本机c++中的备用方法Encoding.Unicode.GetBytes

Question

需要在本地C++中实现Encoding.Unicode.GetBytes

.NET实现:

Console.WriteLine("codePage number: " + Encoding.Unicode.CodePage.ToString());
Console.Write("string: ");
foreach (var ch in Encoding.Unicode.GetBytes("string"))
    Console.Write(ch.ToString("X") + "-");
Console.WriteLine();
Console.Write("строка: ");
foreach (var ch in Encoding.Unicode.GetBytes("строка"))
    Console.Write(ch.ToString("X") + "-");
Console.ReadLine();

.NET实现输出:

codePage number: 1200 
string: 73-0-74-0-72-0-69-0-6E-0-67-0 
строка: 41-4-42-4-40-4-3E-4-3A-4-30-4

如何实现这种方法(不使用boost, QT等)到c++ ?

---

我从Windows找到了这个方法:

#include <exception>
#include <iostream>
#include <ostream>
#include <string>
#include <Windows.h>
std::wstring ConvertToUTF16(const std::string & source, const UINT codePage)
{
    // Fail if an invalid input character is encountered
    static const DWORD conversionFlags = MB_ERR_INVALID_CHARS;
    // Require size for destination string
    int utf16Length = ::MultiByteToWideChar(
        codePage,           // code page for the conversion
        conversionFlags,    // flags
        source.c_str(),     // source string
        source.length(),    // length (in chars) of source string
        NULL,               // unused - no conversion done in this step
        0                   // request size of destination buffer, in wchar_t's
    );
    if (utf16Length == 0)
    {
        const DWORD error = ::GetLastError();
        throw std::exception(
            "MultiByteToWideChar() failed: Can't get length of destination UTF-16 string.",
            error);
    }
    // Allocate room for destination string
    std::wstring utf16Text;
    utf16Text.resize(utf16Length);
    // Convert to Unicode
    if (!::MultiByteToWideChar(
        codePage,           // code page for conversion
        0,                  // validation was done in previous call
        source.c_str(),     // source string
        source.length(),    // length (in chars) of source string
        &utf16Text[0],      // destination buffer
        utf16Text.length()  // size of destination buffer, in wchar_t's
    ))
    {
        const DWORD error = ::GetLastError();
        throw std::exception(
            "MultiByteToWideChar() failed: Can't convert to UTF-16 string.",
            error);
    }
    return utf16Text;
}
void main()
{
    try
    {
        // ASCII text
        std::string inText("string");
        // Unicode
        static const UINT codePage = 1200;
        // Convert to Unicode
        const std::wstring utf16Text = ConvertToUTF16(inText, codePage);
        // Show result
        for (size_t i = 0; i < utf16Text.size(); i++)
            printf("%X-", utf16Text[i]);
    }
    catch (const std::exception& e)
    {
        std::cerr << "*** ERROR:n";
        std::cerr << e.what();
        std::cerr << std::endl;
    }
    getchar();
}

但是MultiByteToWideChar没有返回1200代码页(Unicode)的字符串大小。

Answer 1

MultiByteToWideChar()的codepage参数指定输入 char数据的编码，因此可以将从编码转换为 UTF-16。在Win32编程中永远不要使用1200码页。

. net中的字符串用UTF-16编码。Encoding.Unicode.GetBytes()返回一个UTF-16LE编码的字节数组。因此字符数据按原样返回。

对于Windows上的UTF-16，使用基于wchar_t或char16_t的字符串(如std::wstring或std::u16string)。如果您需要一个UTF-16编码的字节数组，请分配2 * length字节(例如使用std::vector)并按原样复制原始字符串字符:

std::vector<BYTE> GetUnicodeBytes(const std::wstring &str)
{
    std::vector<BYTE> result;
    if (!str.empty())
    {
        result.resize(sizeof(wchar_t) * str.length());
        CopyMemory(&result[0], str.c_str(), result.size());
    }
    return result;
}

std::wcout << L"string: ";
for (auto ch: GetUnicodeBytes(L"string"))
    std::wcout << std::hex << (int)ch << L"-";
std::wcout << std::endl;
std::wcout << L"строка: ";
for (auto ch: GetUnicodeBytes(L"строка"))
    std::wcout << std::hex << (int)ch << L"-";
std::wcout << std::endl;

另外:

std::vector<BYTE> GetUnicodeBytes(const std::u16string &str)
{
    std::vector<BYTE> result;
    if (!str.empty())
    {
        result.resize(sizeof(char16_t) * str.length());
        CopyMemory(&result[0], str.c_str(), result.size());
    }
    return result;
}

std::wcout << L"string: ";
for (auto ch: GetUnicodeBytes(u"string"))
    std::wcout << std::hex << (int)ch << L"-";
std::wcout << std::endl;
std::wcout << L"строка: ";
for (auto ch: GetUnicodeBytes(u"строка"))
    std::wcout << std::hex << (int)ch << L"-";
std::wcout << std::endl;