Remove Empty Pages

Aspose.Words Product Family
1

is there a way to programmatically search and remove empty pages inside a document in java?Problem.zip (205.4 KB)

2

Problem.zip (205.4 KB)

3

Hi there,
Thanks for your inquiry. Please use following code example to remove empty pages from the document. Hope this helps you.

private static ArrayList GetParagraphsByPage(int page, Document document) throws Exception
{
    ArrayList nodes = new ArrayList();
    LayoutCollector lc = new LayoutCollector(document);
    for (Paragraph paragraph: (Iterable <Paragraph> ) document.getChildNodes(NodeType.PARAGRAPH, true))
    {
        if (lc.getStartPageIndex(paragraph) == page)
            nodes.add(paragraph);
    }
    return nodes;
}

public static void RemoveEmptyPages() throws Exception
{
    Document doc = new Document(MyDir + "Problem.docx");
    doc.updatePageLayout();

    Boolean PageBreak = false;
    String PageText = "";
    LayoutCollector lc = new LayoutCollector(doc);
    int pages = doc.getPageCount();

    ArrayList <Node> removenodes = new ArrayList <Node> ();
    ArrayList <Node> pagebreaknodes = new ArrayList <Node> ();
    for (int i = 1; i <= pages; i++)
    {
        PageBreak = false;
        PageText = "";
        ArrayList <Paragraph> nodes = GetParagraphsByPage(i, doc);

        for (int page = 0; page <nodes.size(); page++)
        {
            Paragraph para = nodes.get(page);
            if (para.hasChildNodes())
            {
                if (para.getText().contains(ControlChar.PAGE_BREAK))
                {
                    if (para.getRuns().get(0).getText().contains(ControlChar.PAGE_BREAK))
                    {
                        pagebreaknodes.add(para);
                    }
                }
                PageText = "Page is not empty";
                break;
            }
            else
            {
                for (Paragraph paragraph: nodes)
                {
                    if (paragraph.getText().contains(ControlChar.PAGE_BREAK))
                    {
                        PageBreak = true;
                    }
                    PageText += paragraph.toString(SaveFormat.TEXT).trim();
                }

                // If page's text is empty and there is only page break
                // then remove the page break
                if (PageText.length() == 0 && PageBreak == true)
                {
                    for (Node node: nodes)
                    {
                        if (node.getText().contains(ControlChar.PAGE_BREAK))
                        {
                            pagebreaknodes.add(node);
                        }
                    }
                }

                if (PageText.equals("")) //Empty Page
                {
                    for (Node node: nodes)
                    {
                        removenodes.add(node);
                    }
                }
                nodes.clear();
                PageBreak = false;
            }
        }
    }

    //Remove nodes from empty pages
    for (Node node: removenodes)
    {
        node.remove();
    }

    //Remove page breaks
    for (Node node: pagebreaknodes)
    {
        node.getRange().replace(ControlChar.PAGE_BREAK, "", new FindReplaceOptions());
    }

    //Remove empty pages from the end of document
    while (!doc.getLastSection().getBody().getLastParagraph().hasChildNodes() && doc.getLastSection().getBody().getLastParagraph().toString(SaveFormat.TEXT).trim().equals(""))
    {
        if (doc.getLastSection().getBody().getLastParagraph().getPreviousSibling() != null &&
            doc.getLastSection().getBody().getLastParagraph().getNodeType() != NodeType.PARAGRAPH)
            break;
        doc.getLastSection().getBody().getLastParagraph().remove();

        // If the current section becomes empty, we should remove it.
        if (!doc.getLastSection().getBody().hasChildNodes())
            doc.getLastSection().remove();

        // We should exit the loop if the document becomes empty.
        if (!doc.hasChildNodes())
            break;
    }

    doc.save(MyDir + "Output.docx");
}

Best Regards,
Tahir Manzoor
Aspose - File Format APIs
Keep in touch! We’re on Twitter and Facebook

5

Thank you
Regards
Priya

6