X-Git-Url: http://git.rot13.org/?a=blobdiff_plain;f=html.pl;h=8467a5591c30bf55389836ce4701a9257162a7f0;hb=18d433ab44358cf0393da0f95754d3f17d669013;hp=80d3cc15045c5e1938b007629e7787e5c86e5ab0;hpb=c512cb23ab9074fae1b74ff32872c9593353f467;p=koha-bibliografija diff --git a/html.pl b/html.pl index 80d3cc1..8467a55 100755 --- a/html.pl +++ b/html.pl @@ -10,24 +10,57 @@ use Data::Dump qw(dump); use autodie; use locale; use Text::Unaccent; +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 $dbh = C4::Context->dbh; sub debug { my ($title, $data) = @_; - print "# $title ",dump($data), $/; + print "# $title ",dump($data), $/ if $ENV{DEBUG}; } my $xslfilename = 'compact.xsl'; +my $azvo_group_title = { +'znanstveno nastavni' => qr/(profes|docent|znanstveni savjetnik|znanstveni suradnik)/i, +'lektori i predavači' => qr/(lektor|predavač)/i, +'asistenti i novaci' => qr/(asistent|novak)/i, +}; + +my $department_groups = { +'AAB_humanističke' => qr/(anglistiku|arheologiju|antropologiju|filozofiju|fonetiku|germanistiku|hungarologiju|indologiju|slavenske|filologiju|komparativnu|kroatistiku|lingvistiku|povijest|romanistiku|talijanistiku)/i, +'AAC_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; @@ -35,26 +68,62 @@ 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; +store $auth_department, '/dev/shm/auth_department.storable'; +debug 'auth_group' => $auth_group; +debug 'department_in_sum' => $department_in_sum; my $authors; -my $author_count; my $marcxml; my $sth_select_authors = $dbh->prepare(q{ @@ -77,6 +146,7 @@ where =cut my $biblio_year; +my $biblio_full_name; my $type_stats; my $parser = XML::LibXML->new(); @@ -86,29 +156,38 @@ my $xslt = XML::LibXSLT->new(); my $parsed = $xslt->parse_stylesheet($style_doc); my $biblio_html; +my $biblio_parsed; +my $biblio_data; +my $biblio_author_external; 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} || die "missing $biblionumber marcxml"; + 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"; +# 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 ); - return ( $biblio_html->{$biblionumber}, $source ) if wantarray; + delete $biblio_parsed->{$biblionumber}; + return $biblio_html->{$biblionumber}; } @@ -120,9 +199,9 @@ 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; } @@ -137,9 +216,11 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) { my $extract = { '008' => undef, - '100' => '9', - '700' => '(9|4)', - '942' => 't' + '100' => '(9|a)', + '245' => 'a', + '680' => 'i', + '700' => '(9|4|a)', + '942' => '(t|r|v)' }; my $data; @@ -151,7 +232,14 @@ 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') { @@ -166,51 +254,121 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) { } } push @{ $data->{$tag} }, $sf_data if $sf_data; - } - } + } + } + + if ( ! defined $data->{year} ) { + warn "MISSING year in ", $row->{biblionumber}; +=for remove-year-limit + } elsif ( $data->{year} < 2008 ) { + push @{ $skip->{year_lt_2008} }, $row->{biblionumber}; + next; + } elsif ( $data->{year} > 2013 ) { + push @{ $skip->{year_gt_2013} }, $row->{biblionumber}; + next; +=cut + } # warn "# ", $row->{biblionumber}, " data ",dump($data); my $category = $data->{942}->[0]->{'t'}; if ( ! $category ) { - warn "# SKIP ", $row->{biblionumber}, " no category in ", dump($data); +# warn "# SKIP ", $row->{biblionumber}, " no category in ", dump($data); push @{ $skip->{no_category} }, $row->{biblionumber}; next; } + my $have_100 = 1; if ( exists $data->{100} ) { - my @first_author = map { $_->{'9'} } @{ $data->{100} }; + my @first_author = + map { $_->{'9'} } + grep { + if ( ! exists $_->{9} ) { + $biblio_author_external->{ $row->{biblionumber} }++; + 0; + } elsif ( exists $auth_header->{ $_->{9} } ) { + 1; # from FFZXG + } else { + 0; + } + } + @{ $data->{100} }; foreach my $authid ( @first_author ) { - push @{ $authors->{$authid}->{ $category } }, $row->{biblionumber}; - $author_count->{aut}->{$authid}++; + 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} ) { - foreach my $auth ( @{ $data->{700} } ) { + my @other_authors = + grep { + if ( ! exists $_->{9} ) { + $biblio_author_external->{ $row->{biblionumber} }++; + 0; + } elsif ( exists $auth_header->{ $_->{9} } ) { + 1; # from FFZXG + } else { + 0; + } + } + @{ $data->{700} }; + foreach my $auth ( @other_authors ) { my $authid = $auth->{9} || next; my $type = $auth->{4} || next; #die "no 4 in ",dump($data); $type_stats->{$type}++; - push @{ $authors->{$authid}->{ $category } }, $row->{biblionumber}; - if ( $type =~ m/aut/ ) { - $author_count->{aut}->{ $authid }++; - } elsif ( $type =~ m/(edt|tr)/ ) { - $author_count->{$1}->{ $authid }++; - } else { - warn "# SKIP ", $row->{biblionumber}, ' no 700$4 in ', dump($data); - push @{ $skip->{ 'no_700$4' } }, $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 { +# warn "# SKIP ", $row->{biblionumber}, ' no 700$4 in ', dump($data); + $skip->{ 'no_700$4' }->{ $row->{biblionumber} }++; + } } } + delete $data->{700}; } + $biblio_data->{ $row->{biblionumber} } = $data; + } debug 'authors' => $authors; -debug 'author_count' => $author_count; +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; my $category_label; my $sth_categories = $dbh->prepare(q{ @@ -229,13 +387,18 @@ sub html_title { |, join(" ", @_), qq| + + |; } sub html_end { - return qq|\nZadnji puta osvježeno: |, + strftime("%Y-%m-%d %H:%M:%S\n", localtime()), + qq|\n\n|; } mkdir 'html' unless -d 'html'; @@ -247,6 +410,139 @@ my $first_letter = ''; debug 'authors' => \@authors; +sub li_biblio { + my ($biblionumber) = @_; + return qq|
  • |, + qq|$biblionumber|, + biblioitem_html($biblionumber), + qq|edit|, + qq|
  • \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|

    $label

    \n|; + + foreach my $category ( sort keys %{ $authors->{$authid}->{$type} } ) { + my $label = $category_label->{$category} || 'Bez kategorije'; + print $fh qq|

    $label

    \n
      \n|; + foreach my $biblionumber ( unique_biblionumber @{ $authors->{$authid}->{$type}->{$category} } ) { + print $fh li_biblio( $biblionumber ); + } + print $fh qq|
    \n|; + } +} + +my @toc_type_label = ( +'aut' => 'Primarno autorstvo', +'edt' => 'UredniÅ¡tva', +'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 ( unique_biblionumber @{ $authors->{$authid}->{$type}->{$category} } ) { + $years->{ $biblio_year->{ $biblionumber } }->{ $type . '-' . $category }->{ $biblionumber }++; + } + } + } + return $years; +} + +sub html_year_selection { + my $fh = shift; + my @authids = unique @_; + + debug 'html_year_selection authids=', [ @authids ]; + + print $fh qq|Godine:\n|; + my $type_cat_count = {}; + my $years; + + foreach my $authid ( @authids ) { + $years = count_author_years( $years, $authid ); + } + + debug 'years' => $years; + + foreach my $year ( sort { $b <=> $a } keys %$years ) { + print $fh qq| \n|; + foreach my $type_cat ( keys %{ $years->{$year} } ) { + 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| + + + |; + + print $fh qq||; + + print $fh q| + + + |; + + debug 'type_cat_count' => $type_cat_count; + + # TOC + print $fh qq|\n|; + +} + + foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) { my $first = substr( $row->{full_name}, 0, 1 ); @@ -260,19 +556,17 @@ foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) { my $path = "html/$row->{authid}"; open(my $fh, '>:encoding(utf-8)', "$path.new"); print $fh html_title($row->{full_name}, "bibliografija"); - print $fh qq|

    $row->{full_name} - bibliografija za razdoblje 2008-2013

    |; - foreach my $category ( sort keys %{ $authors->{ $row->{authid} } } ) { - my $label = $category_label->{$category} || 'Bez kategorije'; - print $fh qq|

    $label

    \n\n|; + print $fh qq|

    $row->{full_name} - bibliografija

    \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); rename "$path.new", "$path.html"; @@ -289,47 +583,266 @@ 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; + push @{ $department_category_author->{'AAA_ukupno'}->{$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 }++; + } } } } debug 'department_category_author' => $department_category_author; + +sub department_html { + my ( $fh, $department, $type, $label, $csv_fh ) = @_; + + print $fh qq|

    $label

    \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 { @{ $authors->{$_}->{$type}->{$category} } } grep { exists $authors->{$_}->{$type}->{$category} } @authids; + + next unless @biblionumber; + + my $cat_label = $category_label->{$category} || 'Bez kategorije'; + print $fh qq|

    $cat_label

    \n
      \n|; + + foreach my $bib_num ( @biblionumber ) { + my @li = li_biblio( $bib_num ); + my $li_html = join('', @li); + $li_html =~ s{
      }{}g; + print $fh $li_html; + + next unless $csv_fh; + + my $year = $li[1]; + my $html = $li[4]; + $html =~ s{
      }{\t}gs; +# $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|
    |; + } + +} + + 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|