J. Duke | 319a3b9 | 2007-12-01 00:00:00 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 2003 Sun Microsystems, Inc. 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 Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, |
| 20 | * CA 95054 USA or visit www.sun.com if you need additional information or |
| 21 | * have any questions. |
| 22 | */ |
| 23 | |
| 24 | /* |
| 25 | @test |
| 26 | @bug 4217441 4533872 4900935 |
| 27 | @summary toLowerCase should lower-case Greek Sigma correctly depending |
| 28 | on the context (final/non-final). Also it should handle |
| 29 | Locale specific (lt, tr, and az) lowercasings and supplementary |
| 30 | characters correctly. |
| 31 | */ |
| 32 | |
| 33 | import java.util.Locale; |
| 34 | |
| 35 | public class ToLowerCase { |
| 36 | |
| 37 | public static void main(String[] args) { |
| 38 | Locale turkish = new Locale("tr", "TR"); |
| 39 | Locale lt = new Locale("lt"); // Lithanian |
| 40 | Locale az = new Locale("az"); // Azeri |
| 41 | |
| 42 | // Greek Sigma final/non-final tests |
| 43 | test("\u03A3", Locale.US, "\u03C3"); |
| 44 | test("LAST\u03A3", Locale.US, "last\u03C2"); |
| 45 | test("MID\u03A3DLE", Locale.US, "mid\u03C3dle"); |
| 46 | test("WORD1 \u03A3 WORD3", Locale.US, "word1 \u03C3 word3"); |
| 47 | test("WORD1 LAST\u03A3 WORD3", Locale.US, "word1 last\u03C2 word3"); |
| 48 | test("WORD1 MID\u03A3DLE WORD3", Locale.US, "word1 mid\u03C3dle word3"); |
| 49 | test("\u0399\u0395\u03a3\u03a5\u03a3 \u03a7\u03a1\u0399\u03a3\u03a4\u039f\u03a3", Locale.US, |
| 50 | "\u03b9\u03b5\u03c3\u03c5\u03c2 \u03c7\u03c1\u03b9\u03c3\u03c4\u03bf\u03c2"); // "IESUS XRISTOS" |
| 51 | |
| 52 | // Explicit dot above for I's and J's whenever there are more accents above (Lithanian) |
| 53 | test("I", lt, "i"); |
| 54 | test("I\u0300", lt, "i\u0307\u0300"); // "I" followed by COMBINING GRAVE ACCENT (cc==230) |
| 55 | test("I\u0316", lt, "i\u0316"); // "I" followed by COMBINING GRAVE ACCENT BELOW (cc!=230) |
| 56 | test("J", lt, "j"); |
| 57 | test("J\u0300", lt, "j\u0307\u0300"); // "J" followed by COMBINING GRAVE ACCENT (cc==230) |
| 58 | test("J\u0316", lt, "j\u0316"); // "J" followed by COMBINING GRAVE ACCENT BELOW (cc!=230) |
| 59 | test("\u012E", lt, "\u012F"); |
| 60 | test("\u012E\u0300", lt, "\u012F\u0307\u0300"); // "I (w/ OGONEK)" followed by COMBINING GRAVE ACCENT (cc==230) |
| 61 | test("\u012E\u0316", lt, "\u012F\u0316"); // "I (w/ OGONEK)" followed by COMBINING GRAVE ACCENT BELOW (cc!=230) |
| 62 | test("\u00CC", lt, "i\u0307\u0300"); |
| 63 | test("\u00CD", lt, "i\u0307\u0301"); |
| 64 | test("\u0128", lt, "i\u0307\u0303"); |
| 65 | test("I\u0300", Locale.US, "i\u0300"); // "I" followed by COMBINING GRAVE ACCENT (cc==230) |
| 66 | test("J\u0300", Locale.US, "j\u0300"); // "J" followed by COMBINING GRAVE ACCENT (cc==230) |
| 67 | test("\u012E\u0300", Locale.US, "\u012F\u0300"); // "I (w/ OGONEK)" followed by COMBINING GRAVE ACCENT (cc==230) |
| 68 | test("\u00CC", Locale.US, "\u00EC"); |
| 69 | test("\u00CD", Locale.US, "\u00ED"); |
| 70 | test("\u0128", Locale.US, "\u0129"); |
| 71 | |
| 72 | // I-dot tests (Turkish and Azeri) |
| 73 | test("\u0130", turkish, "i"); |
| 74 | test("\u0130", az, "i"); |
| 75 | test("\u0130", Locale.US, "i"); |
| 76 | |
| 77 | // Remove dot_above in the sequence I + dot_above (Turkish and Azeri) |
| 78 | test("I\u0307", turkish, "i"); |
| 79 | test("I\u0307", az, "i"); |
| 80 | test("J\u0307", turkish, "j\u0307"); |
| 81 | test("J\u0307", az, "j\u0307"); |
| 82 | |
| 83 | // Unless an I is before a dot_above, it turns into a dotless i (Turkish and Azeri) |
| 84 | test("I", turkish, "\u0131"); |
| 85 | test("I", az, "\u0131"); |
| 86 | test("I", Locale.US, "i"); |
| 87 | test("IABC", turkish, "\u0131abc"); |
| 88 | test("IABC", az, "\u0131abc"); |
| 89 | test("IABC", Locale.US, "iabc"); |
| 90 | |
| 91 | // Supplementary character tests |
| 92 | // |
| 93 | // U+10400 ("\uD801\uDC00"): DESERET CAPITAL LETTER LONG I |
| 94 | // U+10401 ("\uD801\uDC01"): DESERET CAPITAL LETTER LONG E |
| 95 | // U+10402 ("\uD801\uDC02"): DESERET CAPITAL LETTER LONG A |
| 96 | // U+10428 ("\uD801\uDC28"): DESERET SMALL LETTER LONG I |
| 97 | // U+10429 ("\uD801\uDC29"): DESERET SMALL LETTER LONG E |
| 98 | // U+1042A ("\uD801\uDC2A"): DESERET SMALL LETTER LONG A |
| 99 | // |
| 100 | // valid code point tests: |
| 101 | test("\uD801\uDC00\uD801\uDC01\uD801\uDC02", Locale.US, "\uD801\uDC28\uD801\uDC29\uD801\uDC2A"); |
| 102 | test("\uD801\uDC00A\uD801\uDC01B\uD801\uDC02C", Locale.US, "\uD801\uDC28a\uD801\uDC29b\uD801\uDC2Ac"); |
| 103 | // invalid code point tests: |
| 104 | test("\uD800\uD800\uD801A\uDC00\uDC00\uDC00B", Locale.US, "\uD800\uD800\uD801a\uDC00\uDC00\uDC00b"); |
| 105 | |
| 106 | } |
| 107 | |
| 108 | static void test(String in, Locale locale, String expected) { |
| 109 | String result = in.toLowerCase(locale); |
| 110 | if (!result.equals(expected)) { |
| 111 | System.err.println("input: " + in + ", locale: " + locale + |
| 112 | ", expected: " + expected + ", actual: " + result); |
| 113 | throw new RuntimeException(); |
| 114 | } |
| 115 | } |
| 116 | } |