17down voteaccepted

Here's some code. Only lightly tested and there's probably a few improvements. Call this function to convert a UTF-8 string to a UTF-16 wstring. If it thinks the input string is not UTF-8 then it will throw an exception, otherwise it returns the equivalent UTF-16 wstring.

std::wstring utf8_to_utf16(const std::string& utf8)
{
std::vector<unsigned long> unicode;
size_t i = 0;
while (i < utf8.size())
{
unsigned long uni;
size_t todo;
bool error = false;
unsigned char ch = utf8[i++];
if (ch <= 0x7F)
{
uni = ch;
todo = 0;
}
else if (ch <= 0xBF)
{
throw std::logic_error("not a UTF-8 string");
}
else if (ch <= 0xDF)
{
uni = ch&0x1F;
todo = 1;
}
else if (ch <= 0xEF)
{
uni = ch&0x0F;
todo = 2;
}
else if (ch <= 0xF7)
{
uni = ch&0x07;
todo = 3;
}
else
{
throw std::logic_error("not a UTF-8 string");
}
for (size_t j = 0; j < todo; ++j)
{
if (i == utf8.size())
throw std::logic_error("not a UTF-8 string");
unsigned char ch = utf8[i++];
if (ch < 0x80 || ch > 0xBF)
throw std::logic_error("not a UTF-8 string");
uni <<= 6;
uni += ch & 0x3F;
}
if (uni >= 0xD800 && uni <= 0xDFFF)
throw std::logic_error("not a UTF-8 string");
if (uni > 0x10FFFF)
throw std::logic_error("not a UTF-8 string");
unicode.push_back(uni);
}
std::wstring utf16;
for (size_t i = 0; i < unicode.size(); ++i)
{
unsigned long uni = unicode[i];
if (uni <= 0xFFFF)
{
utf16 += (wchar_t)uni;
}
else
{
uni -= 0x10000;
utf16 += (wchar_t)((uni >> 10) + 0xD800);
utf16 += (wchar_t)((uni & 0x3FF) + 0xDC00);
}
}
return utf16;
}

http://stackoverflow.com/questions/7153935/how-to-convert-utf-8-stdstring-to-utf-16-stdwstring

#pragma once
#include <string> #ifdef tstring
#error "\"tstring\" Macro has been defined."
#else
#ifdef _UNICODE
#define tstring wstring
#else
#define tstring string
#endif
#endif class EncodingConverter
{
public:
static int AnsiStrToWideStr(std::string& strSrc, std::wstring& strDest)
{
int nLen = strSrc.length() + ;
int nRet = ; nLen *= sizeof(wchar_t); wchar_t* pszW = new wchar_t[nLen];
memset(pszW, , nLen); nRet = MultiByteToWideChar(CP_ACP, , strSrc.c_str(), -, pszW, nLen); strDest = pszW;
delete[] pszW; return nRet;
}; static int WideStrToAnsiStr(std::wstring& strSrc, std::string& strDest)
{
int nLen = strSrc.length() + ;
int nRet = ; nLen *= sizeof(wchar_t); char* pszA = new char[nLen];
memset(pszA, , nLen); nRet = WideCharToMultiByte(CP_ACP, , strSrc.c_str(), -, pszA, nLen, NULL, NULL); strDest = pszA;
delete[] pszA; return nRet;
}; static int AnsiStrToTStr(std::string& strSrc, std::tstring& strDest)
{
int nRet = ; #ifdef _UNICODE
nRet = AnsiStrToWideStr(strSrc, strDest);
#else
strDest = strSrc;
nRet = strDest.length();
#endif return nRet;
}; static int TStrToAnsiStr(std::tstring& strSrc, std::string& strDest)
{
int nRet = ; #ifdef _UNICODE
nRet = WideStrToAnsiStr(strSrc, strDest);
#else
strDest = strSrc;
nRet = strDest.length();
#endif return nRet;
}; static int WideStrToTStr(std::wstring& strSrc, std::tstring& strDest)
{
int nRet = ; #ifdef _UNICODE
strDest = strSrc;
nRet = strDest.length();
#else
nRet = WideStrToAnsiStr(strSrc, strDest);
#endif return nRet;
}; static int TStrToWideStr(std::tstring& strSrc, std::wstring& strDest)
{
int nRet = ; #ifdef _UNICODE
strDest = strSrc;
nRet = strDest.length();
#else
nRet = AnsiStrToWideStr(strSrc, strDest);
#endif return nRet;
}; static std::string ToAnsiString(const wchar_t* lpStr)
{
std::wstring wide_string = lpStr;
std::string ansi_string; WideStrToAnsiStr(wide_string, ansi_string);
return ansi_string;
}; static std::string ToAnsiString(const char* lpStr)
{
return std::string(lpStr);
}; static std::wstring ToWideString(const wchar_t* lpStr)
{
return std::wstring(lpStr);
}; static std::wstring ToWideString(const char* lpStr)
{
std::string ansi_string = lpStr;
std::wstring wide_string; AnsiStrToWideStr(ansi_string, wide_string);
return wide_string;
}; static std::tstring ToTString(const char* lpStr)
{
#ifdef _UNICODE
return ToWideString(lpStr);
#else
return ToAnsiString(lpStr);
#endif
}; static std::tstring ToTString(const wchar_t* lpStr)
{
#ifdef _UNICODE
return ToWideString(lpStr);
#else
return ToAnsiString(lpStr);
#endif
}; static int WideStrToUtf8Str(std::wstring& strSrc, std::string& strDest)
{
int nRet = ;
int nLen = ; nLen = WideCharToMultiByte(CP_UTF8, , strSrc.c_str(), -, NULL, , NULL, NULL); char * lpUtf8Str = new char[nLen+];
memset(lpUtf8Str, , nLen);
nRet = WideCharToMultiByte(CP_UTF8, , strSrc.c_str(), -, lpUtf8Str, nLen, NULL, NULL);
strDest = lpUtf8Str;
delete[] lpUtf8Str; return nRet;
}; static int AnsiStrToUtf8Str(std::string& strSrc, std::string& strDest)
{
int nRet = ;
std::wstring wide_string; nRet = AnsiStrToWideStr(strSrc, wide_string);
nRet = WideStrToUtf8Str(wide_string, strDest); return nRet;
}; static int Utf8StrToWideStr(const std::string& strSrc, std::wstring& strDest)
{
int nRet = ;
int nLen = ; nLen = MultiByteToWideChar(CP_UTF8, , strSrc.c_str(), -, NULL, ); wchar_t* lpWideStr = new wchar_t[nLen];
memset(lpWideStr, , nLen*sizeof(lpWideStr[]));
nRet = MultiByteToWideChar(CP_UTF8, , strSrc.c_str(), -, lpWideStr, nLen);
strDest = lpWideStr;
delete[] lpWideStr; return nRet;
}; static int Utf8StrToAnsiStr(const std::string& strSrc, std::string& strDest)
{
int nRet = ;
std::wstring wide_string; nRet = Utf8StrToWideStr(strSrc, wide_string);
nRet = WideStrToAnsiStr(wide_string, strDest); return nRet;
}; static int Utf8StrToTStr(const std::string& strSrc, std::tstring& strDest)
{
#ifdef UNICODE
return Utf8StrToWideStr(strSrc, strDest);
#else
return Utf8StrToAnsiStr(strSrc, strDest);
#endif
}; static std::string ToUtf8String(const std::string& str)
{
std::string ansi_string = str;
std::string utf8_string; AnsiStrToUtf8Str(ansi_string, utf8_string);
return utf8_string;
}; static std::string ToUtf8String(const std::wstring& str)
{
std::wstring wide_string = str;
std::string utf8_string; WideStrToUtf8Str(wide_string, utf8_string);
return utf8_string;
};
};

https://github.com/yaocoder/utility/blob/master/src/common/EncodingConverter.h

utf8_to_utf16的更多相关文章

  1. boost::xml——基本操作以及中文乱码解决方案 (续)

    本博文主要想说明以下两点: 1.对于上一篇的<boost::xml——基本操作以及中文乱码解决方案>解释,这篇博文基本解决了正确输入输出中英文问题,但是好像还没有解决修改中文出现乱码的问题 ...

  2. C++ MFC std::string转为 std::wstring

    std::string转为 std::wstring std::wstring UTF8_To_UTF16(const std::string& source) { unsigned long ...

  3. 谷歌拼音自带lua

    function fast_string_banji(argument) return {"快捷1", "快捷2", "快捷3", &quo ...

  4. 谷歌拼音输入法扩展API开发指南

    为了帮助开发者在谷歌拼音输入法的基本输入功能基础上,开发和定义更丰富的扩展输入功能,谷歌拼音输入法提供了以Lua脚本编程语言为基础的输入法扩展API.利用输入法扩展API,开发者可以编写自定义的输入功 ...

随机推荐

  1. Reactor构架模式--转载

    原文:http://cache.baiducontent.com/c?m=9f65cb4a8c8507ed4fece76310468a3b404380143c86964868d4e419ce3b464 ...

  2. HDU2056JAVA

    Rectangles Time Limit: 1000/1000 MS (Java/Others)    Memory Limit: 32768/32768 K (Java/Others)Total ...

  3. Shell脚本编程入门(一) 分类: 学习笔记 linux ubuntu 2015-07-09 21:06 29人阅读 评论(0) 收藏

    最近在学shell,记录一下. if语句的使用: 1.判断两个参数大小 #!/bin/sh #a test about if statement a=10 b=20 if [ $a -eq $b ]; ...

  4. 对于Maven管理的项目制定虚拟目录

    基于Maven管理的web项目结构: target目录是用来存放项目打包之后生成的文件的目录,此目录中的文件必须调用mvn clean package后才能生成, 如果把虚拟目录设置在此目录中,则每次 ...

  5. 【原创教程】一、Angular教程系列之认识angular

    为什么我会准备写这个原创教程系列? 写下这个标题之后,看着屏幕上空白的内容区,不知从何下手,想说的似乎有很多,似乎又没啥说的.有时候就会陷入这种矛盾中,有时候就是这样,于是,我下定决心这一次一定要把这 ...

  6. PHP ajax实现数组返回

    首先,我想要实这样一个功能, 当选择一个下拉框时,让其它三个文本框得到从服务器上返回的值!也就把返回的值,赋给那三个文本框! 我用的是jquery+php!! 由于我前台,后台,js,数据库采用的都是 ...

  7. VS2010打不开VS2012 .NET MVC 工程,及打开后部分模块加载不正确的解决办法

    转自http://www.xuebuyuan.com/2042634.html 首先,如果sln打开不正确,用(notepad++)打开sln 比如 VS2010的前两行为: Microsoft Vi ...

  8. Javascript基础学习(3)_对象和数组

    一.对象是一种无序的属性集合,每个属性都有自己的名字和值. 1.创建对象 花括号内逗号分隔 var person = { "Name" : "LiCheng", ...

  9. “jni.h”: No such file or directory

    VS2010解决方案: 进入 “包含目录“ 方式: 右键项目属性页-> 配置属性->VC++目录->包含目录 在”包含目录“中编辑 添加以下路径: C:\Program Files\ ...

  10. javascript 用函数实现“继承”

    一.知识储备: 1.枚举属性名称的函数: (1)for...in:可以在循环体中遍历对象中所有可枚举的属性(包括自有属性和继承属性) (2)Object.keys():返回数组(可枚举的自有属性) ( ...