确定文本文件是否为Unicode编码

Posted 2021-02-24

The .NET Framework doesn't support automatic detection of character encoding in the default file I/O methods. This is a quick function that returns True in the specified file is Unicode.

Private Function is_unicode(ByVal path As String) As Boolean
        Dim enc As System.Text.Encoding = Nothing
        Dim file As System.IO.FileStream = New System.IO.FileStream(path, FileMode.Open, FileAccess.Read, FileShare.Read)
        If file.CanSeek Then
            Dim bom As Byte() = New Byte(3) {} ' Get the byte-order mark, if there is one
            file.Read(bom, 0, 4)
            If (bom(0) = &HEF AndAlso bom(1) = &HBB AndAlso bom(2) = &HBF) OrElse (bom(0) = &HFF AndAlso bom(1) = &HFE) OrElse (bom(0) = &HFE AndAlso bom(1) = &HFF) OrElse (bom(0) = 0 AndAlso bom(1) = 0 AndAlso bom(2) = &HFE AndAlso bom(3) = &HFF) Then ' ucs-4
                Return True
            Else
                Return False
            End If
 
            ' Now reposition the file cursor back to the start of the file
            file.Seek(0, System.IO.SeekOrigin.Begin)
        Else
            Return False
        End If
    End Function