OLD | NEW |
1 // Copyright (c) 2009 The Chromium Authors. All rights reserved. | 1 // Copyright (c) 2009 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 #ifndef BASE_UTF_STRING_CONVERSION_UTILS_H_ | 5 #ifndef BASE_UTF_STRING_CONVERSION_UTILS_H_ |
6 #define BASE_UTF_STRING_CONVERSION_UTILS_H_ | 6 #define BASE_UTF_STRING_CONVERSION_UTILS_H_ |
7 | 7 |
8 // This should only be used by the various UTF string conversion files. | 8 // This should only be used by the various UTF string conversion files. |
9 | 9 |
10 #include "base/string16.h" | 10 #include "base/string16.h" |
11 | 11 |
12 namespace base { | 12 namespace base { |
13 | 13 |
14 inline bool IsValidCodepoint(uint32 code_point) { | 14 inline bool IsValidCodepoint(uint32 code_point) { |
15 // Excludes non-characters (U+FDD0..U+FDEF, and all codepoints ending in | 15 // Excludes the surrogate code points ([0xD800, 0xDFFF]) and |
16 // 0xFFFE or 0xFFFF), surrogate code points (U+D800..U+DFFF), and codepoints | 16 // codepoints larger than 0x10FFFF (the highest codepoint allowed). |
17 // larger than U+10FFFF (the highest codepoint allowed). | 17 // Non-characters and unassigned codepoints are allowed. |
18 return code_point < 0xD800u || (code_point >= 0xE000u && | 18 return code_point < 0xD800u || |
19 code_point < 0xFDD0u) || (code_point > 0xFDEFu && | 19 (code_point >= 0xE000u && code_point <= 0x10FFFFu); |
20 code_point <= 0x10FFFFu && (code_point & 0xFFFEu) != 0xFFFEu); | |
21 } | 20 } |
22 | 21 |
23 // ReadUnicodeCharacter -------------------------------------------------------- | 22 // ReadUnicodeCharacter -------------------------------------------------------- |
24 | 23 |
25 // Reads a UTF-8 stream, placing the next code point into the given output | 24 // Reads a UTF-8 stream, placing the next code point into the given output |
26 // |*code_point|. |src| represents the entire string to read, and |*char_index| | 25 // |*code_point|. |src| represents the entire string to read, and |*char_index| |
27 // is the character offset within the string to start reading at. |*char_index| | 26 // is the character offset within the string to start reading at. |*char_index| |
28 // will be updated to index the last character read, such that incrementing it | 27 // will be updated to index the last character read, such that incrementing it |
29 // (as in a for loop) will take the reader to the next character. | 28 // (as in a for loop) will take the reader to the next character. |
30 // | 29 // |
(...skipping 47 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
78 void PrepareForUTF8Output(const CHAR* src, size_t src_len, std::string* output); | 77 void PrepareForUTF8Output(const CHAR* src, size_t src_len, std::string* output); |
79 | 78 |
80 // Prepares an output buffer (containing either UTF-16 or -32 data) given some | 79 // Prepares an output buffer (containing either UTF-16 or -32 data) given some |
81 // UTF-8 input that will be converted to it. See PrepareForUTF8Output(). | 80 // UTF-8 input that will be converted to it. See PrepareForUTF8Output(). |
82 template<typename STRING> | 81 template<typename STRING> |
83 void PrepareForUTF16Or32Output(const char* src, size_t src_len, STRING* output); | 82 void PrepareForUTF16Or32Output(const char* src, size_t src_len, STRING* output); |
84 | 83 |
85 } // namespace base | 84 } // namespace base |
86 | 85 |
87 #endif // BASE_UTF_STRING_CONVERSION_UTILS_H_ | 86 #endif // BASE_UTF_STRING_CONVERSION_UTILS_H_ |
OLD | NEW |