SQL Server

Determine File Type from Binary Content of File

Note: This example requires Chilkat v9.5.0.64 or later.

Many file types have "signatures" (leading bytes) that signify the type of file. It allows for programs to identify the likely type of file given the first few bytes contained within the file. This example shows how to identify a few common types files. For other file types, you can do a short bit of investigative work by examining the first few bytes of an sample file, and searching the Internet for information about the file type. Use this same technique for handling other file types that have leading "signature" bytes.

SQL Server

-- Important: See this note about string length limitations for strings returned by sp_OAMethod calls.
--
CREATE PROCEDURE ChilkatSample
AS
BEGIN
    DECLARE @hr int
    -- Important: Do not use nvarchar(max).  See the warning about using nvarchar(max).
    DECLARE @sTmp0 nvarchar(4000)
    -- Note: This example requires Chilkat v9.5.0.64 or later.

    -- To identify a file by the first few bytes, we'll load a few bytes from the start
    -- of the file, and then examine the bytes as both hex and quoted-printable.

    DECLARE @fac int
    EXEC @hr = sp_OACreate 'Chilkat.FileAccess', @fac OUT
    IF @hr <> 0
    BEGIN
        PRINT 'Failed to create ActiveX component'
        RETURN
    END

    -- A JPG file.
    DECLARE @jpgData int
    EXEC @hr = sp_OACreate 'Chilkat.BinData', @jpgData OUT

    DECLARE @success int
    EXEC sp_OAMethod @fac, 'OpenForRead', @success OUT, 'qa_data/jpg/starfish.jpg'
    -- The the first 8 bytes of the JPG file.
    EXEC sp_OAMethod @fac, 'FileReadBd', @success OUT, 8, @jpgData
    EXEC sp_OAMethod @fac, 'FileClose', NULL

    -- JPG hex: FFD8FFE000104A46
    -- JPG qp: =FF=D8=FF=E0=00=10JF

    EXEC sp_OAMethod @jpgData, 'GetEncoded', @sTmp0 OUT, 'hex'
    PRINT 'JPG hex: ' + @sTmp0

    EXEC sp_OAMethod @jpgData, 'GetEncoded', @sTmp0 OUT, 'qp'
    PRINT 'JPG qp: ' + @sTmp0

    -- A JPG begins with the following two bytes: 0xFF, 0xD8
    -- Your program can check to see if the hex string begins with "FFD8", or if the qp string begins with "=FF=D8".

    -- ----------------------------------------
    -- A PNG file.
    DECLARE @pngData int
    EXEC @hr = sp_OACreate 'Chilkat.BinData', @pngData OUT

    EXEC sp_OAMethod @fac, 'OpenForRead', @success OUT, 'qa_data/png/anemone.png'
    -- The the first 8 bytes of the PNG file.
    EXEC sp_OAMethod @fac, 'FileReadBd', @success OUT, 8, @pngData
    EXEC sp_OAMethod @fac, 'FileClose', NULL

    -- PNG hex: 89504E470D0A1A0A
    -- PNG qp: =89PNG=1A=0A

    EXEC sp_OAMethod @pngData, 'GetEncoded', @sTmp0 OUT, 'hex'
    PRINT 'PNG hex: ' + @sTmp0

    EXEC sp_OAMethod @pngData, 'GetEncoded', @sTmp0 OUT, 'qp'
    PRINT 'PNG qp: ' + @sTmp0
    -- A PNG file begins with the byte 0x89, followed by the us-ascii bytes "PNG".

    -- ----------------------------------------
    -- A PDF file.
    DECLARE @pdfData int
    EXEC @hr = sp_OACreate 'Chilkat.BinData', @pdfData OUT

    EXEC sp_OAMethod @fac, 'OpenForRead', @success OUT, 'qa_data/pdf/fishing.pdf'
    -- The the first 8 bytes of the PDF file.
    EXEC sp_OAMethod @fac, 'FileReadBd', @success OUT, 8, @pdfData
    EXEC sp_OAMethod @fac, 'FileClose', NULL

    -- PDF hex: 255044462D312E33
    -- PDF qp: %PDF-1.3

    EXEC sp_OAMethod @pdfData, 'GetEncoded', @sTmp0 OUT, 'hex'
    PRINT 'PDF hex: ' + @sTmp0

    EXEC sp_OAMethod @pdfData, 'GetEncoded', @sTmp0 OUT, 'qp'
    PRINT 'PDF qp: ' + @sTmp0
    -- A PDF file begins with the us-ascii chars "%PDF"

    -- ----------------------------------------
    -- A Zip file.
    DECLARE @zipData int
    EXEC @hr = sp_OACreate 'Chilkat.BinData', @zipData OUT

    EXEC sp_OAMethod @fac, 'OpenForRead', @success OUT, 'qa_data/zips/test.zip'
    -- The the first 8 bytes of the Zip file.
    EXEC sp_OAMethod @fac, 'FileReadBd', @success OUT, 8, @zipData
    EXEC sp_OAMethod @fac, 'FileClose', NULL

    -- PDF hex: 504B030414000000
    -- PDF qp: PK=03=04=14=00=00=00

    EXEC sp_OAMethod @zipData, 'GetEncoded', @sTmp0 OUT, 'hex'
    PRINT 'PDF hex: ' + @sTmp0

    EXEC sp_OAMethod @zipData, 'GetEncoded', @sTmp0 OUT, 'qp'
    PRINT 'PDF qp: ' + @sTmp0
    -- A Zip archive begins with the us-ascii chars "PK" followed by the bytes 0x03, 0x04.

    EXEC @hr = sp_OADestroy @fac
    EXEC @hr = sp_OADestroy @jpgData
    EXEC @hr = sp_OADestroy @pngData
    EXEC @hr = sp_OADestroy @pdfData
    EXEC @hr = sp_OADestroy @zipData


END
GO