Changeset 7018

Timestamp:

2004-03-11T12:25:02+13:00 (20 years ago)

Author:

jrm21

Message:

oops... fixed up unicode-byte marker removal for first line.

File:

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

trunk/gsdl/bin/script/pdftohtml.pl

@@ -147 +147 @@
     my $line;
     my $seen_textual_content=$allow_no_text;
-    while ($line=<INFILE>) {
+    # check for unicode byte-order marker at the start of the file
+    $line = <INFILE>;
+    $line =~ s#\376\377##g;
+    while ($line) {
     $line =~ s#</b><b>##g;
     $line =~ s#</i><i>##g;
     $line =~ s#\\#\\\\#g; # until macro language parsing is fixed...
-    $line =~ s#\376\377##g;
 # check for any extracted text
     if ($seen_textual_content == 0) {
@@ -186 +188 @@
 
     print OUTFILE $line;
+    $line = <INFILE>;
     }
     close INFILE;