请教，vb.net读文本文件ANSI编码，读过后文本文件就乱码

prcstone

请教，vb.net中，读文本文件（ANSI编码），读过后文本文件就乱码，有没有办法解决，急等.......


补充内容 (2023-2-24 18:48):
以下代码由VBS转成VB.NET，VBS下是可以成功运行的。VB.NET中还有问题，不能正常运行，有懂的高手，帮修改一下，谢谢。'用法：将要更改编码的所有文件放到同一个文件夹中，将文件夹拖到该vbs上，输入要转换成的字...

prcstone

好像vb.net不支持ANSI编码

临沂-枸杞

至少把你的示例文本文件和你用的代码发出来啊_(:з」∠)_

prcstone

临沂-枸杞 发表于 2023-2-23 08:46
至少把你的示例文本文件和你用的代码发出来啊_(:з」∠)_

    Public Sub ReadFileToArray(ByVal fileName As String, ByRef LineArr As String(), ByRef arr As String())
        arr = File.ReadAllLines(fileName, Encoding.Default)
        Dim str As String = String.Join(",", arr)
        LineArr = str.Split(",")
    End Sub

prcstone

    Public Sub ReadFileToArray(ByVal fileName As String, ByRef LineArr As String(), ByRef arr As String())


        arr = File.ReadAllLines(fileName, Encoding.Default)

        Dim str As String = String.Join(",", arr)
        LineArr = str.Split(",")

    End Sub

prcstone

'用法：将要更改编码的所有文件放到同一个文件夹中，将文件夹拖到该vbs上，输入要转换成的字符编码
    Dim fso,fd,fl,f,fdpath,charset
    On Error Resume Next
    If WScript.Arguments.Length>=1 Then
        fdpath = WScript.Arguments(0)
    Else
        fdpath = InputBox("E:\xunlian\新增加的训练集\博彩","第一个参数")
        If fdpath = "" Then WScript.Quit
    End If
    If WScript.Arguments.Length>=2 Then
        charset = WScript.Arguments(1)
    Else
        charset = InputBox("UTF-8","第二个参数")
        if charset = "" then WScript.Quit
        if UCase(charset) = "ANSI" then charset = "GB2312"
    End If
    Set fso = CreateObject("scripting.filesystemobject")
    Set fd = fso.GetFolder(fdpath)
    Set fl=fd.Files
    For each f in fl
        convertct f.Path,charset
    Next
    MsgBox "字符编码转换结束",,"tya提示"
  
'将读取的文件内容以指定编码写入文件
Function convertct(filepath,charset)
    Dim FileName, FileContents, dFileContents
    FileName = filepath
    FileContents = LoadFile(FileName)
    Set savefile = CreateObject("adodb.stream")
    savefile.Type = 2  '这里1为二进制，2为文本型
    savefile.Mode = 3
    savefile.Open()
    savefile.charset = charset
    savefile.Position = savefile.Size
    savefile.Writetext(FileContents)  'write写二进制,writetext写文本型
    savefile.SaveToFile filepath,2
    savefile.Close()
    set savefile = nothing
End Function

'以文件本身编码读取文件
Function LoadFile(Path)
    Dim Stm2
    Set Stm2 = CreateObject("ADODB.Stream")
    Stm2.Type = 2
    Stm2.Mode = 3
    Stm2.Open
    Stm2.Charset = CheckCode(path)
    'Stm2.Charset = "UTF-8"
    'Stm2.Charset = "Unicode"
    'Stm2.Charset = "GB2312"
    Stm2.position = Stm2.Size
    Stm2.LoadFromFile Path
    LoadFile = Stm2.ReadText
    Stm2.Close
    Set Stm2 = Nothing
End Function

'该函数检查并返回文件的编码类型
Function CheckCode(file)
    Dim slz
    set slz = CreateObject("Adodb.Stream")
    slz.Type = 1
    slz.Mode = 3
    slz.Open
    slz.Position = 0
    slz.Loadfromfile file
    Bin=slz.read(2)
    If is_valid_utf8(read(file)) Then
        Codes="UTF-8"
    ElseIf AscB(MidB(Bin,1,1))=&HFF and AscB(MidB(Bin,2,1))=&HFE Then
        Codes="Unicode"
    Else
        Codes="GB2312"
    End if
    slz.Close
    Set slz = Nothing
    CheckCode = Codes
End Function

'将Byte()数组转成String字符串
Function read(path)
    Dim ado, a(), i, n
    Set ado = CreateObject("ADODB.Stream")
    ado.Type = 1 : ado.Open
    ado.LoadFromFile path
    n = ado.Size - 1
    ReDim a(n)
    For i = 0 To n
        a(i) = ChrW(AscB(ado.Read(1)))
    Next
    read = Join(a, "")
End Function

'准确验证文件是否为utf-8（能验证无BOM头的uft-8文件）
Function is_valid_utf8(ByRef input) 'ByRef以提高效率
    Dim s, re
    Set re = New 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]"
    re.Pattern = s
    is_valid_utf8 = (Not re.Test(input))
End Function

prcstone

'用法：将要更改编码的所有文件放到同一个文件夹中，将文件夹拖到该vbs上，输入要转换成的字符编码
    Dim fso,fd,fl,f,fdpath,charset
    On Error Resume Next
    If WScript.Arguments.Length>=1 Then
        fdpath = WScript.Arguments(0)
    Else
        fdpath = InputBox("E:\xunlian\新增加的训练集\博彩","第一个参数")
        If fdpath = "" Then WScript.Quit
    End If
    If WScript.Arguments.Length>=2 Then
        charset = WScript.Arguments(1)
    Else
        charset = InputBox("UTF-8","第二个参数")
        if charset = "" then WScript.Quit
        if UCase(charset) = "ANSI" then charset = "GB2312"
    End If
    Set fso = CreateObject("scripting.filesystemobject")
    Set fd = fso.GetFolder(fdpath)
    Set fl=fd.Files
    For each f in fl
        convertct f.Path,charset
    Next
    MsgBox "字符编码转换结束",,"tya提示"
  
'将读取的文件内容以指定编码写入文件
Function convertct(filepath,charset)
    Dim FileName, FileContents, dFileContents
    FileName = filepath
    FileContents = LoadFile(FileName)
    Set savefile = CreateObject("adodb.stream")
    savefile.Type = 2  '这里1为二进制，2为文本型
    savefile.Mode = 3
    savefile.Open()
    savefile.charset = charset
    savefile.Position = savefile.Size
    savefile.Writetext(FileContents)  'write写二进制,writetext写文本型
    savefile.SaveToFile filepath,2
    savefile.Close()
    set savefile = nothing
End Function

'以文件本身编码读取文件
Function LoadFile(Path)
    Dim Stm2
    Set Stm2 = CreateObject("ADODB.Stream")
    Stm2.Type = 2
    Stm2.Mode = 3
    Stm2.Open
    Stm2.Charset = CheckCode(path)
    'Stm2.Charset = "UTF-8"
    'Stm2.Charset = "Unicode"
    'Stm2.Charset = "GB2312"
    Stm2.position = Stm2.Size
    Stm2.LoadFromFile Path
    LoadFile = Stm2.ReadText
    Stm2.Close
    Set Stm2 = Nothing
End Function

'该函数检查并返回文件的编码类型
Function CheckCode(file)
    Dim slz
    set slz = CreateObject("Adodb.Stream")
    slz.Type = 1
    slz.Mode = 3
    slz.Open
    slz.Position = 0
    slz.Loadfromfile file
    Bin=slz.read(2)
    If is_valid_utf8(read(file)) Then
        Codes="UTF-8"
    ElseIf AscB(MidB(Bin,1,1))=&HFF and AscB(MidB(Bin,2,1))=&HFE Then
        Codes="Unicode"
    Else
        Codes="GB2312"
    End if
    slz.Close
    Set slz = Nothing
    CheckCode = Codes
End Function

'将Byte()数组转成String字符串
Function read(path)
    Dim ado, a(), i, n
    Set ado = CreateObject("ADODB.Stream")
    ado.Type = 1 : ado.Open
    ado.LoadFromFile path
    n = ado.Size - 1
    ReDim a(n)
    For i = 0 To n
        a(i) = ChrW(AscB(ado.Read(1)))
    Next
    read = Join(a, "")
End Function

'准确验证文件是否为utf-8（能验证无BOM头的uft-8文件）
Function is_valid_utf8(ByRef input) 'ByRef以提高效率
    Dim s, re
    Set re = New 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]"
    re.Pattern = s
    is_valid_utf8 = (Not re.Test(input))
End Function

mjzxlmg

1. #Region "读取文件流"
   
2.     ''' <summary>
   
3.     ''' 读取文件流
   
4.     ''' </summary>
   
5.     ''' <param name="path">文件地址</param>
   
6.     ''' <returns>返回Byte文件流</returns>
   
7.     <Runtime.CompilerServices.Extension>
   
8.     Public Function ReadFile(path As String) As String
   
9.         Using FileStream As New FileStream(path, FileMode.Open, FileAccess.Read)
   
10.             Try
    
11.                 With FileStream
    
12.                     Dim Buffur(.Length - 1) As Byte
    
13.                     .Read(Buffur, 0, .Length)
    
14.                     .Seek(0, SeekOrigin.Begin)
    
15.                     Return Buffur.BytesFormatText
    
16.                 End With
    
17.             Catch ex As IOException
    
18.                 Throw New IOException(ex.Message)
    
19.                 Return Nothing
    
20.             End Try
    
21.         End Using
    
22.     End Function
    
23. #End Region
    
24. #Region "写入文件流"
    
25.     ''' <summary>
    
26.     ''' 写入文件流
    
27.     ''' </summary>
    
28.     ''' <param name="content"></param>
    
29.     ''' <param name="path"></param>
    
30.     ''' <returns>是否成功</returns>
    
31.     Public Function WriterFile(content As String, path As String, Optional Append As Boolean = False) As Boolean
    
32.         If String.IsNullOrEmpty(content) Then Return False
    
33.         Dim Buffur() As Byte = Encoding.Default.GetBytes(content)
    
34.         Using FileStream As New FileStream(path, FileMode.Create)
    
35.             Try
    
36.                 With FileStream
    
37.                     If Append = True Then .Position = .Length
    
38.                     .Write(Buffur, 0, Buffur.Length)
    
39.                     .Close()
    
40.                 End With
    
41.                 Return True
    
42.             Catch ex As IOException
    
43.                 Throw New IOException(ex.Message)
    
44.                 Return False
    
45.             End Try
    
46.         End Using
    
47.     End Function
    
48.     ''' <summary>
    
49.     ''' 写入文件流
    
50.     ''' </summary>
    
51.     ''' <param name="sb"></param>
    
52.     ''' <param name="path"></param>
    
53.     ''' <returns></returns>
    
54.     Public Function WriterFile(sb As StringBuilder, path As String, Optional Append As Boolean = False) As Boolean
    
55.         Return sb IsNot Nothing AndAlso Not String.IsNullOrEmpty(sb.ToString) AndAlso WriterFile(sb.ToString, path, Append)
    
56.     End Function
    
57.     ''' <summary>
    
58.     ''' 写入文件流
    
59.     ''' </summary>
    
60.     ''' <param name="array"></param>
    
61.     ''' <param name="path"></param>
    
62.     ''' <param name="Append"></param>
    
63.     ''' <returns></returns>
    
64.     Public Function WriterFile(array As IEnumerable(Of String), path As String, Optional Append As Boolean = False) As Boolean
    
65.         Return array IsNot Nothing AndAlso WriterFile(String.Join(vbTab, array), path, Append)
    
66.     End Function
    
67. #End Region

复制代码