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 #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 #pragma once | 7 #pragma once |
8 | 8 |
9 // This should only be used by the various UTF string conversion files. | 9 // This should only be used by the various UTF string conversion files. |
10 | 10 |
11 #include "base/base_api.h" | 11 #include "base/base_export.h" |
12 #include "base/string16.h" | 12 #include "base/string16.h" |
13 | 13 |
14 namespace base { | 14 namespace base { |
15 | 15 |
16 inline bool IsValidCodepoint(uint32 code_point) { | 16 inline bool IsValidCodepoint(uint32 code_point) { |
17 // Excludes the surrogate code points ([0xD800, 0xDFFF]) and | 17 // Excludes the surrogate code points ([0xD800, 0xDFFF]) and |
18 // codepoints larger than 0x10FFFF (the highest codepoint allowed). | 18 // codepoints larger than 0x10FFFF (the highest codepoint allowed). |
19 // Non-characters and unassigned codepoints are allowed. | 19 // Non-characters and unassigned codepoints are allowed. |
20 return code_point < 0xD800u || | 20 return code_point < 0xD800u || |
21 (code_point >= 0xE000u && code_point <= 0x10FFFFu); | 21 (code_point >= 0xE000u && code_point <= 0x10FFFFu); |
22 } | 22 } |
23 | 23 |
24 inline bool IsValidCharacter(uint32 code_point) { | 24 inline bool IsValidCharacter(uint32 code_point) { |
25 // Excludes non-characters (U+FDD0..U+FDEF, and all codepoints ending in | 25 // Excludes non-characters (U+FDD0..U+FDEF, and all codepoints ending in |
26 // 0xFFFE or 0xFFFF) from the set of valid code points. | 26 // 0xFFFE or 0xFFFF) from the set of valid code points. |
27 return code_point < 0xD800u || (code_point >= 0xE000u && | 27 return code_point < 0xD800u || (code_point >= 0xE000u && |
28 code_point < 0xFDD0u) || (code_point > 0xFDEFu && | 28 code_point < 0xFDD0u) || (code_point > 0xFDEFu && |
29 code_point <= 0x10FFFFu && (code_point & 0xFFFEu) != 0xFFFEu); | 29 code_point <= 0x10FFFFu && (code_point & 0xFFFEu) != 0xFFFEu); |
30 } | 30 } |
31 | 31 |
32 // ReadUnicodeCharacter -------------------------------------------------------- | 32 // ReadUnicodeCharacter -------------------------------------------------------- |
33 | 33 |
34 // Reads a UTF-8 stream, placing the next code point into the given output | 34 // Reads a UTF-8 stream, placing the next code point into the given output |
35 // |*code_point|. |src| represents the entire string to read, and |*char_index| | 35 // |*code_point|. |src| represents the entire string to read, and |*char_index| |
36 // is the character offset within the string to start reading at. |*char_index| | 36 // is the character offset within the string to start reading at. |*char_index| |
37 // will be updated to index the last character read, such that incrementing it | 37 // will be updated to index the last character read, such that incrementing it |
38 // (as in a for loop) will take the reader to the next character. | 38 // (as in a for loop) will take the reader to the next character. |
39 // | 39 // |
40 // Returns true on success. On false, |*code_point| will be invalid. | 40 // Returns true on success. On false, |*code_point| will be invalid. |
41 BASE_API bool ReadUnicodeCharacter(const char* src, | 41 BASE_EXPORT bool ReadUnicodeCharacter(const char* src, |
42 int32 src_len, | 42 int32 src_len, |
43 int32* char_index, | 43 int32* char_index, |
44 uint32* code_point_out); | 44 uint32* code_point_out); |
45 | 45 |
46 // Reads a UTF-16 character. The usage is the same as the 8-bit version above. | 46 // Reads a UTF-16 character. The usage is the same as the 8-bit version above. |
47 BASE_API bool ReadUnicodeCharacter(const char16* src, | 47 BASE_EXPORT bool ReadUnicodeCharacter(const char16* src, |
48 int32 src_len, | 48 int32 src_len, |
49 int32* char_index, | 49 int32* char_index, |
50 uint32* code_point); | 50 uint32* code_point); |
51 | 51 |
52 #if defined(WCHAR_T_IS_UTF32) | 52 #if defined(WCHAR_T_IS_UTF32) |
53 // Reads UTF-32 character. The usage is the same as the 8-bit version above. | 53 // Reads UTF-32 character. The usage is the same as the 8-bit version above. |
54 BASE_API bool ReadUnicodeCharacter(const wchar_t* src, | 54 BASE_EXPORT bool ReadUnicodeCharacter(const wchar_t* src, |
55 int32 src_len, | 55 int32 src_len, |
56 int32* char_index, | 56 int32* char_index, |
57 uint32* code_point); | 57 uint32* code_point); |
58 #endif // defined(WCHAR_T_IS_UTF32) | 58 #endif // defined(WCHAR_T_IS_UTF32) |
59 | 59 |
60 // WriteUnicodeCharacter ------------------------------------------------------- | 60 // WriteUnicodeCharacter ------------------------------------------------------- |
61 | 61 |
62 // Appends a UTF-8 character to the given 8-bit string. Returns the number of | 62 // Appends a UTF-8 character to the given 8-bit string. Returns the number of |
63 // bytes written. | 63 // bytes written. |
64 // TODO(brettw) Bug 79631: This function should not be exposed. | 64 // TODO(brettw) Bug 79631: This function should not be exposed. |
65 BASE_API size_t WriteUnicodeCharacter(uint32 code_point, std::string* output); | 65 BASE_EXPORT size_t WriteUnicodeCharacter(uint32 code_point, |
| 66 std::string* output); |
66 | 67 |
67 // Appends the given code point as a UTF-16 character to the given 16-bit | 68 // Appends the given code point as a UTF-16 character to the given 16-bit |
68 // string. Returns the number of 16-bit values written. | 69 // string. Returns the number of 16-bit values written. |
69 size_t WriteUnicodeCharacter(uint32 code_point, string16* output); | 70 size_t WriteUnicodeCharacter(uint32 code_point, string16* output); |
70 | 71 |
71 #if defined(WCHAR_T_IS_UTF32) | 72 #if defined(WCHAR_T_IS_UTF32) |
72 // Appends the given UTF-32 character to the given 32-bit string. Returns the | 73 // Appends the given UTF-32 character to the given 32-bit string. Returns the |
73 // number of 32-bit values written. | 74 // number of 32-bit values written. |
74 inline size_t WriteUnicodeCharacter(uint32 code_point, std::wstring* output) { | 75 inline size_t WriteUnicodeCharacter(uint32 code_point, std::wstring* output) { |
75 // This is the easy case, just append the character. | 76 // This is the easy case, just append the character. |
(...skipping 12 matching lines...) Expand all Loading... |
88 void PrepareForUTF8Output(const CHAR* src, size_t src_len, std::string* output); | 89 void PrepareForUTF8Output(const CHAR* src, size_t src_len, std::string* output); |
89 | 90 |
90 // Prepares an output buffer (containing either UTF-16 or -32 data) given some | 91 // Prepares an output buffer (containing either UTF-16 or -32 data) given some |
91 // UTF-8 input that will be converted to it. See PrepareForUTF8Output(). | 92 // UTF-8 input that will be converted to it. See PrepareForUTF8Output(). |
92 template<typename STRING> | 93 template<typename STRING> |
93 void PrepareForUTF16Or32Output(const char* src, size_t src_len, STRING* output); | 94 void PrepareForUTF16Or32Output(const char* src, size_t src_len, STRING* output); |
94 | 95 |
95 } // namespace base | 96 } // namespace base |
96 | 97 |
97 #endif // BASE_UTF_STRING_CONVERSION_UTILS_H_ | 98 #endif // BASE_UTF_STRING_CONVERSION_UTILS_H_ |
OLD | NEW |