中文汉字GB2312和UTF-8的编码转换程序


  在使用Google或者百度进行中文搜索的时候,我们会发现搜索过程中URL地址栏会变成一串格式字符串编码,我们编写程序经常也需要进行中文汉字到这类URL编码的转换,这里介绍两段相关的转换函数。

  对于使用UTF-8的Google搜索引擎来说,使用Google搜索“汉字”会变成http://www.google.com/search?q=%E6%B1%89%E5%AD%97 ,而对于使用GB2312的百度搜索引擎来说,使用百度搜索“汉字”会变成另外的 http://www.baidu.com/s?wd=%BA%BA%D7%D6 。下面的两段VB代码分别针对UTF-8(UTF8EncodeURI)和GB2312(GBKEncodeURI)进行了编码的转换。

    Private Sub command1_click()
        Debug.Print (UTF8EncodeURI("汉字"))
        Debug.Print (GBKEncodeURI("汉字"))
    End Sub


    Function UTF8EncodeURI(szInput)
        Dim wch, uch, szRet
        Dim x
        Dim nAsc, nAsc2, nAsc3

        If szInput = "" Then
            UTF8EncodeURI = szInput
            Exit Function
        End If

        For x = 1 To Len(szInput)
            wch = Mid(szInput, x, 1)
            nAsc = AscW(wch)

            If nAsc < 0 Then nAsc = nAsc + 65536

            If (nAsc And &HFF80) = 0 Then
                szRet = szRet & wch
            Else
                If (nAsc And &HF000) = 0 Then
                    uch = "%" & Hex(((nAsc \ 2 ^ 6)) Or &HC0) & Hex(nAsc And &H3F Or &H80)
                    szRet = szRet & uch
                Else
                    uch = "%" & Hex((nAsc \ 2 ^ 12) Or &HE0) & "%" & _
                    Hex((nAsc \ 2 ^ 6) And &H3F Or &H80) & "%" & _
                    Hex(nAsc And &H3F Or &H80)
                    szRet = szRet & uch
                End If
            End If
        Next

        UTF8EncodeURI = szRet
    End Function

    Function GBKEncodeURI(szInput)
        Dim i As Long
        Dim x() As Byte
        Dim szRet As String

        szRet = ""
        x = StrConv(szInput, vbFromUnicode)
        For i = LBound(x) To UBound(x)
            szRet = szRet & "%" & Hex(x(i))
        Next
        GBKEncodeURI = szRet
    End Function