[] {"AB\u4e00", "AB\u4e00"}, 140 new String[] {"ab\u4e00", "AB\u4e00"}, 141 new String[] {"aB\u4e00", "AB\u4e00"}, 142 new String[] {"AB\uD800\uDC00", "AB\uD800\uDC00"}, 143 new String[] {"Ab\uD800\uDC00", "AB\uD800\uDC00"}, 144 new String[] {"ab\uD800\uDC00", "AB\uD800\uDC00"}, 145 new String[] {"AB\uD801\uDC44", "AB\uD801\uDC1C"}, 146 new String[] {"Ab\uD801\uDC44", "AB\uD801\uDC1C"}, 147 new String[] {"ab\uD801\uDC44", "AB\uD801\uDC1C"}, 148 }) { 149 test0(ss[0] + " " + in, locale, ss[1] + " " + expected); 150 test0(in + " " + ss[0], locale, expected + " " + ss[1]); 151 } 152 } 153 test0(String in, Locale locale, String expected)154 static void test0(String in, Locale locale, String expected) { 155 String result = in.toUpperCase(locale); 156 if (!result.equals(expected)) { 157 System.err.println("input: " + in + ", locale: " + locale + 158 ", expected: " + expected + ", actual: " + result); 159 throw new RuntimeException(); 160 } 161 } 162 } 163