List of usage examples for org.apache.pdfbox.pdmodel PDDocumentInformation getKeywords
public String getKeywords()
From source file:org.wandora.piccolo.utils.crawler.handlers.PDFHandler.java
License:Open Source License
public void handle(CrawlerAccess crawler, InputStream in, int depth, URL page) { try {/*from ww w . jav a 2 s .co m*/ Document d = new Document(); PDDocument doc = PDDocument.load(page); PDDocumentInformation info = doc.getDocumentInformation(); PDFTextStripper stripper = new PDFTextStripper(); String content = stripper.getText(doc); doc.close(); d.add(LuceneCrawler.subject(info.getSubject())); d.add(LuceneCrawler.title(info.getTitle())); d.add(LuceneCrawler.keywords(info.getKeywords())); d.add(LuceneCrawler.content(content)); d.add(LuceneCrawler.location(page.toString())); crawler.addObject(d); } catch (IOException e) { e.printStackTrace(); } catch (Exception e) { e.printStackTrace(); } }
From source file:org.xstudiosys.pdfxmp.AddMetadataFromDocInfo.java
License:Apache License
/** * This will print the documents data.// www . ja va 2s. co m * * @param args The command line arguments. * * @throws Exception If there is an error parsing the document. */ public static void main(String[] args) throws Exception { if (args.length != 2) { usage(); } else { PDDocument document = null; try { document = PDDocument.load(args[0]); if (document.isEncrypted()) { System.err.println("Error: Cannot add metadata to encrypted document."); System.exit(1); } PDDocumentCatalog catalog = document.getDocumentCatalog(); PDDocumentInformation info = document.getDocumentInformation(); XMPMetadata metadata = new XMPMetadata(); XMPSchemaPDF pdfSchema = metadata.addPDFSchema(); pdfSchema.setKeywords(info.getKeywords()); pdfSchema.setProducer(info.getProducer()); XMPSchemaBasic basicSchema = metadata.addBasicSchema(); basicSchema.setModifyDate(info.getModificationDate()); basicSchema.setCreateDate(info.getCreationDate()); basicSchema.setCreatorTool(info.getCreator()); basicSchema.setMetadataDate(new GregorianCalendar()); XMPSchemaDublinCore dcSchema = metadata.addDublinCoreSchema(); dcSchema.setTitle(info.getTitle()); dcSchema.addCreator("PDFBox"); dcSchema.setDescription(info.getSubject()); PDMetadata metadataStream = new PDMetadata(document); metadataStream.importXMPMetadata(metadata); catalog.setMetadata(metadataStream); document.save(args[1]); } finally { if (document != null) { document.close(); } } } }
From source file:org.xstudiosys.pdfxmp.MarkBuilder.java
License:Open Source License
public void onComplete(PDDocument document) { try {/*w w w . j ava2 s. c om*/ PDDocumentCatalog catalog = document.getDocumentCatalog(); PDDocumentInformation info = document.getDocumentInformation(); XMPMetadata metadata = new XMPMetadata(); XMPSchemaPDF pdfSchema = metadata.addPDFSchema(); pdfSchema.setKeywords(info.getKeywords()); pdfSchema.setProducer(info.getProducer()); XMPSchemaBasic basicSchema = metadata.addBasicSchema(); basicSchema.setModifyDate(info.getModificationDate()); basicSchema.setCreateDate(info.getCreationDate()); basicSchema.setCreatorTool(info.getCreator()); basicSchema.setMetadataDate(new GregorianCalendar()); XMPSchemaDublinCore dcSchema = metadata.addDublinCoreSchema(); dcSchema.setTitle(info.getTitle()); dcSchema.addCreator("PDFBox"); dcSchema.setDescription(info.getSubject()); PDMetadata metadataStream = new PDMetadata(document); metadataStream.importXMPMetadata(metadata); catalog.setMetadata(metadataStream); } catch (Exception e) { e.printStackTrace(); } }
From source file:org.xstudiosys.pdfxmp.XMPUtil.java
License:Open Source License
/** * Helper function for retrieving a BibtexEntry from the * PDDocumentInformation in a PDF file.// w w w . j ava2 s .c o m * * To understand how to get hold of a PDDocumentInformation have a look in * the test cases for XMPUtil. * * The BibtexEntry is build by mapping individual fields in the document * information (like author, title, keywords) to fields in a bibtex entry. * * @param di * The document information from which to build a BibtexEntry. * * @return The bibtex entry found in the document information. */ @SuppressWarnings("unchecked") public static BibtexEntry getBibtexEntryFromDocumentInformation(PDDocumentInformation di) { BibtexEntry entry = new BibtexEntry(); String s = di.getAuthor(); if (s != null) entry.setField("author", s); s = di.getTitle(); if (s != null) entry.setField("title", s); s = di.getKeywords(); if (s != null) entry.setField("keywords", s); s = di.getSubject(); if (s != null) entry.setField("abstract", s); COSDictionary dict = di.getDictionary(); for (Map.Entry<COSName, COSBase> o : dict.entrySet()) { String key = o.getKey().getName(); if (key.startsWith("bibtex/")) { String value = dict.getString(key); key = key.substring("bibtex/".length()); if (key.equals("entrytype")) { BibtexEntryType type = BibtexEntryType.getStandardType(value); if (type != null) entry.setType(type); } else entry.setField(key, value); } } // Return null if no values were found return (entry.getAllFields().size() > 0 ? entry : null); }
From source file:uk.bl.wa.tika.parser.pdf.pdfbox.PDFParser.java
License:Apache License
private void extractMetadata(PDDocument document, Metadata metadata) throws TikaException { PDDocumentInformation info = document.getDocumentInformation(); metadata.set(PagedText.N_PAGES, document.getNumberOfPages()); addMetadata(metadata, Metadata.TITLE, info.getTitle()); addMetadata(metadata, Metadata.AUTHOR, info.getAuthor()); addMetadata(metadata, Metadata.KEYWORDS, info.getKeywords()); addMetadata(metadata, "pdf:creator", info.getCreator()); addMetadata(metadata, "pdf:producer", info.getProducer()); addMetadata(metadata, Metadata.SUBJECT, info.getSubject()); addMetadata(metadata, "trapped", info.getTrapped()); addMetadata(metadata, "created", info.getCreationDate()); addMetadata(metadata, Metadata.CREATION_DATE, info.getCreationDate()); Calendar modified = info.getModificationDate(); addMetadata(metadata, Metadata.LAST_MODIFIED, modified); // All remaining metadata is custom // Copy this over as-is List<String> handledMetadata = Arrays.asList(new String[] { "Author", "Creator", "CreationDate", "ModDate", "Keywords", "Producer", "Subject", "Title", "Trapped" }); if (info.getCOSObject() != null && info.getCOSObject().keySet() != null) { for (COSName key : info.getCOSObject().keySet()) { String name = key.getName(); if (!handledMetadata.contains(name)) { addMetadata(metadata, name, info.getCOSObject().getDictionaryObject(key)); }//from ww w . j a va 2s . c om } } // ANJ Extensions: // // // Add other data of interest: metadata.set("pdf:version", "" + document.getDocument().getVersion()); metadata.set("pdf:numPages", "" + document.getNumberOfPages()); //metadata.set("pdf:cryptoMode", ""+getCryptoModeAsString(reader)); //metadata.set("pdf:openedWithFullPermissions", ""+reader.isOpenedWithFullPermissions()); metadata.set("pdf:encrypted", "" + document.isEncrypted()); //metadata.set("pdf:metadataEncrypted", ""+document.isMetadataEncrypted()); //metadata.set("pdf:128key", ""+reader.is128Key()); //metadata.set("pdf:tampered", ""+reader.isTampered()); try { if (document.getDocumentCatalog().getMetadata() != null) { XMPMetadata xmp = XMPMetadata.load(document.getDocumentCatalog().getMetadata().exportXMPMetadata()); // There is a special class for grabbing data in the PDF schema - not sure it will add much here: // Could parse xmp:CreatorTool and pdf:Producer etc. etc. out of here. XMPSchemaPDF pdfxmp = xmp.getPDFSchema(); // Added a PDF/A schema class: xmp.addXMLNSMapping(XMPSchemaPDFA.NAMESPACE, XMPSchemaPDFA.class); XMPSchemaPDFA pdfaxmp = (XMPSchemaPDFA) xmp.getSchemaByClass(XMPSchemaPDFA.class); if (pdfaxmp != null) { metadata.set("pdfaid:part", pdfaxmp.getPart()); metadata.set("pdfaid:conformance", pdfaxmp.getConformance()); String version = "A-" + pdfaxmp.getPart() + pdfaxmp.getConformance().toLowerCase(); //metadata.set("pdfa:version", version ); metadata.set("pdf:version", version); } // TODO WARN if this XMP version is inconsistent with document header version? } } catch (IOException e) { log.error("XMP Parsing failed: " + e); metadata.set("pdf:metadata-xmp-parse-failed", "" + e); } // Attempt to determine Adobe extension level, if present: COSDictionary root = document.getDocumentCatalog().getCOSObject(); COSDictionary extensions = (COSDictionary) root.getDictionaryObject(COSName.getPDFName("Extensions")); if (extensions != null) { for (COSName extName : extensions.keySet()) { // If it's an Adobe one, interpret it to determine the extension level: if (extName.equals(COSName.getPDFName("ADBE"))) { COSDictionary adobeExt = (COSDictionary) extensions.getDictionaryObject(extName); if (adobeExt != null) { String baseVersion = adobeExt.getNameAsString(COSName.getPDFName("BaseVersion")); int el = adobeExt.getInt(COSName.getPDFName("ExtensionLevel")); metadata.set("pdf:version", baseVersion + " Adobe Extension Level " + el); } // TODO WARN if this embedded version is inconsistent with document header version? } else { // WARN that there is an Extension, but it's not Adobe's, and so is a 'new' format'. metadata.set("pdf:foundNonAdobeExtensionName", extName.getName()); } } } // End Of ANJ Extensions. }
From source file:zhaw.PDFIndexer.java
License:Apache License
/** * This will add the contents to the lucene document. * /* w ww . ja v a 2 s .com*/ * @param document * The document to add the contents to. * @param is * The stream to get the contents from. * @param documentLocation * The location of the document, used just for debug messages. * @throws IOException * If there is an error parsing the document. */ private void addContent(Document document, InputStream is, String documentLocation) throws IOException { PDDocument pdfDocument = null; PDFTextStripper stripper; try { pdfDocument = PDDocument.load(is); if (pdfDocument.isEncrypted()) { // Just try using the default password and move on pdfDocument.decrypt(""); } // create a writer where to append the text content. StringWriter writer = new StringWriter(); stripper = new PDFTextStripper(); try { stripper.writeText(pdfDocument, writer); } catch (Exception e) { System.out.println("Error in stripper.writeText()"); } String contents = writer.getBuffer().toString(); StringReader reader = new StringReader(contents); addTextField(document, Indexer.contents, reader); PDDocumentInformation info = pdfDocument.getDocumentInformation(); if (info != null) { addTextField(document, Indexer.Author, info.getAuthor()); try { addTextField(document, Indexer.created, info.getCreationDate()); } catch (IOException io) { // ignore, bad date but continue with indexing } addTextField(document, Indexer.keywords, info.getKeywords()); try { addTextField(document, Indexer.modified, info.getModificationDate()); } catch (IOException io) { // ignore, bad date but continue with indexing } addTextField(document, "Subject", info.getSubject()); addTextField(document, Indexer.Title, info.getTitle()); } int summarySize = Math.min(contents.length(), 500); String summary = contents.substring(0, summarySize); // Add the summary as an UnIndexed field, so that it is stored and // returned // with hit documents for display. addUnindexedField(document, Indexer.summary, summary); } catch (CryptographyException e) { throw new IOException("Error decrypting document(" + documentLocation + "): " + e); } catch (InvalidPasswordException e) { // they didn't suppply a password and the default of "" was wrong. throw new IOException( "Error: The document(" + documentLocation + ") is encrypted and will not be indexed."); } finally { if (pdfDocument != null) { pdfDocument.close(); } } }