Conversion in .net: Native Utf-8 <-> Managed String
Marshal.PtrToStringUTF8 and Marshal.StringToCoTaskMemUTF8 were added in .NET 5 (.NET Standard 2.1)
Slightly faster than Hans' solution (1 less buffer copy):
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);
}
Here's I demo round-tripping a string:
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!
Just perform the exact same operation strlen() performs. Do consider keeping the buffer around, the code does generate garbage in a hurry.
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);
}