Changeset 3614

Timestamp:

2002-12-03T14:41:17+13:00 (21 years ago)

Author:

jrm21

Message:

modified section-handling stuff to work with output from v.0.34 of pdftohtml.

File:

• trunk/gsdl/perllib/plugins/PDFPlug.pm (modified) (2 diffs)

trunk/gsdl/perllib/plugins/PDFPlug.pm

@@ -118 +118 @@
     my $textref=$_[0];
 
-    # This might be specific to the version of pdftohtml in <=  gsdl-2.38
-    my @sections = split('<a name=\d+>', $$textref);
+    # we have "<a name=1></a>" etc for each page
+    my @sections = split('<a name=', $$textref);
 
     shift @sections; # don't need HTML header, etc
@@ -141 +141 @@
     # add metadata per section...
     foreach my $section (@sections) {
-        $section =~ m@^<b>Page (\d+)</b>@;
+        $section =~ s@^(\d+)></a>@@; # leftover from split expression...
+
         $title = $1; # Greenstone does magic if sections are titled digits
         if (! defined($title) ) {