public static void SplitDocumentToPages(string docName)
{
string folderName = Path.GetDirectoryName(docName);
string fileName = Path.GetFileNameWithoutExtension(docName);
string extensionName = Path.GetExtension(docName);
string outFolder = Path.Combine(folderName, "Out");
Console.WriteLine("Processing document: " + fileName + extensionName);
Document doc = new Document(docName);
// Create and attach collector to the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// This will build layout model and collect necessary information.
doc.UpdatePageLayout();
// Split nodes in the document into separate pages.
DocumentPageSplitter splitter = new DocumentPageSplitter(layoutCollector);
// Save each page to the disk as a separate document.
for (int page = 1; page <= doc.PageCount; page++)
{
Document pageDoc = splitter.GetDocumentOfPage(page);
pageDoc.Save(Path.Combine(outFolder, string.Format("{0} - page{1} Out{2}", fileName, page, extensionName)));
}
// Detach the collector from the document.
layoutCollector.Document = null;
}
public static void SplitDocumentToPages(string docName)
{
string folderName = Path.GetDirectoryName(docName);
string fileName = Path.GetFileNameWithoutExtension(docName);
string extensionName = Path.GetExtension(docName);
string outFolder = Path.Combine(folderName, "Out");
Console.WriteLine("Processing document: " + fileName + extensionName);
Document doc = new Document(docName);
// Create and attach collector to the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// This will build layout model and collect necessary information.
doc.UpdatePageLayout();
// Split nodes in the document into separate pages.
DocumentPageSplitter splitter = new DocumentPageSplitter(layoutCollector);
// Save each page to the disk as a separate document.
for (int page = 1; page <= doc.PageCount; page++)
{
Document pageDoc = splitter.GetDocumentOfPage(page);
pageDoc.Save(Path.Combine(outFolder, string.Format("{0} - page{1} Out{2}", fileName, page, extensionName)));
}
// Detach the collector from the document.
layoutCollector.Document = null;
}
public static void Run()
{
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_WorkingWithDocument();
Document doc = new Document(dataDir + "TestFile.docx");
// Create and attach collector before the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// This will build layout model and collect necessary information.
doc.UpdatePageLayout();
// Print the details of each document node including the page numbers.
foreach (Node node in doc.FirstSection.Body.GetChildNodes(NodeType.Any, true))
{
Console.WriteLine(" --------- ");
Console.WriteLine("NodeType: " + Node.NodeTypeToString(node.NodeType));
Console.WriteLine("Text: \"" + node.ToString(SaveFormat.Text).Trim() + "\"");
Console.WriteLine("Page Start: " + layoutCollector.GetStartPageIndex(node));
Console.WriteLine("Page End: " + layoutCollector.GetEndPageIndex(node));
Console.WriteLine(" --------- ");
Console.WriteLine();
}
// Detatch the collector from the document.
layoutCollector.Document = null;
Console.WriteLine("\nFound the page numbers of all nodes successfully.");
}
public static void Main()
{
string dataDir = Path.GetFullPath("../../../Data/");
Document doc = new Document(dataDir + "TestFile.docx");
// Create and attach collector before the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// This will build layout model and collect necessary information.
doc.UpdatePageLayout();
// Print the details of each document node including the page numbers.
foreach (Node node in doc.FirstSection.Body.GetChildNodes(NodeType.Any, true))
{
Console.WriteLine(" --------- ");
Console.WriteLine("NodeType: " + Node.NodeTypeToString(node.NodeType));
Console.WriteLine("Text: \"" + node.ToString(SaveFormat.Text).Trim() + "\"");
Console.WriteLine("Page Start: " + layoutCollector.GetStartPageIndex(node));
Console.WriteLine("Page End: " + layoutCollector.GetEndPageIndex(node));
Console.WriteLine(" --------- ");
Console.WriteLine();
}
// Detatch the collector from the document.
layoutCollector.Document = null;
Console.ReadLine();
}
public static void Main()
{
// This a document that we want to add an image and custom text for each page without using the header or footer.
Document doc = new Document(gDataDir + "TestFile.doc");
// Create and attach collector before the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// Images in a document are added to paragraphs, so to add an image to every page we need to find at any paragraph
// belonging to each page.
IEnumerator enumerator = doc.SelectNodes("//Body/Paragraph").GetEnumerator();
// Loop through each document page.
for (int page = 1; page <= doc.PageCount; page++)
{
while (enumerator.MoveNext())
{
// Check if the current paragraph belongs to the target page.
Paragraph paragraph = (Paragraph)enumerator.Current;
if (layoutCollector.GetStartPageIndex(paragraph) == page)
{
AddImageToPage(paragraph, page);
break;
}
}
}
doc.Save(gDataDir + "TestFile Out.docx");
}
public void AddImageToEachPage()
{
Document doc = new Document(MyDir + "Document.docx");
// Create and attach collector before the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// Images in a document are added to paragraphs to add an image to every page we need
// to find at any paragraph belonging to each page.
IEnumerator enumerator = doc.SelectNodes("// Body/Paragraph").GetEnumerator();
for (int page = 1; page <= doc.PageCount; page++)
{
while (enumerator.MoveNext())
{
// Check if the current paragraph belongs to the target page.
Paragraph paragraph = (Paragraph)enumerator.Current;
if (layoutCollector.GetStartPageIndex(paragraph) == page)
{
AddImageToPage(paragraph, page, ImagesDir);
break;
}
}
}
// If we need to save the document as a PDF or image, call UpdatePageLayout() method.
doc.UpdatePageLayout();
doc.Save(ArtifactsDir + "WorkingWithImages.AddImageToEachPage.docx");
}
public static void Main()
{
string dataDir = Path.GetFullPath("../../../Data/");
Document doc = new Document(dataDir + "TestFile.docx");
// Create and attach collector before the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// This will build layout model and collect necessary information.
doc.UpdatePageLayout();
// Print the details of each document node including the page numbers.
foreach (Node node in doc.FirstSection.Body.GetChildNodes(NodeType.Any, true))
{
Console.WriteLine(" --------- ");
Console.WriteLine("NodeType: " + Node.NodeTypeToString(node.NodeType));
Console.WriteLine("Text: \"" + node.ToString(SaveFormat.Text).Trim() + "\"");
Console.WriteLine("Page Start: " + layoutCollector.GetStartPageIndex(node));
Console.WriteLine("Page End: " + layoutCollector.GetEndPageIndex(node));
Console.WriteLine(" --------- ");
Console.WriteLine();
}
// Detatch the collector from the document.
layoutCollector.Document = null;
Console.ReadLine();
}
static void Main(string[] args)
{
ApplyLicense();
Document doc = new Document("eSignature.Test.02.docx");
//Find the text between <<>> and insert bookmark
doc.Range.Replace(new Regex(@"\<<.*?\>>"), "", new FindReplaceOptions()
{
ReplacingCallback = new FindAndInsertBookmark()
});
LayoutCollector layoutCollector = new LayoutCollector(doc);
LayoutEnumerator layoutEnumerator = new LayoutEnumerator(doc);
//Display the left top position of text between angle bracket.
foreach (Bookmark bookmark in doc.Range.Bookmarks)
{
if (bookmark.Name.StartsWith("bookmark_"))
{
layoutEnumerator.Current = layoutCollector.GetEntity(bookmark.BookmarkStart);
Console.WriteLine(" --> Left : " + layoutEnumerator.Rectangle.Left + " Top : " + layoutEnumerator.Rectangle.Top);
}
}
doc.Save("20.10.docx");
System.Diagnostics.Process.Start("20.10.docx");
}
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 static void Run()
{
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_WorkingWithDocument();
Document doc = new Document(dataDir + "TestFile.docx");
// Create and attach collector before the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// This will build layout model and collect necessary information.
doc.UpdatePageLayout();
// Print the details of each document node including the page numbers.
foreach (Node node in doc.FirstSection.Body.GetChildNodes(NodeType.Any, true))
{
Console.WriteLine(" --------- ");
Console.WriteLine("NodeType: " + Node.NodeTypeToString(node.NodeType));
Console.WriteLine("Text: \"" + node.ToString(SaveFormat.Text).Trim() + "\"");
Console.WriteLine("Page Start: " + layoutCollector.GetStartPageIndex(node));
Console.WriteLine("Page End: " + layoutCollector.GetEndPageIndex(node));
Console.WriteLine(" --------- ");
Console.WriteLine();
}
// Detatch the collector from the document.
layoutCollector.Document = null;
Console.WriteLine("\nFound the page numbers of all nodes successfully.");
}
public static void Main()
{
// This a document that we want to add an image and custom text for each page without using the header or footer.
Document doc = new Document(gDataDir + "TestFile.doc");
// Create and attach collector before the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// Images in a document are added to paragraphs, so to add an image to every page we need to find at any paragraph
// belonging to each page.
IEnumerator enumerator = doc.SelectNodes("//Body/Paragraph").GetEnumerator();
// Loop through each document page.
for (int page = 1; page <= doc.PageCount; page++)
{
while (enumerator.MoveNext())
{
// Check if the current paragraph belongs to the target page.
Paragraph paragraph = (Paragraph)enumerator.Current;
if (layoutCollector.GetStartPageIndex(paragraph) == page)
{
AddImageToPage(paragraph, page);
break;
}
}
}
doc.Save(gDataDir + "TestFile Out.docx");
}
public static void Run()
{
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_WorkingWithImages();
// This a document that we want to add an image and custom text for each page without using the header or footer.
Document doc = new Document(dataDir + "TestFile.doc");
// Create and attach collector before the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// Images in a document are added to paragraphs, so to add an image to every page we need to find at any paragraph
// belonging to each page.
IEnumerator enumerator = doc.SelectNodes("//Body/Paragraph").GetEnumerator();
// Loop through each document page.
for (int page = 1; page <= doc.PageCount; page++)
{
while (enumerator.MoveNext())
{
// Check if the current paragraph belongs to the target page.
Paragraph paragraph = (Paragraph)enumerator.Current;
if (layoutCollector.GetStartPageIndex(paragraph) == page)
{
AddImageToPage(paragraph, page, dataDir);
break;
}
}
}
doc.Save(dataDir + "TestFile Out.docx");
Console.WriteLine("\nInserted images on each page of the document successfully.\nFile saved at " + dataDir + "TestFile Out.docx");
}
public static void Run()
{
// The path to the documents directory.
string dataDir = RunExamples.GetDataDir_WorkingWithImages();
// This a document that we want to add an image and custom text for each page without using the header or footer.
Document doc = new Document(dataDir + "TestFile.doc");
// Create and attach collector before the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// Images in a document are added to paragraphs, so to add an image to every page we need to find at any paragraph
// belonging to each page.
IEnumerator enumerator = doc.SelectNodes("//Body/Paragraph").GetEnumerator();
// Loop through each document page.
for (int page = 1; page <= doc.PageCount; page++)
{
while (enumerator.MoveNext())
{
// Check if the current paragraph belongs to the target page.
Paragraph paragraph = (Paragraph)enumerator.Current;
if (layoutCollector.GetStartPageIndex(paragraph) == page)
{
AddImageToPage(paragraph, page, dataDir);
break;
}
}
}
doc.Save(dataDir + "TestFile Out.docx");
Console.WriteLine("\nInserted images on each page of the document successfully.\nFile saved at " + dataDir + "TestFile Out.docx");
}
/// <summary>
/// Creates a new instance from the supplied Aspose.Words.Document class.
/// </summary>
/// <param name="document">A document whose page layout model to enumerate.</param>
/// <remarks><para>If page layout model of the document hasn't been built the enumerator calls <see cref="Document.UpdatePageLayout"/> to build it.</para>
/// <para>Whenever document is updated and new page layout model is created, a new RenderedDocument instance must be used to access the changes.</para></remarks>
public RenderedDocument(Document doc)
{
mLayoutCollector = new LayoutCollector(doc);
mEnumerator = new LayoutEnumerator(doc);
ProcessLayoutElements(this);
LinkLayoutMarkersToNodes(doc);
CollectLinesAndAddToMarkers();
}
/// <summary>
/// Creates a new instance from the supplied Document class.
/// </summary>
/// <param name="document">A document whose page layout model to enumerate.</param>
/// <remarks><para>If page layout model of the document hasn't been built the enumerator calls <see cref="Document.UpdatePageLayout"/> to build it.</para>
/// <para>Whenever document is updated and new page layout model is created, a new RenderedDocument instance must be used to access the changes.</para></remarks>
public RenderedDocument(Document doc)
{
mLayoutCollector = new LayoutCollector(doc);
mEnumerator = new LayoutEnumerator(doc);
ProcessLayoutElements(this);
LinkLayoutMarkersToNodes(doc);
CollectLinesAndAddToMarkers();
}
public static PageNumberFinder Create(Document document)
{
LayoutCollector layoutCollector = new LayoutCollector(document);
document.UpdatePageLayout();
PageNumberFinder pageNumberFinder = new PageNumberFinder(layoutCollector);
pageNumberFinder.SplitNodesAcrossPages();
return(pageNumberFinder);
}
/// <summary>
/// Change hyperlinks to _page{pageNumber}_{...}
/// </summary>
/// <param name="doc"></param>
private void PrepareInternalLinks(Document doc, LayoutCollector lc)
{
foreach (var field in doc.Range.Fields)
{
try
{
if (field.Type == FieldType.FieldHyperlink)
{
var link = (FieldHyperlink)field;
if (!string.IsNullOrEmpty(link.SubAddress))
{
var bookmark = doc.Range.Bookmarks[link.SubAddress];
if (bookmark == null)
{
continue;
}
var pageNumber = lc.GetStartPageIndex(bookmark.BookmarkStart);
if (pageNumber == 0)
{
continue;
}
var name = $"_page{pageNumber}{link.SubAddress}";
bookmark.Name = name;
link.SubAddress = name;
}
}
else if (field.Type == FieldType.FieldRef)
{
var link = (FieldRef)field;
var bookmark = doc.Range.Bookmarks[link.BookmarkName];
if (bookmark == null)
{
continue;
}
var pageNumber = lc.GetStartPageIndex(bookmark.BookmarkStart);
if (pageNumber == 0)
{
continue;
}
var name = $"_page{pageNumber}{link.BookmarkName}";
bookmark.Name = name;
link.BookmarkName = name;
}
}
catch (Exception ex)
{
Console.WriteLine(ex.Message);
}
}
var filename = Config.Configuration.OutputDirectory + Opts.FolderName + "/" +
Path.GetFileNameWithoutExtension(Opts.FileName) + "_links.docx";
doc.Save(filename);
}
void IImageSavingCallback.ImageSaving(ImageSavingArgs args)
{
args.KeepImageStreamOpen = false;
Assert.True(args.IsImageAvailable);
Console.WriteLine($"{args.Document.OriginalFileName.Split('\\').Last()} Image #{++mImageCount}");
LayoutCollector layoutCollector = new LayoutCollector(args.Document);
Console.WriteLine($"\tOn page:\t{layoutCollector.GetStartPageIndex(args.CurrentShape)}");
Console.WriteLine($"\tDimensions:\t{args.CurrentShape.Bounds.ToString()}");
Console.WriteLine($"\tAlignment:\t{args.CurrentShape.VerticalAlignment}");
Console.WriteLine($"\tWrap type:\t{args.CurrentShape.WrapType}");
Console.WriteLine($"Output filename:\t{args.ImageFileName}\n");
}
public HttpResponseMessage Search(RequestData request)
{
Opts.AppName = "Viewer";
Opts.FileName = request.fileName;
Opts.FolderName = request.folderName;
Opts.MethodName = "Search";
try
{
if (Opts.FolderName.Contains(".."))
{
throw new Exception("Break-in attempt");
}
if (string.IsNullOrEmpty(request.searchQuery))
{
return(Request.CreateResponse(HttpStatusCode.OK, new int[] { }));
}
var doc = new Document(Opts.WorkingFileName);
var lst = new HashSet <int>();
var findings = new AsposeWordsSearch.FindCallback();
var options = new FindReplaceOptions()
{
ReplacingCallback = findings,
Direction = FindReplaceDirection.Forward,
MatchCase = false
};
doc.Range.Replace(new Regex(request.searchQuery, RegexOptions.IgnoreCase), "", options);
var lc = new LayoutCollector(doc);
foreach (var mathchedNode in findings.MatchedNodes)
{
foreach (var node in mathchedNode.Value.Select(x => x.MatchNode))
{
var pageNumber = lc.GetStartPageIndex(node);
lst.Add(pageNumber);
}
}
return(Request.CreateResponse(HttpStatusCode.OK, lst));
}
catch (Exception ex)
{
return(ExceptionResponse(ex));
}
}
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);
}
public static void SplitDocumentToPages(string docName)
{
string folderName = Path.GetDirectoryName(docName);
string fileName = Path.GetFileNameWithoutExtension(docName);
string extensionName = Path.GetExtension(docName);
string outFolder = Path.Combine(folderName, "_out_");
Document doc = new Document(docName);
// Create and attach collector to the document before page layout is built.
LayoutCollector layoutCollector = new LayoutCollector(doc);
// This will build layout model and collect necessary information.
doc.UpdatePageLayout();
// Split nodes in the document into separate pages.
DocumentPageSplitter splitter = new DocumentPageSplitter(layoutCollector);
HtmlSaveOptions option = new HtmlSaveOptions();
option.ExportHeadersFootersMode = ExportHeadersFootersMode.PerSection;
option.PrettyFormat = true;
option.UseAntiAliasing = true;
// Save each page to the disk as a separate document.
for (int page = 1; page <= doc.PageCount; page++)
{
Document pageDoc = splitter.GetDocumentOfPage(page);
NodeCollection paras = pageDoc.GetChildNodes(NodeType.Paragraph, true);
foreach (Paragraph para in paras)
{
if (para.GetText().Contains("Evaluation Only. Created with Aspose.Words. Copyright 2003-2016 Aspose Pty Ltd."))
{
paras.Remove(para);
pageDoc.UpdatePageLayout();
}
}
var name = Path.Combine(outFolder, string.Format("{0}{1}{2}", fileName, page, ".html"));
pageDoc.Save(name, option);
}
// Detach the collector from the document.
layoutCollector.Document = null;
}
public void PageBreakBefore(bool pageBreakBefore)
{
//ExStart
//ExFor:ParagraphFormat.PageBreakBefore
//ExSummary:Shows how to create paragraphs with page breaks at the beginning.
Document doc = new Document();
DocumentBuilder builder = new DocumentBuilder(doc);
// Set this flag to "true" to apply a page break to each paragraph's beginning
// that the document builder will create under this ParagraphFormat configuration.
// The first paragraph will not receive a page break.
// Leave this flag as "false" to start each new paragraph on the same page
// as the previous, provided there is sufficient space.
builder.ParagraphFormat.PageBreakBefore = pageBreakBefore;
builder.Writeln("Paragraph 1.");
builder.Writeln("Paragraph 2.");
LayoutCollector layoutCollector = new LayoutCollector(doc);
ParagraphCollection paragraphs = doc.FirstSection.Body.Paragraphs;
if (pageBreakBefore)
{
Assert.AreEqual(1, layoutCollector.GetStartPageIndex(paragraphs[0]));
Assert.AreEqual(2, layoutCollector.GetStartPageIndex(paragraphs[1]));
}
else
{
Assert.AreEqual(1, layoutCollector.GetStartPageIndex(paragraphs[0]));
Assert.AreEqual(1, layoutCollector.GetStartPageIndex(paragraphs[1]));
}
doc.Save(ArtifactsDir + "ParagraphFormat.PageBreakBefore.docx");
//ExEnd
doc = new Document(ArtifactsDir + "ParagraphFormat.PageBreakBefore.docx");
paragraphs = doc.FirstSection.Body.Paragraphs;
Assert.AreEqual(pageBreakBefore, paragraphs[0].ParagraphFormat.PageBreakBefore);
Assert.AreEqual(pageBreakBefore, paragraphs[1].ParagraphFormat.PageBreakBefore);
}
public HttpResponseMessage DocumentInfo(RequestData request)
{
Opts.AppName = "Viewer";
Opts.FileName = request.fileName;
Opts.FolderName = request.folderName;
Opts.MethodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
try
{
if (Opts.FolderName.Contains(".."))
{
throw new Exception("Break-in attempt");
}
var doc = new Document(Opts.WorkingFileName);
var lc = new LayoutCollector(doc);
PrepareInternalLinks(doc, lc);
var lst = new List <PageView>(doc.PageCount);
for (int i = 0; i < doc.PageCount; i++)
{
var pageInfo = doc.GetPageInfo(i);
var size = pageInfo.GetSizeInPixels(1, 72);
lst.Add(new PageView()
{
width = size.Width,
height = size.Height,
angle = 0,
number = i + 1
});
}
return(Request.CreateResponse(HttpStatusCode.OK, new PageParametersResponse(request.fileName, lst, PrepareNavigationPaneList(doc, lc))));
}
catch (Exception ex)
{
return(ExceptionResponse(ex));
}
}
/// <summary>
/// Initializes a new instance of the <see cref="PageNumberFinder"/> class.
/// </summary>
/// <param name="collector">A collector instance that has layout model records for the document.</param>
public PageNumberFinder(LayoutCollector collector)
{
this.collector = collector;
}
/// <summary>
/// Initializes new instance of this class. This method splits the document into sections so that each page
/// begins and ends at a section boundary. It is recommended not to modify the document afterwards.
/// </summary>
/// <param name="collector">A collector instance which has layout model records for the document.</param>
public DocumentPageSplitter(LayoutCollector collector)
{
mPageNumberFinder = new PageNumberFinder(collector);
mPageNumberFinder.SplitNodesAcrossPages();
}
public void LayoutCollector()
{
//ExStart
//ExFor:Layout.LayoutCollector
//ExFor:Layout.LayoutCollector.#ctor(Document)
//ExFor:Layout.LayoutCollector.Clear
//ExFor:Layout.LayoutCollector.Document
//ExFor:Layout.LayoutCollector.GetEndPageIndex(Node)
//ExFor:Layout.LayoutCollector.GetEntity(Node)
//ExFor:Layout.LayoutCollector.GetNumPagesSpanned(Node)
//ExFor:Layout.LayoutCollector.GetStartPageIndex(Node)
//ExFor:Layout.LayoutEnumerator.Current
//ExSummary:Shows how to see the page spans of nodes.
// Open a blank document and create a DocumentBuilder
Document doc = new Document();
DocumentBuilder builder = new DocumentBuilder(doc);
// Create a LayoutCollector object for our document that will have information about the nodes we placed
LayoutCollector layoutCollector = new LayoutCollector(doc);
// The document itself is a node that contains everything, which currently spans 0 pages
Assert.AreEqual(doc, layoutCollector.Document);
Assert.AreEqual(0, layoutCollector.GetNumPagesSpanned(doc));
// Populate the document with sections and page breaks
builder.Write("Section 1");
builder.InsertBreak(BreakType.PageBreak);
builder.InsertBreak(BreakType.PageBreak);
doc.AppendChild(new Section(doc));
doc.LastSection.AppendChild(new Body(doc));
builder.MoveToDocumentEnd();
builder.Write("Section 2");
builder.InsertBreak(BreakType.PageBreak);
builder.InsertBreak(BreakType.PageBreak);
// The collected layout data won't automatically keep up with the real document contents
Assert.AreEqual(0, layoutCollector.GetNumPagesSpanned(doc));
// After we clear the layout collection and update it, the layout entity collection will be populated with up-to-date information about our nodes
// The page span for the document now shows 5, which is what we would expect after placing 4 page breaks
layoutCollector.Clear();
doc.UpdatePageLayout();
Assert.AreEqual(5, layoutCollector.GetNumPagesSpanned(doc));
// We can also see the start/end pages of any other node, and their overall page spans
NodeCollection nodes = doc.GetChildNodes(NodeType.Any, true);
foreach (Node node in nodes)
{
Console.WriteLine($"-> NodeType.{node.NodeType}: ");
Console.WriteLine(
$"\tStarts on page {layoutCollector.GetStartPageIndex(node)}, ends on page {layoutCollector.GetEndPageIndex(node)}," +
$" spanning {layoutCollector.GetNumPagesSpanned(node)} pages.");
}
// We can iterate over the layout entities using a LayoutEnumerator
LayoutEnumerator layoutEnumerator = new LayoutEnumerator(doc);
Assert.AreEqual(LayoutEntityType.Page, layoutEnumerator.Type);
// The LayoutEnumerator can traverse the collection of layout entities like a tree
// We can also point it to any node's corresponding layout entity like this
layoutEnumerator.Current = layoutCollector.GetEntity(doc.GetChild(NodeType.Paragraph, 1, true));
Assert.AreEqual(LayoutEntityType.Span, layoutEnumerator.Type);
Assert.AreEqual("¶", layoutEnumerator.Text);
//ExEnd
}
public void LayoutCollector()
{
//ExStart
//ExFor:Layout.LayoutCollector
//ExFor:Layout.LayoutCollector.#ctor(Document)
//ExFor:Layout.LayoutCollector.Clear
//ExFor:Layout.LayoutCollector.Document
//ExFor:Layout.LayoutCollector.GetEndPageIndex(Node)
//ExFor:Layout.LayoutCollector.GetEntity(Node)
//ExFor:Layout.LayoutCollector.GetNumPagesSpanned(Node)
//ExFor:Layout.LayoutCollector.GetStartPageIndex(Node)
//ExFor:Layout.LayoutEnumerator.Current
//ExSummary:Shows how to see the the ranges of pages that a node spans.
Document doc = new Document();
LayoutCollector layoutCollector = new LayoutCollector(doc);
// Call the "GetNumPagesSpanned" method to count how many pages the content of our document spans.
// Since the document is empty, that number of pages is currently zero.
Assert.AreEqual(doc, layoutCollector.Document);
Assert.AreEqual(0, layoutCollector.GetNumPagesSpanned(doc));
// Populate the document with 5 pages of content.
DocumentBuilder builder = new DocumentBuilder(doc);
builder.Write("Section 1");
builder.InsertBreak(BreakType.PageBreak);
builder.InsertBreak(BreakType.PageBreak);
builder.InsertBreak(BreakType.SectionBreakEvenPage);
builder.Write("Section 2");
builder.InsertBreak(BreakType.PageBreak);
builder.InsertBreak(BreakType.PageBreak);
// Before the layout collector, we need to call the "UpdatePageLayout" method to give us
// an accurate figure for any layout-related metric, such as the page count.
Assert.AreEqual(0, layoutCollector.GetNumPagesSpanned(doc));
layoutCollector.Clear();
doc.UpdatePageLayout();
Assert.AreEqual(5, layoutCollector.GetNumPagesSpanned(doc));
// We can see the numbers of the start and end pages of any node and their overall page spans.
NodeCollection nodes = doc.GetChildNodes(NodeType.Any, true);
foreach (Node node in nodes)
{
Console.WriteLine($"-> NodeType.{node.NodeType}: ");
Console.WriteLine(
$"\tStarts on page {layoutCollector.GetStartPageIndex(node)}, ends on page {layoutCollector.GetEndPageIndex(node)}," +
$" spanning {layoutCollector.GetNumPagesSpanned(node)} pages.");
}
// We can iterate over the layout entities using a LayoutEnumerator.
LayoutEnumerator layoutEnumerator = new LayoutEnumerator(doc);
Assert.AreEqual(LayoutEntityType.Page, layoutEnumerator.Type);
// The LayoutEnumerator can traverse the collection of layout entities like a tree.
// We can also apply it to any node's corresponding layout entity.
layoutEnumerator.Current = layoutCollector.GetEntity(doc.GetChild(NodeType.Paragraph, 1, true));
Assert.AreEqual(LayoutEntityType.Span, layoutEnumerator.Type);
Assert.AreEqual("¶", layoutEnumerator.Text);
//ExEnd
}
/// <summary>
/// word生成html字符串
/// </summary>
/// <param name="path">word路径</param>
/// <returns></returns>
public override string ToHTML(string path)
{
//openxml引用
//string htmlPath=WmlToHtmlConverterHelper.ConvertToHtml(path, this.FilePath);
//aspose引用 api网址http://www.aspose.com
if (!File.Exists(path))
{
return(string.Empty);
}
//PageNumberFinder
Document doc = new Document(path);
var paperSize = doc.FirstSection.PageSetup.PaperSize.ToString(); //纸张大小
var pageCount = doc.PageCount; //获得页数
doc.MailMerge.UseNonMergeFields = false;
doc.MailMerge.UseWholeParagraphAsRegion = true;
//doc.MailMergeSettings.ViewMergedData = false;
//doc.MailMergeSettings.LinkToQuery = true;
//doc.MailMergeSettings.MailAsAttachment = true;
//html设置
ws.HtmlSaveOptions option = new ws.HtmlSaveOptions(SaveFormat.Html);
option.ExportHeadersFootersMode = ws.ExportHeadersFootersMode.PerSection;
option.PrettyFormat = true;
option.UseAntiAliasing = true;
option.ExportTocPageNumbers = false;
option.ExportRoundtripInformation = true;
//option.ExportListLabels = ExportListLabels.AsInlineText;
string name = Path.GetFileNameWithoutExtension(path);
//生成图片保存路径
option.ImagesFolderAlias = MapPathReverse(path);
//Path.Combine(Path.GetDirectoryName(path), name);
//string.Format("/Resource/emw/UserFile/{0}/", name);
var savePath = Path.Combine(this.FilePath, name + "\\");
if (!Directory.Exists(savePath))
{
Directory.CreateDirectory(savePath);
}
LayoutCollector layoutCollector = new LayoutCollector(doc);
// 构建布局模型,收集必要的信息。
doc.UpdatePageLayout();
// 节点在文档分割成单独的页面。
DocumentPageSplitter splitter = new DocumentPageSplitter(layoutCollector);
//for (int page = 1; page <= doc.PageCount; page++)
//{
// Document pageDoc = splitter.GetDocumentOfPage(page);
// NodeCollection paras = pageDoc.GetChildNodes(NodeType.Paragraph, true);
// foreach (Paragraph para in paras)
// {
// if (para.GetText().Contains("Evaluation Only. Created with Aspose.Words. Copyright 2003-2016 Aspose Pty Ltd."))
// {
// paras.Remove(para);
// }
// }
// var pageFileName = Path.Combine(savePath, string.Format("{0}-page{1}{2}", name, page, ".html"));
// pageDoc.Save(pageFileName,option);
//}
// 从文档中分离收集器。
layoutCollector.Document = null;
//html保存地址
string htmlPath = savePath + name + ".html";
doc.Save(htmlPath, option);
XElement xhtml = XElement.Load(htmlPath);
var idCounter = 1000000;
foreach (var d in xhtml.Descendants())
{
if (d.Name.LocalName == "head" || d.Name.LocalName == "meta" || d.Name.LocalName == "title" || d.Name.LocalName == "body")
{
continue;
}
string idName = d.Name.LocalName + "-" + idCounter.ToString().Substring(1);
XAttribute id = new XAttribute("data-uniqid", idName);
if (d.Attribute("id") == null)
{
d.Add(id);
}
idCounter++;
}
File.WriteAllText(htmlPath, xhtml.ToString(), Encoding.UTF8);
string htmlString = xhtml.ToString();// File.ReadAllText(htmlPath);
string jsonStr = JsonConvert.SerializeObject(new { pageCount = pageCount, paperSize = paperSize, htmlString = htmlString, path = path });
return(jsonStr);
}
/// <summary>
/// Initializes new instance of this class. This method splits the document into sections so that each page
/// begins and ends at a section boundary. It is recommended not to modify the document afterwards.
/// </summary>
/// <param name="collector">A collector instance which has layout model records for the document.</param>
public DocumentPageSplitter(LayoutCollector collector)
{
mPageNumberFinder = new PageNumberFinder(collector);
mPageNumberFinder.SplitNodesAcrossPages();
}
/// <summary>
/// Initializes new instance of this class.
/// </summary>
/// <param name="collector">A collector instance which has layout model records for the document.</param>
public PageNumberFinder(LayoutCollector collector)
{
mCollector = collector;
}
private static DocCompareModel Compare(Document original, Document current)
{
var docCompareModel = new DocCompareModel();
var pages = new List <DocumentPage>();
original.Compare(current, "Apose", DateTime.Now);
LayoutCollector layout = new LayoutCollector(original);
foreach (Revision revision in original.Revisions)
{
if (revision.RevisionType == RevisionType.Insertion)
{
var index = layout.GetStartPageIndex(revision.ParentNode);
if (index == 0)
{
continue;
}
if (pages.Where(i => i.PageNumber == index).ToList().Any())
{
var page = pages.Find(i => i.PageNumber == index);
page.Added++;
}
else
{
pages.Add(new DocumentPage
{
PageNumber = index,
Added = 1
});
}
continue;
}
if (revision.RevisionType == RevisionType.Deletion)
{
var index = layout.GetStartPageIndex(revision.ParentNode);
if (index == 0)
{
continue;
}
if (pages.Where(i => i.PageNumber == index).ToList().Any())
{
var page = pages.Find(i => i.PageNumber == index);
page.Deleted++;
}
else
{
pages.Add(new DocumentPage
{
PageNumber = index,
Deleted = 1
});
}
}
}
docCompareModel.Pages = pages;
using (var stream = new MemoryStream())
{
original.Save(stream, SaveFormat.Docx);
var doc = new Document(stream);
ImageSaveOptions options = new ImageSaveOptions(SaveFormat.Jpeg)
{
PageCount = 1
};
var urls = new Dictionary <int, string>();
docCompareModel.PageCount = doc.PageCount;
for (int i = 0; i < doc.PageCount; i++)
{
options.PageIndex = i;
using (var imgStream = new MemoryStream())
{
doc.Save(imgStream, options);
var base64Image = new Base64Image
{
FileContents = imgStream.ToArray(),
ContentType = "image/png"
};
urls.Add(i, base64Image.ToString());
}
}
docCompareModel.PageImages = urls;
}
return(docCompareModel);
}
private void FillUpWithEmptyLines()
{
try
{
int NoOfSections = doc.Sections.Count;
int currentSection = 0;
foreach (Section section in doc.Sections)
{
DocumentBuilder builder = new DocumentBuilder(doc);
Node startNode = GenerateStartNode(section);
Node node;
int NoOfParagraphs = section.Body.ChildNodes.Count;
int currentParagraph = 0;
for (node = startNode; node != null; node = node.NextSibling)
{
if (node.NodeType == NodeType.Paragraph)
{
builder.MoveTo(node);
Paragraph para = (Paragraph)node;
// string test = para.GetText();
Aspose.Words.Font font;
ParagraphFormat paragraphFormat;
InitFormats(para, ref builder, out font, out paragraphFormat);
Paragraph paraToInsert;
int paraRuns;
bool isEndOfFile;
if (para.GetText().IndexOf(ControlChar.PageBreakChar) >= 0)
{
LayoutCollector layoutCollector = new LayoutCollector(doc);
doc.UpdatePageLayout();
int origPage = layoutCollector.GetEndPageIndex(node);
int newpage = origPage;
while (newpage == origPage)
{
paraToInsert = (Paragraph)node;
isEndOfFile = paraToInsert == section.Body.LastParagraph;
paraRuns = paraToInsert.Runs.Count;
if (paraRuns != 0 && !isEndOfFile)
{
builder.MoveTo(paraToInsert.Runs[paraRuns - 1]);
}
else
{
builder.MoveTo(paraToInsert);
}
builder.Writeln(ControlChar.Tab);
if (builder.ListFormat.IsListItem)
{
builder.ListFormat.RemoveNumbers();
}
layoutCollector = new LayoutCollector(doc);
doc.UpdatePageLayout();
node = node.NextSibling;
newpage = layoutCollector.GetEndPageIndex(node);
}
Node nodeToRemove = node.PreviousSibling;
Paragraph paraToRemove = (Paragraph)nodeToRemove;
string TextToRemove = paraToRemove.GetText();
if (TextToRemove == "\t\r")
{
paraToInsert = (Paragraph)node;
nodeToRemove.Remove();
isEndOfFile = paraToInsert == section.Body.LastParagraph;
paraRuns = paraToInsert.Runs.Count;
if (paraRuns != 0 && !isEndOfFile)
{
builder.MoveTo(paraToInsert.Runs[paraRuns - 1]);
}
else if (paraRuns != 0 && isEndOfFile)
{
builder.MoveTo(paraToInsert.Runs[paraRuns]);
}
else
{
builder.MoveTo(paraToInsert);
}
builder.Write(ControlChar.Tab);
}
else
{
node = node.PreviousSibling;
node.NextSibling.Remove();
}
}
else
{
builder.MoveTo(node);
builder.Write(ControlChar.Tab);
}
}
else if (node.NodeType == NodeType.Table)
{
Table table = (Table)node;
LayoutCollector layoutCollector = new LayoutCollector(doc);
foreach (Row row in table.Rows)
{
foreach (Cell cell in row.Cells)
{
Node tblStartNode = cell.FirstChild;
for (Node tblNode = tblStartNode; tblNode != null; tblNode = tblNode.NextSibling)
{
builder.MoveTo(tblNode);
if (tblNode.NodeType == NodeType.Paragraph)
{
Paragraph tblPara = (Paragraph)tblNode;
Aspose.Words.Font font;
ParagraphFormat paragraphFormat;
InitFormats(tblPara, ref builder, out font, out paragraphFormat);
builder.MoveTo(tblNode);
builder.Write(ControlChar.Tab);
}
}
}
}
}
currentParagraph++;
double dblKeszultseg = ((70.0 / Convert.ToDouble(NoOfSections)) /
Convert.ToDouble(NoOfParagraphs)) * Convert.ToDouble(currentParagraph);
Program.mainWindow.updateProgress(30 + Convert.ToInt32(Math.Round(dblKeszultseg)));
}
currentSection++;
}
}
catch (Exception ex)
{
Log.AddLog("Adding empty lines error.\r\n" + ex.Message, true);
}
}
