cleanup output, maintain merged $data

diff --git a/upari.pl b/upari.pl
index 1755230..9a5c3c4 100755 (executable)
--- a/upari.pl
+++ b/upari.pl
@@ -82,6 +82,8 @@ if ( -e $keys_file ) {
        print "LOAD $keys_file", scalar keys %$keys, "\n";
 }
 
+our $data;
+
 foreach my $val ( 1 .. 4 ) {
        my $file = "$val.csv";
        warn "# $file\n";
@@ -89,10 +91,18 @@ foreach my $val ( 1 .. 4 ) {
        my $csv = Text::CSV->new ({ binary => 1, auto_diag => 1 });
        open my $fh, "<:encoding(utf8)", $file or die "$file: $!";
        while (my $row = $csv->getline ($fh)) {
-               $stat->{lines}->{$val}++;
-               $stat->{ $file }->{lines}++;
-               $row->[1] =~ s/\D+//g && $stat->{corrupt}->{skola}->{$val}++ && print 'c1';
-               $row->[2] =~ s/\D+//g && $stat->{corrupt}->{razred}->{$val}++ && print 'c2';
+               $stat->{file}->{$file}->{lines}++;
+               $stat->{file}->{$file}->{columns}->{ $#$row }++;
+
+               if ( ! exists $stat->{file}->{$file}->{header} ) {
+                       $stat->{file}->{$file}->{header} = $row;
+                       next;
+               }
+
+               my $c_s = $row->[1];
+               my $c_r = $row->[2];
+               $row->[1] =~ s/\D+//g && $stat->{file}->{$file}->{corrupt_s}->{$c_s}++ && print 'c1';
+               $row->[2] =~ s/\D+//g && $stat->{file}->{$file}->{corrupt_r}->{$c_r}++ && print 'c2';
                my $id = join('-',
                        uc $row->[0],
                        $row->[1],
@@ -116,18 +126,18 @@ foreach my $val ( 1 .. 4 ) {
 
                push @{ $stat->{_}->{ $id } }, $val;
 
-               $data->{$key_id}->{$val}->
+               $data->{$key_id}->{$val}->{$id} = $row;
        }
        close $fh;
 
 }
 
 
-
+my $merge_ids;
 
 my $first = 1;
 # 0.9 - 0.7 -- 0.6 is too lax
-foreach my $limit ( 0.7, 0.6 ) {
+foreach my $limit ( 0.7 ) { #, 0.6 ) {
 warn "XXX limit $limit\n";
 
 print "# total = ",scalar keys %{ $stat->{_} }, $/;
@@ -180,6 +190,16 @@ foreach my $id ( sort keys %{ $stat->{_} } ) {
                                        push @{ $stat->{_}->{ $m_id } }, $val;
                                        print "++ $m_id $val ";
                                        $stat->{merge_val}->{$val}++;
+
+                                       my ( $id_s, $s, $r ) = split('-', $id);
+                                       my $key_s = "$s-$r";
+
+                                       die "ERROR merge: $val $id $m_id exists",dump( $merge_ids->{$val}->{$key_s}->{$id_s} ) if exists $merge_ids->{$val}->{$key_s}->{$id_s};
+                                       my $m_id_s = (split('-',$m_id,3))[0];
+                                       $merge_ids->{$val}->{$key_s}->{$id_s} = $m_id_s;
+
+                                       $data->{$key_s}->{$val}->{$id_s} = delete $data->{$key_s}->{$val}->{$m_id_s};
+
                                }
                                print "result val=",dump( $stat->{_}->{ $m_id } ), " result_elements=", scalar @{ $stat->{_}->{ $m_id } }, $/;
                        }
@@ -217,6 +237,12 @@ $first++;
 print "# stat = ",dump( $stat );
 #print "# keys = ",dump( $keys );
 
-
 store $keys, $keys_file;
 
+my $merge_file = 'merge.storable';
+store $merge_ids, $merge_file;
+
+__END__
+open(my $out_fh, '>', 'merged.csv');
+foreach my $val ( 1 .. 4 ) {
+       foreach my $key_s