Code Samples

Easy file inspection, data extraction and format conversion with the Document Filters SDK

Using Document Filters in your applications is easy and intuitive. Document Filters runs natively on 27 platforms and flexible APIs give you the choice of language to integrate with your application. Many functions like text extraction and file format conversion cab be done in 15 lines of code or less!

See more extensive code samples on GitHub.

Check it out for yourself:

Extracting text from a PDF

class Program
{
    // Extract all subfiles from a file
    static void Run(string sourceFile, string outputDirectory)
    {
        // Create an initialize an instance of the Document Filters API
        var docFilters = new DocumentFilters();
        docFilters.Initialize(LICENSE_KEY);

        // Load the source document ready for processing
        using var doc = docFilters.GetExtractor(sourceFile);

        // Extract text
        var text = "";
        while (!doc.EndOfStream)            text += doc.GetText(4096);

        // Extract each subfile 
        for (var subfile = doc.GetFirstSubFile(); subfile != null; subfile = doc.GetNextSubFile()) {
            subfile.CopyTo(System.IO.Path.Combine(outputDirectory, subfile.Name));
        }
    }
}

Converting a Word document to PDF

class Program
{
    // Create a multi-page PDF from a source file
    static void Run(string sourceFile, string outputFile)
    {
        // Create an initialize an instance of the Document Filters API
        var docFilters = new DocumentFilters();
        docFilters.Initialize(LICENSE_KEY);

        // Load the source document ready for processing
        using var doc = docFilters.GetExtractor(sourceFile);
        doc.Open(isys_docfilters.IGR_BODY_AND_META | isys_docfilters.IGR_FORMAT_IMAGE);

        // Create a PDF canvas
        using var canvas = docFilters.MakeOutputCanvas(outputFile, isys_docfilters.IGR_DEVICE_PDF, "");

        // Render each page of the document into the PDF
        for (int pageIndex = 0; pageIndex < doc.GetPageCount(); pageIndex++) {
            canvas.RenderPage(doc.GetPage(pageIndex))
        }
    }
}

Converting a Word document to PNG

class Program
{
    // Create one PNG per page
    static void Run(string sourceFile, string outputDirectory)
    {
        // Create an initialize an instance of the Document Filters API
        var docFilters = new DocumentFilters();
        docFilters.Initialize(LICENSE_KEY);

        // Load the source document ready for processing
        using var doc = docFilters.GetExtractor(sourceFile);
        doc.Open(isys_docfilters.IGR_BODY_AND_META | isys_docfilters.IGR_FORMAT_IMAGE);

        // Render each page to it's own PNG
        for (int pageIndex = 0; pageIndex < doc.GetPageCount(); pageIndex++) {
            using var canvas = docFilters.MakeOutputCanvas(System.IO.Path.Combine(
            outputDirectory, $"page-{pageIndex+1}.png"),
            isys_docfilters.IGR_DEVICE_IMAGE_PNG, "")) {
                canvas.RenderPage(doc.GetPage(pageIndex))
            }
        }
    }
}

Code Samples

Easy file inspection, data extraction and format conversion with the Document Filters SDK

Contact us

By Type

By Topic

By Industry

Popular Resources

Site Search