|
|
参考文档：http://www.linuxforum.net/books/UTF-8-Unicode.html
代码如下：
＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝
复制代码 代码如下:
<script language="VBScript">
'http://www.linuxforum.net/books/UTF-8-Unicode.html
Public Function UTF8EncodeChar(z)
Dim c : c=AscW(z)'取UNICODE编码
if c>0 And c<256 Then'Asc编码直接返回
UTF8EncodeChar=z
Exit Function
End If
If c<0 Then c=c + &H10000&'VBScript的Integer溢出，加上
Dim k : k=CLng(c)'备份一个编码，后面判断要用
Dim b()
Dim i : i=0
While c>&H0&'将编码按照6位一组，分组存到字节数组 b 中
ReDim Preserve b(i)
b(i)=CByte(c And &H3F&)
c=c \ &H40&
i=i+1
Wend
If UBound(b)>0 Then '如果分开的6位组不止一个，除最高一组外，全部加上二进制10000000
For i=0 To UBound(b)-1
b(i)=b(i) + &H80
Next
End If
i=UBound(b)'根据字符的UNICODE编码范围，给最高组加上前缀
If k<=CLng(&H7F&) Then
b(i) = b(i) + 0
ElseIf k<=CLng(&H7FF&) Then
b(i) = b(i) + &HC0
ElseIf k<=Clng(&HFFFF&) Then
b(i) = b(i) + &HE0
ElseIf k<=CLng(&H1FFFFF&) Then
b(i) = b(i) + &HF0
ElseIf k<=CLng(&H3FFFFFF&) Then
b(i) = b(i) + &HF8
Else
b(i) = b(i) + &HFC
End If
UTF8EncodeChar=""
For i=UBound(b) To 0 Step -1'将分组转换成URL编码
UTF8EncodeChar=UTF8EncodeChar & "%" & Right("00" & Hex(b(i)),2)
Next
Erase b
End Function
Public Function UTF8EncodeString(s)
Dim i,l,c : l=Len(s)
For i=1 To l
UTF8EncodeString=UTF8EncodeString & UTF8EncodeChar(Mid(s,i,1))
Next
End Function
MsgBox UTF8EncodeString("圪圪 eglic ")
</script>
测试方法：
http://www.google.com/search?hl=zh-CN&newwindow=1&rls=GGLG%2CGGLG%3A2006-15%2CGGLG%3Azh-CN&q=你的编码
复制代码 代码如下:
function revertUTF8(szInput)
{
var x,wch,wch1,wch2,uch="",szRet="";
for (x=0; x<szInput.length; x++)
{
if (szInput.charAt(x)=="%")
{
wch =parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
if (!wch) {break;}
if (!(wch & 0x80))
{
wch = wch;
}
else if (!(wch & 0x20))
{
x++;
wch1 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
wch = (wch & 0x1F)<< 6;
wch1 = wch1 & 0x3F;
wch = wch + wch1;
}
else
{
x++;
wch1 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
x++;
wch2 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
wch = (wch & 0x0F)<< 12;
wch1 = (wch1 & 0x3F)<< 6;
wch2 = (wch2 & 0x3F);
wch = wch + wch1 + wch2;
}
szRet += String.fromCharCode(wch);
}
else
{
szRet += szInput.charAt(x);
}
}
return(szRet);
}
function u2utf8($c)
{
/*for($i=0;$i<count($c);$i++)*/
$str="";
if ($c < 0x80) {
$str.=$c;
}
else if ($c < 0x800) {
$str.=chr(0xC0 | $c>>6);
$str.=chr(0x80 | $c & 0x3F);
}
else if ($c < 0x10000) {
$str.=chr(0xE0 | $c>>12);
$str.=chr(0x80 | $c>>6 & 0x3F);
$str.=chr(0x80 | $c & 0x3F);
}
else if ($c < 0x200000) {
$str.=chr(0xF0 | $c>>18);
$str.=chr(0x80 | $c>>12 & 0x3F);
$str.=chr(0x80 | $c>>6 & 0x3F);
$str.=chr(0x80 | $c & 0x3F);
}
return $str;
}
复制代码 代码如下:
'UTF8 URLEncode
Public Function URLEncodeUTF8(ByVal s)
Dim i, k
Dim sl
Dim c
Dim uni
Dim tp, h1, h2, h3
sl = Len(s)
tp = ""
k = 0
For i = 1 To sl
c = Mid(s, i, 1)
uni = AscW(c)
If uni < 0 Then uni = uni + 65536
If uni < 128 Then
tp = tp & Chr(c)
k = k + 1
ElseIf uni < 2048 Then
k = k + 2
h2 = "%" & Hex(&H80 XOr (uni And &H3F))
uni = uni \ (2^6)
h1 = "%" & Hex(&HC0 XOr (uni And &H1F))
tp = tp & h1 & h2
Else
h3 = "%" & Hex(&H80 XOr (uni And &H3F))
uni = uni \ (2^6)
h2 = "%" & Hex(&H80 XOr (uni And &H3F))
uni = uni \ (2^6)
h1 = "%" & Hex(&HE0 XOr (uni And &H0F))
tp = tp & h1 & h2 & h3
End If
Next
URLEncodeUTF8 = tp
End Function
'A-Fa-f0-9 Byte
Public Function isxdigit(c)
isxdigit = CBool((c>=48 And c<=57) Or (c>=65 And c<=70) Or (c>=97 And c<=102))
End Function
Public Function isascii(c)
isascii = CBool(c>0 And c<128)
End Function
'判断是否是UTF8字节
Public Function IsUTF8Body(ByVal u)
IsUTF8Body = CBool(u>=&H80 And u<=&HBF)
End Function
'判断有几个UTF8字节
Private Function UTF8Byte(ByVal u)
If u > &H00 And u <= &H7F Then
UTF8Byte = 1
ElseIf u >= &HC0 And u <= &HDF Then
UTF8Byte = 2
ElseIf u >= &HE0 And u <= &HEF Then
UTF8Byte = 3
ElseIf u >= &HF0 And u <= &HF7 Then
UTF8Byte = 4
ElseIf u >= &HF8 And u <= &HFB Then
UTF8Byte = 5
ElseIf u >= &HFC And u <= &HFD Then
UTF8Byte = 6
Else
UTF8Byte = 0
End If
End Function
'判断三个连续字节是不是UTF8字符
Private Function UTF8Test(ByVal u1, ByVal u2, ByVal u3)
UTF8Test = False
If CBool(u1>=&HC0 And u1<=&HFD) Then
UTF8Test = CBool(IsUTF8Body(u2) And IsUTF8Body(u3))
End If
End Function
Private Function ishex(s)
ishex = False
If Len(s)<2 Then Exit Function
If isxdigit(Asc(Mid(s, 1, 1)))=False Then Exit Function
If isxdigit(Asc(Mid(s, 2, 1)))=False Then Exit Function
ishex = True
End Function
Private Function isescape(s)
isescape = False
If Len(s)<5 Then Exit Function
If UCase(Mid(s, 1, 1)) <> "U" Then Exit Function
If isxdigit(Asc(Mid(s, 2, 1)))=False Then Exit Function
If isxdigit(Asc(Mid(s, 3, 1)))=False Then Exit Function
If isxdigit(Asc(Mid(s, 4, 1)))=False Then Exit Function
If isxdigit(Asc(Mid(s, 5, 1)))=False Then Exit Function
isescape = True
End Function
Private Function AscX(s)
AscX = CInt("&H" & Mid(s, 1, 2))
End Function
'URLDecode 完全版
'支持Server.URLEncode，UTF8 URLEncode，Escape 加密的字符串
Public Function URLDecode(s)
Dim tp
Dim i
Dim tl
Dim pp
Dim a, b, c
Dim h
URLDecode = ""
tp = Split(Replace(s, "+", " "), "%")
tl = UBound(tp)
If tl = -1 Then Exit Function
pp = tp(0)
For i = 1 To tl
If isescape(tp(i)) Then
pp = pp & ChrW("&H" & Mid(tp(i), 2, 4)) & Mid(tp(i), 6)
ElseIf ishex(tp(i))=False Then
pp = pp & tp(i)
Else
a = AscX(tp(i))
If isascii(a)=False And Len(tp(i))=2 Then
If (i+1)>tl Then Exit For
b = AscX(tp(i+1))
If (i+2)>tl Then
pp = pp & Chr(a*2^8 Or b) & Mid(tp(i+1), 3)
i = i + 1
Else
c = AscX(tp(i+2))
If UTF8Byte(a)=3 And UTF8Test(a,b,c)=True Then
h = (a And &H0F) * 2 ^12 Or (b And &H3F) * 2 ^ 6 Or (c And &H3F)
If h<0 Then h = h + 65536
pp = pp & ChrW(h) & Mid(tp(i+2), 3)
i = i + 2
Else
pp = pp & Chr(a*2^8 Or b) & Mid(tp(i+1), 3)
i = i + 1
End If
End If
ElseIf isascii(a)=False Then
pp = pp & tp(i)
Else
pp = pp & Chr(a) & Mid(tp(i), 3)
End If
End If
Next
URLDecode = pp
End Function
URLEncodeUTF8只写了多字节的加密，没有写ascii字节的，其实也没必要写这个，有个Server.URLEncode可以用，改成js版本的倒还有用武之地
js的版本,里面有个现成的函数
<script language=javascript>
alert(encodeURI("圪圪 eglic "))
</script>
看上边有人说看不懂，我来解释下吧。梅子的第一个函数是把多字节unicode编码转成我们通常正常的编码，在JS中如果偷懒，decodeURI也可实现这个功能。不过，看到这个具体是怎么实现的，感觉好爽，回家研究去啦。复制代码 代码如下:
<script language=javascript>
function revertUTF8(szInput)
{
var x,wch,wch1,wch2,uch="",szRet="";
for (x=0; x<szInput.length; x++)
{
if (szInput.charAt(x)=="%")
{
wch =parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
if (!wch) {break;}
if (!(wch & 0x80))
{
wch = wch;
}
else if (!(wch & 0x20))
{
x++;
wch1 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
wch = (wch & 0x1F)<< 6;
wch1 = wch1 & 0x3F;
wch = wch + wch1;
}
else
{
x++;
wch1 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
x++;
wch2 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
wch = (wch & 0x0F)<< 12;
wch1 = (wch1 & 0x3F)<< 6;
wch2 = (wch2 & 0x3F);
wch = wch + wch1 + wch2;
}
szRet += String.fromCharCode(wch);
}
else
{
szRet += szInput.charAt(x);
}
}
return(szRet);
}
alert(revertUTF8("%E5%9C%AA%E5%9C%AA%20eglic%20 "))
alert(decodeURI("%E5%9C%AA%E5%9C%AA%20eglic%20 "))
</script>
参考文档：http://www.linuxforum.net/books/UTF-8-Unicode.html
代码如下：
＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝＝
复制代码 代码如下:
<script language="VBScript">
'http://www.linuxforum.net/books/UTF-8-Unicode.html
Public Function UTF8EncodeChar(z)
Dim c : c=AscW(z)'取UNICODE编码
if c>0 And c<256 Then'Asc编码直接返回
UTF8EncodeChar=z
Exit Function
End If
If c<0 Then c=c + &H10000&'VBScript的Integer溢出，加上
Dim k : k=CLng(c)'备份一个编码，后面判断要用
Dim b()
Dim i : i=0
While c>&H0&'将编码按照6位一组，分组存到字节数组 b 中
ReDim Preserve b(i)
b(i)=CByte(c And &H3F&)
c=c \ &H40&
i=i+1
Wend
If UBound(b)>0 Then '如果分开的6位组不止一个，除最高一组外，全部加上二进制10000000
For i=0 To UBound(b)-1
b(i)=b(i) + &H80
Next
End If
i=UBound(b)'根据字符的UNICODE编码范围，给最高组加上前缀
If k<=CLng(&H7F&) Then
b(i) = b(i) + 0
ElseIf k<=CLng(&H7FF&) Then
b(i) = b(i) + &HC0
ElseIf k<=Clng(&HFFFF&) Then
b(i) = b(i) + &HE0
ElseIf k<=CLng(&H1FFFFF&) Then
b(i) = b(i) + &HF0
ElseIf k<=CLng(&H3FFFFFF&) Then
b(i) = b(i) + &HF8
Else
b(i) = b(i) + &HFC
End If
UTF8EncodeChar=""
For i=UBound(b) To 0 Step -1'将分组转换成URL编码
UTF8EncodeChar=UTF8EncodeChar & "%" & Right("00" & Hex(b(i)),2)
Next
Erase b
End Function
Public Function UTF8EncodeString(s)
Dim i,l,c : l=Len(s)
For i=1 To l
UTF8EncodeString=UTF8EncodeString & UTF8EncodeChar(Mid(s,i,1))
Next
End Function
MsgBox UTF8EncodeString("圪圪 eglic ")
</script>
测试方法：
http://www.google.com/search?hl=zh-CN&newwindow=1&rls=GGLG%2CGGLG%3A2006-15%2CGGLG%3Azh-CN&q=你的编码
复制代码 代码如下:
function revertUTF8(szInput)
{
var x,wch,wch1,wch2,uch="",szRet="";
for (x=0; x<szInput.length; x++)
{
if (szInput.charAt(x)=="%")
{
wch =parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
if (!wch) {break;}
if (!(wch & 0x80))
{
wch = wch;
}
else if (!(wch & 0x20))
{
x++;
wch1 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
wch = (wch & 0x1F)<< 6;
wch1 = wch1 & 0x3F;
wch = wch + wch1;
}
else
{
x++;
wch1 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
x++;
wch2 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
wch = (wch & 0x0F)<< 12;
wch1 = (wch1 & 0x3F)<< 6;
wch2 = (wch2 & 0x3F);
wch = wch + wch1 + wch2;
}
szRet += String.fromCharCode(wch);
}
else
{
szRet += szInput.charAt(x);
}
}
return(szRet);
}
function u2utf8($c)
{
/*for($i=0;$i<count($c);$i++)*/
$str="";
if ($c < 0x80) {
$str.=$c;
}
else if ($c < 0x800) {
$str.=chr(0xC0 | $c>>6);
$str.=chr(0x80 | $c & 0x3F);
}
else if ($c < 0x10000) {
$str.=chr(0xE0 | $c>>12);
$str.=chr(0x80 | $c>>6 & 0x3F);
$str.=chr(0x80 | $c & 0x3F);
}
else if ($c < 0x200000) {
$str.=chr(0xF0 | $c>>18);
$str.=chr(0x80 | $c>>12 & 0x3F);
$str.=chr(0x80 | $c>>6 & 0x3F);
$str.=chr(0x80 | $c & 0x3F);
}
return $str;
}
复制代码 代码如下:
'UTF8 URLEncode
Public Function URLEncodeUTF8(ByVal s)
Dim i, k
Dim sl
Dim c
Dim uni
Dim tp, h1, h2, h3
sl = Len(s)
tp = ""
k = 0
For i = 1 To sl
c = Mid(s, i, 1)
uni = AscW(c)
If uni < 0 Then uni = uni + 65536
If uni < 128 Then
tp = tp & Chr(c)
k = k + 1
ElseIf uni < 2048 Then
k = k + 2
h2 = "%" & Hex(&H80 XOr (uni And &H3F))
uni = uni \ (2^6)
h1 = "%" & Hex(&HC0 XOr (uni And &H1F))
tp = tp & h1 & h2
Else
h3 = "%" & Hex(&H80 XOr (uni And &H3F))
uni = uni \ (2^6)
h2 = "%" & Hex(&H80 XOr (uni And &H3F))
uni = uni \ (2^6)
h1 = "%" & Hex(&HE0 XOr (uni And &H0F))
tp = tp & h1 & h2 & h3
End If
Next
URLEncodeUTF8 = tp
End Function
'A-Fa-f0-9 Byte
Public Function isxdigit(c)
isxdigit = CBool((c>=48 And c<=57) Or (c>=65 And c<=70) Or (c>=97 And c<=102))
End Function
Public Function isascii(c)
isascii = CBool(c>0 And c<128)
End Function
'判断是否是UTF8字节
Public Function IsUTF8Body(ByVal u)
IsUTF8Body = CBool(u>=&H80 And u<=&HBF)
End Function
'判断有几个UTF8字节
Private Function UTF8Byte(ByVal u)
If u > &H00 And u <= &H7F Then
UTF8Byte = 1
ElseIf u >= &HC0 And u <= &HDF Then
UTF8Byte = 2
ElseIf u >= &HE0 And u <= &HEF Then
UTF8Byte = 3
ElseIf u >= &HF0 And u <= &HF7 Then
UTF8Byte = 4
ElseIf u >= &HF8 And u <= &HFB Then
UTF8Byte = 5
ElseIf u >= &HFC And u <= &HFD Then
UTF8Byte = 6
Else
UTF8Byte = 0
End If
End Function
'判断三个连续字节是不是UTF8字符
Private Function UTF8Test(ByVal u1, ByVal u2, ByVal u3)
UTF8Test = False
If CBool(u1>=&HC0 And u1<=&HFD) Then
UTF8Test = CBool(IsUTF8Body(u2) And IsUTF8Body(u3))
End If
End Function
Private Function ishex(s)
ishex = False
If Len(s)<2 Then Exit Function
If isxdigit(Asc(Mid(s, 1, 1)))=False Then Exit Function
If isxdigit(Asc(Mid(s, 2, 1)))=False Then Exit Function
ishex = True
End Function
Private Function isescape(s)
isescape = False
If Len(s)<5 Then Exit Function
If UCase(Mid(s, 1, 1)) <> "U" Then Exit Function
If isxdigit(Asc(Mid(s, 2, 1)))=False Then Exit Function
If isxdigit(Asc(Mid(s, 3, 1)))=False Then Exit Function
If isxdigit(Asc(Mid(s, 4, 1)))=False Then Exit Function
If isxdigit(Asc(Mid(s, 5, 1)))=False Then Exit Function
isescape = True
End Function
Private Function AscX(s)
AscX = CInt("&H" & Mid(s, 1, 2))
End Function
'URLDecode 完全版
'支持Server.URLEncode，UTF8 URLEncode，Escape 加密的字符串
Public Function URLDecode(s)
Dim tp
Dim i
Dim tl
Dim pp
Dim a, b, c
Dim h
URLDecode = ""
tp = Split(Replace(s, "+", " "), "%")
tl = UBound(tp)
If tl = -1 Then Exit Function
pp = tp(0)
For i = 1 To tl
If isescape(tp(i)) Then
pp = pp & ChrW("&H" & Mid(tp(i), 2, 4)) & Mid(tp(i), 6)
ElseIf ishex(tp(i))=False Then
pp = pp & tp(i)
Else
a = AscX(tp(i))
If isascii(a)=False And Len(tp(i))=2 Then
If (i+1)>tl Then Exit For
b = AscX(tp(i+1))
If (i+2)>tl Then
pp = pp & Chr(a*2^8 Or b) & Mid(tp(i+1), 3)
i = i + 1
Else
c = AscX(tp(i+2))
If UTF8Byte(a)=3 And UTF8Test(a,b,c)=True Then
h = (a And &H0F) * 2 ^12 Or (b And &H3F) * 2 ^ 6 Or (c And &H3F)
If h<0 Then h = h + 65536
pp = pp & ChrW(h) & Mid(tp(i+2), 3)
i = i + 2
Else
pp = pp & Chr(a*2^8 Or b) & Mid(tp(i+1), 3)
i = i + 1
End If
End If
ElseIf isascii(a)=False Then
pp = pp & tp(i)
Else
pp = pp & Chr(a) & Mid(tp(i), 3)
End If
End If
Next
URLDecode = pp
End Function
URLEncodeUTF8只写了多字节的加密，没有写ascii字节的，其实也没必要写这个，有个Server.URLEncode可以用，改成js版本的倒还有用武之地
js的版本,里面有个现成的函数
<script language=javascript>
alert(encodeURI("圪圪 eglic "))
</script>
看上边有人说看不懂，我来解释下吧。梅子的第一个函数是把多字节unicode编码转成我们通常正常的编码，在JS中如果偷懒，decodeURI也可实现这个功能。不过，看到这个具体是怎么实现的，感觉好爽，回家研究去啦。复制代码 代码如下:
<script language=javascript>
function revertUTF8(szInput)
{
var x,wch,wch1,wch2,uch="",szRet="";
for (x=0; x<szInput.length; x++)
{
if (szInput.charAt(x)=="%")
{
wch =parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
if (!wch) {break;}
if (!(wch & 0x80))
{
wch = wch;
}
else if (!(wch & 0x20))
{
x++;
wch1 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
wch = (wch & 0x1F)<< 6;
wch1 = wch1 & 0x3F;
wch = wch + wch1;
}
else
{
x++;
wch1 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
x++;
wch2 = parseInt(szInput.charAt(++x) + szInput.charAt(++x),16);
wch = (wch & 0x0F)<< 12;
wch1 = (wch1 & 0x3F)<< 6;
wch2 = (wch2 & 0x3F);
wch = wch + wch1 + wch2;
}
szRet += String.fromCharCode(wch);
}
else
{
szRet += szInput.charAt(x);
}
}
return(szRet);
}
alert(revertUTF8("%E5%9C%AA%E5%9C%AA%20eglic%20 "))
alert(decodeURI("%E5%9C%AA%E5%9C%AA%20eglic%20 "))
</script>
|
|
发表于 2006-9-23 00:00:00
