UTF-8 source to Windows-1250 or other (XML)

[Aciano]

Hi all. I am reading an XML that is in utf-8 (XML it self shows OK in the browser), but when I read it with INetGet all of the Czech characters are wrong. This time I Copy and Paste the whole XML from the IE, which I don't like. Can anyone help me and tell me how to convert those "broken letters" (change utf-8 to Windows-1250)? I have been searching and experimenting for couple of days before writting you and I haven't found anything but ANSCII characters. If anyone could help, I will appreciate it. I understand that utf-8 document saves in utf-8 besides Windows-1250 (for exaple) saves in ANSI. I appreciate any help.

Aciano

Edited April 20, 2007 by Aciano

[Zedna]

Grabbed from forum:

http://www.autoitscript.com/forum/index.php?showtopic=21815

expandcollapse popup

Func Asc2Unicode($AscString)
    Local $BufferSize = StringLen($AscString) * 2
    Local $Buffer = DllStructCreate("byte[" & $BufferSize & "]")
    Local $Return = DllCall("Kernel32.dll", "int", "MultiByteToWideChar", _
        "int", 0, _
        "int", 0, _
        "str", $AscString, _
        "int", StringLen($AscString), _
        "ptr", DllStructGetPtr($Buffer), _
        "int", $BufferSize)
    Local $UnicodeString = StringLeft(DllStructGetData($Buffer, 1), $Return[0] * 2)
    $Buffer = 0
    Return $UnicodeString
EndFunc

Func Unicode2Asc($UniString)
    If Not IsBinaryString($UniString) Then
        SetError(1)
        Return $UniString
    EndIf

    Local $BufferLen = StringLen($UniString)
    Local $Input = DllStructCreate("byte[" & $BufferLen & "]")
    Local $Output = DllStructCreate("char[" & $BufferLen & "]")
    DllStructSetData($Input, 1, $UniString)
    Local $Return = DllCall("kernel32.dll", "int", "WideCharToMultiByte", _
        "int", 0, _
        "int", 0, _
        "ptr", DllStructGetPtr($Input), _
        "int", $BufferLen / 2, _
        "ptr", DllStructGetPtr($Output), _
        "int", $BufferLen, _
        "int", 0, _
        "int", 0)   
    Local $AscString = DllStructGetData($Output, 1)
    $Output = 0
    $Input = 0
    Return $AscString
EndFunc

Func Unicode2Utf8($UniString)
    If Not IsBinaryString($UniString) Then
        SetError(1)
        Return $UniString
    EndIf

    Local $UniStringLen = StringLen($UniString)
    Local $BufferLen = $UniStringLen * 2
    Local $Input = DllStructCreate("byte[" & $BufferLen & "]")
    Local $Output = DllStructCreate("char[" & $BufferLen & "]")
    DllStructSetData($Input, 1, $UniString)
    Local $Return = DllCall("kernel32.dll", "int", "WideCharToMultiByte", _
        "int", 65001, _
        "int", 0, _
        "ptr", DllStructGetPtr($Input), _
        "int", $UniStringLen / 2, _
        "ptr", DllStructGetPtr($Output), _
        "int", $BufferLen, _
        "int", 0, _
        "int", 0)   
    Local $Utf8String = DllStructGetData($Output, 1)
    $Output = 0
    $Input = 0
    Return $Utf8String
EndFunc

Func Utf82Unicode($Utf8String)
    Local $BufferSize = StringLen($Utf8String) * 2
    Local $Buffer = DllStructCreate("byte[" & $BufferSize & "]")
    Local $Return = DllCall("Kernel32.dll", "int", "MultiByteToWideChar", _
        "int", 65001, _
        "int", 0, _
        "str", $Utf8String, _
        "int", StringLen($Utf8String), _
        "ptr", DllStructGetPtr($Buffer), _
        "int", $BufferSize)
    Local $UnicodeString = StringLeft(DllStructGetData($Buffer, 1), $Return[0] * 2)
    $Buffer = 0
    Return $UnicodeString   
EndFunc