VisitParagraphStart

DocumentVisitor.VisitParagraphStart method

Called when enumeration of a paragraph has started.

public virtual VisitorAction VisitParagraphStart(Paragraph paragraph)
Parameter Type Description
paragraph Paragraph The object that is being visited.

Return Value

A VisitorAction value that specifies how to continue the enumeration.

Examples

Shows how to use a document visitor to print a document’s node structure.

public void DocStructureToText()
{
    Document doc = new Document(MyDir + "DocumentVisitor-compatible features.docx");
    DocStructurePrinter visitor = new DocStructurePrinter();

    // When we get a composite node to accept a document visitor, the visitor visits the accepting node,
    // and then traverses all the node's children in a depth-first manner.
    // The visitor can read and modify each visited node.
    doc.Accept(visitor);

    Console.WriteLine(visitor.GetText());
}

/// <summary>
/// Traverses a node's tree of child nodes.
/// Creates a map of this tree in the form of a string.
/// </summary>
public class DocStructurePrinter : DocumentVisitor
{
    public DocStructurePrinter()
    {
        mAcceptingNodeChildTree = new StringBuilder();
    }

    public string GetText()
    {
        return mAcceptingNodeChildTree.ToString();
    }

    /// <summary>
    /// Called when a Document node is encountered.
    /// </summary>
    public override VisitorAction VisitDocumentStart(Document doc)
    {
        int childNodeCount = doc.GetChildNodes(NodeType.Any, true).Count;

        IndentAndAppendLine("[Document start] Child nodes: " + childNodeCount);
        mDocTraversalDepth++;

        // Allow the visitor to continue visiting other nodes.
        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called after all the child nodes of a Document node have been visited.
    /// </summary>
    public override VisitorAction VisitDocumentEnd(Document doc)
    {
        mDocTraversalDepth--;
        IndentAndAppendLine("[Document end]");

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a Section node is encountered in the document.
    /// </summary>
    public override VisitorAction VisitSectionStart(Section section)
    {
        // Get the index of our section within the document.
        NodeCollection docSections = section.Document.GetChildNodes(NodeType.Section, false);
        int sectionIndex = docSections.IndexOf(section);

        IndentAndAppendLine("[Section start] Section index: " + sectionIndex);
        mDocTraversalDepth++;

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called after all the child nodes of a Section node have been visited.
    /// </summary>
    public override VisitorAction VisitSectionEnd(Section section)
    {
        mDocTraversalDepth--;
        IndentAndAppendLine("[Section end]");

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a Body node is encountered in the document.
    /// </summary>
    public override VisitorAction VisitBodyStart(Body body)
    {
        int paragraphCount = body.Paragraphs.Count;
        IndentAndAppendLine("[Body start] Paragraphs: " + paragraphCount);
        mDocTraversalDepth++;

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called after all the child nodes of a Body node have been visited.
    /// </summary>
    public override VisitorAction VisitBodyEnd(Body body)
    {
        mDocTraversalDepth--;
        IndentAndAppendLine("[Body end]");

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a Paragraph node is encountered in the document.
    /// </summary>
    public override VisitorAction VisitParagraphStart(Paragraph paragraph)
    {
        IndentAndAppendLine("[Paragraph start]");
        mDocTraversalDepth++;

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called after all the child nodes of a Paragraph node have been visited.
    /// </summary>
    public override VisitorAction VisitParagraphEnd(Paragraph paragraph)
    {
        mDocTraversalDepth--;
        IndentAndAppendLine("[Paragraph end]");

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a Run node is encountered in the document.
    /// </summary>
    public override VisitorAction VisitRun(Run run)
    {
        IndentAndAppendLine("[Run] \"" + run.GetText() + "\"");

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a SubDocument node is encountered in the document.
    /// </summary>
    public override VisitorAction VisitSubDocument(SubDocument subDocument)
    {
        IndentAndAppendLine("[SubDocument]");

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Append a line to the StringBuilder and indent it depending on how deep the visitor is into the document tree.
    /// </summary>
    /// <param name="text"></param>
    private void IndentAndAppendLine(string text)
    {
        for (int i = 0; i < mDocTraversalDepth; i++) mAcceptingNodeChildTree.Append("|  ");

        mAcceptingNodeChildTree.AppendLine(text);
    }

    private int mDocTraversalDepth;
    private readonly StringBuilder mAcceptingNodeChildTree;
}

Shows how to use a DocumentVisitor implementation to remove all hidden content from a document.

{
    Document doc = new Document(MyDir + "Hidden content.docx");

    RemoveHiddenContentVisitor hiddenContentRemover = new RemoveHiddenContentVisitor();

    // Below are three types of fields which can accept a document visitor,
    // which will allow it to visit the accepting node, and then traverse its child nodes in a depth-first manner.
    // 1 -  Paragraph node:
    Paragraph para = (Paragraph) doc.GetChild(NodeType.Paragraph, 4, true);
    para.Accept(hiddenContentRemover);

    // 2 -  Table node:
    Table table = doc.FirstSection.Body.Tables[0];
    table.Accept(hiddenContentRemover);

    // 3 -  Document node:
    doc.Accept(hiddenContentRemover);

    doc.Save(ArtifactsDir + "Font.RemoveHiddenContentFromDocument.docx");

/// <summary>
/// Removes all visited nodes marked as "hidden content".
/// </summary>
public class RemoveHiddenContentVisitor : DocumentVisitor
{
    /// <summary>
    /// Called when a FieldStart node is encountered in the document.
    /// </summary>
    public override VisitorAction VisitFieldStart(FieldStart fieldStart)
    {
        if (fieldStart.Font.Hidden)
            fieldStart.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a FieldEnd node is encountered in the document.
    /// </summary>
    public override VisitorAction VisitFieldEnd(FieldEnd fieldEnd)
    {
        if (fieldEnd.Font.Hidden)
            fieldEnd.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a FieldSeparator node is encountered in the document.
    /// </summary>
    public override VisitorAction VisitFieldSeparator(FieldSeparator fieldSeparator)
    {
        if (fieldSeparator.Font.Hidden)
            fieldSeparator.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a Run node is encountered in the document.
    /// </summary>
    public override VisitorAction VisitRun(Run run)
    {
        if (run.Font.Hidden)
            run.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a Paragraph node is encountered in the document.
    /// </summary>
    public override VisitorAction VisitParagraphStart(Paragraph paragraph)
    {
        if (paragraph.ParagraphBreakFont.Hidden)
            paragraph.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a FormField is encountered in the document.
    /// </summary>
    public override VisitorAction VisitFormField(FormField formField)
    {
        if (formField.Font.Hidden)
            formField.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a GroupShape is encountered in the document.
    /// </summary>
    public override VisitorAction VisitGroupShapeStart(GroupShape groupShape)
    {
        if (groupShape.Font.Hidden)
            groupShape.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a Shape is encountered in the document.
    /// </summary>
    public override VisitorAction VisitShapeStart(Shape shape)
    {
        if (shape.Font.Hidden)
            shape.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a Comment is encountered in the document.
    /// </summary>
    public override VisitorAction VisitCommentStart(Comment comment)
    {
        if (comment.Font.Hidden)
            comment.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a Footnote is encountered in the document.
    /// </summary>
    public override VisitorAction VisitFootnoteStart(Footnote footnote)
    {
        if (footnote.Font.Hidden)
            footnote.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when a SpecialCharacter is encountered in the document.
    /// </summary>
    public override VisitorAction VisitSpecialChar(SpecialChar specialChar)
    {
        if (specialChar.Font.Hidden)
            specialChar.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when visiting of a Table node is ended in the document.
    /// </summary>
    public override VisitorAction VisitTableEnd(Table table)
    {
        // The content inside table cells may have the hidden content flag, but the tables themselves cannot.
        // If this table had nothing but hidden content, this visitor would have removed all of it,
        // and there would be no child nodes left.
        // Thus, we can also treat the table itself as hidden content and remove it.
        // Tables which are empty but do not have hidden content will have cells with empty paragraphs inside,
        // which this visitor will not remove.
        if (!table.HasChildNodes)
            table.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when visiting of a Cell node is ended in the document.
    /// </summary>
    public override VisitorAction VisitCellEnd(Cell cell)
    {
        if (!cell.HasChildNodes && cell.ParentNode != null)
            cell.Remove();

        return VisitorAction.Continue;
    }

    /// <summary>
    /// Called when visiting of a Row node is ended in the document.
    /// </summary>
    public override VisitorAction VisitRowEnd(Row row)
    {
        if (!row.HasChildNodes && row.ParentNode != null)
            row.Remove();

        return VisitorAction.Continue;
    }
}

See Also