나는 파티에 늦었습니다. 여기 전에 호주에서 작성한 Excel VBA 스크립트가 있습니다. 다른 국가를 지원하도록 쉽게 수정할 수 있습니다. 여기에 C # 코드의 GitHub 리포지토리를 만들었습니다. 내 사이트에서 호스팅했으며 여기에서 다운로드 할 수 있습니다 : http://jeremythompson.net/rocks/ParseAddress.xlsm
전략
PostCode가 숫자이거나 RegEx와 일치하는 국가의 경우 내 전략이 매우 효과적입니다.
먼저 우리는 첫 줄과 성 씨를 감지합니다. 확인란을 선택 취소하여 이름을 건너 뛰고 주소로 쉽게 시작할 수 있습니다 ( '이름은 맨 위 행'이라고 함).
다음으로 거리와 숫자로 구성된 주소가 교외보다 먼저 나오고 St, Pde, Ave, Av, Rd, Cres, 루프 등이 구분 기호라고 기대하는 것이 안전합니다.
교외 대 주 및 심지어 국가를 감지하면 충돌이 발생할 수 있으므로 가장 복잡한 파서를 속일 수 있습니다. 이를 극복하기 위해 PoBox, Ph, Fax , Mobile 등 거리와 아파트 / 장치 번호를 제거한 후 PostCode 번호 만 남아 있다는 사실을 기반으로 PostCode 조회를 사용합니다 . 이것은 정규 표현식과 쉽게 일치하여 교외와 국가를 검색 할 수 있습니다.
National Post Office Service는 교외 및 주와 함께 Excel 코드, db 테이블, text / json / xml 파일 등에 저장할 수있는 우편 번호 목록을 무료로 제공합니다.
- 마지막으로 일부 우편 번호에는 여러 교외가 있으므로 주소에 어떤 교외가 나타나는지 확인합니다.
예
VBA 코드
면책 조항, 나는이 코드가 완벽하지는 않지만 잘 작성되었지만 모든 프로그래밍 언어로 변환하고 모든 유형의 응용 프로그램에서 실행하기가 매우 쉽다는 것을 알고 있습니다. 전략은 국가 및 규칙에 따라 답입니다. :
Option Explicit
Private Const TopRow As Integer = 0
Public Sub ParseAddress()
Dim strArr() As String
Dim sigRow() As String
Dim i As Integer
Dim j As Integer
Dim k As Integer
Dim Stat As String
Dim SpaceInName As Integer
Dim Temp As String
Dim PhExt As String
On Error Resume Next
Temp = ActiveSheet.Range("Address")
'Split info into array
strArr = Split(Temp, vbLf)
'Trim the array
For i = 0 To UBound(strArr)
strArr(i) = VBA.Trim(strArr(i))
Next i
'Remove empty items/rows
ReDim sigRow(LBound(strArr) To UBound(strArr))
For i = LBound(strArr) To UBound(strArr)
If Trim(strArr(i)) <> "" Then
sigRow(j) = strArr(i)
j = j + 1
End If
Next i
ReDim Preserve sigRow(LBound(strArr) To j)
'Find the name (MUST BE ON THE FIRST ROW UNLESS CHECKBOX UNTICKED)
i = TopRow
If ActiveSheet.Shapes("chkFirst").ControlFormat.Value = 1 Then
SpaceInName = InStr(1, sigRow(i), " ", vbTextCompare) - 1
If ActiveSheet.Shapes("chkConfirm").ControlFormat.Value = 0 Then
ActiveSheet.Range("FirstName") = VBA.Left(sigRow(i), SpaceInName)
Else
If MsgBox("First Name: " & VBA.Mid$(sigRow(i), 1, SpaceInName), vbQuestion + vbYesNo, "Confirm Details") = vbYes Then ActiveSheet.Range("FirstName") = VBA.Left(sigRow(i), SpaceInName)
End If
If ActiveSheet.Shapes("chkConfirm").ControlFormat.Value = 0 Then
ActiveSheet.Range("Surname") = VBA.Mid(sigRow(i), SpaceInName + 2)
Else
If MsgBox("Surame: " & VBA.Mid(sigRow(i), SpaceInName + 2), vbQuestion + vbYesNo, "Confirm Details") = vbYes Then ActiveSheet.Range("Surname") = VBA.Mid(sigRow(i), SpaceInName + 2)
End If
sigRow(i) = ""
End If
'Find the Street by looking for a "St, Pde, Ave, Av, Rd, Cres, loop, etc"
For i = 1 To UBound(sigRow)
If Len(sigRow(i)) > 0 Then
For j = 0 To 8
If InStr(1, VBA.UCase(sigRow(i)), Street(j), vbTextCompare) > 0 Then
'Find the position of the street in order to get the suburb
SpaceInName = InStr(1, VBA.UCase(sigRow(i)), Street(j), vbTextCompare) + Len(Street(j)) - 1
'If its a po box then add 5 chars
If VBA.Right(Street(j), 3) = "BOX" Then SpaceInName = SpaceInName + 5
If ActiveSheet.Shapes("chkConfirm").ControlFormat.Value = 0 Then
ActiveSheet.Range("Street") = VBA.Mid(sigRow(i), 1, SpaceInName)
Else
If MsgBox("Street Address: " & VBA.Mid(sigRow(i), 1, SpaceInName), vbQuestion + vbYesNo, "Confirm Details") = vbYes Then ActiveSheet.Range("Street") = VBA.Mid(sigRow(i), 1, SpaceInName)
End If
'Trim the Street, Number leaving the Suburb if its exists on the same line
sigRow(i) = VBA.Mid(sigRow(i), SpaceInName) + 2
sigRow(i) = Replace(sigRow(i), VBA.Mid(sigRow(i), 1, SpaceInName), "")
GoTo PastAddress:
End If
Next j
End If
Next i
PastAddress:
'Mobile
For i = 1 To UBound(sigRow)
If Len(sigRow(i)) > 0 Then
For j = 0 To 3
Temp = Mb(j)
If VBA.Left(VBA.UCase(sigRow(i)), Len(Temp)) = Temp Then
If ActiveSheet.Shapes("chkConfirm").ControlFormat.Value = 0 Then
ActiveSheet.Range("Mobile") = VBA.Mid(sigRow(i), Len(Temp) + 2)
Else
If MsgBox("Mobile: " & VBA.Mid(sigRow(i), Len(Temp) + 2), vbQuestion + vbYesNo, "Confirm Details") = vbYes Then ActiveSheet.Range("Mobile") = VBA.Mid(sigRow(i), Len(Temp) + 2)
End If
sigRow(i) = ""
GoTo PastMobile:
End If
Next j
End If
Next i
PastMobile:
'Phone
For i = 1 To UBound(sigRow)
If Len(sigRow(i)) > 0 Then
For j = 0 To 1
Temp = Ph(j)
If VBA.Left(VBA.UCase(sigRow(i)), Len(Temp)) = Temp Then
'TODO: Detect the intl or national extension here.. or if we can from the postcode.
If ActiveSheet.Shapes("chkConfirm").ControlFormat.Value = 0 Then
ActiveSheet.Range("Phone") = VBA.Mid(sigRow(i), Len(Temp) + 3)
Else
If MsgBox("Phone: " & VBA.Mid(sigRow(i), Len(Temp) + 3), vbQuestion + vbYesNo, "Confirm Details") = vbYes Then ActiveSheet.Range("Phone") = VBA.Mid(sigRow(i), Len(Temp) + 3)
End If
sigRow(i) = ""
GoTo PastPhone:
End If
Next j
End If
Next i
PastPhone:
'Email
For i = 1 To UBound(sigRow)
If Len(sigRow(i)) > 0 Then
'replace with regEx search
If InStr(1, sigRow(i), "@", vbTextCompare) And InStr(1, VBA.UCase(sigRow(i)), ".CO", vbTextCompare) Then
Dim email As String
email = sigRow(i)
email = Replace(VBA.UCase(email), "EMAIL:", "")
email = Replace(VBA.UCase(email), "E-MAIL:", "")
email = Replace(VBA.UCase(email), "E:", "")
email = Replace(VBA.UCase(Trim(email)), "E ", "")
email = VBA.LCase(email)
If ActiveSheet.Shapes("chkConfirm").ControlFormat.Value = 0 Then
ActiveSheet.Range("Email") = email
Else
If MsgBox("Email: " & email, vbQuestion + vbYesNo, "Confirm Details") = vbYes Then ActiveSheet.Range("Email") = email
End If
sigRow(i) = ""
Exit For
End If
End If
Next i
'Now the only remaining items will be the postcode, suburb, country
'there shouldn't be any numbers (eg. from PoBox,Ph,Fax,Mobile) except for the Post Code
'Join the string and filter out the Post Code
Temp = Join(sigRow, vbCrLf)
Temp = Trim(Temp)
For i = 1 To Len(Temp)
Dim postCode As String
postCode = VBA.Mid(Temp, i, 4)
'In Australia PostCodes are 4 digits
If VBA.Mid(Temp, i, 1) <> " " And IsNumeric(postCode) Then
If ActiveSheet.Shapes("chkConfirm").ControlFormat.Value = 0 Then
ActiveSheet.Range("PostCode") = postCode
Else
If MsgBox("Post Code: " & postCode, vbQuestion + vbYesNo, "Confirm Details") = vbYes Then ActiveSheet.Range("PostCode") = postCode
End If
'Lookup the Suburb and State based on the PostCode, the PostCode sheet has the lookup
Dim mySuburbArray As Range
Set mySuburbArray = Sheets("PostCodes").Range("A2:B16670")
Dim suburbs As String
For j = 1 To mySuburbArray.Columns(1).Cells.Count
If mySuburbArray.Cells(j, 1) = postCode Then
'Check if the suburb is listed in the address
If InStr(1, UCase(Temp), mySuburbArray.Cells(j, 2), vbTextCompare) > 0 Then
'Set the Suburb and State
ActiveSheet.Range("Suburb") = mySuburbArray.Cells(j, 2)
Stat = mySuburbArray.Cells(j, 3)
ActiveSheet.Range("State") = Stat
'Knowing the State - for Australia we can get the telephone Ext
PhExt = PhExtension(VBA.UCase(Stat))
ActiveSheet.Range("PhExt") = PhExt
'remove the phone extension from the number
Dim prePhone As String
prePhone = ActiveSheet.Range("Phone")
prePhone = Replace(prePhone, PhExt & " ", "")
prePhone = Replace(prePhone, "(" & PhExt & ") ", "")
prePhone = Replace(prePhone, "(" & PhExt & ")", "")
ActiveSheet.Range("Phone") = prePhone
Exit For
End If
End If
Next j
Exit For
End If
Next i
End Sub
Private Function PhExtension(ByVal State As String) As String
Select Case State
Case Is = "NSW"
PhExtension = "02"
Case Is = "QLD"
PhExtension = "07"
Case Is = "VIC"
PhExtension = "03"
Case Is = "NT"
PhExtension = "04"
Case Is = "WA"
PhExtension = "05"
Case Is = "SA"
PhExtension = "07"
Case Is = "TAS"
PhExtension = "06"
End Select
End Function
Private Function Ph(ByVal Num As Integer) As String
Select Case Num
Case Is = 0
Ph = "PH"
Case Is = 1
Ph = "PHONE"
'Case Is = 2
'Ph = "P"
End Select
End Function
Private Function Mb(ByVal Num As Integer) As String
Select Case Num
Case Is = 0
Mb = "MB"
Case Is = 1
Mb = "MOB"
Case Is = 2
Mb = "CELL"
Case Is = 3
Mb = "MOBILE"
'Case Is = 4
'Mb = "M"
End Select
End Function
Private Function Fax(ByVal Num As Integer) As String
Select Case Num
Case Is = 0
Fax = "FAX"
Case Is = 1
Fax = "FACSIMILE"
'Case Is = 2
'Fax = "F"
End Select
End Function
Private Function State(ByVal Num As Integer) As String
Select Case Num
Case Is = 0
State = "NSW"
Case Is = 1
State = "QLD"
Case Is = 2
State = "VIC"
Case Is = 3
State = "NT"
Case Is = 4
State = "WA"
Case Is = 5
State = "SA"
Case Is = 6
State = "TAS"
End Select
End Function
Private Function Street(ByVal Num As Integer) As String
Select Case Num
Case Is = 0
Street = " ST"
Case Is = 1
Street = " RD"
Case Is = 2
Street = " AVE"
Case Is = 3
Street = " AV"
Case Is = 4
Street = " CRES"
Case Is = 5
Street = " LOOP"
Case Is = 6
Street = "PO BOX"
Case Is = 7
Street = " STREET"
Case Is = 8
Street = " ROAD"
Case Is = 9
Street = " AVENUE"
Case Is = 10
Street = " CRESENT"
Case Is = 11
Street = " PARADE"
Case Is = 12
Street = " PDE"
Case Is = 13
Street = " LANE"
Case Is = 14
Street = " COURT"
Case Is = 15
Street = " BLVD"
Case Is = 16
Street = "P.O. BOX"
Case Is = 17
Street = "P.O BOX"
Case Is = 18
Street = "PO BOX"
Case Is = 19
Street = "POBOX"
End Select
End Function