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 3// found in the LICENSE file. 4 5#include "base/strings/utf_string_conversion_utils.h" 6 7#include "base/third_party/icu/icu_utf.h" 8#include "util/build_config.h" 9 10namespace base { 11 12// ReadUnicodeCharacter -------------------------------------------------------- 13 14bool ReadUnicodeCharacter(const char* src, 15 int32_t src_len, 16 int32_t* char_index, 17 uint32_t* code_point_out) { 18 // U8_NEXT expects to be able to use -1 to signal an error, so we must 19 // use a signed type for code_point. But this function returns false 20 // on error anyway, so code_point_out is unsigned. 21 int32_t code_point; 22 CBU8_NEXT(src, *char_index, src_len, code_point); 23 *code_point_out = static_cast<uint32_t>(code_point); 24 25 // The ICU macro above moves to the next char, we want to point to the last 26 // char consumed. 27 (*char_index)--; 28 29 // Validate the decoded value. 30 return IsValidCodepoint(code_point); 31} 32 33bool ReadUnicodeCharacter(const char16_t* src, 34 int32_t src_len, 35 int32_t* char_index, 36 uint32_t* code_point) { 37 if (CBU16_IS_SURROGATE(src[*char_index])) { 38 if (!CBU16_IS_SURROGATE_LEAD(src[*char_index]) || 39 *char_index + 1 >= src_len || !CBU16_IS_TRAIL(src[*char_index + 1])) { 40 // Invalid surrogate pair. 41 return false; 42 } 43 44 // Valid surrogate pair. 45 *code_point = 46 CBU16_GET_SUPPLEMENTARY(src[*char_index], src[*char_index + 1]); 47 (*char_index)++; 48 } else { 49 // Not a surrogate, just one 16-bit word. 50 *code_point = src[*char_index]; 51 } 52 53 return IsValidCodepoint(*code_point); 54} 55 56// WriteUnicodeCharacter ------------------------------------------------------- 57 58size_t WriteUnicodeCharacter(uint32_t code_point, std::string* output) { 59 if (code_point <= 0x7f) { 60 // Fast path the common case of one byte. 61 output->push_back(static_cast<char>(code_point)); 62 return 1; 63 } 64 65 // CBU8_APPEND_UNSAFE can append up to 4 bytes. 66 size_t char_offset = output->length(); 67 size_t original_char_offset = char_offset; 68 output->resize(char_offset + CBU8_MAX_LENGTH); 69 70 CBU8_APPEND_UNSAFE(&(*output)[0], char_offset, code_point); 71 72 // CBU8_APPEND_UNSAFE will advance our pointer past the inserted character, so 73 // it will represent the new length of the string. 74 output->resize(char_offset); 75 return char_offset - original_char_offset; 76} 77 78size_t WriteUnicodeCharacter(uint32_t code_point, std::u16string* output) { 79 if (CBU16_LENGTH(code_point) == 1) { 80 // Thie code point is in the Basic Multilingual Plane (BMP). 81 output->push_back(static_cast<char16_t>(code_point)); 82 return 1; 83 } 84 // Non-BMP characters use a double-character encoding. 85 size_t char_offset = output->length(); 86 output->resize(char_offset + CBU16_MAX_LENGTH); 87 CBU16_APPEND_UNSAFE(&(*output)[0], char_offset, code_point); 88 return CBU16_MAX_LENGTH; 89} 90 91// Generalized Unicode converter ----------------------------------------------- 92 93template <typename CHAR> 94void PrepareForUTF8Output(const CHAR* src, 95 size_t src_len, 96 std::string* output) { 97 output->clear(); 98 if (src_len == 0) 99 return; 100 if (src[0] < 0x80) { 101 // Assume that the entire input will be ASCII. 102 output->reserve(src_len); 103 } else { 104 // Assume that the entire input is non-ASCII and will have 3 bytes per char. 105 output->reserve(src_len * 3); 106 } 107} 108 109// Instantiate versions we know callers will need. 110template void PrepareForUTF8Output(const char16_t*, size_t, std::string*); 111 112template <typename STRING> 113void PrepareForUTF16Or32Output(const char* src, 114 size_t src_len, 115 STRING* output) { 116 output->clear(); 117 if (src_len == 0) 118 return; 119 if (static_cast<unsigned char>(src[0]) < 0x80) { 120 // Assume the input is all ASCII, which means 1:1 correspondence. 121 output->reserve(src_len); 122 } else { 123 // Otherwise assume that the UTF-8 sequences will have 2 bytes for each 124 // character. 125 output->reserve(src_len / 2); 126 } 127} 128 129// Instantiate versions we know callers will need. 130template void PrepareForUTF16Or32Output(const char*, size_t, std::u16string*); 131 132} // namespace base 133