ceph/src/arrow/matlab/src/util/unicode_conversion.cc

   1 // Licensed to the Apache Software Foundation (ASF) under one
   2 // or more contributor license agreements.  See the NOTICE file
   3 // distributed with this work for additional information
   4 // regarding copyright ownership.  The ASF licenses this file
   5 // to you under the Apache License, Version 2.0 (the
   6 // "License"); you may not use this file except in compliance
   7 // with the License.  You may obtain a copy of the License at
   8 //
   9 //   http://www.apache.org/licenses/LICENSE-2.0
  10 //
  11 // Unless required by applicable law or agreed to in writing,
  12 // software distributed under the License is distributed on an
  13 // "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
  14 // KIND, either express or implied.  See the License for the
  15 // specific language governing permissions and limitations
  16 // under the License.
  17
  18 #include <locale> /* for std::wstring_convert */
  19 #include <codecvt> /* for std::codecvt_utf8_utf16 */
  20
  21 #include "unicode_conversion.h"
  22
  23 namespace arrow {
  24 namespace matlab {
  25 namespace util {
  26
  27 mxArray* ConvertUTF8StringToUTF16CharMatrix(const std::string& utf8_string) {
  28   // Get pointers to the start and end of the std::string data.
  29   const char* string_start = utf8_string.c_str();
  30   const char* string_end = string_start + utf8_string.length();
  31
  32   // Due to this issue on MSVC: https://stackoverflow.com/q/32055357 we cannot
  33   // directly use a destination type of char16_t.
  34 #if _MSC_VER >= 1900
  35   using CharType = int16_t;
  36 #else
  37   using CharType = char16_t;
  38 #endif
  39   using ConverterType = std::codecvt_utf8_utf16<CharType>;
  40   std::wstring_convert<ConverterType, CharType> code_converter{};
  41
  42   std::basic_string<CharType> utf16_string;
  43   try {
  44     utf16_string = code_converter.from_bytes(string_start, string_end);
  45   } catch (...) {
  46     // In the case that any error occurs, just try returning a string in the
  47     // user's current locale instead.
  48     return mxCreateString(string_start);
  49   }
  50
  51   // Store the converter UTF-16 string in a mxCharMatrix and return it.
  52   const mwSize dimensions[2] = {1, utf16_string.size()};
  53   mxArray* character_matrix = mxCreateCharArray(2, dimensions);
  54   mxChar* character_matrix_pointer = mxGetChars(character_matrix);
  55   std::copy(utf16_string.data(), utf16_string.data() + utf16_string.size(),
  56       character_matrix_pointer);
  57
  58   return character_matrix;
  59 }
  60
  61 }  // namespace util
  62 }  // namespace matlab
  63 }  // namespace arrow