合并大型 excel 文件，无法绕过缓冲区溢出
Cosolidating large excel files, cant go around buffer overflow
我正在尝试使用以下代码将多个大型 excel 文件合并为一个文件
Sub Macro1()
Application.DisplayAlerts = False
Dim Country As String
Dim i As Integer
Dim j As Integer
Dim k As Integer
k = 2
For i = 1 To 50
Windows("Try2").Activate
Country = Worksheets("Names").Cells(i, 1).Value
Workbooks.Open Filename:= "C:path\" & Country & " "
ActiveWorkbook.Sheets("Main").Activate
finalrow = Cells(Rows.Count, 1).End(xlUp).Row
Workbooks(Country).Sheets("Main").Range(Cells(1, 1), Cells(10000, 64)).Copy
Workbooks("Try2").Sheets("Output").Activate
Workbooks("Try2").Sheets("Output").Cells(k, 2).PasteSpecial xlPasteValues
Range(Cells(k, 1), Cells(k + 10000, 1)) = Country
finalrow2 = 10002 + k
k = finalrow2 + 1
Workbooks(Country).Sheets("Main").Activate
Workbooks(Country).Close SaveChanges:=False
Next i
End Sub
但是在合并 2-3 个文件后 excel 它抛出缓冲区溢出错误。我们有大约 50 个文件。我想弄清楚这是否只是 excel 无法处理大文件的问题，或者我的代码有问题。有什么方法可以引导 excel 处理更大的文件吗？
这里有几件事可能会导致您的宏失效。
首先，您将 i、j 和 k 声明为 'integer' 数据类型；问题在于整数可以容纳的最大可能值是 32,767。如果超出这个范围，就会出现缓冲区溢出。
其次，您声明的是您不使用的变量，而不是声明您确实使用的变量。据我所知，j 没有在代码中的任何地方使用，但是使用了 finalrow 和 finalrow2 但没有在任何地方声明。
我建议您用 long 数据类型（长整型）替换可能非常高的 integer 数据类型。您可能还想为整数使用更具描述性的名称，以使您的代码更易于阅读：
Dim iCycler as integer
Dim kStart as long
Dim FinalRow as Long
Dim FinalRow2 as Long
运行 看看你得到了什么。
编辑添加：
这里有一个适合您的完整流程：
Sub Duplicator()
'Define the source file, sheet, and range
Dim wbkSource As Workbook
Dim shtSource As Worksheet
Dim rngSource As Range
'Define the target file, sheet and range
Dim wbkTarget As Workbook
Dim shtTarget As Worksheet
Dim rngTarget As Range
'Define the sheet with the list of countries
Dim shtControl As Worksheet
'Prepare control integers
Dim iLoop As Integer
Dim lLastRow As Long
'Define the target file as the active workbook
Set wbkTarget = ActiveWorkbook
Set shtTarget = wbkSource.Sheets("Output")
Set rngTarget = shtTarget.Range("A2")
Set shtControl = wbkTarget.Sheets("Names")
'Loop through the list
For iLoop = 1 To 50
'Open the source file and assign it to a variable.
Set wbkSource = Workbooks.Open("C:\path\" & shtControl.Cells(iLoop, 1).Value)
'Assign the source sheet
Set shtSource = wbkSource.Sheets("Main")
'Find the last row of data
lLastRow = shtSource.Range("A" & Rows.Count).End(xlUp).Row
'Use the last row to build a source range variable
Set rngSource = shtSource.Range("A1", "BL" & lLastRow)
'Check that there is space for the copy. If there is not, create a new sheet for the new data
If rngTarget.Row + lLastRow > shtTarget.Rows.Count Then
Set shtTarget = wbkTarget.Sheets.Add
shtTarget.Name = "Output 2"
Set rngTarget = shtTarget.Range("A2")
End If
'Use the size of rngSource to define the size of the target range
Set rngTarget = rngTarget.Resize(rngSource.Rows.Count, rngSource.Columns.Count)
'Duplicate the values over
rngTarget.Value = rngSource.Value
'Prepare the target range for the next loop
Set rngTarget = shtTarget.Range("A" & Rows.Count).End(xlUp).Offset(1, 0)
'Close the source file
wbkSource.Close False
Next iLoop
End Sub
通过在整个过程中声明和使用变量，代码应该更易于编写和阅读。它也应该 运行 更快，因为它使用 range1.value = range2.value 结构，它绕过了相当慢的剪贴板。它还包含一项检查，以确保您没有超过 1,048,576 行数据，否则会导致崩溃。
Werff 已经向您解释了良好的编码实践，您可以尝试其他（注释）代码：
Sub Macro1()
Dim outputSht As Worksheet '<--| declare a variable to set your "output" sheet to
Dim countryData As Variant, countryNames As Variant '<--| declare arrays to store "country names" and "country data" in
Dim country As Variant '<-- "countries" looping variable
Application.Calculation = xlCalculationManual '<-- disable calculations
Application.ScreenUpdating = False '<-- disable screen updating
With Workbooks("Try").Worksheets("Names") '<--| reference "country names" worksheet
countryNames = Application.Transpose(.Range("A1", .Cells(.Rows.count, 1).End(xlUp)).Value) '<--| store country names in column "A" from row 1 down to last not empty row
End With
Set outputSht = Workbooks("Try").Worksheets("Output") '<--| set "output" worksheet
For Each country In countryNames '<-- loop through countries stored in 'countryNames'
With Workbooks.Open(FileName:="C:path\" & Country).Sheets("Main") '<--| open current country workbook and reference its "Main" sheet
countryData = .Range("BL1", .Cells(.Rows.count, 1).End(xlUp)).Value '<--| store current country data in 'countryData' array
.Parent.Close SaveChanges:=False '<--| close current country workbook
End With
With outputSht '<--| reference output sheet
With .Cells(.Rows.count, 1).End(xlUp).Offset(1).Resize(UBound(countryData, 1)) '<--|reference its column A range from first empty cell after last not empty cell down to as many rows as current country array has
.Value = country '<--| write current country name in referenced range
.Offset(, 1).Resize(, 64).Value = countryData '<--| write country data array content from column B rightwards
End With
End With
Next country
Application.Calculation = xlCalculationAutomatic
Application.ScreenUpdating = True
End Sub
由于它使用数组存储数据，因此它受到数组最大大小限制为 65536 行的限制。如果您的 "countries" 工作簿 "Main" 工作表的行数超过此限制，则必须采用不同的粘贴值技术（例如在范围值之间）
我正在尝试使用以下代码将多个大型 excel 文件合并为一个文件
Sub Macro1()
Application.DisplayAlerts = False
Dim Country As String
Dim i As Integer
Dim j As Integer
Dim k As Integer
k = 2
For i = 1 To 50
Windows("Try2").Activate
Country = Worksheets("Names").Cells(i, 1).Value
Workbooks.Open Filename:= "C:path\" & Country & " "
ActiveWorkbook.Sheets("Main").Activate
finalrow = Cells(Rows.Count, 1).End(xlUp).Row
Workbooks(Country).Sheets("Main").Range(Cells(1, 1), Cells(10000, 64)).Copy
Workbooks("Try2").Sheets("Output").Activate
Workbooks("Try2").Sheets("Output").Cells(k, 2).PasteSpecial xlPasteValues
Range(Cells(k, 1), Cells(k + 10000, 1)) = Country
finalrow2 = 10002 + k
k = finalrow2 + 1
Workbooks(Country).Sheets("Main").Activate
Workbooks(Country).Close SaveChanges:=False
Next i
End Sub
但是在合并 2-3 个文件后 excel 它抛出缓冲区溢出错误。我们有大约 50 个文件。我想弄清楚这是否只是 excel 无法处理大文件的问题，或者我的代码有问题。有什么方法可以引导 excel 处理更大的文件吗？
这里有几件事可能会导致您的宏失效。
首先，您将 i、j 和 k 声明为 'integer' 数据类型；问题在于整数可以容纳的最大可能值是 32,767。如果超出这个范围，就会出现缓冲区溢出。
其次，您声明的是您不使用的变量，而不是声明您确实使用的变量。据我所知，j 没有在代码中的任何地方使用，但是使用了 finalrow 和 finalrow2 但没有在任何地方声明。
我建议您用 long 数据类型（长整型）替换可能非常高的 integer 数据类型。您可能还想为整数使用更具描述性的名称，以使您的代码更易于阅读：
Dim iCycler as integer
Dim kStart as long
Dim FinalRow as Long
Dim FinalRow2 as Long
运行 看看你得到了什么。
编辑添加：
这里有一个适合您的完整流程：
Sub Duplicator()
'Define the source file, sheet, and range
Dim wbkSource As Workbook
Dim shtSource As Worksheet
Dim rngSource As Range
'Define the target file, sheet and range
Dim wbkTarget As Workbook
Dim shtTarget As Worksheet
Dim rngTarget As Range
'Define the sheet with the list of countries
Dim shtControl As Worksheet
'Prepare control integers
Dim iLoop As Integer
Dim lLastRow As Long
'Define the target file as the active workbook
Set wbkTarget = ActiveWorkbook
Set shtTarget = wbkSource.Sheets("Output")
Set rngTarget = shtTarget.Range("A2")
Set shtControl = wbkTarget.Sheets("Names")
'Loop through the list
For iLoop = 1 To 50
'Open the source file and assign it to a variable.
Set wbkSource = Workbooks.Open("C:\path\" & shtControl.Cells(iLoop, 1).Value)
'Assign the source sheet
Set shtSource = wbkSource.Sheets("Main")
'Find the last row of data
lLastRow = shtSource.Range("A" & Rows.Count).End(xlUp).Row
'Use the last row to build a source range variable
Set rngSource = shtSource.Range("A1", "BL" & lLastRow)
'Check that there is space for the copy. If there is not, create a new sheet for the new data
If rngTarget.Row + lLastRow > shtTarget.Rows.Count Then
Set shtTarget = wbkTarget.Sheets.Add
shtTarget.Name = "Output 2"
Set rngTarget = shtTarget.Range("A2")
End If
'Use the size of rngSource to define the size of the target range
Set rngTarget = rngTarget.Resize(rngSource.Rows.Count, rngSource.Columns.Count)
'Duplicate the values over
rngTarget.Value = rngSource.Value
'Prepare the target range for the next loop
Set rngTarget = shtTarget.Range("A" & Rows.Count).End(xlUp).Offset(1, 0)
'Close the source file
wbkSource.Close False
Next iLoop
End Sub
通过在整个过程中声明和使用变量，代码应该更易于编写和阅读。它也应该 运行 更快，因为它使用 range1.value = range2.value 结构，它绕过了相当慢的剪贴板。它还包含一项检查，以确保您没有超过 1,048,576 行数据，否则会导致崩溃。
Werff 已经向您解释了良好的编码实践，您可以尝试其他（注释）代码：
Sub Macro1()
Dim outputSht As Worksheet '<--| declare a variable to set your "output" sheet to
Dim countryData As Variant, countryNames As Variant '<--| declare arrays to store "country names" and "country data" in
Dim country As Variant '<-- "countries" looping variable
Application.Calculation = xlCalculationManual '<-- disable calculations
Application.ScreenUpdating = False '<-- disable screen updating
With Workbooks("Try").Worksheets("Names") '<--| reference "country names" worksheet
countryNames = Application.Transpose(.Range("A1", .Cells(.Rows.count, 1).End(xlUp)).Value) '<--| store country names in column "A" from row 1 down to last not empty row
End With
Set outputSht = Workbooks("Try").Worksheets("Output") '<--| set "output" worksheet
For Each country In countryNames '<-- loop through countries stored in 'countryNames'
With Workbooks.Open(FileName:="C:path\" & Country).Sheets("Main") '<--| open current country workbook and reference its "Main" sheet
countryData = .Range("BL1", .Cells(.Rows.count, 1).End(xlUp)).Value '<--| store current country data in 'countryData' array
.Parent.Close SaveChanges:=False '<--| close current country workbook
End With
With outputSht '<--| reference output sheet
With .Cells(.Rows.count, 1).End(xlUp).Offset(1).Resize(UBound(countryData, 1)) '<--|reference its column A range from first empty cell after last not empty cell down to as many rows as current country array has
.Value = country '<--| write current country name in referenced range
.Offset(, 1).Resize(, 64).Value = countryData '<--| write country data array content from column B rightwards
End With
End With
Next country
Application.Calculation = xlCalculationAutomatic
Application.ScreenUpdating = True
End Sub
由于它使用数组存储数据，因此它受到数组最大大小限制为 65536 行的限制。如果您的 "countries" 工作簿 "Main" 工作表的行数超过此限制，则必须采用不同的粘贴值技术（例如在范围值之间）