| OLD | NEW |
| 1 // Copyright (c) 2011 The Chromium Authors. All rights reserved. | 1 // Copyright (c) 2011 The Chromium Authors. All rights reserved. |
| 2 // Use of this source code is governed by a BSD-style license that can be | 2 // Use of this source code is governed by a BSD-style license that can be |
| 3 // found in the LICENSE file. | 3 // found in the LICENSE file. |
| 4 | 4 |
| 5 #include "base/i18n/case_conversion.h" | 5 #include "base/i18n/case_conversion.h" |
| 6 #include "base/i18n/rtl.h" | 6 #include "base/i18n/rtl.h" |
| 7 #include "base/strings/utf_string_conversions.h" | 7 #include "base/strings/utf_string_conversions.h" |
| 8 #include "testing/gtest/include/gtest/gtest.h" | 8 #include "testing/gtest/include/gtest/gtest.h" |
| 9 #include "third_party/icu/source/i18n/unicode/usearch.h" | 9 #include "third_party/icu/source/i18n/unicode/usearch.h" |
| 10 | 10 |
| 11 namespace base { | 11 namespace base { |
| 12 namespace i18n { | 12 namespace i18n { |
| 13 | 13 |
| 14 namespace { | 14 namespace { |
| 15 | 15 |
| 16 class ScopedSetICUDefaultLocale { |
| 17 std::string default_locale; |
| 18 |
| 19 public: |
| 20 ScopedSetICUDefaultLocale(std::string locale); |
| 21 ~ScopedSetICUDefaultLocale(); |
| 22 }; |
| 23 |
| 24 ScopedSetICUDefaultLocale::ScopedSetICUDefaultLocale(std::string locale) |
| 25 : default_locale(locale) {} |
| 26 |
| 27 ScopedSetICUDefaultLocale::~ScopedSetICUDefaultLocale() { |
| 28 i18n::SetICUDefaultLocale(default_locale.data()); |
| 29 } |
| 30 |
| 16 const wchar_t kNonASCIIMixed[] = | 31 const wchar_t kNonASCIIMixed[] = |
| 17 L"\xC4\xD6\xE4\xF6\x20\xCF\xEF\x20\xF7\x25" | 32 L"\xC4\xD6\xE4\xF6\x20\xCF\xEF\x20\xF7\x25" |
| 18 L"\xA4\x23\x2A\x5E\x60\x40\xA3\x24\x2030\x201A\x7E\x20\x1F07\x1F0F" | 33 L"\xA4\x23\x2A\x5E\x60\x40\xA3\x24\x2030\x201A\x7E\x20\x1F07\x1F0F" |
| 19 L"\x20\x1E00\x1E01"; | 34 L"\x20\x1E00\x1E01"; |
| 20 const wchar_t kNonASCIILower[] = | 35 const wchar_t kNonASCIILower[] = |
| 21 L"\xE4\xF6\xE4\xF6\x20\xEF\xEF" | 36 L"\xE4\xF6\xE4\xF6\x20\xEF\xEF" |
| 22 L"\x20\xF7\x25\xA4\x23\x2A\x5E\x60\x40\xA3\x24\x2030\x201A\x7E\x20\x1F07" | 37 L"\x20\xF7\x25\xA4\x23\x2A\x5E\x60\x40\xA3\x24\x2030\x201A\x7E\x20\x1F07" |
| 23 L"\x1F07\x20\x1E01\x1E01"; | 38 L"\x1F07\x20\x1E01\x1E01"; |
| 24 const wchar_t kNonASCIIUpper[] = | 39 const wchar_t kNonASCIIUpper[] = |
| 25 L"\xC4\xD6\xC4\xD6\x20\xCF\xCF" | 40 L"\xC4\xD6\xC4\xD6\x20\xCF\xCF" |
| (...skipping 25 matching lines...) Expand all Loading... |
| 51 | 66 |
| 52 result = ToUpper(mixed); | 67 result = ToUpper(mixed); |
| 53 EXPECT_EQ(expected_upper, result); | 68 EXPECT_EQ(expected_upper, result); |
| 54 } | 69 } |
| 55 | 70 |
| 56 TEST(CaseConversionTest, TurkishLocaleConversion) { | 71 TEST(CaseConversionTest, TurkishLocaleConversion) { |
| 57 const string16 mixed(WideToUTF16(L"\x49\x131")); | 72 const string16 mixed(WideToUTF16(L"\x49\x131")); |
| 58 const string16 expected_lower(WideToUTF16(L"\x69\x131")); | 73 const string16 expected_lower(WideToUTF16(L"\x69\x131")); |
| 59 const string16 expected_upper(WideToUTF16(L"\x49\x49")); | 74 const string16 expected_upper(WideToUTF16(L"\x49\x49")); |
| 60 | 75 |
| 61 std::string default_locale(uloc_getDefault()); | 76 ScopedSetICUDefaultLocale restore_object(uloc_getDefault()); |
| 62 i18n::SetICUDefaultLocale("en_US"); | 77 i18n::SetICUDefaultLocale("en_US"); |
| 63 | 78 |
| 64 string16 result = ToLower(mixed); | 79 string16 result = ToLower(mixed); |
| 65 EXPECT_EQ(expected_lower, result); | 80 EXPECT_EQ(expected_lower, result); |
| 66 | 81 |
| 67 result = ToUpper(mixed); | 82 result = ToUpper(mixed); |
| 68 EXPECT_EQ(expected_upper, result); | 83 EXPECT_EQ(expected_upper, result); |
| 69 | 84 |
| 70 i18n::SetICUDefaultLocale("tr"); | 85 i18n::SetICUDefaultLocale("tr"); |
| 71 | 86 |
| 72 const string16 expected_lower_turkish(WideToUTF16(L"\x131\x131")); | 87 const string16 expected_lower_turkish(WideToUTF16(L"\x131\x131")); |
| 73 const string16 expected_upper_turkish(WideToUTF16(L"\x49\x49")); | 88 const string16 expected_upper_turkish(WideToUTF16(L"\x49\x49")); |
| 74 | 89 |
| 75 result = ToLower(mixed); | 90 result = ToLower(mixed); |
| 76 EXPECT_EQ(expected_lower_turkish, result); | 91 EXPECT_EQ(expected_lower_turkish, result); |
| 77 | 92 |
| 78 result = ToUpper(mixed); | 93 result = ToUpper(mixed); |
| 79 EXPECT_EQ(expected_upper_turkish, result); | 94 EXPECT_EQ(expected_upper_turkish, result); |
| 80 | |
| 81 SetICUDefaultLocale(default_locale.data()); | |
| 82 } | 95 } |
| 83 | 96 |
| 84 TEST(CaseConversionTest, FoldCase) { | 97 TEST(CaseConversionTest, FoldCase) { |
| 85 // Simple ASCII, should lower-case. | 98 // Simple ASCII, should lower-case. |
| 86 EXPECT_EQ(ASCIIToUTF16("hello, world"), | 99 EXPECT_EQ(ASCIIToUTF16("hello, world"), |
| 87 FoldCase(ASCIIToUTF16("Hello, World"))); | 100 FoldCase(ASCIIToUTF16("Hello, World"))); |
| 88 | 101 |
| 89 // Non-ASCII cases from above. They should all fold to the same result. | 102 // Non-ASCII cases from above. They should all fold to the same result. |
| 90 EXPECT_EQ(FoldCase(WideToUTF16(kNonASCIIMixed)), | 103 EXPECT_EQ(FoldCase(WideToUTF16(kNonASCIIMixed)), |
| 91 FoldCase(WideToUTF16(kNonASCIILower))); | 104 FoldCase(WideToUTF16(kNonASCIILower))); |
| 92 EXPECT_EQ(FoldCase(WideToUTF16(kNonASCIIMixed)), | 105 EXPECT_EQ(FoldCase(WideToUTF16(kNonASCIIMixed)), |
| 93 FoldCase(WideToUTF16(kNonASCIIUpper))); | 106 FoldCase(WideToUTF16(kNonASCIIUpper))); |
| 94 | 107 |
| 95 // Turkish cases from above. This is the lower-case expected result from the | 108 // Turkish cases from above. This is the lower-case expected result from the |
| 96 // US locale. It should be the same even when the current locale is Turkish. | 109 // US locale. It should be the same even when the current locale is Turkish. |
| 97 const string16 turkish(WideToUTF16(L"\x49\x131")); | 110 const string16 turkish(WideToUTF16(L"\x49\x131")); |
| 98 const string16 turkish_expected(WideToUTF16(L"\x69\x131")); | 111 const string16 turkish_expected(WideToUTF16(L"\x69\x131")); |
| 99 | 112 |
| 100 std::string default_locale(uloc_getDefault()); | 113 ScopedSetICUDefaultLocale restore_object(uloc_getDefault()); |
| 101 i18n::SetICUDefaultLocale("en_US"); | 114 i18n::SetICUDefaultLocale("en_US"); |
| 102 EXPECT_EQ(turkish_expected, FoldCase(turkish)); | 115 EXPECT_EQ(turkish_expected, FoldCase(turkish)); |
| 103 | 116 |
| 104 i18n::SetICUDefaultLocale("tr"); | 117 i18n::SetICUDefaultLocale("tr"); |
| 105 EXPECT_EQ(turkish_expected, FoldCase(turkish)); | 118 EXPECT_EQ(turkish_expected, FoldCase(turkish)); |
| 106 | 119 |
| 107 // Test a case that gets bigger when processed. | 120 // Test a case that gets bigger when processed. |
| 108 // U+130 = LATIN CAPITAL LETTER I WITH DOT ABOVE gets folded to a lower case | 121 // U+130 = LATIN CAPITAL LETTER I WITH DOT ABOVE gets folded to a lower case |
| 109 // "i" followed by U+307 COMBINING DOT ABOVE. | 122 // "i" followed by U+307 COMBINING DOT ABOVE. |
| 110 EXPECT_EQ(WideToUTF16(L"i\u0307j"), FoldCase(WideToUTF16(L"\u0130j"))); | 123 EXPECT_EQ(WideToUTF16(L"i\u0307j"), FoldCase(WideToUTF16(L"\u0130j"))); |
| 111 | 124 |
| 112 // U+00DF (SHARP S) and U+1E9E (CAPIRAL SHARP S) are both folded to "ss". | 125 // U+00DF (SHARP S) and U+1E9E (CAPIRAL SHARP S) are both folded to "ss". |
| 113 EXPECT_EQ(ASCIIToUTF16("ssss"), FoldCase(WideToUTF16(L"\u00DF\u1E9E"))); | 126 EXPECT_EQ(ASCIIToUTF16("ssss"), FoldCase(WideToUTF16(L"\u00DF\u1E9E"))); |
| 114 } | 127 } |
| 115 | 128 |
| 116 } // namespace i18n | 129 } // namespace i18n |
| 117 } // namespace base | 130 } // namespace base |
| 118 | 131 |
| 119 | 132 |
| 120 | 133 |
| OLD | NEW |