git.rot13.org Git - koha-bibliografija/blob - html.pl

   1 #!/usr/bin/perl
   2
   3 # LC_COLLATE=hr_HR.utf8 KOHA_CONF=/etc/koha/sites/ffzg/koha-conf.xml ./html.pl
   4
   5 use warnings;
   6 use strict;
   7
   8 use DBI;
   9 use Data::Dump qw(dump);
  10 use autodie;
  11 use locale;
  12 use Text::Unaccent;
  13 use Carp qw(confess);
  14
  15 use lib '/srv/koha_ffzg';
  16 use C4::Context;
  17 use XML::LibXML;
  18 use XML::LibXSLT;
  19
  20 my $dbh = C4::Context->dbh;
  21
  22 sub debug {
  23         my ($title, $data) = @_;
  24         print "# $title ",dump($data), $/;
  25 }
  26
  27 my $xslfilename = 'compact.xsl';
  28
  29 my $auth_header;
  30 my $auth_department;
  31 my @authors;
  32
  33 my $skip;
  34
  35 my $sth_auth = $dbh->prepare(q{
  36 select
  37         authid,
  38         ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="a"]') as full_name,
  39         ExtractValue(marcxml,'//datafield[@tag="680"]/subfield[@code="a"]') as department
  40 from auth_header
  41 });
  42
  43 $sth_auth->execute();
  44 while( my $row = $sth_auth->fetchrow_hashref ) {
  45         $auth_header->{ $row->{authid} } = $row->{full_name};
  46         $row->{department} =~ s/, Filozofski fakultet u Zagrebu\s*// || next;
  47         $row->{department} =~ s/^.+\.\s*//;
  48         push @{ $auth_department->{ $row->{department} } }, $row->{authid};
  49 #       warn dump( $row );
  50         push @authors, $row;
  51
  52 }
  53
  54 debug 'auth_department' => $auth_department;
  55
  56
  57 my $authors;
  58 my $marcxml;
  59
  60 my $sth_select_authors  = $dbh->prepare(q{
  61 select
  62         biblionumber,
  63         itemtype,
  64         marcxml
  65 from biblioitems
  66 where
  67         agerestriction > 0
  68 });
  69
  70 =for sql
  71 --      ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="9"]') as first_author,
  72 --      ExtractValue(marcxml,'//datafield[@tag="700"]/subfield[@code="9"]') as other_authors,
  73 --      ExtractValue(marcxml,'//datafield[@tag="942"]/subfield[@code="t"]') as category,
  74
  75 --      and SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) between 2008 and 2013
  76 -- order by SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) desc
  77 =cut
  78
  79 my $biblio_year;
  80 my $type_stats;
  81
  82 my $parser = XML::LibXML->new();
  83 $parser->recover_silently(0); # don't die when you find &, >, etc
  84 my $style_doc = $parser->parse_file($xslfilename);
  85 my $xslt = XML::LibXSLT->new();
  86 my $parsed = $xslt->parse_stylesheet($style_doc);
  87
  88 my $biblio_html;
  89
  90 open(my $xml_fh, '>', '/tmp/bibliografija.xml') if $ENV{XML};
  91
  92 sub biblioitem_html {
  93         my $biblionumber = shift;
  94
  95         return $biblio_html->{$biblionumber} if exists $biblio_html->{$biblionumber};
  96
  97         my $xmlrecord = $marcxml->{$biblionumber} || confess "missing $biblionumber marcxml";
  98
  99         print $xml_fh $xmlrecord if $ENV{XML};
 100
 101         my $source = eval { $parser->parse_string($xmlrecord) };
 102         if ( $@ ) {
 103 #               warn "SKIP $biblionumber corrupt XML";
 104                 push @{ $skip->{XML_corrupt} }, $biblionumber;
 105                 return;
 106         }
 107
 108         my $transformed = $parsed->transform($source);
 109         $biblio_html->{$biblionumber} = $parsed->output_string( $transformed );
 110
 111         return ( $biblio_html->{$biblionumber}, $source ) if wantarray;
 112         return $biblio_html->{$biblionumber};
 113 }
 114
 115 $sth_select_authors->execute();
 116 while( my $row = $sth_select_authors->fetchrow_hashref ) {
 117 #       warn dump($row),$/;
 118
 119         my $biblio;
 120
 121         $marcxml->{ $row->{biblionumber} } = $row->{marcxml};
 122
 123         my ( undef, $doc ) = biblioitem_html( $row->{biblionumber} );
 124         if ( ! $doc ) {
 125                 warn "ERROR can't parse MARCXML ", $row->{biblionumber}, " ", $row->{marcxml}, "\n";
 126                 next;
 127         }
 128
 129         my $root = $doc->documentElement;
 130 =for leader
 131         my @leaders = $root->getElementsByLocalName('leader');
 132         if (@leaders) {
 133                 my $leader = $leaders[0]->textContent;
 134                 warn "leader $leader\n";
 135         }
 136 =cut
 137
 138         my $extract = {
 139                 '008' => undef,
 140                 '100' => '9',
 141                 '700' => '(9|4)',
 142                 '942' => 't'
 143         };
 144
 145         my $data;
 146
 147         foreach my $elt ($root->getChildrenByLocalName('*')) {
 148                 my $tag = $elt->getAttribute('tag');
 149                 next if ! $tag;
 150                 next unless exists $extract->{ $tag };
 151
 152         if ($elt->localname eq 'controlfield') {
 153                         if ( $tag eq '008' ) {
 154                                  $biblio_year->{ $row->{biblionumber} } = $elt->textContent;
 155                         }
 156                         next;
 157         } elsif ($elt->localname eq 'datafield') {
 158                         my $sf_data;
 159             foreach my $sfelt ($elt->getChildrenByLocalName('subfield')) {
 160                 my $sf = $sfelt->getAttribute('code');
 161                                 next unless $sf =~ m/$extract->{$tag}/;
 162                                 if ( exists $sf_data->{$sf} ) {
 163                                         $sf_data->{$sf} .= " " . $sfelt->textContent();
 164                                 } else {
 165                                         $sf_data->{$sf} = $sfelt->textContent();
 166                                 }
 167                         }
 168                         push @{ $data->{$tag} }, $sf_data if $sf_data;
 169         }
 170     }
 171
 172 #       warn "# ", $row->{biblionumber}, " data ",dump($data);
 173
 174         my $category = $data->{942}->[0]->{'t'};
 175         if ( ! $category ) {
 176 #               warn "# SKIP ", $row->{biblionumber}, " no category in ", dump($data);
 177                 push @{ $skip->{no_category} }, $row->{biblionumber};
 178                 next;
 179         }
 180
 181
 182         my $have_100 = 1;
 183
 184         if ( exists $data->{100} ) {
 185                         my @first_author = map { $_->{'9'} } @{ $data->{100} };
 186                         foreach my $authid ( @first_author ) {
 187                                 push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber};
 188                         }
 189         } else {
 190                 $have_100 = 0;
 191         }
 192
 193         my $have_edt;
 194
 195         if ( exists $data->{700} ) {
 196                         foreach my $auth ( @{ $data->{700} } ) {
 197                                 my $authid = $auth->{9} || next;
 198                                 my $type   = $auth->{4} || next; #die "no 4 in ",dump($data);
 199
 200                                 $type_stats->{$type}++;
 201
 202                                 if ( $type =~ m/(edt|trl|com|ctb)/ ) {
 203                                         push @{ $authors->{$authid}->{sec}->{ $category } }, $row->{biblionumber};
 204                                         push @{ $authors->{$authid}->{$1}->{ $category } }, $row->{biblionumber};
 205                                 } elsif ( $type =~ m/aut/ ) {
 206                                         if ( ! $have_100 ) {
 207                                                 $have_edt = grep { exists $_->{4} && $_->{4} =~ m/edt/ } @{ $data->{700} } if ! defined $have_edt;
 208                                                 if ( $have_edt ) {
 209                                                         $skip->{ have_700_edt }->{ $row->{biblionumber} }++;
 210                                                 } else {
 211                                                         push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber};
 212                                                 }
 213                                         } else {
 214                                                 push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber};
 215                                         }
 216                                 } else {
 217 #                                       warn "# SKIP ", $row->{biblionumber}, ' no 700$4 in ', dump($data);
 218                                         $skip->{ 'no_700$4' }->{ $row->{biblionumber} }++;
 219                                 }
 220                         }
 221         }
 222
 223 }
 224
 225 debug 'authors' => $authors;
 226 debug 'type_stats' => $type_stats;
 227 debug 'skip' => $skip;
 228
 229 my $category_label;
 230 my $sth_categories = $dbh->prepare(q{
 231 select authorised_value, lib from authorised_values where category = 'BIBCAT'
 232 });
 233 $sth_categories->execute();
 234 while( my $row = $sth_categories->fetchrow_hashref ) {
 235         $category_label->{ $row->{authorised_value} } = $row->{lib};
 236
 237 }
 238 debug 'category_label' => $category_label;
 239
 240 sub html_title {
 241         return qq|<html>
 242 <head>
 243 <meta charset="UTF-8">
 244 <title>|, join(" ", @_), qq|</title>
 245 <link href="style.css" type="text/css" rel="stylesheet" />
 246 </head>
 247 <body>
 248 |;
 249 }
 250
 251 sub html_end {
 252         return qq|</body>\n</html\n|;
 253 }
 254
 255 mkdir 'html' unless -d 'html';
 256
 257 open(my $index, '>:encoding(utf-8)', 'html/index.new');
 258 print $index html_title('Bibliografija Filozofskog fakulteta');
 259
 260 my $first_letter = '';
 261
 262 debug 'authors' => \@authors;
 263
 264 sub li_biblio {
 265         my ($biblionumber) = @_;
 266         return qq|<li>|,
 267                 qq|<a href="https://koha.ffzg.hr/cgi-bin/koha/opac-detail.pl?biblionumber=$biblionumber">$biblionumber</a>|,
 268                 biblioitem_html($biblionumber),
 269                 qq|<a href="https://koha.ffzg.hr:8443/cgi-bin/koha/cataloguing/addbiblio.pl?biblionumber=$biblionumber">edit</a>|,
 270                 qq|</li>\n|;
 271 }
 272
 273 sub author_html {
 274         my ( $fh, $authid, $type, $label ) = @_;
 275
 276         return unless exists $authors->{$authid}->{$type};
 277
 278         print $fh qq|<h2>$label</h2>\n|;
 279
 280         foreach my $category ( sort keys %{ $authors->{$authid}->{$type} } ) {
 281                 my $label = $category_label->{$category} || 'Bez kategorije';
 282                 print $fh qq|<h3>$label</h3>\n<ul>\n|;
 283                 foreach my $biblionumber ( @{ $authors->{$authid}->{$type}->{$category} } ) {
 284                         print $fh li_biblio( $biblionumber );
 285                 }
 286                 print $fh qq|</ul>\n|;
 287         }
 288 }
 289
 290 foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) {
 291
 292         my $first = substr( $row->{full_name}, 0, 1 );
 293         if ( $first ne $first_letter ) {
 294                 print $index qq{</ul>\n} if $first_letter;
 295                 $first_letter = $first;
 296                 print $index qq{<h1>$first</h1>\n<ul>\n};
 297         }
 298         print $index qq{<li><a href="}, $row->{authid}, qq{.html">}, $row->{full_name}, "</a></li>\n";
 299
 300         my $path = "html/$row->{authid}";
 301         open(my $fh, '>:encoding(utf-8)', "$path.new");
 302         print $fh html_title($row->{full_name}, "bibliografija");
 303         print $fh qq|<h1>$row->{full_name} - bibliografija za razdoblje 2008-2013</h1>|;
 304
 305         author_html( $fh, $row->{authid}, 'aut' => 'Primarno autorstvo' );
 306         author_html( $fh, $row->{authid}, 'sec' => 'Sekundarno autorstvo' );
 307
 308         print $fh html_end;
 309         close($fh);
 310         rename "$path.new", "$path.html";
 311
 312 }
 313
 314 print $index html_end;
 315 close($index);
 316 rename 'html/index.new', 'html/index.html';
 317
 318 debug 'auth_header' => $auth_header;
 319
 320
 321 my $department_category_author;
 322 foreach my $department ( sort keys %$auth_department ) {
 323         foreach my $authid ( sort @{ $auth_department->{$department} } ) {
 324                 my   @categories = keys %{ $authors->{$authid}->{aut} };
 325                 push @categories,  keys %{ $authors->{$authid}->{sec} };
 326                 foreach my $category ( sort @categories ) {
 327                         push @{ $department_category_author->{$department}->{$category} }, $authid;
 328                 }
 329         }
 330 }
 331
 332 debug 'department_category_author' => $department_category_author;
 333
 334 mkdir 'html/departments' unless -d 'html/departments';
 335
 336 open(my $dep_fh, '>:encoding(utf-8)', 'html/departments/index.new');
 337 print $dep_fh html_title('Odsijeci Filozofskog fakulteta u Zagrebu'), qq|<ul>\n|;
 338 foreach my $department ( sort keys %$department_category_author ) {
 339         my $dep = $department || 'Nema odsjeka';
 340         my $dep_file = unac_string('utf-8',$dep);
 341         print $dep_fh qq|<li><a href="$dep_file.html">$dep</a></li>\n|;
 342         open(my $fh, '>:encoding(utf-8)', "html/departments/$dep_file.new");
 343
 344         print $fh html_title($department . ' bibliografija');
 345         print $fh qq|<h1>$department bibliografija</h1>\n|;
 346
 347         print $fh qq|<h2>Primarno autorstvo</h2>\n|;
 348
 349         foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
 350
 351                 my @authids = @{ $department_category_author->{$department}->{$category} };
 352                 next unless @authids;
 353
 354                 my @biblionumber = map { @{ $authors->{$_}->{aut}->{$category} } } grep { exists $authors->{$_}->{aut}->{$category} } @authids;
 355
 356                 next unless @biblionumber;
 357
 358                 my $label = $category_label->{$category} || 'Bez kategorije';
 359                 print $fh qq|<h3>$label</h3>\n<ul>\n|;
 360
 361                 print $fh li_biblio( $_ ) foreach @biblionumber;
 362
 363                 print $fh qq|</ul>|;
 364         }
 365
 366
 367         print $fh qq|<h2>Sekundarno autorstvo</h2>\n|;
 368
 369         foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
 370
 371                 my @authids = @{ $department_category_author->{$department}->{$category} };
 372                 next unless @authids;
 373
 374                 my @biblionumber = map { @{ $authors->{$_}->{sec}->{$category} } } grep { exists $authors->{$_}->{sec}->{$category} } @authids;
 375
 376                 next unless @biblionumber;
 377
 378                 my $label = $category_label->{$category} || 'Bez kategorije';
 379                 print $fh qq|<h3>$label</h3>\n<ul>\n|;
 380
 381                 print $fh li_biblio( $_ ) foreach @biblionumber;
 382
 383                 print $fh qq|</ul>|;
 384         }
 385
 386
 387         print $fh html_end;
 388         close($fh);
 389         rename "html/departments/$dep_file.new", "html/departments/$dep_file.html";
 390 }
 391 print $dep_fh qq|</ul>\n|, html_end;
 392 close($dep_fh);
 393 rename 'html/departments/index.new', 'html/departments/index.html';
 394
 395 my $azvo_stat;
 396
 397 foreach my $department ( sort keys %$department_category_author ) {
 398         foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
 399                 foreach my $authid ( @{ $department_category_author->{$department}->{$category} } ) {
 400                         foreach my $type ( keys %{ $authors->{$authid} } ) {
 401                                 next unless exists $authors->{$authid}->{$type}->{$category};
 402                                 $azvo_stat->{ $department }->{ $category }->{ $type } += $#{ $authors->{$authid}->{$type}->{$category} } + 1;
 403                         }
 404                 }
 405         }
 406 }
 407
 408 debug 'azvo_stat' => $azvo_stat;
 409
 410 =for later
 411 open(my $fh, '>', 'html/azvo.new');
 412
 413
 414
 415 close($fh);
 416 rename 'html/azvo.new', 'html/azvo.html';
 417 =cut
 418