Perl Requires Chilkat v11.7.0+

Remove PDF Objects Nothing Refers To

See more PDF Optimization Examples

Demonstrates removeUnreferenced. When a page, an image or a whole section is replaced in an editor, the objects it used often stay in the file with nothing pointing at them any more. They are not old revisions -- they are in the current revision, simply unreachable -- so only a reachability walk from the document catalog finds them. In a publication assembled over several editing passes this is frequently the largest single saving. Perl

use chilkat();

$success = 0;

#  This example requires the Chilkat API to have been previously unlocked.
#  See Global Unlock Sample for sample code.

#  The PDF used in this example is available at watersense_accomplishments.pdf

$pdf = chilkat::CkPdf->new();
$success = $pdf->LoadFile("qa_data/pdf/watersense_accomplishments.pdf");
if ($success == 0) {
    print $pdf->lastErrorText() . "\r\n";
    exit;
}

$json = chilkat::CkJsonObject->new();
$jsonOut = chilkat::CkJsonObject->new();
$success = $pdf->Optimize("audit",$json,$jsonOut);
if ($success == 0) {
    print $pdf->lastErrorText() . "\r\n";
    exit;
}

print "fileSize: " . $jsonOut->IntOf("fileSize") . "\r\n";
print "removeUnreferenced would save: " . $jsonOut->IntOf("estimatedSavings.removeUnreferenced") . "\r\n";

#  Optimize with the defaults and see how many objects were actually dropped.
$success = $pdf->Optimize("optimize",$json,$jsonOut);
if ($success == 0) {
    print $pdf->lastErrorText() . "\r\n";
    exit;
}

$success = $pdf->WriteFile("qa_output/watersense_optimized.pdf");
if ($success == 0) {
    print $pdf->lastErrorText() . "\r\n";
    exit;
}

print "objects removed: " . $jsonOut->IntOf("actions.removeUnreferenced.count") . "\r\n";
print "bytes saved:     " . $jsonOut->IntOf("actions.removeUnreferenced.bytesSaved") . "\r\n";

#  Nothing a page needs is ever removed: the walk starts at the document catalog and follows every
#  reference, including the ones in annotations, the structure tree, named destinations and the
#  optional-content configuration.
print "pages after: " . $pdf->get_NumPages() . "\r\n";