ASP关于编码的几个有用的函数小结(utf8)

1、'utf转gb---将utf8编码文字转换为gb编码文字

function utf2gb(utfstr)

for dig=1 to len(utfstr)
'如果utf8编码文字以%开头则进行转换
if mid(utfstr,dig,1)="%" then
'utf8编码文字大于8则转换为汉字
if len(utfstr) >= dig+8 then
gbstr=gbstr & convchinese(mid(utfstr,dig,9))
dig=dig+8
else
gbstr=gbstr & mid(utfstr,dig,1)
end if
else
gbstr=gbstr & mid(utfstr,dig,1)
end if
next
utf2gb=gbstr
end function

'utf8编码文字将转换为汉字
function convchinese(x)
a=split(mid(x,2),"%")
i=0
j=0
for i=0 to ubound(a)
a(i)=c16to2(a(i))
next
for i=0 to ubound(a)-1
digs=instr(a(i),"0")
unicode=""
for j=1 to digs-1
if j=1 then
a(i)=right(a(i),len(a(i))-digs)
unicode=unicode & a(i)
else
i=i+1
a(i)=right(a(i),len(a(i))-2)
unicode=unicode & a(i)
end if
next

if len(c2to16(unicode))=4 then
convchinese=convchinese & chrw(int("&h" & c2to16(unicode)))
else
convchinese=convchinese & chr(int("&h" & c2to16(unicode)))
end if
next
end function

'二进制代码转换为十六进制代码
function c2to16(x)
i=1
for i=1 to len(x) step 4
c2to16=c2to16 & hex(c2to10(mid(x,i,4)))
next
end function

'二进制代码转换为十进制代码
function c2to10(x)
c2to10=0
if x="0" then exit function
i=0
for i= 0 to len(x) -1
if mid(x,len(x)-i,1)="1" then c2to10=c2to10+2^(i)
next
end function

'十六进制代码转换为二进制代码
function c16to2(x)
i=0
for i=1 to len(trim(x))
tempstr= c10to2(cint(int("&h" & mid(x,i,1))))
do while len(tempstr)<4
tempstr="0" & tempstr
loop
c16to2=c16to2 & tempstr
next
end function

'十进制代码转换为二进制代码
function c10to2(x)
mysign=sgn(x)
x=abs(x)
digs=1
do
if x<2^digs then
exit do
else
digs=digs+1
end if
loop
tempnum=x

i=0
for i=digs to 1 step-1
if tempnum>=2^(i-1) then
tempnum=tempnum-2^(i-1)
c10to2=c10to2 & "1"
else
c10to2=c10to2 & "0"
end if
next
if mysign=-1 then c10to2="-" & c10to2
end function

2、'gb转utf8--将gb编码文字转换为utf8编码文字

function toutf8(szinput)
dim wch, uch, szret
dim x
dim nasc, nasc2, nasc3
'如果输入参数为空，则退出函数
if szinput = "" then
toutf8 = szinput
exit function
end if
'开始转换
for x = 1 to len(szinput)
'利用mid函数分拆gb编码文字
wch = mid(szinput, x, 1)
'利用ascw函数返回每一个gb编码文字的unicode字符代码
'注：asc函数返回的是ansi 字符代码，注意区别
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
'gb编码文字的unicode字符代码在0800 - ffff之间采用三字节模版
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

toutf8 = szret
end function

3、'gb转unicode---将gb编码文字转换为unicode编码文字

function chinese2unicode(str)
dim i
dim str_one
dim str_unicode
if(isnull(str)) then
exit function
end if
for i=1 to len(str)
str_one=mid(str,i,1)
str_unicode=str_unicode&chr(38)
str_unicode=str_unicode&chr(35)
str_unicode=str_unicode&chr(120)
str_unicode=str_unicode& hex(ascw(str_one))
str_unicode=str_unicode&chr(59)
next
chinese2unicode=str_unicode
end function

4、'url解码

function urldecode(enstr)
dim destr
dim c,i,v
destr=""
for i=1 to len(enstr)
c=mid(enstr,i,1)
if c="%" then
v=eval("&h"+mid(enstr,i+1,2))
if v<128 then
destr=destr&chr(v)
i=i+2
else
if isvalidhex(mid(enstr,i,3)) then
if isvalidhex(mid(enstr,i+3,3)) then
v=eval("&h"+mid(enstr,i+1,2)+mid(enstr,i+4,2))
destr=destr&chr(v)
i=i+5
else
v=eval("&h"+mid(enstr,i+1,2)+cstr(hex(asc(mid(enstr,i+3,1)))))
destr=destr&chr(v)
i=i+3
end if
else
destr=destr&c
end if
end if
else
if c="+" then
destr=destr&" "
else
destr=destr&c
end if
end if
next
urldecode=destr
end function

'判断是否为有效的十六进制代码
function isvalidhex(str)
dim c
isvalidhex=true
str=ucase(str)
if len(str)<>3 then isvalidhex=false:exit function
if left(str,1)<>"%" then isvalidhex=false:exit function
c=mid(str,2,1)
if not (((c>="0") and (c<="9")) or ((c>="a") and (c<="z"))) then isvalidhex=false:exit function
c=mid(str,3,1)
if not (((c>="0") and (c<="9")) or ((c>="a") and (c<="z"))) then isvalidhex=false:exit function
end function
%>