silent make

category_def.yaml

@@ -7,12 +7,15 @@ geo:
   detail:
     subject:
       title:
-        en: Subject archives folders
-        de: Sacharchiv Mappen
+        en: Subject archives
+        de: Sacharchiv
     ware:
       title:
-        en: Commodities/wares archives folders
-        de: Warenarchiv Mappen
+        en: Commodities/wares archives
+        de: Warenarchiv
+      ordered_by:
+        en: by wares
+        de: nach Waren
 subject:
   prov: hwwa
   title:
@@ -22,8 +25,11 @@ subject:
   detail:
     geo:
       title:
-        en: Countries-subject archives folders
-        de: Länder-Sacharchiv Mappen
+        en: Countries-subject archives
+        de: Länder-Sacharchiv
+      ordered_by:
+        en: by countries
+        de: nach Ländern
 ware:
   prov: hwwa
   title:
@@ -33,5 +39,5 @@ ware:
   detail:
     geo:
       title:
-        en: Commodities/wares archives folders
-        de: Warenarchiv Mappen
+        en: Commodities/wares archives
+        de: Warenarchiv

count_film_images.pl

@@ -8,7 +8,8 @@
 
 use strict;
 use warnings;
-use utf8;
+use autodie;
+use utf8::all;
 
 use Data::Dumper;
 ##use Data::Dumper::Names;
@@ -49,7 +50,8 @@
     # findbuch input
     my $findbuch_file =
       $filmdata_root->child( $set . '_' . $collection . '.json' );
-    my $findbuch_data = from_json( $findbuch_file->slurp ) || die "not found";
+    my $findbuch_data = decode_json( $findbuch_file->slurp_raw )
+      || die "not found";
 
     my $last_film_id = 0;
     foreach my $entry ( @{$findbuch_data} ) {

create_category_pages.pl

@@ -13,9 +13,8 @@
 
 use strict;
 use warnings;
-use utf8;
-
-use lib './lib';
+use autodie;
+use utf8::all;
 
 use Carp;
 use Data::Dumper;
@@ -30,8 +29,6 @@
 use ZBW::PM20x::Folder;
 use ZBW::PM20x::Vocab;
 
-binmode( STDOUT, ":encoding(UTF-8)" );
-
 ##Readonly my $WEB_ROOT        => path('/tmp/category');
 Readonly my $WEB_ROOT        => path('../web/category');
 Readonly my $KLASSDATA_ROOT  => path('../data/klassdata');
@@ -162,8 +159,11 @@
 
         my %filmsections;
         foreach my $filming (qw/ 1 2/) {
-          $filmsections{$filming} =
-            [ $master_voc->filmsectionlist( $category_id, $filming ) ];
+          $filmsections{$filming} = [
+            $master_voc->filmsectionlist(
+              $category_id, $filming, $detail_type
+            )
+          ];
         }
 
         my $folder_count =
@@ -184,7 +184,8 @@
               $category_type eq 'ware'
             ? $firstletter
             : $master_voc->subheading( $lang, $firstletter );
-          push( @lines, '', "### $subhead <a name='id_$firstletter'></a>", '' );
+          push( @lines, '', "#### $subhead <a name='id_$firstletter'></a>",
+            '' );
           push( @tabs, { startchar => $firstletter } );
           $firstletter_old = $firstletter;
         }
@@ -317,6 +318,19 @@
 #
 ###########################
 
+# data structure %category_data:
+
+#   category_type
+#     category_id       # defines page
+#       detail_type
+#         folder
+#           lines
+#             de|en
+#         filming_loop
+#           de|en
+#             filming
+#               filmsection_loop
+
 my %category_data;
 
 print "\nCollect data for folders\n";
@@ -460,7 +474,7 @@
           # prepend subheading
           my $subheading =
             $detail_voc->subheading( $lang, $firstletter ) || $firstletter;
-          $text .= "\n\n### $subheading\n\n";
+          $text .= "\n\n#### $subheading\n\n";
 
           # all text line for this subheading
           $text .= join( "\n", @{ $lines_ref->{$firstletter} } );
@@ -479,12 +493,13 @@
 
 print "\n\nCollect data for film sections\n";
 
-# only top level for the country-subject and ware archives
-foreach my $category_type (qw/ geo ware /) {
+# now for all top level pages
+foreach my $category_type (qw/ geo subject ware /) {
   print "\nfilm sections category_type: $category_type\n";
 
   # master vocabulary reference
   $master_voc = ZBW::PM20x::Vocab->new($category_type);
+  my $master_type = $master_voc->vocab_name;
 
   foreach my $lang (@LANGUAGES) {
     print "  lang: $lang\n";
@@ -493,9 +508,9 @@
     my @detail_types =
       sort keys %{ $definitions_ref->{$category_type}{detail} };
     foreach my $detail_type (@detail_types) {
-      next if $category_type eq 'geo' and $detail_type eq 'ware';
 
       print "    detail_type: $detail_type\n";
+      my $detail_voc = ZBW::PM20x::Vocab->new($detail_type);
       my $def_ref = $definitions_ref->{$category_type}->{detail}{$detail_type};
       my $detail_title = $def_ref->{title}{$lang};
 
@@ -507,57 +522,102 @@
         foreach my $filming (qw/ 1 2 /) {
           my $filming_ref = $filming_def_ref->{$filming};
 
+          # filmsections for the master / detail combination (works in either
+          # normal or inversed hierarchical order)
           my @filmsectionlist =
-            $master_voc->filmsectionlist( $category_id, $filming );
+            $master_voc->filmsectionlist( $category_id, $filming,
+            $detail_type );
 
-          # how to deal deal wth mission information depends ...
+          # how to deal deal with missing information depends ...
           if ( not scalar(@filmsectionlist) > 0 ) {
             if (  $filming eq '1'
               and $category_data{$category_type}{$category_id}{$detail_type}
               {folder}{complete} )
             {
               ## is ok
             } else {
+              ## in which cases should a warning be issued?
               ## warn "no film data for $category_id in filming $filming\n";
             }
             next;
           }
 
           my @filmsection_loop;
           foreach my $section (@filmsectionlist) {
-            ## TODO is this correct? includes position and R/L!
-            my $film_id = substr( $section->{'@id'}, 25 );
-            my $entry   = {
+            my $section_id = substr( $section->{'@id'}, 25 );
+
+            my $section_label =
+              $section->label( $lang, $detail_voc ) || $section->{title};
+
+            my $entry = {
               "is_$lang"     => 1,
               filmviewer_url => $section->{'@id'},
-              film_id        => $film_id,
-              first_img      => $section->{title},
+              section_id     => $section_id,
+              section_label  => $section_label,
+              image_count    => $section->img_count,
             };
+            if ( $section->is_filmstartonly ) {
+              $entry->{is_filmstartonly} = 1;
+            }
             push( @filmsection_loop, $entry );
           }
 
+          # sort ware entries alphabetically
+          if ( $detail_type eq 'ware' ) {
+            my $uc = Unicode::Collate->new();
+            @filmsection_loop =
+              sort { $uc->cmp( $a->{'section_label'}, $b->{'section_label'} ) }
+              @filmsection_loop;
+          }
+
           my %filming_data = (
             "is_$lang"             => 1,
+            detail_title           => $detail_title,
             filming_title          => $filming_ref->{title}{$lang},
             legal                  => $filming_ref->{legal}{$lang},
             filmsection_loop       => \@filmsection_loop,
             total_number_of_images =>
               $master_voc->film_img_count( $category_id, $filming ),
           );
 
+          # remove image count for ware section on geo pages
+          # or geo sections on subject pages
+          if ( ( $master_type eq 'geo' and $detail_type eq 'ware' )
+            or ( $master_type eq 'subject' and $detail_type eq 'geo' ) )
+          {
+            delete $filming_data{total_number_of_images};
+          }
+
           push( @filmings, \%filming_data );
         }    # $filming
 
         if ( scalar(@filmings) ) {
           $category_data{$category_type}{$category_id}{$detail_type}
             {filming_loop}{$lang} = \@filmings;
-        }
+
+          # add data for special text about secondary categories
+          if ( ( $master_type eq 'geo' and $detail_type eq 'ware' )
+            or ( $master_type eq 'subject' and $detail_type eq 'geo' ) )
+          {
+            my $collection = $detail_type eq 'ware' ? 'wa' : 'sh';
+            my %suppl      = (
+              label        => $master_voc->label( $lang, $category_id ),
+              detail_title => $detail_title,
+              ordered_by   => $def_ref->{ordered_by}{$lang},
+              filmlist1    => "/film/h1_$collection.de.html",
+              filmlist2    => "/film/h2_$collection.de.html",
+            );
+            $category_data{$category_type}{$category_id}{$detail_type}
+              {secondary_category}{$lang} = \%suppl;
+          }    # secondary_category
+        }    # scalar(@filmings)
       }    # $category_id
     }    # $detail_type
   }    # $lang
 }
 
 ###print "\n## size inc. film: ", total_size(\%category_data) / (1024*1024), "\n";
+###path('/tmp/category.dat')->spew(Dumper \%category_data); exit;
 
 print "\n\nOutput of individual category pages\n\n";
 
@@ -593,8 +653,19 @@
         if ( defined $filming_loop_ref ) {
           $data{filming_loop} = $filming_loop_ref;
         }
-        push( @detail_data, \%data );
 
+        # supplemental data for secondary category
+        ## TODO fix ugly construct
+        if ( defined $category_ref->{$detail_type}{secondary_category} ) {
+          $data{is_secondary_category} = 1;
+          foreach
+            my $key (qw[ label ordered_by detail_title filmlist1 filmlist2 ])
+          {
+            $data{$key} =
+              $category_ref->{$detail_type}{secondary_category}{$lang}{$key};
+          }
+        }
+        push( @detail_data, \%data );
       }    # $detail_type
 
       # actual output
@@ -617,6 +688,7 @@ sub output_category_page {
     $PROV{ $definitions_ref->{$category_type}{prov} }{name}{$lang};
   my $signature = $master_voc->signature($id);
   my $label     = $master_voc->label( $lang, $id );
+  $label =~ s/"/\\"/g;
   my $backlinktitle =
     $lang eq 'en'
     ? 'Category Overview'

create_euipo.pl

@@ -7,7 +7,8 @@
 
 use strict;
 use warnings;
-use utf8;
+use autodie;
+use utf8::all;
 
 use Data::Dumper;
 use JSON;

create_filmlists.pl

@@ -5,7 +5,8 @@
 
 use strict;
 use warnings;
-use utf8;
+use autodie;
+use utf8::all;
 
 use Data::Dumper;
 use JSON;
@@ -17,7 +18,7 @@
 my $filmdata_root = path('../data/filmdata');
 my $img_file      = $filmdata_root->child('img_count.json');
 my $ip_hints =
-  path('../web/templates/fragments/ip_hints.de.md.frag')->slurp_utf8;
+  path('../web/templates/fragments/ip_hints.de.md.frag')->slurp;
 
 my %page = (
   h => {
@@ -72,7 +73,7 @@
 );
 
 # TEMPORARY: remove path
-my $img_count = decode_json( $img_file->slurp );
+my $img_count = decode_json( $img_file->slurp_raw );
 my %img_cnt;
 foreach my $key ( keys %{$img_count} ) {
   my $shortkey = substr( $key, 18 );
@@ -90,7 +91,7 @@
     my $zotero_file = $filmdata_root->child("zotero.$page_name.json");
     my %zotero_film;
     if ( -f $zotero_file ) {
-      %zotero_film = %{ decode_json( $zotero_file->slurp ) };
+      %zotero_film = %{ decode_json( $zotero_file->slurp_raw ) };
     }
 
     # some header information for the page
@@ -119,7 +120,7 @@
       $filmfile = $filmdata_root->child( $page_name . '.json' );
     }
     my @film_sections =
-      @{ decode_json( $filmfile->slurp ) };
+      @{ decode_json( $filmfile->slurp_raw ) };
 
     # iterate through the list of film sections (from the excel file)
     foreach my $film_section (@film_sections) {

create_filmviewer_links.pl

@@ -8,9 +8,8 @@
 
 use strict;
 use warnings;
-use utf8;
-
-use lib './lib';
+use autodie;
+use utf8::all;
 
 use Data::Dumper;
 use JSON;

create_folder_list.pl

@@ -9,9 +9,8 @@
 
 use strict;
 use warnings;
-use utf8;
-
-use lib './lib';
+use autodie;
+use utf8::all;
 
 use Data::Dumper;
 use HTML::Template;
@@ -22,7 +21,6 @@
 use YAML;
 use ZBW::PM20x::Folder;
 
-binmode( STDOUT, ":utf8" );
 $Data::Dumper::Sortkeys = 1;
 
 Readonly my $FOLDER_DATA    => path('/pm20/data/rdf/pm20.extended.jsonld');
@@ -268,7 +266,7 @@ sub load_ids {
   my $coll_id_ref = shift or die "param missing";
 
   # create a list of numerical keys for each collection
-  my $data = decode_json( $FOLDER_DATA->slurp );
+  my $data = decode_json( $FOLDER_DATA->slurp_raw );
   foreach my $entry ( @{ $data->{'@graph'} } ) {
     $entry->{identifier} =~ m/^(co|pe|sh|wa)\/(\d{6}(?:,\d{6})?)$/;
     push( @{ $coll_id_ref->{$1} }, $2 );