B4X 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. B4X

Dim success As Boolean = False

'  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

Dim pdf As ChilkatPdf
pdf.Initialize("pdf")
success = pdf.LoadFile("qa_data/pdf/watersense_accomplishments.pdf")
If success = False Then
    Log(pdf.LastErrorText)
    Return
End If


Dim json As ChilkatJsonObject
json.Initialize
Dim jsonOut As ChilkatJsonObject
jsonOut.Initialize
success = pdf.Optimize("audit", json, jsonOut)
If success = False Then
    Log(pdf.LastErrorText)
    Return
End If


Log("fileSize: " & jsonOut.IntOf("fileSize"))
Log("removeUnreferenced would save: " & jsonOut.IntOf("estimatedSavings.removeUnreferenced"))

'  Optimize with the defaults and see how many objects were actually dropped.
success = pdf.Optimize("optimize", json, jsonOut)
If success = False Then
    Log(pdf.LastErrorText)
    Return
End If


success = pdf.WriteFile("qa_output/watersense_optimized.pdf")
If success = False Then
    Log(pdf.LastErrorText)
    Return
End If


Log("objects removed: " & jsonOut.IntOf("actions.removeUnreferenced.count"))
Log("bytes saved:     " & jsonOut.IntOf("actions.removeUnreferenced.bytesSaved"))

'  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.
Log("pages after: " & pdf.NumPages)