PowerBuilder 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. PowerBuilder

integer li_rc
long li_Success
oleobject loo_Pdf
oleobject loo_Json
oleobject loo_JsonOut
long i
long li_Count_i

li_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

loo_Pdf = create oleobject
li_rc = loo_Pdf.ConnectToNewObject("Chilkat.Pdf")
if li_rc < 0 then
    destroy loo_Pdf
    MessageBox("Error","Connecting to COM object failed")
    return
end if
li_Success = loo_Pdf.LoadFile("qa_data/pdf/hidden_text.pdf")
if li_Success = 0 then
    Write-Debug loo_Pdf.LastErrorText
    destroy loo_Pdf
    return
end if

loo_Json = create oleobject
li_rc = loo_Json.ConnectToNewObject("Chilkat.JsonObject")

loo_JsonOut = create oleobject
li_rc = loo_JsonOut.ConnectToNewObject("Chilkat.JsonObject")

//  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.
li_Success = loo_Pdf.ExtractText("text",loo_Json,loo_JsonOut)
if li_Success = 0 then
    Write-Debug loo_Pdf.LastErrorText
    destroy loo_Pdf
    destroy loo_Json
    destroy loo_JsonOut
    return
end if

Write-Debug "---- default ----"
Write-Debug loo_JsonOut.StringOf("text")

//  The quality report says what was left out.
i = 0
li_Count_i = loo_JsonOut.SizeOfArray("quality.pages[0].issues")
do while i < li_Count_i
    loo_JsonOut.I = i
    Write-Debug "issue: " + loo_JsonOut.StringOf("quality.pages[0].issues[i].code")
    i = i + 1
loop

//  Include everything.
loo_Json.UpdateString("clippedText","include")
loo_Json.UpdateString("offPageText","include")
loo_Json.UpdateString("obscuredText","include")
li_Success = loo_Pdf.ExtractText("text",loo_Json,loo_JsonOut)
if li_Success = 0 then
    Write-Debug loo_Pdf.LastErrorText
    destroy loo_Pdf
    destroy loo_Json
    destroy loo_JsonOut
    return
end if

Write-Debug "---- clippedText, offPageText, obscuredText: include ----"
Write-Debug loo_JsonOut.StringOf("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.


destroy loo_Pdf
destroy loo_Json
destroy loo_JsonOut