Using .NET, how can you find the mime type of a file based on the file signature not the extension
I am looking for a simple way to get a mime type where the file extension is incorrect or not given, something similar to this question only in .Net.
回答1
In Urlmon.dll, there's a function called FindMimeFromData.
From the documentation
MIME type detection, or "data sniffing," refers to the process of determining an appropriate MIME type from binary data. The final result depends on a combination of server-supplied MIME type headers, file extension, and/or the data itself. Usually, only the first 256 bytes of data are significant.
So, read the first (up to) 256 bytes from the file and pass it to FindMimeFromData.
I suppose that's because docx is ostensibly a zip file.
Docx is a zip file, but the mimetype for .docx is "application/vnd.openxmlformats-officedocument.wordprocessingml.document". While this CAN be determined from a binary-only examination, it's probably not the most efficient way to do it, and in most cases you would have to read in more than the first 256 bytes.
回答2
I did use urlmon.dll in the end. I thought there would be an easier way but this works. I include the code to help anyone else and allow me to find it again if I need it.
using System.Runtime.InteropServices;
[DllImport(@"urlmon.dll", CharSet = CharSet.Auto)] private extern static System.UInt32 FindMimeFromData( System.UInt32 pBC, [MarshalAs(UnmanagedType.LPStr)] System.String pwzUrl, [MarshalAs(UnmanagedType.LPArray)] byte[] pBuffer, System.UInt32 cbSize, [MarshalAs(UnmanagedType.LPStr)] System.String pwzMimeProposed, System.UInt32 dwMimeFlags, out System.UInt32 ppwzMimeOut, System.UInt32 dwReserverd ); public static string getMimeFromFile(string filename) { if (!File.Exists(filename)) throw new FileNotFoundException(filename + " not found"); byte[] buffer = new byte[256]; using (FileStream fs = new FileStream(filename, FileMode.Open)) { if (fs.Length >= 256) fs.Read(buffer, 0, 256); else fs.Read(buffer, 0, (int)fs.Length); } try { System.UInt32 mimetype; FindMimeFromData(0, null, buffer, 256, null, 0, out mimetype, 0); System.IntPtr mimeTypePtr = new IntPtr(mimetype); string mime = Marshal.PtrToStringUni(mimeTypePtr); Marshal.FreeCoTaskMem(mimeTypePtr); return mime; } catch (Exception e) { return "unknown/unknown"; } }
回答3
Edit: Just use Mime Detective
I use byte array sequences to determine the correct MIME type of a given file. The advantage of this over just looking at the file extension of the file name is that if a user were to rename a file to bypass certain file type upload restrictions, the file name extension would fail to catch this. On the other hand, getting the file signature via byte array will stop this mischievous behavior from happening.
Here is an example in C#:
public class MimeType { private static readonly byte[] BMP = { 66, 77 }; private static readonly byte[] DOC = { 208, 207, 17, 224, 161, 177, 26, 225 }; private static readonly byte[] EXE_DLL = { 77, 90 }; private static readonly byte[] GIF = { 71, 73, 70, 56 }; private static readonly byte[] ICO = { 0, 0, 1, 0 }; private static readonly byte[] JPG = { 255, 216, 255 }; private static readonly byte[] MP3 = { 255, 251, 48 }; private static readonly byte[] OGG = { 79, 103, 103, 83, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0 }; private static readonly byte[] PDF = { 37, 80, 68, 70, 45, 49, 46 }; private static readonly byte[] PNG = { 137, 80, 78, 71, 13, 10, 26, 10, 0, 0, 0, 13, 73, 72, 68, 82 }; private static readonly byte[] RAR = { 82, 97, 114, 33, 26, 7, 0 }; private static readonly byte[] SWF = { 70, 87, 83 }; private static readonly byte[] TIFF = { 73, 73, 42, 0 }; private static readonly byte[] TORRENT = { 100, 56, 58, 97, 110, 110, 111, 117, 110, 99, 101 }; private static readonly byte[] TTF = { 0, 1, 0, 0, 0 }; private static readonly byte[] WAV_AVI = { 82, 73, 70, 70 }; private static readonly byte[] WMV_WMA = { 48, 38, 178, 117, 142, 102, 207, 17, 166, 217, 0, 170, 0, 98, 206, 108 }; private static readonly byte[] ZIP_DOCX = { 80, 75, 3, 4 }; public static string GetMimeType(byte[] file, string fileName) { string mime = "application/octet-stream"; //DEFAULT UNKNOWN MIME TYPE //Ensure that the filename isn't empty or null if (string.IsNullOrWhiteSpace(fileName)) { return mime; } //Get the file extension string extension = Path.GetExtension(fileName) == null ? string.Empty : Path.GetExtension(fileName).ToUpper(); //Get the MIME Type if (file.Take(2).SequenceEqual(BMP)) { mime = "image/bmp"; } else if (file.Take(8).SequenceEqual(DOC)) { mime = "application/msword"; } else if (file.Take(2).SequenceEqual(EXE_DLL)) { mime = "application/x-msdownload"; //both use same mime type } else if (file.Take(4).SequenceEqual(GIF)) { mime = "image/gif"; } else if (file.Take(4).SequenceEqual(ICO)) { mime = "image/x-icon"; } else if (file.Take(3).SequenceEqual(JPG)) { mime = "image/jpeg"; } else if (file.Take(3).SequenceEqual(MP3)) { mime = "audio/mpeg"; } else if (file.Take(14).SequenceEqual(OGG)) { if (extension == ".OGX") { mime = "application/ogg"; } else if (extension == ".OGA") { mime = "audio/ogg"; } else { mime = "video/ogg"; } } else if (file.Take(7).SequenceEqual(PDF)) { mime = "application/pdf"; } else if (file.Take(16).SequenceEqual(PNG)) { mime = "image/png"; } else if (file.Take(7).SequenceEqual(RAR)) { mime = "application/x-rar-compressed"; } else if (file.Take(3).SequenceEqual(SWF)) { mime = "application/x-shockwave-flash"; } else if (file.Take(4).SequenceEqual(TIFF)) { mime = "image/tiff"; } else if (file.Take(11).SequenceEqual(TORRENT)) { mime = "application/x-bittorrent"; } else if (file.Take(5).SequenceEqual(TTF)) { mime = "application/x-font-ttf"; } else if (file.Take(4).SequenceEqual(WAV_AVI)) { mime = extension == ".AVI" ? "video/x-msvideo" : "audio/x-wav"; } else if (file.Take(16).SequenceEqual(WMV_WMA)) { mime = extension == ".WMA" ? "audio/x-ms-wma" : "video/x-ms-wmv"; } else if (file.Take(4).SequenceEqual(ZIP_DOCX)) { mime = extension == ".DOCX" ? "application/vnd.openxmlformats-officedocument.wordprocessingml.document" : "application/x-zip-compressed"; } return mime; } }
Edit: Just use Mime Detective
I use byte array sequences to determine the correct MIME type of a given file. The advantage of this over just looking at the file extension of the file name is that if a user were to rename a file to bypass certain file type upload restrictions, the file name extension would fail to catch this. On the other hand, getting the file signature via byte array will stop this mischievous behavior from happening.
Here is an example in C#:
public class MimeType
{
private static readonly byte[] BMP = { 66, 77 };
private static readonly byte[] DOC = { 208, 207, 17, 224, 161, 177, 26, 225 };
private static readonly byte[] EXE_DLL = { 77, 90 };
private static readonly byte[] GIF = { 71, 73, 70, 56 };
private static readonly byte[] ICO = { 0, 0, 1, 0 };
private static readonly byte[] JPG = { 255, 216, 255 };
private static readonly byte[] MP3 = { 255, 251, 48 };
private static readonly byte[] OGG = { 79, 103, 103, 83, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0 };
private static readonly byte[] PDF = { 37, 80, 68, 70, 45, 49, 46 };
private static readonly byte[] PNG = { 137, 80, 78, 71, 13, 10, 26, 10, 0, 0, 0, 13, 73, 72, 68, 82 };
private static readonly byte[] RAR = { 82, 97, 114, 33, 26, 7, 0 };
private static readonly byte[] SWF = { 70, 87, 83 };
private static readonly byte[] TIFF = { 73, 73, 42, 0 };
private static readonly byte[] TORRENT = { 100, 56, 58, 97, 110, 110, 111, 117, 110, 99, 101 };
private static readonly byte[] TTF = { 0, 1, 0, 0, 0 };
private static readonly byte[] WAV_AVI = { 82, 73, 70, 70 };
private static readonly byte[] WMV_WMA = { 48, 38, 178, 117, 142, 102, 207, 17, 166, 217, 0, 170, 0, 98, 206, 108 };
private static readonly byte[] ZIP_DOCX = { 80, 75, 3, 4 };
public static string GetMimeType(byte[] file, string fileName)
{
string mime = "application/octet-stream"; //DEFAULT UNKNOWN MIME TYPE
//Ensure that the filename isn't empty or null
if (string.IsNullOrWhiteSpace(fileName))
{
return mime;
}
//Get the file extension
string extension = Path.GetExtension(fileName) == null
? string.Empty
: Path.GetExtension(fileName).ToUpper();
//Get the MIME Type
if (file.Take(2).SequenceEqual(BMP))
{
mime = "image/bmp";
}
else if (file.Take(8).SequenceEqual(DOC))
{
mime = "application/msword";
}
else if (file.Take(2).SequenceEqual(EXE_DLL))
{
mime = "application/x-msdownload"; //both use same mime type
}
else if (file.Take(4).SequenceEqual(GIF))
{
mime = "image/gif";
}
else if (file.Take(4).SequenceEqual(ICO))
{
mime = "image/x-icon";
}
else if (file.Take(3).SequenceEqual(JPG))
{
mime = "image/jpeg";
}
else if (file.Take(3).SequenceEqual(MP3))
{
mime = "audio/mpeg";
}
else if (file.Take(14).SequenceEqual(OGG))
{