要直接在Excel公式中使用正则表达式,以下UDF(用户定义的函数)可能会有所帮助。 它或多或少直接将正则表达式功能公开为excel函数。
这个怎么运作
它需要2-3个参数。
要使用正则表达式的文本。
正则表达式。
格式字符串,指定结果的外观。 它可以包含Function regex(strInput As String, matchPattern As String, Optional ByVal outputPattern As String = "$0") As Variant
Dim inputRegexObj As New VBScript_RegExp_55.RegExp, outputRegexObj As New VBScript_RegExp_55.RegExp, outReplaceRegexObj As New VBScript_RegExp_55.RegExp
Dim inputMatches As Object, replaceMatches As Object, replaceMatch As Object
Dim replaceNumber As Integer
With inputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = matchPattern
End With
With outputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = "\$(\d+)"
End With
With outReplaceRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
End With
Set inputMatches = inputRegexObj.Execute(strInput)
If inputMatches.Count = 0 Then
regex = False
Else
Set replaceMatches = outputRegexObj.Execute(outputPattern)
For Each replaceMatch In replaceMatches
replaceNumber = replaceMatch.SubMatches(0)
outReplaceRegexObj.Pattern = "\$" & replaceNumber
If replaceNumber = 0 Then
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).Value)
Else
If replaceNumber > inputMatches(0).SubMatches.Count Then
'regex = "A to high $ tag found. Largest allowed is $" & inputMatches(0).SubMatches.Count & "."
regex = CVErr(xlErrValue)
Exit Function
Else
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).SubMatches(replaceNumber - 1))
End If
End If
Next
regex = outputPattern
End If
End Function,regex,$2等。 $0是整个比赛,$1及以上对应于正则表达式中的各个匹配组。 默认为$0。
一些例子
提取电子邮件地址:
=regex("Peter Gordon: some@email.com, 47", "\w+@\w+\.\w+")
=regex("Peter Gordon: some@email.com, 47", "\w+@\w+\.\w+", "$0")
结果:Function regex(strInput As String, matchPattern As String, Optional ByVal outputPattern As String = "$0") As Variant
Dim inputRegexObj As New VBScript_RegExp_55.RegExp, outputRegexObj As New VBScript_RegExp_55.RegExp, outReplaceRegexObj As New VBScript_RegExp_55.RegExp
Dim inputMatches As Object, replaceMatches As Object, replaceMatch As Object
Dim replaceNumber As Integer
With inputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = matchPattern
End With
With outputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = "\$(\d+)"
End With
With outReplaceRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
End With
Set inputMatches = inputRegexObj.Execute(strInput)
If inputMatches.Count = 0 Then
regex = False
Else
Set replaceMatches = outputRegexObj.Execute(outputPattern)
For Each replaceMatch In replaceMatches
replaceNumber = replaceMatch.SubMatches(0)
outReplaceRegexObj.Pattern = "\$" & replaceNumber
If replaceNumber = 0 Then
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).Value)
Else
If replaceNumber > inputMatches(0).SubMatches.Count Then
'regex = "A to high $ tag found. Largest allowed is $" & inputMatches(0).SubMatches.Count & "."
regex = CVErr(xlErrValue)
Exit Function
Else
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).SubMatches(replaceNumber - 1))
End If
End If
Next
regex = outputPattern
End If
End Function
提取几个子串:
=regex("Peter Gordon: some@email.com, 47", "^(.+): (.+), (\d+)$", "E-Mail: $2, Name: $1")
结果:Function regex(strInput As String, matchPattern As String, Optional ByVal outputPattern As String = "$0") As Variant
Dim inputRegexObj As New VBScript_RegExp_55.RegExp, outputRegexObj As New VBScript_RegExp_55.RegExp, outReplaceRegexObj As New VBScript_RegExp_55.RegExp
Dim inputMatches As Object, replaceMatches As Object, replaceMatch As Object
Dim replaceNumber As Integer
With inputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = matchPattern
End With
With outputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = "\$(\d+)"
End With
With outReplaceRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
End With
Set inputMatches = inputRegexObj.Execute(strInput)
If inputMatches.Count = 0 Then
regex = False
Else
Set replaceMatches = outputRegexObj.Execute(outputPattern)
For Each replaceMatch In replaceMatches
replaceNumber = replaceMatch.SubMatches(0)
outReplaceRegexObj.Pattern = "\$" & replaceNumber
If replaceNumber = 0 Then
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).Value)
Else
If replaceNumber > inputMatches(0).SubMatches.Count Then
'regex = "A to high $ tag found. Largest allowed is $" & inputMatches(0).SubMatches.Count & "."
regex = CVErr(xlErrValue)
Exit Function
Else
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).SubMatches(replaceNumber - 1))
End If
End If
Next
regex = outputPattern
End If
End Function
将单个单元格中的组合字符串拆分为多个单元格中的组件:
=regex("Peter Gordon: some@email.com, 47", "^(.+): (.+), (\d+)$", "$" & 1)
=regex("Peter Gordon: some@email.com, 47", "^(.+): (.+), (\d+)$", "$" & 2)
结果在:Function regex(strInput As String, matchPattern As String, Optional ByVal outputPattern As String = "$0") As Variant
Dim inputRegexObj As New VBScript_RegExp_55.RegExp, outputRegexObj As New VBScript_RegExp_55.RegExp, outReplaceRegexObj As New VBScript_RegExp_55.RegExp
Dim inputMatches As Object, replaceMatches As Object, replaceMatch As Object
Dim replaceNumber As Integer
With inputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = matchPattern
End With
With outputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = "\$(\d+)"
End With
With outReplaceRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
End With
Set inputMatches = inputRegexObj.Execute(strInput)
If inputMatches.Count = 0 Then
regex = False
Else
Set replaceMatches = outputRegexObj.Execute(outputPattern)
For Each replaceMatch In replaceMatches
replaceNumber = replaceMatch.SubMatches(0)
outReplaceRegexObj.Pattern = "\$" & replaceNumber
If replaceNumber = 0 Then
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).Value)
Else
If replaceNumber > inputMatches(0).SubMatches.Count Then
'regex = "A to high $ tag found. Largest allowed is $" & inputMatches(0).SubMatches.Count & "."
regex = CVErr(xlErrValue)
Exit Function
Else
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).SubMatches(replaceNumber - 1))
End If
End If
Next
regex = outputPattern
End If
End Function regex ......
如何使用
要使用此UDF,请执行以下操作(大致基于此Microsoft页面。它们有一些很好的附加信息!):
在启用宏的文件('.xlsm')中的Excel中,按Function regex(strInput As String, matchPattern As String, Optional ByVal outputPattern As String = "$0") As Variant
Dim inputRegexObj As New VBScript_RegExp_55.RegExp, outputRegexObj As New VBScript_RegExp_55.RegExp, outReplaceRegexObj As New VBScript_RegExp_55.RegExp
Dim inputMatches As Object, replaceMatches As Object, replaceMatch As Object
Dim replaceNumber As Integer
With inputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = matchPattern
End With
With outputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = "\$(\d+)"
End With
With outReplaceRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
End With
Set inputMatches = inputRegexObj.Execute(strInput)
If inputMatches.Count = 0 Then
regex = False
Else
Set replaceMatches = outputRegexObj.Execute(outputPattern)
For Each replaceMatch In replaceMatches
replaceNumber = replaceMatch.SubMatches(0)
outReplaceRegexObj.Pattern = "\$" & replaceNumber
If replaceNumber = 0 Then
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).Value)
Else
If replaceNumber > inputMatches(0).SubMatches.Count Then
'regex = "A to high $ tag found. Largest allowed is $" & inputMatches(0).SubMatches.Count & "."
regex = CVErr(xlErrValue)
Exit Function
Else
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).SubMatches(replaceNumber - 1))
End If
End If
Next
regex = outputPattern
End If
End Function以打开Microsoft Visual Basic for Applications Editor。
将VBA引用添加到Regular Expressions库(从Portland Runners ++回答中无耻地复制):点击工具 - > 参考文献(请原谅德国截图)
在列表中找到Microsoft VBScript Regular Expressions 5.5并勾选旁边的复选框。
单击确定。
单击“插入模块”。 如果为模块指定了不同的名称,请确保模块与下面的UDF名称不同(例如,命名模块Function regex(strInput As String, matchPattern As String, Optional ByVal outputPattern As String = "$0") As Variant
Dim inputRegexObj As New VBScript_RegExp_55.RegExp, outputRegexObj As New VBScript_RegExp_55.RegExp, outReplaceRegexObj As New VBScript_RegExp_55.RegExp
Dim inputMatches As Object, replaceMatches As Object, replaceMatch As Object
Dim replaceNumber As Integer
With inputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = matchPattern
End With
With outputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = "\$(\d+)"
End With
With outReplaceRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
End With
Set inputMatches = inputRegexObj.Execute(strInput)
If inputMatches.Count = 0 Then
regex = False
Else
Set replaceMatches = outputRegexObj.Execute(outputPattern)
For Each replaceMatch In replaceMatches
replaceNumber = replaceMatch.SubMatches(0)
outReplaceRegexObj.Pattern = "\$" & replaceNumber
If replaceNumber = 0 Then
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).Value)
Else
If replaceNumber > inputMatches(0).SubMatches.Count Then
'regex = "A to high $ tag found. Largest allowed is $" & inputMatches(0).SubMatches.Count & "."
regex = CVErr(xlErrValue)
Exit Function
Else
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).SubMatches(replaceNumber - 1))
End If
End If
Next
regex = outputPattern
End If
End Function,函数regex导致#NAME!错误)。
在中间的大文本窗口中插入以下内容:
Function regex(strInput As String, matchPattern As String, Optional ByVal outputPattern As String = "$0") As Variant
Dim inputRegexObj As New VBScript_RegExp_55.RegExp, outputRegexObj As New VBScript_RegExp_55.RegExp, outReplaceRegexObj As New VBScript_RegExp_55.RegExp
Dim inputMatches As Object, replaceMatches As Object, replaceMatch As Object
Dim replaceNumber As Integer
With inputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = matchPattern
End With
With outputRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
.Pattern = "\$(\d+)"
End With
With outReplaceRegexObj
.Global = True
.MultiLine = True
.IgnoreCase = False
End With
Set inputMatches = inputRegexObj.Execute(strInput)
If inputMatches.Count = 0 Then
regex = False
Else
Set replaceMatches = outputRegexObj.Execute(outputPattern)
For Each replaceMatch In replaceMatches
replaceNumber = replaceMatch.SubMatches(0)
outReplaceRegexObj.Pattern = "\$" & replaceNumber
If replaceNumber = 0 Then
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).Value)
Else
If replaceNumber > inputMatches(0).SubMatches.Count Then
'regex = "A to high $ tag found. Largest allowed is $" & inputMatches(0).SubMatches.Count & "."
regex = CVErr(xlErrValue)
Exit Function
Else
outputPattern = outReplaceRegexObj.Replace(outputPattern, inputMatches(0).SubMatches(replaceNumber - 1))
End If
End If
Next
regex = outputPattern
End If
End Function
保存并关闭Microsoft Visual Basic for Applications Editor窗口。