diff options
author | brettw@chromium.org <brettw@chromium.org@0039d316-1c4b-4281-b951-d872f2087c98> | 2013-02-07 03:59:06 +0000 |
---|---|---|
committer | brettw@chromium.org <brettw@chromium.org@0039d316-1c4b-4281-b951-d872f2087c98> | 2013-02-07 03:59:06 +0000 |
commit | a3f72189102fc85a7f9cfe60c61e124a2677f0ea (patch) | |
tree | fa5699e92f87a628740fd9b88960b6449541055d /base/utf_string_conversion_utils.h | |
parent | 3d350326fd4def19e343890c55c5388e370c7c2f (diff) | |
download | chromium_src-a3f72189102fc85a7f9cfe60c61e124a2677f0ea.zip chromium_src-a3f72189102fc85a7f9cfe60c61e124a2677f0ea.tar.gz chromium_src-a3f72189102fc85a7f9cfe60c61e124a2677f0ea.tar.bz2 |
Move utf_offset_string_conversions and utf_string_conversion_utils to strings.
Review URL: https://codereview.chromium.org/12087115
git-svn-id: svn://svn.chromium.org/chrome/trunk/src@181183 0039d316-1c4b-4281-b951-d872f2087c98
Diffstat (limited to 'base/utf_string_conversion_utils.h')
-rw-r--r-- | base/utf_string_conversion_utils.h | 97 |
1 files changed, 0 insertions, 97 deletions
diff --git a/base/utf_string_conversion_utils.h b/base/utf_string_conversion_utils.h deleted file mode 100644 index 17e04f1..0000000 --- a/base/utf_string_conversion_utils.h +++ /dev/null @@ -1,97 +0,0 @@ -// Copyright (c) 2011 The Chromium Authors. All rights reserved. -// Use of this source code is governed by a BSD-style license that can be -// found in the LICENSE file. - -#ifndef BASE_UTF_STRING_CONVERSION_UTILS_H_ -#define BASE_UTF_STRING_CONVERSION_UTILS_H_ - -// This should only be used by the various UTF string conversion files. - -#include "base/base_export.h" -#include "base/string16.h" - -namespace base { - -inline bool IsValidCodepoint(uint32 code_point) { - // Excludes the surrogate code points ([0xD800, 0xDFFF]) and - // codepoints larger than 0x10FFFF (the highest codepoint allowed). - // Non-characters and unassigned codepoints are allowed. - return code_point < 0xD800u || - (code_point >= 0xE000u && code_point <= 0x10FFFFu); -} - -inline bool IsValidCharacter(uint32 code_point) { - // Excludes non-characters (U+FDD0..U+FDEF, and all codepoints ending in - // 0xFFFE or 0xFFFF) from the set of valid code points. - return code_point < 0xD800u || (code_point >= 0xE000u && - code_point < 0xFDD0u) || (code_point > 0xFDEFu && - code_point <= 0x10FFFFu && (code_point & 0xFFFEu) != 0xFFFEu); -} - -// ReadUnicodeCharacter -------------------------------------------------------- - -// Reads a UTF-8 stream, placing the next code point into the given output -// |*code_point|. |src| represents the entire string to read, and |*char_index| -// is the character offset within the string to start reading at. |*char_index| -// will be updated to index the last character read, such that incrementing it -// (as in a for loop) will take the reader to the next character. -// -// Returns true on success. On false, |*code_point| will be invalid. -BASE_EXPORT bool ReadUnicodeCharacter(const char* src, - int32 src_len, - int32* char_index, - uint32* code_point_out); - -// Reads a UTF-16 character. The usage is the same as the 8-bit version above. -BASE_EXPORT bool ReadUnicodeCharacter(const char16* src, - int32 src_len, - int32* char_index, - uint32* code_point); - -#if defined(WCHAR_T_IS_UTF32) -// Reads UTF-32 character. The usage is the same as the 8-bit version above. -BASE_EXPORT bool ReadUnicodeCharacter(const wchar_t* src, - int32 src_len, - int32* char_index, - uint32* code_point); -#endif // defined(WCHAR_T_IS_UTF32) - -// WriteUnicodeCharacter ------------------------------------------------------- - -// Appends a UTF-8 character to the given 8-bit string. Returns the number of -// bytes written. -// TODO(brettw) Bug 79631: This function should not be exposed. -BASE_EXPORT size_t WriteUnicodeCharacter(uint32 code_point, - std::string* output); - -// Appends the given code point as a UTF-16 character to the given 16-bit -// string. Returns the number of 16-bit values written. -BASE_EXPORT size_t WriteUnicodeCharacter(uint32 code_point, string16* output); - -#if defined(WCHAR_T_IS_UTF32) -// Appends the given UTF-32 character to the given 32-bit string. Returns the -// number of 32-bit values written. -inline size_t WriteUnicodeCharacter(uint32 code_point, std::wstring* output) { - // This is the easy case, just append the character. - output->push_back(code_point); - return 1; -} -#endif // defined(WCHAR_T_IS_UTF32) - -// Generalized Unicode converter ----------------------------------------------- - -// Guesses the length of the output in UTF-8 in bytes, clears that output -// string, and reserves that amount of space. We assume that the input -// character types are unsigned, which will be true for UTF-16 and -32 on our -// systems. -template<typename CHAR> -void PrepareForUTF8Output(const CHAR* src, size_t src_len, std::string* output); - -// Prepares an output buffer (containing either UTF-16 or -32 data) given some -// UTF-8 input that will be converted to it. See PrepareForUTF8Output(). -template<typename STRING> -void PrepareForUTF16Or32Output(const char* src, size_t src_len, STRING* output); - -} // namespace base - -#endif // BASE_UTF_STRING_CONVERSION_UTILS_H_ |