Swift Requires Chilkat v11.7.0+

Extract PDF Text to a StringBuilder and Save to a File

See more PDF Text Extraction Examples

Demonstrates ExtractTextSb, which writes the extracted text to a StringBuilder instead of returning it as a JSON string. Use it for large documents. The JSON output still receives the quality report. 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 long_report.pdf

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

    print("Number of pages: \(pdf.numPages.intValue)")

    //  ExtractTextSb takes the same operation and options as ExtractText, but the text
    //  goes to a StringBuilder.  This avoids building a very large JSON string for
    //  documents with many pages.
    let json = CkoJsonObject()!
    let sbText = CkoStringBuilder()!
    let jsonOut = CkoJsonObject()!

    success = pdf.extractTextSb(op: "text", jsonIn: json, sbOut: sbText, jsonOut: jsonOut)
    if success == false {
        print("\(pdf.lastErrorText!)")
        return
    }

    print("Extracted \(sbText.length.intValue) characters.")

    //  Save the text to a file.
    success = sbText.writeFile(path: "qa_output/long_report.txt", charset: "utf-8", emitBom: false)
    if success == false {
        print("\(sbText.lastErrorText!)")
        return
    }

    //  The JSON output does not contain the text, but it still has the quality report.
    print("Quality: \(jsonOut.string(of: "quality.rating")!)")
    print("Pages with no text (need OCR): [\(jsonOut.string(of: "quality.pagesNeedingOcr")!)]")

    //  Sample output:

    //  Number of pages: 3
    //  Extracted 4522 characters.
    //  Quality: good
    //  Pages with no text (need OCR): []

}