Swift Requires Chilkat v11.7.0+

Rejoin Words Hyphenated at Line Ends

See more PDF Text Extraction Examples

Demonstrates the "dehyphenate" clean-up option (true by default). A word broken at the end of a line ("docu-" / "ment") is rejoined, while a hyphen that belongs to the word ("self-service") is kept. Set the option to false to keep the lines exactly as printed. 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 hyphenated.pdf

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

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

    //  The paragraph breaks "document", "self-service", "underlying" and "re-issued" at line ends.
    //  The default rejoins them.  "self-service" keeps its hyphen because the word appears with it,
    //  unbroken, elsewhere on the page; "re-issued" appears nowhere else, so it becomes "reissued".
    success = pdf.extractText(op: "text", jsonIn: json, jsonOut: jsonOut)
    if success == false {
        print("\(pdf.lastErrorText!)")
        return
    }

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

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

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

    //  Sample output:

    //  ---- default (dehyphenate: true) ----
    //  Self-Service Kiosk Notes
    //  
    //  The new self-service kiosk in the lobby prints a visitor badge from the document number on the reservation. Staff should direct first-time visitors to the self-service kiosk rather than the desk, and should keep the paper tray topped up. The underlying software restarts itself overnight; a badge that fails to print is reissued at the desk on request.
    //  ---- dehyphenate: false ----
    //  Self-Service Kiosk Notes
    //  
    //  The new self-service kiosk in the lobby prints a visitor badge from the docu- ment number on the reservation. Staff should direct first-time visitors to the self- service kiosk rather than the desk, and should keep the paper tray topped up. The under- lying software restarts itself overnight; a badge that fails to print is re- issued at the desk on request.

}