将 UTF-16 转换为 UTF-8

Question

我目前使用 VC++ 2008 MFC。由于 PostgreSQL 不支持 UTF-16（Windows 使用的 Unicode 编码），我需要在存储之前将字符串从 UTF-16 转换为 UTF-8。

这是我的代码片段。

// demo.cpp : Defines the entry point for the console application.
//

#include "stdafx.h"
#include "demo.h"
#include "Utils.h"
#include <iostream>

#ifdef _DEBUG
#define new DEBUG_NEW
#endif


// The one and only application object

CWinApp theApp;

using namespace std;

int _tmain(int argc, TCHAR* argv[], TCHAR* envp[])
{
    int nRetCode = 0;

    // initialize MFC and print and error on failure
    if (!AfxWinInit(::GetModuleHandle(NULL), NULL, ::GetCommandLine(), 0))
    {
        // TODO: change error code to suit your needs
        _tprintf(_T("Fatal Error: MFC initialization failed\n"));
        nRetCode = 1;
    }
    else
    {
        // TODO: code your application's behavior here.
    }

    CString utf16 = _T("Hello");
    std::cout << utf16.GetLength() << std::endl;
    CStringA utf8 = UTF8Util::ConvertUTF16ToUTF8(utf16);
    std::cout << utf8.GetLength() << std::endl;
    getchar();
    return nRetCode;
}

和转换函数。

namespace UTF8Util
{
//----------------------------------------------------------------------------
// FUNCTION: ConvertUTF8ToUTF16
// DESC: Converts Unicode UTF-8 text to Unicode UTF-16 (Windows default).
//----------------------------------------------------------------------------
CStringW ConvertUTF8ToUTF16( __in const CHAR * pszTextUTF8 )
{
    //
    // Special case of NULL or empty input string
    //
    if ( (pszTextUTF8 == NULL) || (*pszTextUTF8 == '\0') )
    {
        // Return empty string
        return L"";
    }

    //
    // Consider CHAR's count corresponding to total input string length,
    // including end-of-string (\0) character
    //
    const size_t cchUTF8Max = INT_MAX - 1;
    size_t cchUTF8;
    HRESULT hr = ::StringCchLengthA( pszTextUTF8, cchUTF8Max, &cchUTF8 );

    if ( FAILED( hr ) )
    {
        AtlThrow( hr );
    }

    // Consider also terminating \0
    ++cchUTF8;

    // Convert to 'int' for use with MultiByteToWideChar API
    int cbUTF8 = static_cast<int>( cchUTF8 );

    //
    // Get size of destination UTF-16 buffer, in WCHAR's
    //
    int cchUTF16 = ::MultiByteToWideChar(
        CP_UTF8,                // convert from UTF-8
        MB_ERR_INVALID_CHARS,   // error on invalid chars
        pszTextUTF8,            // source UTF-8 string
        cbUTF8,                 // total length of source UTF-8 string,
                                // in CHAR's (= bytes), including end-of-string \0
        NULL,                   // unused - no conversion done in this step
        0                       // request size of destination buffer, in WCHAR's
        );

    ATLASSERT( cchUTF16 != 0 );

    if ( cchUTF16 == 0 )
    {
        AtlThrowLastWin32();
    }

    //
    // Allocate destination buffer to store UTF-16 string
    //
    CStringW strUTF16;
    WCHAR * pszUTF16 = strUTF16.GetBuffer( cchUTF16 );

    //
    // Do the conversion from UTF-8 to UTF-16
    //

    int result = ::MultiByteToWideChar(
        CP_UTF8,                // convert from UTF-8
        MB_ERR_INVALID_CHARS,   // error on invalid chars
        pszTextUTF8,            // source UTF-8 string
        cbUTF8,                 // total length of source UTF-8 string,
                                // in CHAR's (= bytes), including end-of-string \0
        pszUTF16,               // destination buffer
        cchUTF16                // size of destination buffer, in WCHAR's
        );

    ATLASSERT( result != 0 );

    if ( result == 0 )
    {
        AtlThrowLastWin32();
    }

    // Release internal CString buffer
    strUTF16.ReleaseBuffer();

    // Return resulting UTF16 string
    return strUTF16;
}

//----------------------------------------------------------------------------
// FUNCTION: ConvertUTF16ToUTF8
// DESC: Converts Unicode UTF-16 (Windows default) text to Unicode UTF-8.
//----------------------------------------------------------------------------
CStringA ConvertUTF16ToUTF8( __in const WCHAR * pszTextUTF16 )
{
    //
    // Special case of NULL or empty input string
    //
    if ( (pszTextUTF16 == NULL) || (*pszTextUTF16 == L'\0') )
    {
        // Return empty string
        return "";
    }

    //
    // Consider WCHAR's count corresponding to total input string length,
    // including end-of-string (L'\0') character.
    //
    const size_t cchUTF16Max = INT_MAX - 1;
    size_t cchUTF16;
    HRESULT hr = ::StringCchLengthW( pszTextUTF16, cchUTF16Max, &cchUTF16 );

    if ( FAILED( hr ) )
    {
        AtlThrow( hr );
    }

    // Consider also terminating \0
    ++cchUTF16;

    //
    // WC_ERR_INVALID_CHARS flag is set to fail if invalid input character
    // is encountered.
    // This flag is supported on Windows Vista and later.
    // Don't use it on Windows XP and previous.
    //

#if (WINVER >= 0x0600)
    DWORD dwConversionFlags = WC_ERR_INVALID_CHARS;
#else
    DWORD dwConversionFlags = 0;
#endif

    //
    // Get size of destination UTF-8 buffer, in CHAR's (= bytes)
    //
    int cbUTF8 = ::WideCharToMultiByte(
        CP_UTF8,                // convert to UTF-8
        dwConversionFlags,      // specify conversion behavior
        pszTextUTF16,           // source UTF-16 string
        static_cast<int>( cchUTF16 ),   // total source string length, in WCHAR's,
                                        // including end-of-string \0
        NULL,                   // unused - no conversion required in this step
        0,                      // request buffer size
        NULL, NULL              // unused
        );

    ATLASSERT( cbUTF8 != 0 );

    if ( cbUTF8 == 0 )
    {
        AtlThrowLastWin32();
    }

    //
    // Allocate destination buffer for UTF-8 string
    //
    CStringA strUTF8;
    int cchUTF8 = cbUTF8; // sizeof(CHAR) = 1 byte
    CHAR * pszUTF8 = strUTF8.GetBuffer( cchUTF8 );

    //
    // Do the conversion from UTF-16 to UTF-8
    //
    int result = ::WideCharToMultiByte(
        CP_UTF8,                // convert to UTF-8
        dwConversionFlags,      // specify conversion behavior
        pszTextUTF16,           // source UTF-16 string
        static_cast<int>( cchUTF16 ),   // total source string length, in WCHAR's,
                                        // including end-of-string \0
        pszUTF8,                // destination buffer
        cbUTF8,                 // destination buffer size, in bytes
        NULL, NULL              // unused
        ); 

    ATLASSERT( result != 0 );

    if ( result == 0 )
    {
        AtlThrowLastWin32();
    }

    // Release internal CString buffer
    strUTF8.ReleaseBuffer();

    // Return resulting UTF-8 string
    return strUTF8;
}

} // namespace UTF8Util

但是，在运行时，我收到异常

ATLASSERT( cbUTF8 != 0 );

在尝试获取目标 UTF-8 缓冲区的大小时

1. 我错过了什么？
2. 如果我使用中文字符进行测试，如何验证生成的 UTF-8 字符串是否正确？

Answer 1

您还可以使用 ATL 字符串转换宏 - 从 UTF- 进行转换16 到 UTF-8 使用 CW2A 并传递 CP_UTF8 作为代码页，例如：

CW2A utf8(buffer, CP_UTF8);
const char* data = utf8.m_psz;

Answer 2

问题是您指定了 WC_ERR_INVALID_CHARS 标志：

Windows Vista 及更高版本：如果遇到无效的输入字符，则会失败。如果未设置此标志，该函数会默默地删除非法代码点。调用 GetLastError 返回 ERROR_NO_UNICODE_TRANSLATION。请注意，仅当 CodePage 指定为 CP_UTF8 或 54936（对于 Windows Vista 及更高版本）时，此标志才适用。它不能与其他代码页值一起使用。

你的转换函数看起来很长。这个对你来说怎么样？

//----------------------------------------------------------------------------
// FUNCTION: ConvertUTF16ToUTF8
// DESC: Converts Unicode UTF-16 (Windows default) text to Unicode UTF-8.
//----------------------------------------------------------------------------
CStringA ConvertUTF16ToUTF8( __in LPCWSTR pszTextUTF16 ) {
    if (pszTextUTF16 == NULL) return "";

    int utf16len = wcslen(pszTextUTF16);
    int utf8len = WideCharToMultiByte(CP_UTF8, 0, pszTextUTF16, utf16len, 
        NULL, 0, NULL, NULL );

    CArray<CHAR> buffer;
    buffer.SetSize(utf8len+1);
    buffer.SetAt(utf8len, '\0');

    WideCharToMultiByte(CP_UTF8, 0, pszTextUTF16, utf16len, 
        buffer.GetData(), utf8len, 0, 0 );

    return buffer.GetData();
}

我看到您使用一个名为 StringCchLengthW 的函数来获取输出缓冲区所需的长度。我看到的大多数地方都建议使用 WideCharToMultiByte 函数本身来告诉您它需要多少个 CHAR。

编辑：
正如 Rob 指出的，您可以将 CW2A 与 CP_UTF8 代码页一起使用：

CStringA str = CW2A(wStr, CP_UTF8);

当我编辑时，我可以回答您的第二个问题：

如何验证生成的 UTF-8 字符串是否正确？

将其写入文本文件，然后在 Mozilla Firefox 或等效程序中打开它。在“视图”菜单中，您可以转到“字符编码”并手动切换到 UTF-8（假设 Firefox 一开始就没有正确猜测）。将其与具有相同文本的 UTF-16 文档进行比较，看看是否有任何差异。