public virtual void SpaceTrimColumnTextTest()
{
Document doc = new Document(PageSize.A4, 50, 30, 50, 30);
PdfWriter writer = PdfWriter.GetInstance(doc, new FileStream(OUTSPTRIMCT, FileMode.Create));
doc.Open();
Phrase under = new Phrase();
under.Font = new Font(Font.FontFamily.TIMES_ROMAN, 12, Font.UNDERLINE);
under.Add(new Chunk(" 1 1 9 "));
Paragraph underlineTest = new Paragraph(under);
underlineTest.KeepTogether = true;
doc.Add(underlineTest);
doc.Close();
writer.Close();
PdfReader reader = new PdfReader(OUTSPTRIMCT);
MyTextRenderListener listener = new MyTextRenderListener();
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(listener);
PdfDictionary pageDic = reader.GetPageN(1);
PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES);
processor.ProcessContent(ContentByteUtils.GetContentBytesForPage(reader, 1), resourcesDic);
Assert.IsTrue(listener.GetText().Length == 60, "Unexpected text length");
}
public static string ExtractText(string pdfFilename, int pageNumber)
{
PdfReader reader = new PdfReader(pdfFilename);
MyTextRenderListener listener = new MyTextRenderListener();
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(listener);
PdfDictionary pageDic = reader.GetPageN(pageNumber);
PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES);
processor.ProcessContent(ContentByteUtils.GetContentBytesForPage(reader, 1), resourcesDic);
return(listener.Text.ToString());
}
virtual public void WeirdHyphensTest() {
PdfReader reader = TestResourceUtils.GetResourceAsPdfReader(TEST_RESOURCES_PATH, "WeirdHyphens.pdf");
List<String> textChunks = new List<String>();
IRenderListener listener = new MyTextRenderListener(textChunks);
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(listener);
PdfDictionary pageDic = reader.GetPageN(1);
PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES);
processor.ProcessContent(ContentByteUtils.GetContentBytesForPage(reader, 1), resourcesDic);
/**
* This assertion makes sure that encoding has been read properly from FontDescriptor.
* If not the vallue will be "\u0000 14".
*/
Assert.AreEqual("\u0096 14", textChunks[18]);
reader.Close();
}
public void extractSnippets(String src, String dest)
{
TextWriter output = new StreamWriter(new FileStream(dest, FileMode.Create));
PdfReader reader = new PdfReader(src);
IRenderListener listener = new MyTextRenderListener(output);
PdfContentStreamProcessor processor =
new PdfContentStreamProcessor(listener);
PdfDictionary pageDic = reader.GetPageN(1);
PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES);
processor.ProcessContent(ContentByteUtils.GetContentBytesForPage(reader, 1), resourcesDic);
output.Flush();
output.Close();
reader.Close();
}
virtual public void WeirdHyphensTest()
{
PdfReader reader = TestResourceUtils.GetResourceAsPdfReader(TEST_RESOURCES_PATH, "WeirdHyphens.pdf");
List <String> textChunks = new List <String>();
IRenderListener listener = new MyTextRenderListener(textChunks);
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(listener);
PdfDictionary pageDic = reader.GetPageN(1);
PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES);
processor.ProcessContent(ContentByteUtils.GetContentBytesForPage(reader, 1), resourcesDic);
/**
* This assertion makes sure that encoding has been read properly from FontDescriptor.
* If not the vallue will be "\u0000 14".
*/
Assert.AreEqual("\u0096 14", textChunks[18]);
reader.Close();
}
public virtual void SpaceTrimColumnTextTest() {
Document doc = new Document(PageSize.A4, 50, 30, 50, 30);
PdfWriter writer = PdfWriter.GetInstance(doc, new FileStream(OUTSPTRIMCT, FileMode.Create));
doc.Open();
Phrase under = new Phrase();
under.Font = new Font(Font.FontFamily.TIMES_ROMAN, 12, Font.UNDERLINE);
under.Add(new Chunk(" 1 1 9 "));
Paragraph underlineTest = new Paragraph(under);
underlineTest.KeepTogether = true;
doc.Add(underlineTest);
doc.Close();
writer.Close();
PdfReader reader = new PdfReader(OUTSPTRIMCT);
MyTextRenderListener listener = new MyTextRenderListener();
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(listener);
PdfDictionary pageDic = reader.GetPageN(1);
PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES);
processor.ProcessContent(ContentByteUtils.GetContentBytesForPage(reader, 1), resourcesDic);
Assert.IsTrue(listener.GetText().Length == 60, "Unexpected text length");
}