Tcl Requires Chilkat v11.7.0+

Clipped, Off-Page and White-on-White Text in PDF Extraction

See more PDF Text Extraction Examples

Demonstrates the "clippedText", "offPageText" and "obscuredText" filters. Text that a reader never sees - hidden by a clipping path, outside the crop box, or drawn in the same color as the box beneath it - is excluded by default, and the quality report notes what was skipped. Each kind can be included. Tcl

load ./chilkat.dll

set 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 hidden_text.pdf

set pdf [new_CkPdf]

set success [CkPdf_LoadFile $pdf "qa_data/pdf/hidden_text.pdf"]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    exit
}

set json [new_CkJsonObject]

set jsonOut [new_CkJsonObject]

#  The page has a visible paragraph plus three hidden lines: one drawn outside its clipping
#  rectangle, one below the crop box, and one in white on a white box.
set success [CkPdf_ExtractText $pdf "text" $json $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

puts "---- default ----"
puts [CkJsonObject_stringOf $jsonOut text]

#  The quality report says what was left out.
set i 0
set count_i [CkJsonObject_SizeOfArray $jsonOut "quality.pages[0].issues"]
while {$i < $count_i} {
    CkJsonObject_put_I $jsonOut $i
    puts "issue: [CkJsonObject_stringOf $jsonOut {quality.pages[0].issues[i].code}]"
    set i [expr $i + 1]
}

#  Include everything.
CkJsonObject_UpdateString $json "clippedText" "include"
CkJsonObject_UpdateString $json "offPageText" "include"
CkJsonObject_UpdateString $json "obscuredText" "include"
set success [CkPdf_ExtractText $pdf "text" $json $jsonOut]
if {$success == 0} then {
    puts [CkPdf_lastErrorText $pdf]
    delete_CkPdf $pdf
    delete_CkJsonObject $json
    delete_CkJsonObject $jsonOut
    exit
}

puts "---- clippedText, offPageText, obscuredText: include ----"
puts [CkJsonObject_stringOf $jsonOut text]

#  Sample output:

#  ---- default ----
#  Visible Text
#  
#  This paragraph is visible. The page also carries three kinds of text a reader never sees.
#  
#  End of the visible text.
#  issue: obscuredTextSkipped
#  issue: clippedTextSkipped
#  ---- clippedText, offPageText, obscuredText: include ----
#  Visible Text
#  
#  This paragraph is visible. The page also carries three kinds of text a reader never sees.
#  
#  CLIPPED: this line is drawn outside its clipping rectangle.
#  
#  OBSCURED: this line is white on a white box.
#  
#  End of the visible text.
#  
#  OFFPAGE: this line sits below the crop box.

delete_CkPdf $pdf
delete_CkJsonObject $json
delete_CkJsonObject $jsonOut