/// <summary>
/// Extracts text fragments from the 2nd page and highlights the glyphs in the fragment.
/// </summary>
/// <param name="document"></param>
private static void ExtractTextAndHighlightGlyphs(PDFFixedDocument document)
{
PDFRgbColor penColor = new PDFRgbColor();
PDFPen pen = new PDFPen(penColor, 0.5);
Random rnd = new Random();
byte[] rgb = new byte[3];
PDFContentExtractor ce = new PDFContentExtractor(document.Pages[1]);
PDFTextRunCollection trc = ce.ExtractTextRuns();
PDFTextRun tr = trc[1];
for (int i = 0; i < tr.Glyphs.Count; i++)
{
rnd.NextBytes(rgb);
penColor.R = rgb[0];
penColor.G = rgb[1];
penColor.B = rgb[2];
PDFPath boundingPath = new PDFPath();
boundingPath.StartSubpath(tr.Glyphs[i].GlyphCorners[0].X, tr.Glyphs[i].GlyphCorners[0].Y);
boundingPath.AddLineTo(tr.Glyphs[i].GlyphCorners[1].X, tr.Glyphs[i].GlyphCorners[1].Y);
boundingPath.AddLineTo(tr.Glyphs[i].GlyphCorners[2].X, tr.Glyphs[i].GlyphCorners[2].Y);
boundingPath.AddLineTo(tr.Glyphs[i].GlyphCorners[3].X, tr.Glyphs[i].GlyphCorners[3].Y);
boundingPath.CloseSubpath();
document.Pages[1].Canvas.DrawPath(pen, boundingPath);
}
}
/// <summary>
/// Extracts text fragments from the 3rd page and highlights the glyphs in the fragment.
/// </summary>
/// <param name="document"></param>
private static void ExtractImagesAndHighlight(PDFFixedDocument document)
{
PDFPen pen = new PDFPen(new PDFRgbColor(255, 0, 192), 0.5);
PDFBrush brush = new PDFBrush(new PDFRgbColor(0, 0, 0));
PDFStandardFont helvetica = new PDFStandardFont(PDFStandardFontFace.Helvetica, 8);
PDFStringAppearanceOptions sao = new PDFStringAppearanceOptions();
sao.Brush = brush;
sao.Font = helvetica;
PDFStringLayoutOptions slo = new PDFStringLayoutOptions();
slo.Width = 1000;
PDFContentExtractor ce = new PDFContentExtractor(document.Pages[2]);
PDFVisualImageCollection eic = ce.ExtractImages(false);
for (int i = 0; i < eic.Count; i++)
{
string imageProperties = string.Format("Image ID: {0}\nPixel width: {1} pixels\nPixel height: {2} pixels\n" +
"Display width: {3} points\nDisplay height: {4} points\nHorizonal Resolution: {5} dpi\nVertical Resolution: {6} dpi",
eic[i].ImageID, eic[i].Width, eic[i].Height, eic[i].DisplayWidth, eic[i].DisplayHeight, eic[i].DpiX, eic[i].DpiY);
PDFPath boundingPath = new PDFPath();
boundingPath.StartSubpath(eic[i].ImageCorners[0].X, eic[i].ImageCorners[0].Y);
boundingPath.AddLineTo(eic[i].ImageCorners[1].X, eic[i].ImageCorners[1].Y);
boundingPath.AddLineTo(eic[i].ImageCorners[2].X, eic[i].ImageCorners[2].Y);
boundingPath.AddLineTo(eic[i].ImageCorners[3].X, eic[i].ImageCorners[3].Y);
boundingPath.CloseSubpath();
document.Pages[2].Canvas.DrawPath(pen, boundingPath);
slo.X = eic[i].ImageCorners[3].X + 1;
slo.Y = eic[i].ImageCorners[3].Y + 1;
document.Pages[2].Canvas.DrawString(imageProperties, sao, slo);
}
}
static void Main(string[] args)
{
// Load the PDF file.
//PDF4NET v5: PDFDocument doc = new PDFDocument("..\\SupportFiles\\Images.pdf");
PDFFixedDocument doc = new PDFFixedDocument("..\\..\\..\\..\\..\\SupportFiles\\content.pdf");
//for (int i = 0; i < doc.Pages.Count; i++)
//{
// Convert the pages to PDFImportedPage to get access to ExtractImages method.
//PDF4NET v5: PDFImportedPage ip = doc.Pages[i] as PDFImportedPage;
PDFContentExtractor ce = new PDFContentExtractor(doc.Pages[2]);
//PDF4NET v5: Bitmap[] images = ip.ExtractImages();
PDFVisualImageCollection images = ce.ExtractImages(true);
// Save the page images to disk, if there are any.
for (int j = 0; j < images.Count; j++)
{
//PDF4NET v5: images[j].Save("image" + i.ToString() + j.ToString() + ".png", ImageFormat.Png);
FileStream fs = File.OpenWrite("image" + j.ToString() + ".png");
images[j].Save(fs, PDFVisualImageSaveFormat.Png);
fs.Flush();
fs.Close();
}
//}
}
public static void Main(string[] args)
{
string supportPath = "..\\..\\..\\..\\..\\SupportFiles\\";
FileStream input = File.OpenRead(supportPath + "content.pdf");
PDFFixedDocument document = new PDFFixedDocument(input);
input.Close();
PDFContentExtractor ce = new PDFContentExtractor(document.Pages[0]);
PDFTextSearchResultCollection searchResults = ce.SearchText("lorem");
if (searchResults.Count > 0)
{
PDFContentRedactor cr = new PDFContentRedactor(document.Pages[0]);
cr.BeginRedaction();
for (int i = 0; i < searchResults.Count; i++)
{
cr.RedactArea(searchResults[i].VisualBounds);
}
cr.ApplyRedaction();
}
using (FileStream output = File.Create("RedactedSearchResults.pdf"))
{
document.Save(output);
}
}
/// <summary>
/// Main method for running the sample.
/// </summary>
public static SampleOutputInfo[] Run(Stream input)
{
PDFFixedDocument document = new PDFFixedDocument(input);
PDFContentExtractor ce = new PDFContentExtractor(document.Pages[0]);
// Simple search.
PDFTextSearchResultCollection searchResults = ce.SearchText("at");
HighlightSearchResults(document.Pages[0], searchResults, PDFRgbColor.Red);
// Whole words search.
searchResults = ce.SearchText("at", PDFTextSearchOptions.WholeWordSearch);
HighlightSearchResults(document.Pages[0], searchResults, PDFRgbColor.Green);
// Regular expression search, find all words that start with uppercase.
searchResults = ce.SearchText("[A-Z][a-z]*", PDFTextSearchOptions.RegExSearch);
HighlightSearchResults(document.Pages[0], searchResults, PDFRgbColor.Blue);
SampleOutputInfo[] output = new SampleOutputInfo[] { new SampleOutputInfo(document, "searchtext.pdf") };
return(output);
}
/// <summary>
/// Main method for running the sample.
/// </summary>
public static SampleOutputInfo[] Run(Stream input)
{
PDFBrush brush = new PDFBrush();
PDFPen redPen = new PDFPen(PDFRgbColor.Red, 1);
PDFStandardFont helvetica = new PDFStandardFont(PDFStandardFontFace.Helvetica, 10);
PDFFixedDocument document = new PDFFixedDocument(input);
PDFContentExtractor ce = new PDFContentExtractor(document.Pages[0]);
PDFVisualObjectCollection voc = ce.ExtractVisualObjects(false);
PDFPath contour = null;
for (int i = 0; i < voc.Count; i++)
{
switch (voc[i].Type)
{
case PDFVisualObjectType.Image:
PDFImageVisualObject ivo = voc[i] as PDFImageVisualObject;
contour = new PDFPath();
contour.StartSubpath(ivo.Image.ImageCorners[0].X - 5, ivo.Image.ImageCorners[0].Y + 5);
contour.AddLineTo(ivo.Image.ImageCorners[1].X + 5, ivo.Image.ImageCorners[1].Y + 5);
contour.AddLineTo(ivo.Image.ImageCorners[2].X + 5, ivo.Image.ImageCorners[2].Y - 5);
contour.AddLineTo(ivo.Image.ImageCorners[3].X - 5, ivo.Image.ImageCorners[3].Y - 5);
contour.CloseSubpath();
document.Pages[0].Canvas.DrawPath(redPen, contour);
document.Pages[0].Canvas.DrawString("Image", helvetica, brush,
ivo.Image.ImageCorners[0].X - 5, ivo.Image.ImageCorners[0].Y + 5);
break;
case PDFVisualObjectType.Text:
PDFTextVisualObject tvo = voc[i] as PDFTextVisualObject;
contour = new PDFPath();
contour.StartSubpath(tvo.TextFragment.FragmentCorners[0].X - 5, tvo.TextFragment.FragmentCorners[0].Y + 5);
contour.AddLineTo(tvo.TextFragment.FragmentCorners[1].X + 5, tvo.TextFragment.FragmentCorners[1].Y + 5);
contour.AddLineTo(tvo.TextFragment.FragmentCorners[2].X + 5, tvo.TextFragment.FragmentCorners[2].Y - 5);
contour.AddLineTo(tvo.TextFragment.FragmentCorners[3].X - 5, tvo.TextFragment.FragmentCorners[3].Y - 5);
contour.CloseSubpath();
document.Pages[0].Canvas.DrawPath(redPen, contour);
document.Pages[0].Canvas.DrawString("Text", helvetica, brush,
tvo.TextFragment.FragmentCorners[0].X - 5, tvo.TextFragment.FragmentCorners[0].Y + 5);
break;
case PDFVisualObjectType.Path:
PDFPathVisualObject pvo = voc[i] as PDFPathVisualObject;
// Examine all the path points and determine the minimum rectangle that bounds the path.
double minX = 999999, minY = 999999, maxX = -999999, maxY = -999999;
for (int j = 0; j < pvo.PathItems.Count; j++)
{
PDFPathItem pi = pvo.PathItems[j];
if (pi.Points != null)
{
for (int k = 0; k < pi.Points.Length; k++)
{
if (minX >= pi.Points[k].X)
{
minX = pi.Points[k].X;
}
if (minY >= pi.Points[k].Y)
{
minY = pi.Points[k].Y;
}
if (maxX <= pi.Points[k].X)
{
maxX = pi.Points[k].X;
}
if (maxY <= pi.Points[k].Y)
{
maxY = pi.Points[k].Y;
}
}
}
}
contour = new PDFPath();
contour.StartSubpath(minX - 5, minY - 5);
contour.AddLineTo(maxX + 5, minY - 5);
contour.AddLineTo(maxX + 5, maxY + 5);
contour.AddLineTo(minX - 5, maxY + 5);
contour.CloseSubpath();
document.Pages[0].Canvas.DrawPath(redPen, contour);
document.Pages[0].Canvas.DrawString("Path", helvetica, brush, minX - 5, maxY + 5);
// Skip the rest of path objects, they are the evaluation message
i = voc.Count;
break;
}
}
SampleOutputInfo[] output = new SampleOutputInfo[] { new SampleOutputInfo(document, "pageobjects.pdf") };
return(output);
}