modified report for departments by authors
[koha-bibliografija] / html.pl
diff --git a/html.pl b/html.pl
index 28da23f..e9194b3 100755 (executable)
--- a/html.pl
+++ b/html.pl
@@ -21,6 +21,20 @@ 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 {
@@ -100,7 +114,7 @@ while( my $row = $sth_auth->fetchrow_hashref ) {
 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;
@@ -114,10 +128,11 @@ my $marcxml;
 
 my $sth_select_authors  = $dbh->prepare(q{
 select
-       biblionumber,
+       biblioitems.biblionumber,
        itemtype,
-       marcxml
+       metadata as marcxml
 from biblioitems
+join biblio_metadata on (biblio_metadata.biblionumber = biblioitems.biblionumber)
 where
        agerestriction > 0
 });
@@ -311,23 +326,33 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) {
 
                                $type_stats->{$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};
@@ -364,6 +389,7 @@ sub html_title {
 <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>
 |;
@@ -394,15 +420,19 @@ sub li_biblio {
                qq|</li>\n|;
 }
 
+sub unique {
+       my $unique;
+       $unique->{$_}++ foreach @_;
+       return keys %$unique;
+}
+
 sub unique_biblionumber {
-       my @v = @_;
-       my $u;
-       $u->{$_}++ foreach @v;
+       my @v = unique @_;
        return sort {
                $biblio_year->{$b} <=> $biblio_year->{$a} ||
                $biblio_full_name->{$a} cmp $biblio_full_name->{$b} ||
                $a <=> $b
-       } keys %$u;
+       } @v;
 }
 
 sub author_html {
@@ -410,26 +440,34 @@ sub author_html {
 
        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|;
+               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) = @_;
        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 }++;
                        }
                }
        }
@@ -438,7 +476,9 @@ sub count_author_years {
 
 sub html_year_selection {
        my $fh = shift;
-       my @authids = @_;
+       my @authids = unique @_;
+
+       debug 'html_year_selection authids=', [ @authids ];
 
        print $fh qq|<span id="years">Godine:\n|;
        my $type_cat_count = {};
@@ -448,10 +488,17 @@ sub html_year_selection {
                $years = count_author_years( $years, $authid );
        }
 
+       debug 'years' => $years;
+
        foreach my $year ( sort { $b <=> $a } keys %$years ) {
                print $fh qq|<label><input name="year_selection" value="$year" type=checkbox onClick="toggle_year($year, this)" checked="checked">$year</label>&nbsp;\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;
                }
        }
 
@@ -469,65 +516,34 @@ var years = |, encode_json($years), q|;
 
 var type_cat_count = |, encode_json($type_cat_count), q|;
 
-function year_show(year) {
-       $('.y'+year).show();
-       console.debug('show', year);
-       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');
-               }
-       }
-}
+</script>
 
-function year_hide(year) {
-       $('.y'+year).hide();
-       console.debug('hide', year);
-       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');
-               }
-       }
-}
+       |;
 
-function toggle_year(year, el) {
-       if ( el.checked ) {
-               year_show(year);
-       } else {
-               year_hide(year);
+       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|;
 
-function all_years( turn_on ) {
-       $('input[name=year_selection]').each( function(i,el) {
-               if ( turn_on ) {
-                       if ( ! el.checked ) {
-                               el.checked = true;
-                               year_show( el.value );
-                       }
-               } else {
-                       if ( el.checked ) {
-                               el.checked = false;
-                               year_hide( el.value );
-                       }
-               }
-       } );
 }
 
-$(document).ready( function() {
-       console.info('ready');
-
-       $('input[name=year_selection]').each( function(i, el) {
-               var year = el.value;
-               console.debug( 'on load', year, el.checked );
-               if (! el.checked) year_hide(year);
-       });
-
-});
-</script>
-       |;
-}
+my $authid_fullname;
 
 foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) {
 
@@ -539,6 +555,8 @@ foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) {
        }
        print $index qq{<li><a href="}, $row->{authid}, qq{.html">}, $row->{full_name}, "</a></li>\n";
 
+       $authid_fullname->{ $row->{authid} } = $row->{full_name};
+
        my $path = "html/$row->{authid}";
        open(my $fh, '>:encoding(utf-8)', "$path.new");
        print $fh html_title($row->{full_name}, "bibliografija");
@@ -546,8 +564,12 @@ foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) {
 
        html_year_selection $fh => $row->{authid};
 
-       author_html( $fh, $row->{authid}, 'aut' => 'Primarno autorstvo' );
-       author_html( $fh, $row->{authid}, 'sec' => 'Uredništva, prijevodi, krička izdanja' );
+       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);
@@ -561,12 +583,13 @@ rename 'html/index.new', 'html/index.html';
 
 debug 'auth_header' => $auth_header;
 
+debug 'authid_fullname' => $authid_fullname;
 
 my $department_category_author;
 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};
@@ -583,9 +606,9 @@ debug 'department_category_author' => $department_category_author;
 
 
 sub department_html {
-       my ( $fh, $department, $type, $label ) = @_;
+       my ( $fh, $department, $type, $label, $csv_fh ) = @_;
 
-       print $fh qq|<h2>$label</h2>\n|;
+       print $fh qq|<a name="$type"><h2>$label</h2></a>\n|;
 
        foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
 
@@ -596,12 +619,36 @@ sub department_html {
 
                next unless @biblionumber;
 
-               my $label = $category_label->{$category} || 'Bez kategorije';
-               print $fh qq|<a name="$type-$category"><h3>$label</h3></a>\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|;
+
+               foreach my $bib_num ( @biblionumber ) {
+                       my @li = li_biblio( $bib_num );
+                       my $li_html = join('', @li);
+                       $li_html =~ s{<a name="(col-\d+)"/a>}{<!-- $1 -->}gs;
+                       print $fh $li_html;
+
+                       next unless $csv_fh;
+
+                       my $year = $li[1];
+                       my @html;
+                       foreach ( split(/<a name="col-/, $li[4]) ) {
+                               if ( s{^(\d+)"></a>}{} ) {
+                                       my $nr = $1;
+                                       s{\s+}{ }gs;
+                                       $html[$nr] = $_;
+                               } else {
+                                       warn "SKIPPED: Can't find col in [$_] from $li[4]" unless m/^<[^>]+>$/;
+                               }
+                       }
+                       my $html = join("\t", @html);
 
-               print $fh li_biblio( $_ ) foreach @biblionumber;
+                       $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";
+               }
 
-               print $fh qq|</ul>|;
+               print $fh qq|</ol>|;
        }
 
 }
@@ -610,7 +657,7 @@ sub department_html {
 mkdir 'html/departments' unless -d 'html/departments';
 
 open(my $dep_fh, '>:encoding(utf-8)', 'html/departments/index.new');
-print $dep_fh html_title('Odsijeci Filozofskog fakulteta u Zagrebu'), qq|<ul>\n|;
+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);
@@ -626,13 +673,24 @@ foreach my $department ( sort keys %$department_category_author ) {
        }
        html_year_selection $fh => @authids;
 
-       department_html( $fh, $department, 'aut', 'Primarno autorstvo' );
+       my $csv_fh;
+       if ( $department eq 'AAA_ukupno' ) {
+               open($csv_fh, '>:encoding(utf-8)', "html/departments/$department.csv");
+       }
+
+       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 );
+       }
 
-       department_html( $fh, $department, 'sec', 'Sekundarno autorstvo' );
+       close($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);
@@ -670,7 +728,7 @@ my @report_labels;
 
 my $label;
 my $sub_labels;
-open(my $report, '<:encoding(utf-8)', 'AZVO.txt');
+open(my $report, '<:encoding(utf-8)', 'nAZVO.txt');
 while( <$report> ) {
        chomp;
        if ( /^([^\t]+)\t+(.+)/ ) {
@@ -707,12 +765,9 @@ sub table_count {
        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 ) {
@@ -761,7 +816,7 @@ foreach my $department ( @departments ) {
 
 } # group
 
-debug 'table', $table;
+#debug 'table', $table;
 
 open(my $fh, '>:encoding(utf-8)', 'html/azvo.new');
 open(my $fh2, '>:encoding(utf-8)', 'html/azvo2.new');
@@ -804,3 +859,63 @@ close($fh2);
 rename 'html/azvo.new', 'html/azvo.html';
 rename 'html/azvo2.new', 'html/azvo2.html';
 
+my $dep_au_count;
+
+foreach my $department ( @departments ) {
+       foreach my $line ( @report_lines ) {
+               my $label = $line->[0];
+               my @biblionumbers;
+               foreach ( 1 .. $#$line ) {
+                       my ( $category, $type ) = @{ $line->[ $_ ] };
+
+                       foreach my $authid ( @{ $auth_department->{$department} } ) {
+                               next unless exists $authors->{$authid}->{$type}->{$category};
+                               my @biblionumbers = @{ $authors->{$authid}->{$type}->{$category} };
+
+                               $dep_au_count->{ $department }->{ $authid }->{ $label } += scalar @biblionumbers;
+                       }
+               }
+       }
+}
+
+debug 'dep_au_count', $dep_au_count;
+
+mkdir 'html/dep_au' unless -d 'html/dep_au';
+open(my $dep_fh, '>', 'html/dep_au/index.new');
+print $dep_fh html_title('Odsjeci Filozofskog fakulteta u Zagrebu'), qq|<ul>\n|;
+foreach my $department ( sort keys %{ $dep_au_count } ) {
+
+       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 $fh, '>:encoding(utf-8)', "html/dep_au/$dep_file.new");
+
+       print $fh html_title($department . ' bibliografija tablica');
+       
+       # FIXME table
+       print $fh qq|<table>\n<tr><th></th><th>|
+               , join('</th><th>', @report_labels )
+               , qq|</th></tr>\n|
+               ;
+
+       foreach my $authid ( keys %{ $dep_au_count->{ $department } } ) {
+               print $fh qq|<tr><th>$authid_fullname->{$authid}</th><th>|
+                               , join('</th><th>', map { $dep_au_count->{$department}->{$authid}->{$_} || '-' } @report_labels )
+                               , qq|</th></tr>\n|
+                               ;
+       }
+
+
+       print $fh qq|</table>\n|;
+
+       print $fh html_end;
+       close($fh);
+       rename "html/dep_au/$dep_file.new", "html/dep_au/$dep_file.html";
+}
+
+print $dep_fh html_end;
+close($dep_fh);
+rename "html/dep_au/index.new", "html/dep_au/index.html";
+
+unlink $pid_file;
+