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 use utf8;
  15 use JSON;
  16 use POSIX qw(strftime);
  17 use Storable;
  18
  19 use lib '/srv/koha_ffzg';
  20 use C4::Context;
  21 use XML::LibXML;
  22 use XML::LibXSLT;
  23
  24 my $pid_file = '/dev/shm/bibliografija.pid';
  25 {
  26         if ( -e $pid_file ) {
  27                 open(my $fh, '<', $pid_file);
  28                 my $pid = <$fh>;
  29                 no autodie; # it will die on kill
  30                 kill 0, $pid || die "$0 allready running as pid $pid";
  31         }
  32         open(my $fh, '>', $pid_file);
  33         print $fh $$;
  34         close($fh);
  35 }
  36
  37
  38 my $dbh = C4::Context->dbh;
  39
  40 sub debug {
  41         my ($title, $data) = @_;
  42         print "# $title ",dump($data), $/ if $ENV{DEBUG};
  43 }
  44
  45 my $xslfilename = 'compact.xsl';
  46
  47 my $azvo_group_title = {
  48 'znanstveno nastavni' => qr/(profes|docent|znanstveni savjetnik|znanstveni suradnik)/i,
  49 'lektori i predavači' => qr/(lektor|predavač)/i,
  50 'asistenti i novaci' => qr/(asistent|novak)/i,
  51 };
  52
  53 my $department_groups = {
  54 'AAB_humanističke'             => qr/(anglistiku|arheologiju|antropologiju|filozofiju|fonetiku|germanistiku|hungarologiju|indologiju|slavenske|filologiju|komparativnu|kroatistiku|lingvistiku|povijest|romanistiku|talijanistiku)/i,
  55 'AAC_društvene'                        => qr/(informacijske|pedagogiju|psihologiju|sociologiju)/i,
  56 };
  57
  58 my $auth_header;
  59 my $auth_department;
  60 my $auth_group;
  61 my @authors;
  62 my $department_in_sum;
  63 my $department_in_group;
  64
  65 my $skip;
  66
  67 my $sth_auth = $dbh->prepare(q{
  68 select
  69         authid,
  70         ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="a"]') as full_name,
  71         ExtractValue(marcxml,'//datafield[@tag="680"]/subfield[@code="a"]') as department,
  72         ExtractValue(marcxml,'//datafield[@tag="680"]/subfield[@code="i"]') as academic_title
  73 from auth_header
  74 });
  75
  76 $sth_auth->execute();
  77 while( my $row = $sth_auth->fetchrow_hashref ) {
  78         if ( $row->{department} !~ m/Filozofski fakultet u Zagrebu/ ) {
  79                 push @{ $skip->{nije_ffzg} }, $row;
  80                 next;
  81         }
  82         $auth_header->{ $row->{authid} } = $row->{full_name};
  83         $row->{department} =~ s/, Filozofski fakultet u Zagrebu.*$//;
  84         $row->{department} =~ s/^.+\.\s*//;
  85         $row->{department} =~ s/\s+$//s;
  86         my $group;
  87         foreach my $title ( keys %$azvo_group_title ) {
  88                 if ( $row->{academic_title} =~ $azvo_group_title->{$title} ) {
  89                         $group = $title;
  90                         last;
  91                 }
  92         }
  93         if ( $group ) {
  94                 $row->{academic_group} = $group;
  95                 $auth_group->{ $row->{authid} } = $group;
  96                 $skip->{group_stat}->{$group}++;
  97         } else {
  98                 push @{ $skip->{no_academic_group} }, $row;
  99         }
 100
 101 #       warn "# ", dump( $row );
 102         push @{ $auth_department->{ $row->{department} } }, $row->{authid};
 103         push @authors, $row;
 104         $department_in_sum->{ $row->{department} }++;
 105         foreach my $name ( keys %$department_groups ) {
 106                 my $regex = $department_groups->{$name};
 107                 if ( $row->{department} =~ $regex ) {
 108                         $department_in_group->{ $row->{department} } = $name;
 109                         last;
 110                 }
 111         }
 112 }
 113
 114 debug 'department_in_group' => $department_in_group;
 115
 116 foreach my $department ( keys %$department_in_sum ) {
 117 #       $department_in_sum->{$department} = 0 unless $department =~ m/(centar|croaticum|katedra|odsjek)/i;
 118 }
 119
 120 debug 'auth_department' => $auth_department;
 121 store $auth_department, '/dev/shm/auth_department.storable';
 122 debug 'auth_group' => $auth_group;
 123 debug 'department_in_sum' => $department_in_sum;
 124
 125
 126 my $authors;
 127 my $marcxml;
 128
 129 my $sth_select_authors  = $dbh->prepare(q{
 130 select
 131         biblioitems.biblionumber,
 132         itemtype,
 133         metadata as marcxml
 134 from biblioitems
 135 join biblio_metadata on (biblio_metadata.biblionumber = biblioitems.biblionumber)
 136 where
 137         agerestriction > 0
 138 });
 139
 140 =for sql
 141 --      ExtractValue(marcxml,'//datafield[@tag="100"]/subfield[@code="9"]') as first_author,
 142 --      ExtractValue(marcxml,'//datafield[@tag="700"]/subfield[@code="9"]') as other_authors,
 143 --      ExtractValue(marcxml,'//datafield[@tag="942"]/subfield[@code="t"]') as category,
 144
 145 --      and SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) between 2008 and 2013
 146 -- order by SUBSTR(ExtractValue(marcxml,'//controlfield[@tag="008"]'),8,4) desc
 147 =cut
 148
 149 my $biblio_year;
 150 my $biblio_full_name;
 151 my $type_stats;
 152
 153 my $parser = XML::LibXML->new();
 154 $parser->recover_silently(0); # don't die when you find &, >, etc
 155 my $style_doc = $parser->parse_file($xslfilename);
 156 my $xslt = XML::LibXSLT->new();
 157 my $parsed = $xslt->parse_stylesheet($style_doc);
 158
 159 my $biblio_html;
 160 my $biblio_parsed;
 161 my $biblio_data;
 162 my $biblio_author_external;
 163
 164 open(my $xml_fh, '>', '/tmp/bibliografija.xml') if $ENV{XML};
 165
 166 sub biblioitem_html {
 167         my ($biblionumber, $parse_only) = @_;
 168
 169         return $biblio_html->{$biblionumber} if exists $biblio_html->{$biblionumber} && ! $parse_only;
 170
 171         my $xmlrecord = $marcxml->{$biblionumber} || confess "missing $biblionumber marcxml";
 172
 173         print $xml_fh $xmlrecord if $ENV{XML};
 174
 175         my $source = eval { $parser->parse_string($xmlrecord) };
 176         if ( $@ ) {
 177 #               warn "SKIP $biblionumber corrupt XML";
 178                 push @{ $skip->{XML_corrupt} }, $biblionumber;
 179                 return;
 180         }
 181
 182         if ( $parse_only ) {
 183                 $biblio_parsed->{$biblionumber} = $source;
 184                 return $source;
 185         }
 186
 187         my $transformed = $parsed->transform($source);
 188         $biblio_html->{$biblionumber} = $parsed->output_string( $transformed );
 189
 190         delete $biblio_parsed->{$biblionumber};
 191
 192         return $biblio_html->{$biblionumber};
 193 }
 194
 195 $sth_select_authors->execute();
 196 while( my $row = $sth_select_authors->fetchrow_hashref ) {
 197 #       warn dump($row),$/;
 198
 199         my $biblio;
 200
 201         $marcxml->{ $row->{biblionumber} } = $row->{marcxml};
 202
 203         my $doc = biblioitem_html( $row->{biblionumber}, 1 );
 204         if ( ! $doc ) {
 205 #               warn "ERROR can't parse MARCXML ", $row->{biblionumber}, " ", $row->{marcxml}, "\n";
 206                 next;
 207         }
 208
 209         my $root = $doc->documentElement;
 210 =for leader
 211         my @leaders = $root->getElementsByLocalName('leader');
 212         if (@leaders) {
 213                 my $leader = $leaders[0]->textContent;
 214                 warn "leader $leader\n";
 215         }
 216 =cut
 217
 218         my $extract = {
 219                 '008' => undef,
 220                 '100' => '(9|a)',
 221                 '245' => 'a',
 222                 '680' => 'i',
 223                 '700' => '(9|4|a)',
 224                 '942' => '(t|r|v)'
 225         };
 226
 227         my $data;
 228
 229         foreach my $elt ($root->getChildrenByLocalName('*')) {
 230                 my $tag = $elt->getAttribute('tag');
 231                 next if ! $tag;
 232                 next unless exists $extract->{ $tag };
 233
 234         if ($elt->localname eq 'controlfield') {
 235                         if ( $tag eq '008' ) {
 236                                 my $content = $elt->textContent;
 237                                 my $year = substr($content, 7, 4 );
 238                                 if ( $year !~ m/^\d+$/ ) {
 239                                         $year = 0;
 240                                         push @{ $skip->{invalid_year} }, $row->{biblionumber};
 241                                 }
 242                                 $biblio_year->{ $row->{biblionumber} } = $data->{year} = $year;
 243                                 $data->{'008'} = $content;
 244                         }
 245                         next;
 246         } elsif ($elt->localname eq 'datafield') {
 247                         my $sf_data;
 248             foreach my $sfelt ($elt->getChildrenByLocalName('subfield')) {
 249                 my $sf = $sfelt->getAttribute('code');
 250                                 next unless $sf =~ m/$extract->{$tag}/;
 251                                 if ( exists $sf_data->{$sf} ) {
 252                                         $sf_data->{$sf} .= " " . $sfelt->textContent();
 253                                 } else {
 254                                         $sf_data->{$sf} = $sfelt->textContent();
 255                                 }
 256                         }
 257                         push @{ $data->{$tag} }, $sf_data if $sf_data;
 258                 }
 259         }
 260
 261         if ( ! defined $data->{year} ) {
 262                 warn "MISSING year in ", $row->{biblionumber};
 263 =for remove-year-limit
 264         } elsif ( $data->{year} < 2008 ) {
 265                 push @{ $skip->{year_lt_2008} }, $row->{biblionumber};
 266                 next;
 267         } elsif ( $data->{year} > 2013 ) {
 268                 push @{ $skip->{year_gt_2013} }, $row->{biblionumber};
 269                 next;
 270 =cut
 271         }
 272
 273 #       warn "# ", $row->{biblionumber}, " data ",dump($data);
 274
 275         my $category = $data->{942}->[0]->{'t'};
 276         if ( ! $category ) {
 277 #               warn "# SKIP ", $row->{biblionumber}, " no category in ", dump($data);
 278                 push @{ $skip->{no_category} }, $row->{biblionumber};
 279                 next;
 280         }
 281
 282         my $have_100 = 1;
 283
 284         if ( exists $data->{100} ) {
 285                         my @first_author =
 286                                 map { $_->{'9'} }
 287                                 grep {
 288                                         if ( ! exists $_->{9} ) {
 289                                                 $biblio_author_external->{ $row->{biblionumber} }++;
 290                                                 0;
 291                                         } elsif ( exists $auth_header->{ $_->{9} } ) {
 292                                                 1; # from FFZXG
 293                                         } else {
 294                                                 0;
 295                                         }
 296                                 }
 297                                 @{ $data->{100} };
 298                         foreach my $authid ( @first_author ) {
 299                                 push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber};
 300                         }
 301                         $biblio_full_name->{ $row->{biblionumber} } = $data->{100}->[0]->{a};
 302         } else {
 303                 $have_100 = 0;
 304         }
 305
 306         $biblio_full_name->{ $row->{biblionumber} } ||= $data->{245}->[0]->{a};
 307
 308         my $have_edt;
 309
 310         if ( exists $data->{700} ) {
 311                         my @other_authors =
 312                                 grep {
 313                                         if ( ! exists $_->{9} ) {
 314                                                 $biblio_author_external->{ $row->{biblionumber} }++;
 315                                                 0;
 316                                         } elsif ( exists $auth_header->{ $_->{9} } ) {
 317                                                 1; # from FFZXG
 318                                         } else {
 319                                                 0;
 320                                         }
 321                                 }
 322                                 @{ $data->{700} };
 323                         foreach my $auth ( @other_authors ) {
 324                                 my $authid = $auth->{9} || next;
 325                                 my $type   = $auth->{4} || next; #die "no 4 in ",dump($data);
 326
 327                                 $type_stats->{$type}++;
 328
 329                                 my @types = split(/[\s\/]+/, $type);
 330
 331                                 foreach my $type ( @types ) {
 332                                         my $type = substr($type,0,3);
 333                                         $type_stats->{_count_each_type}->{$type}++;
 334
 335                                         if ( $type =~ m/(edt|trl|com|ctb)/ ) {
 336                                                 push @{ $authors->{$authid}->{__sec}->{ $category } }, $row->{biblionumber};
 337                                                 push @{ $authors->{$authid}->{$type}->{ $category } }, $row->{biblionumber};
 338                                                 $type =~ s/(com|ctb)/_ostalo/;
 339                                                 push @{ $authors->{$authid}->{$type}->{ $category } }, $row->{biblionumber};
 340
 341                                         } elsif ( $type =~ m/aut/ ) {
 342                                                 if ( ! $have_100 ) {
 343                                                         $have_edt = grep { exists $_->{4} && $_->{4} =~ m/edt/ } @{ $data->{700} } if ! defined $have_edt;
 344                                                         if ( $have_edt ) {
 345                                                                 $skip->{ have_700_edt }->{ $row->{biblionumber} }++;
 346                                                         } else {
 347                                                                 push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber};
 348                                                         }
 349                                                 } else {
 350                                                         push @{ $authors->{$authid}->{aut}->{ $category } }, $row->{biblionumber};
 351                                                 }
 352                                         } else {
 353 #                                               warn "# SKIP ", $row->{biblionumber}, ' no 700$4 in ', dump($data);
 354                                                 $skip->{ 'no_700$4' }->{ $row->{biblionumber} }++;
 355                                         }
 356                                 }
 357                         }
 358                         delete $data->{700};
 359         }
 360
 361         $biblio_data->{ $row->{biblionumber} } = $data;
 362
 363 }
 364
 365 debug 'authors' => $authors;
 366 store $authors, '/dev/shm/authors.storable';
 367 debug 'type_stats' => $type_stats;
 368 debug 'skip' => $skip;
 369 debug 'biblio_year' => $biblio_year;
 370 debug 'biblio_full_name' => $biblio_full_name;
 371 debug 'biblio_data' => $biblio_data;
 372 debug 'biblio_author_external' => $biblio_author_external;
 373
 374 my $category_label;
 375 my $sth_categories = $dbh->prepare(q{
 376 select authorised_value, lib from authorised_values where category = 'BIBCAT'
 377 });
 378 $sth_categories->execute();
 379 while( my $row = $sth_categories->fetchrow_hashref ) {
 380         $category_label->{ $row->{authorised_value} } = $row->{lib};
 381
 382 }
 383 debug 'category_label' => $category_label;
 384
 385 sub html_title {
 386         return qq|<html>
 387 <head>
 388 <meta charset="UTF-8">
 389 <title>|, join(" ", @_), qq|</title>
 390 <link href="style.css" type="text/css" rel="stylesheet" />
 391 <script src="//code.jquery.com/jquery-1.11.2.js"></script>
 392 <script src="filters.js"></script>
 393 </head>
 394 <body>
 395 |;
 396 }
 397
 398 sub html_end {
 399         return
 400                 qq|<small style="color:gray">Zadnji puta osvježeno: |,
 401                 strftime("%Y-%m-%d %H:%M:%S\n", localtime()),
 402                 qq|</body>\n</html>\n|;
 403 }
 404
 405 mkdir 'html' unless -d 'html';
 406
 407 open(my $index, '>:encoding(utf-8)', 'html/index.new');
 408 print $index html_title('Bibliografija Filozofskog fakulteta');
 409
 410 my $first_letter = '';
 411
 412 debug 'authors' => \@authors;
 413
 414 sub li_biblio {
 415         my ($biblionumber) = @_;
 416         return qq|<li class="y|, $biblio_year->{$biblionumber}, qq|">|,
 417                 qq|<a href="https://koha.ffzg.hr/cgi-bin/koha/opac-detail.pl?biblionumber=$biblionumber">$biblionumber</a>|,
 418                 biblioitem_html($biblionumber),
 419                 qq|<a href="https://koha.ffzg.hr:8443/cgi-bin/koha/cataloguing/addbiblio.pl?biblionumber=$biblionumber">edit</a>|,
 420                 qq|</li>\n|;
 421 }
 422
 423 sub unique {
 424         my $unique;
 425         $unique->{$_}++ foreach @_;
 426         return keys %$unique;
 427 }
 428
 429 sub unique_biblionumber {
 430         my @v = unique @_;
 431         return sort {
 432                 $biblio_year->{$b} <=> $biblio_year->{$a} ||
 433                 $biblio_full_name->{$a} cmp $biblio_full_name->{$b} ||
 434                 $a <=> $b
 435         } @v;
 436 }
 437
 438 sub author_html {
 439         my ( $fh, $authid, $type, $label ) = @_;
 440
 441         return unless exists $authors->{$authid}->{$type};
 442
 443         print $fh qq|<a name="$type"><h2>$label</h2></a>\n|;
 444
 445         foreach my $category ( sort keys %{ $authors->{$authid}->{$type} } ) {
 446                 my $label = $category_label->{$category} || 'Bez kategorije';
 447                 print $fh qq|<a name="$type-$category"><h3>$label</h3></a>\n<ol>\n|;
 448                 foreach my $biblionumber ( unique_biblionumber @{ $authors->{$authid}->{$type}->{$category} } ) {
 449                         print $fh li_biblio( $biblionumber );
 450                 }
 451                 print $fh qq|</ol>\n|;
 452         }
 453 }
 454
 455 my @toc_type_label = (
 456 'aut' => 'Primarno autorstvo',
 457 'edt' => 'Uredništva',
 458 'trl' => 'Prijevodi',
 459 '_ostalo' => 'Ostalo',
 460 );
 461
 462
 463 sub count_author_years {
 464         my $years = shift;
 465         my ($authid) = @_;
 466         foreach my $type ( keys %{ $authors->{$authid} } ) {
 467 #               next if $type =~ m/^_/; # FIXME
 468                 foreach my $category ( keys %{ $authors->{$authid}->{$type} } ) {
 469                         foreach my $biblionumber ( unique_biblionumber @{ $authors->{$authid}->{$type}->{$category} } ) {
 470                                 $years->{ $biblio_year->{ $biblionumber } }->{ $type . '-' . $category }->{ $biblionumber }++;
 471                         }
 472                 }
 473         }
 474         return $years;
 475 }
 476
 477 sub html_year_selection {
 478         my $fh = shift;
 479         my @authids = unique @_;
 480
 481         debug 'html_year_selection authids=', [ @authids ];
 482
 483         print $fh qq|<span id="years">Godine:\n|;
 484         my $type_cat_count = {};
 485         my $years;
 486
 487         foreach my $authid ( @authids ) {
 488                 $years = count_author_years( $years, $authid );
 489         }
 490
 491         debug 'years' => $years;
 492
 493         foreach my $year ( sort { $b <=> $a } keys %$years ) {
 494                 print $fh qq|<label><input name="year_selection" value="$year" type=checkbox onClick="toggle_year($year, this)" checked="checked">$year</label>&nbsp;\n|;
 495                 foreach my $type_cat ( keys %{ $years->{$year} } ) {
 496                         my $count = scalar keys %{ $years->{$year}->{$type_cat} };
 497                         $years->{$year}->{$type_cat} = $count; # remove biblionumbers and use count
 498                         $type_cat_count->{ $type_cat } += $count;
 499                         my ($type,$cat) = split(/-/, $type_cat);
 500                         $type_cat_count->{_toc}->{$type}->{$cat}++;
 501                         $type_cat_count->{_toc_count}->{$type} += $count;
 502                 }
 503         }
 504
 505         print $fh qq|
 506 <input type=button value="all" onClick="all_years(1)">
 507 <input type=button value="none" onClick="all_years(0)">
 508         |;
 509
 510         print $fh qq|</span>|;
 511
 512         print $fh q|
 513 <script>
 514
 515 var years = |, encode_json($years), q|;
 516
 517 var type_cat_count = |, encode_json($type_cat_count), q|;
 518
 519 </script>
 520
 521         |;
 522
 523         debug 'type_cat_count' => $type_cat_count;
 524
 525         # TOC
 526         print $fh qq|<ul id="toc">\n|;
 527         my $i = 0;
 528         while ( $i < $#toc_type_label ) {
 529                 my $type  = $toc_type_label[$i++] || die "type";
 530                 my $label = $toc_type_label[$i++] || die "label";
 531                 next unless exists $type_cat_count->{_toc}->{$type};
 532                 print $fh qq| <li class="toc" id="toc-$type"><a href="#$type">$label</a> <tt id="toc-count-$type">$type_cat_count->{_toc_count}->{$type}</tt></li>\n <ul>\n|;
 533                 foreach my $category ( sort keys %{ $type_cat_count->{_toc}->{$type} } ) {
 534                         my $label = $category_label->{$category} || 'Bez kategorije';
 535                         my $count = $type_cat_count->{ $type . '-' . $category };
 536                         my $cat_html = $category;
 537                         $cat_html =~ s/\./-/g;
 538                         print $fh qq|  <li class="toc" id="toc-$category"><a href="#$type-$category">$label</a> <tt id="toc-count-$type-$cat_html">$count</tt></li>\n|;
 539                 }
 540                 print $fh qq| </ul>\n|;
 541         }
 542         print $fh qq|</ul>\n|;
 543
 544 }
 545
 546 my $authid_fullname;
 547
 548 foreach my $row ( sort { $a->{full_name} cmp $b->{full_name} } @authors ) {
 549
 550         my $first = substr( $row->{full_name}, 0, 1 );
 551         if ( $first ne $first_letter ) {
 552                 print $index qq{</ul>\n} if $first_letter;
 553                 $first_letter = $first;
 554                 print $index qq{<h1>$first</h1>\n<ul>\n};
 555         }
 556         print $index qq{<li><a href="}, $row->{authid}, qq{.html">}, $row->{full_name}, "</a></li>\n";
 557
 558         $authid_fullname->{ $row->{authid} } = $row->{full_name};
 559
 560         my $path = "html/$row->{authid}";
 561         open(my $fh, '>:encoding(utf-8)', "$path.new");
 562         print $fh html_title($row->{full_name}, "bibliografija");
 563         print $fh qq|<h1>$row->{full_name} - bibliografija</h1>\n|;
 564
 565         html_year_selection $fh => $row->{authid};
 566
 567         my $i = 0;
 568         while ( $i < $#toc_type_label ) {
 569                 my $type  = $toc_type_label[$i++] || die "type";
 570                 my $label = $toc_type_label[$i++] || die "label";
 571                 author_html( $fh, $row->{authid}, $type => $label );
 572         }
 573
 574         print $fh html_end;
 575         close($fh);
 576         rename "$path.new", "$path.html";
 577
 578 }
 579
 580 print $index html_end;
 581 close($index);
 582 rename 'html/index.new', 'html/index.html';
 583
 584 debug 'auth_header' => $auth_header;
 585
 586 debug 'authid_fullname' => $authid_fullname;
 587
 588 my $department_category_author;
 589 foreach my $department ( sort keys %$auth_department ) {
 590         foreach my $authid ( sort @{ $auth_department->{$department} } ) {
 591                 my   @categories = keys %{ $authors->{$authid}->{aut} };
 592                 push @categories,  keys %{ $authors->{$authid}->{__sec} };
 593                 foreach my $category ( sort @categories ) {
 594                         push @{ $department_category_author->{$department}->{$category} }, $authid;
 595                         push @{ $department_category_author->{'AAA_ukupno'}->{$category} }, $authid if $department_in_sum->{$department};
 596                         if ( my $group = $department_in_group->{ $department } ) {
 597                                 push @{ $department_category_author->{$group}->{$category} }, $authid;
 598                         } else {
 599                                 $skip->{'department_not_in_group'}->{ $department }++;
 600                         }
 601                 }
 602         }
 603 }
 604
 605 debug 'department_category_author' => $department_category_author;
 606
 607
 608 sub department_html {
 609         my ( $fh, $department, $type, $label, $csv_fh ) = @_;
 610
 611         print $fh qq|<a name="$type"><h2>$label</h2></a>\n|;
 612
 613         foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
 614
 615                 my @authids = @{ $department_category_author->{$department}->{$category} };
 616                 next unless @authids;
 617
 618                 my @biblionumber = unique_biblionumber map { @{ $authors->{$_}->{$type}->{$category} } } grep { exists $authors->{$_}->{$type}->{$category} } @authids;
 619
 620                 next unless @biblionumber;
 621
 622                 my $cat_label = $category_label->{$category} || 'Bez kategorije';
 623                 print $fh qq|<a name="$type-$category"><h3>$cat_label</h3></a>\n<ol>\n|;
 624
 625                 foreach my $bib_num ( @biblionumber ) {
 626                         my @li = li_biblio( $bib_num );
 627                         my $li_html = join('', @li);
 628                         $li_html =~ s{<a name="(col-\d+)"/a>}{<!-- $1 -->}gs;
 629                         print $fh $li_html;
 630
 631                         next unless $csv_fh;
 632
 633                         my $year = $li[1];
 634                         my @html;
 635                         foreach ( split(/<a name="col-/, $li[4]) ) {
 636                                 if ( s{^(\d+)"></a>}{} ) {
 637                                         my $nr = $1;
 638                                         s{\s+}{ }gs;
 639                                         $html[$nr] = $_;
 640                                 } else {
 641                                         warn "SKIPPED: Can't find col in [$_] from $li[4]" unless m/^<[^>]+>$/;
 642                                 }
 643                         }
 644                         my $html = join("\t", @html);
 645
 646                         $html =~ s{</?[^>]*>}{}gs;
 647                         $html =~ s{\s+$}{}gs;
 648                         print $csv_fh "$bib_num\t$year\t$type\t$label\t$category\t$cat_label\t$html\n";
 649                 }
 650
 651                 print $fh qq|</ol>|;
 652         }
 653
 654 }
 655
 656
 657 mkdir 'html/departments' unless -d 'html/departments';
 658
 659 open(my $dep_fh, '>:encoding(utf-8)', 'html/departments/index.new');
 660 print $dep_fh html_title('Odsjeci Filozofskog fakulteta u Zagrebu'), qq|<ul>\n|;
 661 foreach my $department ( sort keys %$department_category_author ) {
 662         my $dep = $department || 'Nema odsjeka';
 663         my $dep_file = unac_string('utf-8',$dep);
 664         print $dep_fh qq|<li><a href="$dep_file.html">$dep</a></li>\n|;
 665         open(my $fh, '>:encoding(utf-8)', "html/departments/$dep_file.new");
 666
 667         print $fh html_title($department . ' bibliografija');
 668         print $fh qq|<h1>$department bibliografija</h1>\n|;
 669
 670         my @authids;
 671         foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
 672                 push @authids, @{ $department_category_author->{$department}->{$category} };
 673         }
 674         html_year_selection $fh => @authids;
 675
 676         my $csv_fh;
 677         if ( $department eq 'AAA_ukupno' ) {
 678                 open($csv_fh, '>:encoding(utf-8)', "html/departments/$department.csv");
 679         }
 680
 681         my $i = 0;
 682         while ( $i < $#toc_type_label ) {
 683                 my $type  = $toc_type_label[$i++] || die "type";
 684                 my $label = $toc_type_label[$i++] || die "label";
 685                 department_html( $fh, $department, $type, $label, $csv_fh );
 686         }
 687
 688         close($csv_fh) if $csv_fh;
 689
 690         print $fh html_end;
 691         close($fh);
 692         rename "html/departments/$dep_file.new", "html/departments/$dep_file.html";
 693
 694 }
 695 print $dep_fh qq|</ul>\n|, html_end;
 696 close($dep_fh);
 697 rename 'html/departments/index.new', 'html/departments/index.html';
 698
 699 my $azvo_stat_biblio;
 700
 701 foreach my $department ( sort keys %$department_category_author ) {
 702         foreach my $category ( sort keys %{ $department_category_author->{$department} } ) {
 703                 foreach my $authid ( @{ $department_category_author->{$department}->{$category} } ) {
 704                         my $group = $auth_group->{$authid};
 705                         if ( ! $group ) {
 706                                 push @{ $skip->{no_auth_group} }, $authid;
 707                                 next;
 708                         }
 709                         foreach my $type ( keys %{ $authors->{$authid} } ) {
 710                                 next unless exists $authors->{$authid}->{$type}->{$category};
 711                                 push @{ $azvo_stat_biblio->{ $department }->{ $category }->{ $type }->{$group} },  @{ $authors->{$authid}->{$type}->{$category} };
 712                                 push @{ $azvo_stat_biblio->{ $department }->{ $category }->{ $type }->{''} },  @{ $authors->{$authid}->{$type}->{$category} };
 713                         }
 714                 }
 715                 foreach my $type ( keys %{ $azvo_stat_biblio->{ $department }->{ $category } } ) {
 716                         foreach my $group ( keys %{ $azvo_stat_biblio->{ $department }->{ $category }->{ $type } } ) {
 717                                 my @biblios = unique_biblionumber @{ $azvo_stat_biblio->{ $department }->{ $category }->{ $type }->{ $group } };
 718                                 $azvo_stat_biblio->{ $department }->{ $category }->{ $type }->{ $group } = [ @biblios ];
 719                         }
 720                 }
 721         }
 722 }
 723
 724 debug 'azvo_stat_biblio' => $azvo_stat_biblio;
 725
 726 my @report_lines;
 727 my @report_labels;
 728
 729 my $label;
 730 my $sub_labels;
 731 open(my $report, '<:encoding(utf-8)', 'nAZVO.txt');
 732 while( <$report> ) {
 733         chomp;
 734         if ( /^([^\t]+)\t+(.+)/ ) {
 735                 $label = $1;
 736                 push @report_labels, $label;
 737                 my $type = [ map { m/\s+/ ? [ split(/\s+/,$_) ] : [ $_, 'aut' ] } split (/\s*\+\s*/, $2) ];
 738                 push @report_lines, [ $label, @$type ];
 739         } elsif ( /^\t+([^\t]+):\t+(\d+)(\w*)\t*(.*)$/ ) {
 740                 push @{ $sub_labels->{$label} }, [ $1, $2, $3, $4 ];
 741                 my $sub_label = $1;
 742                 pop (@report_labels) if ( $report_labels[ $#report_labels ] =~ m/^$label$/ ); # remove partial name
 743                 push @report_labels, $label . $sub_label;
 744         } else {
 745                 die "ERROR: [$_]\n";
 746         }
 747 }
 748
 749 debug 'report_lines', \@report_lines;
 750 debug 'sub_labels', $sub_labels;
 751 debug 'report_labels', \@report_labels;
 752
 753 my @departments = ( sort { lc($a) cmp lc($b) } keys %$azvo_stat_biblio );
 754
 755 debug 'departments' => \@departments;
 756
 757 my $department2col;
 758 $department2col->{ $departments[$_] } = $_ foreach ( 0 .. $#departments );
 759 my $label2row;
 760 $label2row->{ $report_labels[$_] } = $_ foreach ( 0 .. $#report_labels );
 761
 762 my $table;
 763
 764 sub table_count {
 765         my $label = shift @_;
 766         my $department = shift @_;
 767         my $group = shift @_;
 768         my @biblionumbers = unique @_;
 769         $table->{ffzg}->{$group}->[ $label2row->{ $label } ]->[ $department2col->{$department} ] = scalar @biblionumbers;
 770         $table->{external}->{$group}->[ $label2row->{ $label } ]->[ $department2col->{$department} ] = scalar grep { $biblio_author_external->{$_} } @biblionumbers;
 771 }
 772
 773 foreach my $group ( '', keys %$azvo_group_title ) {
 774
 775 foreach my $department ( @departments ) {
 776         foreach my $line ( @report_lines ) {
 777                 my $label = $line->[0];
 778                 my @biblionumbers;
 779                 foreach ( 1 .. $#$line ) {
 780                         my ( $category, $type ) = @{ $line->[ $_ ] };
 781                         my $b = $azvo_stat_biblio->{ $department }->{$category}->{$type}->{$group};
 782                         push @biblionumbers, @$b if $b;
 783                 }
 784                 if ( $sub_labels->{$label} ) {
 785                         my $sub_stats;
 786                         foreach my $biblionumber ( @biblionumbers ) {
 787                                 my $data = $biblio_data->{$biblionumber} || die "can't find biblionumber $biblionumber";
 788                                 foreach my $sub_label ( @{ $sub_labels->{$label} } ) {
 789                                         my ( $sub_label, $field, $sf, $regex ) = @$sub_label;
 790                                         if ( ! $regex ) {
 791                                                 push @{ $sub_stats->{ $sub_label } }, $biblionumber;
 792                                                 last;
 793                                         }
 794                                         if ( $field < 100 ) {
 795                                                 if ( $data->{$field} =~ m/$regex/ ) {
 796                                                         push @{ $sub_stats->{ $sub_label } }, $biblionumber;
 797                                                         last;
 798                                                 }
 799                                         } else {
 800                                                 if ( exists $data->{$field}->[0]->{$sf} && $data->{$field}->[0]->{$sf} =~ m/$regex/ ) {
 801                                                         push @{ $sub_stats->{ $sub_label } }, $biblionumber;
 802                                                         last;
 803                                                 }
 804                                         }
 805                                 }
 806                         }
 807                         foreach my $sub_label ( keys %$sub_stats ) {
 808                                 my $full_label = $label . $sub_label;
 809                                 table_count $full_label, $department, $group, @{ $sub_stats->{$sub_label} };
 810                         }
 811                 } else {
 812                         table_count $label, $department, $group, @biblionumbers;
 813                 }
 814         }
 815 }
 816
 817 } # group
 818
 819 #debug 'table', $table;
 820
 821 open(my $fh, '>:encoding(utf-8)', 'html/azvo.new');
 822 open(my $fh2, '>:encoding(utf-8)', 'html/azvo2.new');
 823
 824 sub print_fh {
 825         print $fh @_;
 826         print $fh2 @_;
 827 }
 828
 829 print $fh html_title('AZVO tablica - FFZG');
 830 print $fh2 html_title('AZVO tablica - kolaboracija sa FFZG');
 831
 832 foreach my $group ( keys %{ $table->{ffzg} } ) {
 833
 834                 print_fh "<h1>$group</h1>" if $group;
 835
 836                 print_fh "<table border=1>\n";
 837                 print_fh "<tr><th></th>";
 838                 print_fh "<th>$_</th>" foreach @departments;
 839                 print_fh "</tr>\n";
 840
 841                 foreach my $row ( 0 .. $#{ $table->{ffzg}->{$group} } ) {
 842                         print_fh "<tr><th>", $report_labels[$row], "</th>\n";
 843                         foreach ( 0 .. $#departments ) {
 844                                 print_fh "<td>";
 845                                 print $fh $table->{ffzg}->{$group}->[ $row ]->[ $_ ] || '';
 846                                 print $fh2 $table->{external}->{$group}->[ $row ]->[ $_ ] || '';
 847                                 print_fh "</td>\n"
 848                         }
 849                         print_fh "</tr>\n";
 850                 }
 851
 852                 print_fh "</table>\n";
 853
 854 } # group
 855
 856 print_fh html_end;
 857 close($fh);
 858 close($fh2);
 859 rename 'html/azvo.new', 'html/azvo.html';
 860 rename 'html/azvo2.new', 'html/azvo2.html';
 861
 862 my $dep_au_count;
 863
 864 foreach my $department ( @departments ) {
 865         foreach my $line ( @report_lines ) {
 866                 my $label = $line->[0];
 867                 my @biblionumbers;
 868                 foreach ( 1 .. $#$line ) {
 869                         my ( $category, $type ) = @{ $line->[ $_ ] };
 870
 871                         foreach my $authid ( @{ $auth_department->{$department} } ) {
 872                                 next unless exists $authors->{$authid}->{$type}->{$category};
 873                                 my @biblionumbers = grep { $biblio_year->{$_} >= 2012 } @{ $authors->{$authid}->{$type}->{$category} };
 874
 875                                 $dep_au_count->{ $department }->{ $authid }->{ $label } += scalar @biblionumbers;
 876                         }
 877                 }
 878         }
 879 }
 880
 881 debug 'dep_au_count', $dep_au_count;
 882
 883 mkdir 'html/dep_au' unless -d 'html/dep_au';
 884 open(my $dep_fh, '>', 'html/dep_au/index.new');
 885 print $dep_fh html_title('Odsjeci Filozofskog fakulteta u Zagrebu'), qq|<ul>\n|;
 886 foreach my $department ( sort keys %{ $dep_au_count } ) {
 887
 888         my $dep = $department || 'Nema odsjeka';
 889         my $dep_file = unac_string('utf-8',$dep);
 890         print $dep_fh qq|<li><a href="$dep_file.html">$dep</a></li>\n|;
 891         open(my $fh, '>:encoding(utf-8)', "html/dep_au/$dep_file.new");
 892
 893         print $fh html_title($department . ' bibliografija tablica');
 894
 895         # FIXME table
 896         print $fh qq|<table>\n<tr><th></th><th>|
 897                 , join('</th><th>', @report_labels )
 898                 , qq|</th></tr>\n|
 899                 ;
 900
 901         foreach my $authid ( keys %{ $dep_au_count->{ $department } } ) {
 902                 print $fh qq|<tr><th>$authid_fullname->{$authid}</th><th>|
 903                                 , join('</th><th>', map { $dep_au_count->{$department}->{$authid}->{$_} || '-' } @report_labels )
 904                                 , qq|</th></tr>\n|
 905                                 ;
 906         }
 907
 908
 909         print $fh qq|</table>\n|;
 910
 911         print $fh html_end;
 912         close($fh);
 913         rename "html/dep_au/$dep_file.new", "html/dep_au/$dep_file.html";
 914 }
 915
 916 print $dep_fh html_end;
 917 close($dep_fh);
 918 rename "html/dep_au/index.new", "html/dep_au/index.html";
 919
 920 unlink $pid_file;
 921