#!/usr/bin/perl use strict; use warnings; use Algorithm::Diff; #use Data::Dumper; $Data::Dumper::Useqq = 1; $| = 1; { my @sets = ( [ qw( a c f g e h i ) ], # X [ qw( a b c d e f g h i ) ], # Y [ qw( a c d e f g h i ) ], # Z ); # my @sets = ( # [ qw( a b c f g ) ], # X # [ qw( a b d f g ) ], # Y # [ qw( a b e f g ) ], # Z # ); my @all_merged = merge_multiple_lists( @sets ); print dump_rotated_indexes_of_lists( @all_merged ); # foreach (@all_merged) { # my ( $item, @offsets ) = @{ $_ }; # @offsets = map { defined $_ ? $_ : ' ' } @offsets; # print "$item @offsets\n"; # } exit; } # Rotate @all_merged 90 degrees to match the expected output. sub dump_rotated_indexes_of_lists { my @lists = @_; my @idx; foreach (@lists) { my ( $item, @offsets ) = @{ $_ }; foreach my $i ( 0 .. $#offsets ) { push @{ $idx[$i] }, $offsets[$i]; } } foreach (@idx) { my $dump = join ', ', # map { sprintf '%5s', $_ } map { defined $_ ? $_ : 'undef' } @{ $_ }; print " [ $dump ],\n"; } } sub merge_multiple_lists { my @list_arefs = @_; foreach my $list_aref ( @list_arefs) { my $count = 0; $list_aref = [ map { [ $_, $count++ ] } @{ $list_aref } ]; } my $accumulator_aref = shift @list_arefs; my $offset_width = 1; foreach my $next_to_merge_aref ( @list_arefs ) { $accumulator_aref = merge_two_lists( $accumulator_aref, $next_to_merge_aref, $offset_width ); ++$offset_width; } return @{ $accumulator_aref }; } # Each list element will be an aref. # The item to be compared is in position 0. sub key_on_first_element { my ($self) = @_; return $self->[0]; } sub merge_two_lists { my ( $list1_aref, $list2_aref, $offset_width ) = @_; $offset_width = 1 if not defined $offset_width; my $diff = Algorithm::Diff->new( $list1_aref, $list2_aref, { keyGen => \&key_on_first_element }, ); my @merged; while( $diff->Next() ) { my @indices1 = $diff->Range(1); my @indices2 = $diff->Range(2); my $which_list = $diff->Diff(); # 0 means lists are identical in this chunk. if ( $which_list == 0 ) { die "Can't happen" if @indices1 != @indices2; foreach my $i ( 0 .. $#indices1 ) { my ( $item1, @offsets ) = @{ $list1_aref->[ $indices1[$i] ] }; my ( $item2, $offset ) = @{ $list2_aref->[ $indices2[$i] ] }; die unless $item1 eq $item2; push @offsets, $offset; push @merged, [ $item1, @offsets ]; } } # 1 means that only list 1 has entries in this chunk elsif ( $which_list == 1 ) { foreach ( @{ $list1_aref }[ @indices1 ] ) { my ( $item1, @offsets ) = @{ $_ }; push @offsets, undef; push @merged, [ $item1, @offsets ]; } } # 2 means that only list 2 has entries in this chunk elsif ( $which_list == 2 ) { foreach ( @{ $list2_aref }[ @indices2 ] ) { my ( $item2, $offset ) = @{ $_ }; my @offsets = map { undef() } 1 .. $offset_width; push @offsets, $offset; push @merged, [ $item2, @offsets ]; } } # 3 means both lists have entries in this chunk. # XXX # This is the "each set having a unique element" situation. # Extra code may be needed to put these into a desired order. elsif ( $which_list == 3 ) { # XXX Dup code from which_list==(1|2) foreach ( @{ $list1_aref }[ @indices1 ] ) { my ( $item1, @offsets ) = @{ $_ }; push @offsets, undef; push @merged, [ $item1, @offsets ]; } foreach ( @{ $list2_aref }[ @indices2 ] ) { my ( $item2, $offset ) = @{ $_ }; my @offsets = map { undef() } 1 .. $offset_width; push @offsets, $offset; push @merged, [ $item2, @offsets ]; } } else { die "Can't happen"; } } return \@merged; }