public Dictionary<int, string> ExecuteHighlight(BackgroundWorker backgroundWorker)
{
OutputMg.OutputContent(backgroundWorker, "Starting highlight file " + originalFilePath);
//if the document is open, close it firstly
System.Diagnostics.Process[] processes = System.Diagnostics.Process.GetProcessesByName("WINWORD");
if (processes != null)
{
if (processes.Length > 0)
{
string targetDocPath = "";
int dirIndex = highlightedFilePath.LastIndexOf("\\");
if (dirIndex > 0)
{
targetDocPath = highlightedFilePath.Substring(dirIndex + 2);
}
foreach (System.Diagnostics.Process process in processes)
{
string temp = process.MainWindowTitle.ToString();
if (temp.Length == 0)
{
process.Kill();
}
else if (temp.Contains(targetDocPath))
{
process.Kill();
System.IO.File.Delete(highlightedFilePath);
}
}
}
}
Dictionary<int, string> pageContents = new Dictionary<int, string>();
var app = new Microsoft.Office.Interop.Word.Application();
app.Visible = false;
object readOnly = false;
object missing = System.Reflection.Missing.Value;
var doc = app.Documents.Open(this.originalFilePath, missing, readOnly);
int pageNum = doc.Content.ComputeStatistics(Microsoft.Office.Interop.Word.WdStatistic.wdStatisticPages); //doc page
List<string> topicTerms = ReadTargetTopicTerms.ParseTopicTerms(this.topicTermPath, this.targetTopicName);
AddUserSearchTerms(topicTerms);
//identify each word
for (int p = 1; p <= pageNum; p++)
{
OutputMg.OutputContent(backgroundWorker, "Parsing page: " + p);
string pageHighlight = "";
object what = WdGoToItem.wdGoToPage;
object which = WdGoToDirection.wdGoToAbsolute;
object nextPage = p + 1;
Range startRange;
Range endRange;
try
{
startRange = app.Selection.GoTo(ref what, ref which, p, ref missing);
endRange = app.Selection.GoTo(what, which, nextPage, missing);
}
catch (Exception)
{
doc.Close();
app.Quit();
MessageBox.Show("This document is locked by author. We cannot execute highlight", "Failed", MessageBoxButtons.OK, MessageBoxIcon.Warning);
break;
}
if (startRange.Start == endRange.Start)
{
which = WdGoToDirection.wdGoToLast;
what = WdGoToItem.wdGoToLine;
endRange = app.Selection.GoTo(what, which, nextPage, missing);
}
endRange.SetRange(startRange.Start, endRange.End);
foreach (Paragraph field in endRange.Paragraphs)
{
Range fieldRange = field.Range;
string paraText = fieldRange.Text.ToLower();
if (paraText.Length == 0)
{
continue;
}
else
{
foreach (string topicTerm in topicTerms)
{
if (paraText.Contains(topicTerm) || paraText.Contains(topicTerm + "s"))
{
fieldRange.HighlightColorIndex = WdColorIndex.wdYellow;
pageHighlight += paraText + "\t";
break;
}
}
}
}
pageContents.Add(p, pageHighlight);
}
doc.SaveAs2(this.highlightedFilePath);
doc.Close();
app.Quit();
return pageContents;
}
public Dictionary <int, string> ExecuteHighlight(BackgroundWorker backgroundWorker)
{
OutputMg.OutputContent(backgroundWorker, "Starting highlight file " + pdfFilePath);
List <string> topicTerms = ReadTargetTopicTerms.ParseTopicTerms(this.topicTermPath, this.targetTopicName);
AddUserSearchTerms(topicTerms);
string origiFile = pdfFilePath;
//Create a new file from our test file with highlighting
string highLightFile = highlightedPDFPath;
int pdfNum = 0;
PdfReader reader = new PdfReader(origiFile);
using (FileStream fs = new FileStream(highLightFile, FileMode.Create, FileAccess.Write, FileShare.None))
{
using (PdfStamper stamper = new PdfStamper(reader, fs))
{
using (var r = new PdfReader(origiFile))
{
pdfNum = r.NumberOfPages;
string ex = "";
ITextExtractionStrategy strategy;
for (int i = 1; i <= pdfNum; i++)
{
OutputMg.OutputContent(backgroundWorker, "Parsing page: " + i);
Rectangle pageRect = r.GetPageSize(i);
Document doc = new Document(pageRect);
float leftMargin = doc.LeftMargin;
float rightMargin = doc.RightMargin;
float lineWidth = pageRect.Width;
var textPos = new FutherLocationTextExtractionStrategy(topicTerms);
//Create an instance of our strategy
ex = PdfTextExtractor.GetTextFromPage(r, i, textPos); //store the text and the position info in textPos
List <iTextSharp.text.Rectangle> quadList = new List <iTextSharp.text.Rectangle>();
foreach (var p in textPos.myPoints)
{
string p_text = p.Text;
iTextSharp.text.Rectangle rect = p.Rect;
quadList.Add(rect);//collect the coordination of keywords
}
List <string> pageContent = new List <string>();
if (quadList.Count > 0)
{
List <iTextSharp.text.Rectangle> orderedRect = orderRectByBottom(quadList);
//merge and adjust the rectangle, highlight the adjusted rect
List <iTextSharp.text.Rectangle> adjustedRect = adjustRect(orderedRect, lineWidth, leftMargin);
foreach (Rectangle rect in adjustedRect)
{
//Create an array of quad points based on that rectangle. NOTE: The order below doesn't appear to match the actual spec but is what Acrobat produces
//the co-ordination of four points
float[] quad = { rect.Left, rect.Bottom, rect.Right, rect.Bottom, rect.Left, rect.Top, rect.Right, rect.Top };
////Create our hightlight
PdfAnnotation highlight = PdfAnnotation.CreateMarkup(stamper.Writer, rect, null, PdfAnnotation.MARKUP_HIGHLIGHT, quad);
////Set the color
highlight.Color = BaseColor.YELLOW;
stamper.AddAnnotation(highlight, i); // i is the page
//get the text of highlighting
RenderFilter[] filter = { new RegionTextRenderFilter(rect) };
strategy = new MyFilteredTextRenderListener(new LocationTextExtractionStrategy(), filter);
string text = PdfTextExtractor.GetTextFromPage(reader, i, strategy).Trim();
if (!pageContent.Contains(text))
{
pageContent.Add(text);
}
}
StringBuilder sb = new StringBuilder();
foreach (string tmp in pageContent)
{
sb.AppendLine(tmp);
}
pageContents.Add(i, sb.ToString());
}
}
}
}
}
return(pageContents);
}