X-Git-Url: http://git.rot13.org/?a=blobdiff_plain;f=html.pl;h=8f246ea351c45406caca9642917b41ca412175ae;hb=6f739ea5d041badf4c86ef58ea5ff65726d0cc83;hp=ca39fe27defd4fc00e797bec1784f6842fe8e44d;hpb=29366ef95af0f6da60bb4dd7dbe949a5d8712468;p=koha-bibliografija diff --git a/html.pl b/html.pl index ca39fe2..8f246ea 100755 --- a/html.pl +++ b/html.pl @@ -9,89 +9,205 @@ use DBI; use Data::Dump qw(dump); use autodie; use locale; +use Text::Unaccent; use lib '/srv/koha_ffzg'; use C4::Context; use XML::LibXML; use XML::LibXSLT; -use XML::Simple; my $dbh = C4::Context->dbh; +sub debug { + my ($title, $data) = @_; + print "# $title ",dump($data), $/; +} + my $xslfilename = 'compact.xsl'; +my $auth_header; +my $auth_department; +my @authors; + +my $skip; + +my $sth_auth = $dbh->prepare(q{ +select + authid, + ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="a"]') as full_name, + ExtractValue(marcxml,'//datafield[@tag="680"]/subfield[@code="a"]') as department +from auth_header +}); + +$sth_auth->execute(); +while( my $row = $sth_auth->fetchrow_hashref ) { + $auth_header->{ $row->{authid} } = $row->{full_name}; + $row->{department} =~ s/, Filozofski fakultet u Zagrebu\s*// || next; + $row->{department} =~ s/^.+\.\s*//; + push @{ $auth_department->{ $row->{department} } }, $row->{authid}; +# warn dump( $row ); + push @authors, $row; + +} + +debug 'auth_department' => $auth_department; + + my $authors; my $marcxml; my $sth_select_authors = $dbh->prepare(q{ select biblionumber, - ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="9"]') as first_author, - ExtractValue(marcxml,'//datafield[@tag="700"]/subfield[@code="9"]') as other_authors, - ExtractValue(marcxml,'//datafield[@tag="942"]/subfield[@code="t"]') as category, itemtype, marcxml from biblioitems where agerestriction > 0 - and SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) between 2008 and 2013 -order by SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) desc }); +=for sql +-- ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="9"]') as first_author, +-- ExtractValue(marcxml,'//datafield[@tag="700"]/subfield[@code="9"]') as other_authors, +-- ExtractValue(marcxml,'//datafield[@tag="942"]/subfield[@code="t"]') as category, + +-- and SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) between 2008 and 2013 +-- order by SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) desc +=cut + +my $biblio_year; +my $type_stats; + +my $parser = XML::LibXML->new(); +$parser->recover_silently(0); # don't die when you find &, >, etc +my $style_doc = $parser->parse_file($xslfilename); +my $xslt = XML::LibXSLT->new(); +my $parsed = $xslt->parse_stylesheet($style_doc); + +my $biblio_html; + +open(my $xml_fh, '>', '/tmp/bibliografija.xml') if $ENV{XML}; + +sub biblioitem_html { + my $biblionumber = shift; + + return $biblio_html->{$biblionumber} if exists $biblio_html->{$biblionumber}; + + my $xmlrecord = $marcxml->{$biblionumber} || die "missing $biblionumber marcxml"; + + print $xml_fh $xmlrecord if $ENV{XML}; + + my $source = eval { $parser->parse_string($xmlrecord) }; + if ( $@ ) { +# warn "SKIP $biblionumber corrupt XML"; + push @{ $skip->{XML_corrupt} }, $biblionumber; + return; + } + + my $transformed = $parsed->transform($source); + $biblio_html->{$biblionumber} = $parsed->output_string( $transformed ); + + return ( $biblio_html->{$biblionumber}, $source ) if wantarray; + return $biblio_html->{$biblionumber}; +} + $sth_select_authors->execute(); while( my $row = $sth_select_authors->fetchrow_hashref ) { # warn dump($row),$/; - if ( $row->{first_author} || $row->{itemtype} !~ m/^KNJ/ ) { - my $all_authors = join(' ', $row->{first_author}, $row->{other_authors}); - foreach my $authid ( split(/\s+/, $all_authors) ) { - push @{ $authors->{$authid}->{ $row->{category} } }, $row->{biblionumber}; - $marcxml->{ $row->{biblionumber} } = $row->{marcxml}; - } - } else { - my $xml = XMLin( $row->{marcxml}, ForceArray => [ 'subfield' ] ); - foreach my $f700 ( map { $_->{subfield} } grep { $_->{tag} eq 700 } @{ $xml->{datafield} } ) { - my $authid = 0; - my $is_edt = 0; - foreach my $sf ( @$f700 ) { - if ( $sf->{code} eq '4' && $sf->{content} =~ m/^edt/ ) { - $is_edt++; - } elsif ( $sf->{code} eq '9' ) { - $authid = $sf->{content}; + + my $biblio; + + $marcxml->{ $row->{biblionumber} } = $row->{marcxml}; + + my ( undef, $doc ) = biblioitem_html( $row->{biblionumber} ); + if ( ! $doc ) { + warn "ERROR can't parse MARCXML ", $row->{biblionumber}, " ", $row->{marcxml}, "\n"; + next; + } + + my $root = $doc->documentElement; +=for leader + my @leaders = $root->getElementsByLocalName('leader'); + if (@leaders) { + my $leader = $leaders[0]->textContent; + warn "leader $leader\n"; + } +=cut + + my $extract = { + '008' => undef, + '100' => '9', + '700' => '(9|4)', + '942' => 't' + }; + + my $data; + + foreach my $elt ($root->getChildrenByLocalName('*')) { + my $tag = $elt->getAttribute('tag'); + next if ! $tag; + next unless exists $extract->{ $tag }; + + if ($elt->localname eq 'controlfield') { + if ( $tag eq '008' ) { + $biblio_year->{ $row->{biblionumber} } = $elt->textContent; + } + next; + } elsif ($elt->localname eq 'datafield') { + my $sf_data; + foreach my $sfelt ($elt->getChildrenByLocalName('subfield')) { + my $sf = $sfelt->getAttribute('code'); + next unless $sf =~ m/$extract->{$tag}/; + if ( exists $sf_data->{$sf} ) { + $sf_data->{$sf} .= " " . $sfelt->textContent(); + } else { + $sf_data->{$sf} = $sfelt->textContent(); } } - if ( $authid && $is_edt ) { -# warn "# ++ ", $row->{biblionumber}, " $authid f700 ", dump( $f700 ); - push @{ $authors->{$authid}->{ $row->{category} } }, $row->{biblionumber}; - $marcxml->{ $row->{biblionumber} } = $row->{marcxml}; - } else { -# warn "# -- ", $row->{biblionumber}, " f700 ", dump( $f700 ); + push @{ $data->{$tag} }, $sf_data if $sf_data; + } + } + +# warn "# ", $row->{biblionumber}, " data ",dump($data); + + my $category = $data->{942}->[0]->{'t'}; + if ( ! $category ) { +# warn "# SKIP ", $row->{biblionumber}, " no category in ", dump($data); + push @{ $skip->{no_category} }, $row->{biblionumber}; + next; + } + + + if ( exists $data->{100} ) { + my @first_author = map { $_->{'9'} } @{ $data->{100} }; + foreach my $authid ( @first_author ) { + push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber}; } - } } -} -my $auth_header; -my @authors; + if ( exists $data->{700} ) { + foreach my $auth ( @{ $data->{700} } ) { + my $authid = $auth->{9} || next; + my $type = $auth->{4} || next; #die "no 4 in ",dump($data); -my $all_authids = join(',', grep { length($_) > 0 } keys %$authors); -my $sth_auth = $dbh->prepare(q{ -select - authid, - ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="a"]') as full_name -from auth_header -where - ExtractValue(marcxml,'//datafield[@tag="024"]/subfield[@code="a"]') <> '' and - authid in (} . $all_authids . q{) -}); + $type_stats->{$type}++; -$sth_auth->execute(); -while( my $row = $sth_auth->fetchrow_hashref ) { -# warn dump( $row ); - $auth_header->{ $row->{authid} } = $row->{full_name}; - push @authors, $row; + if ( $type =~ m/aut/ ) { + push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber}; + } elsif ( $type =~ m/(edt|trl|com|ctb)/ ) { + push @{ $authors->{$authid}->{sec}->{ $category } }, $row->{biblionumber}; + } else { +# warn "# SKIP ", $row->{biblionumber}, ' no 700$4 in ', dump($data); + push @{ $skip->{ 'no_700$4' } }, $row->{biblionumber}; + } + } + } } +debug 'authors' => $authors; +debug 'type_stats' => $type_stats; + my $category_label; my $sth_categories = $dbh->prepare(q{ select authorised_value, lib from authorised_values where category = 'BIBCAT' @@ -101,7 +217,7 @@ while( my $row = $sth_categories->fetchrow_hashref ) { $category_label->{ $row->{authorised_value} } = $row->{lib}; } -#warn dump( $category_label ); +debug 'category_label' => $category_label; sub html_title { return qq| @@ -118,30 +234,35 @@ sub html_end { return qq|\n:encoding(utf-8)', 'html/index.new'); +print $index html_title('Bibliografija Filozofskog fakulteta'); - my $xmlrecord = $marcxml->{$biblionumber} || die "missing $biblionumber marcxml"; +my $first_letter = ''; - my $parser = XML::LibXML->new(); - $parser->recover_silently(0); # don't die when you find &, >, etc - my $source = $parser->parse_string($xmlrecord); - my $style_doc = $parser->parse_file($xslfilename); - - my $xslt = XML::LibXSLT->new(); - my $parsed = $xslt->parse_stylesheet($style_doc); - my $transformed = $parsed->transform($source); - return $parsed->output_string( $transformed ); -} +debug 'authors' => \@authors; +sub author_html { + my ( $fh, $authid, $type, $label ) = @_; -mkdir 'html' unless -d 'html'; + return unless exists $authors->{$authid}->{$type}; -open(my $index, '>:encoding(utf-8)', 'html/index.html'); -print $index html_title('Bibliografija Filozogskog fakulteta'); + print $fh qq|

$label

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

$label

\n\n|; + } +} foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) { @@ -153,26 +274,71 @@ foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) { } print $index qq{
  • }, $row->{full_name}, "
    • \n"; - open(my $fh, '>:encoding(utf-8)', "html/$row->{authid}.html"); + my $path = "html/$row->{authid}"; + open(my $fh, '>:encoding(utf-8)', "$path.new"); print $fh html_title($row->{full_name}, "bibliografija"); - 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 za razdoblje 2008-2013

    |; + + author_html( $fh, $row->{authid}, 'aut' => 'Primarno autorstvo' ); + author_html( $fh, $row->{authid}, 'sec' => 'Sekundarno autorstvo' ); + print $fh html_end; close($fh); + rename "$path.new", "$path.html"; } print $index html_end; +close($index); +rename 'html/index.new', 'html/index.html'; + +debug 'auth_header' => $auth_header; + -#print dump( $authors ); +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} } ) { + push @{ $department_category_author->{$department}->{$category} }, $authid; + } + } +} + +debug 'department_category_author' => $department_category_author; + +mkdir 'html/departments' unless -d 'html/departments'; + +open(my $dep_fh, '>:encoding(utf-8)', 'html/departments/index.new'); +print $dep_fh html_title('Odsijeci Filozofskog fakulteta u Zagrebu'), qq|\n|, html_end; +close($dep_fh); +rename 'html/departments/index.new', 'html/departments/index.html'; +debug 'skip' => $skip;