My requirement is to make a custom document library where I can save document with versions.
Is there a way I can modify MS Word documents (.doc or .docx) using CKEditor on the go and save them somewhere in my server?
Suggestions regarding any other options is also acceptable.
I am not sure about .doc but for .docx, you can convert it to html in the following way...
You should implement OpenXml dlls for that. The dlls that you will require are
1. DocumentFormat.OpenXml.dll
2. OpenXmlPowerTools.dll
3. System.IO.Packaging.dll
Here is the working version of code snippets. The DocxToHtml.cs class
using System.IO;
using System.Linq;
using OpenXmlPowerTools;
using DocumentFormat.OpenXml.Packaging;
using System.Drawing.Imaging;
using System.Xml.Linq;
public class DocxToHtml
{
public string ConvertToHtml(string fullFilePath)
{
if (string.IsNullOrEmpty(fullFilePath) || Path.GetExtension(fullFilePath) != ".docx")
return "Unsupported format";
FileInfo fileInfo = new FileInfo(fullFilePath);
string htmlText = string.Empty;
try
{
htmlText = ParseDOCX(fileInfo);
}
catch (OpenXmlPackageException e)
{
if (e.ToString().Contains("Invalid Hyperlink"))
{
using (FileStream fs = new FileStream(fullFilePath, FileMode.OpenOrCreate, FileAccess.ReadWrite))
{
UriFixer.FixInvalidUri(fs, brokenUri => FixUri(brokenUri));
}
htmlText = ParseDOCX(fileInfo);
}
}
return htmlText;
}
private static string FixUri(string brokenUri)
{
string newURI = string.Empty;
if (brokenUri.Contains("mailto:"))
{
int mailToCount = "mailto:".Length;
brokenUri = brokenUri.Remove(0, mailToCount);
newURI = brokenUri;
}
else
{
newURI = " ";
}
return newURI;
}
private string ParseDOCX(FileInfo fileInfo)
{
byte[] byteArray = File.ReadAllBytes(fileInfo.FullName);
using (MemoryStream memoryStream = new MemoryStream())
{
memoryStream.Write(byteArray, 0, byteArray.Length);
using (WordprocessingDocument wDoc = WordprocessingDocument.Open(memoryStream, true))
{
int imageCounter = 0;
var pageTitle = fileInfo.FullName;
var part = wDoc.CoreFilePropertiesPart;
if (part != null)
pageTitle = (string)part.GetXDocument().Descendants(DC.title).FirstOrDefault() ?? fileInfo.FullName;
// TODO: Determine max-width from size of content area.
WmlToHtmlConverterSettings settings = new WmlToHtmlConverterSettings()
{
AdditionalCss = "body { margin: 1cm auto; max-width: 20cm; padding: 0; }",
PageTitle = pageTitle,
FabricateCssClasses = true,
CssClassPrefix = "pt-",
RestrictToSupportedLanguages = false,
RestrictToSupportedNumberingFormats = false,
ImageHandler = imageInfo =>
{
++imageCounter;
string extension = imageInfo.ContentType.Split('/')[1].ToLower();
ImageFormat imageFormat = null;
if (extension == "png")
imageFormat = ImageFormat.Png;
else if (extension == "gif")
imageFormat = ImageFormat.Gif;
else if (extension == "bmp")
imageFormat = ImageFormat.Bmp;
else if (extension == "jpeg")
imageFormat = ImageFormat.Jpeg;
else if (extension == "tiff")
{
// Convert tiff to gif.
extension = "gif";
imageFormat = ImageFormat.Gif;
}
else if (extension == "x-wmf")
{
extension = "wmf";
imageFormat = ImageFormat.Wmf;
}
// If the image format isn't one that we expect, ignore it,
// and don't return markup for the link.
if (imageFormat == null)
return null;
string base64 = null;
try
{
using (MemoryStream ms = new MemoryStream())
{
imageInfo.Bitmap.Save(ms, imageFormat);
var ba = ms.ToArray();
base64 = System.Convert.ToBase64String(ba);
}
}
catch (System.Runtime.InteropServices.ExternalException)
{ return null; }
ImageFormat format = imageInfo.Bitmap.RawFormat;
ImageCodecInfo codec = ImageCodecInfo.GetImageDecoders().First(c => c.FormatID == format.Guid);
string mimeType = codec.MimeType;
string imageSource = string.Format("data:{0};base64,{1}", mimeType, base64);
XElement img = new XElement(Xhtml.img,
new XAttribute(NoNamespace.src, imageSource),
imageInfo.ImgStyleAttribute,
imageInfo.AltText != null ?
new XAttribute(NoNamespace.alt, imageInfo.AltText) : null);
return img;
}
};
XElement htmlElement = WmlToHtmlConverter.ConvertToHtml(wDoc, settings);
var html = new XDocument(new XDocumentType("html", null, null, null), htmlElement);
var htmlString = html.ToString(SaveOptions.DisableFormatting);
return htmlString;
}
}
}
}
This is the Uri fixer class used by the above code
using System;
using System.IO;
using System.IO.Compression;
using System.Linq;
using System.Xml;
using System.Xml.Linq;
public static class UriFixer
{
public static void FixInvalidUri(Stream fs, Func<string, string> invalidUriHandler)
{
XNamespace relNs = "http://schemas.openxmlformats.org/package/2006/relationships";
using (ZipArchive za = new ZipArchive(fs, ZipArchiveMode.Update))
{
foreach (var entry in za.Entries.ToList())
{
if (!entry.Name.EndsWith(".rels"))
continue;
bool replaceEntry = false;
XDocument entryXDoc = null;
using (var entryStream = entry.Open())
{
try
{
entryXDoc = XDocument.Load(entryStream);
if (entryXDoc.Root != null && entryXDoc.Root.Name.Namespace == relNs)
{
var urisToCheck = entryXDoc
.Descendants(relNs + "Relationship")
.Where(r => r.Attribute("TargetMode") != null && (string)r.Attribute("TargetMode") == "External");
foreach (var rel in urisToCheck)
{
var target = (string)rel.Attribute("Target");
if (target != null)
{
try
{
Uri uri = new Uri(target);
}
catch (UriFormatException)
{
string newUri = invalidUriHandler(target);
rel.Attribute("Target").Value = newUri;
replaceEntry = true;
}
}
}
}
}
catch (XmlException)
{
continue;
}
}
if (replaceEntry)
{
var fullName = entry.FullName;
entry.Delete();
var newEntry = za.CreateEntry(fullName);
using (StreamWriter writer = new StreamWriter(newEntry.Open()))
using (XmlWriter xmlWriter = XmlWriter.Create(writer))
{
entryXDoc.WriteTo(xmlWriter);
}
}
}
}
}
}
All you have to do is provide the file path to your .docx file to the ConvertToHtml method and it will do the work for you and give you the html.
Note: This only supports for .docx