use autodie;
use locale;
use Text::Unaccent;
+use Carp qw(confess);
use lib '/srv/koha_ffzg';
use C4::Context;
use XML::LibXML;
use XML::LibXSLT;
-use XML::Simple;
my $dbh = C4::Context->dbh;
+sub debug {
+ my ($title, $data) = @_;
+ print "# $title ",dump($data), $/ if $ENV{DEBUG};
+}
+
my $xslfilename = 'compact.xsl';
+my $auth_header;
+my $auth_department;
+my @authors;
+
+my $skip;
+
+my $sth_auth = $dbh->prepare(q{
+select
+ authid,
+ ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="a"]') as full_name,
+ ExtractValue(marcxml,'//datafield[@tag="680"]/subfield[@code="a"]') as department
+from auth_header
+});
+
+$sth_auth->execute();
+while( my $row = $sth_auth->fetchrow_hashref ) {
+ if ( $row->{department} !~ m/Filozofski fakultet u Zagrebu/ ) {
+ push @{ $skip->{nije_ffzg} }, $row;
+ next;
+ }
+ $auth_header->{ $row->{authid} } = $row->{full_name};
+ $row->{department} =~ s/, Filozofski fakultet u Zagrebu.*$//;
+ $row->{department} =~ s/^.+\.\s*//;
+# warn dump( $row );
+ push @{ $auth_department->{ $row->{department} } }, $row->{authid};
+ push @authors, $row;
+
+}
+
+debug 'auth_department' => $auth_department;
+
+
my $authors;
my $marcxml;
my $sth_select_authors = $dbh->prepare(q{
select
biblionumber,
- ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="9"]') as first_author,
- ExtractValue(marcxml,'//datafield[@tag="700"]/subfield[@code="9"]') as other_authors,
- ExtractValue(marcxml,'//datafield[@tag="942"]/subfield[@code="t"]') as category,
itemtype,
marcxml
from biblioitems
where
agerestriction > 0
- and SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) between 2008 and 2013
-order by SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) desc
});
+=for sql
+-- ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="9"]') as first_author,
+-- ExtractValue(marcxml,'//datafield[@tag="700"]/subfield[@code="9"]') as other_authors,
+-- ExtractValue(marcxml,'//datafield[@tag="942"]/subfield[@code="t"]') as category,
+
+-- and SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) between 2008 and 2013
+-- order by SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) desc
+=cut
+
+my $biblio_year;
+my $type_stats;
+
+my $parser = XML::LibXML->new();
+$parser->recover_silently(0); # don't die when you find &, >, etc
+my $style_doc = $parser->parse_file($xslfilename);
+my $xslt = XML::LibXSLT->new();
+my $parsed = $xslt->parse_stylesheet($style_doc);
+
+my $biblio_html;
+my $biblio_parsed;
+my $biblio_in_database;
+
+open(my $xml_fh, '>', '/tmp/bibliografija.xml') if $ENV{XML};
+
+sub biblioitem_html {
+ my ($biblionumber, $parse_only) = @_;
+
+ return $biblio_html->{$biblionumber} if exists $biblio_html->{$biblionumber} && ! $parse_only;
+
+ my $xmlrecord = $marcxml->{$biblionumber} || confess "missing $biblionumber marcxml";
+
+ print $xml_fh $xmlrecord if $ENV{XML};
+
+ my $source = eval { $parser->parse_string($xmlrecord) };
+ if ( $@ ) {
+# warn "SKIP $biblionumber corrupt XML";
+ push @{ $skip->{XML_corrupt} }, $biblionumber;
+ return;
+ }
+
+ if ( $parse_only ) {
+ $biblio_parsed->{$biblionumber} = $source;
+ return $source;
+ }
+
+ my $transformed = $parsed->transform($source);
+ $biblio_html->{$biblionumber} = $parsed->output_string( $transformed );
+
+ delete $biblio_parsed->{$biblionumber};
+
+ return $biblio_html->{$biblionumber};
+}
+
$sth_select_authors->execute();
while( my $row = $sth_select_authors->fetchrow_hashref ) {
# warn dump($row),$/;
- if ( $row->{first_author} || $row->{itemtype} !~ m/^KNJ/ ) {
- my $all_authors = join(' ', $row->{first_author}, $row->{other_authors});
- foreach my $authid ( split(/\s+/, $all_authors) ) {
- push @{ $authors->{$authid}->{ $row->{category} } }, $row->{biblionumber};
- $marcxml->{ $row->{biblionumber} } = $row->{marcxml};
- }
- } else {
- my $xml = XMLin( $row->{marcxml}, ForceArray => [ 'subfield' ] );
- foreach my $f700 ( map { $_->{subfield} } grep { $_->{tag} eq 700 } @{ $xml->{datafield} } ) {
- my $authid = 0;
- my $is_edt = 0;
- foreach my $sf ( @$f700 ) {
- if ( $sf->{code} eq '4' && $sf->{content} =~ m/^edt/ ) {
- $is_edt++;
- } elsif ( $sf->{code} eq '9' ) {
- $authid = $sf->{content};
+
+ my $biblio;
+
+ $marcxml->{ $row->{biblionumber} } = $row->{marcxml};
+
+ my $doc = biblioitem_html( $row->{biblionumber}, 1 );
+ if ( ! $doc ) {
+# warn "ERROR can't parse MARCXML ", $row->{biblionumber}, " ", $row->{marcxml}, "\n";
+ next;
+ }
+
+ my $root = $doc->documentElement;
+=for leader
+ my @leaders = $root->getElementsByLocalName('leader');
+ if (@leaders) {
+ my $leader = $leaders[0]->textContent;
+ warn "leader $leader\n";
+ }
+=cut
+
+ my $extract = {
+ '008' => undef,
+ '100' => '9',
+ '700' => '(9|4)',
+ '942' => '(t|r)'
+ };
+
+ my $data;
+
+ foreach my $elt ($root->getChildrenByLocalName('*')) {
+ my $tag = $elt->getAttribute('tag');
+ next if ! $tag;
+ next unless exists $extract->{ $tag };
+
+ if ($elt->localname eq 'controlfield') {
+ if ( $tag eq '008' ) {
+ my $year = substr($elt->textContent, 7, 4 );
+ if ( $year !~ m/^\d+$/ ) {
+ $year = 0;
+ push @{ $skip->{invalid_year} }, $row->{biblionumber};
}
+ $biblio_year->{ $row->{biblionumber} } = $data->{year} = $year;
}
- if ( $authid && $is_edt ) {
-# warn "# ++ ", $row->{biblionumber}, " $authid f700 ", dump( $f700 );
- push @{ $authors->{$authid}->{ $row->{category} } }, $row->{biblionumber};
- $marcxml->{ $row->{biblionumber} } = $row->{marcxml};
- } else {
-# warn "# -- ", $row->{biblionumber}, " f700 ", dump( $f700 );
+ next;
+ } elsif ($elt->localname eq 'datafield') {
+ my $sf_data;
+ foreach my $sfelt ($elt->getChildrenByLocalName('subfield')) {
+ my $sf = $sfelt->getAttribute('code');
+ next unless $sf =~ m/$extract->{$tag}/;
+ if ( exists $sf_data->{$sf} ) {
+ $sf_data->{$sf} .= " " . $sfelt->textContent();
+ } else {
+ $sf_data->{$sf} = $sfelt->textContent();
+ }
}
- }
+ push @{ $data->{$tag} }, $sf_data if $sf_data;
+ }
+ }
+
+ if ( $data->{year} < 2008 ) {
+ push @{ $skip->{year_lt_2008} }, $row->{biblionumber};
+ next;
+ } elsif ( $data->{year} > 2013 ) {
+ push @{ $skip->{year_gt_2013} }, $row->{biblionumber};
+ next;
}
-}
-my $auth_header;
-my $auth_department;
-my @authors;
+# warn "# ", $row->{biblionumber}, " data ",dump($data);
-my $all_authids = join(',', grep { length($_) > 0 } keys %$authors);
-my $sth_auth = $dbh->prepare(q{
-select
- authid,
- ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="a"]') as full_name,
- ExtractValue(marcxml,'//datafield[@tag="680"]/subfield[@code="a"]') as department
-from auth_header
-where
- authid in (} . $all_authids . q{)
-});
+ my $category = $data->{942}->[0]->{'t'};
+ if ( ! $category ) {
+# warn "# SKIP ", $row->{biblionumber}, " no category in ", dump($data);
+ push @{ $skip->{no_category} }, $row->{biblionumber};
+ next;
+ }
-$sth_auth->execute();
-while( my $row = $sth_auth->fetchrow_hashref ) {
- $auth_header->{ $row->{authid} } = $row->{full_name};
- $row->{department} =~ s/, Filozofski fakultet u Zagrebu\s*// || next;
- $row->{department} =~ s/^.+\.\s*//;
- push @{ $auth_department->{ $row->{department} } }, $row->{authid};
-# warn dump( $row );
- push @authors, $row;
+ if ( my $in_database = $data->{942}->[0]->{'r'} ) {
+ $biblio_in_database->{ $row->{biblionumber} } = $in_database;
+ }
+
+ my $have_100 = 1;
+
+ if ( exists $data->{100} ) {
+ my @first_author = map { $_->{'9'} } @{ $data->{100} };
+ foreach my $authid ( @first_author ) {
+ push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber};
+ }
+ } else {
+ $have_100 = 0;
+ }
+
+ my $have_edt;
+
+ if ( exists $data->{700} ) {
+ foreach my $auth ( @{ $data->{700} } ) {
+ my $authid = $auth->{9} || next;
+ my $type = $auth->{4} || next; #die "no 4 in ",dump($data);
+
+ $type_stats->{$type}++;
+
+ if ( $type =~ m/(edt|trl|com|ctb)/ ) {
+ push @{ $authors->{$authid}->{sec}->{ $category } }, $row->{biblionumber};
+ push @{ $authors->{$authid}->{$1}->{ $category } }, $row->{biblionumber};
+ } elsif ( $type =~ m/aut/ ) {
+ if ( ! $have_100 ) {
+ $have_edt = grep { exists $_->{4} && $_->{4} =~ m/edt/ } @{ $data->{700} } if ! defined $have_edt;
+ if ( $have_edt ) {
+ $skip->{ have_700_edt }->{ $row->{biblionumber} }++;
+ } else {
+ push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber};
+ }
+ } else {
+ push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber};
+ }
+ } else {
+# warn "# SKIP ", $row->{biblionumber}, ' no 700$4 in ', dump($data);
+ $skip->{ 'no_700$4' }->{ $row->{biblionumber} }++;
+ }
+ }
+ }
}
+debug 'authors' => $authors;
+debug 'type_stats' => $type_stats;
+debug 'skip' => $skip;
+debug 'biblio_year' => $biblio_year;
+debug 'biblio_in_database' => $biblio_in_database;
+
my $category_label;
my $sth_categories = $dbh->prepare(q{
select authorised_value, lib from authorised_values where category = 'BIBCAT'
$category_label->{ $row->{authorised_value} } = $row->{lib};
}
-#warn dump( $category_label );
+debug 'category_label' => $category_label;
sub html_title {
return qq|<html>
return qq|</body>\n</html\n|;
}
-my $biblio_html;
-
-sub biblioitem_html {
- my $biblionumber = shift;
+mkdir 'html' unless -d 'html';
- return $biblio_html->{$biblionumber} if exists $biblio_html->{$biblionumber};
+open(my $index, '>:encoding(utf-8)', 'html/index.new');
+print $index html_title('Bibliografija Filozofskog fakulteta');
- my $xmlrecord = $marcxml->{$biblionumber} || die "missing $biblionumber marcxml";
+my $first_letter = '';
- my $parser = XML::LibXML->new();
- $parser->recover_silently(0); # don't die when you find &, >, etc
- my $source = $parser->parse_string($xmlrecord);
- my $style_doc = $parser->parse_file($xslfilename);
+debug 'authors' => \@authors;
- my $xslt = XML::LibXSLT->new();
- my $parsed = $xslt->parse_stylesheet($style_doc);
- my $transformed = $parsed->transform($source);
- return $biblio_html->{$biblionumber} = $parsed->output_string( $transformed );
+sub li_biblio {
+ my ($biblionumber) = @_;
+ return qq|<li>|,
+ qq|<a href="https://koha.ffzg.hr/cgi-bin/koha/opac-detail.pl?biblionumber=$biblionumber">$biblionumber</a>|,
+ biblioitem_html($biblionumber),
+ qq|<a href="https://koha.ffzg.hr:8443/cgi-bin/koha/cataloguing/addbiblio.pl?biblionumber=$biblionumber">edit</a>|,
+ qq|</li>\n|;
}
+sub author_html {
+ my ( $fh, $authid, $type, $label ) = @_;
-mkdir 'html' unless -d 'html';
+ return unless exists $authors->{$authid}->{$type};
-open(my $index, '>:encoding(utf-8)', 'html/index.new');
-print $index html_title('Bibliografija Filozofskog fakulteta');
+ print $fh qq|<h2>$label</h2>\n|;
-my $first_letter = '';
+ foreach my $category ( sort keys %{ $authors->{$authid}->{$type} } ) {
+ my $label = $category_label->{$category} || 'Bez kategorije';
+ print $fh qq|<h3>$label</h3>\n<ul>\n|;
+ foreach my $biblionumber ( @{ $authors->{$authid}->{$type}->{$category} } ) {
+ print $fh li_biblio( $biblionumber );
+ }
+ print $fh qq|</ul>\n|;
+ }
+}
foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) {
open(my $fh, '>:encoding(utf-8)', "$path.new");
print $fh html_title($row->{full_name}, "bibliografija");
print $fh qq|<h1>$row->{full_name} - bibliografija za razdoblje 2008-2013</h1>|;
- foreach my $category ( sort keys %{ $authors->{ $row->{authid} } } ) {
- my $label = $category_label->{$category} || 'Bez kategorije';
- print $fh qq|<h2>$label</h2>\n<ul>\n|;
- foreach my $biblionumber ( @{ $authors->{ $row->{authid} }->{$category} } ) {
- print $fh qq|<li>|,
- qq|<a href="https://koha.ffzg.hr/cgi-bin/koha/opac-detail.pl?biblionumber=$biblionumber">$biblionumber</a>|,
- biblioitem_html($biblionumber),
- qq|<a href="https://koha.ffzg.hr:8443/cgi-bin/koha/cataloguing/addbiblio.pl?biblionumber=$biblionumber">edit</a>|,
- qq|</li>\n|;
- }
- print $fh qq|</ul>\n|;
- }
+
+ author_html( $fh, $row->{authid}, 'aut' => 'Primarno autorstvo' );
+ author_html( $fh, $row->{authid}, 'sec' => 'Uredništva, prijevodi, krička izdanja' );
+
print $fh html_end;
close($fh);
rename "$path.new", "$path.html";
close($index);
rename 'html/index.new', 'html/index.html';
-#print dump( $authors );
-
-#print dump( $auth_header );
-
-#print dump( $auth_department );
+debug 'auth_header' => $auth_header;
my $department_category_author;
foreach my $department ( sort keys %$auth_department ) {
foreach my $authid ( sort @{ $auth_department->{$department} } ) {
- foreach my $category ( sort keys %{ $authors->{$authid} } ) {
+ my @categories = keys %{ $authors->{$authid}->{aut} };
+ push @categories, keys %{ $authors->{$authid}->{sec} };
+ foreach my $category ( sort @categories ) {
push @{ $department_category_author->{$department}->{$category} }, $authid;
}
}
}
-#print dump( $department_category_author );
+debug 'department_category_author' => $department_category_author;
mkdir 'html/departments' unless -d 'html/departments';
+sub unique_biblionumber {
+ my @v = @_;
+ my $u;
+ $u->{$_}++ foreach @v;
+ return sort { $biblio_year->{$b} <=> $biblio_year->{$a} || $a <=> $b } keys %$u;
+}
+
open(my $dep_fh, '>:encoding(utf-8)', 'html/departments/index.new');
print $dep_fh html_title('Odsijeci Filozofskog fakulteta u Zagrebu'), qq|<ul>\n|;
foreach my $department ( sort keys %$department_category_author ) {
my $dep_file = unac_string('utf-8',$dep);
print $dep_fh qq|<li><a href="$dep_file.html">$dep</a></li>\n|;
open(my $fh, '>:encoding(utf-8)', "html/departments/$dep_file.new");
+
print $fh html_title($department . ' bibliografija');
+ print $fh qq|<h1>$department bibliografija</h1>\n|;
+
+ print $fh qq|<h2>Primarno autorstvo</h2>\n|;
+
foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
+
+ my @authids = @{ $department_category_author->{$department}->{$category} };
+ next unless @authids;
+
+ my @biblionumber = unique_biblionumber map { @{ $authors->{$_}->{aut}->{$category} } } grep { exists $authors->{$_}->{aut}->{$category} } @authids;
+ my $unique;
+ $unique->{$_}++ foreach @biblionumber;
+
+ next unless @biblionumber;
+
my $label = $category_label->{$category} || 'Bez kategorije';
- print $fh qq|<h1>$label</h1>\n<ul>\n|;
+ print $fh qq|<h3>$label</h3>\n<ul>\n|;
- foreach my $authid ( @{ $department_category_author->{$department}->{$category} } ) {
- foreach my $biblionumber ( @{ $authors->{$authid}->{$category} } ) {
- print $fh qq|<li>|,
- qq|<a href="https://koha.ffzg.hr/cgi-bin/koha/opac-detail.pl?biblionumber=$biblionumber">$biblionumber</a>|,
- biblioitem_html($biblionumber),
- qq|<a href="https://koha.ffzg.hr:8443/cgi-bin/koha/cataloguing/addbiblio.pl?biblionumber=$biblionumber">edit</a>|,
- qq|</li>\n|;
- }
- }
+ print $fh li_biblio( $_ ) foreach @biblionumber;
print $fh qq|</ul>|;
}
+
+
+ print $fh qq|<h2>Sekundarno autorstvo</h2>\n|;
+
+ foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
+
+ my @authids = @{ $department_category_author->{$department}->{$category} };
+ next unless @authids;
+
+ my @biblionumber = unique_biblionumber map { @{ $authors->{$_}->{sec}->{$category} } } grep { exists $authors->{$_}->{sec}->{$category} } @authids;
+
+ next unless @biblionumber;
+
+ my $label = $category_label->{$category} || 'Bez kategorije';
+ print $fh qq|<h3>$label</h3>\n<ul>\n|;
+
+ print $fh li_biblio( $_ ) foreach @biblionumber;
+
+ print $fh qq|</ul>|;
+ }
+
+
print $fh html_end;
close($fh);
rename "html/departments/$dep_file.new", "html/departments/$dep_file.html";
close($dep_fh);
rename 'html/departments/index.new', 'html/departments/index.html';
+my $azvo_stat_authors;
+my $azvo_stat_biblio;
+
+foreach my $department ( sort keys %$department_category_author ) {
+ foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
+ foreach my $authid ( @{ $department_category_author->{$department}->{$category} } ) {
+ foreach my $type ( keys %{ $authors->{$authid} } ) {
+ next unless exists $authors->{$authid}->{$type}->{$category};
+ $azvo_stat_authors->{ $department }->{ $category }->{ $type } += $#{ $authors->{$authid}->{$type}->{$category} } + 1;
+ push @{ $azvo_stat_biblio->{ $department }->{ $category }->{ $type } }, @{ $authors->{$authid}->{$type}->{$category} };
+ }
+ }
+ foreach my $type ( keys %{ $azvo_stat_biblio->{ $department }->{ $category } } ) {
+ my @biblios = unique_biblionumber @{ $azvo_stat_biblio->{ $department }->{ $category }->{ $type } };
+ $azvo_stat_biblio->{ $department }->{ $category }->{ $type } = $#biblios + 1;
+ }
+ }
+}
+
+debug 'azvo_stat_authors' => $azvo_stat_authors;
+debug 'azvo_stat_biblio' => $azvo_stat_biblio;
+
+=for later
+open(my $fh, '>', 'html/azvo.new');
+
+
+
+close($fh);
+rename 'html/azvo.new', 'html/azvo.html';
+=cut
+