List of usage examples for com.itextpdf.text.pdf PdfString toUnicodeString
public String toUnicodeString()
String value of this PdfString-object. From source file:commentextractor.CommentExtractorApp.java
License:GNU General Public License
static String extractComments(String filename, int first, int last) { StringBuffer output = null;/*from w w w. j a v a 2s. com*/ try { PdfReader reader = new PdfReader(filename); if (last >= reader.getNumberOfPages() || (last == -1)) { last = reader.getNumberOfPages(); } output = new StringBuffer(1024); for (int i = first; i <= last; i++) { PdfDictionary page = reader.getPageN(i); PdfArray annotsArray = null; if (page.getAsArray(PdfName.ANNOTS) == null) { continue; } annotsArray = page.getAsArray(PdfName.ANNOTS); for (ListIterator<PdfObject> iter = annotsArray.listIterator(); iter.hasNext();) { PdfDictionary annot = (PdfDictionary) PdfReader.getPdfObject(iter.next()); PdfString content = (PdfString) PdfReader.getPdfObject(annot.get(PdfName.CONTENTS)); if (content != null) { output.append("----------\n"); output.append("Page " + i); output.append("\n"); output.append(content.toUnicodeString().replaceAll("\r", "\r\n")); output.append("\n"); } } } } catch (Exception e) { Logger.getLogger(CommentExtractorApp.class.getName()).log(Level.SEVERE, null, e); } return new String(output); }
From source file:de.offis.health.icardea.cied.pdf.extractor.PDFiText5Extractor.java
License:GNU General Public License
/** * This method will populate the text bookmark list. * // w ww . j av a2 s .c o m * @param rootOutlinesPdfDictionary The node element for the bookmark item. * @param indentionString The base indention string to be used. */ @SuppressWarnings("unchecked") private void populateBookmarkTextList(PdfDictionary rootOutlinesPdfDictionary, String indentionString) { PdfDictionary outlineItemPdfDictionary = (PdfDictionary) PdfReader .getPdfObjectRelease(rootOutlinesPdfDictionary.get(PdfName.FIRST)); while (outlineItemPdfDictionary != null) { PdfString bookmarkTitle = (PdfString) PdfReader .getPdfObjectRelease(outlineItemPdfDictionary.get(PdfName.TITLE)); bookmarkTextList.add(indentionString + bookmarkTitle.toUnicodeString()); logger.trace(indentionString + bookmarkTitle.toUnicodeString()); /* * Recursive call to fill List */ populateBookmarkTextList(outlineItemPdfDictionary, indentionString + bookmarkIndentionString()); /* * Get next outline item */ outlineItemPdfDictionary = (PdfDictionary) PdfReader .getPdfObjectRelease(outlineItemPdfDictionary.get(PdfName.NEXT)); } // end while }
From source file:mkl.testarea.itext5.pdfcleanup.StrictPdfCleanUpProcessor.java
License:Open Source License
/** * Deletes redact annotations from the page and substitutes them with either OverlayText or RO object if it's needed. *//*from ww w . ja va 2s. co m*/ private void deleteRedactAnnots(int pageNum) throws IOException, DocumentException { Set<String> indirRefs = redactAnnotIndirRefs.get(pageNum); if (indirRefs == null || indirRefs.isEmpty()) { return; } PdfReader reader = pdfStamper.getReader(); PdfContentByte canvas = pdfStamper.getOverContent(pageNum); PdfDictionary pageDict = reader.getPageN(pageNum); PdfArray annotsArray = pageDict.getAsArray(PdfName.ANNOTS); // j is for access annotRect (i can be decreased, so we need to store additional index, // indicating current position in ANNOTS array in case if we don't remove anything for (int i = 0, j = 0; i < annotsArray.size(); ++i, ++j) { PdfIndirectReference annotIndRef = annotsArray.getAsIndirectObject(i); PdfDictionary annotDict = annotsArray.getAsDict(i); if (indirRefs.contains(annotIndRef.toString()) || indirRefs.contains(getParentIndRefStr(annotDict))) { PdfStream formXObj = annotDict.getAsStream(PdfName.RO); PdfString overlayText = annotDict.getAsString(PdfName.OVERLAYTEXT); if (fillCleanedArea && formXObj != null) { PdfArray rectArray = annotDict.getAsArray(PdfName.RECT); Rectangle annotRect = new Rectangle(rectArray.getAsNumber(0).floatValue(), rectArray.getAsNumber(1).floatValue(), rectArray.getAsNumber(2).floatValue(), rectArray.getAsNumber(3).floatValue()); insertFormXObj(canvas, pageDict, formXObj, clippingRects.get(j), annotRect); } else if (fillCleanedArea && overlayText != null && overlayText.toUnicodeString().length() > 0) { drawOverlayText(canvas, clippingRects.get(j), overlayText, annotDict.getAsString(PdfName.DA), annotDict.getAsNumber(PdfName.Q), annotDict.getAsBoolean(PdfName.REPEAT)); } annotsArray.remove(i--); // array size is changed, so we need to decrease i } } if (annotsArray.size() == 0) { pageDict.remove(PdfName.ANNOTS); } }
From source file:mkl.testarea.itext5.pdfcleanup.StrictPdfCleanUpProcessor.java
License:Open Source License
private void drawOverlayText(PdfContentByte canvas, List<Rectangle> textRectangles, PdfString overlayText, PdfString otDA, PdfNumber otQ, PdfBoolean otRepeat) throws DocumentException, IOException { ColumnText ct = new ColumnText(canvas); ct.setLeading(0, 1.2F);//from ww w . j a v a 2s . c om ct.setUseAscender(true); String otStr = overlayText.toUnicodeString(); canvas.saveState(); Map<String, List> parsedDA = parseDAParam(otDA); Font font = null; if (parsedDA.containsKey(STROKE_COLOR)) { List strokeColorArgs = parsedDA.get(STROKE_COLOR); setStrokeColor(canvas, strokeColorArgs); } if (parsedDA.containsKey(FILL_COLOR)) { List fillColorArgs = parsedDA.get(FILL_COLOR); setFillColor(canvas, fillColorArgs); } if (parsedDA.containsKey("Tf")) { List tfArgs = parsedDA.get("Tf"); font = retrieveFontFromAcroForm((PdfName) tfArgs.get(0), (PdfNumber) tfArgs.get(1)); } for (Rectangle textRect : textRectangles) { ct.setSimpleColumn(textRect); if (otQ != null) { ct.setAlignment(otQ.intValue()); } Phrase otPhrase; if (font != null) { otPhrase = new Phrase(otStr, font); } else { otPhrase = new Phrase(otStr); } float y = ct.getYLine(); if (otRepeat != null && otRepeat.booleanValue()) { int status = ct.go(true); while (!ColumnText.hasMoreText(status)) { otPhrase.add(otStr); ct.setText(otPhrase); ct.setYLine(y); status = ct.go(true); } } ct.setText(otPhrase); ct.setYLine(y); ct.go(); } canvas.restoreState(); }
From source file:org.roda.common.certification.PDFSignatureUtils.java
private static StringBuilder getExtractionInformation(AcroFields fields, ArrayList<?> names, Path outputContents, String filename) throws IOException { StringBuilder sb = new StringBuilder(); for (int i = 0; i < names.size(); i++) { String name = (String) names.get(i); Item item = fields.getFieldItem(name); PdfDictionary widget = item.getWidget(0); PdfDictionary infoDictionary = widget.getAsDict(PdfName.V); sb.append("<signature>\n"); try {//from w w w . j a v a 2 s .c o m PdfPKCS7 pk = fields.verifySignature(name); sb = addElementToExtractionResult(sb, "name", name); sb = addElementToExtractionResult(sb, "sign-name", pk.getSignName()); sb = addElementToExtractionResult(sb, "version", Integer.toString(pk.getVersion())); sb = addElementToExtractionResult(sb, "reason", pk.getReason()); sb = addElementToExtractionResult(sb, "location", pk.getLocation()); SimpleDateFormat formatter = new SimpleDateFormat("dd-MM-yyyy"); if (pk.getTimeStampDate() != null) { String timestamp = formatter.format(pk.getTimeStampDate().getTime()); sb = addElementToExtractionResult(sb, "timestamp-time", timestamp); } if (pk.getSignDate() != null) { String sign = formatter.format(pk.getSignDate().getTime()); sb = addElementToExtractionResult(sb, "sign-time", sign); } sb = addElementToExtractionResult(sb, "digest-algorithm", pk.getDigestAlgorithm()); sb = addElementToExtractionResult(sb, "hash-algorithm", pk.getHashAlgorithm()); sb = addElementToExtractionResult(sb, "covers-whole-document", Boolean.toString(fields.signatureCoversWholeDocument(name))); sb = addElementToExtractionResult(sb, "ft", widget.get(PdfName.FT).toString()); if (infoDictionary.contains(PdfName.CONTACTINFO)) sb = addElementToExtractionResult(sb, "contact-info", infoDictionary.getAsString(PdfName.CONTACTINFO).toString()); if (infoDictionary.contains(PdfName.FILTER)) sb = addElementToExtractionResult(sb, "filter", infoDictionary.get(PdfName.FILTER).toString()); if (infoDictionary.contains(PdfName.SUBFILTER)) sb = addElementToExtractionResult(sb, "subfilter", infoDictionary.get(PdfName.SUBFILTER).toString()); if (infoDictionary.contains(PdfName.LOCK)) sb = addElementToExtractionResult(sb, "lock", "true"); if (infoDictionary.contains(PdfName.CONTENTS)) { PdfString elementName = infoDictionary.getAsString(PdfName.CONTENTS); Files.write(outputContents, elementName.toUnicodeString().getBytes()); sb = addElementToExtractionResult(sb, "contents", filename + ".pkcs7"); } } catch (NoSuchFieldError e) { LOGGER.warn("DS information extraction did not execute properly"); } sb.append("</signature>"); } return sb; }
From source file:org.roda.core.plugins.plugins.characterization.PDFSignatureUtils.java
private static StringBuilder getExtractionInformation(AcroFields fields, ArrayList<?> names, Path outputContents, String filename) throws IOException { StringBuilder sb = new StringBuilder(); for (int i = 0; i < names.size(); i++) { String name = (String) names.get(i); Item item = fields.getFieldItem(name); PdfDictionary widget = item.getWidget(0); PdfDictionary infoDictionary = widget.getAsDict(PdfName.V); sb.append("<signature>\n"); try {//from ww w .j ava2s . c om PdfPKCS7 pk = fields.verifySignature(name); sb = addElementToExtractionResult(sb, "name", name); sb = addElementToExtractionResult(sb, "sign-name", pk.getSignName()); sb = addElementToExtractionResult(sb, "version", Integer.toString(pk.getVersion())); sb = addElementToExtractionResult(sb, "reason", pk.getReason()); sb = addElementToExtractionResult(sb, "location", pk.getLocation()); SimpleDateFormat formatter = new SimpleDateFormat("dd-MM-yyyy"); if (pk.getTimeStampDate() != null) { String timestamp = formatter.format(pk.getTimeStampDate().getTime()); sb = addElementToExtractionResult(sb, "timestamp-time", timestamp); } if (pk.getSignDate() != null) { String sign = formatter.format(pk.getSignDate().getTime()); sb = addElementToExtractionResult(sb, "sign-time", sign); } sb = addElementToExtractionResult(sb, "digest-algorithm", pk.getDigestAlgorithm()); sb = addElementToExtractionResult(sb, "hash-algorithm", pk.getHashAlgorithm()); sb = addElementToExtractionResult(sb, "covers-whole-document", Boolean.toString(fields.signatureCoversWholeDocument(name))); sb = addElementToExtractionResult(sb, "ft", widget.get(PdfName.FT).toString()); if (infoDictionary.contains(PdfName.CONTACTINFO)) sb = addElementToExtractionResult(sb, "contact-info", infoDictionary.getAsString(PdfName.CONTACTINFO).toString()); if (infoDictionary.contains(PdfName.FILTER)) sb = addElementToExtractionResult(sb, "filter", infoDictionary.get(PdfName.FILTER).toString()); if (infoDictionary.contains(PdfName.SUBFILTER)) sb = addElementToExtractionResult(sb, "subfilter", infoDictionary.get(PdfName.SUBFILTER).toString()); if (infoDictionary.contains(PdfName.LOCK)) sb = addElementToExtractionResult(sb, "lock", "true"); if (infoDictionary.contains(PdfName.CONTENTS)) { PdfString elementName = infoDictionary.getAsString(PdfName.CONTENTS); Files.write(outputContents, elementName.toUnicodeString().getBytes()); sb = addElementToExtractionResult(sb, "contents", filename + ".pkcs7"); } } catch (NoSuchFieldError e) { LOGGER.warn("DS information extraction did not execute properly"); } sb.append("</signature>"); } return sb; }
From source file:org.sejda.impl.itext5.component.PdfUnpacker.java
License:Open Source License
private void unpack(Set<PdfDictionary> dictionaries) throws TaskIOException { for (PdfDictionary dictionary : dictionaries) { PdfName type = dictionary.getAsName(PdfName.TYPE); if (PdfName.F.equals(type) || PdfName.FILESPEC.equals(type)) { PdfDictionary ef = dictionary.getAsDict(PdfName.EF); PdfString fn = dictionary.getAsString(PdfName.F); if (fn != null && ef != null) { PRStream prs = (PRStream) PdfReader.getPdfObject(ef.get(PdfName.F)); if (prs != null) { File tmpFile = copyToTemporaryFile(prs); outputWriter.addOutput(file(tmpFile).name(fn.toUnicodeString())); }//from w w w. jav a 2s .c o m } } } }