/** * This will print the documents data to System.out. * * @param document The document to get the metadata from. * * @throws IOException If there is an error getting the page count. */ public void printMetadata( PDDocument document ) throws IOException { PDDocumentInformation info = document.getDocumentInformation(); PDDocumentCatalog cat = document.getDocumentCatalog(); PDMetadata metadata = cat.getMetadata(); System.out.println( "Page Count=" + document.getNumberOfPages() ); System.out.println( "Title=" + info.getTitle() ); System.out.println( "Author=" + info.getAuthor() ); System.out.println( "Subject=" + info.getSubject() ); System.out.println( "Keywords=" + info.getKeywords() ); System.out.println( "Creator=" + info.getCreator() ); System.out.println( "Producer=" + info.getProducer() ); System.out.println( "Creation Date=" + formatDate( info.getCreationDate() ) ); System.out.println( "Modification Date=" + formatDate( info.getModificationDate() ) ); System.out.println( "Trapped=" + info.getTrapped() ); if( metadata != null ) { String string = new String( metadata.toByteArray(), "ISO-8859-1" ); System.out.println( "Metadata=" + string ); } }
String author = dico.getAuthor(); if (author != null)
private static void showDocumentInformation(PDDocumentInformation information) { display("Title:", information.getTitle()); display("Subject:", information.getSubject()); display("Author:", information.getAuthor()); display("Creator:", information.getCreator()); display("Producer:", information.getProducer()); }
@Override public String getAuthor() { if (info != null) { return info.getAuthor(); } return null; }
@Override public String getAuthor() { return this.info.getAuthor(); }
if (info != null) addTextField(document, "Author", info.getAuthor()); addTextField(document, "CreationDate", info.getCreationDate()); addTextField(document, "Creator", info.getCreator());
extractMultilingualItems(metadata, TikaCoreProperties.TITLE, info.getTitle(), dcSchema); addMetadata(metadata, PDF.DOC_INFO_TITLE, info.getTitle()); extractDublinCoreListItems(metadata, TikaCoreProperties.CREATOR, info.getAuthor(), dcSchema); addMetadata(metadata, PDF.DOC_INFO_CREATOR, info.getAuthor()); extractDublinCoreListItems(metadata, TikaCoreProperties.CONTRIBUTOR, null, dcSchema); addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator());
/** * This will print the documents data to System.out. * * @param document The document to get the metadata from. * * @throws IOException If there is an error getting the page count. */ public void printMetadata( PDDocument document ) throws IOException { PDDocumentInformation info = document.getDocumentInformation(); PDDocumentCatalog cat = document.getDocumentCatalog(); PDMetadata metadata = cat.getMetadata(); System.out.println( "Page Count=" + document.getNumberOfPages() ); System.out.println( "Title=" + info.getTitle() ); System.out.println( "Author=" + info.getAuthor() ); System.out.println( "Subject=" + info.getSubject() ); System.out.println( "Keywords=" + info.getKeywords() ); System.out.println( "Creator=" + info.getCreator() ); System.out.println( "Producer=" + info.getProducer() ); System.out.println( "Creation Date=" + formatDate( info.getCreationDate() ) ); System.out.println( "Modification Date=" + formatDate( info.getModificationDate() ) ); System.out.println( "Trapped=" + info.getTrapped() ); if( metadata != null ) { String string = new String( metadata.toByteArray(), "ISO-8859-1" ); System.out.println( "Metadata=" + string ); } }
String author = dico.getAuthor(); if (author != null)
String author = dico.getAuthor(); if (author != null)
private static void showDocumentInformation(PDDocumentInformation information) { display("Title:", information.getTitle()); display("Subject:", information.getSubject()); display("Author:", information.getAuthor()); display("Creator:", information.getCreator()); display("Producer:", information.getProducer()); }
void processDocumentInformation(PDDocument document, Metadata metadata) { PDDocumentInformation documentInformation = document.getDocumentInformation(); if (documentInformation == null) { return; } metadata.add("title", documentInformation.getTitle()); metadata.add("subject", documentInformation.getSubject()); metadata.add("author", documentInformation.getAuthor()); metadata.add("creator", documentInformation.getCreator()); metadata.add("producer", documentInformation.getProducer()); }
if (info != null) addTextField(document, "Author", info.getAuthor()); addTextField(document, "CreationDate", info.getCreationDate()); addTextField(document, "Creator", info.getCreator());
String value = docinfo.getAuthor(); if (value != null) { itemService.addMetadata(context, item, MetadataSchema.DC_SCHEMA, "contributor", "author", null, value);
pdfVersion = String.valueOf(pdfDoc.getDocument().getVersion()); PDDocumentInformation docInfo = pdfDoc.getDocumentInformation(); author = checkNotNull(docInfo.getAuthor()); contentCreator = checkNotNull(docInfo.getCreator()); keywords = checkNotNull(docInfo.getKeywords());
context.setVariable(VARIABLE_NAME_KEYWORDS, keywords); String author = info.getAuthor(); if (author != null) { context.setVariable(VARIABLE_NAME_CREATOR, author);
private void extractMetaData(final PDDocument pdf, final ParserFieldsBuilder metas) { metas.set(MIME_TYPE, DEFAULT_MIMETYPES[0]); final PDDocumentInformation info = pdf.getDocumentInformation(); if (info != null) { metas.add(TITLE, info.getTitle()); metas.add(SUBJECT, info.getSubject()); metas.add(AUTHOR, info.getAuthor()); metas.add(PRODUCER, info.getProducer()); metas.add(KEYWORDS, info.getKeywords()); metas.add(CREATION_DATE, info.getCreationDate()); metas.add(MODIFICATION_DATE, info.getModificationDate()); } int pages = pdf.getNumberOfPages(); metas.add(NUMBER_OF_PAGES, pages); PDDocumentCatalog catalog = pdf.getDocumentCatalog(); if (catalog != null) metas.add(LANGUAGE, catalog.getLanguage()); }
author = metadata.getAuthor(); creationDate = metadata.getCreationDate(); creator = metadata.getCreator();
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());
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());