X-Git-Url: http://git.equinoxoli.org/?p=migration-tools.git;a=blobdiff_plain;f=extract_holdings;h=27cf58a419ad361aec61220d80d5d432a53eb4da;hp=742c6e234b7ec54fe96bb4afb26f54043e87c4a2;hb=7a654b50c2edbb1f746895a2e73e6038e59d6e93;hpb=f9d60067f67b846437130ef14bf94179206ab164 diff --git a/extract_holdings b/extract_holdings index 742c6e2..27cf58a 100755 --- a/extract_holdings +++ b/extract_holdings @@ -3,7 +3,7 @@ use strict; use warnings; use Getopt::Long; -use Equinox::Migration::MapDrivenMARCXMLProc; +use Equinox::Migration::MapDrivenMARCXMLProc 1.003; use Equinox::Migration::MARCXMLSampler; my $VERSION = '1.001'; @@ -29,41 +29,49 @@ sub extract_holdings { my ($c) = @_; print "Parsing records for extraction... "; my $m = Equinox::Migration::MapDrivenMARCXMLProc->new( marcfile => $c->{marcfile}, - mapfile => $c->{map} ); + mapfile => $c->{map}, + verbose => 1, + ); + print "Writing holdings to output file(s)...\n"; # open main holdings file open HOLDINGS, '>', ($c->{prefix} . "-HOLDINGS.pg"); - # open the files for multi mappings - # FIXME DO THIS - open X, '>', ($c->{prefix} . "-HOLDINGS-privnotes.pg"); - open Z, '>', ($c->{prefix} . "-HOLDINGS-pubnotes.pg"); - select HOLDINGS; + # create multi files + my $multis = $m->get_multis; + my %MULTIFILE = (); + for my $t ( keys %{$multis} ) { + for my $s ( keys %{$multis->{$t}}) + { open my $fh, ">", ($c->{prefix} . "-HOLDINGS-MULT-$t$s.pg"); $MULTIFILE{"$t$s"} = $fh } + } + + my $i = 0; # record counter + my $j = 0; # holdings counter - while (my $rec = $m->parse_record) { + while ( $m->{data}{recs}[$i] ) { + print HOLDINGS "BEGIN;\n\negid, hseq, " unless $j; + my $rec = $m->{data}{recs}[$i]; + my $k = 0; # holding-within-record pointer # for each holdings tag in the record... - for my $holdidx ( @{$rec->{tmap}{ $c->{holdings} }} ) { + while ( defined $rec->{tmap}{ $c->{holdings} }[$k] ) { + my $holdidx = $rec->{tmap}{ $c->{holdings} }[$k]; my $tagid = $rec->{tags}[$holdidx]{tag}; + $k++; - print STDOUT "\r", $m->recno; my @out = (); # clear the output buffer push @out, $rec->{egid}; # slug in the egid first thing - print "BEGIN;\n\negid\t" if ($m->recno == 1); + push @out, $j; # holding seq goes next # grab the unary mappings and slug 'em in for my $sub ( sort keys %{$rec->{tags}[$holdidx]{uni}} ) { push @out, $rec->{tags}[$holdidx]{uni}{$sub}; - print "l_", $m->name($tagid, $sub),"\t" - if ($m->recno == 1); + print HOLDINGS "l_", $m->name($tagid, $sub),", " unless $j; } - for my $x (@{$rec->{tags}[$holdidx]{multi}{x}} ) { - print X $rec->{egid}, "\t", - $rec->{tags}[$holdidx]{uni}{ $c->{copyid} }, - "\t$x\n"; - } - for my $z (@{$rec->{tags}[$holdidx]{multi}{z}} ) { - print Z $rec->{egid}, "\t", - $rec->{tags}[$holdidx]{uni}{ $c->{copyid} }, - "\t$z\n"; + # handle holdings multis + for my $sub ( sort keys %{$multis->{$tagid}} ) { + for my $value ( @{$rec->{tags}[$holdidx]{multi}{$sub}} ) { + my $fh = $MULTIFILE{"$tagid$sub"}; + print $fh join("\t", $rec->{egid}, $j, $value), "\n"; + } } @@ -73,19 +81,22 @@ sub extract_holdings { my $idx = $rec->{tmap}{$othertag}[0]; # get index into tags struct for my $sub ( sort keys %{$rec->{tags}[$idx]{uni}} ) { push @out, $rec->{tags}[$idx]{uni}{$sub}; - print "l_", $m->name($rec->{tags}[$idx]{tag}, $sub), "\t" - if ($m->recno == 1); + print HOLDINGS "l_", $m->name($rec->{tags}[$idx]{tag}, $sub), ", " + unless $j; } } # and dump it - print "\n" if ($m->recno == 1); - print join("\t", @out); - print "\n"; - } + print HOLDINGS "\n" unless $j; + print HOLDINGS join("\t", @out); + print HOLDINGS "\n"; + $j++; + @out = undef; + } + $i++; + print "\r$i"; } - select STDOUT; print "\n"; } @@ -94,6 +105,7 @@ sub extract_holdings { sub run_samples { my ($c) = @_; my $s; + print "Parsing records for sampling... "; if ($c->{samplemap}) { $s = Equinox::Migration::MARCXMLSampler->new( marcfile => $c->{marcfile}, mapfile => $c->{samplemap}); @@ -103,8 +115,6 @@ sub run_samples { } else { $s = Equinox::Migration::MARCXMLSampler->new( marcfile => $c->{marcfile} ); } - print "Parsing records for sampling... "; - $s->parse_records; dump_sample_overview($c, $s) if $c->{sample}; dump_sample_detail($c, $s) if ($c->{samplemap} or $c->{samplestr});