Package org.apache.pdfbox.pdmodel

Examples of org.apache.pdfbox.pdmodel.PDDocumentInformation

124
125
126
127
128
129
130
131
132
133
134
                }
                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
445
446
447
448
449
450
451
452
453
454
455
        {
            throw new ValidationException("Document provided is null");
        }
        else
        {
            PDDocumentInformation dico = document.getDocumentInformation();
            if (metadata == null)
            {
                throw new ValidationException("Metadata provided are null");
            }
            else
View Full Code Here
448
449
450
451
452
453
454
455
456
457
458
        {
            throw new ValidationException("Document provided is null");
        }
        else
        {
            PDDocumentInformation dico = document.getDocumentInformation();
            if (metadata == null)
            {
                throw new ValidationException("Metadata provided are null");
            }
            else
View Full Code Here
236
237
238
239
240
241
242
243
244
245
246
247
248
        }
        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
65
66
67
68
69
70
71
72
73
74
75
        clearEntry();
        try
        {
                isris = false;
                document = PDDocument.load(file);
                PDDocumentInformation infos = document.getDocumentInformation();

                PDFTextStripper textStripper=new PDFTextStripper();

                pdfletter = new Integer(pdftextletter.getText());
                if( pdfletter < textStripper.getText(document).length())
View Full Code Here
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
         clearEntry();
         try
            {
                isris = false;
                document = PDDocument.load(file);
                PDDocumentInformation infos = document.getDocumentInformation();

                //System.out.println( "Page Count=" + document.getNumberOfPages() );
               
                pdftitle.setText(infos.getTitle());
                pdfauthor.setText(infos.getAuthor());
                pdfabstract.setText(infos.getSubject());

                if( document != null )
                {
                    document.close();
                }
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
        parse(stream, handler, metadata, new ParseContext());
    }

    private void extractMetadata(PDDocument document, Metadata metadata)
            throws TikaException {
        PDDocumentInformation info = document.getDocumentInformation();
        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());
        } 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
        }
    }
View Full Code Here
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
134
135
136
137
138
139
140
141
        parse(stream, handler, metadata, new ParseContext());
    }

    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
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
        }
    }

    private void extractMetadata(PDDocument document, Metadata metadata)
            throws TikaException {
        PDDocumentInformation info = document.getDocumentInformation();
        metadata.set(PagedText.N_PAGES, document.getNumberOfPages());
        addMetadata(metadata, TikaCoreProperties.TITLE, info.getTitle());
        addMetadata(metadata, TikaCoreProperties.CREATOR, info.getAuthor());
        addMetadata(metadata, TikaCoreProperties.CREATOR_TOOL, info.getCreator());
        addMetadata(metadata, TikaCoreProperties.KEYWORDS, info.getKeywords());
        addMetadata(metadata, "producer", info.getProducer());
        // TODO: Move to description in Tika 2.0
        addMetadata(metadata, TikaCoreProperties.TRANSITION_SUBJECT_TO_OO_SUBJECT, info.getSubject());
        addMetadata(metadata, "trapped", info.getTrapped());
        try {
            // TODO Remove these in Tika 2.0
            addMetadata(metadata, "created", info.getCreationDate());
            addMetadata(metadata, TikaCoreProperties.CREATED, info.getCreationDate());
        } catch (IOException e) {
            // Invalid date format, just ignore
        }
        try {
            Calendar modified = info.getModificationDate();
            addMetadata(metadata, Metadata.LAST_MODIFIED, modified);
            addMetadata(metadata, TikaCoreProperties.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
280
281
282
283
284
285
286
287
288
289
290
291
292
        }
        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
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.