14

我创建了这两种方法来将原生 utf-8 字符串 (char*) 转换为托管字符串，反之亦然。以下代码完成了这项工作：

public IntPtr NativeUtf8FromString(string managedString)
{
    byte[] buffer = Encoding.UTF8.GetBytes(managedString); // not null terminated
    Array.Resize(ref buffer, buffer.Length + 1);
    buffer[buffer.Length - 1] = 0; // terminating 0
    IntPtr nativeUtf8 = Marshal.AllocHGlobal(buffer.Length);
    Marshal.Copy(buffer, 0, nativeUtf8, buffer.Length);
    return nativeUtf8;
}

string StringFromNativeUtf8(IntPtr nativeUtf8)
{
    int size = 0;
    byte[] buffer = {};
    do
    {
        ++size;
        Array.Resize(ref buffer, size);
        Marshal.Copy(nativeUtf8, buffer, 0, size);
    } while (buffer[size - 1] != 0); // till 0 termination found

    if (1 == size)
    {
        return ""; // empty string
    }

    Array.Resize(ref buffer, size - 1); // remove terminating 0
    return Encoding.UTF8.GetString(buffer);
}

虽然 NativeUtf8FromString 没问题，但 StringFromNativeUtf8 是一团糟，但我可以运行的唯一安全代码。使用不安全的代码我可以使用一个字节*，但我不想要不安全的代码。还有另一种方法有人可以想到我不必为每个包含的字节复制字符串来找到 0 终止符。

我只是在这里添加未保存的代码：

public unsafe string StringFromNativeUtf8(IntPtr nativeUtf8)
{
    byte* bytes = (byte*)nativeUtf8.ToPointer();
    int size = 0;
    while (bytes[size] != 0)
    {
        ++size;
    }
    byte[] buffer = new byte[size];
    Marshal.Copy((IntPtr)nativeUtf8, buffer, 0, size);
    return Encoding.UTF8.GetString(buffer);
}

如您所见，它并不丑陋，只是需要不安全。

4

3 回答 3

36

只需执行与 strlen() 完全相同的操作即可。请考虑保留缓冲区，代码确实会匆忙生成垃圾。

    public static IntPtr NativeUtf8FromString(string managedString) {
        int len = Encoding.UTF8.GetByteCount(managedString);
        byte[] buffer = new byte[len + 1];
        Encoding.UTF8.GetBytes(managedString, 0, managedString.Length, buffer, 0);
        IntPtr nativeUtf8 = Marshal.AllocHGlobal(buffer.Length);
        Marshal.Copy(buffer, 0, nativeUtf8, buffer.Length);
        return nativeUtf8;
    }

    public static string StringFromNativeUtf8(IntPtr nativeUtf8) {
        int len = 0;
        while (Marshal.ReadByte(nativeUtf8, len) != 0) ++len;
        byte[] buffer = new byte[len];
        Marshal.Copy(nativeUtf8, buffer, 0, buffer.Length);
        return Encoding.UTF8.GetString(buffer);
    }
于 2012-05-27T12:29:43.870 回答
9

比 Hans 的解决方案略快（少 1 个缓冲区副本）：

private unsafe IntPtr AllocConvertManagedStringToNativeUtf8(string input) {
    fixed (char* pInput = input) {
        var len = Encoding.UTF8.GetByteCount(pInput, input.Length);
        var pResult = (byte*)Marshal.AllocHGlobal(len + 1).ToPointer();
        var bytesWritten = Encoding.UTF8.GetBytes(pInput, input.Length, pResult, len);
        Trace.Assert(len == bytesWritten);
        pResult[len] = 0;
        return (IntPtr)pResult;
    }
}

private unsafe string MarshalNativeUtf8ToManagedString(IntPtr pStringUtf8)
    => MarshalNativeUtf8ToManagedString((byte*)pStringUtf8);

private unsafe string MarshalNativeUtf8ToManagedString(byte* pStringUtf8) {
    var len = 0;
    while (pStringUtf8[len] != 0) len++;
    return Encoding.UTF8.GetString(pStringUtf8, len);
}

这是我演示往返字符串：

var input = "Hello, World!";
var native = AllocConvertManagedStringToNativeUtf8(input);
var copy = MarshalNativeUtf8ToManagedString(native);
Marshal.FreeHGlobal(native); // don't leak unmanaged memory!
Trace.Assert(input == copy); // prove they're equal!
于 2019-10-12T21:07:12.880 回答
6

Marshal.PtrToStringUTF8和Marshal.StringToCoTaskMemUTF8在 .NET 5 (.NET Standard 2.1) 中添加

于 2021-01-24T18:11:04.427 回答