public void RunPdfTron(string input_path)
{
PDFNet.Initialize();
// string output_path = "../../../../TestFiles/Output/";
try
{
// Open the test file
PDFDoc doc = new PDFDoc(input_path);
doc.InitSecurityHandler();
PageIterator itr;
ElementReader page_reader = new ElementReader();
for (itr = doc.GetPageIterator(); itr.HasNext(); itr.Next()) // Read every page
{
int pageno = itr.GetPageNumber();
page_reader.Begin(itr.Current());
ProcessElements(page_reader);
page_reader.End();
}
page_reader.Dispose(); // Calling Dispose() on ElementReader/Writer/Builder can result in increased performance and lower memory consumption.
doc.Close();
}
catch (PDFNetException e)
{
ConsoleLog += e.Message;
}
PDFNet.Terminate();
}
static void Main(string[] args)
{
PDFNet.Initialize();
// Relative path to the folder containing test files.
string input_path = "../../TestFiles/";
try
{
Console.WriteLine("-------------------------------------------------");
Console.WriteLine("Sample 1 - Extract text data from all pages in the document.");
// Open the test file
Console.WriteLine("Opening the input pdf...");
using (PDFDoc doc = new PDFDoc(input_path + "newsletter.pdf"))
using (ElementReader page_reader = new ElementReader())
{
doc.InitSecurityHandler();
PageIterator itr;
for (itr = doc.GetPageIterator(); itr.HasNext(); itr.Next()) // Read every page
{
page_reader.Begin(itr.Current());
ProcessElements(page_reader);
page_reader.End();
}
Console.WriteLine("Done.");
}
}
catch (PDFNetException e)
{
Console.WriteLine(e.Message);
}
}
/// <summary>
/// extract text in the pdf page
/// </summary>
void ExtractText()
{
_charCode = -1;
_pageMatrix = PdfPage.GetDefaultMatrix();
_pageHeight = PdfPage.GetPageHeight();
_textLines = new PdfLineOfText[((int)_pageHeight >> 2) + 8];
using (ElementReader page_reader = new ElementReader())
{
page_reader.Begin(PdfPage);
ProcessElements(page_reader);
}
PdfLineOfText preLt = null;
for (int i = 0; i < _textLines.Length; i++)
{
var lt = _textLines[i];
if (preLt != null && lt != null && preLt.FirstChar.Top - lt.FirstChar.Top < 3)
{
preLt.AddPdfChars(lt.Chars);
_textLines[i] = lt = null;
}
preLt = lt;
}
}
// A utility method used to extract all text content from
// a given selection rectangle. The rectangle coordinates are
// expressed in PDF user/page coordinate system.
public string ReadTextFromRect(Page page, Rect pos, ElementReader reader)
{
_srch_str = "";
reader.Begin(page);
RectTextSearch(reader, pos);
reader.End();
return(_srch_str);
}
static void Main(string[] args)
{
PDFNet.Initialize();
// Relative path to the folder containing test files.
string input_path = "../../TestFiles/";
string output_path = "../../TestFiles/Output/";
string input_filename = "newsletter.pdf";
string output_filename = "newsletter_edited.pdf";
try
{
Console.WriteLine("Opening the input file...");
using (PDFDoc doc = new PDFDoc(input_path + input_filename))
{
doc.InitSecurityHandler();
ElementWriter writer = new ElementWriter();
ElementReader reader = new ElementReader();
XSet visited = new XSet();
PageIterator itr = doc.GetPageIterator();
while (itr.HasNext())
{
try
{
Page page = itr.Current();
visited.Add(page.GetSDFObj().GetObjNum());
reader.Begin(page);
writer.Begin(page, ElementWriter.WriteMode.e_replacement, false, true, page.GetResourceDict());
ProcessElements(reader, writer, visited);
writer.End();
reader.End();
itr.Next();
}
catch (PDFNetException e)
{
Console.WriteLine(e.Message);
}
}
doc.Save(output_path + output_filename, SDFDoc.SaveOptions.e_remove_unused);
Console.WriteLine("Done. Result saved in {0}...", output_filename);
}
}
catch (PDFNetException e)
{
Console.WriteLine(e.Message);
}
}
static void Main(string[] args)
{
try
{
PDFNet.Initialize();
Console.WriteLine("-------------------------------------------------");
Console.WriteLine("Extract page element information from all ");
Console.WriteLine("pages in the document.");
// Open the test file
using (PDFDoc doc = new PDFDoc(input_path + "newsletter.pdf"))
{
doc.InitSecurityHandler();
int pgnum = doc.GetPageCount();
PageIterator itr;
using (ElementReader page_reader = new ElementReader())
{
for (itr = doc.GetPageIterator(); itr.HasNext(); itr.Next()) // Read every page
{
Console.WriteLine("Page {0:d}----------------------------------------",
itr.GetPageNumber());
Rect crop_box = itr.Current().GetCropBox();
crop_box.Normalize();
// Console.WriteLine(" Page Rectangle: x={0:f} y={1:f} x2={2:f} y2={3:f}", crop_box.x1, crop_box.y1, crop_box.x2, crop_box.y2);
// Console.WriteLine(" Page Size: width={0:f} height={1:f}", crop_box.Width(), crop_box.Height());
page_reader.Begin(itr.Current());
ProcessElements(page_reader);
page_reader.End();
}
}
Console.WriteLine("Done.");
}
}
catch (PDFNetException e)
{
Console.WriteLine(e.Message);
}
}
public void ReadTextFromCoordinates(string input_path, int pagenumber, int urx, int ury, int llx, int lly)
{
PDFDoc doc = new PDFDoc(input_path);
doc.InitSecurityHandler();
Page page = doc.GetPage(pagenumber);
ElementReader reader = new ElementReader();
PageIterator itr = doc.GetPageIterator();
reader.Begin(itr.Current());
LowLevelTextExtractUtils u = new LowLevelTextExtractUtils();
//u.DumpAllText(reader);
//ConsoleLog += u.ConsoleLog;
//reader.End();
string field3 = u.ReadTextFromRect(page, new Rect(urx, ury, llx, lly), reader);
ConsoleLog = field3;
reader.Dispose();
doc.Close();
}
double GetBottomTextYValue(int pageNum, double bottomAxisValue, double topAxisValue, bool isMatchNum)
{
Page curPage = _pdfDoc.GetPage(pageNum);
List <TextAndAxisValue> values = new List <TextAndAxisValue>();
using (ElementReader pageReader = new ElementReader())
{
pageReader.Begin(curPage);
GetTextElement(pageNum, pageReader, values, bottomAxisValue, topAxisValue, isMatchNum);
}
Merge(values);
Filtrate(values);
double bottomValue = bottomAxisValue;
if (values.Count > 0)
{
double value = values.Min(x => x.yValue) - 15;
if (value > 0)
{
bottomValue = value;
}
}
return(bottomValue);
}
public SortedDictionary <double, FormLineList>[] GetFormLines(int pageNum, LinePos startPos, LinePos endPos
, bool isSubsequentPage, SortedDictionary <double, FormLineList> lastPageVerticalLines)
{
//Get the information of lines and extreme points by travelsaling the page
horizontalLines = new SortedDictionary <double, FormLineList>();
verticalLines = new SortedDictionary <double, FormLineList>();
_pageNum = pageNum;
_startPos = startPos;
_endPos = endPos;
Page page = _pdfDoc.GetPage(pageNum);
pageSize = PdfTronHelper.GetPageSize(page);
topBound.AxisValue = startPos == null ? pageSize[1] : startPos.AxisValue;
bottomBound.AxisValue = endPos == null ? 0 : endPos.AxisValue;
ii = 0;
using (ElementReader page_reader = new ElementReader())
{
page_reader.Begin(page);
ProcessElements(page_reader);
}
RemoveLittleLines(horizontalLines);
RemoveLittleLines(verticalLines);
//Remove short lines.
Rect posRect = GetTablePosRect(_pageNum, _startPos, _endPos, isSubsequentPage);
RemoveTooShortAndTooLongLines(page, horizontalLines, true, posRect);
bool isNotNeedGenerateVerLines =
isSubsequentPage && lastPageVerticalLines != null && verticalLines.Count == lastPageVerticalLines.Count;
if (!isNotNeedGenerateVerLines)
{
RemoveTooShortAndTooLongLines(page, verticalLines, false, posRect);
}
//Generate drawed lines.
Rect areaRect;
bool existRealRect = horizontalLines.Count > 1 && verticalLines.Count > 1 && IsRect(posRect, horizontalLines, verticalLines);
areaRect = existRealRect ? GenerateRectByLines() : posRect;
if (existRealRect || isSubsequentPage)
{
RemoveLinesNotInRect(areaRect, horizontalLines, verticalLines);
isNotNeedGenerateVerLines =
isSubsequentPage && lastPageVerticalLines != null && verticalLines.Count == lastPageVerticalLines.Count;
}
else
{
posRect = GetTablePosRect(_pageNum, _startPos, _endPos, true);
}
FormLineGenerator.RemoveSpareNearLines(verticalLines, false);
if (!isNotNeedGenerateVerLines)
{
isNotNeedGenerateVerLines =
isSubsequentPage && lastPageVerticalLines != null && verticalLines.Count == lastPageVerticalLines.Count;
}
FormLineGenerator lineGenerator = new FormLineGenerator(page, areaRect);
SortedDictionary <double, FormLineList>[] lines = lineGenerator.GetFormLines(existRealRect, horizontalLines, verticalLines, isNotNeedGenerateVerLines);
return(lines);
}
static void Main(string[] args)
{
PDFNet.Initialize();
// Relative path to the folder containing test files.
string input_path = "../../TestFiles/";
string output_path = "../../TestFiles/Output/";
try
{
using (PDFDoc doc = new PDFDoc())
using (ElementBuilder eb = new ElementBuilder()) // ElementBuilder is used to build new Element objects
using (ElementWriter writer = new ElementWriter()) // ElementWriter is used to write Elements to the page
{
// Start a new page ------------------------------------
// Position an image stream on several places on the page
Page page = doc.PageCreate(new Rect(0, 0, 612, 794));
writer.Begin(page); // begin writing to this page
// Create an Image that can be reused multiple times in the document or
// multiple on the same page.
MappedFile img_file = new MappedFile(input_path + "peppers.jpg");
FilterReader img_data = new FilterReader(img_file);
Image img = Image.Create(doc, img_data, 400, 600, 8, ColorSpace.CreateDeviceRGB(), Image.InputFilter.e_jpeg);
Element element = eb.CreateImage(img, new Matrix2D(200, -145, 20, 300, 200, 150));
writer.WritePlacedElement(element);
GState gstate = element.GetGState(); // use the same image (just change its matrix)
gstate.SetTransform(200, 0, 0, 300, 50, 450);
writer.WritePlacedElement(element);
// use the same image again (just change its matrix).
writer.WritePlacedElement(eb.CreateImage(img, 300, 600, 200, -150));
writer.End(); // save changes to the current page
doc.PagePushBack(page);
// Start a new page ------------------------------------
// Construct and draw a path object using different styles
page = doc.PageCreate(new Rect(0, 0, 612, 794));
writer.Begin(page); // begin writing to this page
eb.Reset(); // Reset GState to default
eb.PathBegin(); // start constructing the path
eb.MoveTo(306, 396);
eb.CurveTo(681, 771, 399.75, 864.75, 306, 771);
eb.CurveTo(212.25, 864.75, -69, 771, 306, 396);
eb.ClosePath();
element = eb.PathEnd(); // the path is now finished
element.SetPathFill(true); // the path should be filled
// Set the path color space and color
gstate = element.GetGState();
gstate.SetFillColorSpace(ColorSpace.CreateDeviceCMYK());
gstate.SetFillColor(new ColorPt(1, 0, 0, 0)); // cyan
gstate.SetTransform(0.5, 0, 0, 0.5, -20, 300);
writer.WritePlacedElement(element);
// Draw the same path using a different stroke color
element.SetPathStroke(true); // this path is should be filled and stroked
gstate.SetFillColor(new ColorPt(0, 0, 1, 0)); // yellow
gstate.SetStrokeColorSpace(ColorSpace.CreateDeviceRGB());
gstate.SetStrokeColor(new ColorPt(1, 0, 0)); // red
gstate.SetTransform(0.5, 0, 0, 0.5, 280, 300);
gstate.SetLineWidth(20);
writer.WritePlacedElement(element);
// Draw the same path with with a given dash pattern
element.SetPathFill(false); // this path is should be only stroked
gstate.SetStrokeColor(new ColorPt(0, 0, 1)); // blue
gstate.SetTransform(0.5, 0, 0, 0.5, 280, 0);
double[] dash_pattern = { 30 };
gstate.SetDashPattern(dash_pattern, 0);
writer.WritePlacedElement(element);
// Use the path as a clipping path
writer.WriteElement(eb.CreateGroupBegin()); // Save the graphics state
// Start constructing a new path (the old path was lost when we created
// a new Element using CreateGroupBegin()).
eb.PathBegin();
eb.MoveTo(306, 396);
eb.CurveTo(681, 771, 399.75, 864.75, 306, 771);
eb.CurveTo(212.25, 864.75, -69, 771, 306, 396);
eb.ClosePath();
element = eb.PathEnd(); // path is now built
element.SetPathClip(true); // this path is a clipping path
element.SetPathStroke(true); // this path is should be filled and stroked
gstate = element.GetGState();
gstate.SetTransform(0.5, 0, 0, 0.5, -20, 0);
writer.WriteElement(element);
writer.WriteElement(eb.CreateImage(img, 100, 300, 400, 600));
writer.WriteElement(eb.CreateGroupEnd()); // Restore the graphics state
writer.End(); // save changes to the current page
doc.PagePushBack(page);
// Start a new page ------------------------------------
page = doc.PageCreate(new Rect(0, 0, 612, 794));
writer.Begin(page); // begin writing to this page
eb.Reset(); // Reset GState to default
// Begin writing a block of text
element = eb.CreateTextBegin(Font.Create(doc, Font.StandardType1Font.e_times_roman), 12);
writer.WriteElement(element);
string data = "Hello World!";
element = eb.CreateTextRun(data);
element.SetTextMatrix(10, 0, 0, 10, 0, 600);
element.GetGState().SetLeading(15); // Set the spacing between lines
writer.WriteElement(element);
writer.WriteElement(eb.CreateTextNewLine()); // New line
element = eb.CreateTextRun(data);
gstate = element.GetGState();
gstate.SetTextRenderMode(GState.TextRenderingMode.e_stroke_text);
gstate.SetCharSpacing(-1.25);
gstate.SetWordSpacing(-1.25);
writer.WriteElement(element);
writer.WriteElement(eb.CreateTextNewLine()); // New line
element = eb.CreateTextRun(data);
gstate = element.GetGState();
gstate.SetCharSpacing(0);
gstate.SetWordSpacing(0);
gstate.SetLineWidth(3);
gstate.SetTextRenderMode(GState.TextRenderingMode.e_fill_stroke_text);
gstate.SetStrokeColorSpace(ColorSpace.CreateDeviceRGB());
gstate.SetStrokeColor(new ColorPt(1, 0, 0)); // red
gstate.SetFillColorSpace(ColorSpace.CreateDeviceCMYK());
gstate.SetFillColor(new ColorPt(1, 0, 0, 0)); // cyan
writer.WriteElement(element);
writer.WriteElement(eb.CreateTextNewLine()); // New line
// Set text as a clipping path to the image.
element = eb.CreateTextRun(data);
gstate = element.GetGState();
gstate.SetTextRenderMode(GState.TextRenderingMode.e_clip_text);
writer.WriteElement(element);
// Finish the block of text
writer.WriteElement(eb.CreateTextEnd());
// Draw an image that will be clipped by the above text
writer.WriteElement(eb.CreateImage(img, 10, 100, 1300, 720));
writer.End(); // save changes to the current page
doc.PagePushBack(page);
// Start a new page ------------------------------------
//
// The example illustrates how to embed the external font in a PDF document.
// The example also shows how ElementReader can be used to copy and modify
// Elements between pages.
using (ElementReader reader = new ElementReader())
{
// Start reading Elements from the last page. We will copy all Elements to
// a new page but will modify the font associated with text.
reader.Begin(doc.GetPage(doc.GetPageCount()));
page = doc.PageCreate(new Rect(0, 0, 1300, 794));
writer.Begin(page); // begin writing to this page
eb.Reset(); // Reset GState to default
// Embed an external font in the document.
Font font = Font.CreateTrueTypeFont(doc, input_path + "font.ttf");
while ((element = reader.Next()) != null) // Read page contents
{
if (element.GetType() == Element.Type.e_text)
{
element.GetGState().SetFont(font, 12);
}
writer.WriteElement(element);
}
reader.End();
writer.End(); // save changes to the current page
doc.PagePushBack(page);
// Start a new page ------------------------------------
//
// The example illustrates how to embed the external font in a PDF document.
// The example also shows how ElementReader can be used to copy and modify
// Elements between pages.
// Start reading Elements from the last page. We will copy all Elements to
// a new page but will modify the font associated with text.
reader.Begin(doc.GetPage(doc.GetPageCount()));
page = doc.PageCreate(new Rect(0, 0, 1300, 794));
writer.Begin(page); // begin writing to this page
eb.Reset(); // Reset GState to default
// Embed an external font in the document.
Font font2 = Font.CreateType1Font(doc, input_path + "Misc-Fixed.pfa");
while ((element = reader.Next()) != null) // Read page contents
{
if (element.GetType() == Element.Type.e_text)
{
element.GetGState().SetFont(font2, 12);
}
writer.WriteElement(element);
}
reader.End();
writer.End(); // save changes to the current page
doc.PagePushBack(page);
// Start a new page ------------------------------------
page = doc.PageCreate();
writer.Begin(page); // begin writing to this page
eb.Reset(); // Reset GState to default
// Begin writing a block of text
element = eb.CreateTextBegin(Font.Create(doc, Font.StandardType1Font.e_times_roman), 12);
element.SetTextMatrix(1.5, 0, 0, 1.5, 50, 600);
element.GetGState().SetLeading(15); // Set the spacing between lines
writer.WriteElement(element);
string para = "A PDF text object consists of operators that can show " +
"text strings, move the text position, and set text state and certain " +
"other parameters. In addition, there are three parameters that are " +
"defined only within a text object and do not persist from one text " +
"object to the next: Tm, the text matrix, Tlm, the text line matrix, " +
"Trm, the text rendering matrix, actually just an intermediate result " +
"that combines the effects of text state parameters, the text matrix " +
"(Tm), and the current transformation matrix";
int para_end = para.Length;
int text_run = 0;
int text_run_end;
double para_width = 300; // paragraph width is 300 units
double cur_width = 0;
while (text_run < para_end)
{
text_run_end = para.IndexOf(' ', text_run);
if (text_run_end < 0)
{
text_run_end = para_end - 1;
}
string text = para.Substring(text_run, text_run_end - text_run + 1);
element = eb.CreateTextRun(text);
if (cur_width + element.GetTextLength() < para_width)
{
writer.WriteElement(element);
cur_width += element.GetTextLength();
}
else
{
writer.WriteElement(eb.CreateTextNewLine()); // New line
text = para.Substring(text_run, text_run_end - text_run + 1);
element = eb.CreateTextRun(text);
cur_width = element.GetTextLength();
writer.WriteElement(element);
}
text_run = text_run_end + 1;
}
// -----------------------------------------------------------------------
// The following code snippet illustrates how to adjust spacing between
// characters (text runs).
element = eb.CreateTextNewLine();
writer.WriteElement(element); // Skip 2 lines
writer.WriteElement(element);
writer.WriteElement(eb.CreateTextRun("An example of space adjustments between inter-characters:"));
writer.WriteElement(eb.CreateTextNewLine());
// Write string "AWAY" without space adjustments between characters.
element = eb.CreateTextRun("AWAY");
writer.WriteElement(element);
writer.WriteElement(eb.CreateTextNewLine());
// Write string "AWAY" with space adjustments between characters.
element = eb.CreateTextRun("A");
writer.WriteElement(element);
element = eb.CreateTextRun("W");
element.SetPosAdjustment(140);
writer.WriteElement(element);
element = eb.CreateTextRun("A");
element.SetPosAdjustment(140);
writer.WriteElement(element);
element = eb.CreateTextRun("Y again");
element.SetPosAdjustment(115);
writer.WriteElement(element);
// Draw the same strings using direct content output...
writer.Flush(); // flush pending Element writing operations.
// You can also write page content directly to the content stream using
// ElementWriter.WriteString(...) and ElementWriter.WriteBuffer(...) methods.
// Note that if you are planning to use these functions you need to be familiar
// with PDF page content operators (see Appendix A in PDF Reference Manual).
// Because it is easy to make mistakes during direct output we recommend that
// you use ElementBuilder and Element interface instead.
writer.WriteString("T* T* "); // New Lines
// writer.WriteElement(eb.CreateTextNewLine());
writer.WriteString("(Direct output to PDF page content stream:) Tj T* ");
writer.WriteString("(AWAY) Tj T* ");
writer.WriteString("[(A)140(W)140(A)115(Y again)] TJ ");
// Finish the block of text
writer.WriteElement(eb.CreateTextEnd());
writer.End(); // save changes to the current page
doc.PagePushBack(page);
// Start a new page ------------------------------------
// Image Masks
//
// In the opaque imaging model, images mark all areas they occupy on the page as
// if with opaque paint. All portions of the image, whether black, white, gray,
// or color, completely obscure any marks that may previously have existed in the
// same place on the page.
// In the graphic arts industry and page layout applications, however, it is common
// to crop or 'mask out' the background of an image and then place the masked image
// on a different background, allowing the existing background to show through the
// masked areas. This sample illustrates how to use image masks.
page = doc.PageCreate();
writer.Begin(page); // begin writing to the page
// Create the Image Mask
MappedFile imgf = new MappedFile(input_path + "imagemask.dat");
FilterReader mask_read = new FilterReader(imgf);
ColorSpace device_gray = ColorSpace.CreateDeviceGray();
Image mask = Image.Create(doc, mask_read, 64, 64, 1, device_gray, Image.InputFilter.e_ascii_hex);
mask.GetSDFObj().PutBool("ImageMask", true);
element = eb.CreateRect(0, 0, 612, 794);
element.SetPathStroke(false);
element.SetPathFill(true);
element.GetGState().SetFillColorSpace(device_gray);
element.GetGState().SetFillColor(new ColorPt(0.8));
writer.WritePlacedElement(element);
element = eb.CreateImage(mask, new Matrix2D(200, 0, 0, -200, 40, 680));
element.GetGState().SetFillColor(new ColorPt(0.1));
writer.WritePlacedElement(element);
element.GetGState().SetFillColorSpace(ColorSpace.CreateDeviceRGB());
element.GetGState().SetFillColor(new ColorPt(1, 0, 0));
element = eb.CreateImage(mask, new Matrix2D(200, 0, 0, -200, 320, 680));
writer.WritePlacedElement(element);
element.GetGState().SetFillColor(new ColorPt(0, 1, 0));
element = eb.CreateImage(mask, new Matrix2D(200, 0, 0, -200, 40, 380));
writer.WritePlacedElement(element);
{
// This sample illustrates Explicit Masking.
img = Image.Create(doc, input_path + "peppers.jpg");
// mask is the explicit mask for the primary (base) image
img.SetMask(mask);
element = eb.CreateImage(img, new Matrix2D(200, 0, 0, -200, 320, 380));
writer.WritePlacedElement(element);
}
writer.End(); // save changes to the current page
doc.PagePushBack(page);
// Transparency sample ----------------------------------
// Start a new page -------------------------------------
page = doc.PageCreate();
writer.Begin(page); // begin writing to this page
eb.Reset(); // Reset the GState to default
// Write some transparent text at the bottom of the page.
element = eb.CreateTextBegin(Font.Create(doc, Font.StandardType1Font.e_times_roman), 100);
// Set the text knockout attribute. Text knockout must be set outside of
// the text group.
gstate = element.GetGState();
gstate.SetTextKnockout(false);
gstate.SetBlendMode(GState.BlendMode.e_bl_difference);
writer.WriteElement(element);
element = eb.CreateTextRun("Transparency");
element.SetTextMatrix(1, 0, 0, 1, 30, 30);
gstate = element.GetGState();
gstate.SetFillColorSpace(ColorSpace.CreateDeviceCMYK());
gstate.SetFillColor(new ColorPt(1, 0, 0, 0));
gstate.SetFillOpacity(0.5);
writer.WriteElement(element);
// Write the same text on top the old; shifted by 3 points
element.SetTextMatrix(1, 0, 0, 1, 33, 33);
gstate.SetFillColor(new ColorPt(0, 1, 0, 0));
gstate.SetFillOpacity(0.5);
writer.WriteElement(element);
writer.WriteElement(eb.CreateTextEnd());
// Draw three overlapping transparent circles.
eb.PathBegin(); // start constructing the path
eb.MoveTo(459.223, 505.646);
eb.CurveTo(459.223, 415.841, 389.85, 343.04, 304.273, 343.04);
eb.CurveTo(218.697, 343.04, 149.324, 415.841, 149.324, 505.646);
eb.CurveTo(149.324, 595.45, 218.697, 668.25, 304.273, 668.25);
eb.CurveTo(389.85, 668.25, 459.223, 595.45, 459.223, 505.646);
element = eb.PathEnd();
element.SetPathFill(true);
gstate = element.GetGState();
gstate.SetFillColorSpace(ColorSpace.CreateDeviceRGB());
gstate.SetFillColor(new ColorPt(0, 0, 1)); // Blue Circle
gstate.SetBlendMode(GState.BlendMode.e_bl_normal);
gstate.SetFillOpacity(0.5);
writer.WriteElement(element);
// Translate relative to the Blue Circle
gstate.SetTransform(1, 0, 0, 1, 113, -185);
gstate.SetFillColor(new ColorPt(0, 1, 0)); // Green Circle
gstate.SetFillOpacity(0.5);
writer.WriteElement(element);
// Translate relative to the Green Circle
gstate.SetTransform(1, 0, 0, 1, -220, 0);
gstate.SetFillColor(new ColorPt(1, 0, 0)); // Red Circle
gstate.SetFillOpacity(0.5);
writer.WriteElement(element);
writer.End(); // save changes to the current page
doc.PagePushBack(page);
// End page ------------------------------------
}
doc.Save(output_path + "element_builder.pdf", SDFDoc.SaveOptions.e_remove_unused);
Console.WriteLine("Done. Result saved in element_builder.pdf...");
}
}
catch (PDFNetException e)
{
Console.WriteLine(e.Message);
}
}
public void ReadAdvanced(string input_path)
{
PDFNet.Initialize();
try
{
PDFDoc doc = new PDFDoc(input_path);
doc.InitSecurityHandler();
Page page = doc.GetPage(1);
if (page == null)
{
ConsoleLog += "Page not found.";
return;
}
TextExtractor txt = new TextExtractor();
txt.Begin(page); // Read the page.
// Other options you may want to consider...
// txt.Begin(page, null, TextExtractor.ProcessingFlags.e_no_dup_remove);
// txt.Begin(page, null, TextExtractor.ProcessingFlags.e_remove_hidden_text);
// ...
// Example 1. Get all text on the page in a single string.
// Words will be separated with space or new line characters.
if (example1_basic)
{
// Get the word count.
ConsoleLog += "Word Count: {0}" + txt.GetWordCount();
ConsoleLog += "\n\n- GetAsText --------------------------\n{0}" + txt.GetAsText();
ConsoleLog += "-----------------------------------------------------------";
}
// Example 2. Get XML logical structure for the page.
if (example2_xml)
{
String text = txt.GetAsXML(TextExtractor.XMLOutputFlags.e_words_as_elements | TextExtractor.XMLOutputFlags.e_output_bbox | TextExtractor.XMLOutputFlags.e_output_style_info);
ConsoleLog += "\n\n- GetAsXML --------------------------\n{0}" + text;
ConsoleLog += "-----------------------------------------------------------";
}
// Example 3. Extract words one by one.
if (example3_wordlist)
{
TextExtractor.Word word;
for (TextExtractor.Line line = txt.GetFirstLine(); line.IsValid(); line = line.GetNextLine())
{
for (word = line.GetFirstWord(); word.IsValid(); word = word.GetNextWord())
{
ConsoleLog += word.GetString();
}
}
ConsoleLog += "-----------------------------------------------------------";
}
// Example 3. A more advanced text extraction example.
// The output is XML structure containing paragraphs, lines, words,
// as well as style and positioning information.
if (example4_advanced)
{
Rect bbox;
int cur_flow_id = -1, cur_para_id = -1;
TextExtractor.Line line;
TextExtractor.Word word;
TextExtractor.Style s, line_style;
// For each line on the page...
for (line = txt.GetFirstLine(); line.IsValid(); line = line.GetNextLine())
{
if (line.GetNumWords() == 0)
{
continue;
}
if (cur_flow_id != line.GetFlowID())
{
if (cur_flow_id != -1)
{
if (cur_para_id != -1)
{
cur_para_id = -1;
ConsoleLog += "</Para>";
}
ConsoleLog += "</Flow>";
}
cur_flow_id = line.GetFlowID();
ConsoleLog += "<Flow id=\"{0}\">" + cur_flow_id;
}
if (cur_para_id != line.GetParagraphID())
{
if (cur_para_id != -1)
{
ConsoleLog += "</Para>";
}
cur_para_id = line.GetParagraphID();
ConsoleLog += "<Para id=\"{0}\">" + cur_para_id;
}
bbox = line.GetBBox();
line_style = line.GetStyle();
Console.Write("<Line box=\"" + bbox.y1 + "," + bbox.y2 + "," + bbox.x1 + "," + bbox.x2 + ">");
PrintStyle(line_style);
ConsoleLog += "";
// For each word in the line...
for (word = line.GetFirstWord(); word.IsValid(); word = word.GetNextWord())
{
// Output the bounding box for the word.
bbox = word.GetBBox();
ConsoleLog += "<Word box=\"{0}, {1}, {2}, {3}\"" + bbox.x1 + bbox.y1 + bbox.x2 + bbox.y2;
int sz = word.GetStringLen();
if (sz == 0)
{
continue;
}
// If the word style is different from the parent style, output the new style.
s = word.GetStyle();
if (s != line_style)
{
PrintStyle(s);
}
ConsoleLog += ">\n" + word.GetString();
ConsoleLog += "</Word>";
}
ConsoleLog += "</Line>";
}
if (cur_flow_id != -1)
{
if (cur_para_id != -1)
{
cur_para_id = -1;
ConsoleLog += "</Para>";
}
ConsoleLog += "</Flow>";
}
}
// Note: Calling Dispose() on TextExtractor when it is not anymore in use can result in increased performance and lower memory consumption.
txt.Dispose();
doc.Close();
ConsoleLog += "Done.";
}
catch (PDFNetException e)
{
ConsoleLog += e.Message;
}
// Sample code showing how to use low-level text extraction APIs.
if (example5_low_level)
{
try
{
LowLevelTextExtractUtils util = new LowLevelTextExtractUtils();
PDFDoc doc = new PDFDoc(input_path);
doc.InitSecurityHandler();
// Example 1. Extract all text content from the document
ElementReader reader = new ElementReader();
PageIterator itr = doc.GetPageIterator();
//for (; itr.HasNext(); itr.Next()) // Read every page
{
reader.Begin(itr.Current());
LowLevelTextExtractUtils u = new LowLevelTextExtractUtils();
u.DumpAllText(reader);
ConsoleLog += u.ConsoleLog;
reader.End();
}
// Example 2. Extract text based on the selection rectangle.
ConsoleLog += "----------------------------------------------------";
ConsoleLog += "Extract text based on the selection rectangle.";
ConsoleLog += "----------------------------------------------------";
Page first_page = doc.GetPage(1);
string field1 = util.ReadTextFromRect(first_page, new Rect(27, 392, 563, 534), reader);
string field2 = util.ReadTextFromRect(first_page, new Rect(28, 551, 106, 623), reader);
string field3 = util.ReadTextFromRect(first_page, new Rect(208, 550, 387, 621), reader);
ConsoleLog += "Field 1: {0}" + field1;
ConsoleLog += "Field 2: {0}" + field2;
ConsoleLog += "Field 3: {0}" + field3;
// ...
reader.Dispose();
doc.Close();
ConsoleLog += "Done.";
}
catch (PDFNetException e)
{
ConsoleLog += e.Message;
}
}
PDFNet.Terminate();
}
static void Main(string[] args)
{
PDFNet.Initialize();
// Relative path to the folder containing test files.
string input_path = "../../TestFiles/";
bool example1_basic = false;
bool example2_xml = false;
bool example3_wordlist = false;
bool example4_advanced = true;
bool example5_low_level = false;
// Sample code showing how to use high-level text extraction APIs.
try
{
using (PDFDoc doc = new PDFDoc(input_path + "newsletter.pdf"))
{
doc.InitSecurityHandler();
Page page = doc.GetPage(1);
if (page == null)
{
Console.WriteLine("Page not found.");
return;
}
using (TextExtractor txt = new TextExtractor())
{
txt.Begin(page); // Read the page.
// Other options you may want to consider...
// txt.Begin(page, null, TextExtractor.ProcessingFlags.e_no_dup_remove);
// txt.Begin(page, null, TextExtractor.ProcessingFlags.e_remove_hidden_text);
// ...
// Example 1. Get all text on the page in a single string.
// Words will be separated with space or new line characters.
if (example1_basic)
{
// Get the word count.
Console.WriteLine("Word Count: {0}", txt.GetWordCount());
Console.WriteLine("\n\n- GetAsText --------------------------\n{0}", txt.GetAsText());
Console.WriteLine("-----------------------------------------------------------");
}
// Example 2. Get XML logical structure for the page.
if (example2_xml)
{
String text = txt.GetAsXML(TextExtractor.XMLOutputFlags.e_words_as_elements | TextExtractor.XMLOutputFlags.e_output_bbox | TextExtractor.XMLOutputFlags.e_output_style_info);
Console.WriteLine("\n\n- GetAsXML --------------------------\n{0}", text);
Console.WriteLine("-----------------------------------------------------------");
}
// Example 3. Extract words one by one.
if (example3_wordlist)
{
TextExtractor.Word word;
for (TextExtractor.Line line = txt.GetFirstLine(); line.IsValid(); line = line.GetNextLine())
{
for (word = line.GetFirstWord(); word.IsValid(); word = word.GetNextWord())
{
Console.WriteLine(word.GetString());
}
}
Console.WriteLine("-----------------------------------------------------------");
}
// Example 3. A more advanced text extraction example.
// The output is XML structure containing paragraphs, lines, words,
// as well as style and positioning information.
if (example4_advanced)
{
Rect bbox;
int cur_flow_id = -1, cur_para_id = -1;
TextExtractor.Line line;
TextExtractor.Word word;
TextExtractor.Style s, line_style;
Console.WriteLine("<PDFText>");
// For each line on the page...
for (line = txt.GetFirstLine(); line.IsValid(); line = line.GetNextLine())
{
if (line.GetNumWords() == 0)
{
continue;
}
if (cur_flow_id != line.GetFlowID())
{
if (cur_flow_id != -1)
{
if (cur_para_id != -1)
{
cur_para_id = -1;
Console.WriteLine("</Para>");
}
Console.WriteLine("</Flow>");
}
cur_flow_id = line.GetFlowID();
Console.WriteLine("<Flow id=\"{0}\">", cur_flow_id);
}
if (cur_para_id != line.GetParagraphID())
{
if (cur_para_id != -1)
{
Console.WriteLine("</Para>");
}
cur_para_id = line.GetParagraphID();
Console.WriteLine("<Para id=\"{0}\">", cur_para_id);
}
bbox = line.GetBBox();
line_style = line.GetStyle();
Console.Write("<Line box=\"{0}, {1}, {2}, {3}\"", bbox.x1.ToString("0.00"), bbox.y1.ToString("0.00"), bbox.x2.ToString("0.00"), bbox.y2.ToString("0.00"));
PrintStyle(line_style);
Console.Write(" cur_num=\"" + line.GetCurrentNum() + "\"" + ">\n");
// For each word in the line...
for (word = line.GetFirstWord(); word.IsValid(); word = word.GetNextWord())
{
// Output the bounding box for the word.
bbox = word.GetBBox();
Console.Write("<Word box=\"{0}, {1}, {2}, {3}\"", bbox.x1.ToString("0.00"), bbox.y1.ToString("0.00"), bbox.x2.ToString("0.00"), bbox.y2.ToString("0.00"));
Console.Write(" cur_num=\"" + word.GetCurrentNum() + "\"");
int sz = word.GetStringLen();
if (sz == 0)
{
continue;
}
// If the word style is different from the parent style, output the new style.
s = word.GetStyle();
if (s != line_style)
{
PrintStyle(s);
}
Console.Write(">{0}", word.GetString());
Console.WriteLine("</Word>");
}
Console.WriteLine("</Line>");
}
if (cur_flow_id != -1)
{
if (cur_para_id != -1)
{
cur_para_id = -1;
Console.WriteLine("</Para>");
}
Console.WriteLine("</Flow>");
}
}
}
Console.WriteLine("</PDFText>");
}
}
catch (PDFNetException e)
{
Console.WriteLine(e.Message);
}
// Sample code showing how to use low-level text extraction APIs.
if (example5_low_level)
{
try
{
LowLevelTextExtractUtils util = new LowLevelTextExtractUtils();
using (PDFDoc doc = new PDFDoc(input_path + "newsletter.pdf"))
{
doc.InitSecurityHandler();
// Example 1. Extract all text content from the document
using (ElementReader reader = new ElementReader())
{
PageIterator itr = doc.GetPageIterator();
//for (; itr.HasNext(); itr.Next()) // Read every page
{
reader.Begin(itr.Current());
LowLevelTextExtractUtils.DumpAllText(reader);
reader.End();
}
// Example 2. Extract text based on the selection rectangle.
Console.WriteLine("----------------------------------------------------");
Console.WriteLine("Extract text based on the selection rectangle.");
Console.WriteLine("----------------------------------------------------");
Page first_page = doc.GetPage(1);
string field1 = util.ReadTextFromRect(first_page, new Rect(27, 392, 563, 534), reader);
string field2 = util.ReadTextFromRect(first_page, new Rect(28, 551, 106, 623), reader);
string field3 = util.ReadTextFromRect(first_page, new Rect(208, 550, 387, 621), reader);
Console.WriteLine("Field 1: {0}", field1);
Console.WriteLine("Field 2: {0}", field2);
Console.WriteLine("Field 3: {0}", field3);
// ...
Console.WriteLine("Done.");
}
}
}
catch (PDFNetException e)
{
Console.WriteLine(e.Message);
}
}
}
/// <summary>
/// The main entry point for the application.
/// </summary>
static void Main(string[] args)
{
PDFNet.Initialize();
// Relative path to the folder containing test files.
string input_path = "../../TestFiles/";
string output_path = "../../TestFiles/Output/";
try // Extract logical structure from a PDF document
{
using (PDFDoc doc = new PDFDoc(input_path + "tagged.pdf"))
{
doc.InitSecurityHandler();
bool example1 = true;
bool example2 = true;
bool example3 = true;
if (example1)
{
Console.WriteLine("____________________________________________________________");
Console.WriteLine("Sample 1 - Traverse logical structure tree...");
STree tree = doc.GetStructTree();
if (tree.IsValid())
{
Console.WriteLine("Document has a StructTree root.");
for (int i = 0; i < tree.GetNumKids(); ++i)
{
// Recursively get structure info for all all child elements.
ProcessStructElement(tree.GetKid(i), 0);
}
}
else
{
Console.WriteLine("This document does not contain any logical structure.");
}
Console.WriteLine();
Console.WriteLine("Done 1.");
}
if (example2)
{
Console.WriteLine("____________________________________________________________");
Console.WriteLine("Sample 2 - Get parent logical structure elements from");
Console.WriteLine("layout elements.");
ElementReader reader = new ElementReader();
for (PageIterator itr = doc.GetPageIterator(); itr.HasNext(); itr.Next())
{
reader.Begin(itr.Current());
ProcessElements(reader);
reader.End();
}
Console.WriteLine();
Console.WriteLine("Done 2.");
}
if (example3)
{
Console.WriteLine("____________________________________________________________");
Console.WriteLine("Sample 3 - 'XML style' extraction of PDF logical structure and page content.");
//A map which maps page numbers(as Integers)
//to page Maps(which map from struct mcid(as Integers) to
//text Strings)
Hashtable mcid_doc_map = new Hashtable();
ElementReader reader = new ElementReader();
for (PageIterator itr = doc.GetPageIterator(); itr.HasNext(); itr.Next())
{
Page pg = itr.Current();
reader.Begin(pg);
Hashtable page_mcid_map = new Hashtable();
mcid_doc_map.Add(pg.GetIndex(), page_mcid_map);
ProcessElements2(reader, page_mcid_map);
reader.End();
}
STree tree = doc.GetStructTree();
if (tree.IsValid())
{
for (int i = 0; i < tree.GetNumKids(); ++i)
{
ProcessStructElement2(tree.GetKid(i), mcid_doc_map, 0);
}
}
Console.WriteLine();
Console.WriteLine("Done 3.");
}
doc.Save(output_path + "bookmark.pdf", 0);
}
}
catch (PDFNetException e)
{
Console.WriteLine(e.Message);
}
}
static void Main(string[] args)
{
PDFNet.Initialize();
// Relative path to the folder containing test files.
string input_path = "../../TestFiles/";
string output_path = "../../TestFiles/Output/";
try
{
// Read a PDF document from a stream or pass-in a memory buffer...
FileStream istm = new FileStream(input_path + "tiger.pdf", FileMode.Open, FileAccess.Read);
using (PDFDoc doc = new PDFDoc(istm))
using (ElementWriter writer = new ElementWriter())
using (ElementReader reader = new ElementReader())
{
doc.InitSecurityHandler();
int num_pages = doc.GetPageCount();
Element element;
// Perform some document editing ...
// Here we simply copy all elements from one page to another.
for (int i = 1; i <= num_pages; ++i)
{
Page pg = doc.GetPage(2 * i - 1);
reader.Begin(pg);
Page new_page = doc.PageCreate(pg.GetMediaBox());
doc.PageInsert(doc.GetPageIterator(2 * i), new_page);
writer.Begin(new_page);
while ((element = reader.Next()) != null) // Read page contents
{
writer.WriteElement(element);
}
writer.End();
reader.End();
}
doc.Save(output_path + "doc_memory_edit.pdf", SDFDoc.SaveOptions.e_remove_unused);
// Save the document to a stream or a memory buffer...
using (FileStream ostm = new FileStream(output_path + "doc_memory_edit.txt", FileMode.Create, FileAccess.Write)) {
doc.Save(ostm, SDFDoc.SaveOptions.e_remove_unused);
}
// Read some data from the file stored in memory
reader.Begin(doc.GetPage(1));
while ((element = reader.Next()) != null)
{
if (element.GetType() == Element.Type.e_path)
{
Console.Write("Path, ");
}
}
reader.End();
Console.WriteLine("");
Console.WriteLine("");
Console.WriteLine("Done. Result saved in doc_memory_edit.pdf and doc_memory_edit.txt ...");
}
}
catch (PDFNetException e)
{
Console.WriteLine(e.Message);
}
}
static void Main(string[] args)
{
PDFNet.Initialize();
// Example 1:
// Extract images by traversing the display list for
// every page. With this approach it is possible to obtain
// image positioning information and DPI.
try
{
using (PDFDoc doc = new PDFDoc(input_path + "newsletter.pdf"))
using (ElementReader reader = new ElementReader())
{
doc.InitSecurityHandler();
PageIterator itr;
for (itr = doc.GetPageIterator(); itr.HasNext(); itr.Next())
{
reader.Begin(itr.Current());
ImageExtract(doc, reader);
reader.End();
}
Console.WriteLine("Done.");
}
}
catch (PDFNetException e)
{
Console.WriteLine(e.Message);
}
Console.WriteLine("----------------------------------------------------------------");
// Example 2:
// Extract images by scanning the low-level document.
try
{
using (PDFDoc doc = new PDFDoc(input_path + "newsletter.pdf"))
{
doc.InitSecurityHandler();
image_counter = 0;
SDFDoc cos_doc = doc.GetSDFDoc();
int num_objs = cos_doc.XRefSize();
for (int i = 1; i < num_objs; ++i)
{
Obj obj = cos_doc.GetObj(i);
if (obj != null && !obj.IsFree() && obj.IsStream())
{
// Process only images
DictIterator itr = obj.Find("Subtype");
if (!itr.HasNext() || itr.Value().GetName() != "Image")
{
continue;
}
itr = obj.Find("Type");
if (!itr.HasNext() || itr.Value().GetName() != "XObject")
{
continue;
}
pdftron.PDF.Image image = new pdftron.PDF.Image(obj);
Console.WriteLine("--> Image: {0}", ++image_counter);
Console.WriteLine(" Width: {0}", image.GetImageWidth());
Console.WriteLine(" Height: {0}", image.GetImageHeight());
Console.WriteLine(" BPC: {0}", image.GetBitsPerComponent());
string fname = output_path + "image_extract2_" + image_counter.ToString();
image.Export(fname); // or ExporAsPng() or ExporAsTiff() ...
// Convert PDF bitmap to GDI+ Bitmap...
//Bitmap bmp = image.GetBitmap();
//bmp.Save(fname, ImageFormat.Png);
//bmp.Dispose();
// Instead of converting PDF images to a Bitmap, you can also extract
// uncompressed/compressed image data directly using element.GetImageData()
// as illustrated in ElementReaderAdv sample project.
}
}
}
}
catch (PDFNetException e)
{
Console.WriteLine(e.Message);
}
}