/// <summary>Extract text from a specified page using an extraction strategy.</summary>
/// <remarks>
/// Extract text from a specified page using an extraction strategy.
/// Also allows registration of custom IContentOperators that can influence
/// how (and whether or not) the PDF instructions will be parsed.
/// </remarks>
/// <param name="page">the page for the text to be extracted from</param>
/// <param name="strategy">the strategy to use for extracting text</param>
/// <param name="additionalContentOperators">
/// an optional map of custom
/// <see cref="IContentOperator"/>
/// s for rendering instructions
/// </param>
/// <returns>the extracted text</returns>
public static String GetTextFromPage(PdfPage page, ITextExtractionStrategy strategy, IDictionary <String, IContentOperator
> additionalContentOperators)
{
PdfCanvasProcessor parser = new PdfCanvasProcessor(strategy, additionalContentOperators);
parser.ProcessPageContent(page);
return(strategy.GetResultantText());
}
public virtual void TestCharacterRenderInfos()
{
PdfCanvasProcessor parser = new PdfCanvasProcessor(new TextRenderInfoTest.CharacterPositionEventListener()
);
parser.ProcessPageContent(new PdfDocument(new PdfReader(sourceFolder + "simple_text.pdf")).GetPage(FIRST_PAGE
));
}
/// <summary>Processes content from the specified page number using the specified listener.</summary>
/// <remarks>
/// Processes content from the specified page number using the specified listener.
/// Also allows registration of custom IContentOperators that can influence
/// how (and whether or not) the PDF instructions will be parsed.
/// </remarks>
///
/// <param name="pageNumber">the page number to process</param>
/// <param name="renderListener">the listener that will receive render callbacks</param>
/// <param name="additionalContentOperators">an optional map of custom ContentOperators for rendering instructions
/// </param>
/// <returns>the provided renderListener</returns>
public virtual E ProcessContent <E>(int pageNumber, E renderListener, IDictionary <String, IContentOperator>
additionalContentOperators)
where E : IEventListener
{
PdfCanvasProcessor processor = new PdfCanvasProcessor(renderListener, additionalContentOperators);
processor.ProcessPageContent(pdfDocument.GetPage(pageNumber));
return(renderListener);
}
public virtual void TestClosingEmptyPath()
{
String fileName = "closingEmptyPath.pdf";
PdfDocument document = new PdfDocument(new PdfReader(sourceFolder + fileName));
PdfCanvasProcessor processor = new PdfCanvasProcessor(new PdfCanvasProcessorTest.NoOpEventListener());
// Assert than no exception is thrown when an empty path is handled
processor.ProcessPageContent(document.GetPage(1));
}
/// <summary>
/// Process a PDF page to retrieve tables data from it.
/// </summary>
/// <param name="pdfPage">the pdf page which to process</param>
/// <param name="withBorder">true if tables have fully borders, false otherwise</param>
public FilterTableEventListener(PdfPage pdfPage, bool withBorder)
{
if (withBorder)
{
this.pdfPage = pdfPage;
PdfCanvasProcessor processor = new PdfCanvasProcessor(this);
processor.ProcessPageContent(pdfPage);
GetTablesFromborders();
}
}
static void AnalyzeTextFromListener(string filename)
{
using (var pdf = new PdfDocument(new PdfReader(filename)))
{
var page = pdf.GetFirstPage();
var parser = new PdfCanvasProcessor(new AnalyzeTextListener());
parser.ProcessPageContent(page);
}
}
public static string GetResultantText(string fileName)
{
using (var pdfDoc = new PdfDocument(new PdfReader(fileName)))
{
var strategy = new LocationTextExtractionStrategy();
var parser = new PdfCanvasProcessor(strategy);
parser.ProcessPageContent(pdfDoc.GetFirstPage());
var text = strategy.GetResultantText();
return(text);
}
}
static void ShowLinesFromListener(string filename)
{
using (var pdf = new PdfDocument(new PdfReader(filename)))
{
var page = pdf.GetFirstPage();
var parser = new PdfCanvasProcessor(new UserPathListener());
parser.ProcessPageContent(page);
}
}
public virtual void ContentStreamProcessorTest()
{
PdfDocument document = new PdfDocument(new PdfReader(sourceFolder + "yaxiststar.pdf"), new PdfWriter(new ByteArrayOutputStream
()));
for (int i = 1; i <= document.GetNumberOfPages(); ++i)
{
PdfPage page = document.GetPage(i);
PdfCanvasProcessor processor = new PdfCanvasProcessor(new _IEventListener_40());
processor.ProcessPageContent(page);
}
}
public virtual void ExpectedByteAlignedTiffImageExtractionTest()
{
NUnit.Framework.Assert.That(() => {
//Byte-aligned image is expected in pdf file, but in fact it's not
String inFileName = sourceFolder + "expectedByteAlignedTiffImageExtraction.pdf";
PdfDocument pdfDocument = new PdfDocument(new PdfReader(inFileName));
GetImageBytesTest.ImageExtractor listener = new GetImageBytesTest.ImageExtractor(this);
PdfCanvasProcessor processor = new PdfCanvasProcessor(listener);
processor.ProcessPageContent(pdfDocument.GetPage(1));
}
, NUnit.Framework.Throws.InstanceOf <iText.IO.IOException>().With.Message.EqualTo(MessageFormatUtil.Format(iText.IO.IOException.ExpectedTrailingZeroBitsForByteAlignedLines)))
;
}
private ICollection <Rectangle> ProcessPage(ILocationExtractionStrategy strategy, PdfPage page)
{
PdfCanvasProcessor parser = new PdfCanvasProcessor(strategy);
parser.ProcessPageContent(page);
IList <Rectangle> retval = new List <Rectangle>();
foreach (IPdfTextLocation l in strategy.GetResultantLocations())
{
retval.Add(l.GetRectangle());
}
return(retval);
}
/// <summary>Get extraction strategy for given document.</summary>
public static ExtractionStrategy GetExtractionStrategy(String pdfPath, String layerName, bool useActualText
)
{
PdfDocument pdfDocument = new PdfDocument(new PdfReader(pdfPath));
ExtractionStrategy strategy = new ExtractionStrategy(layerName);
strategy.SetUseActualText(useActualText);
PdfCanvasProcessor processor = new PdfCanvasProcessor(strategy);
processor.ProcessPageContent(pdfDocument.GetFirstPage());
pdfDocument.Close();
return(strategy);
}
public virtual void CheckBboxCalculationForType3FontsWithFontMatrix02()
{
String inputPdf = sourceFolder + "checkBboxCalculationForType3FontsWithFontMatrix02.pdf";
PdfDocument pdfDocument = new PdfDocument(new PdfReader(inputPdf));
GlyphBboxCalculationTest.CharacterPositionEventListener listener = new GlyphBboxCalculationTest.CharacterPositionEventListener
();
PdfCanvasProcessor processor = new PdfCanvasProcessor(listener);
processor.ProcessPageContent(pdfDocument.GetPage(1));
// font size (36) * |fontMatrix| (1) * glyph width (0.6) = 21.6
NUnit.Framework.Assert.AreEqual(21.6, listener.glyphWith, 1e-5);
}
public virtual void ParseCircularReferencesInResourcesTest()
{
NUnit.Framework.Assert.That(() => {
String fileName = "circularReferencesInResources.pdf";
PdfDocument pdfDocument = new PdfDocument(new PdfReader(sourceFolder + fileName));
PdfCanvasProcessor processor = new PdfCanvasProcessor(new PdfCanvasProcessorTest.NoOpEventListener());
PdfPage page = pdfDocument.GetFirstPage();
processor.ProcessPageContent(page);
pdfDocument.Close();
}
, NUnit.Framework.Throws.InstanceOf <OutOfMemoryException>())
;
}
/// <summary>Processes content from the specified page number using the specified listener.</summary>
/// <remarks>
/// Processes content from the specified page number using the specified listener.
/// Also allows registration of custom ContentOperators
/// </remarks>
///
/// <param name="pageNumber">the page number to process</param>
/// <param name="renderListener">the listener that will receive render callbacks</param>
/// <param name="additionalContentOperators">an optional map of custom ContentOperators for rendering instructions
/// </param>
/// <returns>the provided renderListener</returns>
public virtual E ProcessContent <E>(int pageNumber, E renderListener, IDictionary <String, IContentOperator>
additionalContentOperators)
where E : IEventListener
{
PdfCanvasProcessor processor = new PdfCanvasProcessor(renderListener);
foreach (KeyValuePair <String, IContentOperator> entry in additionalContentOperators)
{
processor.RegisterContentOperator(entry.Key, entry.Value);
}
processor.ProcessPageContent(pdfDocument.GetPage(pageNumber));
return(renderListener);
}
public virtual void CheckAverageBboxCalculationForType3FontsWithFontMatrix01Test()
{
String inputPdf = sourceFolder + "checkAverageBboxCalculationForType3FontsWithFontMatrix01.pdf";
PdfDocument pdfDocument = new PdfDocument(new PdfReader(inputPdf));
GlyphBboxCalculationTest.CharacterPositionEventListener listener = new GlyphBboxCalculationTest.CharacterPositionEventListener
();
PdfCanvasProcessor processor = new PdfCanvasProcessor(listener);
processor.ProcessPageContent(pdfDocument.GetPage(1));
NUnit.Framework.Assert.AreEqual(600, listener.firstTextRenderInfo.GetFont().GetFontProgram().GetAvgWidth()
, 0.01f);
}
public void BackgroundTest(string exeFileName, string commandLineParameter, bool expectedBackground)
{
HtmlToPdfRunner runner = new HtmlToPdfRunner(exeFileName);
string html = @"<!DOCTYPE html>
<html>
<head>
</head>
<body style=""background-color:blue;"">
Test Page
</body>
</html>";
using (TempHtmlFile htmlFile = new TempHtmlFile(html))
{
using (TempPdfFile pdfFile = new TempPdfFile(this.TestContext))
{
string commandLine = string.Empty;
if (!string.IsNullOrEmpty(commandLineParameter))
{
commandLine += $"{commandLineParameter} ";
}
commandLine += $"\"{htmlFile.FilePath}\" \"{pdfFile.FilePath}\"";
HtmlToPdfRunResult result = runner.Run(commandLine);
Assert.AreEqual(0, result.ExitCode, result.Output);
using (PdfReader pdfReader = new PdfReader(pdfFile.FilePath))
{
using (PdfDocument pdfDocument = new PdfDocument(pdfReader))
{
int pageCount = pdfDocument.GetNumberOfPages();
Assert.AreEqual(1, pageCount);
PdfPage page = pdfDocument.GetPage(1);
RectangleFinder rectangleFinder = new RectangleFinder();
PdfCanvasProcessor processor = new PdfCanvasProcessor(rectangleFinder);
processor.ProcessPageContent(page);
ICollection <Rectangle> boxes = rectangleFinder.GetBoundingBoxes();
Assert.AreEqual(expectedBackground ? 1 : 0, boxes.Count());
}
}
}
}
}
/// <summary>Get text from layer specified by name from page.</summary>
protected internal virtual String GetTextFromPdfLayer(String pdfPath, String layerName, int page, bool useActualText
)
{
PdfDocument pdfDocument = new PdfDocument(new PdfReader(pdfPath), new DocumentProperties().SetEventCountingMetaInfo
(new PdfOcrMetaInfo()));
IntegrationTestHelper.ExtractionStrategy textExtractionStrategy = new IntegrationTestHelper.ExtractionStrategy
(layerName);
textExtractionStrategy.SetUseActualText(useActualText);
PdfCanvasProcessor processor = new PdfCanvasProcessor(textExtractionStrategy);
processor.ProcessPageContent(pdfDocument.GetPage(page));
pdfDocument.Close();
return(textExtractionStrategy.GetResultantText());
}
public static string GetPDFFromFile(string path)
{
PdfDocument pdfDoc = new PdfDocument(new PdfReader(path));
LocationTextExtractionStrategy strategy = new LocationTextExtractionStrategy();
PdfCanvasProcessor parser = new PdfCanvasProcessor(strategy);
// Known limitation: read more than one page. Sample documents are all one page long.
parser.ProcessPageContent(pdfDoc.GetFirstPage());
pdfDoc.Close();
return(strategy.GetResultantText());
}
public virtual void TestNoninvertibleMatrix()
{
String fileName = "noninvertibleMatrix.pdf";
PdfDocument pdfDocument = new PdfDocument(new PdfReader(sourceFolder + fileName));
LocationTextExtractionStrategy strategy = new LocationTextExtractionStrategy();
PdfCanvasProcessor processor = new PdfCanvasProcessor(strategy);
PdfPage page = pdfDocument.GetFirstPage();
processor.ProcessPageContent(page);
String resultantText = strategy.GetResultantText();
pdfDocument.Close();
NUnit.Framework.Assert.AreEqual("Hello World!\nHello World!\nHello World!\nHello World! Hello World! Hello World!"
, resultantText);
}
public virtual void ProcessGraphicsStateResourceOperatorFillOpacityTest()
{
PdfDocument document = new PdfDocument(new PdfReader(sourceFolder + "transparentText.pdf"));
float? expOpacity = 0.5f;
IDictionary <String, Object> textRenderInfo = new Dictionary <String, Object>();
for (int i = 1; i <= document.GetNumberOfPages(); ++i)
{
PdfPage page = document.GetPage(i);
PdfCanvasProcessor processor = new PdfCanvasProcessor(new PdfCanvasProcessorIntegrationTest.RecordEveryTextRenderEvent
(textRenderInfo));
processor.ProcessPageContent(page);
}
NUnit.Framework.Assert.AreEqual(expOpacity, textRenderInfo.Get("FillOpacity"), "Expected fill opacity not found"
);
}
public virtual void PatternColorParsingNotValidPdfTest()
{
String inputFile = sourceFolder + "patternColorParsingNotValidPdfTest.pdf";
PdfDocument pdfDocument = new PdfDocument(new PdfReader(inputFile));
for (int i = 1; i <= pdfDocument.GetNumberOfPages(); ++i)
{
PdfPage page = pdfDocument.GetPage(i);
PdfCanvasProcessorIntegrationTest.ColorParsingEventListener colorParsingEventListener = new PdfCanvasProcessorIntegrationTest.ColorParsingEventListener
();
PdfCanvasProcessor processor = new PdfCanvasProcessor(colorParsingEventListener);
processor.ProcessPageContent(page);
Color renderInfo = colorParsingEventListener.GetEncounteredPath().GetFillColor();
NUnit.Framework.Assert.IsNull(renderInfo);
}
}
private ICollection <string> GetPDF(string filename)
{
var pageText = new List <string>();
using (PdfDocument pdfDocument = new PdfDocument(new PdfReader(filename)))
{
var pageNumbers = pdfDocument.GetNumberOfPages();
for (int i = 1; i <= pageNumbers; i++)
{
LocationTextExtractionStrategy strategy = new LocationTextExtractionStrategy();
PdfCanvasProcessor parser = new PdfCanvasProcessor(strategy);
parser.ProcessPageContent(pdfDocument.GetPage(i));
pageText.Add(strategy.GetResultantText());
}
}
return(pageText);
}
public virtual void PatternColorParsingValidPdfTest()
{
String inputFile = sourceFolder + "patternColorParsingValidPdfTest.pdf";
PdfDocument pdfDocument = new PdfDocument(new PdfReader(inputFile));
for (int i = 1; i <= pdfDocument.GetNumberOfPages(); ++i)
{
PdfPage page = pdfDocument.GetPage(i);
PdfCanvasProcessorIntegrationTest.ColorParsingEventListener colorParsingEventListener = new PdfCanvasProcessorIntegrationTest.ColorParsingEventListener
();
PdfCanvasProcessor processor = new PdfCanvasProcessor(colorParsingEventListener);
processor.ProcessPageContent(page);
PathRenderInfo renderInfo = colorParsingEventListener.GetEncounteredPath();
PdfColorSpace colorSpace = renderInfo.GetGraphicsState().GetFillColor().GetColorSpace();
NUnit.Framework.Assert.IsTrue(colorSpace is PdfSpecialCs.Pattern);
}
}
public virtual void TestType3FontWidth()
{
String inFile = "type3font_text.pdf";
LineSegment origLineSegment = new LineSegment(new Vector(20.3246f, 769.4974f, 1.0f), new Vector(151.22923f
, 769.4974f, 1.0f));
PdfDocument pdfDocument = new PdfDocument(new PdfReader(sourceFolder + inFile));
TextRenderInfoTest.TextPositionEventListener renderListener = new TextRenderInfoTest.TextPositionEventListener
();
PdfCanvasProcessor processor = new PdfCanvasProcessor(renderListener);
processor.ProcessPageContent(pdfDocument.GetPage(FIRST_PAGE));
NUnit.Framework.Assert.AreEqual(renderListener.GetLineSegments()[FIRST_ELEMENT_INDEX].GetStartPoint().Get(
FIRST_ELEMENT_INDEX), origLineSegment.GetStartPoint().Get(FIRST_ELEMENT_INDEX), 1 / 2f);
NUnit.Framework.Assert.AreEqual(renderListener.GetLineSegments()[FIRST_ELEMENT_INDEX].GetEndPoint().Get(FIRST_ELEMENT_INDEX
), origLineSegment.GetEndPoint().Get(FIRST_ELEMENT_INDEX), 1 / 2f);
}
public void ToTxt(string absoluteFilePath, string outputPath)
{
using (var pdfDocument = new PdfDocument(new PdfReader(absoluteFilePath)))
{
for (var pageIndex = 1; pageIndex <= pdfDocument.GetNumberOfPages(); pageIndex++)
{
using (var fos = System.IO.File.OpenWrite(outputPath))
{
var strategy = new LocationTextExtractionStrategy();
var parser = new PdfCanvasProcessor(strategy);
parser.ProcessPageContent(pdfDocument.GetPage(pageIndex));
var array = Encoding.UTF8.GetBytes(strategy.GetResultantText());
fos.Write(array, 0, array.Length);
fos.Flush();
}
}
}
}
//converting pdf to a txt file
public static void getTextFromPdf(String dest)
{
PdfDocument pdfDoc = new PdfDocument(new PdfReader(SRC));
SimpleTextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
PdfCanvasProcessor parser = new PdfCanvasProcessor(strategy);
for (var i = 1; i <= pdfDoc.GetNumberOfPages(); i++)
{
parser.ProcessPageContent(pdfDoc.GetPage(i));
byte[] array = Encoding.UTF8.GetBytes(strategy.GetResultantText());
using (FileStream stream = new FileStream(dest, FileMode.OpenOrCreate))
{
stream.Write(array, 0, array.Length);
}
}
}
public virtual void TestImageWithoutText()
{
String testName = "testImageWithoutText";
String filePath = TEST_IMAGES_DIRECTORY + "pantone_blue.jpg";
String pdfPath = GetTargetDirectory() + testName + ".pdf";
FileInfo file = new FileInfo(filePath);
OcrPdfCreator ocrPdfCreator = new OcrPdfCreator(tesseractReader);
ocrPdfCreator.CreatePdf(JavaCollectionsUtil.SingletonList <FileInfo>(file), new PdfWriter(pdfPath)).Close();
PdfDocument pdfDocument = new PdfDocument(new PdfReader(pdfPath));
IntegrationTestHelper.ExtractionStrategy strategy = new IntegrationTestHelper.ExtractionStrategy("Text Layer"
);
PdfCanvasProcessor processor = new PdfCanvasProcessor(strategy);
processor.ProcessPageContent(pdfDocument.GetFirstPage());
pdfDocument.Close();
NUnit.Framework.Assert.AreEqual("", strategy.GetResultantText());
}
public virtual void ExtractSingleInlineImageWithIndexedColorSpaceTest()
{
PdfDocument pdf = new PdfDocument(new PdfReader(sourceFolder + "inlineImageExtraction.pdf"));
InlineImageExtractionTest.InlineImageEventListener eventListener = new InlineImageExtractionTest.InlineImageEventListener
();
PdfCanvasProcessor canvasProcessor = new PdfCanvasProcessor(eventListener);
canvasProcessor.ProcessPageContent(pdf.GetFirstPage());
pdf.Close();
IList <PdfStream> inlineImages = eventListener.GetInlineImages();
NUnit.Framework.Assert.AreEqual(1, inlineImages.Count);
byte[] imgBytes = inlineImages[0].GetBytes();
byte[] cmpImgBytes = File.ReadAllBytes(Path.Combine(sourceFolder, "imgtest.dat"));
NUnit.Framework.Assert.AreEqual(cmpImgBytes, imgBytes);
PdfDictionary expectedDict = new PdfDictionary();
expectedDict.Put(PdfName.BitsPerComponent, new PdfNumber(8));
expectedDict.Put(PdfName.Height, new PdfNumber(50));
expectedDict.Put(PdfName.Width, new PdfNumber(50));
String indexedCsLookupData = "\u007F\u007F\u007Fïïï\u000F\u000F\u000F???¿¿¿ÏÏÏ///\u001F\u001F\u001F___ßßß"
+ "\u009F\u009F\u009FOOO¯¯¯ooo\u008F\u008F\u008F°°µ::<ââàuuy,,-ÜÜâ\u000E\u000E\u000Fúúû\u001D\u001D\u001E"
+ "ððõXXZ::?\u0004\u0004\u0004226!!$IIK\u0019\u0019\u001Býýþ\u0092\u0092\u0097õõø\f\f\r" + "))-÷÷úììòÍÍÓ66;\b\b\t\u0084\u0084\u0088¡¡¦îîô\u0014\u0014\u0016òòö\u0010\u0010\u0012¾¾Äffiüüýóó÷..2ûûü"
+ "ööù%%)ííó\u001D\u001D\u001F>>Døøúññö\u000E\u000E\u000Eééç\u008D\u008D\u008CÓÓÒCCI©©¨\u009B\u009B\u009A"
+ "òòñôôózz|888÷÷÷ììëÝÝãµµ¸bbb\u0095\u0095\u0098··¶ûûûºº¼\u0089\u0089\u008Bååãêêë==>ÑÑÖ***qqpààåZZ\\õõõ"
+ "\u007F\u007F~\u008E\u008E\u008E\u001E\u001E\u001FÀÀÅååèÆÆÅççåÇÇÊ\u001C\u001C\u001C]]^±±¶TTTççêÉÉÇFFFáá"
+ "æÅÅÄyy{ÍÍÎÐÐÕ^^^vvyîîí\u0087\u0087\u008A}}}xxzÊÊËjjl--.ëëò\u0000\u0000\u0000ÿÿÿ{{{|||}}}~~~\u007F\u007F"
+ "\u007F\u0080\u0080\u0080\u0081\u0081\u0081\u0082\u0082\u0082\u0083\u0083\u0083\u0084\u0084\u0084\u0085"
+ "\u0085\u0085\u0086\u0086\u0086\u0087\u0087\u0087\u0088\u0088\u0088\u0089\u0089\u0089\u008A\u008A\u008A"
+ "\u008B\u008B\u008B\u008C\u008C\u008C\u008D\u008D\u008D\u008E\u008E\u008E\u008F\u008F\u008F\u0090\u0090"
+ "\u0090\u0091\u0091\u0091\u0092\u0092\u0092\u0093\u0093\u0093\u0094\u0094\u0094\u0095\u0095\u0095\u0096"
+ "\u0096\u0096\u0097\u0097\u0097\u0098\u0098\u0098\u0099\u0099\u0099\u009A\u009A\u009A\u009B\u009B\u009B"
+ "\u009C\u009C\u009C\u009D\u009D\u009D\u009E\u009E\u009E\u009F\u009F\u009F ¡¡¡¢¢¢£££¤¤¤¥¥¥¦¦¦§§§¨¨¨©©©"
+ "ªªª«««¬¬¬\u00AD\u00AD\u00AD®®®¯¯¯°°°±±±²²²³³³´´´µµµ¶¶¶···¸¸¸¹¹¹ººº»»»¼¼¼½½½¾¾¾¿¿¿ÀÀÀÁÁÁÂÂÂÃÃÃÄÄÄÅÅÅÆÆÆ"
+ "ÇÇÇÈÈÈÉÉÉÊÊÊËËËÌÌÌÍÍÍÎÎÎÏÏÏÐÐÐÑÑÑÒÒÒÓÓÓÔÔÔÕÕÕÖÖÖ×××ØØØÙÙÙÚÚÚÛÛÛÜÜÜÝÝÝÞÞÞßßßàààáááâââãããäääåååæææçççèèè"
+ "éééêêêëëëìììíííîîîïïïðððñññòòòóóóôôôõõõööö÷÷÷øøøùùùúúúûûûüüüýýýþþþÿÿÿ";
PdfSpecialCs.Indexed expectedIndexedCs = new PdfSpecialCs.Indexed(PdfName.DeviceRGB, 255, new PdfString(indexedCsLookupData
));
expectedDict.Put(PdfName.ColorSpace, expectedIndexedCs.GetPdfObject());
NUnit.Framework.Assert.IsTrue(new CompareTool().CompareDictionaries(inlineImages[0], expectedDict));
}
public virtual void ContentStreamProcessorTest()
{
PdfDocument document = new PdfDocument(new PdfReader(sourceFolder + "tableWithImageAndText.pdf"), new PdfWriter
(new ByteArrayOutputStream()));
StringBuilder pageEventsLog = new StringBuilder();
for (int i = 1; i <= document.GetNumberOfPages(); ++i)
{
PdfPage page = document.GetPage(i);
PdfCanvasProcessor processor = new PdfCanvasProcessor(new PdfCanvasProcessorIntegrationTest.RecordEveryHighLevelEventListener
(pageEventsLog));
processor.ProcessPageContent(page);
}
byte[] logBytes = File.ReadAllBytes(System.IO.Path.Combine(sourceFolder + "contentStreamProcessorTest_events_log.dat"
));
String expectedPageEventsLog = iText.IO.Util.JavaUtil.GetStringForBytes(logBytes, System.Text.Encoding.UTF8
);
NUnit.Framework.Assert.AreEqual(expectedPageEventsLog, pageEventsLog.ToString());
}