C# 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. C#

bool success = 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

Chilkat.Pdf pdf = new Chilkat.Pdf();
success = pdf.LoadFile("qa_data/pdf/hyphenated.pdf");
if (success == false) {
    Debug.WriteLine(pdf.LastErrorText);
    return;
}

Chilkat.JsonObject json = new Chilkat.JsonObject();
Chilkat.JsonObject jsonOut = new Chilkat.JsonObject();

//  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("text",json,jsonOut);
if (success == false) {
    Debug.WriteLine(pdf.LastErrorText);
    return;
}

Debug.WriteLine("---- default (dehyphenate: true) ----");
Debug.WriteLine(jsonOut.StringOf("text"));

json.UpdateBool("dehyphenate",false);
success = pdf.ExtractText("text",json,jsonOut);
if (success == false) {
    Debug.WriteLine(pdf.LastErrorText);
    return;
}

Debug.WriteLine("---- dehyphenate: false ----");
Debug.WriteLine(jsonOut.StringOf("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.