X-Git-Url: http://git.rot13.org/?a=blobdiff_plain;f=html.pl;h=10c6392d60c46dacead3ad07a5c1aa66888a723b;hb=c928efda112ef1c5f1a05f01d62066362d803a40;hp=0c55a7a89403736dfb6607c094443de3a153f0d9;hpb=9e52f8eb286e7e85d39c1d26117a2b9dda2fbf1d;p=koha-bibliografija diff --git a/html.pl b/html.pl index 0c55a7a..10c6392 100755 --- a/html.pl +++ b/html.pl @@ -11,6 +11,8 @@ use autodie; use locale; use Text::Unaccent; use Carp qw(confess); +use utf8; +use JSON; use lib '/srv/koha_ffzg'; use C4::Context; @@ -21,14 +23,28 @@ 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/(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; @@ -36,7 +52,8 @@ 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 }); @@ -49,13 +66,44 @@ while( my $row = $sth_auth->fetchrow_hashref ) { $auth_header->{ $row->{authid} } = $row->{full_name}; $row->{department} =~ s/, Filozofski fakultet u Zagrebu.*$//; $row->{department} =~ s/^.+\.\s*//; -# warn dump( $row ); + $row->{department} =~ s/\s+$//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}; 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; @@ -90,13 +138,16 @@ 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} || confess "missing $biblionumber marcxml"; @@ -109,10 +160,16 @@ 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}; } @@ -124,9 +181,9 @@ 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; } @@ -141,9 +198,10 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) { my $extract = { '008' => undef, - '100' => '9', - '700' => '(9|4)', - '942' => 't' + '100' => '(9|a)', + '680' => 'i', + '700' => '(9|4|a)', + '942' => '(t|r|v)' }; my $data; @@ -155,7 +213,14 @@ 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') { @@ -170,8 +235,20 @@ 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); @@ -182,11 +259,22 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) { 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}->{aut}->{ $category } }, $row->{biblionumber}; } @@ -197,7 +285,19 @@ while( my $row = $sth_select_authors->fetchrow_hashref ) { 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); @@ -222,13 +322,19 @@ 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; +debug 'biblio_author_external' => $biblio_author_external; my $category_label; my $sth_categories = $dbh->prepare(q{ @@ -247,13 +353,14 @@ sub html_title { |, join(" ", @_), qq| + |; } sub html_end { - return qq|\n\n\n|; } mkdir 'html' unless -d 'html'; @@ -267,7 +374,7 @@ debug 'authors' => \@authors; sub li_biblio { my ($biblionumber) = @_; - return qq|
  • |, + return qq|
  • |, qq|$biblionumber|, biblioitem_html($biblionumber), qq|edit|, @@ -283,14 +390,29 @@ sub author_html { foreach my $category ( sort keys %{ $authors->{$authid}->{$type} } ) { my $label = $category_label->{$category} || 'Bez kategorije'; - print $fh qq|

    $label

    \n