Swift Requires Chilkat v11.7.0+

Search a PDF with a Regular Expression

See more PDF Text Extraction Examples

Demonstrates searching a PDF with a regular expression (regex: true), limiting the number of results (maxResults), and matching whole words only (wholeWord). 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 order_records.pdf

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

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

    //  Find every order number.  With regex set to true, the query is a regular expression.
    json.updateString(jsonPath: "query", value: "ORD-[0-9]{4}-[0-9]{4}")
    json.updateBool(jsonPath: "regex", value: true)
    //  We only want the matched text, so no context is needed.
    json.updateInt(jsonPath: "context", value: 0)

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

    print("Order numbers found: \(jsonOut.int(of: "count").intValue)")
    var i: Int = 0
    var count_i: Int = jsonOut.size(ofArray: "matches").intValue
    while i < count_i {
        jsonOut.i = i
        print("\(jsonOut.string(of: "matches[i].text")!)")
        i = i + 1
    }

    //  Find the e-mail addresses, but stop after the first three.
    json.updateString(jsonPath: "query", value: "[a-z0-9._]+@[a-z]+[.][a-z]+")
    json.updateInt(jsonPath: "maxResults", value: 3)
    success = pdf.extractText(op: "search", jsonIn: json, jsonOut: jsonOut)
    if success == false {
        print("\(pdf.lastErrorText!)")
        return
    }

    print("First three e-mail addresses:")
    i = 0
    count_i = jsonOut.size(ofArray: "matches").intValue
    while i < count_i {
        jsonOut.i = i
        print("\(jsonOut.string(of: "matches[i].text")!)")
        i = i + 1
    }

    //  wholeWord: true matches only whole words.  The word "cat" appears once in the PDF,
    //  but it is also inside "catalog" and "category".
    json.delete(name: "maxResults")
    json.updateBool(jsonPath: "regex", value: false)
    json.updateString(jsonPath: "query", value: "cat")
    success = pdf.extractText(op: "search", jsonIn: json, jsonOut: jsonOut)
    if success == false {
        print("\(pdf.lastErrorText!)")
        return
    }

    print("Occurrences of cat (any): \(jsonOut.int(of: "count").intValue)")

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

    print("Occurrences of cat (whole word): \(jsonOut.int(of: "count").intValue)")

    //  Sample output:

    //  Order numbers found: 9
    //  ORD-2026-0301
    //  ORD-2026-0302
    //  ORD-2026-0303
    //  ORD-2026-0304
    //  ORD-2026-0305
    //  ORD-2026-0306
    //  ORD-2026-0307
    //  ORD-2026-0308
    //  ORD-2026-0307
    //  First three e-mail addresses:
    //  alice.moore@example.com
    //  bkumar@example.org
    //  carla@example.net
    //  Occurrences of cat (any): 3
    //  Occurrences of cat (whole word): 1

}