OLD | NEW |
1 // Copyright (c) 2012 The Chromium Authors. All rights reserved. | 1 // Copyright (c) 2012 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 // File utilities that use the ICU library go in this file. | 5 // File utilities that use the ICU library go in this file. |
6 | 6 |
7 #include "base/i18n/file_util_icu.h" | 7 #include "base/i18n/file_util_icu.h" |
8 | 8 |
9 #include "base/files/file_path.h" | 9 #include "base/files/file_path.h" |
10 #include "base/i18n/icu_string_conversions.h" | 10 #include "base/i18n/icu_string_conversions.h" |
11 #include "base/i18n/string_compare.h" | 11 #include "base/i18n/string_compare.h" |
12 #include "base/logging.h" | 12 #include "base/logging.h" |
13 #include "base/memory/scoped_ptr.h" | 13 #include "base/memory/scoped_ptr.h" |
14 #include "base/memory/singleton.h" | 14 #include "base/memory/singleton.h" |
15 #include "base/strings/string_util.h" | 15 #include "base/strings/string_util.h" |
16 #include "base/strings/sys_string_conversions.h" | 16 #include "base/strings/sys_string_conversions.h" |
17 #include "base/strings/utf_string_conversions.h" | 17 #include "base/strings/utf_string_conversions.h" |
18 #include "build/build_config.h" | 18 #include "build/build_config.h" |
19 #include "third_party/icu/source/common/unicode/uniset.h" | 19 #include "third_party/icu/source/common/unicode/uniset.h" |
20 #include "third_party/icu/source/i18n/unicode/coll.h" | 20 #include "third_party/icu/source/i18n/unicode/coll.h" |
21 | 21 |
22 using base::string16; | 22 namespace base { |
| 23 namespace i18n { |
23 | 24 |
24 namespace { | 25 namespace { |
25 | 26 |
26 class IllegalCharacters { | 27 class IllegalCharacters { |
27 public: | 28 public: |
28 static IllegalCharacters* GetInstance() { | 29 static IllegalCharacters* GetInstance() { |
29 return Singleton<IllegalCharacters>::get(); | 30 return Singleton<IllegalCharacters>::get(); |
30 } | 31 } |
31 | 32 |
32 bool contains(UChar32 ucs4) { | 33 bool contains(UChar32 ucs4) { |
(...skipping 44 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
77 set->add(0xFDD0, 0xFDEF); | 78 set->add(0xFDD0, 0xFDEF); |
78 for (int i = 0; i <= 0x10; ++i) { | 79 for (int i = 0; i <= 0x10; ++i) { |
79 int plane_base = 0x10000 * i; | 80 int plane_base = 0x10000 * i; |
80 set->add(plane_base + 0xFFFE, plane_base + 0xFFFF); | 81 set->add(plane_base + 0xFFFE, plane_base + 0xFFFF); |
81 } | 82 } |
82 set->freeze(); | 83 set->freeze(); |
83 } | 84 } |
84 | 85 |
85 } // namespace | 86 } // namespace |
86 | 87 |
87 namespace file_util { | |
88 | |
89 bool IsFilenameLegal(const string16& file_name) { | 88 bool IsFilenameLegal(const string16& file_name) { |
90 return IllegalCharacters::GetInstance()->containsNone(file_name); | 89 return IllegalCharacters::GetInstance()->containsNone(file_name); |
91 } | 90 } |
92 | 91 |
93 void ReplaceIllegalCharactersInPath(base::FilePath::StringType* file_name, | 92 void ReplaceIllegalCharactersInPath(FilePath::StringType* file_name, |
94 char replace_char) { | 93 char replace_char) { |
95 DCHECK(file_name); | 94 DCHECK(file_name); |
96 | 95 |
97 DCHECK(!(IllegalCharacters::GetInstance()->contains(replace_char))); | 96 DCHECK(!(IllegalCharacters::GetInstance()->contains(replace_char))); |
98 | 97 |
99 // Remove leading and trailing whitespace. | 98 // Remove leading and trailing whitespace. |
100 base::TrimWhitespace(*file_name, base::TRIM_ALL, file_name); | 99 TrimWhitespace(*file_name, TRIM_ALL, file_name); |
101 | 100 |
102 IllegalCharacters* illegal = IllegalCharacters::GetInstance(); | 101 IllegalCharacters* illegal = IllegalCharacters::GetInstance(); |
103 int cursor = 0; // The ICU macros expect an int. | 102 int cursor = 0; // The ICU macros expect an int. |
104 while (cursor < static_cast<int>(file_name->size())) { | 103 while (cursor < static_cast<int>(file_name->size())) { |
105 int char_begin = cursor; | 104 int char_begin = cursor; |
106 uint32 code_point; | 105 uint32 code_point; |
107 #if defined(OS_MACOSX) | 106 #if defined(OS_MACOSX) |
108 // Mac uses UTF-8 encoding for filenames. | 107 // Mac uses UTF-8 encoding for filenames. |
109 U8_NEXT(file_name->data(), cursor, static_cast<int>(file_name->length()), | 108 U8_NEXT(file_name->data(), cursor, static_cast<int>(file_name->length()), |
110 code_point); | 109 code_point); |
(...skipping 15 matching lines...) Expand all Loading... |
126 if (illegal->contains(code_point)) { | 125 if (illegal->contains(code_point)) { |
127 file_name->replace(char_begin, cursor - char_begin, 1, replace_char); | 126 file_name->replace(char_begin, cursor - char_begin, 1, replace_char); |
128 // We just made the potentially multi-byte/word char into one that only | 127 // We just made the potentially multi-byte/word char into one that only |
129 // takes one byte/word, so need to adjust the cursor to point to the next | 128 // takes one byte/word, so need to adjust the cursor to point to the next |
130 // character again. | 129 // character again. |
131 cursor = char_begin + 1; | 130 cursor = char_begin + 1; |
132 } | 131 } |
133 } | 132 } |
134 } | 133 } |
135 | 134 |
136 bool LocaleAwareCompareFilenames(const base::FilePath& a, | 135 bool LocaleAwareCompareFilenames(const FilePath& a, const FilePath& b) { |
137 const base::FilePath& b) { | |
138 UErrorCode error_code = U_ZERO_ERROR; | 136 UErrorCode error_code = U_ZERO_ERROR; |
139 // Use the default collator. The default locale should have been properly | 137 // Use the default collator. The default locale should have been properly |
140 // set by the time this constructor is called. | 138 // set by the time this constructor is called. |
141 scoped_ptr<icu::Collator> collator(icu::Collator::createInstance(error_code)); | 139 scoped_ptr<icu::Collator> collator(icu::Collator::createInstance(error_code)); |
142 DCHECK(U_SUCCESS(error_code)); | 140 DCHECK(U_SUCCESS(error_code)); |
143 // Make it case-sensitive. | 141 // Make it case-sensitive. |
144 collator->setStrength(icu::Collator::TERTIARY); | 142 collator->setStrength(icu::Collator::TERTIARY); |
145 | 143 |
146 #if defined(OS_WIN) | 144 #if defined(OS_WIN) |
147 return base::i18n::CompareString16WithCollator(collator.get(), | 145 return CompareString16WithCollator(collator.get(), |
148 base::WideToUTF16(a.value()), base::WideToUTF16(b.value())) == UCOL_LESS; | 146 WideToUTF16(a.value()), WideToUTF16(b.value())) == UCOL_LESS; |
149 | 147 |
150 #elif defined(OS_POSIX) | 148 #elif defined(OS_POSIX) |
151 // On linux, the file system encoding is not defined. We assume | 149 // On linux, the file system encoding is not defined. We assume |
152 // SysNativeMBToWide takes care of it. | 150 // SysNativeMBToWide takes care of it. |
153 return base::i18n::CompareString16WithCollator( | 151 return CompareString16WithCollator( |
154 collator.get(), | 152 collator.get(), |
155 base::WideToUTF16(base::SysNativeMBToWide(a.value().c_str())), | 153 WideToUTF16(SysNativeMBToWide(a.value().c_str())), |
156 base::WideToUTF16(base::SysNativeMBToWide(b.value().c_str())) | 154 WideToUTF16(SysNativeMBToWide(b.value().c_str()))) == UCOL_LESS; |
157 ) == UCOL_LESS; | |
158 #else | 155 #else |
159 #error Not implemented on your system | 156 #error Not implemented on your system |
160 #endif | 157 #endif |
161 } | 158 } |
162 | 159 |
163 void NormalizeFileNameEncoding(base::FilePath* file_name) { | 160 void NormalizeFileNameEncoding(FilePath* file_name) { |
164 #if defined(OS_CHROMEOS) | 161 #if defined(OS_CHROMEOS) |
165 std::string normalized_str; | 162 std::string normalized_str; |
166 if (base::ConvertToUtf8AndNormalize(file_name->BaseName().value(), | 163 if (ConvertToUtf8AndNormalize(file_name->BaseName().value(), |
167 base::kCodepageUTF8, | 164 kCodepageUTF8, |
168 &normalized_str)) { | 165 &normalized_str)) { |
169 *file_name = file_name->DirName().Append(base::FilePath(normalized_str)); | 166 *file_name = file_name->DirName().Append(FilePath(normalized_str)); |
170 } | 167 } |
171 #endif | 168 #endif |
172 } | 169 } |
173 | 170 |
174 } // namespace | 171 } // namespace i18n |
| 172 } // namespace base |
OLD | NEW |