让jsoncpp库能够支持直接解析unicode编码的字符串

最新推荐文章于 2020-12-07 17:58:56 发布

转载最新推荐文章于 2020-12-07 17:58:56 发布 · 5.7k 阅读

文章标签：

#编码 #json-cpp #c++ #unicode #utf8

c++ 同时被 3 个专栏收录

4 篇文章

订阅专栏

MFC

2 篇文章

订阅专栏

Jsoncpp

2 篇文章

订阅专栏

本文介绍如何修改JSONcpp源代码使其支持Unicode编码的字符串。通过调整codePointToUTF8函数，可以实现对特定Unicode范围内的字符进行正确的UTF-8转换。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

看了看，jsoncpp里面的代码，发现其实并不难，代码很有规矩、易懂，一下就能定位到关键的位置：
json_tool.h中的codePointToUTF8函数。

贴上这个函数的原型来看看就能明白了：

/// Converts a unicode code-point to UTF-8.
static inline JSONCPP_STRING codePointToUTF8(unsigned int cp) {
  JSONCPP_STRING result;

  // based on description from http://en.wikipedia.org/wiki/UTF-8

  if (cp <= 0x7f) {
    result.resize(1);
    result[0] = static_cast<char>(cp);
  } else if (cp <= 0x7FF) {
    result.resize(2);
    result[1] = static_cast<char>(0x80 | (0x3f & cp));
    result[0] = static_cast<char>(0xC0 | (0x1f & (cp >> 6)));
  } else if (cp <= 0xFFFF) {
    result.resize(3);
    result[2] = static_cast<char>(0x80 | (0x3f & cp));
    result[1] = static_cast<char>(0x80 | (0x3f & (cp >> 6)));
    result[0] = static_cast<char>(0xE0 | (0xf & (cp >> 12)));
  } else if (cp <= 0x10FFFF) {
    result.resize(4);
    result[3] = static_cast<char>(0x80 | (0x3f & cp));
    result[2] = static_cast<char>(0x80 | (0x3f & (cp >> 6)));
    result[1] = static_cast<char>(0x80 | (0x3f & (cp >> 12)));
    result[0] = static_cast<char>(0xF0 | (0x7 & (cp >> 18)));
  }

  return result;
}

稍微改改就可以在json解析的时候直接支持unicode编码的字符串了：

/// Converts a unicode code-point to UTF-8.
static inline JSONCPP_STRING codePointToUTF8(unsigned int cp) {
  JSONCPP_STRING result;

  // based on description from http://en.wikipedia.org/wiki/UTF-8

  if (cp <= 0x7f) {
    result.resize(1);
    result[0] = static_cast<char>(cp);
  } else if (cp <= 0x7FF) {
    result.resize(2);
    result[1] = static_cast<char>(0x80 | (0x3f & cp));
    result[0] = static_cast<char>(0xC0 | (0x1f & (cp >> 6)));
  } else if (cp <= 0xFFFF) {
      if (cp >= 0x4E00 && cp <= 0x9FA5 || (cp >= 0xF900 && cp <= 0xFA2D))
      {
          wchar_t src[2] = { 0 };
          char dest[5] = { 0 };
          src[0] = static_cast<wchar_t>(cp);
          std::string curLocale = setlocale(LC_ALL, NULL);
          setlocale(LC_ALL, "chs");
          wcstombs_s(NULL, dest, 5, src, 2);
          result = dest;
          setlocale(LC_ALL, curLocale.c_str());
      } else {
          result.resize(3);
          result[2] = static_cast<char>(0x80 | (0x3f & cp));
          result[1] = static_cast<char>(0x80 | (0x3f & (cp >> 6)));
          result[0] = static_cast<char>(0xE0 | (0xf & (cp >> 12)));
      }
  } else if (cp <= 0x10FFFF) {
    result.resize(4);
    result[3] = static_cast<char>(0x80 | (0x3f & cp));
    result[2] = static_cast<char>(0x80 | (0x3f & (cp >> 6)));
    result[1] = static_cast<char>(0x80 | (0x3f & (cp >> 12)));
    result[0] = static_cast<char>(0xF0 | (0x7 & (cp >> 18)));
  }

  return result;
}