vb.net xls 到 csv 带引号？

Question

我有一个 xls 文件，或一个不带引号的 csv，使用 vb.net 需要将其转换为每个单元格周围都有引号的 csv。如果我在 MS Access 中打开不带引号的 xls/csv，请将每一列设置为文本，然后将其导出为我需要的格式。有没有更简单的方法？如果没有，我如何在 vb.net 中复制它？谢谢。

Answer 1

如果您使用.Net OLE DB provider，您可以在您的数据文件所在文件夹中的 schema.ini 文件中指定 .csv 格式的详细信息。对于“未引用”的 .csv，请参阅规范 应该是这样的

[noquotes.csv]        <-- file name
ColNameHeader=True    <-- or False
CharacterSet=1252     <-- your encoding
Format=Delimited(,)   <-- 
TextDelimiter=        <-- important: no " in source file
Col1=VendorID Integer <-- your columns, of course
Col2=AccountNumber Char Width 15

对于“引用”的 .csv，只需更改名称并删除 TextDelimiter= 行（在文本字段周围加上引号是默认设置）。

然后连接到文本数据库并执行语句

SELECT * INTO [quotes.csv] FROM [noquotes.csv]

（因为这会创建quotes.csv，您可能希望在每次实验运行之前删除该文件）

新增处理“必须引用空字段”

这是一个 VBScript 演示，但重要的是 .GetString() 的参数，您可以轻松地将其移植到 VB：

    Dim sDir   : sDir       = resolvePath( "§LibDir§testdata\txt" )
    Dim sSrc   : sSrc       = "noquotes.csv"
    Dim sSQL   : sSQL       = "SELECT * FROM [" & sSrc & "]"
    Dim oTxtDb : Set oTxtDb = New cADBC.openDb( Array( "jettxt", sDir ) )
    WScript.Echo goFS.OpenTextFile( goFS.BuildPath( sDir, sSrc ) ).ReadAll()
    Dim sAll : sAll = oTxtDb.GetSelectFRO( sSQL ).GetString( _
                             adClipString, , """,""", """" & vbCrlf & """", "" _
                      )
    WScript.Echo   """" & Left( sAll, Len( sAll ) - 1 )

和输出：

    VendorID;AccountNumber;SomethingElse
    1;ABC 123 QQQ;1,2
    2;IJK 654 ZZZ;2,3
    3;;3,4

    "1","ABC 123 QQQ","1,2"
    "2","IJK 654 ZZZ","2,3"
    "3","","3,4"

（德语区域设置，因此字段分隔符；和十进制符号，）

此 VB.Net 代码的相同输出：

    Imports ADODB
    ...

        Sub useGetString()
            Console.WriteLine("useGetString")

            Const adClipString As Integer = 2
            Dim cn As New ADODB.Connection
            Dim rs As ADODB.Recordset
            Dim sAll As String

            cn.ConnectionString = _
                 "Provider=Microsoft.Jet.OLEDB.4.0;" _
               & "Data Source=M:\lib\kurs0705\testdata\txt\;" _
               & "Extended Properties=""text;"""

            cn.Open()
            rs = cn.Execute("SELECT * FROM [noquotes.csv]") 
            sAll = rs.GetString( adClipString, , """,""", """" & vbCrLf & """", "" )
            cn.Close()
            sAll = """" & Left( sAll, Len( sAll ) - 1 )
            Console.WriteLine( sAll )
        End Sub

Answer 2

查看this link 的方法。 您可以做的是确保引号出现在将列数据放入文件的循环中，将引号附加到每个列数据的开头和结尾。

例如使循环如下：

For InnerCount = 0 To ColumnCount - 1
    Str &= """" & DS.Tables(0).Rows(OuterCount).Item(InnerCount) & ""","
Next

Answer 3

Public Class clsTest

Public Sub Test
Dim s as string = "C:\!Data\Test1.csv"

        Dim Contents As String = System.IO.File.ReadAllText(s)


        Dim aryLines As String() = Contents.Split(New String() { Environment.Newline }, StringSplitOptions.None)
        Dim aryParts() As String
        Dim aryHeader() As String
        Dim dt As System.Data.DataTable 
        For i As Integer = 0 To aryLines.Length - 1
            aryParts = SplitCSVLine(aryLines(i))
            If dt Is Nothing And aryHeader Is Nothing Then 
                aryHeader = CType(aryParts.Clone, String())
            ElseIf dt Is Nothing And aryHeader IsNot Nothing Then
                dt = DTFromStringArray(aryParts, 1000, "", aryHeader)
            Else
                DTAddStringArray(dt, aryParts)
            End If
        Next
        dt.dump
End Sub 

Public Shared Function SplitCSVLine(strCSVQuotedLine As String) As String()
        Dim aryLines As String() = strCSVQuotedLine.Split(New String() {Environment.NewLine}, StringSplitOptions.None)
        Dim aryParts As String() = Nothing
        For i As Integer = 0 To aryLines.Length - 1
            Dim regx As New Text.RegularExpressions.Regex(",(?=(?:[^\""]*\""[^\""]*\"")*(?![^\""]*\""))")
            aryParts = regx.Split(aryLines(i))
            For p As Integer = 0 To aryParts.Length - 1
                aryParts(p) = aryParts(p).Trim(" "c, """"c)
            Next
        Next
        Return aryParts
End Function

Public Shared Function DTFromStringArray(ByVal aryValues() As String, Optional ByVal intDefaultColumnWidth As Integer = 255, Optional ByVal strTableName As String = "tblArray", Optional ByVal aryColumnNames() As String = Nothing) As DataTable
        If String.IsNullOrWhiteSpace(strTableName) Then strTableName = "tblArray"
        Dim dt As DataTable = New DataTable(strTableName)
        Dim colNew(aryValues.GetUpperBound(0)) As DataColumn
        If aryColumnNames Is Nothing Then
            ReDim aryColumnNames(aryValues.Length)
        Else
            If aryColumnNames.GetUpperBound(0) < aryValues.GetUpperBound(0) Then
                ReDim Preserve aryColumnNames(aryValues.Length)
            End If
        End If
        For x As Integer = aryColumnNames.GetLowerBound(0) To aryColumnNames.GetUpperBound(0)
            If String.IsNullOrWhiteSpace(aryColumnNames(x)) Then
                aryColumnNames(x) = "Field" & x.ToString
            Else
                aryColumnNames(x) = aryColumnNames(x)
            End If
        Next
        For i As Integer = 0 To aryValues.GetUpperBound(0)
            colNew(i) = New DataColumn
            With colNew(i)
                .ColumnName = aryColumnNames(i) '"Value " & i
                .DataType = GetType(String)
                .AllowDBNull = False
                .DefaultValue = ""
                .MaxLength = intDefaultColumnWidth
                .Unique = False
            End With
        Next
        dt.Columns.AddRange(colNew)
        Dim pRow As DataRow = dt.NewRow
        For i As Integer = aryValues.GetLowerBound(0) To aryValues.GetUpperBound(0)
            pRow.Item(i) = aryValues(i)
        Next
        dt.Rows.Add(pRow)
        Return dt
End Function

Public Shared Sub DTAddStringArray(ByRef dt As DataTable, ByVal aryRowValues() As String)
        Dim pRow As DataRow
        pRow = dt.NewRow
        For i As Integer = aryRowValues.GetLowerBound(0) To aryRowValues.GetUpperBound(0)
            pRow.Item(i) = aryRowValues(i)
        Next
        dt.Rows.Add(pRow)
End Sub

End Class