#! /usr/bin/perl -w
use strict;
use File::Find;
use Data::Dumper;
use PDF;
use PDF::Parse;
my %conferences = ();
my $start_dir = "/gruvi/Data/Proceedings";
sub find_pdfs
{
# simple, yet shoud be effective
if(/\.pdf$/) {
# NOTE: this seems to ignore "top-level" PDFs
# That's not a bug, it's a feature!
my ($conference) = ($File::Find::dir =~ m!$start_dir/(\w+?)/!);
$conference ||= "Top-level";
push @{$conferences{$conference}}, "$File::Find::dir/$_";
return 1;
}
return 0;
}
&File::Find::find(\&find_pdfs, $start_dir);
for (sort keys %conferences) {
&write_conference_page($_, "$_.html", $conferences{$_});
}
sub write_conference_page
{
my ($conference, $outfile, $pdfs) = @_;
open PROCS, '>', "./$outfile"
or die "Cannot open $outfile: $!\n";
# we're going to callously ignore proper HTML for the present
print PROCS "\n\n";
# we're also going to callously ignore proper Perl HTML-gen style
# for the moment
print PROCS "$conference
\n";
print PROCS "\n";
for (@$pdfs) {
my $pdf = PDF->new($_);
$pdf->TargetFile($_);
my $title = $pdf->GetInfo("Title");
my $authors = $pdf->GetInfo("Author");
print PROCS "\t- $authors:
";
print PROCS "$title \n";
}
print PROCS "
\n
\n\n";
print PROCS "\n\n";
close PROCS
or die "Cannot close $outfile: $!\n";
}