Here's what I have now. I borrowed
hdump from the examples directory of HTML::Parser. Then I used
CAM::PDF::GS to make a gs log file.
#!/usr/bin/perl
use strict;
use warnings;
use CAM::PDF;
use Data::Dumper::Concise;
use base qw(CAM::PDF::GS::NoText);
my $file = shift @ARGV;
my $log = '/root/Desktop/gs.log';
binmode STDOUT, ":encoding(utf8)";
open STDOUT, '>', $log;
my $pdf = CAM::PDF->new($file);
my $contentTree = $pdf->getPageContentTree(5);
my $gs = $contentTree->computeGS;
print Dumper($gs):
close STDOUT;
From the cmdline do
perl gscript.pl /path/to/pdf
Then I used hdump to examine gs.log:
#!/usr/bin/perl -w
use strict;
use HTML::TokeParser;
use Data::Dumper::Concise;
$| = 1;
sub h {
my ( $event, $line, $column, $text, $tagname, $attr ) = @_;
my (@d) = uc( substr( $event, 0, 1 ) ) . " L$line C$column";
substr( $text, 40 ) = "..." if length $text > 40;
push @d, $text;
push @d, $tagname if defined $tagname;
push @d, $attr if $attr;
print Dumper(@d);
}
my $p = HTML::Parser->new( api_version => 3 );
$p->handler( default => \&h, "event, line, column, text, tagname, attr
+" );
$p->parse_file( @ARGV ? shift : *STDIN );
From the cmdline:
perl hdump /path/to/gs.log
I hope that it's useful for you.
|