I've got C# code for creating a document, I want to write the same in C++/CLI.
private void HelloWorld(string documentFileName)
{
// Create a Wordprocessing document.
using (WordprocessingDocument myDoc =
WordprocessingDocument.Create(documentFileName,
WordprocessingDocumentType.Document))
{
// Add a new main document part.
MainDocumentPart mainPart = myDoc.AddMainDocumentPart();
//Create Document tree for simple document.
mainPart.Document = new Document();
//Create Body (this element contains
//other elements that we want to include
Body body = new Body();
//Create paragraph
Paragraph paragraph = new Paragraph();
Run run_paragraph = new Run();
// we want to put that text into the output document
Text text_paragraph = new Text("Hello World!");
//Append elements appropriately.
run_paragraph.Append(text_paragraph);
paragraph.Append(run_paragraph);
body.Append(paragraph);
mainPart.Document.Append(body);
// Save changes to the main document part.
mainPart.Document.Save();
}
}
Also please suggest me any links where I can find C++/CLI example for OpenXML SDK
Here's a direct translation:
private:
void HelloWorld(String^ documentFileName)
{
msclr::auto_handle<WordprocessingDocument> myDoc(
WordprocessingDocument::Create(
documentFileName, WordprocessingDocumentType::Document
)
);
MainDocumentPart^ mainPart = myDoc->AddMainDocumentPart();
mainPart->Document = gcnew Document;
Body^ body = gcnew Body;
Paragraph^ paragraph = gcnew Paragraph;
Run^ run_paragraph = gcnew Run;
Text^ text_paragraph = gcnew Text(L"Hello World!");
run_paragraph->Append(text_paragraph);
paragraph->Append(run_paragraph);
body->Append(paragraph);
mainPart->Document->Append(body);
mainPart->Document->Save();
}
msclr::auto_handle<> should generally be considered more idiomatic than try..finally, just as std::shared_ptr<> and std::unique_ptr<> are in C++.
I take it you have tried something? I don't have access to a compiler
http://en.wikipedia.org/wiki/C%2B%2B/CLI should get you started.
If you wonder about translating the using construct (good question, had you asked it!), I suggest something along the following lines (note the try {} finally { delete ... } idom)
private:
void HelloWorld(String^ documentFileName)
{
// Create a Wordprocessing document.
WordprocessingDocument ^myDoc = WordprocessingDocument::Create(documentFileName, WordprocessingDocumentType::Document);
try
{
// Add a new main document part.
MainDocumentPart mainPart = myDoc::AddMainDocumentPart();
//Create Document tree for simple document.
mainPart->Document = gcnew Document();
//Create Body (this element contains
//other elements that we want to include
Body body = gcnew Body();
//Create paragraph
Paragraph paragraph = gcnew Paragraph();
Run run_paragraph = gcnew Run();
// we want to put that text into the output document
Text text_paragraph = gcnew Text("Hello World!");
//Append elements appropriately.
run_paragraph->Append(text_paragraph);
paragraph->Append(run_paragraph);
body->Append(paragraph);
mainPart->Document->Append(body);
// Save changes to the main document part.
mainPart->Document->Save();
} finally
{
delete myDoc;
}
}
I want to repeat I have no compiler available at the moment, so it may be rough around the edges, but should provide some information nonetheless
OpenXML SDK C++ Examples
The syntax is basically the same. "new" needs to be replaced by gcnew, the "." by -> (e.g. body.Append(paragraph) will be body->Append(paragraph). The tricky part will be the "using" directive. To do it the C++ way, you need some kind of smart pointer that "deletes" the object at the end of the block (with delete meaning calling the IDisposable interface) - this is called RAII.
Related
How do I add/append HTML content in an existing .docx file, using OpenXML in asp.net C#?
In an existing word file, I want to append the html content part.
For example:
In this example, I want to place "This is a Heading" inside a H1 tag.
Here its my code
protected void Button1_Click(object sender, EventArgs e)
{
try
{
using (WordprocessingDocument doc = WordprocessingDocument.Open(#"C:\Users\admin\Downloads\WordGenerator\WordGenerator\FTANJS.docx", true))
{
string altChunkId = "myId";
MainDocumentPart mainDocPart = doc.MainDocumentPart;
var run = new Run(new Text("test"));
var p = new Paragraph(new ParagraphProperties(new Justification() { Val = JustificationValues.Center }), run);
var body = mainDocPart.Document.Body;
body.Append(p);
MemoryStream ms = new MemoryStream(Encoding.UTF8.GetBytes("<html><head></head><body><h1>HELLO</h1></body></html>"));
// Uncomment the following line to create an invalid word document.
// MemoryStream ms = new MemoryStream(Encoding.UTF8.GetBytes("<h1>HELLO</h1>"));
// Create alternative format import part.
AlternativeFormatImportPart formatImportPart =
mainDocPart.AddAlternativeFormatImportPart(
AlternativeFormatImportPartType.Html, altChunkId);
//ms.Seek(0, SeekOrigin.Begin);
// Feed HTML data into format import part (chunk).
formatImportPart.FeedData(ms);
AltChunk altChunk = new AltChunk();
altChunk.Id = altChunkId;
mainDocPart.Document.Body.Append(altChunk);
}
}
catch (Exception ex)
{
ex.ToString ();
}
}
Add HTML content as Chunk should work, and you are almost there.
If I understand the question properly, this code should work.
//insert html content to H1 tag
using(WordprocessingDocument fDocx = WordprocessingDocument.Open(sDocxFile,true))
{
string sChunkID = "myhtmlID";
AlternativeFormatImportPart oChunk = fDocx.MainDocumentPart.AddAlternativeFormatImportPart(AlternativeFormatImportPartType.Html, sChunkID);
using(FileStream fs = File.Open(sHtml,FileMode.OpenOrCreate))
{
oChunk.FeedData(fs);
}
AltChunk oAltChunk = new AltChunk();
oAltChunk.Id =sChunkID ;
//insert html to the tag of 'H1' and remove H1.
Body body = fDocx.MainDocumentPart.Document.Body;
Paragraph theParagraph = body.Descendants<Paragraph>().Where(p => p.InnerText == "H1").FirstOrDefault();
theParagraph.InsertAfterSelf<AltChunk>(oAltChunk);
theParagraph.Remove();
fDocx.MainDocumentPart.Document.Save();
}
The short answer is "You can't add HTML to a docx file".
Docx is an open format defined here. If you're using the Microsoft version they have a number of extensions.
In any case, the file contains XML, not HTML and you can't simply add HTML to a docx file. There are styles and formatting objects and pointers that all need to be updated.
If you need to modify a docx file and don't want to do a lot of research and a lot of coding, you'll need to find an existing library to work with.
I'm really having trouble in editing bookmarks in a Word template using Document.Format.OpenXML and then saving it to a new PDF file.
I cannot use Microsoft.Word.Interop as it gives a COM error on the server.
My code is this:
public static void CreateWordDoc(string templatePath, string destinationPath, Dictionary<string, dynamic> dictionary)
{
byte[] byteArray = File.ReadAllBytes(templatePath);
using (MemoryStream stream = new MemoryStream())
{
stream.Write(byteArray, 0, (int)byteArray.Length);
using (WordprocessingDocument wordDoc = WordprocessingDocument.Open(stream, true))
{
var bookmarks = (from bm in wordDoc.MainDocumentPart.Document.Body.Descendants<BookmarkStart>()
select bm).ToList();
foreach (BookmarkStart mark in bookmarks)
{
if (mark.Name != "Table" && mark.Name != "_GoBack")
{
UpdateBookmark(dictionary, mark);//Not doing anything
}
else if (mark.Name != "Table")
{
// CreateTable(dictionary, wordDoc, mark);
}
}
File.WriteAllBytes("D:\\RohitDocs\\newfile_rohitsingh.docx", stream.ToArray());
wordDoc.Close();
}
// Save the file with the new name
}
}
private static void UpdateBookmark(Dictionary<string, dynamic> dictionary, BookmarkStart mark)
{
string name = mark.Name;
string value = dictionary[name];
Run run = new Run(new Text(value));
RunProperties props = new RunProperties();
props.AppendChild(new FontSize() { Val = "20" });
run.RunProperties = props;
var paragraph = new DocumentFormat.OpenXml.Wordprocessing.Paragraph(run);
mark.Parent.InsertAfterSelf(paragraph);
paragraph.PreviousSibling().Remove();
mark.Remove();
}
I was trying to replace bookmarks with my text but the UpdateBookmark method doesn't work. I'm writing stream and saving it because I thought if bookmarks are replaced then I can save it to another file.
I think you want to make sure that when you reference mark.Parent that you are getting the correct instance that you are expecting.
Once you get a reference to the correct Paragraph element where your content should go, use the following code to add/swap the run.
// assuming you have a reference to a paragraph called "p"
p.AppendChild<Run>(new Run(new Text(content)) { RunProperties = props });
// and here is some code to remove a run
p.RemoveChild<Run>(run);
To answers the second part of your question, when I did a similar project a few years ago we used iTextSharp to create PDFs from Docx. It worked very well and the API was easy to grok. We even added password encryption and embedded watermarks to the PDFs.
ok, old question is gone and this is new one:
#JasonPlutext, we decided to do it the way you suggested. custom xml looks like:
<DATA>
<BLOCK>
<FNAME>Test</FNAME>
<LNAME>Test1</LNAME>
</BLOCK>
<PICTURE>
<SIG> domain\username</SIG>
</PICTURE>
</DATA>
Text controls are binded: $rowBlock.FNAME, $rowBlock.LNAME and picture content control is $rowPicture.SIG.
text from xml is displayed, but there is no picture...
Picture is returned by ws (web service input parameter is domain\username from <sig> and picture is returned as byte[]).
//this is part of code where dealing with picture content control
picture[] pic = getPic("domain\username");
Paragraph tP = new Paragraph();
ParagraphProperties tParagraphProperties =
pControl.Descendants<ParagraphProperties>).FirstOrDefault();
tP.ParagraphProperties = (ParagraphProperties)tParagraphProperties.Clone();
...?...
Please suggest what to do next and how to bind picture?
thx
You could consider a slightly different approach.
You can bind a picture content control to an element in a custom xml part which contains a base64 encoded image.
If you do it this way, you can rely on Word to resolve the binding (ie update the image on the document surface with the one in the custom xml part). Or you can mimic what Word does yourself; docx4j.NET contains code to do that for you.
Doing it this way becomes a matter of just updating the custom xml part with the images you want.
Jason, i'm injecting base64 encoded image content as you said, but there is still no picture. in customXml folder of zip document, in item3.xml there is a base64 string inside tag, but in media folder there is only default image. don't know what's wrong... my procedure is:
//first, searching for drawing inside current processing control
`Drawing tDraw = pControl.Descendants<Drawing>().FirstOrDefault();
//if there is a drawing element, then clone control
OpenXmlElement tClone = (OpenXmlElement)pControl.Clone();
//then call method:
private static void insertPicture(OpenXmlElement pControl)
{
//WordprocessingDocument wordDoc = WordprocessingDocument.Open(dokument, true);
MainDocumentPart mainPart = dokument.MainDocumentPart;
CustomXmlPart customPart = mainPart.CustomXmlParts.FirstOrDefault();
//convert image into string
string picName = #"c:\temp\picasso.png";
System.IO.FileStream fileStream = System.IO.File.Open(picName, System.IO.FileMode.Open);
System.IO.BinaryReader br = new System.IO.BinaryReader(fileStream);
byte[] byteArea;
byteArea = br.ReadBytes(System.Convert.ToInt32(fileStream.Length));
string picString = System.Convert.ToBase64String(byteArea);
//Load the XML template
string DataString = iData["DATA"].ToString();
//Properties.Resources.XMLData;
XmlDocument xmlDoc = new XmlDocument();
xmlDoc.LoadXml(DataString);
//change the value
XmlNodeList xmlNode = xmlDoc.GetElementsByTagName("picture");
xmlNode[0].InnerText = picString;
//write the custom xml data into the customxmlpart
System.Xml.XmlTextWriter writer = new System.Xml.XmlTextWriter(customPart.GetStream(System.IO.FileMode.Create), System.Text.Encoding.UTF8);
writer.WriteRaw(xmlDoc.InnerXml);
writer.Flush();
writer.Close();
fileStream.Close();
br.Close();
mainPart.Document.Save();
//dokument.Close();
}
then append control to document
OpenXmlElement tC1 = pControl;
IEnumerable<Run> tEl1 = tClone.Descendants<Run>();
if (tEl1.Count() != 0)
{
foreach (OpenXmlElement tElement in tEl1.Reverse())
{
OpenXmlElement tClone1 = (OpenXmlElement)tElement.Clone();
tC1.InsertBeforeSelf(tClone1);
tC1 = tClone1;
}
}`
Can anybody show me how to apply Fontfamily/size to an AltChunk of Type
AlternativeFormatImportPartType.TextPlain
This is my Code, but I can´t figure out how to do this at all (even Google doesn´t help)
MainDocumentPart main = doc.MainDocumentPart;
string altChunkId = "AltChunkId" + Guid.NewGuid().ToString().Replace("-", "");
var chunk = main.AddAlternativeFormatImportPart
(AlternativeFormatImportPartType.TextPlain, altChunkId);
using (var mStream = new MemoryStream())
{
using (var writer = new StreamWriter(mStream))
{
writer.Write(value);
writer.Flush();
mStream.Position = 0;
chunk.FeedData(mStream);
}
}
var altChunk = new AltChunk();
altChunk.Id = altChunkId;
OpenXmlElement afterThat = null;
foreach (var para in main.Document.Body.Descendants<Paragraph>())
{
if (para.InnerText.Equals("Notizen:"))
{
afterThat = para;
}
}
main.Document.Body.InsertAfter(altChunk, afterThat);
if I do it this way I get "Courier New" with a Size of "10,5"
UPDATE
This is the working Solution I came up with:
Convert Plaintext to RTF, change the Fontfamily/size and apply it to the WordProcessingDocument!
public static string PlainToRtf(string value)
{
using (var rtf = new System.Windows.Forms.RichTextBox())
{
rtf.Text = value;
rtf.SelectAll();
rtf.SelectionFont = new System.Drawing.Font("Calibri", 10);
return rtf.Rtf;
}
}
var chunk = main.AddAlternativeFormatImportPart
(AlternativeFormatImportPartType.Rtf, altChunkId);
using (var mStream = new MemoryStream())
{
using (var writer = new StreamWriter(mStream))
{
var rtf = PlainToRtf(value);
writer.Write(rtf);
writer.Flush();
mStream.Position = 0;
chunk.FeedData(mStream);
}
}
//proceed with creating AltChunk and inserting it to the Document...
How to apply FontFamily/Size to AltChunk of Type [TextPlain]
I am afraid this is NOT possible, in any case, not with OpenXml SDK.
Why?
altChunk (Anchor for Imported External Content) object is further designed for importing content in the document. They are 'temporary' objects: it is a just a reference to an external content, that is incorporated "as is" in the document, and then, when the document will be opened and saved with Word, Word converts this external content in valid OpenXml content.
So you can't, for a newly created document, loop into the paragraphs in order to retrieve it and apply a style.
If you import rtf content for example, the style must be applied to rtf before importing it.
In case of plain text TextPlain (= Text file .txt), there is no style conversion (there is no style attached to the text file, you can change the font in NotePad, it will apply to all documents, this is an Application Level property).
And I can confirm that Word creates by default a style with "Courier New 10,5" to display the content of the file. I just tested.
What can I do?
Apply style after the document has been open/saved with Word. Note you will have to retreive the paragrap(s), or you could try to retrieve the style created in the document and change the font here. This link could help to achieve this:
How to: Apply a style to a paragraph in a word processing document (Open XML SDK).
Or maybe it exists(?) a registry key something Like this that you can change to change Word's default behavior on your computer. And even if it is, it doesn't solve the problem for newly created document which is opened the first time on the client.
Note from the OP:
I think a possible Solution to the Problem could be, converting the PlainText to RTF apply StyleInformation and then append it to WordProcessingDocument as AltChunk.
I totally agreed. Just note when he says apply StyleInformation, it means at rtf level.
I'm developing a web application with asp.net and I have a file called Template.docx that works like a template to generate other reports. Inside this Template.docx I have some MergeFields (Title, CustomerName, Content, Footer, etc) to replace for some dynamic content in C#.
I would like to know, how can I put a content in a mergefield in docx ?
I don't know if MergeFields is the right way to do this or if there is another way. If you can suggest me, I appreciate!
PS: I have openxml referenced in my web application.
Edits:
private MemoryStream LoadFileIntoStream(string fileName)
{
MemoryStream memoryStream = new MemoryStream();
using (FileStream fileStream = File.OpenRead(fileName))
{
memoryStream.SetLength(fileStream.Length);
fileStream.Read(memoryStream.GetBuffer(), 0, (int) fileStream.Length);
memoryStream.Flush();
fileStream.Close();
}
return memoryStream;
}
public MemoryStream GenerateWord()
{
string templateDoc = "C:\\temp\\template.docx";
string reportFileName = "C:\\temp\\result.docx";
var reportStream = LoadFileIntoStream(templateDoc);
// Copy a new file name from template file
//File.Copy(templateDoc, reportFileName, true);
// Open the new Package
Package pkg = Package.Open(reportStream, FileMode.Open, FileAccess.ReadWrite);
// Specify the URI of the part to be read
Uri uri = new Uri("/word/document.xml", UriKind.Relative);
PackagePart part = pkg.GetPart(uri);
XmlDocument xmlMainXMLDoc = new XmlDocument();
xmlMainXMLDoc.Load(part.GetStream(FileMode.Open, FileAccess.Read));
// replace some keys inside xml (it will come from database, it's just a test)
xmlMainXMLDoc.InnerXml = xmlMainXMLDoc.InnerXml.Replace("field_customer", "My Customer Name");
xmlMainXMLDoc.InnerXml = xmlMainXMLDoc.InnerXml.Replace("field_title", "Report of Documents");
xmlMainXMLDoc.InnerXml = xmlMainXMLDoc.InnerXml.Replace("field_content", "Content of Document");
// Open the stream to write document
StreamWriter partWrt = new StreamWriter(part.GetStream(FileMode.Open, FileAccess.Write));
//doc.Save(partWrt);
xmlMainXMLDoc.Save(partWrt);
partWrt.Flush();
partWrt.Close();
reportStream.Flush();
pkg.Close();
return reportStream;
}
PS: When I convert MemoryStream to a file, I got a corrupted file. Thanks!
I know this is an old post, but I could not get the accepted answer to work for me. The project linked would not even compile (which someone has already commented in that link). Also, it seems to use other Nuget packages like WPFToolkit.
So I'm adding my answer here in case someone finds it useful. This only uses the OpenXML SDK 2.5 and also the WindowsBase v4. This works on MS Word 2010 and later.
string sourceFile = #"C:\Template.docx";
string targetFile = #"C:\Result.docx";
File.Copy(sourceFile, targetFile, true);
using (WordprocessingDocument document = WordprocessingDocument.Open(targetFile, true))
{
// If your sourceFile is a different type (e.g., .DOTX), you will need to change the target type like so:
document.ChangeDocumentType(WordprocessingDocumentType.Document);
// Get the MainPart of the document
MainDocumentPart mainPart = document.MainDocumentPart;
var mergeFields = mainPart.RootElement.Descendants<FieldCode>();
var mergeFieldName = "SenderFullName";
var replacementText = "John Smith";
ReplaceMergeFieldWithText(mergeFields, mergeFieldName, replacementText);
// Save the document
mainPart.Document.Save();
}
private void ReplaceMergeFieldWithText(IEnumerable<FieldCode> fields, string mergeFieldName, string replacementText)
{
var field = fields
.Where(f => f.InnerText.Contains(mergeFieldName))
.FirstOrDefault();
if (field != null)
{
// Get the Run that contains our FieldCode
// Then get the parent container of this Run
Run rFldCode = (Run)field.Parent;
// Get the three (3) other Runs that make up our merge field
Run rBegin = rFldCode.PreviousSibling<Run>();
Run rSep = rFldCode.NextSibling<Run>();
Run rText = rSep.NextSibling<Run>();
Run rEnd = rText.NextSibling<Run>();
// Get the Run that holds the Text element for our merge field
// Get the Text element and replace the text content
Text t = rText.GetFirstChild<Text>();
t.Text = replacementText;
// Remove all the four (4) Runs for our merge field
rFldCode.Remove();
rBegin.Remove();
rSep.Remove();
rEnd.Remove();
}
}
What the code above does is basically this:
Identify the 4 Runs that make up the merge field named "SenderFullName".
Identify the Run that contains the Text element for our merge field.
Remove the 4 Runs.
Update the text property of the Text element for our merge field.
UPDATE
For anyone interested, here is a simple static class I used to help me with replacing merge fields.
Frank Fajardo's answer was 99% of the way there for me, but it is important to note that MERGEFIELDS can be SimpleFields or FieldCodes.
In the case of SimpleFields, the text runs displayed to the user in the document are children of the SimpleField.
In the case of FieldCodes, the text runs shown to the user are between the runs containing FieldChars with the Separate and the End FieldCharValues. Occasionally, several text containing runs exist between the Separate and End Elements.
The code below deals with these problems. Further details of how to get all the MERGEFIELDS from the document, including the header and footer is available in a GitHub repository at https://github.com/mcshaz/SimPlanner/blob/master/SP.DTOs/Utilities/OpenXmlExtensions.cs
private static Run CreateSimpleTextRun(string text)
{
Run returnVar = new Run();
RunProperties runProp = new RunProperties();
runProp.Append(new NoProof());
returnVar.Append(runProp);
returnVar.Append(new Text() { Text = text });
return returnVar;
}
private static void InsertMergeFieldText(OpenXmlElement field, string replacementText)
{
var sf = field as SimpleField;
if (sf != null)
{
var textChildren = sf.Descendants<Text>();
textChildren.First().Text = replacementText;
foreach (var others in textChildren.Skip(1))
{
others.Remove();
}
}
else
{
var runs = GetAssociatedRuns((FieldCode)field);
var rEnd = runs[runs.Count - 1];
foreach (var r in runs
.SkipWhile(r => !r.ContainsCharType(FieldCharValues.Separate))
.Skip(1)
.TakeWhile(r=>r!= rEnd))
{
r.Remove();
}
rEnd.InsertBeforeSelf(CreateSimpleTextRun(replacementText));
}
}
private static IList<Run> GetAssociatedRuns(FieldCode fieldCode)
{
Run rFieldCode = (Run)fieldCode.Parent;
Run rBegin = rFieldCode.PreviousSibling<Run>();
Run rCurrent = rFieldCode.NextSibling<Run>();
var runs = new List<Run>(new[] { rBegin, rCurrent });
while (!rCurrent.ContainsCharType(FieldCharValues.End))
{
rCurrent = rCurrent.NextSibling<Run>();
runs.Add(rCurrent);
};
return runs;
}
private static bool ContainsCharType(this Run run, FieldCharValues fieldCharType)
{
var fc = run.GetFirstChild<FieldChar>();
return fc == null
? false
: fc.FieldCharType.Value == fieldCharType;
}
You could try http://www.codeproject.com/KB/office/Fill_Mergefields.aspx which uses the Open XML SDK to do this.