Text Analysis – Detect Encoding and Get String

Detects the encoding of a byte array based on its byte order mark (BOM) and converts it to a string.

If the byte array starts with EF BB BF, UTF-8 with BOM is used.
If the byte array starts with FF FE, UTF-16 LE is assumed.
If the byte array starts with FE FF, UTF-16 BE is assumed.
If no BOM is detected, UTF-8 without BOM is used as the default.

    Public Function DetectEncodingAndGetString(bytes As Byte()) As String
    
        If bytes Is Nothing Then Return String.Empty
        
        Dim enc As Encoding = Encoding.UTF8
        If bytes.Length >= 3 AndAlso bytes(0) = &HEF AndAlso bytes(1) = &HBB AndAlso bytes(2) = &HBF Then
            enc = New UTF8Encoding(encoderShouldEmitUTF8Identifier:=True)
        ElseIf bytes.Length >= 2 AndAlso bytes(0) = &HFF AndAlso bytes(1) = &HFE Then
            enc = Encoding.Unicode
        ElseIf bytes.Length >= 2 AndAlso bytes(0) = &HFE AndAlso bytes(1) = &HFF Then
            enc = Encoding.BigEndianUnicode
        End If
        
        Return enc.GetString(bytes)
    End Function

    Public Function DetectEncodingAndGetString(bytes As Byte()) As String
    
        If bytes Is Nothing Then Return String.Empty
        
        Dim enc As Encoding = Encoding.UTF8
        If bytes.Length >= 3 AndAlso bytes(0) = &HEF AndAlso bytes(1) = &HBB AndAlso bytes(2) = &HBF Then
            enc = New UTF8Encoding(encoderShouldEmitUTF8Identifier:=True)
        ElseIf bytes.Length >= 2 AndAlso bytes(0) = &HFF AndAlso bytes(1) = &HFE Then
            enc = Encoding.Unicode
        ElseIf bytes.Length >= 2 AndAlso bytes(0) = &HFE AndAlso bytes(1) = &HFF Then
            enc = Encoding.BigEndianUnicode
        End If
        
        Return enc.GetString(bytes)
    End Function

Posted by ipercube