Detecting File Type Using Magic Numbers In ColdFusion

magic-numbers.cfm

<cfscript>


	// I determine if the given file starts with the given hex
	// signature. We can use this to losely determine the file type
	// of the given file.
	boolean function startsWithHexSignature(
		required string filepath,
		required string hexSignature,
		numeric signatureOffset = 0
		) {

		// The byte signature is half the length of the hex signature
		// since a single byte is represented by two hex characters.
		var signatureLength = ( len( hexSignature ) / 2 );

		// I am the byte buffer into which bytes will be streamed.
		var byteBuffer = [];

		arraySet( byteBuffer, 1, signatureLength, 0 );

		// Convert the ColdFusion array to a Java byte array so that
		// the input stream will work with it.
		byteBuffer = javaCast( "byte[]", byteBuffer );

		// Open an input stream to the file.
		var inputStream = createObject( "java", "java.io.FileInputStream" ).init(
			javaCast( "string", filepath )
		);

		try {

			// If the signature if offset, read off the bytes that
			// we want to ignore.
			if ( signatureOffset ) {

				for ( var i = 0 ; i < signatureOffset ; i++ ) {

					inputStream.read();

				}

			}

			// Read off the signature bytes.
			inputStream.read( byteBuffer );

			return( binaryEncode( byteBuffer, "hex" ) == hexSignature );

		} catch ( any ioError ) {

			// If anything went wrong with the input stream read,
			// then we'll assume the signatures don't match.
			return( false );

		} finally {

			// No matter what happens, clean up the file.
			inputStream.close();

		}

	}


	// ------------------------------------------------------ //
	// ------------------------------------------------------ //
	// ------------------------------------------------------ //
	// ------------------------------------------------------ //


	// Set up some test files and known hex signatures for the given
	// files. NOTE: I gathered these signatures across different
	// sites which is why there may be multiple tests for a given
	// file type.
	tests = [
		{
			filename = "file.ai",
			hexSignature = "25504446",
			offset = 0
		},
		{
			filename = "file.avi",
			hexSignature = "52494646",
			offset = 0
		},
		{
			filename = "file.avi",
			hexSignature = "415649204C495354",
			offset = 0
		},
		{
			filename = "file.gif",
			hexSignature = "474946383761",
			offset = 0
		},
		{
			filename = "file.gif",
			hexSignature = "474946383961",
			offset = 0
		},
		{
			filename = "file.jpg",
			hexSignature = "FFD8FFE0",
			offset = 0
		},
		{
			filename = "file.jpg",
			hexSignature = "494600",
			offset = 0
		},
		{
			filename = "file.jpg",
			hexSignature = "FFD8FFE1",
			offset = 0
		},
		{
			filename = "file.mov",
			hexSignature = "0000001466747970",
			offset = 0
		},
		{
			filename = "file.mov",
			hexSignature = "6D6F6F76",
			offset = 0
		},
		{
			filename = "file.mov",
			hexSignature = "71742020",
			offset = 4
		},
		{
			filename = "file.mov",
			hexSignature = "66726565",
			offset = 4
		},
		{
			filename = "file.mov",
			hexSignature = "6D646174",
			offset = 4
		},
		{
			filename = "file.mov",
			hexSignature = "77696465",
			offset = 4
		},
		{
			filename = "file.mov",
			hexSignature = "706E6F74",
			offset = 4
		},
		{
			filename = "file.mov",
			hexSignature = "736B6970",
			offset = 4
		},
		{
			filename = "file.mp3",
			hexSignature = "FFFB",
			offset = 0
		},
		{
			filename = "file.mp3",
			hexSignature = "494433",
			offset = 0
		},
		{
			filename = "file.mp4",
			hexSignature = "0000001866747970",
			offset = 0
		},
		{
			filename = "file.mp4",
			hexSignature = "33677035",
			offset = 0
		},
		{
			filename = "file.pdf",
			hexSignature = "25504446", // <-- NOTE: Same as AI.
			offset = 0
		},
		{
			filename = "file.png",
			hexSignature = "89504E470D0A1A0A",
			offset = 0
		},
		{
			filename = "file.psd",
			hexSignature = "4F676753",
			offset = 0
		},
		{
			filename = "file.psd",
			hexSignature = "38425053",
			offset = 0
		},
		{
			filename = "file.xlsx",
			hexSignature = "504B0304", // <-- NOTE: Same as ZIP.
			offset = 0
		},
		{
			filename = "file.zip",
			hexSignature = "504B0304",
			offset = 0
		},
		{
			filename = "file.zip",
			hexSignature = "504B0506",
			offset = 0
		},
		{
			filename = "file.zip",
			hexSignature = "504B0708",
			offset = 0
		},
		{
			filename = "file.zip",
			hexSignature = "504B4C495445",
			offset = 30
		},
		{
			filename = "file.zip",
			hexSignature = "504B537058",
			offset = 526
		},
		{
			filename = "file.zip",
			hexSignature = "57696E5A6970",
			offset = 29
		},
		{
			filename = "file.zip",
			hexSignature = "57696E5A6970",
			offset = 152
		},
		{
			filename = "file.zip",
			hexSignature = "1F8B08",
			offset = 0
		}
	];


	// Loop over each test and test the hex signature.
	for ( test in tests ) {

		writeOutput( "#test.filename# [ #test.hexSignature# ] : " );

		writeOutput(
			startsWithHexSignature(
				expandPath( "./tests/" & test.filename ),
				test.hexSignature ,
				test.offset
			)
		);

		writeOutput( "<br />" );

	}


</cfscript>