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

List of usage examples for com.itextpdf.text.pdf.parser PdfReaderContentParser processContent

  1. HOME
  2. Java
  3. com.itextpdf
  4. com.itextpdf.text.pdf.parser.*
  5. PdfReaderContentParser
  6. processContent

Introduction

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

Prototype

public <E extends RenderListener> E processContent(int pageNumber, E renderListener) throws IOException

Source Link

Document

Processes content from the specified page number using the specified listener

Usage

From source file:be.roots.taconic.pricingguide.util.iTextUtil.java

License:Open Source License

public static Image getImageFromPdf(byte[] pdf) throws IOException, BadElementException {

    try (final ByteArrayOutputStream bos = new ByteArrayOutputStream()) {

        final PdfReader reader = new PdfReader(pdf);
        final PdfReaderContentParser parser = new PdfReaderContentParser(reader);
        final ImageRenderListener listener = new ImageRenderListener(bos);

        parser.processContent(1, listener);

        reader.close();/*  w  w  w  .j a  v  a  2  s .  c  om*/

        return Image.getInstance(bos.toByteArray());
    }

}

From source file:br.com.smarttaco.util.HelenaBarbosa.java

/**
 * pdf2txt/*from  w  w  w .  j  av a  2  s. com*/
 *
 * @param pdf
 * @param paginas se for <code>null</code> realiza leitura completa.
 * @param txt
 * @throws FileNotFoundException
 * @throws IOException
 */
private static void pdf2txt(final String pdf, List<Integer> paginas, final String txt)
        throws FileNotFoundException, IOException {
    PdfReader reader = new PdfReader(pdf);
    //System.out.println(reader.getInfo().toString());
    if (paginas != null) {
        reader.selectPages(paginas);
    }
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    PrintWriter out = new PrintWriter(txt, "UTF-8");
    TextExtractionStrategy strategy;
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
        out.println(strategy.getResultantText());
    }
    out.flush();
    out.close();
    reader.close();
}

From source file:ch.kostceco.tools.kostsimy.comparison.modulepdfa.impl.PdfExtractJpegModuleImpl.java

License:Open Source License

/** Parses a PDF and extracts all the images.
 * //from w w  w . j a  v  a 2s . c  om
 * @param src
 *          the source PDF
 * @param dest
 *          the resulting Image */
public void extractImages(String srcPdf, String destImage) throws IOException, DocumentException {
    jpegCounter = 0;
    ccittCounter = 0;
    jp2Counter = 0;
    jbig2Counter = 0;
    try {
        PdfReader reader = new PdfReader(srcPdf);
        PdfReaderContentParser parser = new PdfReaderContentParser(reader);
        MyImageRenderListener listener = new MyImageRenderListener(destImage);
        for (int i = 1; i <= reader.getNumberOfPages(); i++) {
            parser.processContent(i, listener);
        }
        reader.close();
    } catch (IOException e) {
        getMessageService().logError(getTextResourceService().getText(MESSAGE_XML_MODUL_PDF_EXTRACT)
                + getTextResourceService().getText(ERROR_XML_UNKNOWN, e.getMessage()));
    }
}

From source file:ch.kostceco.tools.kostval.validation.modulepdfa.impl.ValidationJimageValidationModuleImpl.java

License:Open Source License

/** Parses a PDF and extracts all the images.
 * //from  w  ww.j a  va  2  s  . co m
 * @param src
 *          the source PDF
 * @param dest
 *          the resulting PDF */
public void extractImages(String srcPdf, String destImage) throws IOException, DocumentException {
    PdfReader reader = new PdfReader(srcPdf);
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    MyImageRenderListener listener = new MyImageRenderListener(destImage);
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        parser.processContent(i, listener);
    }
    reader.close();
}

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

License:Open Source License

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

    map.clear();/*from  w w w  .  ja  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:com.cloudhub.util.PDFToText.java

License:Apache License

/**
 * Parses a PDF to a plain text file.//from   www  .  ja  v a  2  s. c om
 *
 * @param source the original PDF
 * @param destination the resulting text
 * @throws IOException
 */
public static void parsePdf(String source, String destination) throws IOException {
    PdfReader reader = new PdfReader(source);
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    PrintWriter out = new PrintWriter(new FileOutputStream(destination));
    TextExtractionStrategy strategy;
    for (int i = 1; i <= reader.getNumberOfPages(); i++) {
        strategy = parser.processContent(i, new SimpleTextExtractionStrategy());
        out.println(strategy.getResultantText());
    }
    out.flush();
    out.close();
}

From source file:com.cyberninjas.invoice.pdf.PdfInvoiceEditor.java

License:Open Source License

/**
 * Parses PDF to determine location of text.
 *
 * @throws IOException on I/O error parsing PDF.
 *///from  w w w .j a  va  2 s . co m
public void parseContent() throws IOException {
    PdfReader reader = getReader();

    PdfReaderContentParser parser = new PdfReaderContentParser(reader);

    InvoiceTextExtractionStrategy strategy;

    for (int pageNum = 1; pageNum <= getReader().getNumberOfPages(); pageNum++) {
        strategy = parser.processContent(pageNum, new InvoiceTextExtractionStrategy());

        strategy.parse(settings);

        for (String itemId : strategy.getCumulativeCostLocationMap().keySet()) {
            cumulativeCostLocationMap.put(itemId,
                    new PageVector(pageNum, strategy.getCumulativeCostLocationMap().get(itemId)));
        }

        //set the location to write the cumulative cost subtotal
        if (cumulativeCostSubtotalLocation == null && strategy.getCumulativeCostSubtotalLocation() != null) {
            cumulativeCostSubtotalLocation = new PageVector(pageNum,
                    strategy.getCumulativeCostSubtotalLocation());
        }

        // set the location to write the total funded amount
        if (totalFundedAmountLocation == null && strategy.getTotalFundedAmountLocation() != null) {
            totalFundedAmountLocation = new PageVector(pageNum, strategy.getTotalFundedAmountLocation());
        }
    }
}

From source file:com.cyberninjas.invoice.pdf.PdfInvoiceEditor.java

License:Open Source License

/**
 * Write text relative to the matching reference text.
 *
 * <p>/*from   w ww.ja  v  a 2 s . com*/
 * Note: Due to the way PDF stores text, found blocks of text may contain additional text beyond the reference text.
 * This can cause blocks to be larger than expected requiring a larger or smaller offset to be set to align
 * properly.</p>
 *
 * @param text the text to write.
 * @param referenceText the reference text to write relative to.
 * @param offset the offset to write relative to the reference text.
 * @param align the alignment.
 * @param findAll indicates if text should be written at every occurrence or only the first.
 * @throws IOException on I/O error.
 */
public final void writeTextAtOffset(String text, String referenceText, float offset, final Alignment align,
        boolean findAll) throws IOException {
    PdfReader reader = getReader();

    PdfReaderContentParser parser = new PdfReaderContentParser(reader);

    TextChunkExtractionStrategy strategy;

    for (int pageNum = 1; pageNum <= reader.getNumberOfPages(); pageNum++) {
        strategy = parser.processContent(pageNum, new TextChunkExtractionStrategy());

        if (findAll) {
            for (TextChunk textChunk : strategy.matchAllText(referenceText)) {
                this.writeText(pageNum, text, align, textChunk.getEndLocation().get(Vector.I1) + offset,
                        textChunk.getEndLocation().get(Vector.I2));
            }
        } else {
            TextChunk textChunk = strategy.matchText(referenceText);

            if (textChunk != null) {
                this.writeText(pageNum, text, align, textChunk.getEndLocation().get(Vector.I1) + offset,
                        textChunk.getEndLocation().get(Vector.I2));
            }
        }
    }
}

From source file:com.erikHolz.vertretungsplan.Converter.java

License:Open Source License

public void parsePDF() throws IOException {

    PdfReader reader = new PdfReader(fileDest + ".pdf");
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    PrintWriter out = new PrintWriter(new FileOutputStream(fileDest + "__.txt"));

    TextExtractionStrategy strategy;//w w w .  j a va  2s  . c om
    for (int intI = 1; intI <= reader.getNumberOfPages(); intI++) {
        strategy = parser.processContent(intI, new LocationTextExtractionStrategy());
        out.println(strategy.getResultantText());
    }

    out.flush();
    out.close();
    reader.close();

    // lschen der ursprnglichen pdf
    File f = new File(fileDest + ".pdf");
    if (f.exists())
        f.delete();
}

From source file:com.github.naofum.epubconverter.ReadPdf.java

License:Open Source License

public static List<String> getImages(int page) {
    imageList = new ArrayList<String>();
    PdfReaderContentParser parser = new PdfReaderContentParser(reader);
    renderListener listener = new renderListener();
    try {/*from  w ww .  j  a  v  a  2 s .  c om*/
        parser.processContent(page, listener);
    } catch (IOException e) {
        System.err.println("Failed to extract image " + e.getMessage());
    } catch (OutOfMemoryError e) {
        System.err.println("Out of memory in image extraction " + e.getMessage());
    }
    return imageList;
}