Examples of PDFTextStripperByArea

Examples of org.apache.pdfbox.util.PDFTextStripperByArea

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
                doc = PDDocument.load( args[0] );
                int pageNum = 0;
                for( PDPage page : doc.getPages() )
                {
                    pageNum++;
                    PDFTextStripperByArea stripper = new PDFTextStripperByArea();
                    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.getRotation();
                            if( rotation == 0 )
                            {
                                PDRectangle pageSize = page.getMediaBox();
                                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 " + pageNum +":'" + urlText + "'=" + uri.getURI() );
                            }
View Full Code Here

Examples of org.apache.pdfbox.util.PDFTextStripperByArea

71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
                    {
                        System.err.println( "Error: Document is encrypted with a password." );
                        System.exit( 1 );
                    }
                }
                PDFTextStripperByArea stripper = new PDFTextStripperByArea();
                stripper.setSortByPosition( true );
                Rectangle rect = new Rectangle( 10, 280, 275, 60 );
                stripper.addRegion( "class1", rect );
                PDPage firstPage = document.getPage(0);
                stripper.extractRegions( firstPage );
                System.out.println( "Text in the area:" + rect );
                System.out.println( stripper.getTextForRegion( "class1" ) );

            }
            finally
            {
                if( document != null )
View Full Code Here

Examples of org.apache.pdfbox.util.PDFTextStripperByArea

62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
                document = PDDocument.load( args[0] );
                if( document.isEncrypted() )
                {
                    document.decrypt( "" );
                }
                PDFTextStripperByArea stripper = new PDFTextStripperByArea();
                stripper.setSortByPosition( true );
                Rectangle rect = new Rectangle( 10, 280, 275, 60 );
                stripper.addRegion( "class1", rect );
                List allPages = document.getDocumentCatalog().getAllPages();
                PDPage firstPage = (PDPage)allPages.get( 0 );
                stripper.extractRegions( firstPage );
                System.out.println( "Text in the area:" + rect );
                System.out.println( stripper.getTextForRegion( "class1" ) );

            }
            finally
            {
                if( document != null )
View Full Code Here

Examples of org.apache.pdfbox.util.PDFTextStripperByArea

192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
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
     * Code adapted from http://www.docjar.com/html/api/org/apache/pdfbox/examples/pdmodel/PrintURLs.java.html
     */
    private Map<String, PDAction> extractLinks(PDPage page) throws Exception
    {
        Map<String, PDAction> links = new HashMap<String, PDAction>();
        PDFTextStripperByArea stripper = new PDFTextStripperByArea();
        List<PDAnnotation> annotations = page.getAnnotations();
        // First setup the text extraction regions.
        for (int j = 0; j < annotations.size(); j++) {
            PDAnnotation annotation = annotations.get(j);
            if (annotation instanceof PDAnnotationLink) {
                PDAnnotationLink link = (PDAnnotationLink) annotation;
                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(String.valueOf(j), awtRect);
            }
        }

        stripper.extractRegions(page);

        for (int j = 0; j < annotations.size(); j++) {
            PDAnnotation annotation = annotations.get(j);
            if (annotation instanceof PDAnnotationLink) {
                PDAnnotationLink link = (PDAnnotationLink) annotation;
                String label = stripper.getTextForRegion(String.valueOf(j)).trim();
                links.put(label, link.getAction());
            }
        }

        return links;
View Full Code Here

Examples of org.apache.pdfbox.util.PDFTextStripperByArea

244
245
246
247
248
249
250
251
252
253
        return destination.toString();
    }

    private String getDestinationText(PDPageXYZDestination destination) throws Exception
    {
        PDFTextStripperByArea stripper = new PDFTextStripperByArea();
        stripper.addRegion("destination", getRectangleBelowDestination(destination));
        stripper.extractRegions(destination.getPage());
        return stripper.getTextForRegion("destination").trim();
    }
View Full Code Here

Examples of org.apache.pdfbox.util.PDFTextStripperByArea

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
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
            {
                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() );
                            }
View Full Code Here

Examples of org.apache.pdfbox.util.PDFTextStripperByArea

71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
                    {
                        System.err.println( "Error: Document is encrypted with a password." );
                        System.exit( 1 );
                    }
                }
                PDFTextStripperByArea stripper = new PDFTextStripperByArea();
                stripper.setSortByPosition( true );
                Rectangle rect = new Rectangle( 10, 280, 275, 60 );
                stripper.addRegion( "class1", rect );
                List allPages = document.getDocumentCatalog().getAllPages();
                PDPage firstPage = (PDPage)allPages.get( 0 );
                stripper.extractRegions( firstPage );
                System.out.println( "Text in the area:" + rect );
                System.out.println( stripper.getTextForRegion( "class1" ) );

            }
            finally
            {
                if( document != null )
View Full Code Here

Examples of org.pdfbox.util.PDFTextStripperByArea

85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
                    {
                        System.err.println( "Error: Document is encrypted with a password." );
                        System.exit( 1 );
                    }
                }
                PDFTextStripperByArea stripper = new PDFTextStripperByArea();
                stripper.setSortByPosition( true );
                Rectangle rect = new Rectangle( 10, 280, 275, 60 );
                stripper.addRegion( "class1", rect );
                List allPages = document.getDocumentCatalog().getAllPages();
                PDPage firstPage = (PDPage)allPages.get( 0 );
                stripper.extractRegions( firstPage );
                System.out.println( "Text in the area:" + rect );
                System.out.println( stripper.getTextForRegion( "class1" ) );
               
            }
            finally
            {
                if( document != null )
View Full Code Here

Examples of org.pdfbox.util.PDFTextStripperByArea

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
            {
                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() );
                            }
View Full Code Here

Examples of org.pdfbox.util.PDFTextStripperByArea

497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
      return result;
  }

    private static void processPage(final List result, final PDPage page, final int pageNum) {
        try {
          final PDFTextStripperByArea stripper = new PDFTextStripperByArea();
          final List linkAnnotations = new ArrayList();
          final List linkRegions = new ArrayList();
            extractAnnotations(page, stripper, linkAnnotations, linkRegions);
            stripper.extractRegions(page);
            final Map uriMap = new HashMap();
            final Map textMap = new HashMap();
            collateLinks(linkAnnotations, linkRegions, uriMap, textMap, stripper);
            final Iterator it = uriMap.keySet().iterator();
            while (it.hasNext()) {
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.