use Carp qw(confess);
use utf8;
use JSON;
+use POSIX qw(strftime);
+use Storable;
use lib '/srv/koha_ffzg';
use C4::Context;
use XML::LibXML;
use XML::LibXSLT;
+my $pid_file = '/dev/shm/bibliografija.pid';
+{
+ if ( -e $pid_file ) {
+ open(my $fh, '<', $pid_file);
+ my $pid = <$fh>;
+ no autodie; # it will die on kill
+ kill 0, $pid || die "$0 allready running as pid $pid";
+ }
+ open(my $fh, '>', $pid_file);
+ print $fh $$;
+ close($fh);
+}
+
+
my $dbh = C4::Context->dbh;
sub debug {
debug 'department_in_group' => $department_in_group;
foreach my $department ( keys %$department_in_sum ) {
- $department_in_sum->{$department} = 0 unless $department =~ m/(centar|croaticum|katedra|odsjek)/i;
+# $department_in_sum->{$department} = 0 unless $department =~ m/(centar|croaticum|katedra|odsjek)/i;
}
debug 'auth_department' => $auth_department;
+store $auth_department, '/dev/shm/auth_department.storable';
debug 'auth_group' => $auth_group;
debug 'department_in_sum' => $department_in_sum;
=cut
my $biblio_year;
+my $biblio_full_name;
my $type_stats;
my $parser = XML::LibXML->new();
my $extract = {
'008' => undef,
'100' => '(9|a)',
+ '245' => 'a',
'680' => 'i',
'700' => '(9|4|a)',
'942' => '(t|r|v)'
foreach my $authid ( @first_author ) {
push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber};
}
+ $biblio_full_name->{ $row->{biblionumber} } = $data->{100}->[0]->{a};
} else {
$have_100 = 0;
}
+ $biblio_full_name->{ $row->{biblionumber} } ||= $data->{245}->[0]->{a};
+
my $have_edt;
if ( exists $data->{700} ) {
$type_stats->{$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} }++;
+ my @types = split(/[\s\/]+/, $type);
+
+ foreach my $type ( @types ) {
+ my $type = substr($type,0,3);
+ $type_stats->{_count_each_type}->{$type}++;
+
+ if ( $type =~ m/(edt|trl|com|ctb)/ ) {
+ push @{ $authors->{$authid}->{__sec}->{ $category } }, $row->{biblionumber};
+ push @{ $authors->{$authid}->{$type}->{ $category } }, $row->{biblionumber};
+ $type =~ s/(com|ctb)/_ostalo/;
+ push @{ $authors->{$authid}->{$type}->{ $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 {
- push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber};
+# warn "# SKIP ", $row->{biblionumber}, ' no 700$4 in ', dump($data);
+ $skip->{ 'no_700$4' }->{ $row->{biblionumber} }++;
}
- } else {
-# warn "# SKIP ", $row->{biblionumber}, ' no 700$4 in ', dump($data);
- $skip->{ 'no_700$4' }->{ $row->{biblionumber} }++;
}
}
delete $data->{700};
}
debug 'authors' => $authors;
+store $authors, '/dev/shm/authors.storable';
debug 'type_stats' => $type_stats;
debug 'skip' => $skip;
debug 'biblio_year' => $biblio_year;
+debug 'biblio_full_name' => $biblio_full_name;
debug 'biblio_data' => $biblio_data;
debug 'biblio_author_external' => $biblio_author_external;
<title>|, join(" ", @_), qq|</title>
<link href="style.css" type="text/css" rel="stylesheet" />
<script src="//code.jquery.com/jquery-1.11.2.js"></script>
+<script src="filters.js"></script>
</head>
<body>
|;
}
sub html_end {
- return qq|</body>\n</html>\n|;
+ return
+ qq|<small style="color:gray">Zadnji puta osvježeno: |,
+ strftime("%Y-%m-%d %H:%M:%S\n", localtime()),
+ qq|</body>\n</html>\n|;
}
mkdir 'html' unless -d 'html';
qq|</li>\n|;
}
+sub unique {
+ my $unique;
+ $unique->{$_}++ foreach @_;
+ return keys %$unique;
+}
+
+sub unique_biblionumber {
+ my @v = unique @_;
+ return sort {
+ $biblio_year->{$b} <=> $biblio_year->{$a} ||
+ $biblio_full_name->{$a} cmp $biblio_full_name->{$b} ||
+ $a <=> $b
+ } @v;
+}
+
sub author_html {
my ( $fh, $authid, $type, $label ) = @_;
return unless exists $authors->{$authid}->{$type};
- print $fh qq|<h2>$label</h2>\n|;
+ print $fh qq|<a name="$type"><h2>$label</h2></a>\n|;
foreach my $category ( sort keys %{ $authors->{$authid}->{$type} } ) {
my $label = $category_label->{$category} || 'Bez kategorije';
- print $fh qq|<a name="$type-$category"><h3>$label</h3></a>\n<ul>\n|;
- foreach my $biblionumber ( sort {
- $biblio_year->{$b} <=> $biblio_year->{$a} || $a <=> $b
- } @{ $authors->{$authid}->{$type}->{$category} } ) {
+ print $fh qq|<a name="$type-$category"><h3>$label</h3></a>\n<ol>\n|;
+ foreach my $biblionumber ( unique_biblionumber @{ $authors->{$authid}->{$type}->{$category} } ) {
print $fh li_biblio( $biblionumber );
}
- print $fh qq|</ul>\n|;
+ print $fh qq|</ol>\n|;
}
}
+my @toc_type_label = (
+'aut' => 'Primarno autorstvo',
+'edt' => 'Uredništva',
+'trl' => 'Prijevodi',
+'_ostalo' => 'Ostalo',
+);
+
+
sub count_author_years {
+ my $years = shift;
my ($authid) = @_;
- my $years;
foreach my $type ( keys %{ $authors->{$authid} } ) {
+# next if $type =~ m/^_/; # FIXME
foreach my $category ( keys %{ $authors->{$authid}->{$type} } ) {
- foreach my $biblionumber ( @{ $authors->{$authid}->{$type}->{$category} } ) {
- $years->{ $biblio_year->{ $biblionumber } }->{ $type . '-' . $category }++;
+ foreach my $biblionumber ( unique_biblionumber @{ $authors->{$authid}->{$type}->{$category} } ) {
+ $years->{ $biblio_year->{ $biblionumber } }->{ $type . '-' . $category }->{ $biblionumber }++;
}
}
}
return $years;
}
-foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) {
+sub html_year_selection {
+ my $fh = shift;
+ my @authids = unique @_;
- my $first = substr( $row->{full_name}, 0, 1 );
- if ( $first ne $first_letter ) {
- print $index qq{</ul>\n} if $first_letter;
- $first_letter = $first;
- print $index qq{<h1>$first</h1>\n<ul>\n};
+ debug 'html_year_selection authids=', [ @authids ];
+
+ print $fh qq|<span id="years">Godine:\n|;
+ my $type_cat_count = {};
+ my $years;
+
+ foreach my $authid ( @authids ) {
+ $years = count_author_years( $years, $authid );
}
- print $index qq{<li><a href="}, $row->{authid}, qq{.html">}, $row->{full_name}, "</a></li>\n";
- my $path = "html/$row->{authid}";
- open(my $fh, '>:encoding(utf-8)', "$path.new");
- print $fh html_title($row->{full_name}, "bibliografija");
- print $fh qq|<h1>$row->{full_name} - bibliografija</h1>|;
+ debug 'years' => $years;
- my $years = count_author_years( $row->{authid} );
- print $fh qq|<span id="years">Godine:|;
- my $type_cat_count = {};
foreach my $year ( sort { $b <=> $a } keys %$years ) {
- print $fh qq|<label><input type=checkbox onClick="toggle_year($year, this)" checked>$year</label> \n|;
+ print $fh qq|<label><input name="year_selection" value="$year" type=checkbox onClick="toggle_year($year, this)" checked="checked">$year</label> \n|;
foreach my $type_cat ( keys %{ $years->{$year} } ) {
- $type_cat_count->{ $type_cat } += $years->{$year}->{$type_cat};
+ my $count = scalar keys %{ $years->{$year}->{$type_cat} };
+ $years->{$year}->{$type_cat} = $count; # remove biblionumbers and use count
+ $type_cat_count->{ $type_cat } += $count;
+ my ($type,$cat) = split(/-/, $type_cat);
+ $type_cat_count->{_toc}->{$type}->{$cat}++;
+ $type_cat_count->{_toc_count}->{$type} += $count;
}
}
+
+ print $fh qq|
+<input type=button value="all" onClick="all_years(1)">
+<input type=button value="none" onClick="all_years(0)">
+ |;
+
print $fh qq|</span>|;
print $fh q|
var type_cat_count = |, encode_json($type_cat_count), q|;
-function toggle_year(year, el) {
- if ( el.checked ) {
- $('.y'+year).show();
- console.debug('show', year, el.checked);
- for(var type_cat in years[year]) {
- if ( ( type_cat_count[ type_cat ] += years[year][type_cat] ) == years[year][type_cat]) {
- $('a[name="'+type_cat+'"]').show();
- console.debug(type_cat, 'show');
- }
- }
- } else {
- $('.y'+year).hide();
- console.debug('hide', year, el.checked);
- for(var type_cat in years[year]) {
- if ( ( type_cat_count[ type_cat ] -= years[year][type_cat] ) == 0 ) {
- $('a[name="'+type_cat+'"]').hide();
- console.debug(type_cat, 'hide');
- }
+</script>
+
+ |;
+
+ debug 'type_cat_count' => $type_cat_count;
+
+ # TOC
+ print $fh qq|<ul id="toc">\n|;
+ my $i = 0;
+ while ( $i < $#toc_type_label ) {
+ my $type = $toc_type_label[$i++] || die "type";
+ my $label = $toc_type_label[$i++] || die "label";
+ next unless exists $type_cat_count->{_toc}->{$type};
+ print $fh qq| <li class="toc" id="toc-$type"><a href="#$type">$label</a> <tt id="toc-count-$type">$type_cat_count->{_toc_count}->{$type}</tt></li>\n <ul>\n|;
+ foreach my $category ( sort keys %{ $type_cat_count->{_toc}->{$type} } ) {
+ my $label = $category_label->{$category} || 'Bez kategorije';
+ my $count = $type_cat_count->{ $type . '-' . $category };
+ my $cat_html = $category;
+ $cat_html =~ s/\./-/g;
+ print $fh qq| <li class="toc" id="toc-$category"><a href="#$type-$category">$label</a> <tt id="toc-count-$type-$cat_html">$count</tt></li>\n|;
}
+ print $fh qq| </ul>\n|;
}
+ print $fh qq|</ul>\n|;
+
}
-</script>
- |;
- author_html( $fh, $row->{authid}, 'aut' => 'Primarno autorstvo' );
- author_html( $fh, $row->{authid}, 'sec' => 'Uredništva, prijevodi, krička izdanja' );
+
+foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) {
+
+ my $first = substr( $row->{full_name}, 0, 1 );
+ if ( $first ne $first_letter ) {
+ print $index qq{</ul>\n} if $first_letter;
+ $first_letter = $first;
+ print $index qq{<h1>$first</h1>\n<ul>\n};
+ }
+ print $index qq{<li><a href="}, $row->{authid}, qq{.html">}, $row->{full_name}, "</a></li>\n";
+
+ my $path = "html/$row->{authid}";
+ open(my $fh, '>:encoding(utf-8)', "$path.new");
+ print $fh html_title($row->{full_name}, "bibliografija");
+ print $fh qq|<h1>$row->{full_name} - bibliografija</h1>\n|;
+
+ html_year_selection $fh => $row->{authid};
+
+ my $i = 0;
+ while ( $i < $#toc_type_label ) {
+ my $type = $toc_type_label[$i++] || die "type";
+ my $label = $toc_type_label[$i++] || die "label";
+ author_html( $fh, $row->{authid}, $type => $label );
+ }
print $fh html_end;
close($fh);
foreach my $department ( sort keys %$auth_department ) {
foreach my $authid ( sort @{ $auth_department->{$department} } ) {
my @categories = keys %{ $authors->{$authid}->{aut} };
- push @categories, keys %{ $authors->{$authid}->{sec} };
+ push @categories, keys %{ $authors->{$authid}->{__sec} };
foreach my $category ( sort @categories ) {
push @{ $department_category_author->{$department}->{$category} }, $authid;
push @{ $department_category_author->{'AAA_ukupno'}->{$category} }, $authid if $department_in_sum->{$department};
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 = $department || 'Nema odsjeka';
- 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|;
+sub department_html {
+ my ( $fh, $department, $type, $label, $csv_fh ) = @_;
- print $fh qq|<h2>Primarno autorstvo</h2>\n|;
+ print $fh qq|<a name="$type"><h2>$label</h2></a>\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;
+ my @biblionumber = unique_biblionumber map { @{ $authors->{$_}->{$type}->{$category} } } grep { exists $authors->{$_}->{$type}->{$category} } @authids;
next unless @biblionumber;
- my $label = $category_label->{$category} || 'Bez kategorije';
- print $fh qq|<h3>$label</h3>\n<ul>\n|;
+ my $cat_label = $category_label->{$category} || 'Bez kategorije';
+ print $fh qq|<a name="$type-$category"><h3>$cat_label</h3></a>\n<ol>\n|;
- print $fh li_biblio( $_ ) foreach @biblionumber;
+ foreach my $bib_num ( @biblionumber ) {
+ my @li = li_biblio( $bib_num );
+ my $li_html = join('', @li);
+ $li_html =~ s{<a name="col-\d+"></a>}{}gs;
+ print $fh $li_html;
- print $fh qq|</ul>|;
- }
+ next unless $csv_fh;
+ my $year = $li[1];
+ my @html;
+ foreach ( split(/<a name="col-/, $li[4]) ) {
+ if ( s{(\d+)"></a>}{} ) {
+ s{\s+}{ }gs;
+ $html[$1] = $_;
+ } else {
+ warn "SKIPPED: Can't find col in [$_] from $li[4]" unless m/^<[^>]+>$/;
+ }
+ }
+ my $html = join("\t", @html);
- print $fh qq|<h2>Sekundarno autorstvo</h2>\n|;
+ $html =~ s{</?[^>]*>}{}gs;
+ $html =~ s{\s+$}{}gs;
+ print $csv_fh "$bib_num\t$year\t$type\t$label\t$category\t$cat_label\t$html\n";
+ }
- foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
+ print $fh qq|</ol>|;
+ }
- 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;
+mkdir 'html/departments' unless -d 'html/departments';
- my $label = $category_label->{$category} || 'Bez kategorije';
- print $fh qq|<h3>$label</h3>\n<ul>\n|;
+open(my $dep_fh, '>:encoding(utf-8)', 'html/departments/index.new');
+print $dep_fh html_title('Odsjeci Filozofskog fakulteta u Zagrebu'), qq|<ul>\n|;
+foreach my $department ( sort keys %$department_category_author ) {
+ my $dep = $department || 'Nema odsjeka';
+ 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|;
+
+ my @authids;
+ foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
+ push @authids, @{ $department_category_author->{$department}->{$category} };
+ }
+ html_year_selection $fh => @authids;
- print $fh li_biblio( $_ ) foreach @biblionumber;
+ my $csv_fh;
+ if ( $department eq 'AAA_ukupno' ) {
+ open($csv_fh, '>:encoding(utf-8)', "html/departments/$department.csv");
+ }
- print $fh qq|</ul>|;
+ my $i = 0;
+ while ( $i < $#toc_type_label ) {
+ my $type = $toc_type_label[$i++] || die "type";
+ my $label = $toc_type_label[$i++] || die "label";
+ department_html( $fh, $department, $type, $label, $csv_fh );
}
+ close($csv_fh) if $csv_fh;
print $fh html_end;
close($fh);
rename "html/departments/$dep_file.new", "html/departments/$dep_file.html";
+
}
print $dep_fh qq|</ul>\n|, html_end;
close($dep_fh);
my $label = shift @_;
my $department = shift @_;
my $group = shift @_;
- my @biblionumbers = @_;
- my $unique;
- $unique->{$_}++ foreach @biblionumbers;
- my @bibs = keys %$unique;
- $table->{ffzg}->{$group}->[ $label2row->{ $label } ]->[ $department2col->{$department} ] = scalar @bibs;
- $table->{external}->{$group}->[ $label2row->{ $label } ]->[ $department2col->{$department} ] = scalar grep { $biblio_author_external->{$_} } @bibs;
+ my @biblionumbers = unique @_;
+ $table->{ffzg}->{$group}->[ $label2row->{ $label } ]->[ $department2col->{$department} ] = scalar @biblionumbers;
+ $table->{external}->{$group}->[ $label2row->{ $label } ]->[ $department2col->{$department} ] = scalar grep { $biblio_author_external->{$_} } @biblionumbers;
}
foreach my $group ( '', keys %$azvo_group_title ) {
rename 'html/azvo.new', 'html/azvo.html';
rename 'html/azvo2.new', 'html/azvo2.html';
+unlink $pid_file;
+
projects / koha-bibliografija / blobdiff