好的,看起来您需要两件事:从文件中流式传输数据,并填充二维数组。
我有一个“Join2d”和一个“Split2d”函数(我记得不久前在 StackOverflow 上的另一个回复中发布了它们)。请查看代码中的注释,如果您正在处理大文件,您可能需要了解有关高效字符串处理的一些信息。
但是,它使用起来并不复杂:如果您赶时间,只需粘贴代码即可。
流式传输文件很简单,但我们对文件格式进行了假设:文件中的行是由回车字符还是回车和换行字符对分隔的?我假设'CR'而不是CRLF,但你需要检查一下。
关于格式的另一个假设是数字数据将按原样显示,而字符串或字符数据将被封装在引号中。这应该是正确的,但通常不是......并且去掉引号会增加很多处理 - 大量分配和释放字符串 - 你真的不想在一个大数组中做这些。我已经缩短了明显的逐个单元查找和替换的方法,但这仍然是大文件的问题。
如果您的文件在字符串值中嵌入了逗号,则此代码将不起作用:并且不要尝试编写一个解析器来挑选封装的文本并在将数据行拆分为单个字段时跳过这些嵌入的逗号,因为这种密集的字符串处理无法通过 VBA 优化为快速可靠的 csv 阅读器。
无论如何:这是源代码:注意 StackOverflow 的文本框控件插入的换行符:
运行代码:
请注意,您需要参考 Microsoft 脚本运行时 (system32\scrrun32.dll)
Private Sub test()
Dim arrX As Variant
arrX = ArrayFromCSVfile("MyFile.csv")
End Sub
流式传输 csv 文件。
请注意,我假设您的文件位于临时文件夹中:C:\Documents and Settings[$USERNAME]\Local Settings\Temp 您需要使用文件系统命令将文件复制到本地文件夹中:它总是比跨网络工作。
Public Function ArrayFromCSVfile( _
strName As String, _
Optional RowDelimiter As String = vbCr, _
Optional FieldDelimiter = ",", _
Optional RemoveQuotes As Boolean = True _
) As Variant
' Load a file created by FileToArray into a 2-dimensional array
' The file name is specified by strName, and it is exected to exist
' in the user's temporary folder. This is a deliberate restriction:
' it's always faster to copy remote files to a local drive than to
' edit them across the network
' RemoveQuotes=TRUE strips out the double-quote marks (Char 34) that
' encapsulate strings in most csv files.
On Error Resume Next
Dim objFSO As Scripting.FileSystemObject
Dim arrData As Variant
Dim strFile As String
Dim strTemp As String
Set objFSO = New Scripting.FileSystemObject
strTemp = objFSO.GetSpecialFolder(Scripting.TemporaryFolder).ShortPath
strFile = objFSO.BuildPath(strTemp, strName)
If Not objFSO.FileExists(strFile) Then ' raise an error?
Exit Function
End If
Application.StatusBar = "Reading the file... (" & strName & ")"
If Not RemoveQuotes Then
arrData = Join2d(objFSO.OpenTextFile(strFile, ForReading).ReadAll, RowDelimiter, FieldDelimiter)
Application.StatusBar = "Reading the file... Done"
Else
' we have to do some allocation here...
strTemp = objFSO.OpenTextFile(strFile, ForReading).ReadAll
Application.StatusBar = "Reading the file... Done"
Application.StatusBar = "Parsing the file..."
strTemp = Replace$(strTemp, Chr(34) & RowDelimiter, RowDelimiter)
strTemp = Replace$(strTemp, RowDelimiter & Chr(34), RowDelimiter)
strTemp = Replace$(strTemp, Chr(34) & FieldDelimiter, FieldDelimiter)
strTemp = Replace$(strTemp, FieldDelimiter & Chr(34), FieldDelimiter)
If Right$(strTemp, Len(strTemp)) = Chr(34) Then
strTemp = Left$(strTemp, Len(strTemp) - 1)
End If
If Left$(strTemp, 1) = Chr(34) Then
strTemp = Right$(strTemp, Len(strTemp) - 1)
End If
Application.StatusBar = "Parsing the file... Done"
arrData = Split2d(strTemp, RowDelimiter, FieldDelimiter)
strTemp = ""
End If
Application.StatusBar = False
Set objFSO = Nothing
ArrayFromCSVfile = arrData
Erase arrData
End Function
Split2d
从字符串创建二维 VBA 数组:
Public Function Split2d(ByRef strInput As String, _
Optional RowDelimiter As String = vbCr, _
Optional FieldDelimiter = vbTab, _
Optional CoerceLowerBound As Long = 0 _
) As Variant
' Split up a string into a 2-dimensional array.
' Works like VBA.Strings.Split, for a 2-dimensional array.
' Check your lower bounds on return: never assume that any array in
' VBA is zero-based, even if you've set Option Base 0
' If in doubt, coerce the lower bounds to 0 or 1 by setting
' CoerceLowerBound
' Note that the default delimiters are those inserted into the
' string returned by ADODB.Recordset.GetString
On Error Resume Next
' Coding note: we're not doing any string-handling in VBA.Strings -
' allocating, deallocating and (especially!) concatenating are SLOW.
' We're using the VBA Join & Split functions ONLY. The VBA Join,
' Split, & Replace functions are linked directly to fast (by VBA
' standards) functions in the native Windows code. Feel free to
' optimise further by declaring and using the Kernel string functions
' if you want to.
' ** THIS CODE IS IN THE PUBLIC DOMAIN **
' Nigel Heffernan Excellerando.Blogspot.com
Dim i As Long
Dim j As Long
Dim i_n As Long
Dim j_n As Long
Dim i_lBound As Long
Dim i_uBound As Long
Dim j_lBound As Long
Dim j_uBound As Long
Dim arrTemp1 As Variant
Dim arrTemp2 As Variant
arrTemp1 = Split(strInput, RowDelimiter)
i_lBound = LBound(arrTemp1)
i_uBound = UBound(arrTemp1)
If VBA.LenB(arrTemp1(i_uBound)) <= 0 Then
' clip out empty last row: a common artifact in data
'loaded from files with a terminating row delimiter
i_uBound = i_uBound - 1
End If
i = i_lBound
arrTemp2 = Split(arrTemp1(i), FieldDelimiter)
j_lBound = LBound(arrTemp2)
j_uBound = UBound(arrTemp2)
If VBA.LenB(arrTemp2(j_uBound)) <= 0 Then
' ! potential error: first row with an empty last field...
j_uBound = j_uBound - 1
End If
i_n = CoerceLowerBound - i_lBound
j_n = CoerceLowerBound - j_lBound
ReDim arrData(i_lBound + i_n To i_uBound + i_n, j_lBound + j_n To j_uBound + j_n)
' As we've got the first row already... populate it
' here, and start the main loop from lbound+1
For j = j_lBound To j_uBound
arrData(i_lBound + i_n, j + j_n) = arrTemp2(j)
Next j
For i = i_lBound + 1 To i_uBound Step 1
arrTemp2 = Split(arrTemp1(i), FieldDelimiter)
For j = j_lBound To j_uBound Step 1
arrData(i + i_n, j + j_n) = arrTemp2(j)
Next j
Erase arrTemp2
Next i
Erase arrTemp1
Application.StatusBar = False
Split2d = arrData
End Function
Join2D
将二维 VBA 数组转换为字符串:
Public Function Join2d(ByRef InputArray As Variant, _
Optional RowDelimiter As String = vbCr, _
Optional FieldDelimiter = vbTab, _
Optional SkipBlankRows As Boolean = False _
) As String
' Join up a 2-dimensional array into a string. Works like the standard
' VBA.Strings.Join, for a 2-dimensional array.
' Note that the default delimiters are those inserted into the string
' returned by ADODB.Recordset.GetString
On Error Resume Next
' Coding note: we're not doing any string-handling in VBA.Strings -
' allocating, deallocating and (especially!) concatenating are SLOW.
' We're using the VBA Join & Split functions ONLY. The VBA Join,
' Split, & Replace functions are linked directly to fast (by VBA
' standards) functions in the native Windows code. Feel free to
' optimise further by declaring and using the Kernel string functions
' if you want to.
' ** THIS CODE IS IN THE PUBLIC DOMAIN **
' Nigel Heffernan Excellerando.Blogspot.com
Dim i As Long
Dim j As Long
Dim i_lBound As Long
Dim i_uBound As Long
Dim j_lBound As Long
Dim j_uBound As Long
Dim arrTemp1() As String
Dim arrTemp2() As String
Dim strBlankRow As String
i_lBound = LBound(InputArray, 1)
i_uBound = UBound(InputArray, 1)
j_lBound = LBound(InputArray, 2)
j_uBound = UBound(InputArray, 2)
ReDim arrTemp1(i_lBound To i_uBound)
ReDim arrTemp2(j_lBound To j_uBound)
For i = i_lBound To i_uBound
For j = j_lBound To j_uBound
arrTemp2(j) = InputArray(i, j)
Next j
arrTemp1(i) = Join(arrTemp2, FieldDelimiter)
Next i
If SkipBlankRows Then
If Len(FieldDelimiter) = 1 Then
strBlankRow = String(j_uBound - j_lBound, FieldDelimiter)
Else
For j = j_lBound To j_uBound
strBlankRow = strBlankRow & FieldDelimiter
Next j
End If
Join2d = Replace(Join(arrTemp1, RowDelimiter), strBlankRow, RowDelimiter, "")
i = Len(strBlankRow & RowDelimiter)
If Left(Join2d, i) = strBlankRow & RowDelimiter Then
Mid$(Join2d, 1, i) = ""
End If
Else
Join2d = Join(arrTemp1, RowDelimiter)
End If
Erase arrTemp1
End Function
分享和享受。