| public ProcessContent ( byte contentBytes, PdfDictionary resources ) : void | ||
| contentBytes | byte | |
| resources | PdfDictionary | |
| return | void | |
/**
* Put all data from given day into given table
*/
public static void collectDataforDay(DateTime dateTime, SQLiteConnection m_dbConnection)
{
string zeroMonth = dateTime.Month < 10 ? "0" : "";
string zeroDay = dateTime.Day < 10 ? "0" : "";
string date = zeroMonth + dateTime.Month + "/" + zeroDay + dateTime.Day + "/" + dateTime.Year;
PdfReader reader;
try
{
reader = new PdfReader("http://www.equibase.com/premium/eqbPDFChartPlus.cfm?RACE=A&BorP=P&TID=SAR&CTRY=USA&DT=" + date + "&DAY=D&STYLE=EQB");
}
catch (Exception e)
{
Console.WriteLine("CAPTCHA TIME");
Console.ReadKey();
Console.ReadKey();
reader = new PdfReader("http://www.equibase.com/premium/eqbPDFChartPlus.cfm?RACE=A&BorP=P&TID=SAR&CTRY=USA&DT=" + date + "&DAY=D&STYLE=EQB");
}
StringBuilder builder = new StringBuilder();
for (int x = 1; x <= reader.NumberOfPages; x++)
{
PdfDictionary page = reader.GetPageN(x);
IRenderListener listener = new SBTextRenderer(builder);
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(listener);
PdfDictionary pageDic = reader.GetPageN(x);
PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES);
processor.ProcessContent(ContentByteUtils.GetContentBytesForPage(reader, x), resourcesDic);
}
if (pages.Count != 0)
{
DataHandler handler = new DataHandler(dateTime, pages, m_dbConnection);
Thread thread = new Thread(new ThreadStart(handler.extractPdfData));
thread.Start();
thread.Join();
reader.Dispose();
pages.Clear();
}
else
{
// If there were no races on this particular day, simply skip it! :D
Console.WriteLine("Invalid Date: " + date);
}
}
public void HandleXObject(PdfContentStreamProcessor processor, PdfStream stream, PdfIndirectReference refi)
{
PdfDictionary resources = stream.GetAsDict(PdfName.RESOURCES);
// we read the content bytes up here so if it fails we don't leave the graphics state stack corrupted
// this is probably not necessary (if we fail on this, probably the entire content stream processing
// operation should be rejected
byte[] contentBytes;
contentBytes = ContentByteUtils.GetContentBytesFromContentObject(stream);
PdfArray matrix = stream.GetAsArray(PdfName.MATRIX);
new PushGraphicsState().Invoke(processor, null, null);
if (matrix != null)
{
float a = matrix.GetAsNumber(0).FloatValue;
float b = matrix.GetAsNumber(1).FloatValue;
float c = matrix.GetAsNumber(2).FloatValue;
float d = matrix.GetAsNumber(3).FloatValue;
float e = matrix.GetAsNumber(4).FloatValue;
float f = matrix.GetAsNumber(5).FloatValue;
Matrix formMatrix = new Matrix(a, b, c, d, e, f);
processor.Gs().ctm = formMatrix.Multiply(processor.Gs().ctm);
}
processor.ProcessContent(contentBytes, resources);
new PopGraphicsState().Invoke(processor, null, null);
}
/**
* Processes content from the specified page number using the specified listener
* @param <E> the type of the renderListener - this makes it easy to chain calls
* @param pageNumber the page number to process
* @param renderListener the listener that will receive render callbacks
* @return the provided renderListener
* @throws IOException if operations on the reader fail
*/
public E ProcessContent <E>(int pageNumber, E renderListener) where E : IRenderListener
{
PdfDictionary pageDic = reader.GetPageN(pageNumber);
PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES);
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(renderListener);
processor.ProcessContent(ContentByteUtils.GetContentBytesForPage(reader, pageNumber), resourcesDic);
return(renderListener);
}
/**
* Processes content from the specified page number using the specified listener.
* Also allows registration of custom ContentOperators
* @param <E> the type of the renderListener - this makes it easy to chain calls
* @param pageNumber the page number to process
* @param renderListener the listener that will receive render callbacks
* @param additionalContentOperators an optional dictionary of custom IContentOperators for rendering instructions
* @return the provided renderListener
* @throws IOException if operations on the reader fail
*/
public virtual E ProcessContent <E>(int pageNumber, E renderListener, IDictionary <string, IContentOperator> additionalContentOperators) where E : IRenderListener
{
PdfDictionary pageDic = reader.GetPageN(pageNumber);
PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES);
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(renderListener);
foreach (KeyValuePair <string, IContentOperator> entry in additionalContentOperators)
{
processor.RegisterContentOperator(entry.Key, entry.Value);
}
processor.ProcessContent(ContentByteUtils.GetContentBytesForPage(reader, pageNumber), resourcesDic);
return(renderListener);
}
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();
}
private void ProcessBytes(
string resourceName,
int pageNumber)
{
PdfReader pdfReader = TestResourceUtils.GetResourceAsPdfReader(TEST_RESOURCES_PATH, resourceName);
PdfDictionary pageDictionary = pdfReader.GetPageN(pageNumber);
PdfDictionary resourceDictionary = pageDictionary.GetAsDict(PdfName.RESOURCES);
PdfObject contentObject = pageDictionary.Get(PdfName.CONTENTS);
byte[] contentBytes = ReadContentBytes(contentObject);
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(_renderListener);
processor.ProcessContent(contentBytes, resourceDictionary);
}
public 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));
PdfReader reader = TestResourceUtils.GetResourceAsPdfReader(TEST_RESOURCES_PATH, inFile);
TextPositionRenderListener renderListener = new TextPositionRenderListener();
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(renderListener);
PdfDictionary pageDic = reader.GetPageN(FIRST_PAGE);
PdfDictionary resourcesDic = pageDic.GetAsDict(PdfName.RESOURCES);
processor.ProcessContent(ContentByteUtils.GetContentBytesForPage(reader, FIRST_PAGE), resourcesDic);
Assert.AreEqual(renderListener.LineSegments[FIRST_ELEMENT_INDEX].GetStartPoint()[FIRST_ELEMENT_INDEX],
origLineSegment.GetStartPoint()[FIRST_ELEMENT_INDEX], 1/2f);
Assert.AreEqual(renderListener.LineSegments[FIRST_ELEMENT_INDEX].GetEndPoint()[FIRST_ELEMENT_INDEX],
origLineSegment.GetEndPoint()[FIRST_ELEMENT_INDEX], 1/2f);
}
/**
* Searches for a tag in a page.
*
* @param tag
* the name of the tag
* @param obj
* an identifier to find the marked content
* @param page
* a page dictionary
* @throws IOException
*/
public void ParseTag(String tag, PdfObject obj, PdfDictionary page)
{
PRStream stream = (PRStream)page.GetAsStream(PdfName.CONTENTS);
// if the identifier is a number, we can extract the content right away
if (obj is PdfNumber)
{
PdfNumber mcid = (PdfNumber)obj;
RenderFilter filter = new MarkedContentRenderFilter(mcid.IntValue);
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
FilteredTextRenderListener listener = new FilteredTextRenderListener(strategy, new RenderFilter[] { filter });
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(
listener);
processor.ProcessContent(PdfReader.GetStreamBytes(stream), page
.GetAsDict(PdfName.RESOURCES));
outp.Write(SimpleXMLParser.EscapeXML(listener.GetResultantText(), true));
}
// if the identifier is an array, we call the parseTag method
// recursively
else if (obj is PdfArray)
{
PdfArray arr = (PdfArray)obj;
int n = arr.Size;
for (int i = 0; i < n; i++)
{
ParseTag(tag, arr[i], page);
if (i < n - 1)
{
outp.WriteLine();
}
}
}
// if the identifier is a dictionary, we get the resources from the
// dictionary
else if (obj is PdfDictionary)
{
PdfDictionary mcr = (PdfDictionary)obj;
ParseTag(tag, mcr.GetDirectObject(PdfName.MCID), mcr
.GetAsDict(PdfName.PG));
}
}
public override void ParseTag(String tag, PdfObject obj, PdfDictionary page) {
if (obj is PdfNumber) {
PdfNumber mcid = (PdfNumber) obj;
RenderFilter filter = new MyMarkedContentRenderFilter(mcid.IntValue);
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
FilteredTextRenderListener listener = new FilteredTextRenderListener(
strategy, filter);
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(
listener);
processor.ProcessContent(PdfReader.GetPageContent(page), page
.GetAsDict(PdfName.RESOURCES));
outp.Write(XMLUtil.EscapeXML(listener.GetResultantText(), true));
}
else {
base.ParseTag(tag, obj, page);
}
}
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 void HandleXObject(PdfContentStreamProcessor processor, PdfStream stream, PdfIndirectReference refi) {
PdfDictionary resources = stream.GetAsDict(PdfName.RESOURCES);
// we read the content bytes up here so if it fails we don't leave the graphics state stack corrupted
// this is probably not necessary (if we fail on this, probably the entire content stream processing
// operation should be rejected
byte[] contentBytes;
contentBytes = ContentByteUtils.GetContentBytesFromContentObject(stream);
PdfArray matrix = stream.GetAsArray(PdfName.MATRIX);
new PushGraphicsState().Invoke(processor, null, null);
if (matrix != null){
float a = matrix.GetAsNumber(0).FloatValue;
float b = matrix.GetAsNumber(1).FloatValue;
float c = matrix.GetAsNumber(2).FloatValue;
float d = matrix.GetAsNumber(3).FloatValue;
float e = matrix.GetAsNumber(4).FloatValue;
float f = matrix.GetAsNumber(5).FloatValue;
Matrix formMatrix = new Matrix(a, b, c, d, e, f);
processor.Gs().ctm = formMatrix.Multiply(processor.Gs().ctm);
}
processor.ProcessContent(contentBytes, resources);
new PopGraphicsState().Invoke(processor, null, null);
}
/**
* Searches for a tag in a page.
*
* @param tag
* the name of the tag
* @param obj
* an identifier to find the marked content
* @param page
* a page dictionary
* @throws IOException
*/
public void ParseTag(String tag, PdfObject obj, PdfDictionary page) {
PRStream stream = (PRStream) page.GetAsStream(PdfName.CONTENTS);
// if the identifier is a number, we can extract the content right away
if (obj is PdfNumber) {
PdfNumber mcid = (PdfNumber) obj;
RenderFilter filter = new MarkedContentRenderFilter(mcid.IntValue);
ITextExtractionStrategy strategy = new SimpleTextExtractionStrategy();
FilteredTextRenderListener listener = new FilteredTextRenderListener(strategy, new RenderFilter[]{filter});
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(
listener);
processor.ProcessContent(PdfReader.GetStreamBytes(stream), page
.GetAsDict(PdfName.RESOURCES));
outp.Write(SimpleXMLParser.EscapeXML(listener.GetResultantText(), true));
}
// if the identifier is an array, we call the parseTag method
// recursively
else if (obj is PdfArray) {
PdfArray arr = (PdfArray) obj;
int n = arr.Size;
for (int i = 0; i < n; i++) {
ParseTag(tag, arr[i], page);
if (i < n - 1)
outp.WriteLine();
}
}
// if the identifier is a dictionary, we get the resources from the
// dictionary
else if (obj is PdfDictionary) {
PdfDictionary mcr = (PdfDictionary) obj;
ParseTag(tag, mcr.GetDirectObject(PdfName.MCID), mcr
.GetAsDict(PdfName.PG));
}
}
private void CleanUpPage(int pageNum, IList<PdfCleanUpLocation> cleanUpLocations) {
if (cleanUpLocations.Count == 0) {
return;
}
PdfReader pdfReader = pdfStamper.Reader;
PdfDictionary page = pdfReader.GetPageN(pageNum);
PdfContentByte canvas = pdfStamper.GetUnderContent(pageNum);
byte[] pageContentInput = ContentByteUtils.GetContentBytesForPage(pdfReader, pageNum);
page.Remove(PdfName.CONTENTS);
canvas.SaveState();
PdfCleanUpRegionFilter filter = CreateFilter(cleanUpLocations);
PdfCleanUpRenderListener pdfCleanUpRenderListener = new PdfCleanUpRenderListener(pdfStamper, filter);
pdfCleanUpRenderListener.RegisterNewContext(pdfReader.GetPageResources(page), canvas);
PdfContentStreamProcessor contentProcessor = new PdfContentStreamProcessor(pdfCleanUpRenderListener);
PdfCleanUpContentOperator.PopulateOperators(contentProcessor, pdfCleanUpRenderListener);
contentProcessor.ProcessContent(pageContentInput, page.GetAsDict(PdfName.RESOURCES));
pdfCleanUpRenderListener.PopContext();
canvas.RestoreState();
ColorCleanedLocations(canvas, cleanUpLocations);
if (redactAnnotIndirRefs != null) { // if it isn't null, then we are in "extract locations from redact annots" mode
DeleteRedactAnnots(pageNum);
}
}
// ---------------------------------------------------------------------------
/**
* Extracts text from a PDF document.
* @param src the original PDF document
*/
public string ExtractText(byte[] src) {
PdfReader reader = new PdfReader(src);
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
);
return listener.Text.ToString();
}
