Package org.pdfbox.pdmodel

Examples of org.pdfbox.pdmodel.PDDocument

254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
     *
     * @throws IOException If there is an error parsing the document.
     */
    private static PDDocument parseDocument( InputStream input )throws IOException
    {
        PDDocument document = PDDocument.load( input );
        if( document.isEncrypted() )
        {
            try
            {
                document.decrypt( "" );
            }
            catch( InvalidPasswordException e )
            {
                System.err.println( "Error: The document is encrypted." );
            }
View Full Code Here
75
76
77
78
79
80
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
106
107
108
109
110
111
112
113
        {
            usage();
        }
        else
        {
            PDDocument document = null;
            try
            {
                document = PDDocument.load( args[0] );
                if( document.isEncrypted() )
                {
                    try
                    {
                        document.decrypt( "" );
                    }
                    catch( InvalidPasswordException e )
                    {
                        System.err.println( "Error: Document is encrypted with a password." );
                        System.exit( 1 );
                    }
                }
                PrintTextLocations printer = new PrintTextLocations();
                List allPages = document.getDocumentCatalog().getAllPages();
                for( int i=0; i<allPages.size(); i++ )
                {
                    PDPage page = (PDPage)allPages.get( i );
                    System.out.println( "Processing page: " + i );
                    printer.processStream( page, page.findResources(), page.getContents().getStream() );
                }
            }
            finally
            {
                if( document != null )
                {
                    document.close();
                }
            }
        }
    }
View Full Code Here
84
85
86
87
88
89
90
91
92
93
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
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
        {
            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();
               
                //Right now, PDFBox does not have any XMP library, so we will
                //just consruct the XML by hand.
                StringBuffer xmp= new StringBuffer();
                xmp.append(
                "<?xpacket begin='' id='W5M0MpCehiHzreSzNTczkc9d'?>\n" +
                "<?adobe-xap-filters esc=\"CRLF\"?>\n" +
                "<x:xmpmeta>\n" +
                "    <rdf:RDF xmlns:rdf='http://www.w3.org/1999/02/22-rdf-syntax-ns#'>\n" +
                "        <rdf:Description rdf:about='' xmlns:pdf='http://ns.adobe.com/pdf/1.3/' " +
                                         "pdf:Keywords='" + fixNull( info.getKeywords() ) + "' " +
                                         "pdf:Producer='" + fixNull( info.getProducer() ) + "'></rdf:Description>\n" +
                "        <rdf:Description rdf:about='' xmlns:xap='http://ns.adobe.com/xap/1.0/' " +
                                         "xap:ModifyDate='" + fixNull( info.getModificationDate() ) + "' " +
                                         "xap:CreateDate='" + fixNull( info.getCreationDate() ) + "' " +
                                         "xap:CreatorTool='" + fixNull( info.getCreator() ) + "' " +
                                         "xap:MetadataDate='" + fixNull( new GregorianCalendar() )+ "'>\n" +
                "        </rdf:Description>\n" +
                "        <rdf:Description rdf:about='' xmlns:dc='http://purl.org/dc/elements/1.1/' " +
                                         "dc:format='application/pdf'>\n" +
                "            <dc:title>\n" +
                "                <rdf:Alt>\n" +
                "                    <rdf:li xml:lang='x-default'>" + fixNull( info.getTitle() ) +"</rdf:li>\n" +
                "                </rdf:Alt>\n" +
                "            </dc:title>\n" +
                "            <dc:creator>\n" +
                "                <rdf:Seq>\n" +
                "                    <rdf:li>PDFBox.org</rdf:li>\n" +
                "                </rdf:Seq>\n" +
                "            </dc:creator>\n" +
                "            <dc:description>\n" +
                "                <rdf:Alt>\n" +
                "                    <rdf:li xml:lang='x-default'>" + fixNull( info.getSubject() ) +"</rdf:li>\n" +
                "                </rdf:Alt>\n" +
                "            </dc:description>\n" +
                "        </rdf:Description>\n" +
                "    </rdf:RDF>\n" +
                "</x:xmpmeta>\n" );
               
                //xmp spec says we should put padding, so that the metadata can be appended to
                //in place
                xmp.append( PADDING );
                xmp.append( PADDING );
                xmp.append( PADDING );
                xmp.append( "\n<?xpacket end='w'?>" );
                ByteArrayInputStream mdInput = new ByteArrayInputStream( xmp.toString().getBytes() );
                PDMetadata metadataStream = new PDMetadata(document, mdInput, false );
                catalog.setMetadata( metadataStream );
               
               
                document.save( args[1] );
            }
            finally
            {
                if( document != null )
                {
                    document.close();
                }
            }
        }
    }
View Full Code Here
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
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
134
135
136
137
138
139
140
141
142
143
144
145
146
     *
     * @throws Exception If there is an error extracting the URLs.
     */
    public static void main(String[] args) throws Exception
    {
        PDDocument doc = null;
        try
        {
            if( args.length != 1 )
            {
                usage();
            }
            else
            {
                doc = PDDocument.load( args[0] );
                List allPages = doc.getDocumentCatalog().getAllPages();
                for( int i=0; i<allPages.size(); i++ )
                {
                    PDFTextStripperByArea stripper = new PDFTextStripperByArea();
                    PDPage page = (PDPage)allPages.get( i );
                    List annotations = page.getAnnotations();
                    //first setup text extraction regions
                    for( int j=0; j<annotations.size(); j++ )
                    {
                        PDAnnotation annot = (PDAnnotation)annotations.get( j );
                        if( annot instanceof PDAnnotationLink )
                        {
                            PDAnnotationLink link = (PDAnnotationLink)annot;
                            PDRectangle rect = link.getRectangle();
                            //need to reposition link rectangle to match text space
                            float x = rect.getLowerLeftX();
                            float y = rect.getUpperRightY();
                            float width = rect.getWidth();
                            float height = rect.getHeight();
                            int rotation = page.findRotation();
                            if( rotation == 0 )
                            {
                                PDRectangle pageSize = page.findMediaBox();
                                y = pageSize.getHeight() - y;
                            }
                            else if( rotation == 90 )
                            {
                                //do nothing
                            }
                           
                            Rectangle2D.Float awtRect = new Rectangle2D.Float( x,y,width,height );
                            stripper.addRegion( "" + j, awtRect );
                        }
                    }
                   
                    stripper.extractRegions( page );
                   
                    for( int j=0; j<annotations.size(); j++ )
                    {
                        PDAnnotation annot = (PDAnnotation)annotations.get( j );
                        if( annot instanceof PDAnnotationLink )
                        {
                            PDAnnotationLink link = (PDAnnotationLink)annot;
                            PDAction action = link.getAction();
                            String urlText = stripper.getTextForRegion( "" + j );
                            if( action instanceof PDActionURI )
                            {
                                PDActionURI uri = (PDActionURI)action;
                                System.out.println( "Page " + (i+1) +":'" + urlText + "'=" + uri.getURI() );
                            }
                        }
                    }
                }
            }
        }
        finally
        {
            if( doc != null )
            {
                doc.close();
            }
        }
    }
View Full Code Here
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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
        {
            usage();
        }
        else
        {
            PDDocument document = null;
            FileInputStream file = null;
            try
            {
                file = new FileInputStream( args[0] );
                PDFParser parser = new PDFParser( file );
                parser.parse();
                document = parser.getPDDocument();
                if( document.isEncrypted() )
                {
                    try
                    {
                        document.decrypt( "" );
                    }
                    catch( InvalidPasswordException e )
                    {
                        System.err.println( "Error: Document is encrypted with a password." );
                        System.exit( 1 );
                    }
                }
                PrintDocumentMetaData meta = new PrintDocumentMetaData();
                meta.printMetadata( document );
            }
            finally
            {
                if( file != null )
                {
                    file.close();
                }
                if( document != null )
                {
                    document.close();
                }
            }
        }
    }
View Full Code Here
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
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
     *
     * @throws Exception If there is an error during the process.
     */
    public static void main(String[] args) throws Exception
    {
        PDDocument doc = null;
        try
        {
            if( args.length != 2 )
            {
                usage();
            }
            else
            {
                doc = PDDocument.load( args[0] );
                List allPages = doc.getDocumentCatalog().getAllPages();
                for( int i=0; i<allPages.size(); i++ )
                {
                    PDPage page = (PDPage)allPages.get( i );
                    List annotations = page.getAnnotations();
                   
                    for( int j=0; j<annotations.size(); j++ )
                    {
                        PDAnnotation annot = (PDAnnotation)annotations.get( j );
                        if( annot instanceof PDAnnotationLink )
                        {
                            PDAnnotationLink link = (PDAnnotationLink)annot;
                            PDAction action = link.getAction();
                            if( action instanceof PDActionURI )
                            {
                                PDActionURI uri = (PDActionURI)action;
                                String oldURI = uri.getURI();
                                String newURI = "http://www.pdfbox.org";
                                System.out.println( "Page " + (i+1) +": Replacing " + oldURI + " with " + newURI );
                                uri.setURI( newURI );
                            }
                        }
                    }
                }
                doc.save( args[1] );
            }
        }
        finally
        {
            if( doc != null )
            {
                doc.close();
            }
        }
    }
View Full Code Here
76
77
78
79
80
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
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
     * @throws COSVisitorException If there is an error writing the PDF.
     */
    public void doIt( String file) throws IOException, COSVisitorException
    {
        // the document
        PDDocument doc = null;
        try
        {
            doc = new PDDocument();
           
            PDPage page = new PDPage();
            doc.addPage( page );
            PDFont font = PDType1Font.HELVETICA_BOLD;
           
            PDPageContentStream contentStream = new PDPageContentStream(doc, page);
            contentStream.beginText();
            contentStream.setFont( font, 12 );
            contentStream.moveTextPositionByAmount( 100, 700 );
            contentStream.drawString( "Go to Document->File Attachments to View Embedded Files" );
            contentStream.endText();
            contentStream.close();
           
            //embedded files are stored in a named tree
            PDEmbeddedFilesNameTreeNode efTree = new PDEmbeddedFilesNameTreeNode();
           
           
            //first create the file specification, which holds the embedded file
            PDComplexFileSpecification fs = new PDComplexFileSpecification();
            fs.setFile( "Test.txt" );
            //create a dummy file stream, this would probably normally be a FileInputStream
            byte[] data = "This is the contents of the embedded file".getBytes();
            ByteArrayInputStream fakeFile =
                new ByteArrayInputStream( data );
            PDEmbeddedFile ef = new PDEmbeddedFile(doc, fakeFile );
            //now lets some of the optional parameters
            ef.setSubtype( "test/plain" );
            ef.setSize( data.length );
            ef.setCreationDate( new GregorianCalendar() );
            fs.setEmbeddedFile( ef );
           
            //now add the entry to the embedded file tree and set in the document.
            Map efMap = new HashMap();
            efMap.put( "My first attachment", fs );
            efTree.setNames( efMap );
            PDDocumentNameDictionary names = new PDDocumentNameDictionary( doc.getDocumentCatalog() );
            names.setEmbeddedFiles( efTree );
            doc.getDocumentCatalog().setNames( names );
           
           
            doc.save( file );
        }
        finally
        {
            if( doc != null )
            {
                doc.close();
            }
        }
    }
View Full Code Here
286
287
288
289
290
291
292
     *
     * @throws IOException If there is an error getting the document.
     */
    public PDDocument getPDDocument() throws IOException
    {
        return new PDDocument( getDocument() );
    }
View Full Code Here
63
64
65
66
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
95
    public void doIt(final String file, final String message,
            final String fontfile) throws IOException, COSVisitorException
    {

        // the document
        PDDocument doc = null;
        try
        {
            doc = new PDDocument();

            PDPage page = new PDPage();
            doc.addPage(page);
            PDFont font = new PDType1AfmPfbFont(doc,fontfile);

            PDPageContentStream contentStream = new PDPageContentStream(doc,
                    page);
            contentStream.beginText();
            contentStream.setFont(font, 12);
            contentStream.moveTextPositionByAmount(100, 700);
            contentStream.drawString(message);
            contentStream.endText();
            contentStream.close();
            doc.save(file);
            System.out.println(file + " created!");
        }
        finally
        {
            if (doc != null)
            {
                doc.close();
            }
        }
    }
View Full Code Here
97
98
99
100
101
102
103
104
     *
     * @param doc The document to decrypt.
     */
    public DocumentEncryption( COSDocument doc )
    {
        pdDocument = new PDDocument( doc );
        document = doc;
    }
View Full Code Here
TOP

Related Classes of org.pdfbox.pdmodel.PDDocument

  • br.com.caelum.stella.boleto.transformer.BoletoTransformerIntegrationTest
  • com.stimulus.archiva.extraction.PDFExtractor
  • eu.lsem.bakalarka.filetypeprocess.document.PdfDocumentParser
  • net.sf.jabref.util.XMPUtil
  • org.apache.jackrabbit.core.query.PdfTextFilter
  • org.apache.jackrabbit.extractor.PdfTextExtractor
  • org.apache.nutch.parse.pdf.PdfParser
  • org.exoplatform.services.document.impl.PDFDocumentReader
  • org.infoglue.cms.controllers.kernel.impl.simple.LuceneController
  • org.pdfbox.cos.COSArray
    • 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.