SQL Challenge/Puzzle: How to merge nested ranges?

Question

• This challenge is based on a real life use-case involving IP ranges.
• The solution I came with is based on the stack trace challenge I\'ve presented previously

Answer 1

• The solution is based on the stack trace challenge I've presented previously. Each range start is treated as a PUSH operation and each range end + 1 is treated as a POP operation.
• Performence wise, you may notice how the 2 internal analytic functions use the same windowing, therefore being executed in a single step.

Teradata

select      new_range_start
           ,new_range_end

           ,last_value (range_val ignore nulls) over 
            (
                partition by    stack_depth
                order by        new_range_start ,range_start ,range_end desc 
                rows            unbounded preceding
            )                                                                   as new_range_val

from       (select      new_range_start
                       ,range_val
                       ,range_start
                       ,range_end

                       ,sum (case when range_val is null then -1 else 1 end) over 
                        (
                            order by    new_range_start, range_start ,range_end desc  
                            rows        unbounded preceding
                        )                                                                   as stack_depth

                       ,min (new_range_start) over
                        (
                            order by    new_range_start ,range_start ,range_end desc
                            rows        between 1 following and 1 following

                        ) - 1                                                               as new_range_end

            from        (           select range_start     ,range_start ,range_end ,range_val              from ranges
                        union all   select range_end   + 1 ,range_start ,range_end ,cast (null as char(1)) from ranges
                        )
                        r (new_range_start,range_start,range_end,range_val)
            )
            r

qualify     new_range_end >= new_range_start

order by    new_range_start
;

Oracle

select      new_range_start
           ,new_range_end
           ,new_range_val                       

from       (select      new_range_start
                       ,new_range_end

                       ,last_value (range_val ignore nulls) over 
                        (
                            partition by    stack_depth
                            order by        new_range_start ,range_start ,range_end desc 
                            rows            unbounded preceding
                        )                                                                   as new_range_val


            from       (select      new_range_start
                                   ,range_start
                                   ,range_end
                                   ,range_val

                                   ,sum (case when range_val is null then -1 else 1 end) over 
                                    (
                                        order by    new_range_start, range_start ,range_end desc  
                                        rows        unbounded preceding
                                    )                                                                as stack_depth

                                   ,lead (new_range_start) over
                                    (
                                        order by    new_range_start, range_start ,range_end desc 
                                    ) - 1                                                            as new_range_end

                        from        (           select range_start     as new_range_start ,range_start ,range_end ,range_val              from ranges
                                    union all   select range_end   + 1                    ,range_start ,range_end ,cast (null as char(1)) from ranges
                                    )
                                    r 
                        )
                        r
            )
            r

where       new_range_end >= new_range_start

order by    new_range_start
;

SQL Server / PostgreSQL / Hive

select      *

from       (select      new_range_start
                       ,new_range_end
                       ,min (range_val) over
                        (
                            partition by    stack_depth,new_range_val_group_id
                        )                                                       as new_range_val                       

            from       (select      new_range_start
                                   ,new_range_end
                                   ,range_val
                                   ,stack_depth

                                   ,count (range_val) over 
                                    (
                                        partition by    stack_depth
                                        order by        new_range_start ,range_start ,range_end desc 
                                        rows            unbounded preceding
                                    )                                                                   as new_range_val_group_id


                        from       (select      new_range_start
                                               ,range_start
                                               ,range_end
                                               ,range_val

                                               ,sum (case when range_val is null then -1 else 1 end) over 
                                                (
                                                    order by    new_range_start, range_start ,range_end desc  
                                                    rows        unbounded preceding
                                                )                                                                as stack_depth

                                               ,lead (new_range_start) over
                                                (
                                                    order by    new_range_start, range_start ,range_end desc 
                                                ) - 1                                                            as new_range_end

                                    from        (           select range_start     as new_range_start ,range_start ,range_end ,range_val                           from ranges
                                                union all   select range_end   + 1 as new_range_start ,range_start ,range_end ,cast (null as char(1)) as range_val from ranges
                                                )
                                                r 
                                    )
                                    r
                        )
                        r
            )
            r

where       new_range_end >= new_range_start

order by    new_range_start
;