String keyword = dico.getKeywords(); if (keyword != null)
/** * 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 ); } }
@Override public String getKeywords() { if (info != null) { return info.getKeywords(); } return null; }
addTextField(document, "CreationDate", info.getCreationDate()); addTextField(document, "Creator", info.getCreator()); addTextField(document, "Keywords", info.getKeywords()); addTextField(document, "ModificationDate", info.getModificationDate()); addTextField(document, "Producer", info.getProducer());
@Override public String getKeywords() { return this.info.getKeywords(); }
pdfSchema.setKeywords( info.getKeywords() ); pdfSchema.setProducer( info.getProducer() );
addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator()); addMetadata(metadata, PDF.DOC_INFO_CREATOR_TOOL, info.getCreator()); addMetadata(metadata, Office.KEYWORDS, info.getKeywords()); addMetadata(metadata, PDF.DOC_INFO_KEY_WORDS, info.getKeywords()); addMetadata(metadata, PDF.DOC_INFO_PRODUCER, info.getProducer()); extractMultilingualItems(metadata, TikaCoreProperties.DESCRIPTION, null, dcSchema); addMetadata(metadata, TikaCoreProperties.SUBJECT, info.getKeywords()); addMetadata(metadata, TikaCoreProperties.SUBJECT, info.getSubject()); addMetadata(metadata, OfficeOpenXMLCore.SUBJECT, info.getSubject());
String keyword = dico.getKeywords(); if (keyword != null)
String keyword = dico.getKeywords(); if (keyword != null)
/** * 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 ); } }
addTextField(document, "CreationDate", info.getCreationDate()); addTextField(document, "Creator", info.getCreator()); addTextField(document, "Keywords", info.getKeywords()); addTextField(document, "ModificationDate", info.getModificationDate()); addTextField(document, "Producer", info.getProducer());
value = docinfo.getKeywords(); if (value != null) { itemService.addMetadata(context, item, MetadataSchema.DC_SCHEMA, "subject", "other", null, value);
pdfSchema.setKeywords( info.getKeywords() ); pdfSchema.setProducer( info.getProducer() );
author = checkNotNull(docInfo.getAuthor()); contentCreator = checkNotNull(docInfo.getCreator()); keywords = checkNotNull(docInfo.getKeywords()); try { creationDate = docInfo.getCreationDate();
context.setVariable(VARIABLE_NAME_TITLE, title); String keywords = info.getKeywords(); if (keywords != null) { context.setVariable(VARIABLE_NAME_KEYWORDS, keywords);
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()); }
creationDate = metadata.getCreationDate(); creator = metadata.getCreator(); keywords = metadata.getKeywords(); modificationDate = metadata.getModificationDate(); producer = metadata.getProducer();
addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator()); addMetadata(metadata, PDF.DOC_INFO_CREATOR_TOOL, info.getCreator()); addMetadata(metadata, TikaCoreProperties.KEYWORDS, info.getKeywords()); addMetadata(metadata, PDF.DOC_INFO_KEY_WORDS, info.getKeywords()); addMetadata(metadata, "producer", info.getProducer()); addMetadata(metadata, PDF.DOC_INFO_PRODUCER, info.getProducer());
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.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());