Example usage for com.itextpdf.text.pdf.parser PdfContentStreamProcessor processContent

Introduction

In this page you can find the example usage for com.itextpdf.text.pdf.parser PdfContentStreamProcessor processContent.

Prototype

public void processContent(byte[] contentBytes, PdfDictionary resources)

Source Link

Document

Processes PDF syntax.

Usage

From source file:com.cib.statementstamper.windows.StatementStamperMainWindow.java

License:Open Source License

protected ByteArrayOutputStream doStamper(ByteArrayOutputStream baos) throws IOException, DocumentException {

    map.clear();/*from ww w.  j  a  v a  2 s  .c  o  m*/
    ByteArrayOutputStream baosFinal = new ByteArrayOutputStream();
    PdfReader reader = new PdfReader(baos.toByteArray());

    PdfContentStreamProcessor processor = new PdfContentStreamProcessor(this);
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        actualPage = i;
        PdfDictionary pageDic = reader.getPageN(i);
        PdfDictionary resourcesDic = pageDic.getAsDict(PdfName.RESOURCES);
        processor.processContent(ContentByteUtils.getContentBytesForPage(reader, i), resourcesDic);
    }

    Document newDocument = new Document(PageSize.A4);
    PdfWriter writer = PdfWriter.getInstance(newDocument, baosFinal);

    newDocument.open();
    PdfContentByte canvas = writer.getDirectContent();
    //      Font myFont = FontFactory.getFont(FontFactory.COURIER, 7, Font.BOLD);
    Iterator<Entry<Integer, Map<Float, StringBuffer>>> it = map.entrySet().iterator();

    while (it.hasNext()) {
        Map.Entry<Integer, Map<Float, StringBuffer>> pairs = (Map.Entry<Integer, Map<Float, StringBuffer>>) it
                .next();

        Iterator<Entry<Float, StringBuffer>> iter = pairs.getValue().entrySet().iterator();
        while (iter.hasNext()) {
            Map.Entry<Float, StringBuffer> actualEntry = iter.next();
            canvas.beginText();
            canvas.setFontAndSize(myFontBase, 7);
            canvas.showTextAligned(Element.ALIGN_LEFT, actualEntry.getValue().toString(), 25,
                    actualEntry.getKey() + 60, 0);
            canvas.endText();
        }
        newDocument.newPage();
    }
    newDocument.close();

    reader = new PdfReader(baosFinal.toByteArray());

    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    TextMarginFinder finder;
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        finder = parser.processContent(i, new TextMarginFinder());
        if (finder.getLly() <= 68) {
            getWindow().showNotification("Hiba", "A(z) " + i + ".ik oldalon tl sok a szveg !!!",
                    Notification.TYPE_ERROR_MESSAGE);
            return null;
        }
    }

    reader = new PdfReader(baosFinal.toByteArray());
    PdfStamper stamper = new PdfStamper(reader, baosFinal);
    int n = reader.getNumberOfPages();
    for (int i = 1; i <= n; i++) {
        PdfContentByte overContent = stamper.getOverContent(i);
        overContent.addImage(logo, 131, 0, 0, 32, 44, 775);
        getFooterTable(i, n).writeSelectedRows(0, -1, 27, 68, stamper.getOverContent(i)); // ez a jo
        getIspLogoTable(i, n).writeSelectedRows(0, -1, 425, 45, stamper.getOverContent(i));
    }
    stamper.close();
    reader.close();
    return baosFinal;
}

From source file:mkl.testarea.itext5.pdfcleanup.StrictPdfCleanUpProcessor.java

License:Open Source License

private void cleanUpPage(int pageNum, List<PdfCleanUpLocation> cleanUpLocations)
        throws IOException, DocumentException {
    if (cleanUpLocations.size() == 0) {
        return;//from ww  w . ja v  a 2 s  .c  o  m
    }

    PdfReader pdfReader = pdfStamper.getReader();
    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);
    }
}

From source file:pl.edu.icm.cermine.structure.ITextCharacterExtractor.java

License:Open Source License

/**
 * Extracts text chunks from PDF using iText and stores them in BxDocument object.
 * Depending on parsed PDF, extracted text chunks may or may not be individual glyphs,
 * they correspond to single string operands of PDF's text-showing operators
 * (Tj, TJ, ' and ").//from w  ww .j  a v  a 2s  .c  o m
 * @param stream PDF's stream
 * @return BxDocument containing pages with extracted chunks stored as BxChunk lists
 * @throws AnalysisException AnalysisException
 */
@Override
public BxDocument extractCharacters(InputStream stream) throws AnalysisException {
    try {
        BxDocumentCreator documentCreator = new BxDocumentCreator();

        PdfReader reader = new PdfReader(stream);
        PdfContentStreamProcessor processor = new PdfContentStreamProcessor(documentCreator);

        for (int pageNumber = 1; pageNumber <= reader.getNumberOfPages(); pageNumber++) {
            if (frontPagesLimit > 0 && backPagesLimit > 0 && pageNumber > frontPagesLimit
                    && pageNumber < reader.getNumberOfPages() - 1 - backPagesLimit) {
                continue;
            }
            documentCreator.processNewBxPage(reader.getPageSize(pageNumber));

            PdfDictionary resources = reader.getPageN(pageNumber).getAsDict(PdfName.RESOURCES);
            processAlternativeFontNames(resources);
            processAlternativeColorSpace(resources);

            processor.reset();
            processor.processContent(ContentByteUtils.getContentBytesForPage(reader, pageNumber), resources);
            TimeoutRegister.get().check();
        }

        BxDocument doc = filterComponents(removeDuplicateChunks(documentCreator.document));
        if (doc.getFirstChild() == null) {
            throw new AnalysisException("Document contains no pages");
        }
        return doc;
    } catch (InvalidPdfException ex) {
        throw new AnalysisException("Invalid PDF file", ex);
    } catch (IOException ex) {
        throw new AnalysisException("Cannot extract characters from PDF file", ex);
    }
}