Package org.apache.pdfbox.util

Examples of org.apache.pdfbox.util.PDFTextStripper$WordWithTextPositions

67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
        {
                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())
                {
                    pdftext = textStripper.getText(document).substring(0, pdfletter);
                }
                else
                {
                    pdftext = textStripper.getText(document).substring(0, textStripper.getText(document).length());
                }
                pdfabstract.setText(pdftext);

                if( document != null )
                {
View Full Code Here
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
                        output = new OutputStreamWriter(
                                new FileOutputStream( outputFile ) );
                    }
                }

                PDFTextStripper stripper = null;
                if(toHTML)
                {
                    stripper = new PDFText2HTML(encoding);
                }
                else
                {
                    stripper = new PDFTextStripper(encoding);
                }
                stripper.setForceParsing( force );
                stripper.setSortByPosition( sort );
                stripper.setShouldSeparateByBeads( separateBeads );
                stripper.setStartPage( startPage );
                stripper.setEndPage( endPage );

                startTime = startProcessing("Starting text extraction");
                if (debug)
                {
                    System.err.println("Writing to "+outputFile);
                }
               
                // Extract text for main document:
                stripper.writeText( document, output );
               
                // ... also for any embedded PDFs:
                PDDocumentCatalog catalog = document.getDocumentCatalog();
                PDDocumentNameDictionary names = catalog.getNames();   
                if (names != null)
                {
                    PDEmbeddedFilesNameTreeNode embeddedFiles = names.getEmbeddedFiles();
                    if (embeddedFiles != null)
                    {
                        Map<String,Object> embeddedFileNames = embeddedFiles.getNames();
                        if (embeddedFileNames != null) {
                            for (Map.Entry<String,Object> ent : embeddedFileNames.entrySet())
                            {
                                if (debug)
                                {
                                    System.err.println("Processing embedded file " + ent.getKey() + ":");
                                }
                                PDComplexFileSpecification spec = (PDComplexFileSpecification) ent.getValue();
                                PDEmbeddedFile file = spec.getEmbeddedFile();
                                if (file.getSubtype().equals("application/pdf"))
                                {
                                    if (debug)
                                    {
                                        System.err.println("  is PDF (size=" + file.getSize() + ")");
                                    }
                                    InputStream fis = file.createInputStream();
                                    PDDocument subDoc = null;
                                    try
                                    {
                                        subDoc = PDDocument.load(fis);
                                    }
                                    finally
                                    {
                                        fis.close();
                                    }
                                    try
                                    {
                                        stripper.writeText( subDoc, output );
                                    }
                                    finally
                                    {
                                        subDoc.close();
                                    }
View Full Code Here
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
                        output = new OutputStreamWriter(
                                new FileOutputStream( outputFile ) );
                    }
                }

                PDFTextStripper stripper = null;
                if(toHTML)
                {
                    stripper = new PDFText2HTML(encoding);
                }
                else
                {
                    stripper = new PDFTextStripper(encoding);
                }
                stripper.setForceParsing( force );
                stripper.setSortByPosition( sort );
                stripper.setShouldSeparateByBeads( separateBeads );
                stripper.setStartPage( startPage );
                stripper.setEndPage( endPage );

                startTime = startProcessing("Starting text extraction");
                stripper.writeText( document, output );
                stopProcessing("Time for extraction: ", startTime);
            }
            finally
            {
                if( output != null )
View Full Code Here
44
45
46
47
48
49
50
51
52
        }
    }

    public static String extractTextFrom(PDDocument document) throws IOException {
        Writer output = new StringWriter();
        PDFTextStripper stripper = new PDFTextStripper();
        stripper.writeText(document, output);
        return output.toString().trim();
    }
View Full Code Here
88
89
90
91
92
93
94
95
96
97
98
99
100
101
         catch (IOException e)
         {
            throw new DocumentReadException("Can not load PDF document.", e);
         }

         PDFTextStripper stripper = new PDFTextStripper();
         stripper.setStartPage(1);
         stripper.setEndPage(Integer.MAX_VALUE);
         stripper.writeText(pdDocument, sw);
      }
      finally
      {
         if (pdDocument != null)
            try
View Full Code Here
163
164
165
166
167
168
169
170
171
172
173
174
175
    PDFParser parser = new PDFParser(source);
    parser.parse();

    PDDocument document = parser.getPDDocument();
    PDFTextStripper stripper = new PDFTextStripper();

    String text = stripper.getText(document);

    document.close();

    return text;
  }
View Full Code Here
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
                        output = new OutputStreamWriter(
                                new FileOutputStream( outputFile ) );
                    }
                }

                PDFTextStripper stripper = null;
                if(toHTML)
                {
                    stripper = new PDFText2HTML(encoding);
                }
                else
                {
                    stripper = new PDFTextStripper(encoding);
                }
                stripper.setForceParsing( force );
                stripper.setSortByPosition( sort );
                stripper.setShouldSeparateByBeads( separateBeads );
                stripper.setStartPage( startPage );
                stripper.setEndPage( endPage );

                startTime = startProcessing("Starting text extraction");
                if (debug)
                {
                    System.err.println("Writing to "+outputFile);
                }
               
                // Extract text for main document:
                stripper.writeText( document, output );
               
                // ... also for any embedded PDFs:
                PDDocumentCatalog catalog = document.getDocumentCatalog();
                PDDocumentNameDictionary names = catalog.getNames();   
                if (names != null)
                {
                    PDEmbeddedFilesNameTreeNode embeddedFiles = names.getEmbeddedFiles();
                    if (embeddedFiles != null)
                    {
                        Map<String,COSObjectable> embeddedFileNames = embeddedFiles.getNames();
                        if (embeddedFileNames != null) {
                            for (Map.Entry<String,COSObjectable> ent : embeddedFileNames.entrySet())
                            {
                                if (debug)
                                {
                                    System.err.println("Processing embedded file " + ent.getKey() + ":");
                                }
                                PDComplexFileSpecification spec = (PDComplexFileSpecification) ent.getValue();
                                PDEmbeddedFile file = spec.getEmbeddedFile();
                                if (file != null && file.getSubtype().equals("application/pdf"))
                                {
                                    if (debug)
                                    {
                                        System.err.println("  is PDF (size=" + file.getSize() + ")");
                                    }
                                    InputStream fis = file.createInputStream();
                                    PDDocument subDoc = null;
                                    try
                                    {
                                        subDoc = PDDocument.load(fis);
                                    }
                                    finally
                                    {
                                        fis.close();
                                    }
                                    try
                                    {
                                        stripper.writeText( subDoc, output );
                                    }
                                    finally
                                    {
                                        subDoc.close();
                                    }
View Full Code Here
401
402
403
404
405
406
407
408
409
410
411
            //create a writer where to append the text content.
            StringWriter writer = new StringWriter();
            if( stripper == null )
            {
                stripper = new PDFTextStripper();
            }
            else
            {
                stripper.resetEngine();
            }
View Full Code Here
402
403
404
405
406
407
408
409
410
411
412
            //create a writer where to append the text content.
            StringWriter writer = new StringWriter();
            if( stripper == null )
            {
                stripper = new PDFTextStripper();
            }
            else
            {
                stripper.resetEngine();
            }
View Full Code Here
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
                        output = new OutputStreamWriter(
                                new FileOutputStream( outputFile ) );
                    }
                }

                PDFTextStripper stripper = null;
                if(toHTML)
                {
                    stripper = new PDFText2HTML(encoding);
                }
                else
                {
                    stripper = new PDFTextStripper(encoding);
                }
                stripper.setForceParsing( force );
                stripper.setSortByPosition( sort );
                stripper.setShouldSeparateByBeads( separateBeads );
                stripper.setStartPage( startPage );
                stripper.setEndPage( endPage );
                stripper.writeText( document, output );
            }
            finally
            {
                if( output != null )
                {
View Full Code Here
TOP

Related Classes of org.apache.pdfbox.util.PDFTextStripper$WordWithTextPositions

  • br.com.objectos.way.reports.htmltopdf.Pdfs
  • br.net.woodstock.rockframework.document.pdf.pdfbox.GetTextProcessor
  • br.net.woodstock.rockframework.office.pdf.impl.PDFBoxManager
  • com.cardence.lawshelf.pdf.PdfBoxParserImpl
  • com.gentics.cr.lucene.indexer.transformer.pdf.PDFContentTransformer
  • com.google.code.ftspc.lector.parsers.PDF.PDFParserLocal
  • com.stimulus.archiva.extraction.PDFExtractor
  • de.pdf_scrutinizer.document.DocumentAdapter
  • geopms.GeoPMSImportPDF
  • ir.Indexer
    • 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.