michael@0: // Copyright (c) 2006, Google Inc. michael@0: // All rights reserved. michael@0: // michael@0: // Redistribution and use in source and binary forms, with or without michael@0: // modification, are permitted provided that the following conditions are michael@0: // met: michael@0: // michael@0: // * Redistributions of source code must retain the above copyright michael@0: // notice, this list of conditions and the following disclaimer. michael@0: // * Redistributions in binary form must reproduce the above michael@0: // copyright notice, this list of conditions and the following disclaimer michael@0: // in the documentation and/or other materials provided with the michael@0: // distribution. michael@0: // * Neither the name of Google Inc. nor the names of its michael@0: // contributors may be used to endorse or promote products derived from michael@0: // this software without specific prior written permission. michael@0: // michael@0: // THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS michael@0: // "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT michael@0: // LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR michael@0: // A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT michael@0: // OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, michael@0: // SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT michael@0: // LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, michael@0: // DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY michael@0: // THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT michael@0: // (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE michael@0: // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. michael@0: michael@0: #include michael@0: michael@0: #include "common/convert_UTF.h" michael@0: #include "common/scoped_ptr.h" michael@0: #include "common/string_conversion.h" michael@0: #include "common/using_std_string.h" michael@0: michael@0: namespace google_breakpad { michael@0: michael@0: using std::vector; michael@0: michael@0: void UTF8ToUTF16(const char *in, vector *out) { michael@0: size_t source_length = strlen(in); michael@0: const UTF8 *source_ptr = reinterpret_cast(in); michael@0: const UTF8 *source_end_ptr = source_ptr + source_length; michael@0: // Erase the contents and zero fill to the expected size michael@0: out->clear(); michael@0: out->insert(out->begin(), source_length, 0); michael@0: uint16_t *target_ptr = &(*out)[0]; michael@0: uint16_t *target_end_ptr = target_ptr + out->capacity() * sizeof(uint16_t); michael@0: ConversionResult result = ConvertUTF8toUTF16(&source_ptr, source_end_ptr, michael@0: &target_ptr, target_end_ptr, michael@0: strictConversion); michael@0: michael@0: // Resize to be the size of the # of converted characters + NULL michael@0: out->resize(result == conversionOK ? target_ptr - &(*out)[0] + 1: 0); michael@0: } michael@0: michael@0: int UTF8ToUTF16Char(const char *in, int in_length, uint16_t out[2]) { michael@0: const UTF8 *source_ptr = reinterpret_cast(in); michael@0: const UTF8 *source_end_ptr = source_ptr + sizeof(char); michael@0: uint16_t *target_ptr = out; michael@0: uint16_t *target_end_ptr = target_ptr + 2 * sizeof(uint16_t); michael@0: out[0] = out[1] = 0; michael@0: michael@0: // Process one character at a time michael@0: while (1) { michael@0: ConversionResult result = ConvertUTF8toUTF16(&source_ptr, source_end_ptr, michael@0: &target_ptr, target_end_ptr, michael@0: strictConversion); michael@0: michael@0: if (result == conversionOK) michael@0: return static_cast(source_ptr - reinterpret_cast(in)); michael@0: michael@0: // Add another character to the input stream and try again michael@0: source_ptr = reinterpret_cast(in); michael@0: ++source_end_ptr; michael@0: michael@0: if (source_end_ptr > reinterpret_cast(in) + in_length) michael@0: break; michael@0: } michael@0: michael@0: return 0; michael@0: } michael@0: michael@0: void UTF32ToUTF16(const wchar_t *in, vector *out) { michael@0: size_t source_length = wcslen(in); michael@0: const UTF32 *source_ptr = reinterpret_cast(in); michael@0: const UTF32 *source_end_ptr = source_ptr + source_length; michael@0: // Erase the contents and zero fill to the expected size michael@0: out->clear(); michael@0: out->insert(out->begin(), source_length, 0); michael@0: uint16_t *target_ptr = &(*out)[0]; michael@0: uint16_t *target_end_ptr = target_ptr + out->capacity() * sizeof(uint16_t); michael@0: ConversionResult result = ConvertUTF32toUTF16(&source_ptr, source_end_ptr, michael@0: &target_ptr, target_end_ptr, michael@0: strictConversion); michael@0: michael@0: // Resize to be the size of the # of converted characters + NULL michael@0: out->resize(result == conversionOK ? target_ptr - &(*out)[0] + 1: 0); michael@0: } michael@0: michael@0: void UTF32ToUTF16Char(wchar_t in, uint16_t out[2]) { michael@0: const UTF32 *source_ptr = reinterpret_cast(&in); michael@0: const UTF32 *source_end_ptr = source_ptr + 1; michael@0: uint16_t *target_ptr = out; michael@0: uint16_t *target_end_ptr = target_ptr + 2 * sizeof(uint16_t); michael@0: out[0] = out[1] = 0; michael@0: ConversionResult result = ConvertUTF32toUTF16(&source_ptr, source_end_ptr, michael@0: &target_ptr, target_end_ptr, michael@0: strictConversion); michael@0: michael@0: if (result != conversionOK) { michael@0: out[0] = out[1] = 0; michael@0: } michael@0: } michael@0: michael@0: static inline uint16_t Swap(uint16_t value) { michael@0: return (value >> 8) | static_cast(value << 8); michael@0: } michael@0: michael@0: string UTF16ToUTF8(const vector &in, bool swap) { michael@0: const UTF16 *source_ptr = &in[0]; michael@0: scoped_ptr source_buffer; michael@0: michael@0: // If we're to swap, we need to make a local copy and swap each byte pair michael@0: if (swap) { michael@0: int idx = 0; michael@0: source_buffer.reset(new uint16_t[in.size()]); michael@0: UTF16 *source_buffer_ptr = source_buffer.get(); michael@0: for (vector::const_iterator it = in.begin(); michael@0: it != in.end(); ++it, ++idx) michael@0: source_buffer_ptr[idx] = Swap(*it); michael@0: michael@0: source_ptr = source_buffer.get(); michael@0: } michael@0: michael@0: // The maximum expansion would be 4x the size of the input string. michael@0: const UTF16 *source_end_ptr = source_ptr + in.size(); michael@0: size_t target_capacity = in.size() * 4; michael@0: scoped_array target_buffer(new UTF8[target_capacity]); michael@0: UTF8 *target_ptr = target_buffer.get(); michael@0: UTF8 *target_end_ptr = target_ptr + target_capacity; michael@0: ConversionResult result = ConvertUTF16toUTF8(&source_ptr, source_end_ptr, michael@0: &target_ptr, target_end_ptr, michael@0: strictConversion); michael@0: michael@0: if (result == conversionOK) { michael@0: const char *targetPtr = reinterpret_cast(target_buffer.get()); michael@0: return targetPtr; michael@0: } michael@0: michael@0: return ""; michael@0: } michael@0: michael@0: } // namespace google_breakpad