1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/security/sandbox/chromium/base/strings/utf_string_conversion_utils.h Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,97 @@
1.4 +// Copyright (c) 2011 The Chromium Authors. All rights reserved.
1.5 +// Use of this source code is governed by a BSD-style license that can be
1.6 +// found in the LICENSE file.
1.7 +
1.8 +#ifndef BASE_STRINGS_UTF_STRING_CONVERSION_UTILS_H_
1.9 +#define BASE_STRINGS_UTF_STRING_CONVERSION_UTILS_H_
1.10 +
1.11 +// This should only be used by the various UTF string conversion files.
1.12 +
1.13 +#include "base/base_export.h"
1.14 +#include "base/strings/string16.h"
1.15 +
1.16 +namespace base {
1.17 +
1.18 +inline bool IsValidCodepoint(uint32 code_point) {
1.19 + // Excludes the surrogate code points ([0xD800, 0xDFFF]) and
1.20 + // codepoints larger than 0x10FFFF (the highest codepoint allowed).
1.21 + // Non-characters and unassigned codepoints are allowed.
1.22 + return code_point < 0xD800u ||
1.23 + (code_point >= 0xE000u && code_point <= 0x10FFFFu);
1.24 +}
1.25 +
1.26 +inline bool IsValidCharacter(uint32 code_point) {
1.27 + // Excludes non-characters (U+FDD0..U+FDEF, and all codepoints ending in
1.28 + // 0xFFFE or 0xFFFF) from the set of valid code points.
1.29 + return code_point < 0xD800u || (code_point >= 0xE000u &&
1.30 + code_point < 0xFDD0u) || (code_point > 0xFDEFu &&
1.31 + code_point <= 0x10FFFFu && (code_point & 0xFFFEu) != 0xFFFEu);
1.32 +}
1.33 +
1.34 +// ReadUnicodeCharacter --------------------------------------------------------
1.35 +
1.36 +// Reads a UTF-8 stream, placing the next code point into the given output
1.37 +// |*code_point|. |src| represents the entire string to read, and |*char_index|
1.38 +// is the character offset within the string to start reading at. |*char_index|
1.39 +// will be updated to index the last character read, such that incrementing it
1.40 +// (as in a for loop) will take the reader to the next character.
1.41 +//
1.42 +// Returns true on success. On false, |*code_point| will be invalid.
1.43 +BASE_EXPORT bool ReadUnicodeCharacter(const char* src,
1.44 + int32 src_len,
1.45 + int32* char_index,
1.46 + uint32* code_point_out);
1.47 +
1.48 +// Reads a UTF-16 character. The usage is the same as the 8-bit version above.
1.49 +BASE_EXPORT bool ReadUnicodeCharacter(const char16* src,
1.50 + int32 src_len,
1.51 + int32* char_index,
1.52 + uint32* code_point);
1.53 +
1.54 +#if defined(WCHAR_T_IS_UTF32)
1.55 +// Reads UTF-32 character. The usage is the same as the 8-bit version above.
1.56 +BASE_EXPORT bool ReadUnicodeCharacter(const wchar_t* src,
1.57 + int32 src_len,
1.58 + int32* char_index,
1.59 + uint32* code_point);
1.60 +#endif // defined(WCHAR_T_IS_UTF32)
1.61 +
1.62 +// WriteUnicodeCharacter -------------------------------------------------------
1.63 +
1.64 +// Appends a UTF-8 character to the given 8-bit string. Returns the number of
1.65 +// bytes written.
1.66 +// TODO(brettw) Bug 79631: This function should not be exposed.
1.67 +BASE_EXPORT size_t WriteUnicodeCharacter(uint32 code_point,
1.68 + std::string* output);
1.69 +
1.70 +// Appends the given code point as a UTF-16 character to the given 16-bit
1.71 +// string. Returns the number of 16-bit values written.
1.72 +BASE_EXPORT size_t WriteUnicodeCharacter(uint32 code_point, string16* output);
1.73 +
1.74 +#if defined(WCHAR_T_IS_UTF32)
1.75 +// Appends the given UTF-32 character to the given 32-bit string. Returns the
1.76 +// number of 32-bit values written.
1.77 +inline size_t WriteUnicodeCharacter(uint32 code_point, std::wstring* output) {
1.78 + // This is the easy case, just append the character.
1.79 + output->push_back(code_point);
1.80 + return 1;
1.81 +}
1.82 +#endif // defined(WCHAR_T_IS_UTF32)
1.83 +
1.84 +// Generalized Unicode converter -----------------------------------------------
1.85 +
1.86 +// Guesses the length of the output in UTF-8 in bytes, clears that output
1.87 +// string, and reserves that amount of space. We assume that the input
1.88 +// character types are unsigned, which will be true for UTF-16 and -32 on our
1.89 +// systems.
1.90 +template<typename CHAR>
1.91 +void PrepareForUTF8Output(const CHAR* src, size_t src_len, std::string* output);
1.92 +
1.93 +// Prepares an output buffer (containing either UTF-16 or -32 data) given some
1.94 +// UTF-8 input that will be converted to it. See PrepareForUTF8Output().
1.95 +template<typename STRING>
1.96 +void PrepareForUTF16Or32Output(const char* src, size_t src_len, STRING* output);
1.97 +
1.98 +} // namespace base
1.99 +
1.100 +#endif // BASE_STRINGS_UTF_STRING_CONVERSION_UTILS_H_
