/**
* 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 extends RenderListener> E processContent(int pageNumber, E renderListener)
throws IOException {
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;
}
private String extractTextFromPdf(byte pdfAsByteArray[]) throws IOException, IOException {
PdfReader reader = new PdfReader(pdfAsByteArray);
TextRenderListener listener = new TextRenderListener();
PdfContentStreamProcessor processor = new PdfContentStreamProcessor(listener);
PdfDictionary pageDic = reader.getPageN(1);
PdfDictionary resourcesDic = pageDic.getAsDict(PdfName.RESOURCES);
byte array[] = ContentByteUtils.getContentBytesForPage(reader, 1);
processor.processContent(array, resourcesDic);
return listener.getSb();
}
