常用汉字utf-8编码为byte数组的计算过程（asp）

 

常用的汉字占3个字节，比如 中

普通的转法得出的结果是：[228,184,173]，但这个是不对的

t = "中"

Hunicode = replace((Tounicode(t)),"\u","") '中文转二进制，先转unicode 得出：4E2D

这里用到一个大神的进制转换函数：

Function base_convert(number, frombase, tobase)
    'Author: Demon
    'Date: 2011/12/17
    'Website: 

    Dim digits, num, ptr, i, n, c
    digits = "0123456789abcdefghijklmnopqrstuvwxyz"
    
    If frombase < 2 Or frombase > 36 Then
        Err.Raise vbObjectError + 7575,,"Invalid from base"
    End If
    
    If tobase < 2 Or tobase > 36 Then
        Err.Raise vbObjectError + 7575,,"Invalid to base"
    End If
    
    number = CStr(number) : n = Len(number)
    
    For i = 1 To n
        c = Mid(number, i, 1)
        
        If c >= "0" And c <= "9" Then
            c = c - "0"
        ElseIf c >= "A" And c <= "Z" Then
            c = Asc(c) - Asc("A") + 10
        ElseIf c >= "a" And c <= "z" Then
            c = Asc(c) - Asc("a") + 10
        Else
            c = frombase
        End If
        
        If c < frombase Then
            num = num * frombase + c
        End If
    Next
        
    Do
        ptr = ptr & Mid(digits, (num Mod tobase + 1), 1)
        num = num \ tobase
    Loop While num
    
    base_convert = StrReverse(ptr)
End Function

把中文转成3个字节的二进制。得出：

11100100  10111000 10101101

然后取反，去掉高位，转10进制+1

比如 11100100 == 》 00011011 ==》 0011011