1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/toolkit/crashreporter/google-breakpad/src/common/string_conversion.cc Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,155 @@
1.4 +// Copyright (c) 2006, Google Inc.
1.5 +// All rights reserved.
1.6 +//
1.7 +// Redistribution and use in source and binary forms, with or without
1.8 +// modification, are permitted provided that the following conditions are
1.9 +// met:
1.10 +//
1.11 +// * Redistributions of source code must retain the above copyright
1.12 +// notice, this list of conditions and the following disclaimer.
1.13 +// * Redistributions in binary form must reproduce the above
1.14 +// copyright notice, this list of conditions and the following disclaimer
1.15 +// in the documentation and/or other materials provided with the
1.16 +// distribution.
1.17 +// * Neither the name of Google Inc. nor the names of its
1.18 +// contributors may be used to endorse or promote products derived from
1.19 +// this software without specific prior written permission.
1.20 +//
1.21 +// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
1.22 +// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
1.23 +// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
1.24 +// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
1.25 +// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
1.26 +// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
1.27 +// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
1.28 +// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
1.29 +// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
1.30 +// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
1.31 +// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
1.32 +
1.33 +#include <string.h>
1.34 +
1.35 +#include "common/convert_UTF.h"
1.36 +#include "common/scoped_ptr.h"
1.37 +#include "common/string_conversion.h"
1.38 +#include "common/using_std_string.h"
1.39 +
1.40 +namespace google_breakpad {
1.41 +
1.42 +using std::vector;
1.43 +
1.44 +void UTF8ToUTF16(const char *in, vector<uint16_t> *out) {
1.45 + size_t source_length = strlen(in);
1.46 + const UTF8 *source_ptr = reinterpret_cast<const UTF8 *>(in);
1.47 + const UTF8 *source_end_ptr = source_ptr + source_length;
1.48 + // Erase the contents and zero fill to the expected size
1.49 + out->clear();
1.50 + out->insert(out->begin(), source_length, 0);
1.51 + uint16_t *target_ptr = &(*out)[0];
1.52 + uint16_t *target_end_ptr = target_ptr + out->capacity() * sizeof(uint16_t);
1.53 + ConversionResult result = ConvertUTF8toUTF16(&source_ptr, source_end_ptr,
1.54 + &target_ptr, target_end_ptr,
1.55 + strictConversion);
1.56 +
1.57 + // Resize to be the size of the # of converted characters + NULL
1.58 + out->resize(result == conversionOK ? target_ptr - &(*out)[0] + 1: 0);
1.59 +}
1.60 +
1.61 +int UTF8ToUTF16Char(const char *in, int in_length, uint16_t out[2]) {
1.62 + const UTF8 *source_ptr = reinterpret_cast<const UTF8 *>(in);
1.63 + const UTF8 *source_end_ptr = source_ptr + sizeof(char);
1.64 + uint16_t *target_ptr = out;
1.65 + uint16_t *target_end_ptr = target_ptr + 2 * sizeof(uint16_t);
1.66 + out[0] = out[1] = 0;
1.67 +
1.68 + // Process one character at a time
1.69 + while (1) {
1.70 + ConversionResult result = ConvertUTF8toUTF16(&source_ptr, source_end_ptr,
1.71 + &target_ptr, target_end_ptr,
1.72 + strictConversion);
1.73 +
1.74 + if (result == conversionOK)
1.75 + return static_cast<int>(source_ptr - reinterpret_cast<const UTF8 *>(in));
1.76 +
1.77 + // Add another character to the input stream and try again
1.78 + source_ptr = reinterpret_cast<const UTF8 *>(in);
1.79 + ++source_end_ptr;
1.80 +
1.81 + if (source_end_ptr > reinterpret_cast<const UTF8 *>(in) + in_length)
1.82 + break;
1.83 + }
1.84 +
1.85 + return 0;
1.86 +}
1.87 +
1.88 +void UTF32ToUTF16(const wchar_t *in, vector<uint16_t> *out) {
1.89 + size_t source_length = wcslen(in);
1.90 + const UTF32 *source_ptr = reinterpret_cast<const UTF32 *>(in);
1.91 + const UTF32 *source_end_ptr = source_ptr + source_length;
1.92 + // Erase the contents and zero fill to the expected size
1.93 + out->clear();
1.94 + out->insert(out->begin(), source_length, 0);
1.95 + uint16_t *target_ptr = &(*out)[0];
1.96 + uint16_t *target_end_ptr = target_ptr + out->capacity() * sizeof(uint16_t);
1.97 + ConversionResult result = ConvertUTF32toUTF16(&source_ptr, source_end_ptr,
1.98 + &target_ptr, target_end_ptr,
1.99 + strictConversion);
1.100 +
1.101 + // Resize to be the size of the # of converted characters + NULL
1.102 + out->resize(result == conversionOK ? target_ptr - &(*out)[0] + 1: 0);
1.103 +}
1.104 +
1.105 +void UTF32ToUTF16Char(wchar_t in, uint16_t out[2]) {
1.106 + const UTF32 *source_ptr = reinterpret_cast<const UTF32 *>(&in);
1.107 + const UTF32 *source_end_ptr = source_ptr + 1;
1.108 + uint16_t *target_ptr = out;
1.109 + uint16_t *target_end_ptr = target_ptr + 2 * sizeof(uint16_t);
1.110 + out[0] = out[1] = 0;
1.111 + ConversionResult result = ConvertUTF32toUTF16(&source_ptr, source_end_ptr,
1.112 + &target_ptr, target_end_ptr,
1.113 + strictConversion);
1.114 +
1.115 + if (result != conversionOK) {
1.116 + out[0] = out[1] = 0;
1.117 + }
1.118 +}
1.119 +
1.120 +static inline uint16_t Swap(uint16_t value) {
1.121 + return (value >> 8) | static_cast<uint16_t>(value << 8);
1.122 +}
1.123 +
1.124 +string UTF16ToUTF8(const vector<uint16_t> &in, bool swap) {
1.125 + const UTF16 *source_ptr = &in[0];
1.126 + scoped_ptr<uint16_t> source_buffer;
1.127 +
1.128 + // If we're to swap, we need to make a local copy and swap each byte pair
1.129 + if (swap) {
1.130 + int idx = 0;
1.131 + source_buffer.reset(new uint16_t[in.size()]);
1.132 + UTF16 *source_buffer_ptr = source_buffer.get();
1.133 + for (vector<uint16_t>::const_iterator it = in.begin();
1.134 + it != in.end(); ++it, ++idx)
1.135 + source_buffer_ptr[idx] = Swap(*it);
1.136 +
1.137 + source_ptr = source_buffer.get();
1.138 + }
1.139 +
1.140 + // The maximum expansion would be 4x the size of the input string.
1.141 + const UTF16 *source_end_ptr = source_ptr + in.size();
1.142 + size_t target_capacity = in.size() * 4;
1.143 + scoped_array<UTF8> target_buffer(new UTF8[target_capacity]);
1.144 + UTF8 *target_ptr = target_buffer.get();
1.145 + UTF8 *target_end_ptr = target_ptr + target_capacity;
1.146 + ConversionResult result = ConvertUTF16toUTF8(&source_ptr, source_end_ptr,
1.147 + &target_ptr, target_end_ptr,
1.148 + strictConversion);
1.149 +
1.150 + if (result == conversionOK) {
1.151 + const char *targetPtr = reinterpret_cast<const char *>(target_buffer.get());
1.152 + return targetPtr;
1.153 + }
1.154 +
1.155 + return "";
1.156 +}
1.157 +
1.158 +} // namespace google_breakpad
