Better Text Alignment using Indentation Hierarchy, Unique Line flags,...

Option Base 1
Option Explicit

Sub fxUniqueLine()
    ''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''
    ' This procedure iterates through every line of text checking  '
    ' for uniqueness by comparing it to every other line. As each  '
    ' line is confirmed unique or duplicate, it is marked as such. '
    ''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''

    Dim intLineCount As Integer
    Dim intIndentLevel As Integer
    Dim intIndex As Integer
    Dim strOriginal As String
    Dim strNew As String
    Dim strIgnore As String
    Dim intIgnore As Integer
    Dim c As Integer
    Dim i As Integer
    Dim j As Integer
    Dim k As Integer
    Dim r As Integer
    Dim bolIgnore As Boolean
    Dim arrText() As Variant
    Dim arrText2() As Variant
    Dim arrText2() As Variant
    Dim intIgnoreStrings As Integer
    Dim arrIgnoreStrings() As Variant

    ' create array of strings to ignore (i.e. ignore comments)
    Worksheets("IgnoreStrings").Select
    Cells(Worksheets("IgnoreStrings").Rows.Count, 1).End(xlUp).Select
    intIgnoreStrings = Selection.Row
    arrIgnoreStrings() = Range(Cells(1, 1), Cells(intIgnoreStrings, 2)).Value2
    ' calculate and store the length of each IgnoreString to help the loop
    For i = LBound(arrIgnoreStrings) To UBound(arrIgnoreStrings)
        arrIgnoreStrings(i, 2) = Len(arrIgnoreStrings(i, 1))
    Next

    ' get the range containing the text we want to check
    Worksheets("Text1").Select ' change "Text1" to the name of the tab in which you paste your text to check
    Cells(Worksheets("Text1").Rows.Count, 1).End(xlUp).Select
    intLineCount = Selection.Row
'    create a loop with these code blocks (above/below) to iterate through x files (ranges) to compare
'    Worksheets("Text2").Select
'    Cells(Worksheets("Text2").Rows.Count, 1).End(xlUp).Select
'    intLineCount = Selection.Row

    intIndex = 1 ' our array indexer

    For r = 1 To intLineCount ' loop through cells in rngText; ignore blank lines and IgnoreStrings
        strOriginal = Cells(r, 1).Value2 ' save the original string just in case we need it
        If strOriginal <> "" Then ' if cell is blank ignore (keep non-blank lines)
            ReDim Preserve arrText(8, intIndex) ' ReDim can only expand last dimension of array...
            arrText(1, intIndex) = intIndex ' add a line number to each kept string
            arrText(2, intIndex) = strOriginal ' store the original string
            intIgnore = 0 ' initialise character position to ignore from
            bolIgnore = False ' initialise ignore flag to false (i.e. by default do not ignore any characters from string)
            For c = 1 To (Len(strOriginal)) ' loop through characters in current line (string)
                For k = LBound(arrIgnoreStrings) To UBound(arrIgnoreStrings) ' loop through list of ignore strings for each string position
                    If Mid(strOriginal, c, arrIgnoreStrings(k, 2)) = arrIgnoreStrings(k, 1) Then ' if current IgnoreString is found
                        bolIgnore = True ' then we have to ignore all characters in the string starting from current position
                        Exit For ' exit IgnoreString check loop because we found a matching IgnoreString (only need 1 match)
                    End If
                Next ' else check next IgnoreString
                If bolIgnore Then intIgnore = c ' if line contains IgnoreString then
                If intIgnore > 0 Then ' if the IgnoreString starts after the 1st character then
                    strNew = Left(strOriginal, intIgnore - 1) ' store the part not to be ignored
                    strIgnore = Right(strOriginal, Len(strOriginal) - Len(strNew)) ' and the part to be ignored
                    Exit For ' then exit string check loop because we found an IgnoreString
                Else
                    strNew = strOriginal ' elseif no IgnoreString found then new string = original string (we will check whole line for uniqueness)
                    strIgnore = "" ' and set the ignore part to empty - there is nothing to be ignored in the line
                End If
            Next
            arrText(3, intIndex) = strNew ' store the new match string to be checked for uniqueness
            arrText(4, intIndex) = strIgnore ' store the string to be ignored
            intIndentLevel = 0
            For j = 1 To Len(strOriginal) ' loop through original string again
                If Not Mid(strOriginal, j, 1) Like " " Then ' count leading spaces to use as IndentLevel
                    Exit For ' when no more leading spaces are found exit loop - we know the IndentLevel
                Else
                    intIndentLevel = intIndentLevel + 1 ' otherwise add 1 to the IndentLevel
                End If
            Next ' check next character in string
            arrText(5, intIndex) = intIndentLevel ' store the indentation level
            arrText(6, intIndex) = intIndentLevel & "." & intIndex ' use the line number as the indentation level index
            arrText(7, intIndex) = Len(strNew) ' store the new match string length
            intIndex = intIndex + 1
        End If
    Next

    bolUnique = False
'   Loop through the source array (arrText) and mark unique lines
    For k = LBound(arrText, 2) To UBound(arrText, 2) - 1
        If Not arrText(8, k) = "Duplicate" Then
            bolUnique = True
            For j = k + 1 To UBound(arrText, 2)
                If Not arrText(8, j) = "Duplicate" Then
                    If arrText(3, k) = arrText(3, j) Then
                        arrText(8, j) = "Duplicate"
                        bolUnique = False
                    End If
                End If
            Next
            If bolUnique Then arrText(8, k) = "Unique" Else arrText(8, k) = "Duplicated"
            Debug.Print "arrText(3, " & k & ")[" & arrText(3, k) & "] is " & arrText(8, k)
        End If
    Next
    If IsEmpty(arrText(8, UBound(arrText, 2))) Then arrText(8, UBound(arrText, 2)) = "Unique"

End Sub