X-Git-Url: http://git.rot13.org/?a=blobdiff_plain;f=html.pl;h=525e7748574a0d1c1d1dfb3c8f961b2d7a7e4868;hb=614429415aeadc2d81dac9259b78db4f9f1c19ed;hp=9c4ec3297cd77300222df21656a3ef93294d03d7;hpb=ecc58c1936e543dc082d4df5604dc4be4cb65cf6;p=koha-bibliografija

diff --git a/html.pl b/html.pl
index 9c4ec32..525e774 100755
--- a/html.pl
+++ b/html.pl
@@ -11,6 +11,7 @@ use autodie;
 use locale;
 use Text::Unaccent;
 use Carp qw(confess);
+use utf8;
 
 use lib '/srv/koha_ffzg';
 use C4::Context;
@@ -21,14 +22,28 @@ my $dbh = C4::Context->dbh;
 
 sub debug {
 	my ($title, $data) = @_;
-	print "# $title ",dump($data), $/;
+	print "# $title ",dump($data), $/ if $ENV{DEBUG};
 }
 
 my $xslfilename = 'compact.xsl';
 
+my $azvo_group_title = {
+'znanstveno nastavni' => qr/(profesor|docent|znanstveni)/i,
+'lektori i predavači' => qr/(lektor|predavač)/i,
+'asistenti i novaci' => qr/(asistent|novak)/i,
+};
+
+my $department_groups = {
+'AAA_humanističke'		=> qr/(anglistiku|arheologiju|antropologiju|filozofiju|fonetiku|germanistiku|hungarologiju|indologiju|slavenske|filologiju|komparativnu|kroatistiku|lingvistiku|povijest|romanistiku|talijanistiku)/i,
+'AAB_društvene'			=> qr/(informacijske|pedagogiju|psihologiju|sociologiju)/i,
+};
+
 my $auth_header;
 my $auth_department;
+my $auth_group;
 my @authors;
+my $department_in_sum;
+my $department_in_group;
 
 my $skip;
 
@@ -36,22 +51,58 @@ 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
+	ExtractValue(marcxml,'//datafield[@tag="680"]/subfield[@code="a"]') as department,
+	ExtractValue(marcxml,'//datafield[@tag="680"]/subfield[@code="i"]') as academic_title
 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\s*// || next;
+	$row->{department} =~ s/, Filozofski fakultet u Zagrebu.*$//;
 	$row->{department} =~ s/^.+\.\s*//;
+	$row->{department} =~ s/\s+$//s;
+	my $group;
+	foreach my $title ( keys %$azvo_group_title ) {
+		if ( $row->{academic_title} =~ $azvo_group_title->{$title} ) {
+			$group = $title;
+			last;
+		}
+	}
+	if ( $group ) {
+		$row->{academic_group} = $group;
+		$auth_group->{ $row->{authid} } = $group;
+		$skip->{group_stat}->{$group}++;
+	} else {
+		push @{ $skip->{no_academic_group} }, $row;
+	}
+
+#	warn "# ", dump( $row );
 	push @{ $auth_department->{ $row->{department} } }, $row->{authid};
-#	warn dump( $row );
 	push @authors, $row;
+	$department_in_sum->{ $row->{department} }++;
+	foreach my $name ( keys %$department_groups ) {
+		my $regex = $department_groups->{$name};
+		if ( $row->{department} =~ $regex ) {
+			$department_in_group->{ $row->{department} } = $name;
+			last;
+		}
+	}
+}
+
+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;
 }
 
 debug 'auth_department' => $auth_department;
+debug 'auth_group' => $auth_group;
+debug 'department_in_sum' => $department_in_sum;
 
 
 my $authors;
@@ -86,13 +137,15 @@ my $xslt = XML::LibXSLT->new();
 my $parsed = $xslt->parse_stylesheet($style_doc);
 
 my $biblio_html;
+my $biblio_parsed;
+my $biblio_data;
 
 open(my $xml_fh, '>', '/tmp/bibliografija.xml') if $ENV{XML};
 
 sub biblioitem_html {
-	my $biblionumber = shift;
+	my ($biblionumber, $parse_only) = @_;
 
-	return $biblio_html->{$biblionumber} if exists $biblio_html->{$biblionumber};
+	return $biblio_html->{$biblionumber} if exists $biblio_html->{$biblionumber} && ! $parse_only;
 
 	my $xmlrecord = $marcxml->{$biblionumber} || confess "missing $biblionumber marcxml";
 
@@ -105,10 +158,16 @@ sub biblioitem_html {
 		return;
 	}
 
+	if ( $parse_only ) {
+		$biblio_parsed->{$biblionumber} = $source;
+		return $source;
+	}
+
 	my $transformed = $parsed->transform($source);
 	$biblio_html->{$biblionumber} = $parsed->output_string( $transformed );
 
-	return ( $biblio_html->{$biblionumber}, $source ) if wantarray;
+	delete $biblio_parsed->{$biblionumber};
+
 	return $biblio_html->{$biblionumber};
 }
 
@@ -120,9 +179,9 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) {
 
 	$marcxml->{ $row->{biblionumber} } = $row->{marcxml};
 
-	my ( undef, $doc ) = biblioitem_html( $row->{biblionumber} );
+	my $doc = biblioitem_html( $row->{biblionumber}, 1 );
 	if ( ! $doc ) {
-		warn "ERROR can't parse MARCXML ", $row->{biblionumber}, " ", $row->{marcxml}, "\n";
+#		warn "ERROR can't parse MARCXML ", $row->{biblionumber}, " ", $row->{marcxml}, "\n";
 		next;
 	}
 
@@ -138,8 +197,9 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) {
 	my $extract = {
 		'008' => undef,
 		'100' => '9',
+		'680' => 'i',
 		'700' => '(9|4)',
-		'942' => 't'
+		'942' => '(t|r|v)'
 	};
 
 	my $data;
@@ -151,7 +211,14 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) {
 
         if ($elt->localname eq 'controlfield') {
 			if ( $tag eq '008' ) {
-				 $biblio_year->{ $row->{biblionumber} } = $elt->textContent;
+				my $content = $elt->textContent;
+				my $year = substr($content, 7, 4 );
+				if ( $year !~ m/^\d+$/ ) {
+					$year = 0;
+					push @{ $skip->{invalid_year} }, $row->{biblionumber};
+				}
+				$biblio_year->{ $row->{biblionumber} } = $data->{year} = $year;
+				$data->{'008'} = $content;
 			}
 			next;
         } elsif ($elt->localname eq 'datafield') {
@@ -169,6 +236,14 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) {
         }
     }
 
+	if ( $data->{year} < 2008 ) {
+		push @{ $skip->{year_lt_2008} }, $row->{biblionumber};
+		next;
+	} elsif ( $data->{year} > 2013 ) {
+		push @{ $skip->{year_gt_2013} }, $row->{biblionumber};
+		next;
+	}
+
 #	warn "# ", $row->{biblionumber}, " data ",dump($data);
 
 	my $category = $data->{942}->[0]->{'t'};
@@ -178,7 +253,6 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) {
 		next;
 	}
 
-
 	my $have_100 = 1;
 
 	if ( exists $data->{100} ) {
@@ -218,13 +292,18 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) {
 					$skip->{ 'no_700$4' }->{ $row->{biblionumber} }++;
 				}
 			}
+			delete $data->{700};
 	}
 
+	$biblio_data->{ $row->{biblionumber} } = $data;
+
 }
 
 debug 'authors' => $authors;
 debug 'type_stats' => $type_stats;
 debug 'skip' => $skip;
+debug 'biblio_year' => $biblio_year;
+debug 'biblio_data' => $biblio_data;
 
 my $category_label;
 my $sth_categories = $dbh->prepare(q{
@@ -249,7 +328,7 @@ sub html_title {
 }
 
 sub html_end {
-	return qq|</body>\n</html\n|;
+	return qq|</body>\n</html>\n|;
 }
 
 mkdir 'html' unless -d 'html';
@@ -303,7 +382,7 @@ foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) {
 	print $fh qq|<h1>$row->{full_name} - bibliografija za razdoblje 2008-2013</h1>|;
 
 	author_html( $fh, $row->{authid}, 'aut' => 'Primarno autorstvo' );
-	author_html( $fh, $row->{authid}, 'sec' => 'Sekundarno autorstvo' );
+	author_html( $fh, $row->{authid}, 'sec' => 'Uredništva, prijevodi, krička izdanja' );
 
 	print $fh html_end;
 	close($fh);
@@ -325,6 +404,12 @@ foreach my $department ( sort keys %$auth_department ) {
 		push @categories,  keys %{ $authors->{$authid}->{sec} };
 		foreach my $category ( sort @categories ) {
 			push @{ $department_category_author->{$department}->{$category} }, $authid;
+			push @{ $department_category_author->{'AAZ_ukupno'}->{$category} }, $authid if $department_in_sum->{$department};
+			if ( my $group = $department_in_group->{ $department } ) {
+				push @{ $department_category_author->{$group}->{$category} }, $authid;
+			} else {
+				$skip->{'department_not_in_group'}->{ $department }++;
+			}
 		}
 	}
 }
@@ -333,6 +418,13 @@ 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 ) {
@@ -351,7 +443,9 @@ foreach my $department ( sort keys %$department_category_author ) {
 		my @authids = @{ $department_category_author->{$department}->{$category} };
 		next unless @authids;
 
-		my @biblionumber = map { @{ $authors->{$_}->{aut}->{$category} } } grep { exists $authors->{$_}->{aut}->{$category} } @authids;
+		my @biblionumber = unique_biblionumber map { @{ $authors->{$_}->{aut}->{$category} } } grep { exists $authors->{$_}->{aut}->{$category} } @authids;
+		my $unique;
+		$unique->{$_}++ foreach @biblionumber;
 
 		next unless @biblionumber;
 
@@ -371,7 +465,7 @@ foreach my $department ( sort keys %$department_category_author ) {
 		my @authids = @{ $department_category_author->{$department}->{$category} };
 		next unless @authids;
 
-		my @biblionumber = map { @{ $authors->{$_}->{sec}->{$category} } } grep { exists $authors->{$_}->{sec}->{$category} } @authids;
+		my @biblionumber = unique_biblionumber map { @{ $authors->{$_}->{sec}->{$category} } } grep { exists $authors->{$_}->{sec}->{$category} } @authids;
 
 		next unless @biblionumber;
 
@@ -392,3 +486,153 @@ print $dep_fh qq|</ul>\n|, html_end;
 close($dep_fh);
 rename 'html/departments/index.new', 'html/departments/index.html';
 
+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} } ) {
+			my $group = $auth_group->{$authid};
+			if ( ! $group ) {
+				push @{ $skip->{no_auth_group} }, $authid;
+				next;
+			}
+			foreach my $type ( keys %{ $authors->{$authid} } ) {
+				next unless exists $authors->{$authid}->{$type}->{$category};
+				push @{ $azvo_stat_biblio->{ $department }->{ $category }->{ $type }->{$group} },  @{ $authors->{$authid}->{$type}->{$category} };
+				push @{ $azvo_stat_biblio->{ $department }->{ $category }->{ $type }->{''} },  @{ $authors->{$authid}->{$type}->{$category} };
+			}
+		}
+		foreach my $type ( keys %{ $azvo_stat_biblio->{ $department }->{ $category } } ) {
+			foreach my $group ( keys %{ $azvo_stat_biblio->{ $department }->{ $category }->{ $type } } ) {
+				my @biblios = unique_biblionumber @{ $azvo_stat_biblio->{ $department }->{ $category }->{ $type }->{ $group } };
+				$azvo_stat_biblio->{ $department }->{ $category }->{ $type }->{ $group } = [ @biblios ];
+			}
+		}
+	}
+}
+
+debug 'azvo_stat_biblio' => $azvo_stat_biblio;
+
+my @report_lines;
+my @report_labels;
+
+my $label;
+my $sub_labels;
+open(my $report, '<:encoding(utf-8)', 'AZVO.txt');
+while( <$report> ) {
+	chomp;
+	if ( /^([^\t]+)\t+(.+)/ ) {
+		$label = $1;
+		push @report_labels, $label;
+		my $type = [ map { m/\s+/ ? [ split(/\s+/,$_) ] : [ $_, 'aut' ] } split (/\s*\+\s*/, $2) ];
+		push @report_lines, [ $label, @$type ];
+	} elsif ( /^\t+([^\t]+):\t+(\d+)(\w*)\t*(.*)$/ ) {
+		push @{ $sub_labels->{$label} }, [ $1, $2, $3, $4 ];
+		my $sub_label = $1;
+		pop (@report_labels) if ( $report_labels[ $#report_labels ] =~ m/^$label$/ ); # remove partial name
+		push @report_labels, $label . $sub_label;
+	} else {
+		die "ERROR: [$_]\n";
+	}
+}
+
+debug 'report_lines', \@report_lines;
+debug 'sub_labels', $sub_labels;
+debug 'report_labels', \@report_labels;
+
+my @departments = ( sort { lc($a) cmp lc($b) } keys %$azvo_stat_biblio );
+
+debug 'departments' => \@departments;
+
+my $department2col;
+$department2col->{ $departments[$_] } = $_ foreach ( 0 .. $#departments );
+my $label2row;
+$label2row->{ $report_labels[$_] } = $_ foreach ( 0 .. $#report_labels );
+
+my $table;
+
+sub table_count {
+	my $label = shift @_;
+	my $department = shift @_;
+	my $group = shift @_;
+	my @biblionumbers = @_;
+	my $unique;
+	$unique->{$_}++ foreach @biblionumbers;
+	$table->{$group}->[ $label2row->{ $label } ]->[ $department2col->{$department} ] = scalar keys %$unique;
+}
+
+foreach my $group ( '', keys %$azvo_group_title ) {
+
+foreach my $department ( @departments ) {
+	foreach my $line ( @report_lines ) {
+		my $label = $line->[0];
+		my @biblionumbers;
+		foreach ( 1 .. $#$line ) {
+			my ( $category, $type ) = @{ $line->[ $_ ] };
+			my $b = $azvo_stat_biblio->{ $department }->{$category}->{$type}->{$group};
+			push @biblionumbers, @$b if $b;
+		}
+		if ( $sub_labels->{$label} ) {
+			my $sub_stats;
+			foreach my $biblionumber ( @biblionumbers ) {
+				my $data = $biblio_data->{$biblionumber} || die "can't find biblionumber $biblionumber";
+				foreach my $sub_label ( @{ $sub_labels->{$label} } ) {
+					my ( $sub_label, $field, $sf, $regex ) = @$sub_label;
+					if ( ! $regex ) {
+						push @{ $sub_stats->{ $sub_label } }, $biblionumber;
+						last;
+					}
+					if ( $field < 100 ) {
+						if ( $data->{$field} =~ m/$regex/ ) {
+							push @{ $sub_stats->{ $sub_label } }, $biblionumber;
+							last;
+						}
+					} else {
+						if ( exists $data->{$field}->[0]->{$sf} && $data->{$field}->[0]->{$sf} =~ m/$regex/ ) {
+							push @{ $sub_stats->{ $sub_label } }, $biblionumber;
+							last;
+						}
+					}
+				}
+			}
+			foreach my $sub_label ( keys %$sub_stats ) {
+				my $full_label = $label . $sub_label;
+				table_count $full_label, $department, $group, @{ $sub_stats->{$sub_label} };
+			}
+		} else {
+			table_count $label, $department, $group, @biblionumbers;
+		}
+	}
+}
+
+} # group
+
+debug 'table', $table;
+
+open(my $fh, '>:encoding(utf-8)', 'html/azvo.new');
+
+print $fh html_title('AZVO tablica');
+
+foreach my $group ( keys %$table ) {
+
+		print $fh "<h1>$group</h1>" if $group;
+
+		print $fh "<table border=1>\n";
+		print $fh "<tr><th></th>";
+		print $fh "<th>$_</th>" foreach @departments;
+		print $fh "</tr>\n";
+
+		foreach my $row ( 0 .. $#{ $table->{$group} } ) {
+			print $fh "<tr><th>", $report_labels[$row], "</th>\n";
+			print $fh " <td>", $table->{$group}->[ $row ]->[ $_ ] || '', "</td>\n" foreach 0 .. $#departments;
+			print $fh "</tr>\n";
+		}
+
+		print $fh "</table>\n";
+
+} # group
+
+print $fh html_end;
+close($fh);
+rename 'html/azvo.new', 'html/azvo.html';
+