From: Dobrica Pavlinusic <dpavlin@rot13.org>
Date: Wed, 22 Nov 2023 11:27:41 +0000 (+0100)
Subject: dump merged.csv
X-Git-Url: http://git.rot13.org/?a=commitdiff_plain;h=844c5b82db1e0b773f3db45ea1e4e016aeb28be3;p=csv-join-similarity

dump merged.csv
---

diff --git a/upari.pl b/upari.pl
index 9a5c3c4..0dbb777 100755
--- a/upari.pl
+++ b/upari.pl
@@ -83,6 +83,7 @@ if ( -e $keys_file ) {
 }
 
 our $data;
+our @data_headers;
 
 foreach my $val ( 1 .. 4 ) {
 	my $file = "$val.csv";
@@ -96,11 +97,14 @@ foreach my $val ( 1 .. 4 ) {
 
 		if ( ! exists $stat->{file}->{$file}->{header} ) {
 			$stat->{file}->{$file}->{header} = $row;
+			$data_headers[$val] = $row;
 			next;
 		}
 
+		my $c_id = $row->[0];
 		my $c_s = $row->[1];
 		my $c_r = $row->[2];
+		$row->[0] =~ s/[^A-Z0-9]+//g && $stat->{file}->{$file}->{corrupt_id}->{$c_id}++ && print 'c0';
 		$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('-',
@@ -126,7 +130,7 @@ foreach my $val ( 1 .. 4 ) {
 
 		push @{ $stat->{_}->{ $id } }, $val;
 
-		$data->{$key_id}->{$val}->{$id} = $row;
+		$data->{$key_id}->{$num}->{$val} = $row;
 	}
 	close $fh;
 
@@ -198,7 +202,9 @@ foreach my $id ( sort keys %{ $stat->{_} } ) {
 					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};
+					my $o_row = delete $data->{$key_s}->{$id_s}->{$val};
+					die "FATAL: $id | $m_id | data $key_s $id_s $val" unless $o_row;
+					$data->{$key_s}->{$m_id_s}->{$val} = $o_row;
 
 				}
 				print "result val=",dump( $stat->{_}->{ $m_id } ), " result_elements=", scalar @{ $stat->{_}->{ $m_id } }, $/;
@@ -242,7 +248,27 @@ 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 
+my $out_file = 'merged.csv';
+print "out_file $out_file";
+open(my $out_fh, '>', $out_file);
+print $out_fh join(',', map { @{ $data_headers[$_] } } 1 .. 4 ), "\n";
+
+foreach my $key ( sort keys %$data ) {
+	print " $key";
+	foreach my $id ( sort keys %{ $data->{$key} } ) {
+		print $out_fh "## $id ## ";
+		foreach my $val ( 1 .. 4 ) {
+			if ( my $id_data = $data->{$key}->{$id}->{$val} ) {
+				print $out_fh join(',', @$id_data);
+			} else {
+				print $out_fh ( '_' x $#{ $data_headers[$val] } ) ; # FIXME +1?
+			}
+			print $out_fh '|' if $val < 4;
+		}
+		print $out_fh "\n";
+	}
+	print $out_fh "\n";
+}
+close $out_fh;
+print "\n", -s $out_file, " bytes created\n";
+