/// <summary>
/// Creates a TextStyle object by getting the font name and font size
/// from a TextRenderInfo object.
/// </summary>
/// <param name="textRenderInfo">Object that contains info about a text snippet</param>
public TextStyle(TextRenderInfo textRenderInfo)
{
String font = textRenderInfo.GetFont().FullFontName[0][3];
if (font.Contains("+"))
font = font.Substring(font.IndexOf("+") + 1, font.Length - font.IndexOf("+") - 1);
if (font.Contains("-"))
font = font.Substring(0, font.IndexOf("-"));
this.fontName = font;
this.fontSize = textRenderInfo.GetAscentLine().GetStartPoint()[1] - textRenderInfo.GetDescentLine().GetStartPoint()[1];
}
public void RenderText(iTextSharp.text.pdf.parser.TextRenderInfo renderInfo)
{
//to check the components , you can use to print line by line
//DataModel dataModel = new DataModel(); //1.1.18
string curDataItself = renderInfo.GetText();
//Console.WriteLine(curDataItself);
string curDataFontStyle = "";
string curFont = renderInfo.GetFont().PostscriptFontName; // http://itextsupport.com/apidocs/itext5/5.5.9/com/itextpdf/text/pdf/parser/TextRenderInfo.html#getFont--
if ((renderInfo.GetTextRenderMode() == 2 /*(int)TextRenderMode.FillThenStrokeText*/))
{
curDataFontStyle = "BOLD";
curFont += "-Bold";
}
//This code assumes that if the baseline changes then we're on a newline
Vector curBaseline = renderInfo.GetBaseline().GetStartPoint();
Vector topRight = renderInfo.GetAscentLine().GetEndPoint();
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(curBaseline[Vector.I1], curBaseline[Vector.I2], topRight[Vector.I1], topRight[Vector.I2]);
Single curFontSize = rect.Height;
//dataModel.fontSize = curFontSize;
if (lastBaseLine != null && lastBaseLine[Vector.I2] != curBaseline[Vector.I2])
{
DataModel aDataModel = new DataModel();
aDataModel.dataItself = lastDataItself;
aDataModel.fontSize = lastFontSize;
aDataModel.dataFontStyle = lastDataFontStyle;
aDataModel.fontName = lastFont;
listOfData.Add(aDataModel);
lastDataItself = curDataItself;
lastFont = curFont;
lastDataFontStyle = curDataFontStyle;
lastFontSize = curFontSize;
}
else
{
lastDataItself += curDataItself;
lastFont = curFont;
lastFontSize = curFontSize;
lastDataFontStyle = curDataFontStyle;
}
if (lastBaseLine == null)
{
lastDataItself = curDataItself;
lastFont = curFont;
lastFontSize = curFontSize;
lastDataFontStyle = curDataFontStyle;
}
this.lastBaseLine = curBaseline;
}
/**
* Method invokes by the PdfContentStreamProcessor.
* Passes a TextRenderInfo for every text chunk that is encountered.
* We'll use this object to obtain coordinates.
* @see com.itextpdf.text.pdf.parser.RenderListener#renderText(com.itextpdf.text.pdf.parser.TextRenderInfo)
*/
virtual public void RenderText(TextRenderInfo renderInfo) {
if (textRectangle == null)
textRectangle = renderInfo.GetDescentLine().GetBoundingRectange();
else
textRectangle.Add(renderInfo.GetDescentLine().GetBoundingRectange());
textRectangle.Add(renderInfo.GetAscentLine().GetBoundingRectange());
}
/// <summary>
/// Stores the start and end points and the ascent and descent info from
/// a text snippet into a Rectangle object.
/// </summary>
/// <param name="textRenderInfo">Object that contains info about a text snippet</param>
/// <returns>coordinates in the form of a Rectangle object</returns>
static Rectangle GetRectangle(TextRenderInfo textRenderInfo)
{
LineSegment descentLine = textRenderInfo.GetDescentLine();
LineSegment ascentLine = textRenderInfo.GetAscentLine();
float x0 = descentLine.GetStartPoint()[0];
float x1 = descentLine.GetEndPoint()[0];
float y0 = descentLine.GetStartPoint()[1];
float y1 = ascentLine.GetEndPoint()[1];
return new Rectangle(x0, y0, x1, y1);
}
/**
* Method invokes by the PdfContentStreamProcessor.
* Passes a TextRenderInfo for every text chunk that is encountered.
* We'll use this object to obtain coordinates.
* @see com.itextpdf.text.pdf.parser.RenderListener#renderText(com.itextpdf.text.pdf.parser.TextRenderInfo)
*/
virtual public void RenderText(TextRenderInfo renderInfo)
{
if (textRectangle == null)
{
textRectangle = renderInfo.GetDescentLine().GetBoundingRectange();
}
else
{
textRectangle.Add(renderInfo.GetDescentLine().GetBoundingRectange());
}
textRectangle.Add(renderInfo.GetAscentLine().GetBoundingRectange());
}
public override bool AllowText(TextRenderInfo renderInfo) {
LineSegment ascent = renderInfo.GetAscentLine();
LineSegment descent = renderInfo.GetDescentLine();
Rectangle r1 = new Rectangle(Math.Min(descent.GetStartPoint()[0], descent.GetEndPoint()[0]),
descent.GetStartPoint()[1],
Math.Max(descent.GetStartPoint()[0], descent.GetEndPoint()[0]),
ascent.GetEndPoint()[1]);
foreach (Rectangle rectangle in rectangles) {
if (Intersect(r1, rectangle)) {
return false;
}
}
return true;
}
public void RenderText(iTextSharp.text.pdf.parser.TextRenderInfo renderInfo)
{
string curFont = renderInfo.GetFont().PostscriptFontName;
//Check if faux bold is used
if ((renderInfo.GetTextRenderMode() == (int)TextRenderMode.FillThenStrokeText))
{
curFont += "-Bold";
}
//This code assumes that if the baseline changes then we're on a newline
Vector curBaseline = renderInfo.GetBaseline().GetStartPoint();
Vector topRight = renderInfo.GetAscentLine().GetEndPoint();
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(curBaseline[Vector.I1], curBaseline[Vector.I2], topRight[Vector.I1], topRight[Vector.I2]);
Single curFontSize = rect.Height;
//See if something has changed, either the baseline, the font or the font size
if ((this.lastBaseLine == null) || (curBaseline[Vector.I2] != lastBaseLine[Vector.I2]) || (curFontSize != lastFontSize) || (curFont != lastFont))
{
//if we've put down at least one span tag close it
if ((this.lastBaseLine != null))
{
this.result.AppendLine("</span>");
}
//If the baseline has changed then insert a line break
if ((this.lastBaseLine != null) && curBaseline[Vector.I2] != lastBaseLine[Vector.I2])
{
this.result.AppendLine("<br />");
}
//Create an HTML tag with appropriate styles
this.result.AppendFormat("<span style=\"font-family:{0};font-size:{1}\">", curFont, curFontSize);
}
//Append the current text
this.result.Append(renderInfo.GetText());
//Set currently used properties
this.lastBaseLine = curBaseline;
this.lastFontSize = curFontSize;
this.lastFont = curFont;
}
public override void RenderText(TextRenderInfo renderInfo)
{
base.RenderText(renderInfo);
var bottomLeft = renderInfo.GetDescentLine().GetStartPoint();
var topRight = renderInfo.GetAscentLine().GetEndPoint();
var rect = new iTextSharp.text.Rectangle(
bottomLeft[Vector.I1],
bottomLeft[Vector.I2],
topRight[Vector.I1],
topRight[Vector.I2]
);
this.containers.Add(new TextContainer()
{
Container = rect,
Text = renderInfo.GetText()
});
}
public override bool AllowText(TextRenderInfo renderInfo) {
LineSegment ascent = renderInfo.GetAscentLine();
LineSegment descent = renderInfo.GetDescentLine();
Point2D[] glyphRect = new Point2D[] {
new Point2D.Float(ascent.GetStartPoint()[0], ascent.GetStartPoint()[1]),
new Point2D.Float(ascent.GetEndPoint()[0], ascent.GetEndPoint()[1]),
new Point2D.Float(descent.GetEndPoint()[0], descent.GetEndPoint()[1]),
new Point2D.Float(descent.GetStartPoint()[0], descent.GetStartPoint()[1]),
};
foreach (Rectangle rectangle in rectangles) {
Point2D[] redactRect = GetVertices(rectangle);
if (Intersect(glyphRect, redactRect)) {
return false;
}
}
return true;
}
public void RenderText(iTextSharp.text.pdf.parser.TextRenderInfo renderInfo)
{
string curFont = renderInfo.GetFont().PostscriptFontName;
if ((renderInfo.GetTextRenderMode() == (int)TextRenderMode.FillThenStrokeText))
{
curFont += "-Bold";
}
Vector curBaseline = renderInfo.GetBaseline().GetStartPoint();
Vector topRight = renderInfo.GetAscentLine().GetEndPoint();
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(curBaseline[Vector.I1], curBaseline[Vector.I2], topRight[Vector.I1], topRight[Vector.I2]);
Single curFontSize = rect.Height;
if ((this.lastBaseLine == null) || (curBaseline[Vector.I2] != lastBaseLine[Vector.I2]) || (curFontSize != lastFontSize) || (curFont != lastFont))
{
if ((this.lastBaseLine != null))
{
this.result.AppendLine("\"},");
}
if ((this.lastBaseLine != null) && curBaseline[Vector.I2] != lastBaseLine[Vector.I2])
{
this.result.Append("<br />");
}
if (this.result.Length == 0)
{
this.result.Append("{\"fontName\":\"" + curFont + "\",\"fontSize\":\"" + curFontSize + "\",\"text\":\"");
}
else
{
this.result.Append("{\"fontName\":\"" + curFont + "\",\"fontSize\":\"" + curFontSize + "\",\"text\":\"");
}
}
this.result.Append(renderInfo.GetText());
this.lastBaseLine = curBaseline;
this.lastFontSize = curFontSize;
this.lastFont = curFont;
}
public void RenderText(TextRenderInfo renderInfo)
{
var curFont = renderInfo.GetFont().PostscriptFontName;
//Check if faux bold is used
if ((renderInfo.GetTextRenderMode() == (int) TextRenderMode.FillThenStrokeText))
curFont += "-Bold";
//This code assumes that if the baseline changes then we're on a newline
var curBaseline = renderInfo.GetBaseline().GetStartPoint();
var topRight = renderInfo.GetAscentLine().GetEndPoint();
var rect = new Rectangle(curBaseline[Vector.I1], curBaseline[Vector.I2], topRight[Vector.I1], topRight[Vector.I2]);
var curFontSize = rect.Height;
//See if something has changed, either the baseline, the font or the font size
if ((lastBaseLine == null) || (curBaseline[Vector.I2] != lastBaseLine[Vector.I2]) || (curFontSize != lastFontSize) ||
(curFont != lastFont))
{
//if we've put down at least one span tag close it
if ((lastBaseLine != null))
result.AppendLine("</span>");
//If the baseline has changed then insert a line break
if ((lastBaseLine != null) && curBaseline[Vector.I2] != lastBaseLine[Vector.I2])
result.AppendLine("<br />");
//Create an HTML tag with appropriate styles
result.AppendFormat("<span style=\"font-family:{0};font-size:{1}; position: relative; top: {2}; left: {3};\">",
curFont, curFontSize, 850 - rect.Top, rect.Left);
}
//Append the current text
result.Append(renderInfo.GetText());
//Set currently used properties
lastBaseLine = curBaseline;
lastFontSize = curFontSize;
lastFont = curFont;
}
//Automatically called for each chunk of text in the PDF
public override void RenderText(TextRenderInfo renderInfo) {
base.RenderText(renderInfo);
//Get the bounding box for the chunk of text
var bottomLeft = renderInfo.GetDescentLine().GetStartPoint();
var topRight = renderInfo.GetAscentLine().GetEndPoint();
//Create a rectangle from it
var rect = new iTextSharp.text.Rectangle(
bottomLeft[Vector.I1],
bottomLeft[Vector.I2],
topRight[Vector.I1],
topRight[Vector.I2]
);
//Add this to our main collection
this.myPoints.Add(new RectAndText(rect, renderInfo.GetText()));
}
public virtual void RenderText(TextRenderInfo renderInfo) {
Vector startPoint = renderInfo.GetDescentLine().GetStartPoint();
Vector endPoint = renderInfo.GetAscentLine().GetEndPoint();
float x1 = Math.Min(startPoint[0], endPoint[0]);
float x2 = Math.Max(startPoint[0], endPoint[0]);
float y1 = Math.Min(startPoint[1], endPoint[1]);
float y2 = Math.Max(startPoint[1], endPoint[1]);
rectangles.Add(new Rectangle(x1, y1, x2, y2));
}
public void RenderText(iTextSharp.text.pdf.parser.TextRenderInfo renderInfo)
{//.Remove(0,7)
string curFont = renderInfo.GetFont().PostscriptFontName;
string Bold = "NOTBOLD";
string Color;
float URX = 0f;
float URY = 0f;
float LLX = 0f;
float LLY = 0f;
//Check if faux bold is used
if ((renderInfo.GetTextRenderMode() == (int)TextRenderMode.FillThenStrokeText))
{
Bold = "BOLD";
}
Color = "Not Available;";
try
{
Color = renderInfo.GetFillColor().ToString();
}
catch (Exception)
{
}
//This code assumes that if the baseline changes then we're on a newline
Vector curBaseline = renderInfo.GetBaseline().GetStartPoint();
Vector topRight = renderInfo.GetAscentLine().GetEndPoint();
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(curBaseline[Vector.I1], curBaseline[Vector.I2], topRight[Vector.I1], topRight[Vector.I2]);
Single curFontSize = rect.Height;
//See if something has changed, either the baseline, the font or the font size
if ((this.lastBaseLine == null) || (curBaseline[Vector.I2] != lastBaseLine[Vector.I2]) || (curFontSize != lastFontSize) || (curFont != lastFont))
{
URX = topRight[Vector.I1];
URY = topRight[Vector.I2];
LLX = curBaseline[Vector.I1];
LLY = curBaseline[Vector.I2];
//if we've put down at least one span tag close it
if ((this.lastBaseLine != null))
{
this.result.AppendLine("</span>");
}
//If the baseline has changed then insert a line break
if ((this.lastBaseLine != null) && curBaseline[Vector.I2] != lastBaseLine[Vector.I2])
{
this.result.AppendLine("<br />");
}
//Create an HTML tag with appropriate styles
this.result.AppendFormat("<span style=\"font-family:{0};font-size:{1};z={2};color={3};coordinates:{4},{5},{6},{7};\">", curFont, curFontSize, Bold, Color, URX, URY, LLX, LLY);
}
//Append the current text
this.result.Append(renderInfo.GetText());
//Set currently used properties
this.lastBaseLine = curBaseline;
this.lastFontSize = curFontSize;
this.lastFont = curFont;
}
/// <summary>
///
/// </summary>
/// <param name="renderInfo"></param>
public override void RenderText(TextRenderInfo renderInfo)
{
iTextSharp.text.pdf.parser.LineSegment segment = renderInfo.GetBaseline();
TextChunkEx location = new TextChunkEx(renderInfo.GetText(), segment.GetStartPoint(), segment.GetEndPoint(), renderInfo.GetSingleSpaceWidth(), renderInfo.GetAscentLine(), renderInfo.GetDescentLine());
m_locationResult.Add(location);
}
/// <summary>
///
/// </summary>
/// <param name="renderInfo"></param>
public override void RenderText(TextRenderInfo renderInfo)
{
LineSegment segment = renderInfo.GetBaseline();
string x = renderInfo.GetText();
TextChunk location = new TextChunk(renderInfo.GetText(), segment.GetStartPoint(), segment.GetEndPoint(), renderInfo.GetSingleSpaceWidth(), renderInfo.GetAscentLine(), renderInfo.GetDescentLine());
m_locationResult.Add(location);
}
public void RenderText(iTextSharp.text.pdf.parser.TextRenderInfo renderInfo)
{
string curFont = renderInfo.GetFont().PostscriptFontName;
string curColor = "";
try
{
curColor = renderInfo.GetFillColor().ToString();
}
catch (Exception) { }
curColor = curColor.Replace("Color value[", "").Replace("]", "");
//Console.WriteLine(curColor);
//string curColor = renderInfo.GetStrokeColor().RGB.ToString();
//Check if faux bold is used
if ((renderInfo.GetTextRenderMode() == (int)TextRenderMode.FillThenStrokeText))
{
curFont += "-Bold";
}
//This code assumes that if the baseline changes then we're on a newline
Vector curBaseline = renderInfo.GetBaseline().GetStartPoint();
Vector topRight = renderInfo.GetAscentLine().GetEndPoint();
iTextSharp.text.Rectangle rect = new iTextSharp.text.Rectangle(curBaseline[Vector.I1], curBaseline[Vector.I2], topRight[Vector.I1], topRight[Vector.I2]);
Single curFontSize = rect.Height;
if (_doFootnoteCheck == true)
{
string text = renderInfo.GetText();
//cislo < 3.92M && cislo > 3.8M
//cislo == 3.9104M || cislo == 3.910416M
if (Decimal.TryParse(curFontSize.ToString(), out currentFontSize) && (currentFontSize == 3.890762M))
{
string s = " ";
if (text == "1," || text == "2," || text == "3," || text == "4," || text == "5," || text == "6," || text == "7," ||
text == "1" || text == "2" || text == "3" || text == "4" || text == "5" || text == "6" || text == "7")
{
//Console.WriteLine(text);
if (_prevDoubleText.Length > 1)
{
s = _prevDoubleText.Substring(0, 1);
}
if (_prevDoubleText.Length == 2 && s == text && topRight[1] == _prevTopRight)
{
_badFootnoteFound = true;
}
_prevDoubleText = text;
_prevTopRight = topRight[1];
}
}
//if (Decimal.TryParse(curFontSize.ToString(), out cislo) && (cislo > 3.5M || cislo < 4M) && !string.IsNullOrWhiteSpace(text) && Int32.TryParse(text, out icislo))
if (Decimal.TryParse(curFontSize.ToString(), out currentFontSize) && (currentFontSize == 3.9104M || currentFontSize == 3.910416M || currentFontSize == 3.910412M || currentFontSize == 3.890762M) && !string.IsNullOrWhiteSpace(text) && Int32.TryParse(text, out currentFootnoteValue))
{
if (topRight[1] > 0 && topRight[1] < 700)
{
//Console.WriteLine(pageCounter);
/*
* Console.WriteLine("------------------------------------------");
* Console.WriteLine(curFontSize);
* Console.WriteLine("page:" + pageCounter);
* Console.WriteLine("txt: " + text);
* Console.WriteLine("prv: " + prev_icislo);
* Console.WriteLine("trgh: " + topRight[1]);
* Console.WriteLine("------------------------------------------");
*/
if (!dictionary.ContainsKey(currentFootnoteValue))
{
dictionary.Add(currentFootnoteValue, (float)topRight[1]);
dr = dt.NewRow();
dr["Number"] = currentFootnoteValue;
dr["Position"] = (float)topRight[1];
dr["Page"] = (int)pageCounter;
dt.Rows.Add(dr);
}
else
{
if (replaceCounter < 10)
{
dictionary[currentFootnoteValue] = (float)topRight[1];
for (int i = 0; i < dt.Rows.Count; i++)
{
if (dt.Rows[i][0].ToString() == currentFootnoteValue.ToString().Trim())
{
dt.Rows[i][1] = (float)topRight[1];
dt.Rows[i][2] = pageCounter;
}
}
dr = dt.NewRow();
dr["Number"] = currentFootnoteValue;
dr["Position"] = (float)topRight[1];
dr["Page"] = (int)pageCounter;
dt.Rows.Add(dr);
replaceCounter++;
}
}
}
_prevInumber = currentFootnoteValue;
}
}
if (curColor == "FFFF0000")
{
//Console.WriteLine("Red detected!");
//Console.WriteLine(curColor);
string s = renderInfo.GetText();
if (string.IsNullOrWhiteSpace(s))
{
}
else
{
//Console.WriteLine(s);
redWords.Add(s);
_redWords++;
}
}
//See if something has changed, either the baseline, the font or the font size
if ((this.lastBaseLine == null) || (curBaseline[Vector.I2] != lastBaseLine[Vector.I2]) || (curFontSize != lastFontSize) || (curFont != lastFont))
{
//if we've put down at least one span tag close it
if ((this.lastBaseLine != null))
{
this.result.AppendLine("</span>");
}
//If the baseline has changed then insert a line break
if ((this.lastBaseLine != null) && curBaseline[Vector.I2] != lastBaseLine[Vector.I2])
{
this.result.AppendLine("<br />");
}
//Create an HTML tag with appropriate styles
this.result.AppendFormat("<span style=\"font-family:{0};font-size:{1}\font-color:{2}>", curFont, curFontSize, curColor);
}
//Append the current text
this.result.Append(renderInfo.GetText());
//Set currently used properties
this.lastBaseLine = curBaseline;
this.lastFontSize = curFontSize;
this.lastFont = curFont;
}
//Automatically called for each chunk of text in the PDF
public override void RenderText(TextRenderInfo renderInfo)
{
base.RenderText(renderInfo);
var startPosition = System.Globalization.CultureInfo.CurrentCulture.CompareInfo.IndexOf(renderInfo.GetText(), this.TextToSearchFor, this.CompareOptions);
var texto = renderInfo.GetText();
var x = renderInfo.GetText().Contains(TextToSearchFor);
//Get the bounding box for the chunk of text
/*if (x)
{
var bottomLeft = renderInfo.GetDescentLine().GetStartPoint();
var topRight = renderInfo.GetAscentLine().GetEndPoint();
//Create a rectangle from it
var rect = new iTextSharp.text.Rectangle(
bottomLeft[Vector.I1],
bottomLeft[Vector.I2],
topRight[Vector.I1],
topRight[Vector.I2]
);
this.myPoints.Add(new RectAndText(rect, renderInfo.GetText()));
}*/
//This code assumes that if the baseline changes then we're on a newline
Vector curBaseline = renderInfo.GetBaseline().GetStartPoint();
Vector curBaseline2 = renderInfo.GetAscentLine().GetEndPoint();
//See if the baseline has changed
if ((this.lastBaseLine != null) && (curBaseline[Vector.I2] != lastBaseLine[Vector.I2]))
{
//See if we have text and not just whitespace
if ((!String.IsNullOrWhiteSpace(this.result.ToString())))
{
//Mark the previous line as done by adding it to our buffers
this.baselines.Add(this.lastBaseLine[Vector.I2]);
this.strings.Add(this.result.ToString());
if (this.result.ToString().ToLower().Contains(TextToSearchFor.ToLower()))
{
//Create a rectangle from it
var rect = new iTextSharp.text.Rectangle(startPositionWord[Vector.I1],
startPositionWord[Vector.I2],
lastAscentLine[Vector.I1],
lastAscentLine[Vector.I2]);
this.myPoints.Add(new RectAndText(rect, this.result.ToString()));
startPositionWord = null;
endPositionWord = null;
}
}
//Reset our "line" buffer
this.result.Clear();
wordended = true;
}
//Append the current text to our line buffer
//if (!string.IsNullOrWhiteSpace(renderInfo.GetText()))
this.result.Append(renderInfo.GetText());
if (!string.IsNullOrWhiteSpace(result.ToString()) && wordended)
{
wordended = false;
startPositionWord = renderInfo.GetDescentLine().GetStartPoint();
}
//Reset the last used line
this.lastBaseLine = curBaseline;
this.lastAscentLine = curBaseline2;
}
