Changeset 36057 for main

Timestamp:

2022-02-14T14:31:15+13:00 (2 years ago)

Author:

kjdon

Message:

in the whakatohea project, converting the pdfs to paged_pretty_html resulted in unclosed divs in the sections. This is because the <div page=1> was outside the <h2> or <h3> headings. Put these <h> headings on the outside of divs to keep the resulting doc.xml nicer.

File:

• main/trunk/greenstone2/perllib/plugins/PDFv2Plugin.pm (modified) (3 diffs)

main/trunk/greenstone2/perllib/plugins/PDFv2Plugin.pm

@@ -581 +581 @@
     # If number of remaining pages >= 10, then create new bucket heading
     # e.g. "Pages 30-40"
+        my $header_text = ""; #we want the <h2/3> tags to come outside the <div page=1> tag, otherwise we end up with unclosed divs in
+        # some sections
     if(($page_num % 10) == 1 && ($num_html_pages > 10)) {
         # Double-digit page numbers that start with 2
@@ -586 +588 @@
         my $start_range = $page_num - ($page_num % 10) + 1;
         my $end_range = $page_num + 10 - ($page_num % 10);
-        $page_div .= "<h2 style=\"font-size:1em;font-weight:normal;\">Pages ".$start_range . "-" . $end_range."</h2>\n";
+        #$page_div .= "<h2 style=\"font-size:1em;font-weight:normal;\">Pages ".$start_range . "-" . $end_range."</h2>\n";
+            $header_text = "<h2 style=\"font-size:1em;font-weight:normal;\">Pages ".$start_range . "-" . $end_range."</h2>\n";
     }
 
@@ -592 +595 @@
     # Whether we're starting a new bucket or not, add a simpler heading: just the pagenumber, "Page #"
     # However, this should be <H3> when there are buckets and <H2> when there aren't any.
+        my $hx="h2";
     if($num_html_pages > 10) {
-        $page_div .= "<h3 style=\"font-size:1em;font-weight:normal;\">Page ".$page_num."</h3>\n";       
-    } else { # PDF has less than 10 pages in total
-        $page_div .= "<h2 style=\"font-size:1em;font-weight:normal;\">Page ".$page_num."</h2>\n";       
-    }
+            $hx = "h3";
+        }
+        #$page_div .= "<$hx style=\"font-size:1em;font-weight:normal;\">Page ".$page_num."</$hx>\n";        
+        $header_text .= "<$hx style=\"font-size:1em;font-weight:normal;\">Page ".$page_num."</$hx>\n";
+        $page_div = $header_text . $page_div;
     }