Swift 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. Swift

func chilkatTest() {
    var success: Bool = 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 hidden_text.pdf

    let pdf = CkoPdf()!
    success = pdf.loadFile(filePath: "qa_data/pdf/hidden_text.pdf")
    if success == false {
        print("\(pdf.lastErrorText!)")
        return
    }

    let json = CkoJsonObject()!
    let jsonOut = CkoJsonObject()!

    //  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.
    success = pdf.extractText(op: "text", jsonIn: json, jsonOut: jsonOut)
    if success == false {
        print("\(pdf.lastErrorText!)")
        return
    }

    print("---- default ----")
    print("\(jsonOut.string(of: "text")!)")

    //  The quality report says what was left out.
    var i: Int = 0
    var count_i: Int = jsonOut.size(ofArray: "quality.pages[0].issues").intValue
    while i < count_i {
        jsonOut.i = i
        print("issue: \(jsonOut.string(of: "quality.pages[0].issues[i].code")!)")
        i = i + 1
    }

    //  Include everything.
    json.updateString(jsonPath: "clippedText", value: "include")
    json.updateString(jsonPath: "offPageText", value: "include")
    json.updateString(jsonPath: "obscuredText", value: "include")
    success = pdf.extractText(op: "text", jsonIn: json, jsonOut: jsonOut)
    if success == false {
        print("\(pdf.lastErrorText!)")
        return
    }

    print("---- clippedText, offPageText, obscuredText: include ----")
    print("\(jsonOut.string(of: "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.

}