Go 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). Go

    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 order_records.pdf

    pdf := chilkat.NewPdf()
    success = pdf.LoadFile("qa_data/pdf/order_records.pdf")
    if success == false {
        fmt.Println(pdf.LastErrorText())
        pdf.DisposePdf()
        return
    }

    json := chilkat.NewJsonObject()
    jsonOut := chilkat.NewJsonObject()

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

    success = pdf.ExtractText("search",json,jsonOut)
    if success == false {
        fmt.Println(pdf.LastErrorText())
        pdf.DisposePdf()
        json.DisposeJsonObject()
        jsonOut.DisposeJsonObject()
        return
    }

    fmt.Println("Order numbers found: ", jsonOut.IntOf("count"))
    i := 0
    count_i := jsonOut.SizeOfArray("matches")
    for i < count_i {
        jsonOut.SetI(i)
        fmt.Println(*jsonOut.StringOf("matches[i].text"))
        i = i + 1
    }

    //  Find the e-mail addresses, but stop after the first three.
    json.UpdateString("query","[a-z0-9._]+@[a-z]+[.][a-z]+")
    json.UpdateInt("maxResults",3)
    success = pdf.ExtractText("search",json,jsonOut)
    if success == false {
        fmt.Println(pdf.LastErrorText())
        pdf.DisposePdf()
        json.DisposeJsonObject()
        jsonOut.DisposeJsonObject()
        return
    }

    fmt.Println("First three e-mail addresses:")
    i = 0
    count_i = jsonOut.SizeOfArray("matches")
    for i < count_i {
        jsonOut.SetI(i)
        fmt.Println(*jsonOut.StringOf("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("maxResults")
    json.UpdateBool("regex",false)
    json.UpdateString("query","cat")
    success = pdf.ExtractText("search",json,jsonOut)
    if success == false {
        fmt.Println(pdf.LastErrorText())
        pdf.DisposePdf()
        json.DisposeJsonObject()
        jsonOut.DisposeJsonObject()
        return
    }

    fmt.Println("Occurrences of cat (any): ", jsonOut.IntOf("count"))

    json.UpdateBool("wholeWord",true)
    success = pdf.ExtractText("search",json,jsonOut)
    if success == false {
        fmt.Println(pdf.LastErrorText())
        pdf.DisposePdf()
        json.DisposeJsonObject()
        jsonOut.DisposeJsonObject()
        return
    }

    fmt.Println("Occurrences of cat (whole word): ", jsonOut.IntOf("count"))

    //  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

    pdf.DisposePdf()
    json.DisposeJsonObject()
    jsonOut.DisposeJsonObject()