Splitting rows that contain a list of postcode prefixes into multiple rows, based on postcode area - excel

Question

I have a table with several columns of data, one of which contains a list of different combined postcode prefixes on the same row.
Here's an example of the table layout:
+------+-----------------------------+
| Col1 | Col2 |
+------+-----------------------------+
| a | AB10; AB11; DD10; DD9 |
| b | S5; SS7; AA1; AA4 |
| c | AB33; AB34; AB36; GG10; GS9 |
+------+-----------------------------+
I'm looking to split the postcode prefixes into multiple rows, based on the area of the postcode, as below:
+------+------------------+
| Col1 | Col2 |
+------+------------------+
| a | AB10; AB11 |
| a | DD10; DD9 |
| b | S5 |
| b | SS7 |
| b | AA1; AA4 |
| c | AB33; AB34; AB36 |
| c | GG10 |
| c | GS9 |
+------+------------------+
I've found a VBA solution that splits, using the semicolon as a delimiter, but not how I need it done.
Sub splitByColB()
Dim r As Range, i As Long, ar
Set r = Worksheets("Sheet1").Range("B4").End(xlUp)
Do While r.Row > 1
ar = Split(r.Value, ";")
If UBound(ar) >= 0 Then r.Value = ar(0)
For i = UBound(ar) To 1 Step -1
r.EntireRow.Copy
r.Offset(1).EntireRow.Insert
r.Offset(1).Value = ar(i)
Next
Set r = r.Offset(-1)
Loop
End Sub
I could import the table in SQLExpress, so an SQL solution would also be welcome.

Answer 1

The SQL solution I put together uses a T-SQL function called DelimitedSplit8K which works like the VB SPLIT function you are using.
-- Sample Data
DECLARE #table TABLE (Col1 CHAR(1) UNIQUE, Col2 CHAR(200));
INSERT #table (Col1,Col2) VALUES ('a','AB10; AB11; DD10; DD9'),
('b','S5; SS7; AA1; AA4'),('c','AB33; AB34; AB36; GG10; GS9');
WITH xx(Col1,i,Pre) AS
(
SELECT t2.Col1, ss.Item+'', f.Pre
FROM #table AS t2
CROSS APPLY dbo.DelimitedSplit8K(t2.Col2,';') AS s
CROSS APPLY (VALUES(RTRIM(LTRIM(s.item)))) AS ss(Item)
CROSS APPLY (VALUES(SUBSTRING(ss.Item,0,PATINDEX('%[0-9]%',ss.Item)))) AS f(Pre)
)
SELECT xx.col1, col2 = STUFF((SELECT '; '+i
FROM xx AS x2
WHERE x2.Col1 = xx.Col1 AND x2.Pre = xx.Pre
FOR XML PATH('')),1,2,'')
FROM xx
GROUP BY col1, xx.Pre;
Returns:
col1 Col2
---- ----------------------
a AB10; AB11
a DD10; DD9
b AA1; AA4
b S5
b SS7
c AB33; AB34; AB36
c GG10
c GS9
I also put together a solution that works with SQL Server 2017 which is cleaner (in case you upgrade or others or using 2017.)
-- Sample Data
DECLARE #table TABLE (Col1 CHAR(1) UNIQUE, Col2 CHAR(200));
INSERT #table (Col1,Col2) VALUES ('a','AB10; AB11; DD10; DD9'),
('b','S5; SS7; AA1; AA4'),('c','AB33; AB34; AB36; GG10; GS9');
SELECT t.Col1, split.item
FROM #table AS t
CROSS APPLY
(
SELECT STRING_AGG(ss.Item,'; ') WITHIN GROUP (ORDER BY ss.Item)
FROM #table AS t2
CROSS APPLY STRING_SPLIT(t2.Col2,';') AS s
CROSS APPLY (VALUES(TRIM(s.[value]))) AS ss(Item)
WHERE t.Col1 = t2.col1
GROUP BY SUBSTRING(ss.Item,0,PATINDEX('%[0-9]%',ss.Item))
) AS split(item);

Answer 2

you could use nested dictionary objects:
Sub splitByColB()
Dim r As Range, ar, val1, val2, prefix As String
Dim obj1 As Object, obj2 As Object
Set obj1 = CreateObject("Scripting.Dictionary")
With Worksheets("Sheet1")
For Each r In .Range("B2:B4")
Set obj2 = CreateObject("Scripting.Dictionary")
With obj2
For Each val2 In Split(Replace(r.Value2, " ", vbNullString), ";")
prefix = GetLetters(CStr(val2))
.Item(prefix) = .Item(prefix) & val2 & " "
Next
End With
Set obj1.Item(r.Offset(, -1).Value2) = obj2
Next
.Range("A2:B4").ClearContents
For Each val1 In obj1.keys
.Cells(.Rows.Count, 1).End(xlUp).Offset(1).Resize(obj1(val1).Count).Value = val1
For Each val2 In obj1(val1).keys
.Cells(.Rows.Count, 2).End(xlUp).Offset(1).Value = obj1(val1)(val2)
Next
Next
End With
End Sub
Function GetLetters(s As String) As String
Dim i As Long
Do While Not IsNumeric(Mid(s, i + 1, 1))
i = i + 1
Loop
GetLetters = Left(s, i)
End Function