Klasyczna ASP (VBScript) konwertuje kody HTML na zwykły tekst

Question

Próbuję przekonwertować kody HTML, takie jak & #XXXX; (gdzie XXXX to liczba) do zwykłego tekstu z klasycznym ASP (VBScript).

Dodaję tekst do wiadomości e-mail w formacie zwykłego tekstu, a jeśli dodaję je jako kody HTML, po prostu wyświetla kod i nie konwertuje ich.

Jedną z poprawek będzie zmiana e-maila na HTML, który rozwiązuje ten problem, ale powoduje też inne problemy dotyczące mojego adresu e-mail, które nie zostaną wprowadzone.

Czy istnieje wbudowana funkcja lub niestandardowa funkcja, której mogę użyć do przekonwertowania tych kodów HTML na zwykły tekst?

Answer 1

Potrzebny jest HTML Decode, choć niestety ASP go nie zawiera.

Ta funkcja, znaleziona na ASP Nut i zmodyfikowana przeze mnie, powinna zrobić to, czego potrzebujesz. Testowałem to jako vbscript działający na moim lokalnym komputerze i wydawało mi się, że działa dobrze, nawet z symbolami Unicode w zasięgu 1000+.

Function HTMLDecode(sText) 
    Dim regEx 
    Dim matches 
    Dim match 
    sText = Replace(sText, """, Chr(34)) 
    sText = Replace(sText, "<" , Chr(60)) 
    sText = Replace(sText, ">" , Chr(62)) 
    sText = Replace(sText, "&" , Chr(38)) 
    sText = Replace(sText, " ", Chr(32)) 


    Set regEx= New RegExp 

    With regEx 
    .Pattern = "&#(\d+);" 'Match html unicode escapes 
    .Global = True 
    End With 

    Set matches = regEx.Execute(sText) 

    'Iterate over matches 
    For Each match in matches 
     'For each unicode match, replace the whole match, with the ChrW of the digits. 

     sText = Replace(sText, match.Value, ChrW(match.SubMatches(0))) 
    Next 

    HTMLDecode = sText 
End Function 

_{Uwaga: Musisz skryptu w wersji 5.0 zainstalowanego na serwerze do korzystania z obiektu RegExp.}

Answer 2

Zrobiłem to na podstawie powyższej odpowiedzi C.Rossa i kodu od kogoś innego stworzonego przez fb_app.inc. To powinno wystarczyć.

<% 
    Option Explicit 

    Dim objHelper 
    Set objHelper = New HtmlEntityToUnicode 

    Response.Write(objHelper.HtmlDecode("<br/><br/>hi &#128154; green heart! purple heart &#128156; ! ")) 

    Set objHelper = Nothing 

    Class HtmlEntityToUnicode 
    dim BITS_TO_A_BYTE 
    dim BYTES_TO_A_WORD 
    dim BITS_TO_A_WORD 
    Dim m_lOnBits(30) 
    Dim m_l2Power(30) 

    Sub Class_Initialize() 


     BITS_TO_A_BYTE = 8 
     BYTES_TO_A_WORD = 4 
     BITS_TO_A_WORD = 32 

     m_lOnBits(0) = CLng(1) 
     m_lOnBits(1) = CLng(3) 
     m_lOnBits(2) = CLng(7) 
     m_lOnBits(3) = CLng(15) 
     m_lOnBits(4) = CLng(31) 
     m_lOnBits(5) = CLng(63) 
     m_lOnBits(6) = CLng(127) 
     m_lOnBits(7) = CLng(255) 
     m_lOnBits(8) = CLng(511) 
     m_lOnBits(9) = CLng(1023) 
     m_lOnBits(10) = CLng(2047) 
     m_lOnBits(11) = CLng(4095) 
     m_lOnBits(12) = CLng(8191) 
     m_lOnBits(13) = CLng(16383) 
     m_lOnBits(14) = CLng(32767) 
     m_lOnBits(15) = CLng(65535) 
     m_lOnBits(16) = CLng(131071) 
     m_lOnBits(17) = CLng(262143) 
     m_lOnBits(18) = CLng(524287) 
     m_lOnBits(19) = CLng(1048575) 
     m_lOnBits(20) = CLng(2097151) 
     m_lOnBits(21) = CLng(4194303) 
     m_lOnBits(22) = CLng(8388607) 
     m_lOnBits(23) = CLng(16777215) 
     m_lOnBits(24) = CLng(33554431) 
     m_lOnBits(25) = CLng(67108863) 
     m_lOnBits(26) = CLng(134217727) 
     m_lOnBits(27) = CLng(268435455) 
     m_lOnBits(28) = CLng(536870911) 
     m_lOnBits(29) = CLng(1073741823) 
     m_lOnBits(30) = CLng(2147483647) 

     m_l2Power(0) = CLng(1) 
     m_l2Power(1) = CLng(2) 
     m_l2Power(2) = CLng(4) 
     m_l2Power(3) = CLng(8) 
     m_l2Power(4) = CLng(16) 
     m_l2Power(5) = CLng(32) 
     m_l2Power(6) = CLng(64) 
     m_l2Power(7) = CLng(128) 
     m_l2Power(8) = CLng(256) 
     m_l2Power(9) = CLng(512) 
     m_l2Power(10) = CLng(1024) 
     m_l2Power(11) = CLng(2048) 
     m_l2Power(12) = CLng(4096) 
     m_l2Power(13) = CLng(8192) 
     m_l2Power(14) = CLng(16384) 
     m_l2Power(15) = CLng(32768) 
     m_l2Power(16) = CLng(65536) 
     m_l2Power(17) = CLng(131072) 
     m_l2Power(18) = CLng(262144) 
     m_l2Power(19) = CLng(524288) 
     m_l2Power(20) = CLng(1048576) 
     m_l2Power(21) = CLng(2097152) 
     m_l2Power(22) = CLng(4194304) 
     m_l2Power(23) = CLng(8388608) 
     m_l2Power(24) = CLng(16777216) 
     m_l2Power(25) = CLng(33554432) 
     m_l2Power(26) = CLng(67108864) 
     m_l2Power(27) = CLng(134217728) 
     m_l2Power(28) = CLng(268435456) 
     m_l2Power(29) = CLng(536870912) 
     m_l2Power(30) = CLng(1073741824) 

    End Sub 

    Public Function HTMLDecode(sText) 
     Dim regEx 
     Dim matches 
     Dim match 
     sText = Replace(sText, "&quot;", Chr(34)) 
     sText = Replace(sText, "&lt;" , Chr(60)) 
     sText = Replace(sText, "&gt;" , Chr(62)) 
     sText = Replace(sText, "&amp;" , Chr(38)) 
     sText = Replace(sText, "&nbsp;", Chr(32)) 


     Set regEx= New RegExp 

     With regEx 
     .Pattern = "&#(\d+);" 'Match html unicode escapes 
     .Global = True 
     End With 

     Set matches = regEx.Execute(sText) 

     'Iterate over matches 
     For Each match in matches 
     'For each unicode match, replace the whole match, with the ChrW of the digits. 
      sText = Replace(sText, match.Value, "\U"&WordToHex(match.SubMatches(0))) 
     Next 

     HTMLDecode = sText 
    End Function 


    Private Function WordToHex(lValue) 
     Dim lByte 
     Dim lCount 

     For lCount = 0 To 3 
      lByte = RShift(lValue, lCount * BITS_TO_A_BYTE) And m_lOnBits(BITS_TO_A_BYTE - 1) 
      WordToHex = Right("0" & Hex(lByte), 2) & WordToHex 
     Next 
    End Function 

    Private Function RShift(lValue, iShiftBits) 
     If iShiftBits = 0 Then 
      RShift = lValue 
      Exit Function 
     ElseIf iShiftBits = 31 Then 
      If lValue And &H80000000 Then 
       RShift = 1 
      Else 
       RShift = 0 
      End If 
      Exit Function 
     ElseIf iShiftBits < 0 Or iShiftBits > 31 Then 
      Err.Raise 6 
     End If 

     RShift = (lValue And &H7FFFFFFE) \ m_l2Power(iShiftBits) 

     If (lValue And &H80000000) Then 
      RShift = (RShift Or (&H40000000 \ m_l2Power(iShiftBits - 1))) 
     End If 
    End Function 

    End Class 


    %> 

Answer 3

Bardziej exausted dekoder epanding C. Ross odpowiedź

Function HTMLDecode(sText) 
    Dim regEx 
    Dim matches 
    Dim match 
    sText = Replace(sText, """, Chr(34)) 
    sText = Replace(sText, "<" , Chr(60)) 
    sText = Replace(sText, ">" , Chr(62)) 
    sText = Replace(sText, "&" , Chr(38)) 
    sText = Replace(sText, " ", Chr(32)) 

    sText = Replace(sText, "¡", Chr(161)) 
    sText = Replace(sText, "£", Chr(163)) 
    sText = Replace(sText, "¥", Chr(165)) 
    sText = Replace(sText, "©", Chr(168)) 
    sText = Replace(sText, "«", Chr(171)) 
    sText = Replace(sText, "»", Chr(187)) 
    sText = Replace(sText, "¿", Chr(191)) 
    sText = Replace(sText, "À", Chr(192)) 
    sText = Replace(sText, "Á", Chr(193)) 
    sText = Replace(sText, "Â", Chr(194)) 
    sText = Replace(sText, "Ã", Chr(195)) 
    sText = Replace(sText, "Ä", Chr(196)) 
    sText = Replace(sText, "Å", Chr(197)) 
    sText = Replace(sText, "Æ", Chr(198)) 
    sText = Replace(sText, "Ç", Chr(199)) 
    sText = Replace(sText, "È", Chr(200)) 
    sText = Replace(sText, "É", Chr(201)) 
    sText = Replace(sText, "Ê", Chr(202)) 
    sText = Replace(sText, "Ë", Chr(203)) 
    sText = Replace(sText, "Ì", Chr(204)) 
    sText = Replace(sText, "Í", Chr(205)) 
    sText = Replace(sText, "Î", Chr(206)) 
    sText = Replace(sText, "Ï", Chr(207)) 
    sText = Replace(sText, "Ñ", Chr(209)) 
    sText = Replace(sText, "Ò", Chr(210)) 
    sText = Replace(sText, "Ó", Chr(211)) 
    sText = Replace(sText, "Ô", Chr(212)) 
    sText = Replace(sText, "Õ", Chr(213)) 
    sText = Replace(sText, "Ö", Chr(214)) 
    sText = Replace(sText, "×", Chr(215)) 
    sText = Replace(sText, "Ø", Chr(216)) 
    sText = Replace(sText, "Ù", Chr(217)) 
    sText = Replace(sText, "Ú", Chr(218)) 
    sText = Replace(sText, "Û", Chr(219)) 
    sText = Replace(sText, "Ü", Chr(220)) 
    sText = Replace(sText, "Ý", Chr(221)) 
    sText = Replace(sText, "Þ", Chr(222)) 
    sText = Replace(sText, "ß", Chr(223)) 
    sText = Replace(sText, "à", Chr(224)) 
    sText = Replace(sText, "á", Chr(225)) 
    sText = Replace(sText, "â", Chr(226)) 
    sText = Replace(sText, "ã", Chr(227)) 
    sText = Replace(sText, "ä", Chr(228)) 
    sText = Replace(sText, "å", Chr(229)) 
    sText = Replace(sText, "æ", Chr(230)) 
    sText = Replace(sText, "ç", Chr(231)) 
    sText = Replace(sText, "è", Chr(232)) 
    sText = Replace(sText, "é", Chr(233)) 
    sText = Replace(sText, "ê", Chr(234)) 
    sText = Replace(sText, "ë", Chr(235)) 
    sText = Replace(sText, "ì", Chr(236)) 
    sText = Replace(sText, "í", Chr(237)) 
    sText = Replace(sText, "î", Chr(238)) 
    sText = Replace(sText, "ï", Chr(239)) 
    sText = Replace(sText, "ð", Chr(240)) 
    sText = Replace(sText, "ñ", Chr(241)) 
    sText = Replace(sText, "ò", Chr(242)) 
    sText = Replace(sText, "ó", Chr(243)) 
    sText = Replace(sText, "ô", Chr(244)) 
    sText = Replace(sText, "õ", Chr(245)) 
    sText = Replace(sText, "ö", Chr(246)) 
    sText = Replace(sText, "÷", Chr(247)) 
    sText = Replace(sText, "ø", Chr(248)) 
    sText = Replace(sText, "ù", Chr(249)) 
    sText = Replace(sText, "ú", Chr(250)) 
    sText = Replace(sText, "û", Chr(251)) 
    sText = Replace(sText, "ü", Chr(252)) 
    sText = Replace(sText, "ý", Chr(253)) 
    sText = Replace(sText, "þ", Chr(254)) 
    sText = Replace(sText, "ÿ", Chr(255)) 

    Set regEx= New RegExp 

    With regEx 
    .Pattern = "&#(\d+);" 'Match html unicode escapes 
    .Global = True 
    End With 

    Set matches = regEx.Execute(sText) 

    'Iterate over matches 
    For Each match in matches 
     'For each unicode match, replace the whole match, with the ChrW of the digits. 

     sText = Replace(sText, match.Value, ChrW(match.SubMatches(0))) 
    Next 

    HTMLDecode = sText 
End Function