public void ProcessWordDocument(string docFilePath)
{
tableIndex = 1;
mathIndex = 1;
imageIndex = 1;
textIndex = 1;
using (WordprocessingDocument doc = WordprocessingDocument.Open(docFilePath, false))
{
foreach (var table in doc.MainDocumentPart.Document.Descendants<DocumentFormat.OpenXml.Wordprocessing.Table>())
{
int trows = table.Descendants<DocumentFormat.OpenXml.Wordprocessing.TableRow>().Count();
int tcols = table.Descendants<DocumentFormat.OpenXml.Wordprocessing.TableRow>().First().Descendants<DocumentFormat.OpenXml.Wordprocessing.TableCell>().Count();
WordTable wordTable = new WordTable(trows, tcols);
//create a table class and add the text from the rows and cells
int row = 0, cell = 0;
foreach (var tableRow in table.Descendants<DocumentFormat.OpenXml.Wordprocessing.TableRow>())
{
foreach (var tableCell in tableRow.Descendants<DocumentFormat.OpenXml.Wordprocessing.TableCell>())
{
string text = tableCell.InnerText;
wordTable.AddText(row, cell, text);
cell++;
//save the cell into a table class for later processing with row info
}
cell = 0;
row++;
}
DocumentFormat.OpenXml.Wordprocessing.Paragraph para = new DocumentFormat.OpenXml.Wordprocessing.Paragraph();
Run run = para.AppendChild(new Run());
string IDplaceholder = "%Table-&" + tableIndex;
run.AppendChild(new Text(IDplaceholder));
table.Parent.ReplaceChild(para, table);
//table.Remove();
tableIndex++;
//store the table
TableList.Add(IDplaceholder, wordTable);
}
foreach (var formula in doc.MainDocumentPart.Document.Descendants<DocumentFormat.OpenXml.Math.OfficeMath>())
{
string wordDocXml = formula.OuterXml;
XslCompiledTransform xslTransform = new XslCompiledTransform();
xslTransform.Load(officeMathMLSchemaFilePath);
string mmlFormula = null;
using (TextReader tr = new StringReader(wordDocXml))
{
// Load the xml of your main document part.
using (XmlReader reader = XmlReader.Create(tr))
{
XmlWriterSettings settings = xslTransform.OutputSettings.Clone();
// Configure xml writer to omit xml declaration.
settings.ConformanceLevel = ConformanceLevel.Fragment;
settings.OmitXmlDeclaration = true;
using (MemoryStream ms = new MemoryStream())
{
XmlWriter xw = XmlWriter.Create(ms, settings);
// Transform our OfficeMathML to MathML.
xslTransform.Transform(reader, xw);
ms.Seek(0, SeekOrigin.Begin);
using (StreamReader sr = new StreamReader(ms, Encoding.UTF8))
{
mmlFormula = sr.ReadToEnd();
}
}
}
DocumentFormat.OpenXml.Wordprocessing.Paragraph para = formula.Parent.AppendChild(new DocumentFormat.OpenXml.Wordprocessing.Paragraph());
Run run = para.AppendChild(new Run());
string IDplaceholder = "%Math-&" + mathIndex;
run.AppendChild(new Text(IDplaceholder));
mathIndex++;
formula.Remove();
if (mmlFormula != null)
{
MathList.Add(IDplaceholder, mmlFormula);
}
}
}
foreach (var graphic in doc.MainDocumentPart.Document.Descendants<DocumentFormat.OpenXml.Drawing.Graphic>())
{
DocumentFormat.OpenXml.Drawing.Blip blip = graphic.FirstChild.Descendants<DocumentFormat.OpenXml.Drawing.Blip>().First();
string imageId = blip.Embed.Value;
ImagePart imagePart = (ImagePart)doc.MainDocumentPart.GetPartById(imageId);
var uri = imagePart.Uri;
var filename = uri.ToString().Split('/').Last();
var stream = doc.Package.GetPart(uri).GetStream();
Bitmap b = new Bitmap(stream);
string imagePath = TempImageFolder + filename;
b.Save(imagePath);
DocumentFormat.OpenXml.Wordprocessing.Paragraph para = graphic.Parent.Parent.Parent.Parent.AppendChild(new DocumentFormat.OpenXml.Wordprocessing.Paragraph());
Run run = para.AppendChild(new Run());
string IDplaceholder = "%Image-&" + imageIndex;
run.AppendChild(new Text(IDplaceholder));
imageIndex++;
ImageList.Add(IDplaceholder, imagePath);
}
try
{
foreach (var video in doc.MainDocumentPart.Document.Descendants<DocumentFormat.OpenXml.Drawing.VideoFromFile>())
{
string localName = video.LocalName;
string innerXml = video.InnerXml;
}
foreach (var video in doc.MainDocumentPart.EmbeddedObjectParts)
{
string vct = video.ContentType;
}
} catch
{
}
foreach (var element in doc.MainDocumentPart.Document.Descendants<DocumentFormat.OpenXml.Wordprocessing.Paragraph>())
{
try
{
var psID = element.ParagraphProperties.ParagraphStyleId;
string type = null;
switch (psID.Val.ToString().ToLowerInvariant())
{
//for each case save the inner text of the paragraph and remove it
case "heading1": { type = "h1-"; break; }
case "heading2": { type = "h2-"; break; }
case "heading3": { type = "h3-"; break; }
case "heading4": { type = "h4-"; break; }
case "heading5": { type = "h5-"; break; }
case "title": { type = "title-"; break; }
case "subtitle": { type = "subtitle-"; break; }
default: break;
}
if (type != null)
{
string id = "%" + type + "&" + textIndex;
PlainTextList.Add(id, element.InnerText);
textIndex++;
element.RemoveAllChildren();
DocumentFormat.OpenXml.Wordprocessing.Paragraph para = element.AppendChild(new DocumentFormat.OpenXml.Wordprocessing.Paragraph());
Run run = para.AppendChild(new Run());
run.AppendChild(new Text(id));
}
}
catch
{ //do nothing
}
}
PlaceholderIDList = ExtractTextAndCreatePlaceholderList(doc);
if (textBuilder.Length > 0)
{
string s2 = AddTextToTextList();
if (s2 != null)
PlaceholderIDList.Add(s2);
}
}
}
public void ProcessWordDocument(string docFilePath)
{
tableIndex = 1;
mathIndex = 1;
imageIndex = 1;
videoIndex = 1;
textIndex = 1;
using (WordprocessingDocument doc = WordprocessingDocument.Open(docFilePath, false))
{
foreach (var table in doc.MainDocumentPart.Document.Descendants <DocumentFormat.OpenXml.Wordprocessing.Table>())
{
int trows = table.Descendants <DocumentFormat.OpenXml.Wordprocessing.TableRow>().Count();
int tcols = table.Descendants <DocumentFormat.OpenXml.Wordprocessing.TableRow>().First().Descendants <DocumentFormat.OpenXml.Wordprocessing.TableCell>().Count();
WordTable wordTable = new WordTable(trows, tcols);
//create a table class and add the text from the rows and cells
int row = 0, cell = 0;
foreach (var tableRow in table.Descendants <DocumentFormat.OpenXml.Wordprocessing.TableRow>())
{
foreach (var tableCell in tableRow.Descendants <DocumentFormat.OpenXml.Wordprocessing.TableCell>())
{
string text = tableCell.InnerText;
wordTable.AddText(row, cell, text);
cell++;
//save the cell into a table class for later processing with row info
}
cell = 0;
row++;
}
DocumentFormat.OpenXml.Wordprocessing.Paragraph para = new DocumentFormat.OpenXml.Wordprocessing.Paragraph();
Run run = para.AppendChild(new Run());
string IDplaceholder = "%Table-&" + tableIndex;
run.AppendChild(new Text(IDplaceholder));
table.Parent.ReplaceChild(para, table);
//table.Remove();
tableIndex++;
//store the table
TableList.Add(IDplaceholder, wordTable);
}
foreach (var formula in doc.MainDocumentPart.Document.Descendants <DocumentFormat.OpenXml.Math.OfficeMath>())
{
string wordDocXml = formula.OuterXml;
XslCompiledTransform xslTransform = new XslCompiledTransform();
xslTransform.Load(officeMathMLSchemaFilePath);
string mmlFormula = null;
using (TextReader tr = new StringReader(wordDocXml))
{
// Load the xml of your main document part.
using (XmlReader reader = XmlReader.Create(tr))
{
XmlWriterSettings settings = xslTransform.OutputSettings.Clone();
// Configure xml writer to omit xml declaration.
settings.ConformanceLevel = ConformanceLevel.Fragment;
settings.OmitXmlDeclaration = true;
using (MemoryStream ms = new MemoryStream())
{
XmlWriter xw = XmlWriter.Create(ms, settings);
// Transform our OfficeMathML to MathML.
xslTransform.Transform(reader, xw);
ms.Seek(0, SeekOrigin.Begin);
using (StreamReader sr = new StreamReader(ms, Encoding.UTF8))
{
mmlFormula = sr.ReadToEnd();
}
}
}
DocumentFormat.OpenXml.Wordprocessing.Paragraph para = formula.Parent.AppendChild(new DocumentFormat.OpenXml.Wordprocessing.Paragraph());
Run run = para.AppendChild(new Run());
string IDplaceholder = "%Math-&" + mathIndex;
run.AppendChild(new Text(IDplaceholder));
mathIndex++;
formula.Remove();
if (mmlFormula != null)
{
MathList.Add(IDplaceholder, mmlFormula);
}
}
}
foreach (var graphic in doc.MainDocumentPart.Document.Descendants <DocumentFormat.OpenXml.Drawing.Graphic>())
{
DocumentFormat.OpenXml.Drawing.Blip blip = graphic.FirstChild.Descendants <DocumentFormat.OpenXml.Drawing.Blip>().First();
string imageId = blip.Embed.Value;
ImagePart imagePart = (ImagePart)doc.MainDocumentPart.GetPartById(imageId);
var uri = imagePart.Uri;
var filename = uri.ToString().Split('/').Last();
var stream = doc.Package.GetPart(uri).GetStream();
Bitmap b = new Bitmap(stream);
string imagePath = TempImageFolder + filename;
b.Save(imagePath);
DocumentFormat.OpenXml.Wordprocessing.Paragraph para = graphic.Parent.Parent.Parent.Parent.AppendChild(new DocumentFormat.OpenXml.Wordprocessing.Paragraph());
Run run = para.AppendChild(new Run());
string IDplaceholder = "%Image-&" + imageIndex;
run.AppendChild(new Text(IDplaceholder));
imageIndex++;
ImageList.Add(IDplaceholder, imagePath);
}
try
{
foreach (var video in doc.MainDocumentPart.Document.Descendants <DocumentFormat.OpenXml.Drawing.VideoFromFile>())
{
//extract video bytes from word document
DocumentFormat.OpenXml.Drawing.Blip blip = video.FirstChild.Descendants <DocumentFormat.OpenXml.Drawing.Blip>().First();
var vid = doc.MainDocumentPart.GetPartById(blip.Embed.Value);
var uri = vid.Uri;
var filename = uri.ToString().Split('/').Last();
var stream = doc.Package.GetPart(uri).GetStream();
byte[] videoBytes;
using (BinaryReader br = new BinaryReader(stream))
{
videoBytes = br.ReadBytes((int)stream.Length);
}
//TODO set these up universally somewhere
string videoFolder = @"C:\websites\RoboBraille.Web.Api\dist\";
string urlDistribution = @"http://2.109.50.18:5150/dist/" + filename;
//write bytes to shared web folder
File.WriteAllBytes(videoFolder + filename, videoBytes);
//send post video request to Amara
//put placeholder
//TODO check that video.Parent.Parent ...points to the right parent
DocumentFormat.OpenXml.Wordprocessing.Paragraph para = video.Parent.Parent.Parent.Parent.AppendChild(new DocumentFormat.OpenXml.Wordprocessing.Paragraph());
Run run = para.AppendChild(new Run());
string IDplaceholder = "%Video-&" + videoIndex;
run.AppendChild(new Text(IDplaceholder));
videoIndex++;
//make somehow an list of videos sent to amara and their source location and store that info somewhere? maybe as jobs?
}
} catch
{
}
foreach (var element in doc.MainDocumentPart.Document.Descendants <DocumentFormat.OpenXml.Wordprocessing.Paragraph>())
{
try
{
var psID = element.ParagraphProperties.ParagraphStyleId;
string type = null;
switch (psID.Val.ToString().ToLowerInvariant())
{
//for each case save the inner text of the paragraph and remove it
case "heading1": { type = "h1-"; break; }
case "heading2": { type = "h2-"; break; }
case "heading3": { type = "h3-"; break; }
case "heading4": { type = "h4-"; break; }
case "heading5": { type = "h5-"; break; }
case "title": { type = "title-"; break; }
case "subtitle": { type = "subtitle-"; break; }
default: break;
}
if (type != null)
{
string id = "%" + type + "&" + textIndex;
PlainTextList.Add(id, element.InnerText);
textIndex++;
element.RemoveAllChildren();
DocumentFormat.OpenXml.Wordprocessing.Paragraph para = element.AppendChild(new DocumentFormat.OpenXml.Wordprocessing.Paragraph());
Run run = para.AppendChild(new Run());
run.AppendChild(new Text(id));
}
}
catch
{ //do nothing
}
}
PlaceholderIDList = ExtractTextAndCreatePlaceholderList(doc);
if (textBuilder.Length > 0)
{
string s2 = AddTextToTextList();
if (s2 != null)
{
PlaceholderIDList.Add(s2);
}
}
}
}
