很早以前网上找的代码,怕以后找不到了,先留下记录
具体逻辑我也不清楚,反正好用。
'判断文本文件格式
Public Function GetCode(ByVal myFileName As String)
Dim i As Long
Dim n As Long
Dim str1, str2, str3 As String
Open myFileName For Binary Access Read As #1
n = LOF(1) - 1
ReDim Tmp(n) As Byte
ReDim tp(n)
Get #1, , Tmp
Close #1
For i = 0 To n
tp(i) = ChrW(Tmp(i)) '返回与ANSI 字符代码相对应的字符
Next
str1 = Tmp(0) & Tmp(1) '前二个
str2 = str1 & Tmp(2) '前三个
str3 = Join(tp, "")
If str1 = "255254" Then
GetCode = "Unicode"
ElseIf str1 = "254255" Then
GetCode = "Unicode Big Endian"
ElseIf str2 = "239187191" Then
GetCode = "UTF-8"
ElseIf is_valid_utf8(str3) Then '判断是否UTF8
GetCode = "UTF8_NOBOM"
Else
GetCode = "ANSI"
End If
End Function
'下面是判断是否为UTF8
Public Function is_valid_utf8(ByRef str) 'ByRef以提高效率
Dim S, mRegExp
Set mRegExp = CreateObject("VbScript.regexp")
S = "[\xC0-\xDF]([^\x80-\xBF]|$)"
S = S & "|[\xE0-\xEF].{0,1}([^\x80-\xBF]|$)"
S = S & "|[\xF0-\xF7].{0,2}([^\x80-\xBF]|$)"
S = S & "|[\xF8-\xFB].{0,3}([^\x80-\xBF]|$)"
S = S & "|[\xFC-\xFD].{0,4}([^\x80-\xBF]|$)"
S = S & "|[\xFE-\xFE].{0,5}([^\x80-\xBF]|$)"
S = S & "|[\x00-\x7F][\x80-\xBF]"
S = S & "|[\xC0-\xDF].[\x80-\xBF]"
S = S & "|[\xE0-\xEF]..[\x80-\xBF]"
S = S & "|[\xF0-\xF7]...[\x80-\xBF]"
S = S & "|[\xF8-\xFB]....[\x80-\xBF]"
S = S & "|[\xFC-\xFD].....[\x80-\xBF]"
S = S & "|[\xFE-\xFE]......[\x80-\xBF]"
S = S & "|^[\x80-\xBF]"
mRegExp.Pattern = S
is_valid_utf8 = (Not mRegExp.test(str))
End Function
下面是具体使用方法
Debug.Print GetCode(FileName)