Question

我有一个1亿字符的文本文件，我正试图导入MS Access数据库。该文件没有任何换行符，因此它只是一个巨大的文本行。我尝试将其加载到字符串变量中但由于大小不起作用。然后我成功地将它加载到一个字节数组中，但我不确定如何以我需要的方式解析它。该文件具有固定长度的记录，但具有多种类型的记录。一种类型可以是180个字符的数据和220个字符的填充符，另一种类型可以是100个字符的数据和300个字符的填充符。我想将不同的记录类型分成不同的表格。我正在考虑将数据重写为400个字符块的新文本文件，然后可能使用Trim来获取我需要的数据而没有填充。从那里我可以测试行长度并导入。

这是我所拥有的，但它不起作用。

Public Sub modMain_ParseAQTFiles()

Dim bytFile(400)    As Byte
Dim intFileIn       As Integer
Dim intFileOut      As Integer
Dim intFileOut1     As Integer
Dim intFileOut2     As Integer
Dim intFFIn         As Integer
Dim intFFOut        As Integer
Dim lngBytePos      As Long
Dim dblStartChar    As Double
Dim lngNoRecs       As Long
Dim lngIndex        As Long
Dim strFileIn       As String
Dim strFileOut1     As String
Dim strFileOut2     As String
Dim strLineOfText   As String
Dim strTextLine     As String
Dim strUserName     As String

'Get username
strUserName = Environ("Username")

'Set file paths
strFileIn = "C:\Users\" & strUserName & "\Desktop\Pooltalk\aqt.txt"
strFileOut1 = "C:\Users\" & strUserName  & "\ Desktop\Pooltalk\            AQT_Quartiles_Header-out.txt"
 strFileOut2 = "C:\Users\" & strUserName & "\Desktop\Pooltalk \AQT_Quartiles_Detail-out.txt"

'Reads data into byte array
intFFIn = FreeFile
intFFOut = FreeFile
dblStartChar = 1
Open strFileIn For Binary Access Read As #intFFIn
lngNoRecs = LOF(intFFIn) / 400
For lngIndex = 1 To lngNoRecs
     Get #intFFIn, dblStartChar, bytFile
     strLineOfText = StrConv(bytFile, vbFromUnicode)
     Open strFileOut For Binary Access Write As #intFFOut
     Put intFFOut, dblStartChar, strLineOfText & vbCrLf
     Debug.Print strLineOfText
     dblStartChar = dblStartChar + 400
Next lngIndex
Close #intFFIn
Close #intFFOut

End Sub

我很高兴听到是否有人有任何建议让这个工作。感谢。

编辑：

以下是一种记录类型：

1004569 AS20170431360FCE319840701

34个字符的数据和366个空白

这是第二种记录类型：

200456906875{06875{06875{06875{06875{06875{07I07I07I07I07I07I40B40B40B40B40B40B0000630000{0000630000{0000630000{0000630000{0000630000{0000630000{48{48{48{48{48{48{05926{05926{05926{05926{05926{05926{01250{01250{01250{01250{01250{01250{06875{06875{06875{06875{06875{06875{16875{16875{16875{16875{16875{16875{

307个字符和93个空白。

这是我的最终代码：

Public Sub modMain_ParseAQTFiles()
Dim intFileIn       As Integer
Dim intFileOut1     As Integer
Dim intFFIn         As Integer
Dim intFFOut        As Integer
Dim lngNoRecs       As Long
Dim lngIndex        As Long
Dim strFileIn       As String
Dim strFileOut1     As String
Dim strUserName     As String
Dim strRecord      As String
Dim dblStartChar   As Double
Dim lngCharNo     As Long

strUserName = Environ("Username")

'Set file paths
strFileIn = "C:\Users\" & strUserName & "\Desktop\Pooltalk\aqt.txt"
strFileOut1 = "C:\Users\" & strUserName & "\Desktop\Pooltalk\AQT_Parsed.txt"

strRecord = Space$(400)
dblStartChar = 1

'Reads data into byte array
intFFIn = FreeFile
Open strFileIn For Binary Access Read As #intFFIn
intFFOut = FreeFile
Open strFileOut1 For Binary Access Write As #intFFOut

'Find number of records
lngNoRecs = LOF(intFFIn) / 400

For lngIndex = 1 To lngNoRecs
    Get #intFFIn, dblStartChar, strRecord
    strRecord = Trim(strRecord)
    Put intFFOut, , strRecord & vbCrLf
    dblStartChar = dblStartChar + 400
    strRecord = Space$(400)
Next lngIndex

Close #intFFIn
Close #intFFOut

MsgBox "Done!"
End Sub

Answer 1

如果所有记录的长度都是400个字符，我会将它们直接读入该长度的字符串变量中。

Dim strRecord As String
Dim x As Long
' Get reads as many characters as are in the target variable
strRecord = Space$(400)
Get #intFFIn, dblStartChar, strRecord 
' Find first 0-byte character
x = Instr(strRecord, Chr$(0))
' and trim off the fillers
strRecord = Left$(strRecord, x-1)

请参阅底部的https://msdn.microsoft.com/VBA/Language-Reference-VBA/articles/get-statement（示例前）。

使用MS Access使用VBA解析字节数组

1 个答案: