Swift Requires Chilkat v11.7.0+

Extract Text from a Two-Column PDF

See more PDF Text Extraction Examples

Demonstrates how multi-column pages are read. By default the columns are detected and each column is read top to bottom before the next ("columns": "auto"); "columns": "none" reads the full page width line by line, which interleaves the columns. The quality report tells how many columns were found. 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 two-column PDF used in this example is available at two_column_article.pdf

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

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

    //  With the default options the columns are detected, and the text of the left column
    //  comes before the text of the right column.
    success = pdf.extractText(op: "text", jsonIn: json, jsonOut: jsonOut)
    if success == false {
        print("\(pdf.lastErrorText!)")
        return
    }

    print("Columns detected: \(jsonOut.int(of: "quality.pages[0].columns").intValue)")
    print("Reading order: \(jsonOut.string(of: "quality.pages[0].readingOrderSource")!)")
    print("\(jsonOut.string(of: "text")!)")

    //  "none" switches column detection off: the page is read across its full width, line by line,
    //  so each output line holds a line of the left column followed by a line of the right column.
    //  This is rarely wanted, but it shows what the detection does.
    json.updateString(jsonPath: "columns", value: "none")
    json.updateString(jsonPath: "layout", value: "lines")
    success = pdf.extractText(op: "text", jsonIn: json, jsonOut: jsonOut)
    if success == false {
        print("\(pdf.lastErrorText!)")
        return
    }

    print("---- columns: none ----")
    print("\(jsonOut.string(of: "text")!)")

    //  Sample output (abbreviated):

    //  Columns detected: 2
    //  Reading order: visual
    //  The Harbor Lighthouse, Season Two
    //  
    //  The harbor lighthouse was built in 1874 to mark the entrance to the inner channel. It operated continuously until 1968, ...
    //  
    //  The restoration society took ownership in 2021 with three goals: ...
    //  ...
    //  The lantern room frame was stripped, primed and repainted in the original dark green. ...
    //  ...
    //  ---- columns: none ----
    //  The Harbor Lighthouse, Season Two
    //  The harbor lighthouse was built in 1874 to The lantern room frame was stripped, primed
    //  mark the entrance to the inner channel. It and repainted in the original dark green. New
    //  ...

}