Package org.apache.pdfbox.pdmodel

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

281
282
283
284
285
286
287
288
289
290
291
292
293
        }
        if (source.isEncrypted())
        {
            throw new IOException("Error: source PDF is encrypted, can't append encrypted PDF documents.");
        }
        PDDocumentInformation destInfo = destination.getDocumentInformation();
        PDDocumentInformation srcInfo = source.getDocumentInformation();
        destInfo.getDictionary().mergeInto(srcInfo.getDictionary());

        PDDocumentCatalog destCatalog = destination.getDocumentCatalog();
        PDDocumentCatalog srcCatalog = source.getDocumentCatalog();

        // use the highest version number for the resulting pdf
View Full Code Here
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
            // Add the tag-stripped contents as a Reader-valued Text field so it will
            // get tokenized and indexed.
            addTextField( document, "contents", reader );

            PDDocumentInformation info = pdfDocument.getDocumentInformation();
            if( info != null )
            {
                addTextField( document, "Author", info.getAuthor() );
                try
                {
                    addTextField( document, "CreationDate", info.getCreationDate() );
                }
                catch( IOException io )
                {
                    //ignore, bad date but continue with indexing
                }
                addTextField( document, "Creator", info.getCreator() );
                addTextField( document, "Keywords", info.getKeywords() );
                try
                {
                    addTextField( document, "ModificationDate", info.getModificationDate() );
                }
                catch( IOException io )
                {
                    //ignore, bad date but continue with indexing
                }
                addTextField( document, "Producer", info.getProducer() );
                addTextField( document, "Subject", info.getSubject() );
                addTextField( document, "Title", info.getTitle() );
                addTextField( document, "Trapped", info.getTrapped() );
            }
            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.
View Full Code Here
227
228
229
230
231
232
233
234
235
236
237
238
239
        }
        if( source.isEncrypted() )
        {
            throw new IOException( "Error: source PDF is encrypted, can't append encrypted PDF documents." );
        }
        PDDocumentInformation destInfo = destination.getDocumentInformation();
        PDDocumentInformation srcInfo = source.getDocumentInformation();
        destInfo.getDictionary().mergeInto( srcInfo.getDictionary() );

        PDDocumentCatalog destCatalog = destination.getDocumentCatalog();
        PDDocumentCatalog srcCatalog = source.getDocumentCatalog();

        if( destCatalog.getOpenAction() == null )
View Full Code Here
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
        }
    }

    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.CREATOR, info.getCreator());
        addMetadata(metadata, Metadata.KEYWORDS, info.getKeywords());
        addMetadata(metadata, "producer", info.getProducer());
        addMetadata(metadata, Metadata.SUBJECT, info.getSubject());
        addMetadata(metadata, "trapped", info.getTrapped());
        try {
            addMetadata(metadata, "created", info.getCreationDate());
            addMetadata(metadata, Metadata.CREATION_DATE, info.getCreationDate());
        } catch (IOException e) {
            // Invalid date format, just ignore
        }
        try {
            Calendar modified = info.getModificationDate();
            addMetadata(metadata, Metadata.LAST_MODIFIED, modified);
        } catch (IOException e) {
            // Invalid date format, just ignore
        }
       
        // 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"
        });
        for(COSName key : info.getDictionary().keySet()) {
            String name = key.getName();
            if(! handledMetadata.contains(name)) {
          addMetadata(metadata, name, info.getDictionary().getDictionaryObject(key));
            }
        }
    }
View Full Code Here
228
229
230
231
232
233
234
235
236
237
238
239
240
        }
        if( source.isEncrypted() )
        {
            throw new IOException( "Error: source PDF is encrypted, can't append encrypted PDF documents." );
        }
        PDDocumentInformation destInfo = destination.getDocumentInformation();
        PDDocumentInformation srcInfo = source.getDocumentInformation();
        destInfo.getDictionary().mergeInto( srcInfo.getDictionary() );

        PDDocumentCatalog destCatalog = destination.getDocumentCatalog();
        PDDocumentCatalog srcCatalog = source.getDocumentCatalog();

        if( destCatalog.getOpenAction() == null )
View Full Code Here
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
            // Add the tag-stripped contents as a Reader-valued Text field so it will
            // get tokenized and indexed.
            addTextField( document, "contents", reader );

            PDDocumentInformation info = pdfDocument.getDocumentInformation();
            if( info != null )
            {
                addTextField( document, "Author", info.getAuthor() );
                try
                {
                    addTextField( document, "CreationDate", info.getCreationDate() );
                }
                catch( IOException io )
                {
                    //ignore, bad date but continue with indexing
                }
                addTextField( document, "Creator", info.getCreator() );
                addTextField( document, "Keywords", info.getKeywords() );
                try
                {
                    addTextField( document, "ModificationDate", info.getModificationDate() );
                }
                catch( IOException io )
                {
                    //ignore, bad date but continue with indexing
                }
                addTextField( document, "Producer", info.getProducer() );
                addTextField( document, "Subject", info.getSubject() );
                addTextField( document, "Title", info.getTitle() );
                addTextField( document, "Trapped", info.getTrapped() );
            }
            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.
View Full Code Here
114
115
116
117
118
119
120
121
122
123
124
                    }
                }
                else
                {
                    // The pdf doesn't contain any metadata, try to use the document information instead
                    PDDocumentInformation information = document.getDocumentInformation();
                    if ( information != null)
                    {
                        showDocumentInformation(information);
                    }
                }
View Full Code Here
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
     *
     * @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 )
        {
            System.out.println( "Metadata=" + metadata.getInputStreamAsString() );
        }
    }
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
                {
                    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 );
View Full Code Here
79
80
81
82
83
84
85
86
87
88
89
90
91
92
     *
     * @return The thread information.
     */
    public PDDocumentInformation getThreadInfo()
    {
        PDDocumentInformation retval = null;
        COSDictionary info = (COSDictionary)thread.getDictionaryObject( "I" );
        if( info != null )
        {
            retval = new PDDocumentInformation( info );
        }

        return retval;
    }
View Full Code Here
TOP

Related Classes of org.apache.pdfbox.pdmodel.PDDocumentInformation

  • de.pdf_scrutinizer.API.app.doc.Info
  • de.pdf_scrutinizer.emulation.InterpreterEmulation
  • geopms.GeoPMSImportPDF
  • net.sf.regain.crawler.preparator.PdfBoxPreparator
  • net.yacy.document.parser.pdfParser
  • org.apache.camel.component.fop.FopHelper
  • org.apache.jackrabbit.core.query.pdf.PDFParser
  • org.apache.padaf.preflight.xmp.SynchronizedMetaDataValidation
  • org.apache.pdfbox.cos.COSDictionary
  • org.apache.pdfbox.examples.lucene.LucenePDFDocument
    • Copyright © 2018 www.massapicom. All rights reserved.
    All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.