Changeset 7120 for trunk/gsdl

Timestamp:

2004-03-25T16:45:10+12:00 (20 years ago)

Author:

jrm21

Message:

remove the title added by pdftohtml if the title is merely the filename.
This way HTMLPlug will give it a more meaningful title based on the first
sentence.

File:

• trunk/gsdl/bin/script/pdftohtml.pl (modified) (2 diffs)

trunk/gsdl/bin/script/pdftohtml.pl

@@ -163 +163 @@
         $seen_textual_content=1;
         }
+        # special - added to remove the filename from the title
+        # this should be in the header, before we see "textual content"
+        if ($line =~ m@<title>(.*?)</title>@) {
+        my $title=$1;
+        # is this title the name of a filename?
+        if (-r "$title.pdf" || -r "$title.html") {
+            # remove the title
+            $line =~ s@<title>.*?</title>@<title></title>@;
+        }
+        }
     }
 
@@ -199 +209 @@
     my $directory=$output_filestem;
     $directory =~ s@[^\/]*$@@;    # assume filename has no embedded slashes...
-
+    # newer versions of pdftohtml don't seem to do images this way anymore?
     if (open (IMAGES, "${directory}images.log") || 
     open (IMAGES, "${directory}image.log")) {