Office File API

Split Documents

This demo uses the DevExpress Word Processing Document API to split a document into logical parts and save each part as a separate file in the required format.

You can split the predefined sample file or supply your own document. To do the latter, select Upload a File in the file selection drop-down menu. Select the document split mode in the dropdown list below.

Use the Split and Save as... dropdown button to select the output format, split the document, and download the result.

Example

Sample document

Sample.docx

Split Mode

View Source
Docs




using DevExpress.XtraRichEdit;
using DevExpress.XtraRichEdit.API.Layout;
using DevExpress.XtraRichEdit.API.Native;

IReadOnlyList<Stream> SplitBySection(Stream inputStream, DocumentFormat targetFormat, bool pdfOutput) {
    using var wordProcessor = new RichEditDocumentServer();
    wordProcessor.LoadDocument(inputStream);

    var document = wordProcessor.Document;
    using var sectionProcessor = new RichEditDocumentServer();
    var outputStreams = new List<Stream>();

    foreach(Section section in document.Sections) {
        sectionProcessor.DocxBytes = document.GetDocxBytes(section.Range);
        var sectionStream = new MemoryStream();
        if(pdfOutput)
            sectionProcessor.ExportToPdf(sectionStream);
        else
            sectionProcessor.SaveDocument(sectionStream, targetFormat);
        sectionStream.Position = 0;
        outputStreams.Add(sectionStream);
    }

    return outputStreams;
}

IReadOnlyList<Stream> SplitByHeading(Stream inputStream, DocumentFormat targetFormat, bool pdfOutput) {
    const string styleName = "Heading 1";

    using var wordProcessor = new RichEditDocumentServer();
    wordProcessor.LoadDocument(inputStream);

    var document = wordProcessor.Document;
    if(document.ParagraphStyles[styleName] == null)
        return null;

    var headingParagraphs = document.Paragraphs.Where(p => p.Style.Name == styleName).ToList();
    using var headingProcessor = new RichEditDocumentServer();
    var outputStreams = new List<Stream>();
    for(int i = 0; i < headingParagraphs.Count; i++) {
        var startPosition = headingParagraphs[i].Range.Start;
        DocumentPosition endPosition;
        if(i == headingParagraphs.Count - 1)
            endPosition = document.Range.End;
        else
            endPosition = headingParagraphs[i + 1].Range.Start;
        var headingRange = document.CreateRange(startPosition, endPosition.ToInt() - startPosition.ToInt());

        headingProcessor.DocxBytes = document.GetDocxBytes(headingRange);
        var headingStream = new MemoryStream();
        if(pdfOutput)
            headingProcessor.ExportToPdf(headingStream);
        else
            headingProcessor.SaveDocument(headingStream, targetFormat);
        headingStream.Position = 0;
        outputStreams.Add(headingStream);
    }
    return outputStreams;
}

IReadOnlyList<Stream> SplitByPage(Stream inputStream, DocumentFormat targetFormat, bool pdfOutput) {
    using var wordProcessor = new RichEditDocumentServer();
    wordProcessor.LoadDocument(inputStream);

    var pageCount = wordProcessor.DocumentLayout.GetPageCount();
    var document = wordProcessor.Document;
    using var pageProcessor = new RichEditDocumentServer();
    var outputStreams = new List<Stream>();
    for(int i = 0; i < pageCount; i++) {
        var page = wordProcessor.DocumentLayout.GetPage(i);
        var pageRange = document.CreateRange(page.MainContentRange.Start, page.MainContentRange.Length);
        pageProcessor.DocxBytes = document.GetDocxBytes(pageRange);
        var pageStream = new MemoryStream();
        if(pdfOutput)
            pageProcessor.ExportToPdf(pageStream);
        else
            pageProcessor.SaveDocument(pageStream, targetFormat);
        pageStream.Position = 0;
        outputStreams.Add(pageStream);
    }
    return outputStreams;
}

Word Processing

Spreadsheet Document API

PDF Document API

Presentation API

Split Documents