//ExStart
//ExFor:Font.Hidden
//ExFor:Paragraph.Accept
//ExFor:DocumentVisitor.VisitParagraphStart(Aspose.Words.Paragraph)
//ExFor:DocumentVisitor.VisitFormField(Aspose.Words.Fields.FormField)
//ExFor:DocumentVisitor.VisitTableEnd(Aspose.Words.Tables.Table)
//ExFor:DocumentVisitor.VisitCellEnd(Aspose.Words.Tables.Cell)
//ExFor:DocumentVisitor.VisitRowEnd(Aspose.Words.Tables.Row)
//ExFor:DocumentVisitor.VisitSpecialChar(Aspose.Words.SpecialChar)
//ExFor:DocumentVisitor.VisitGroupShapeStart(Aspose.Words.Drawing.GroupShape)
//ExFor:DocumentVisitor.VisitShapeStart(Aspose.Words.Drawing.Shape)
//ExFor:DocumentVisitor.VisitCommentStart(Aspose.Words.Comment)
//ExFor:DocumentVisitor.VisitFootnoteStart(Aspose.Words.Footnote)
//ExFor:SpecialChar
//ExFor:Node.Accept
//ExFor:Paragraph.ParagraphBreakFont
//ExFor:Table.Accept
//ExSummary:Implements the Visitor Pattern to remove all content formatted as hidden from the document.
public void RemoveHiddenContentFromDocument()
{
// Open the document we want to remove hidden content from.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Font.Hidden.doc");
// Create an object that inherits from the DocumentVisitor class.
RemoveHiddenContentVisitor hiddenContentRemover = new RemoveHiddenContentVisitor();
// This is the well known Visitor pattern. Get the model to accept a visitor.
// The model will iterate through itself by calling the corresponding methods
// on the visitor object (this is called visiting).
// We can run it over the entire the document like so:
doc.Accept(hiddenContentRemover);
// Or we can run it on only a specific node.
Paragraph para = (Paragraph)doc.GetChild(NodeType.Paragraph, 4, true);
para.Accept(hiddenContentRemover);
// Or over a different type of node like below.
Table table = (Table)doc.GetChild(NodeType.Table, 0, true);
table.Accept(hiddenContentRemover);
doc.Save(MyDir + "Font.Hidden Out.doc");
Assert.AreEqual(13, doc.GetChildNodes(NodeType.Paragraph, true).Count); //ExSkip
Assert.AreEqual(1, doc.GetChildNodes(NodeType.Table, true).Count); //ExSkip
}
public void DeleteAllImagesPreOrder()
{
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Image.SampleImages.doc");
Assert.AreEqual(6, doc.GetChildNodes(NodeType.Shape, true).Count);
//ExStart
//ExFor:Node.NextPreOrder
//ExSummary:Shows how to delete all images from a document using pre-order tree traversal.
Aspose.Words.Node curNode = doc;
while (curNode != null)
{
Aspose.Words.Node nextNode = curNode.NextPreOrder(doc);
if (curNode.NodeType.Equals(NodeType.Shape))
{
Shape shape = (Shape)curNode;
// Several shape types can have an image including image shapes and OLE objects.
if (shape.HasImage)
{
shape.Remove();
}
}
curNode = nextNode;
}
//ExEnd
Assert.AreEqual(1, doc.GetChildNodes(NodeType.Shape, true).Count);
doc.Save(MyDir + "Image.DeleteAllImagesPreOrder Out.doc");
}
private void ParseDoc(ref FileObject fo, string filePath)
{
Aspose.Words.Document doc = new Aspose.Words.Document(filePath);
Aspose.Words.Properties.BuiltInDocumentProperties dp = doc.BuiltInDocumentProperties;
fo.wordCount = dp.Words;
fo.characterCount = dp.CharactersWithSpaces;
fo.pageCount = dp.Pages;
fo.hasPassword = dp.Security == Aspose.Words.Properties.DocumentSecurity.PasswordProtected;
NodeCollection shapes = doc.GetChildNodes(NodeType.Shape, true);
int NoOfImages = 0;
foreach (Aspose.Words.Drawing.Shape shape in shapes)
{
if (shape.HasImage)
{
NoOfImages++;
}
}
fo.imageCount = NoOfImages;
NodeCollection embeddedDocs = doc.GetChildNodes(NodeType.SubDocument, true);
fo.embeddedDocsCount = embeddedDocs.Count;
}
public void StretchImagefitSizeLim()
{
Aspose.Words.Document doc = DocumentHelper.CreateTemplateDocumentWithDrawObjects("<<image [src.ImageStream] -fitSizeLim>>", ShapeType.TextBox);
ImageTestClass imageStream = new ImageTestBuilder().WithImageStream(new FileStream(this.mImage, FileMode.Open, FileAccess.Read)).Build();
BuildReport(doc, imageStream, "src", ReportBuildOptions.None);
MemoryStream dstStream = new MemoryStream();
doc.Save(dstStream, SaveFormat.Docx);
doc = new Aspose.Words.Document(dstStream);
NodeCollection shapes = doc.GetChildNodes(NodeType.Shape, true);
foreach (Shape shape in shapes)
{
// Assert that the image is really insert in textbox
Assert.IsTrue(shape.ImageData.HasImage);
// Assert that textbox size are equal image size
Assert.AreEqual(346.35, shape.Height);
Assert.AreEqual(258.54, shape.Width);
}
dstStream.Dispose();
}
public void ChangeStyleIdentifier()
{
//ExStart
//ExFor:Font.StyleIdentifier
//ExFor:StyleIdentifier
//ExSummary:Shows how to use style identifier to find text formatted with a specific character style and apply different character style.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Font.StyleIdentifier.doc");
// Select all run nodes in the document.
NodeCollection runs = doc.GetChildNodes(NodeType.Run, true);
// Loop through every run node.
foreach (Run run in runs)
{
// If the character style of the run is what we want, do what we need. Change the style in this case.
// Note that using StyleIdentifier we can identify a built-in style regardless
// of the language of Microsoft Word used to create the document.
if (run.Font.StyleIdentifier.Equals(StyleIdentifier.Emphasis))
{
run.Font.StyleIdentifier = StyleIdentifier.Strong;
}
}
doc.Save(MyDir + "Font.StyleIdentifier Out.doc");
//ExEnd
}
public void ChangeStyleName()
{
//ExStart
//ExFor:Font.StyleName
//ExSummary:Shows how to use style name to find text formatted with a specific character style and apply different character style.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Font.StyleName.doc");
// Select all run nodes in the document.
NodeCollection runs = doc.GetChildNodes(NodeType.Run, true);
// Loop through every run node.
foreach (Run run in runs)
{
// If the character style of the run is what we want, do what we need. Change the style in this case.
// Note that names of built in styles could be different in documents
// created by Microsoft Word versions for different languages.
if (run.Font.StyleName.Equals("Emphasis"))
{
run.Font.StyleName = "Strong";
}
}
doc.Save(MyDir + "Font.StyleName Out.doc");
//ExEnd
}
public void ChangeTOCTabStops()
{
//ExStart
//ExFor:TabStop
//ExFor:ParagraphFormat.TabStops
//ExFor:Style.StyleIdentifier
//ExFor:TabStopCollection.RemoveByPosition
//ExFor:TabStop.Alignment
//ExFor:TabStop.Position
//ExFor:TabStop.Leader
//ExId:ChangeTOCTabStops
//ExSummary:Shows how to modify the position of the right tab stop in TOC related paragraphs.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Document.TableOfContents.doc");
// Iterate through all paragraphs in the document
foreach (Paragraph para in doc.GetChildNodes(NodeType.Paragraph, true))
{
// Check if this paragraph is formatted using the TOC result based styles. This is any style between TOC and TOC9.
if (para.ParagraphFormat.Style.StyleIdentifier >= StyleIdentifier.Toc1 && para.ParagraphFormat.Style.StyleIdentifier <= StyleIdentifier.Toc9)
{
// Get the first tab used in this paragraph, this should be the tab used to align the page numbers.
TabStop tab = para.ParagraphFormat.TabStops[0];
// Remove the old tab from the collection.
para.ParagraphFormat.TabStops.RemoveByPosition(tab.Position);
// Insert a new tab using the same properties but at a modified position.
// We could also change the separators used (dots) by passing a different Leader type
para.ParagraphFormat.TabStops.Add(tab.Position - 50, tab.Alignment, tab.Leader);
}
}
doc.Save(MyDir + "Document.TableOfContentsTabStops Out.doc");
//ExEnd
}
public void GetAllFonts()
{
//ExStart
//ExFor:Run
//ExSummary:Gets all fonts used in a document.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Font.Names.doc");
// Select all runs in the document.
NodeCollection runs = doc.GetChildNodes(NodeType.Run, true);
// Use a hashtable so we will keep only unique font names.
Hashtable fontNames = new Hashtable();
foreach (Run run in runs)
{
// This adds an entry into the hashtable.
// The key is the font name. The value is null, we don't need the value.
fontNames[run.Font.Name] = null;
}
// There are two fonts used in this document.
Console.WriteLine("Font Count: " + fontNames.Count);
//ExEnd
// Verify the font count is correct.
Assert.AreEqual(2, fontNames.Count);
}
/// <summary>
/// Извлечение текста из документа
/// </summary>
/// <param name="bytes">Файл</param>
/// <param name="extension">Расширение файла</param>
/// <returns></returns>
protected override DocumentContent ExtractTextInternal(byte[] bytes, string extension)
{
var content = new StringBuilder();
var result = new DocumentContent();
try {
using (var ms = new MemoryStream(bytes)) {
var doc = new Document(ms, new LoadOptions(GetLoadFormat(extension), null, null));
var paragraphs = doc.GetChildNodes(NodeType.Paragraph, true);
//NOTE: Не всегда получает только первую страницу. Довольно часто цепляет еще несколько
foreach (var node in paragraphs)
{
var text = node.GetText();
if (text.Contains(ControlChar.PageBreak))
{
var index = text.IndexOf(ControlChar.PageBreak, StringComparison.Ordinal);
content.Append(text.Substring(0, index + 1));
break;
}
content.Append(text);
}
}
} catch (Exception ex) {
_logger.Error(ex, $"При обработке {extension} возникло исключение");
}
result.Content = content.ToString();
return(result);
}
public void ChangeTOCTabStops()
{
//ExStart
//ExFor:TabStop
//ExFor:ParagraphFormat.TabStops
//ExFor:Style.StyleIdentifier
//ExFor:TabStopCollection.RemoveByPosition
//ExFor:TabStop.Alignment
//ExFor:TabStop.Position
//ExFor:TabStop.Leader
//ExId:ChangeTOCTabStops
//ExSummary:Shows how to modify the position of the right tab stop in TOC related paragraphs.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Document.TableOfContents.doc");
// Iterate through all paragraphs in the document
foreach (Paragraph para in doc.GetChildNodes(NodeType.Paragraph, true))
{
// Check if this paragraph is formatted using the TOC result based styles. This is any style between TOC and TOC9.
if (para.ParagraphFormat.Style.StyleIdentifier >= StyleIdentifier.Toc1 && para.ParagraphFormat.Style.StyleIdentifier <= StyleIdentifier.Toc9)
{
// Get the first tab used in this paragraph, this should be the tab used to align the page numbers.
TabStop tab = para.ParagraphFormat.TabStops[0];
// Remove the old tab from the collection.
para.ParagraphFormat.TabStops.RemoveByPosition(tab.Position);
// Insert a new tab using the same properties but at a modified position.
// We could also change the separators used (dots) by passing a different Leader type
para.ParagraphFormat.TabStops.Add(tab.Position - 50, tab.Alignment, tab.Leader);
}
}
doc.Save(ExDir + "Document.TableOfContentsTabStops Out.doc");
//ExEnd
}
//ExStart
//ExFor:Node.GetAncestor(NodeType)
//ExFor:Table.NodeType
//ExFor:Cell.Tables
//ExFor:TableCollection
//ExFor:NodeCollection.Count
//ExSummary:Shows how to find out if a table contains another table or if the table itself is nested inside another table.
public void CalcuateDepthOfNestedTables()
{
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Table.NestedTables.doc");
int tableIndex = 0;
foreach (Table table in doc.GetChildNodes(NodeType.Table, true))
{
// First lets find if any cells in the table have tables themselves as children.
int count = GetChildTableCount(table);
Console.WriteLine("Table #{0} has {1} tables directly within its cells", tableIndex, count);
// Now let's try the other way around, lets try find if the table is nested inside another table and at what depth.
int tableDepth = GetNestedDepthOfTable(table);
if (tableDepth > 0)
{
Console.WriteLine("Table #{0} is nested inside another table at depth of {1}", tableIndex, tableDepth);
}
else
{
Console.WriteLine("Table #{0} is a non nested table (is not a child of another table)", tableIndex);
}
tableIndex++;
}
}
private List <NavigationPaneItem> PrepareNavigationPaneList(Document doc, LayoutCollector lc)
{
try
{
var lst = new List <NavigationPaneItem>();
foreach (Paragraph para in doc.GetChildNodes(NodeType.Paragraph, true))
{
switch (para.ParagraphFormat.StyleIdentifier)
{
case StyleIdentifier.Subtitle:
case StyleIdentifier.Title:
case StyleIdentifier.Heading3:
case StyleIdentifier.Heading2:
case StyleIdentifier.Heading1:
var text = para.Range.Text;
if (text.Count(char.IsLetterOrDigit) > 0)
{
lst.Add(new NavigationPaneItem(text, para.ParagraphFormat.StyleIdentifier, lc.GetStartPageIndex(para)));
}
break;
}
}
return(lst);
}
catch (Exception ex)
{
Console.WriteLine(ex.Message);
return(null);
}
}
public void Style()
{
//ExStart
//ExFor:Font.Style
//ExFor:Style.BuiltIn
//ExSummary:Applies double underline to all runs in a document that are formatted with custom character styles.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Font.Style.doc");
// Select all run nodes in the document.
NodeCollection runs = doc.GetChildNodes(NodeType.Run, true);
// Loop through every run node.
foreach (Run run in runs)
{
Aspose.Words.Style charStyle = run.Font.Style;
// If the style of the run is not a built-in character style, apply double underline.
if (!charStyle.BuiltIn)
{
run.Font.Underline = Underline.Double;
}
}
doc.Save(MyDir + "Font.Style Out.doc");
//ExEnd
}
//ExEnd
private void TestResourceLoadingCallback(Document doc)
{
foreach (Shape shape in doc.GetChildNodes(NodeType.Shape, true))
{
Assert.IsTrue(shape.HasImage);
Assert.IsNotEmpty(shape.ImageData.ImageBytes);
}
TestUtil.VerifyWebResponseStatusCode(HttpStatusCode.OK, "http://www.google.com/images/logos/ps_logo2.png");
}
protected void rptCampaign_ItemCommand(object source, RepeaterCommandEventArgs e)
{
if (e.CommandName == "Export")
{
var campaignId = Convert.ToInt32(e.CommandArgument);
var campaign = GoldenDayListCampaignBLL.CampaginGetById(campaignId);
MemoryStream mem = new MemoryStream();
var document = new Aspose.Words.Document(Server.MapPath("/Modules/Sails/Admin/ExportTemplates/Golden_Days_Form.doc"));
DocumentBuilder builder = new DocumentBuilder(document);
document.Range.Replace("{Month}", campaign.Month.ToString("0#"), false, false);
document.Range.Replace("{Year}", campaign.Year.ToString(), false, false);
NodeCollection tables = document.GetChildNodes(NodeType.Table, true);
var table = tables[0] as Aspose.Words.Tables.Table;
for (var i = table.Rows.Count - 1; i > 1; i--)
{
table.Rows.RemoveAt(i);
}
foreach (var goldenDay in campaign.GoldenDays)
{
var cloneOfRow = (Row)table.Rows[1].Clone(true);
cloneOfRow.Cells[0].RemoveAllChildren();
cloneOfRow.Cells[0].AppendChild(new Paragraph(document));
cloneOfRow.Cells[0].FirstParagraph.AppendChild(new Run(document, goldenDay.Date.ToString("dd MMM")));
cloneOfRow.Cells[1].RemoveAllChildren();
cloneOfRow.Cells[1].AppendChild(new Paragraph(document));
cloneOfRow.Cells[1].FirstParagraph.AppendChild(new Run(document, goldenDay.Policy != null ? goldenDay.Policy.Replace("\n", ControlChar.LineBreak) : ""));
table.Rows.Insert(table.Rows.Count, cloneOfRow);
}
table.Rows.RemoveAt(1);
document.Save(mem, Aspose.Words.SaveFormat.Docx);
Response.Clear();
Response.ContentEncoding = System.Text.Encoding.UTF8;
Response.ContentType = "application/vnd.openxmlformats-officedocument.wordprocessingml.document";
var fileName = string.Format("\"{0}.docx\"", campaign.Name);
Response.AppendHeader("content-disposition", "attachment; filename=" + fileName);
mem.Position = 0;
byte[] buffer = mem.ToArray();
Response.BinaryWrite(buffer);
Response.End();
}
if (e.CommandName == "Delete")
{
var campaignId = 0;
try
{
campaignId = Convert.ToInt32(e.CommandArgument);
}
catch { }
var campaign = GoldenDayListCampaignBLL.CampaginGetById(campaignId);
GoldenDayListCampaignBLL.CampaignDelete(campaign);
Response.Redirect(Request.RawUrl);
}
}
private static void RemoveTableOfContents(Aspose.Words.Document doc, int index)
{
// Store the FieldStart nodes of TOC fields in the document for quick access.
ArrayList fieldStarts = new ArrayList();
// This is a list to store the nodes found inside the specified TOC. They will be removed
// at the end of this method.
ArrayList nodeList = new ArrayList();
foreach (FieldStart start in doc.GetChildNodes(NodeType.FieldStart, true))
{
if (start.FieldType == FieldType.FieldTOC)
{
// Add all FieldStarts which are of type FieldTOC.
fieldStarts.Add(start);
}
}
// Ensure the TOC specified by the passed index exists.
if (index > fieldStarts.Count - 1)
{
throw new ArgumentOutOfRangeException("TOC index is out of range");
}
bool isRemoving = true;
// Get the FieldStart of the specified TOC.
Node currentNode = (Node)fieldStarts[index];
while (isRemoving)
{
// It is safer to store these nodes and delete them all at once later.
nodeList.Add(currentNode);
currentNode = currentNode.NextPreOrder(doc);
// Once we encounter a FieldEnd node of type FieldTOC then we know we are at the end
// of the current TOC and we can stop here.
if (currentNode.NodeType == NodeType.FieldEnd)
{
FieldEnd fieldEnd = (FieldEnd)currentNode;
if (fieldEnd.FieldType == FieldType.FieldTOC)
{
isRemoving = false;
}
}
}
// Remove all nodes found in the specified TOC.
foreach (Node node in nodeList)
{
node.Remove();
}
}
public void DisplayContentOfTables()
{
//ExStart
//ExFor:Table
//ExFor:Row.Cells
//ExFor:Table.Rows
//ExFor:Cell
//ExFor:Row
//ExFor:RowCollection
//ExFor:CellCollection
//ExFor:NodeCollection.IndexOf(Node)
//ExSummary:Shows how to iterate through all tables in the document and display the content from each cell.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Table.Document.doc");
// Here we get all tables from the Document node. You can do this for any other composite node
// which can contain block level nodes. For example you can retrieve tables from header or from a cell
// containing another table (nested tables).
NodeCollection tables = doc.GetChildNodes(NodeType.Table, true);
// Iterate through all tables in the document
foreach (Table table in tables)
{
// Get the index of the table node as contained in the parent node of the table
int tableIndex = table.ParentNode.ChildNodes.IndexOf(table);
Console.WriteLine("Start of Table {0}", tableIndex);
// Iterate through all rows in the table
foreach (Row row in table.Rows)
{
int rowIndex = table.Rows.IndexOf(row);
Console.WriteLine("\tStart of Row {0}", rowIndex);
// Iterate through all cells in the row
foreach (Cell cell in row.Cells)
{
int cellIndex = row.Cells.IndexOf(cell);
// Get the plain text content of this cell.
string cellText = cell.ToString(SaveFormat.Text).Trim();
// Print the content of the cell.
Console.WriteLine("\t\tContents of Cell:{0} = \"{1}\"", cellIndex, cellText);
}
//Console.WriteLine();
Console.WriteLine("\tEnd of Row {0}", rowIndex);
}
Console.WriteLine("End of Table {0}", tableIndex);
Console.WriteLine();
}
//ExEnd
Assert.Greater(tables.Count, 0);
}
public void DeleteAllShapes()
{
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Shape.DeleteAllShapes.doc");
//ExStart
//ExFor:Shape
//ExSummary:Shows how to delete all shapes from a document.
// Here we get all shapes from the document node, but you can do this for any smaller
// node too, for example delete shapes from a single section or a paragraph.
NodeCollection shapes = doc.GetChildNodes(NodeType.Shape, true);
shapes.Clear();
// There could also be group shapes, they have different node type, remove them all too.
NodeCollection groupShapes = doc.GetChildNodes(NodeType.GroupShape, true);
groupShapes.Clear();
//ExEnd
Assert.AreEqual(0, doc.GetChildNodes(NodeType.Shape, true).Count);
Assert.AreEqual(0, doc.GetChildNodes(NodeType.GroupShape, true).Count);
doc.Save(MyDir + "Shape.DeleteAllShapes Out.doc");
}
public void ReplaceTextboxesWithImages()
{
//ExStart
//ExFor:WrapSide
//ExFor:ShapeBase.WrapSide
//ExFor:NodeCollection
//ExFor:CompositeNode.InsertAfter(Node, Node)
//ExFor:NodeCollection.ToArray
//ExSummary:Shows how to replace all textboxes with images.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Shape.ReplaceTextboxesWithImages.doc");
// This gets a live collection of all shape nodes in the document.
NodeCollection shapeCollection = doc.GetChildNodes(NodeType.Shape, true);
// Since we will be adding/removing nodes, it is better to copy all collection
// into a fixed size array, otherwise iterator will be invalidated.
Aspose.Words.Node[] shapes = shapeCollection.ToArray();
foreach (Shape shape in shapes)
{
// Filter out all shapes that we don't need.
if (shape.ShapeType.Equals(ShapeType.TextBox))
{
// Create a new shape that will replace the existing shape.
Shape image = new Shape(doc, ShapeType.Image);
// Load the image into the new shape.
image.ImageData.SetImage(MyDir + "Hammer.wmf");
// Make new shape's position to match the old shape.
image.Left = shape.Left;
image.Top = shape.Top;
image.Width = shape.Width;
image.Height = shape.Height;
image.RelativeHorizontalPosition = shape.RelativeHorizontalPosition;
image.RelativeVerticalPosition = shape.RelativeVerticalPosition;
image.HorizontalAlignment = shape.HorizontalAlignment;
image.VerticalAlignment = shape.VerticalAlignment;
image.WrapType = shape.WrapType;
image.WrapSide = shape.WrapSide;
// Insert new shape after the old shape and remove the old shape.
shape.ParentNode.InsertAfter(image, shape);
shape.Remove();
}
}
doc.Save(MyDir + "Shape.ReplaceTextboxesWithImages Out.doc");
//ExEnd
}
public void DeleteAllImages()
{
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Image.SampleImages.doc");
Assert.AreEqual(6, doc.GetChildNodes(NodeType.Shape, true).Count);
//ExStart
//ExFor:Shape.HasImage
//ExFor:Node.Remove
//ExSummary:Shows how to delete all images from a document.
// Here we get all shapes from the document node, but you can do this for any smaller
// node too, for example delete shapes from a single section or a paragraph.
NodeCollection shapes = doc.GetChildNodes(NodeType.Shape, true);
// We cannot delete shape nodes while we enumerate through the collection.
// One solution is to add nodes that we want to delete to a temporary array and delete afterwards.
ArrayList shapesToDelete = new ArrayList();
foreach (Shape shape in shapes)
{
// Several shape types can have an image including image shapes and OLE objects.
if (shape.HasImage)
{
shapesToDelete.Add(shape);
}
}
// Now we can delete shapes.
foreach (Shape shape in shapesToDelete)
{
shape.Remove();
}
//ExEnd
Assert.AreEqual(1, doc.GetChildNodes(NodeType.Shape, true).Count);
doc.Save(MyDir + "Image.DeleteAllImages Out.doc");
}
/// <summary>
/// 追加表格
/// </summary>
/// <param name="tableIndex"></param>
/// <param name="dt"></param>
/// <param name="widthLst"></param>
/// <returns></returns>
public bool AddTable(int tableIndex, System.Data.DataTable dt, List <double> widthLst)
{
NodeCollection allTables = _Doc.GetChildNodes(NodeType.Table, true); //拿到所有表格
Aspose.Words.Tables.Table table = allTables[tableIndex] as Aspose.Words.Tables.Table; //拿到第tableIndex个表格
for (int row = 0; row < dt.Rows.Count; row++)
{
Aspose.Words.Tables.Row r = new Aspose.Words.Tables.Row(_Doc);
var newRow = CreateRow(dt.Columns.Count, dt.Rows[row].ItemArray, _Doc, widthLst); //创建一行
table.Rows.Add(newRow); //添加一行
}
return(true);
}
/// <summary>
/// Извлечение текста из картинок в документе
/// </summary>
/// <param name="bytes">Файл</param>
/// <param name="extension">Расширение файла</param>
/// <returns></returns>
protected override async Task <DocumentContent> ExtractImageTextInternal(byte[] bytes, string extension)
{
var content = new StringBuilder();
var result = new DocumentContent();
try {
using (var ms = new MemoryStream(bytes)) {
var doc = new Document(ms, new LoadOptions(GetLoadFormat(extension), null, null));
foreach (var node in doc.GetChildNodes(NodeType.Shape, true))
{
var shape = (Shape)node;
if (!shape.HasImage || shape.ImageData.ImageBytes == null || shape.ImageData.ImageBytes.Length == 8818)
{
continue;
}
string extractTextImage;
if (shape.ImageData.ImageType == ImageType.Emf)
{
using (var imageBytes = new MemoryStream()) {
shape.GetShapeRenderer().Save(imageBytes, new ImageSaveOptions(SaveFormat.Png));
extractTextImage = await _imageExtractor.ExtractTextImage(imageBytes.ToArray());
}
}
else
{
extractTextImage = await _imageExtractor.ExtractTextImage(shape.ImageData.ImageBytes);
}
if (string.IsNullOrWhiteSpace(extractTextImage))
{
var image = shape.ImageData.ToImage();
extractTextImage = await _imageExtractor.ExtractTextImage(image.Bytes);
}
content.Append(extractTextImage);
result.HasImageContent = true;
}
}
} catch (Exception ex) {
_logger.Error(ex, $"При обработке {extension} возникло исключение");
}
result.Content = content.ToString();
return(result);
}
public static ArrayList RunsByStyleName(Aspose.Words.Document doc, string styleName)
{
// Create an array to collect runs of the specified style.
ArrayList runsWithStyle = new ArrayList();
// Get all runs from the document.
NodeCollection runs = doc.GetChildNodes(NodeType.Run, true);
// Look through all runs to find those with the specified style.
foreach (Run run in runs)
{
if (run.Font.Style.Name == styleName)
{
runsWithStyle.Add(run);
}
}
return(runsWithStyle);
}
public static ArrayList ParagraphsByStyleName(Aspose.Words.Document doc, string styleName)
{
// Create an array to collect paragraphs of the specified style.
ArrayList paragraphsWithStyle = new ArrayList();
// Get all paragraphs from the document.
NodeCollection paragraphs = doc.GetChildNodes(NodeType.Paragraph, true);
// Look through all paragraphs to find those with the specified style.
foreach (Paragraph paragraph in paragraphs)
{
if (paragraph.ParagraphFormat.Style.Name == styleName)
{
paragraphsWithStyle.Add(paragraph);
}
}
return(paragraphsWithStyle);
}
/// <summary>
/// doc清洁方法
/// </summary>
/// <param name="srcBytes">doc源二进制数据</param>
/// <param name="extension"></param>
/// <returns></returns>
public static byte[] CleanDoc(byte[] srcBytes, string extension)
{
// 参数验证
if (srcBytes == null)
{
throw new InvalidDataException();
}
if (string.IsNullOrEmpty(extension))
{
throw new InvalidDataException();
}
byte[] result = null;
Stream docStream = new System.IO.MemoryStream(srcBytes);
Aspose.Words.Document doc = new Aspose.Words.Document(docStream);
// 接受全部修订
doc.AcceptAllRevisions();
//StyleCollection styleCollection=
//清除批注
NodeCollection nodeCollection = doc.GetChildNodes(NodeType.Comment, true);
foreach (Node comment in nodeCollection)
{
nodeCollection.Remove(comment);
}
//二进制另存
using (MemoryStream ms = new MemoryStream())
{
if (extension == ".docx" || extension == "docx")
{
doc.Save(ms, SaveFormat.Docx);
result = ms.ToArray();
}
if (extension == ".doc" || extension == "doc")
{
doc.Save(ms, SaveFormat.Doc);
result = ms.ToArray();
}
}
return(result);
}
public void RenameMergeFields()
{
// Specify your document name here.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "RenameMergeFields.doc");
// Select all field start nodes so we can find the merge fields.
NodeCollection fieldStarts = doc.GetChildNodes(NodeType.FieldStart, true);
foreach (FieldStart fieldStart in fieldStarts)
{
if (fieldStart.FieldType.Equals(FieldType.FieldMergeField))
{
MergeField mergeField = new MergeField(fieldStart);
mergeField.Name = mergeField.Name + "_Renamed";
}
}
doc.Save(MyDir + "RenameMergeFields Out.doc");
}
[Test] //ExSkip
public void ExtractImagesToFiles()
{
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Image.SampleImages.doc");
NodeCollection shapes = doc.GetChildNodes(NodeType.Shape, true);
int imageIndex = 0;
foreach (Shape shape in shapes)
{
if (shape.HasImage)
{
string imageFileName = string.Format(
"Image.ExportImages.{0} Out{1}", imageIndex, FileFormatUtil.ImageTypeToExtension(shape.ImageData.ImageType));
shape.ImageData.Save(MyDir + imageFileName);
imageIndex++;
}
}
}
public static ArrayList GetNodesByPage(int page, Aspose.Words.Document document)
{
ArrayList nodes = new ArrayList();
LayoutCollector lc = new LayoutCollector(document);
foreach (Paragraph para in document.GetChildNodes(NodeType.Paragraph, true))
{
if (lc.GetStartPageIndex(para) == page)
{
nodes.Add(para);
}
}
return(nodes);
}
//ExStart
//ExId:TextboxToTable
//ExSummary:Shows how to convert a textbox to a table and retain almost identical formatting. This is useful for HTML export.
public void ConvertTextboxToTable()
{
// Open the document
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Shape.Textbox.doc");
// Convert all shape nodes which contain child nodes.
// We convert the collection to an array as static "snapshot" because the original textboxes will be removed after conversion which will
// invalidate the enumerator.
foreach (Shape shape in doc.GetChildNodes(NodeType.Shape, true).ToArray())
{
if (shape.HasChildNodes)
{
ConvertTextboxToTable(shape);
}
}
doc.Save(MyDir + "Table.ConvertTextboxToTable Out.html");
}
[Test] //ExSkip
public void RenameMergeFields()
{
// Specify your document name here.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "RenameMergeFields.doc");
// Select all field start nodes so we can find the merge fields.
NodeCollection fieldStarts = doc.GetChildNodes(NodeType.FieldStart, true);
foreach (FieldStart fieldStart in fieldStarts)
{
if (fieldStart.FieldType.Equals(FieldType.FieldMergeField))
{
MergeField mergeField = new MergeField(fieldStart);
mergeField.Name = mergeField.Name + "_Renamed";
}
}
doc.Save(MyDir + "RenameMergeFields Out.doc");
}
[Test] //ExSkip
public void ResourceLoadingCallback()
{
Document doc = new Document();
doc.ResourceLoadingCallback = new ImageNameHandler();
DocumentBuilder builder = new DocumentBuilder(doc);
// Images usually are inserted using a URI, or a byte array.
// Every instance of a resource load will call our callback's ResourceLoading method.
builder.InsertImage("Google logo");
builder.InsertImage("Aspose logo");
builder.InsertImage("Watermark");
Assert.AreEqual(3, doc.GetChildNodes(NodeType.Shape, true).Count);
doc.Save(ArtifactsDir + "DocumentBase.ResourceLoadingCallback.docx");
TestResourceLoadingCallback(new Document(ArtifactsDir + "DocumentBase.ResourceLoadingCallback.docx")); //ExSkip
}
public void SplitTable()
{
//ExStart
//ExId:SplitTableAtRow
//ExSummary:Shows how to split a table into two tables a specific row.
// Load the document.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Table.SimpleTable.doc");
// Get the first table in the document.
Table firstTable = (Table)doc.GetChild(NodeType.Table, 0, true);
// We will split the table at the third row (inclusive).
Row row = firstTable.Rows[2];
// Create a new container for the split table.
Table table = (Table)firstTable.Clone(false);
// Insert the container after the original.
firstTable.ParentNode.InsertAfter(table, firstTable);
// Add a buffer paragraph to ensure the tables stay apart.
firstTable.ParentNode.InsertAfter(new Paragraph(doc), firstTable);
Row currentRow;
do
{
currentRow = firstTable.LastRow;
table.PrependChild(currentRow);
}while (currentRow != row);
doc.Save(MyDir + "Table.SplitTable Out.doc");
//ExEnd
doc = new Aspose.Words.Document(MyDir + "Table.SplitTable Out.doc");
// Test we are adding the rows in the correct order and the
// selected row was also moved.
Assert.AreEqual(row, table.FirstRow);
Assert.AreEqual(2, firstTable.Rows.Count);
Assert.AreEqual(2, table.Rows.Count);
Assert.AreEqual(2, doc.GetChildNodes(NodeType.Table, true).Count);
}
public void CheckShapeInline()
{
//ExStart
//ExFor:ShapeBase.IsInline
//ExSummary:Shows how to test if a shape in the document is inline or floating.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Shape.DeleteAllShapes.doc");
foreach (Shape shape in doc.GetChildNodes(NodeType.Shape, true))
{
if(shape.IsInline)
Console.WriteLine("Shape is inline.");
else
Console.WriteLine("Shape is floating.");
}
//ExEnd
// Verify that the first shape in the document is not inline.
Assert.False(((Shape)doc.GetChild(NodeType.Shape, 0, true)).IsInline);
}
public void AddComment()
{
//ExStart
//ExFor:Comment
//ExFor:InlineStory
//ExFor:InlineStory.Paragraphs
//ExFor:InlineStory.FirstParagraph
//ExFor:Comment.#ctor(DocumentBase, String, String, DateTime)
//ExSummary:Shows how to add a comment to a paragraph in the document.
Aspose.Words.Document doc = new Aspose.Words.Document();
DocumentBuilder builder = new DocumentBuilder(doc);
builder.Write("Some text is added.");
Aspose.Words.Comment comment = new Aspose.Words.Comment(doc, "Amy Lee", "AL", DateTime.Today);
builder.CurrentParagraph.AppendChild(comment);
comment.Paragraphs.Add(new Paragraph(doc));
comment.FirstParagraph.Runs.Add(new Run(doc, "Comment text."));
//ExEnd
Assert.AreEqual("Comment text.\r", (doc.GetChildNodes(NodeType.Comment, true)[0]).GetText());
}
public void AddFootnote()
{
//ExStart
//ExFor:Footnote
//ExFor:InlineStory
//ExFor:InlineStory.Paragraphs
//ExFor:InlineStory.FirstParagraph
//ExFor:FootnoteType
//ExFor:Footnote.#ctor
//ExSummary:Shows how to add a footnote to a paragraph in the document.
Aspose.Words.Document doc = new Aspose.Words.Document();
DocumentBuilder builder = new DocumentBuilder(doc);
builder.Write("Some text is added.");
Footnote footnote = new Footnote(doc, FootnoteType.Footnote);
builder.CurrentParagraph.AppendChild(footnote);
footnote.Paragraphs.Add(new Paragraph(doc));
footnote.FirstParagraph.Runs.Add(new Run(doc, "Footnote text."));
//ExEnd
Assert.AreEqual("Footnote text.", doc.GetChildNodes(NodeType.Footnote, true)[0].ToString(SaveFormat.Text).Trim());
}
//ExStart
//ExFor:Node.GetAncestor(NodeType)
//ExFor:Table.NodeType
//ExFor:Cell.Tables
//ExFor:TableCollection
//ExFor:NodeCollection.Count
//ExSummary:Shows how to find out if a table contains another table or if the table itself is nested inside another table.
public void CalcuateDepthOfNestedTables()
{
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Table.NestedTables.doc");
int tableIndex = 0;
foreach (Table table in doc.GetChildNodes(NodeType.Table, true))
{
// First lets find if any cells in the table have tables themselves as children.
int count = GetChildTableCount(table);
Console.WriteLine("Table #{0} has {1} tables directly within its cells", tableIndex, count);
// Now let's try the other way around, lets try find if the table is nested inside another table and at what depth.
int tableDepth = GetNestedDepthOfTable(table);
if (tableDepth > 0)
Console.WriteLine("Table #{0} is nested inside another table at depth of {1}", tableIndex, tableDepth);
else
Console.WriteLine("Table #{0} is a non nested table (is not a child of another table)", tableIndex);
tableIndex++;
}
}
public void GetIndexOfTableElements()
{
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Table.Document.doc");
Table table = (Table)doc.GetChild(NodeType.Table, 0, true);
//ExStart
//ExFor:NodeCollection.IndexOf
//ExId:IndexOfTable
//ExSummary:Retrieves the index of a table in the document.
NodeCollection allTables = doc.GetChildNodes(NodeType.Table, true);
int tableIndex = allTables.IndexOf(table);
//ExEnd
Row row = table.Rows[2];
//ExStart
//ExFor:Row
//ExFor:CompositeNode.IndexOf
//ExId:IndexOfRow
//ExSummary:Retrieves the index of a row in a table.
int rowIndex = table.IndexOf(row);
//ExEnd
Cell cell = row.LastCell;
//ExStart
//ExFor:Cell
//ExFor:CompositeNode.IndexOf
//ExId:IndexOfCell
//ExSummary:Retrieves the index of a cell in a row.
int cellIndex = row.IndexOf(cell);
//ExEnd
Assert.AreEqual(0, tableIndex);
Assert.AreEqual(2, rowIndex);
Assert.AreEqual(4, cellIndex);
}
//ExStart
//ExId:TextboxToTable
//ExSummary:Shows how to convert a textbox to a table and retain almost identical formatting. This is useful for HTML export.
public void ConvertTextboxToTable()
{
// Open the document
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Shape.Textbox.doc");
// Convert all shape nodes which contain child nodes.
// We convert the collection to an array as static "snapshot" because the original textboxes will be removed after conversion which will
// invalidate the enumerator.
foreach (Shape shape in doc.GetChildNodes(NodeType.Shape, true).ToArray())
{
if (shape.HasChildNodes)
{
ConvertTextboxToTable(shape);
}
}
doc.Save(ExDir + "Table.ConvertTextboxToTable Out.html");
}
public void JoinRunsWithSameFormatting()
{
//ExStart
//ExFor:Document.JoinRunsWithSameFormatting
//ExSummary:Shows how to join runs in a document to reduce unneeded runs.
// Let's load this particular document. It contains a lot of content that has been edited many times.
// This means the document will most likely contain a large number of runs with duplicate formatting.
Aspose.Words.Document doc = new Aspose.Words.Document(MyDir + "Rendering.doc");
// This is for illustration purposes only, remember how many run nodes we had in the original document.
int runsBefore = doc.GetChildNodes(NodeType.Run, true).Count;
// Join runs with the same formatting. This is useful to speed up processing and may also reduce redundant
// tags when exporting to HTML which will reduce the output file size.
int joinCount = doc.JoinRunsWithSameFormatting();
// This is for illustration purposes only, see how many runs are left after joining.
int runsAfter = doc.GetChildNodes(NodeType.Run, true).Count;
Console.WriteLine("Number of runs before:{0}, after:{1}, joined:{2}", runsBefore, runsAfter, joinCount);
// Save the optimized document to disk.
doc.Save(MyDir + "Document.JoinRunsWithSameFormatting Out.html");
//ExEnd
// Verify that runs were joined in the document.
Assert.Less(runsAfter, runsBefore);
Assert.AreNotEqual(0, joinCount);
}
public void SplitTable()
{
//ExStart
//ExId:SplitTableAtRow
//ExSummary:Shows how to split a table into two tables a specific row.
// Load the document.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Table.SimpleTable.doc");
// Get the first table in the document.
Table firstTable = (Table)doc.GetChild(NodeType.Table, 0, true);
// We will split the table at the third row (inclusive).
Row row = firstTable.Rows[2];
// Create a new container for the split table.
Table table = (Table)firstTable.Clone(false);
// Insert the container after the original.
firstTable.ParentNode.InsertAfter(table, firstTable);
// Add a buffer paragraph to ensure the tables stay apart.
firstTable.ParentNode.InsertAfter(new Paragraph(doc), firstTable);
Row currentRow;
do
{
currentRow = firstTable.LastRow;
table.PrependChild(currentRow);
}
while (currentRow != row);
doc.Save(ExDir + "Table.SplitTable Out.doc");
//ExEnd
doc = new Aspose.Words.Document(ExDir + "Table.SplitTable Out.doc");
// Test we are adding the rows in the correct order and the
// selected row was also moved.
Assert.AreEqual(row, table.FirstRow);
Assert.AreEqual(2, firstTable.Rows.Count);
Assert.AreEqual(2, table.Rows.Count);
Assert.AreEqual(2, doc.GetChildNodes(NodeType.Table, true).Count);
}
public void Style()
{
//ExStart
//ExFor:Font.Style
//ExFor:Style.BuiltIn
//ExSummary:Applies double underline to all runs in a document that are formatted with custom character styles.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Font.Style.doc");
// Select all run nodes in the document.
NodeCollection runs = doc.GetChildNodes(NodeType.Run, true);
// Loop through every run node.
foreach (Run run in runs)
{
Aspose.Words.Style charStyle = run.Font.Style;
// If the style of the run is not a built-in character style, apply double underline.
if (!charStyle.BuiltIn)
run.Font.Underline = Underline.Double;
}
doc.Save(ExDir + "Font.Style Out.doc");
//ExEnd
}
static void Main(string[] args)
{
stopwatch.Start();
writeToLog("Application PDBOT Started...");
Console.WriteLine("Application PDBOT Started...");
//license details
Aspose.Words.License asposeWordsLicense = new Aspose.Words.License();
asposeWordsLicense.SetLicense("Aspose.Words.lic");
Aspose.Pdf.License asposePdfLisence = new Aspose.Pdf.License();
asposePdfLisence.SetLicense("Aspose.Pdf.lic");
string hflDocumentPath = null;
string path = @"C:\Users\51210\Desktop\Customers\SG Finans\Oppgraderings Prosjekt SG Finans\BL0019\pdbot_control.xml";
XmlDocument controlXMl = null;
XmlNamespaceManager nsmngr = null;
//Lists for saving values from control xml
List<string> documentKeyswordsList = null;
List<string> globalsKeywordsList = null;
Aspose.Words.Document docTemplate = null;
//load xml document
try
{
controlXMl = new XmlDocument();
controlXMl.Load(path);
nsmngr = new XmlNamespaceManager(controlXMl.NameTable);
nsmngr.AddNamespace("pdbot", "www.canon.no/pdbot");
writeToLog("Control xml loaded successfuly");
}
catch (Exception e)
{
Console.WriteLine("Application PDBOT failed with error " + e.StackTrace);
writeToLog("Error loading control xml " + e.StackTrace);
Console.ReadKey();
}
//----------------------------------------------------------------------------------------------------------------------------------
//get information from control xml nodes
if (controlXMl != null)
{
try
{
//get global document keys and value
//select Globals/Keys/Key
globalsKeywordsList = new List<string>();
XmlNodeList keyNodes = controlXMl.SelectNodes("//pdbot:Globals//pdbot:Keys//pdbot:Key", nsmngr);
if (keyNodes.Count != 0)
{
foreach (XmlNode KeyNode in keyNodes)
{
string keyword = KeyNode["Keyword"].InnerText;
string value = KeyNode["Value"].InnerText;
string KeywordAndValue = keyword + "|" + value;
globalsKeywordsList.Add(KeywordAndValue);
}
writeToLog("Global keywords and value read");
}
//---------------------------------------------------------------------------------------------------------------------------
//get Global sections
//select Globals/Sections/section
List<string> sectionsList = new List<string>();
XmlNodeList sectionNodes = controlXMl.SelectNodes("//pdbot:Globals//pdbot:Sections//pdbot:Section", nsmngr);
if (sectionNodes.Count != 0)
{
foreach (XmlNode sectionNode in sectionNodes)
{
string name = sectionNode["Name"].InnerText;
sectionsList.Add(name);
}
writeToLog("Global Section names read");
}
//---------------------------------------------------------------------------------------------------------------------------
//get all documents in the control xml
XmlNodeList documentNodes = controlXMl.SelectNodes("//pdbot:Docs//pdbot:Doc", nsmngr);
//get all document information
//get document content - Fields, Keys, paragraphkeywords, sections, copies and pagewatermarkings
foreach (XmlNode documentNode in documentNodes)
{
//get document template information
List<string> documentFieldsList = new List<string>();
string templateFormat = documentNode["TemplateFormat"].InnerText;
string repositoryTemplate = documentNode["RepositoryTemplate"].InnerText;
//---------------------------------------------------------------------------------------------------------------------------
//get document field names and value
//select Docs/Doc/DocContent/Fields
XmlNodeList fieldNodes = documentNode.SelectNodes("pdbot:DocContent//pdbot:Fields//pdbot:Field", nsmngr);
if (fieldNodes.Count != 0)
{
foreach (XmlNode fieldNode in fieldNodes)
{
string fieldName = fieldNode["FieldName"].InnerText;
string fieldNameValue = fieldNode["Value"].InnerText;
string fieldNameWithValue = fieldName + "|" + fieldNameValue;
documentFieldsList.Add(fieldNameWithValue);
}
writeToLog("Document archive fields read");
}
//---------------------------------------------------------------------------------------------------------------------------
//get document keywords and value
//select Docs/Doc/DocContent/Keys
documentKeyswordsList = new List<string>();
XmlNodeList docKeyNodes = documentNode.SelectNodes("pdbot:DocContent//pdbot:Keys//pdbot:Key", nsmngr);
if (docKeyNodes.Count != 0)
{
foreach (XmlNode docKeyNode in docKeyNodes)
{
string keyword = docKeyNode["Keyword"].InnerText;
string value = docKeyNode["Value"].InnerText;
string keywordWithValue = keyword + "|" + value;
documentKeyswordsList.Add(keywordWithValue);
}
writeToLog("Document keys read");
}
//---------------------------------------------------------------------------------------------------------------------------
//get document paragraphs and value
//select Docs/Doc/DocContent/ParagraphKeywords/Paragraph
List<string> paragraphKeywordsList = new List<string>();
XmlNodeList paragraphNodes = documentNode.SelectNodes("pdbot:DocContent//pdbot:ParagraphKeywords//pdbot:Paragraph", nsmngr);
if (paragraphNodes.Count != 0)
{
foreach (XmlNode paragraphNode in paragraphNodes)
{
string keyword = paragraphNode["Keyword"].InnerText;
string value = paragraphNode["Value"].InnerText;
string keywordWithValue = keyword + "|" + value;
paragraphKeywordsList.Add(keywordWithValue);
}
writeToLog("Document paragragh keys read");
}
//---------------------------------------------------------------------------------------------------------------------------
//get document sections
//select Docs/Doc/DocContent/Sections/Section
XmlNodeList docSectionNodes = documentNode.SelectNodes("pdbot:DocContent//pdbot:Sections//pdbot:Section", nsmngr);
if (docSectionNodes.Count != 0)
{
foreach (XmlNode docSectionNode in docSectionNodes)
{
string name = docSectionNode["Name"].InnerText;
if (!sectionsList.Contains(name))
{
sectionsList.Add(name);
}
}
writeToLog("Document sections read");
}
//---------------------------------------------------------------------------------------------------------------------------
//get PageWatermarkings
//select Docs/Doc/PageWatermarkings/PageWatermarking
XmlNode hflPageWatermarkingsNodes = documentNode.SelectSingleNode("pdbot:PageWatermarkings//pdbot:PageWatermarking", nsmngr);
hflDocumentPath = hflPageWatermarkingsNodes["ResourceFile"].InnerText;
//select Docs/Doc/PageWatermarkings/PageWatermarking/Watermark
XmlNodeList pageWatermarkingsNodes = documentNode.SelectNodes("pdbot:PageWatermarkings//pdbot:PageWatermarking//pdbot:Watermark", nsmngr);
List<string> waterMarkings = new List<string>();
//get watermark values
if (pageWatermarkingsNodes.Count != 0)
{
foreach (XmlNode watermarkNode in pageWatermarkingsNodes)
{
string wmark = watermarkNode.InnerText;
waterMarkings.Add(wmark);
}
writeToLog("PageWatermarkings dokument variables read");
}
//---------------------------------------------------------------------------------------------------------------------------
//get PageInserts
//select Docs/Doc/PageInserts/Inserts
XmlNode PageInsertNodes = documentNode.SelectSingleNode("pdbot:PageInserts//pdbot:Inserts", nsmngr);
//---------------------------------------------------------------------------------------------------------------------------
//get copies information
//select Docs/Doc/Copies/Copy
List<string> copiesList = new List<string>();
XmlNodeList copyNodes = documentNode.SelectNodes("pdbot:Copies//pdbot:Copy", nsmngr);
if (copyNodes.Count != 0)
{
foreach (XmlNode copyNode in copyNodes)
{
string name = copyNode["Name"].InnerText;
string stampText = copyNode["StampText"].InnerText;
string flatten = copyNode["Flatten"].InnerText;
string outputFile = copyNode["OutputFile"].InnerText;
string copyValues = name + "|" + stampText + "|" + flatten + "|" + outputFile;
copiesList.Add(copyValues);
}
writeToLog("Copies document variables read.");
}
//---------------------------------------------------------------------------------------------------------------------------
//replace variables from word template with keywords and values
//loop through all the fields in the document and replace content with values from control xml:
//load word document template
try
{
//Read RepositoryTemplate
string keyword = null;
string value = null;
repositoryTemplate = repositoryTemplate.Replace("xml", "docx");
docTemplate = new Aspose.Words.Document(repositoryTemplate);
writeToLog("Document template " + docTemplate.OriginalFileName.ToString() + " loaded succesfully");
//--------------------------------------------------------------------------------------------------------------------------
if (docTemplate != null)
{
//Remove content controls/sections which will not be used
if (sectionsList.Count != 0)
{
var ccntrls = docTemplate.GetChildNodes(NodeType.StructuredDocumentTag, true);
foreach (var ccntrl in ccntrls)
{
var sdt = ccntrl as StructuredDocumentTag;
var section = sdt.Title;
if (!sectionsList.Contains(section))
{
sdt.Remove();
}
}
writeToLog("Sections which will not be used in the document removed from template");
}
//--------------------------------------------------------------------------------------------------------------------------
//loop through all the fields in the document and replace content with values from control xml:
//replace word template variables/keywords with document values
if (documentKeyswordsList.Count != 0)
{
foreach (var key in documentKeyswordsList)
{
//split keywords and value
string[] keywordWithValues = key.Split('|');
keyword = keywordWithValues[keywordWithValues.Length - 2];
value = keywordWithValues[keywordWithValues.Length - 1];
//loop through all the fields in the document and replace content with values from control xml:
docTemplate.Range.Replace(keyword, value, false, false);
}
writeToLog("Document template variables replaced with document keywords and values");
//---------------------------------------------------------------------------------------------------------------------------
}
//replace word template variables/keywords with global document values
if (globalsKeywordsList.Count != 0)
{
foreach (var key in globalsKeywordsList)
{
//split keywords and value
string[] keywordWithValues = key.Split('|');
keyword = keywordWithValues[keywordWithValues.Length - 2];
value = keywordWithValues[keywordWithValues.Length - 1];
docTemplate.Range.Replace(keyword, value, false, false);
}
writeToLog("Document template variables replaced with global keywords and values");
}
//---------------------------------------------------------------------------------------------------------------------------
//replace word template paragraphs variables/keywords with document paragraphs values from control xml
if (paragraphKeywordsList.Count != 0)
{
foreach (var key in paragraphKeywordsList)
{
//split keywords and value
string[] keywordWithValues = key.Split('|');
keyword = keywordWithValues[keywordWithValues.Length - 2];
value = keywordWithValues[keywordWithValues.Length - 1];
//add a line break in paragraphs with line breaks
if (value.Contains(@"\n"))
{
string[] paragraphLines = value.Split('\n');
foreach (var line in paragraphLines)
{
string paragraphText = value.Replace(@"\n", ControlChar.LineBreak);
docTemplate.Range.Replace(keyword, paragraphText, false, false);
}
}
else
{
docTemplate.Range.Replace(keyword, value, false, false);
}
}
writeToLog("Document template paragraph variables replaced with paragraoh keywords and values");
}
//---------------------------------------------------------------------------------------------------------------------------
//Table building!!!!------------------------------------
//NB! THIS WILL ONLY WORK WITH TEMPLATE THAT HAS ONLY ONE TABLES!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
//select Docs/Doc/DocContent/table/Row
List<string> tableCellKeyList = new List<string>();
XmlNodeList rowNodes = documentNode.SelectNodes("pdbot:DocContent//pdbot:Table//pdbot:Row", nsmngr);
if (rowNodes.Count != 0)
{
Aspose.Words.Tables.Table table = null;
Aspose.Words.Tables.Row firstRow = null;
foreach (XmlNode rowNode in rowNodes)
{
//select the table to insert rows. 1 represents table no.
table = (Aspose.Words.Tables.Table)docTemplate.GetChild(NodeType.Table, 1, true);
//clone the first table row
firstRow = (Aspose.Words.Tables.Row)table.LastRow.Clone(true);
XmlNodeList cellKeyNodes = rowNode.SelectNodes("pdbot:CellKey", nsmngr);
foreach (XmlNode cellKeyNode in cellKeyNodes)
{
string cellKey = cellKeyNode["Key"].InnerText;
string cellValue = cellKeyNode["Value"].InnerText;
docTemplate.Range.Replace(cellKey, cellValue, false, false);
}
//Insert a new table row after the current row (template row):
table.AppendChild(firstRow);
}
//Delete the last template table row after the table is created
table.LastRow.Remove();
}
writeToLog("Tabel cell keys and keywords read from control xml and replaced in the document template");
//---------------------------------------------------------------------------------------------------------------------------
//produce document copies
foreach (var copy in copiesList)
{
//split copy values
string[] copyValues = copy.Split('|');
string name = copyValues[copyValues.Length - 4];
string stampText = copyValues[copyValues.Length - 3];
string slatten = copyValues[copyValues.Length - 2];
outputFile = copyValues[copyValues.Length - 1];
//manage pagebreaks problem - remove pagebreak and insert sectionbreak - new page
RemovePageBreaks(docTemplate);
////save document
saveDoc(docTemplate, outputFile);
////watermark and stamp final document
WaterMarkDocument(outputFile, hflDocumentPath, stampText, waterMarkings);
}
//---------------------------------------------------------------------------------------------------------------------------
}
}
catch (Exception e)
{
Console.WriteLine("Application failed with error " + e.Message + "." + e.StackTrace);
writeToLog("Error loading document template " + docTemplate.OriginalFileName.ToString() + "," + e.StackTrace);
Console.ReadKey();
}
}
}
catch (Exception e)
{
Console.WriteLine("Application failed with error: " + e.Message + "." + e.StackTrace);
writeToLog("Error reading control xml " + e.StackTrace);
Console.ReadKey();
}
//save pdbot control xml in the same temp folder as the produced documents
string outputfilename = outputFile.Remove(outputFile.Remove(outputFile.Length - 1).LastIndexOf('\\') + 1);
outputfilename = outputfilename + "pdbot_control.xml";
controlXMl.Save(outputfilename);
}
controlXMl = null;
//stopwatch.Stop();
//Console.WriteLine("Time used: " + stopwatch.Elapsed.Seconds + " Seconds");
//Console.ReadKey();
//---------------------------------------------------------------------------------------------------------------------------------------------
}
public void GetListLabels()
{
//ExStart
//ExFor:Document.UpdateListLabels()
//ExFor:Node.ToString(SaveFormat)
//ExFor:ListLabel
//ExFor:Paragraph.ListLabel
//ExFor:ListLabel.LabelValue
//ExFor:ListLabel.LabelString
//ExSummary:Shows how to extract the label of each paragraph in a list as a value or a string.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Lists.PrintOutAllLists.doc");
doc.UpdateListLabels();
int listParaCount = 1;
foreach (Paragraph paragraph in doc.GetChildNodes(NodeType.Paragraph, true))
{
// Find if we have the paragraph list. In our document our list uses plain arabic numbers,
// which start at three and ends at six.
if (paragraph.ListFormat.IsListItem)
{
Console.WriteLine("Paragraph #{0}", listParaCount);
// This is the text we get when actually getting when we output this node to text format.
// The list labels are not included in this text output. Trim any paragraph formatting characters.
string paragraphText = paragraph.ToString(SaveFormat.Text).Trim();
Console.WriteLine("Exported Text: " + paragraphText);
ListLabel label = paragraph.ListLabel;
// This gets the position of the paragraph in current level of the list. If we have a list with multiple level then this
// will tell us what position it is on that particular level.
Console.WriteLine("Numerical Id: " + label.LabelValue);
// Combine them together to include the list label with the text in the output.
Console.WriteLine("List label combined with text: " + label.LabelString + " " + paragraphText);
listParaCount++;
}
}
//ExEnd
}
public void NestedTablesUsingNodeConstructors()
{
Aspose.Words.Document doc = new Aspose.Words.Document();
// Create the outer table with three rows and four columns.
Table outerTable = CreateTable(doc, 3, 4, "Outer Table");
// Add it to the document body.
doc.FirstSection.Body.AppendChild(outerTable);
// Create another table with two rows and two columns.
Table innerTable = CreateTable(doc, 2, 2, "Inner Table");
// Add this table to the first cell of the outer table.
outerTable.FirstRow.FirstCell.AppendChild(innerTable);
doc.Save(ExDir + "Table.CreateNestedTable Out.doc");
Assert.AreEqual(2, doc.GetChildNodes(NodeType.Table, true).Count); // ExSkip
Assert.AreEqual(1, outerTable.FirstRow.FirstCell.Tables.Count); //ExSkip
Assert.AreEqual(16, outerTable.GetChildNodes(NodeType.Cell, true).Count); //ExSkip
Assert.AreEqual(4, innerTable.GetChildNodes(NodeType.Cell, true).Count); //ExSkip
}
public void CloneTable()
{
//ExStart
//ExId:CloneTable
//ExSummary:Shows how to make a clone of a table in the document and insert it after the original table.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Table.SimpleTable.doc");
// Retrieve the first table in the document.
Table table = (Table)doc.GetChild(NodeType.Table, 0, true);
// Create a clone of the table.
Table tableClone = (Table)table.Clone(true);
// Insert the cloned table into the document after the original
table.ParentNode.InsertAfter(tableClone, table);
// Insert an empty paragraph between the two tables or else they will be combined into one
// upon save. This has to do with document validation.
table.ParentNode.InsertAfter(new Paragraph(doc), table);
doc.Save(ExDir + "Table.CloneTableAndInsert Out.doc");
//ExEnd
// Verify that the table was cloned and inserted properly.
Assert.AreEqual(2, doc.GetChildNodes(NodeType.Table, true).Count);
Assert.AreEqual(table.Range.Text, tableClone.Range.Text);
//ExStart
//ExId:CloneTableRemoveContent
//ExSummary:Shows how to remove all content from the cells of a cloned table.
foreach (Cell cell in tableClone.GetChildNodes(NodeType.Cell, true))
cell.RemoveAllChildren();
//ExEnd
Assert.AreEqual(String.Empty, tableClone.ToString(SaveFormat.Text).Trim());
}
public void CombineTables()
{
//ExStart
//ExFor:Table
//ExFor:Cell.CellFormat
//ExFor:CellFormat.Borders
//ExFor:Table.Rows
//ExFor:Table.FirstRow
//ExFor:CellFormat.ClearFormatting
//ExId:CombineTables
//ExSummary:Shows how to combine the rows from two tables into one.
// Load the document.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Table.Document.doc");
// Get the first and second table in the document.
// The rows from the second table will be appended to the end of the first table.
Table firstTable = (Table)doc.GetChild(NodeType.Table, 0, true);
Table secondTable = (Table)doc.GetChild(NodeType.Table, 1, true);
// Append all rows from the current table to the next.
// Due to the design of tables even tables with different cell count and widths can be joined into one table.
while (secondTable.HasChildNodes)
firstTable.Rows.Add(secondTable.FirstRow);
// Remove the empty table container.
secondTable.Remove();
doc.Save(ExDir + "Table.CombineTables Out.doc");
//ExEnd
Assert.AreEqual(1, doc.GetChildNodes(NodeType.Table, true).Count);
Assert.AreEqual(9, doc.FirstSection.Body.Tables[0].Rows.Count);
Assert.AreEqual(42, doc.FirstSection.Body.Tables[0].GetChildNodes(NodeType.Cell, true).Count);
}
public void InsertTableFromHtml()
{
//ExStart
//ExId:InsertTableFromHtml
//ExSummary:Shows how to insert a table in a document from a string containing HTML tags.
Aspose.Words.Document doc = new Aspose.Words.Document();
DocumentBuilder builder = new DocumentBuilder(doc);
// Insert the table from HTML. Note that AutoFitSettings does not apply to tables
// inserted from HTML.
builder.InsertHtml("<table>" +
"<tr>" +
"<td>Row 1, Cell 1</td>" +
"<td>Row 1, Cell 2</td>" +
"</tr>" +
"<tr>" +
"<td>Row 2, Cell 2</td>" +
"<td>Row 2, Cell 2</td>" +
"</tr>" +
"</table>");
doc.Save(ExDir + "DocumentBuilder.InsertTableFromHtml Out.doc");
//ExEnd
// Verify the table was constructed properly.
Assert.AreEqual(1, doc.GetChildNodes(NodeType.Table, true).Count);
Assert.AreEqual(2, doc.GetChildNodes(NodeType.Row, true).Count);
Assert.AreEqual(4, doc.GetChildNodes(NodeType.Cell, true).Count);
}
public void DisplayContentOfTables()
{
//ExStart
//ExFor:Table
//ExFor:Row.Cells
//ExFor:Table.Rows
//ExFor:Cell
//ExFor:Row
//ExFor:RowCollection
//ExFor:CellCollection
//ExFor:NodeCollection.IndexOf(Node)
//ExSummary:Shows how to iterate through all tables in the document and display the content from each cell.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Table.Document.doc");
// Here we get all tables from the Document node. You can do this for any other composite node
// which can contain block level nodes. For example you can retrieve tables from header or from a cell
// containing another table (nested tables).
NodeCollection tables = doc.GetChildNodes(NodeType.Table, true);
// Iterate through all tables in the document
foreach (Table table in tables)
{
// Get the index of the table node as contained in the parent node of the table
int tableIndex = table.ParentNode.ChildNodes.IndexOf(table);
Console.WriteLine("Start of Table {0}", tableIndex);
// Iterate through all rows in the table
foreach (Row row in table.Rows)
{
int rowIndex = table.Rows.IndexOf(row);
Console.WriteLine("\tStart of Row {0}", rowIndex);
// Iterate through all cells in the row
foreach (Cell cell in row.Cells)
{
int cellIndex = row.Cells.IndexOf(cell);
// Get the plain text content of this cell.
string cellText = cell.ToString(SaveFormat.Text).Trim();
// Print the content of the cell.
Console.WriteLine("\t\tContents of Cell:{0} = \"{1}\"", cellIndex, cellText);
}
//Console.WriteLine();
Console.WriteLine("\tEnd of Row {0}", rowIndex);
}
Console.WriteLine("End of Table {0}", tableIndex);
Console.WriteLine();
}
//ExEnd
Assert.Greater(tables.Count, 0);
}
public void ExtractImagesToFiles()
{
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Image.SampleImages.doc");
NodeCollection shapes = doc.GetChildNodes(NodeType.Shape, true);
int imageIndex = 0;
foreach (Shape shape in shapes)
{
if (shape.HasImage)
{
string imageFileName = string.Format(
"Image.ExportImages.{0} Out{1}", imageIndex, FileFormatUtil.ImageTypeToExtension(shape.ImageData.ImageType));
shape.ImageData.Save(ExDir + imageFileName);
imageIndex++;
}
}
}
public void DeleteAllImagesPreOrder()
{
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Image.SampleImages.doc");
Assert.AreEqual(6, doc.GetChildNodes(NodeType.Shape, true).Count);
//ExStart
//ExFor:Node.NextPreOrder
//ExSummary:Shows how to delete all images from a document using pre-order tree traversal.
Aspose.Words.Node curNode = doc;
while (curNode != null)
{
Aspose.Words.Node nextNode = curNode.NextPreOrder(doc);
if (curNode.NodeType.Equals(NodeType.Shape))
{
Shape shape = (Shape)curNode;
// Several shape types can have an image including image shapes and OLE objects.
if (shape.HasImage)
shape.Remove();
}
curNode = nextNode;
}
//ExEnd
Assert.AreEqual(1, doc.GetChildNodes(NodeType.Shape, true).Count);
doc.Save(ExDir + "Image.DeleteAllImagesPreOrder Out.doc");
}
public void DetectBulletedParagraphs()
{
Aspose.Words.Document doc = new Aspose.Words.Document();
//ExStart
//ExFor:Paragraph.ListFormat
//ExFor:ListFormat.IsListItem
//ExFor:CompositeNode.GetText
//ExFor:List.ListId
//ExSummary:Finds and outputs all paragraphs in a document that are bulleted or numbered.
NodeCollection paras = doc.GetChildNodes(NodeType.Paragraph, true);
foreach (Paragraph para in paras)
{
if (para.ListFormat.IsListItem)
{
Console.WriteLine(string.Format("*** A paragraph belongs to list {0}", para.ListFormat.List.ListId));
Console.WriteLine(para.GetText());
}
}
//ExEnd
}
public void DeleteAllImages()
{
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Image.SampleImages.doc");
Assert.AreEqual(6, doc.GetChildNodes(NodeType.Shape, true).Count);
//ExStart
//ExFor:Shape.HasImage
//ExFor:Node.Remove
//ExSummary:Shows how to delete all images from a document.
// Here we get all shapes from the document node, but you can do this for any smaller
// node too, for example delete shapes from a single section or a paragraph.
NodeCollection shapes = doc.GetChildNodes(NodeType.Shape, true);
// We cannot delete shape nodes while we enumerate through the collection.
// One solution is to add nodes that we want to delete to a temporary array and delete afterwards.
ArrayList shapesToDelete = new ArrayList();
foreach (Shape shape in shapes)
{
// Several shape types can have an image including image shapes and OLE objects.
if (shape.HasImage)
shapesToDelete.Add(shape);
}
// Now we can delete shapes.
foreach (Shape shape in shapesToDelete)
shape.Remove();
//ExEnd
Assert.AreEqual(1, doc.GetChildNodes(NodeType.Shape, true).Count);
doc.Save(ExDir + "Image.DeleteAllImages Out.doc");
}
public void InsertTableUsingNodeConstructors()
{
//ExStart
//ExFor:Table
//ExFor:Row
//ExFor:Row.RowFormat
//ExFor:RowFormat
//ExFor:Cell
//ExFor:Cell.CellFormat
//ExFor:CellFormat
//ExFor:CellFormat.Shading
//ExFor:Cell.FirstParagraph
//ExId:InsertTableUsingNodeConstructors
//ExSummary:Shows how to insert a table using the constructors of nodes.
Aspose.Words.Document doc = new Aspose.Words.Document();
// We start by creating the table object. Note how we must pass the document object
// to the constructor of each node. This is because every node we create must belong
// to some document.
Table table = new Table(doc);
// Add the table to the document.
doc.FirstSection.Body.AppendChild(table);
// Here we could call EnsureMinimum to create the rows and cells for us. This method is used
// to ensure that the specified node is valid, in this case a valid table should have at least one
// row and one cell, therefore this method creates them for us.
// Instead we will handle creating the row and table ourselves. This would be the best way to do this
// if we were creating a table inside an algorthim for example.
Row row = new Row(doc);
row.RowFormat.AllowBreakAcrossPages = true;
table.AppendChild(row);
// We can now apply any auto fit settings.
table.AutoFit(AutoFitBehavior.FixedColumnWidths);
// Create a cell and add it to the row
Cell cell = new Cell(doc);
cell.CellFormat.Shading.BackgroundPatternColor = Color.LightBlue;
cell.CellFormat.Width = 80;
// Add a paragraph to the cell as well as a new run with some text.
cell.AppendChild(new Paragraph(doc));
cell.FirstParagraph.AppendChild(new Run(doc, "Row 1, Cell 1 Text"));
// Add the cell to the row.
row.AppendChild(cell);
// We would then repeat the process for the other cells and rows in the table.
// We can also speed things up by cloning existing cells and rows.
row.AppendChild(cell.Clone(false));
row.LastCell.AppendChild(new Paragraph(doc));
row.LastCell.FirstParagraph.AppendChild(new Run(doc, "Row 1, Cell 2 Text"));
doc.Save(ExDir + "Table.InsertTableUsingNodes Out.doc");
//ExEnd
Assert.AreEqual(1, doc.GetChildNodes(NodeType.Table, true).Count);
Assert.AreEqual(1, doc.GetChildNodes(NodeType.Row, true).Count);
Assert.AreEqual(2, doc.GetChildNodes(NodeType.Cell, true).Count);
Assert.AreEqual("Row 1, Cell 1 Text\r\nRow 1, Cell 2 Text", doc.FirstSection.Body.Tables[0].ToString(SaveFormat.Text).Trim());
}
public void GetAllFonts()
{
//ExStart
//ExFor:Run
//ExSummary:Gets all fonts used in a document.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Font.Names.doc");
// Select all runs in the document.
NodeCollection runs = doc.GetChildNodes(NodeType.Run, true);
// Use a hashtable so we will keep only unique font names.
Hashtable fontNames = new Hashtable();
foreach (Run run in runs)
{
// This adds an entry into the hashtable.
// The key is the font name. The value is null, we don't need the value.
fontNames[run.Font.Name] = null;
}
// There are two fonts used in this document.
Console.WriteLine("Font Count: " + fontNames.Count);
//ExEnd
// Verify the font count is correct.
Assert.AreEqual(2, fontNames.Count);
}
public void ChangeStyleName()
{
//ExStart
//ExFor:Font.StyleName
//ExSummary:Shows how to use style name to find text formatted with a specific character style and apply different character style.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Font.StyleName.doc");
// Select all run nodes in the document.
NodeCollection runs = doc.GetChildNodes(NodeType.Run, true);
// Loop through every run node.
foreach (Run run in runs)
{
// If the character style of the run is what we want, do what we need. Change the style in this case.
// Note that names of built in styles could be different in documents
// created by Microsoft Word versions for different languages.
if (run.Font.StyleName.Equals("Emphasis"))
run.Font.StyleName = "Strong";
}
doc.Save(ExDir + "Font.StyleName Out.doc");
//ExEnd
}
public void ReplaceTextboxesWithImages()
{
//ExStart
//ExFor:WrapSide
//ExFor:ShapeBase.WrapSide
//ExFor:NodeCollection
//ExFor:CompositeNode.InsertAfter(Node, Node)
//ExFor:NodeCollection.ToArray
//ExSummary:Shows how to replace all textboxes with images.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Shape.ReplaceTextboxesWithImages.doc");
// This gets a live collection of all shape nodes in the document.
NodeCollection shapeCollection = doc.GetChildNodes(NodeType.Shape, true);
// Since we will be adding/removing nodes, it is better to copy all collection
// into a fixed size array, otherwise iterator will be invalidated.
Aspose.Words.Node[] shapes = shapeCollection.ToArray();
foreach (Shape shape in shapes)
{
// Filter out all shapes that we don't need.
if (shape.ShapeType.Equals(ShapeType.TextBox))
{
// Create a new shape that will replace the existing shape.
Shape image = new Shape(doc, ShapeType.Image);
// Load the image into the new shape.
image.ImageData.SetImage(ExDir + "Hammer.wmf");
// Make new shape's position to match the old shape.
image.Left = shape.Left;
image.Top = shape.Top;
image.Width = shape.Width;
image.Height = shape.Height;
image.RelativeHorizontalPosition = shape.RelativeHorizontalPosition;
image.RelativeVerticalPosition = shape.RelativeVerticalPosition;
image.HorizontalAlignment = shape.HorizontalAlignment;
image.VerticalAlignment = shape.VerticalAlignment;
image.WrapType = shape.WrapType;
image.WrapSide = shape.WrapSide;
// Insert new shape after the old shape and remove the old shape.
shape.ParentNode.InsertAfter(image, shape);
shape.Remove();
}
}
doc.Save(ExDir + "Shape.ReplaceTextboxesWithImages Out.doc");
//ExEnd
}
//ExStart
//ExFor:Font.Hidden
//ExFor:Paragraph.Accept
//ExFor:DocumentVisitor.VisitParagraphStart(Aspose.Words.Paragraph)
//ExFor:DocumentVisitor.VisitFormField(Aspose.Words.Fields.FormField)
//ExFor:DocumentVisitor.VisitTableEnd(Aspose.Words.Tables.Table)
//ExFor:DocumentVisitor.VisitCellEnd(Aspose.Words.Tables.Cell)
//ExFor:DocumentVisitor.VisitRowEnd(Aspose.Words.Tables.Row)
//ExFor:DocumentVisitor.VisitSpecialChar(Aspose.Words.SpecialChar)
//ExFor:DocumentVisitor.VisitGroupShapeStart(Aspose.Words.Drawing.GroupShape)
//ExFor:DocumentVisitor.VisitShapeStart(Aspose.Words.Drawing.Shape)
//ExFor:DocumentVisitor.VisitCommentStart(Aspose.Words.Comment)
//ExFor:DocumentVisitor.VisitFootnoteStart(Aspose.Words.Footnote)
//ExFor:SpecialChar
//ExFor:Node.Accept
//ExFor:Paragraph.ParagraphBreakFont
//ExFor:Table.Accept
//ExSummary:Implements the Visitor Pattern to remove all content formatted as hidden from the document.
public void RemoveHiddenContentFromDocument()
{
// Open the document we want to remove hidden content from.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Font.Hidden.doc");
// Create an object that inherits from the DocumentVisitor class.
RemoveHiddenContentVisitor hiddenContentRemover = new RemoveHiddenContentVisitor();
// This is the well known Visitor pattern. Get the model to accept a visitor.
// The model will iterate through itself by calling the corresponding methods
// on the visitor object (this is called visiting).
// We can run it over the entire the document like so:
doc.Accept(hiddenContentRemover);
// Or we can run it on only a specific node.
Paragraph para = (Paragraph)doc.GetChild(NodeType.Paragraph, 4, true);
para.Accept(hiddenContentRemover);
// Or over a different type of node like below.
Table table = (Table)doc.GetChild(NodeType.Table, 0, true);
table.Accept(hiddenContentRemover);
doc.Save(ExDir + "Font.Hidden Out.doc");
Assert.AreEqual(13, doc.GetChildNodes(NodeType.Paragraph, true).Count); //ExSkip
Assert.AreEqual(1, doc.GetChildNodes(NodeType.Table, true).Count); //ExSkip
}
public void InsertFootnote()
{
//ExStart
//ExFor:Footnote
//ExFor:FootnoteType
//ExFor:DocumentBuilder.InsertFootnote(FootnoteType,string)
//ExSummary:Shows how to add a footnote to a paragraph in the document using DocumentBuilder.
Aspose.Words.Document doc = new Aspose.Words.Document();
DocumentBuilder builder = new DocumentBuilder(doc);
builder.Write("Some text");
builder.InsertFootnote(FootnoteType.Footnote, "Footnote text.");
//ExEnd
Assert.AreEqual("Footnote text.", doc.GetChildNodes(NodeType.Footnote, true)[0].ToString(SaveFormat.Text).Trim());
}
public void ChangeStyleIdentifier()
{
//ExStart
//ExFor:Font.StyleIdentifier
//ExFor:StyleIdentifier
//ExSummary:Shows how to use style identifier to find text formatted with a specific character style and apply different character style.
Aspose.Words.Document doc = new Aspose.Words.Document(ExDir + "Font.StyleIdentifier.doc");
// Select all run nodes in the document.
NodeCollection runs = doc.GetChildNodes(NodeType.Run, true);
// Loop through every run node.
foreach (Run run in runs)
{
// If the character style of the run is what we want, do what we need. Change the style in this case.
// Note that using StyleIdentifier we can identify a built-in style regardless
// of the language of Microsoft Word used to create the document.
if (run.Font.StyleIdentifier.Equals(StyleIdentifier.Emphasis))
run.Font.StyleIdentifier = StyleIdentifier.Strong;
}
doc.Save(ExDir + "Font.StyleIdentifier Out.doc");
//ExEnd
}
public void BuildNestedTableUsingDocumentBuilder()
{
//ExStart
//ExFor:Cell.FirstParagraph
//ExId:BuildNestedTableUsingDocumentBuilder
//ExSummary:Shows how to insert a nested table using DocumentBuilder.
Aspose.Words.Document doc = new Aspose.Words.Document();
DocumentBuilder builder = new DocumentBuilder(doc);
// Build the outer table.
Cell cell = builder.InsertCell();
builder.Writeln("Outer Table Cell 1");
builder.InsertCell();
builder.Writeln("Outer Table Cell 2");
// This call is important in order to create a nested table within the first table
// Without this call the cells inserted below will be appended to the outer table.
builder.EndTable();
// Move to the first cell of the outer table.
builder.MoveTo(cell.FirstParagraph);
// Build the inner table.
builder.InsertCell();
builder.Writeln("Inner Table Cell 1");
builder.InsertCell();
builder.Writeln("Inner Table Cell 2");
builder.EndTable();
doc.Save(ExDir + "DocumentBuilder.InsertNestedTable Out.doc");
//ExEnd
Assert.AreEqual(2, doc.GetChildNodes(NodeType.Table, true).Count);
Assert.AreEqual(4, doc.GetChildNodes(NodeType.Cell, true).Count);
Assert.AreEqual(1, cell.Tables[0].Count);
Assert.AreEqual(2, cell.Tables[0].FirstRow.Cells.Count);
}
