Package org.apache.pdfbox.pdmodel

Examples of org.apache.pdfbox.pdmodel.PDDocument

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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
  @SuppressWarnings("unchecked")
  public void prepare(RawDocument rawDocument) throws RegainException {
    String url = rawDocument.getUrl();

    InputStream stream = null;
    PDDocument pdfDocument = null;

    try {
      // Create a InputStream that reads the content.
      stream = rawDocument.getContentAsStream();

      // Parse the content
      PDFParser parser = new PDFParser(stream);
      parser.parse();
      pdfDocument = parser.getPDDocument();

      // Decrypt the PDF-Dokument
      if (pdfDocument.isEncrypted()) {
        mLog.debug("Document is encrypted: " + url);
        StandardDecryptionMaterial sdm = new StandardDecryptionMaterial("");
        pdfDocument.openProtection(sdm);
        AccessPermission ap = pdfDocument.getCurrentAccessPermission();

        if (!ap.canExtractContent()) {
          throw new RegainException("Document is encrypted and can't be opened: " + url);
        }
      }

      // Extract the text with a utility class
      PDFTextStripper stripper = new PDFTextStripper();
      stripper.setSuppressDuplicateOverlappingText(false);
      stripper.setSortByPosition(true);
      stripper.setStartPage(1);
      stripper.setEndPage(Integer.MAX_VALUE);

      setCleanedContent(stripper.getText(pdfDocument).replaceAll("visiblespace", " "));

      // extract annotations
      StringBuilder annotsResult = new StringBuilder();
      List allPages = pdfDocument.getDocumentCatalog().getAllPages();
      for (int i = 0; i < allPages.size(); i++) {
        int pageNum = i + 1;
        PDPage page = (PDPage) allPages.get(i);
        List<PDAnnotation> annotations = page.getAnnotations();
        if (annotations.size() < 1) {
          continue;
        }
        mLog.debug("Total annotations = " + annotations.size());
        mLog.debug("\nProcess Page " + pageNum + "...");
        for (PDAnnotation annotation : annotations) {
          if (annotation.getContents() != null && annotation.getContents().length() > 0) {
            annotsResult.append(annotation.getContents());
            annotsResult.append(" ");
            mLog.debug("Text from annotation: " + annotation.getContents());
          }
        }
      }
      if (annotsResult.length() > 0) {
        setCleanedContent(getCleanedContent() + " Annotations " + annotsResult.toString());
      }

      // Get the meta data
      PDDocumentInformation info = pdfDocument.getDocumentInformation();
      StringBuilder metaData = new StringBuilder();
      metaData.append("p.");
      metaData.append(Integer.toString(pdfDocument.getNumberOfPages()));
      metaData.append(" ");

      // Check if fields are null
      if (info.getAuthor() != null) {
        metaData.append(info.getAuthor());
        metaData.append(" ");
      }
      if (info.getSubject() != null) {
        metaData.append(info.getSubject());
        metaData.append(" ");
      }
      if (info.getKeywords() != null) {
        metaData.append(info.getKeywords());
        metaData.append(" ");
      }

      if (info.getTitle() != null) {
        setTitle(info.getTitle());
      }

      setCleanedMetaData(metaData.toString());
      if (mLog.isDebugEnabled()) {
        mLog.debug("Extracted meta data ::" + getCleanedMetaData()
                + ":: from " + rawDocument.getUrl());
      }

    } catch (CryptographyException exc) {
      throw new RegainException("Error decrypting document: " + url, exc);

    } catch (BadSecurityHandlerException exc) {
      // They didn't supply a password and the default of "" was wrong.
      throw new RegainException("Document is encrypted: " + url, exc);

    } catch (IOException exc) {
      throw new RegainException("Error reading document: " + url, exc);

    } finally {
      if (stream != null) {
        try {
          stream.close();
        } catch (Exception exc) {
        }
      }
      if (pdfDocument != null) {
        try {
          pdfDocument.close();
        } catch (Exception exc) {
        }
      }
    }
  }
View Full Code Here
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
147
148
149
150
151
152
153
154
155
        // check memory for parser
        if (!MemoryControl.request(200 * 1024 * 1024, true))
            throw new Parser.Failure("Not enough Memory available for pdf parser: " + MemoryControl.available(), location);

        // create a pdf parser
        PDDocument pdfDoc = null;
        //final PDFParser pdfParser;
        try {
            Thread.currentThread().setPriority(Thread.MIN_PRIORITY);
            pdfDoc = PDDocument.load(source);
            //pdfParser = new PDFParser(source);
            //pdfParser.parse();
            //pdfDoc = pdfParser.getPDDocument();
        } catch (final IOException e) {
            throw new Parser.Failure(e.getMessage(), location);
        } finally {
            Thread.currentThread().setPriority(Thread.NORM_PRIORITY);
        }

        if (pdfDoc.isEncrypted()) {
            try {
                pdfDoc.openProtection(new StandardDecryptionMaterial(""));
            } catch (final BadSecurityHandlerException e) {
                try {pdfDoc.close();} catch (final IOException ee) {}
                throw new Parser.Failure("Document is encrypted (1): " + e.getMessage(), location);
            } catch (final IOException e) {
                try {pdfDoc.close();} catch (final IOException ee) {}
                throw new Parser.Failure("Document is encrypted (2): " + e.getMessage(), location);
            } catch (final CryptographyException e) {
                try {pdfDoc.close();} catch (final IOException ee) {}
                throw new Parser.Failure("Document is encrypted (3): " + e.getMessage(), location);
            }
            final AccessPermission perm = pdfDoc.getCurrentAccessPermission();
            if (perm == null || !perm.canExtractContent())
                throw new Parser.Failure("Document is encrypted and cannot be decrypted", location);
        }

        // extracting some metadata
        final PDDocumentInformation info = pdfDoc.getDocumentInformation();
        String docTitle = null, docSubject = null, docAuthor = null, docPublisher = null, docKeywordStr = null;
        if (info != null) {
            docTitle = info.getTitle();
            docSubject = info.getSubject();
            docAuthor = info.getAuthor();
            docPublisher = info.getProducer();
            if (docPublisher == null || docPublisher.length() == 0) docPublisher = info.getCreator();
            docKeywordStr = info.getKeywords();
            // unused:
            // info.getTrapped());
            // info.getCreationDate());
            // info.getModificationDate();
        }

        if (docTitle == null || docTitle.length() == 0) {
            docTitle = MultiProtocolURI.unescape(location.getFileName());
        }
        CharBuffer writer = null;
        try {
            // create a writer for output
            PDFTextStripper stripper = null;
            writer = new CharBuffer();
            stripper = new PDFTextStripper();
            stripper.writeText(pdfDoc, writer); // may throw a NPE
            pdfDoc.close();
            writer.close();
        } catch (final IOException e) {
            // close the writer
            if (writer != null) try { writer.close(); } catch (final Exception ex) {}
            try {pdfDoc.close();} catch (final IOException ee) {}
            //throw new Parser.Failure(e.getMessage(), location);
        } catch (final NullPointerException e) {
            // this exception appeared after the insertion of the jempbox-1.5.0.jar library
            Log.logException(e);
            // close the writer
            if (writer != null) try { writer.close(); } catch (final Exception ex) {}
            try {pdfDoc.close();} catch (final IOException ee) {}
            //throw new Parser.Failure(e.getMessage(), location);
        } finally {
            try {pdfDoc.close();} catch (final IOException e) {}
        }
        pdfDoc = null;

        String[] docKeywords = null;
        if (docKeywordStr != null) {
View Full Code Here
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
    @Override
    public void run() {
        try {
            String fileContent = "";
            File filePDF = new File(pathToFile);
            PDDocument pdDoc = PDDocument.load(new FileInputStream(filePDF));
            PDFTextStripper PDFTextStripper = null;

            Integer numberOfPages = pdDoc.getNumberOfPages();

            for (int page = 0; page < numberOfPages; page++) {
                PDFTextStripper = new PDFTextStripper("UTF-8");
                PDFTextStripper.setStartPage(page);
                PDFTextStripper.setEndPage(page);
                String text = PDFTextStripper.getText(pdDoc);
                fileContent += " " + text.replaceAll("\\s+", " ").trim();
                text = null;
            }

            pdDoc.close();
            pdDoc = null;
            filePDF = null;
            PDFTextStripper = null;

            if (fileContent.length() < 1) {
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        PDDocument pdfDocument = PDDocument.load(stream);
        try {
            if (pdfDocument.isEncrypted()
                    && !pdfDocument.getCurrentAccessPermission().canExtractContent()) {
                try {
                    String password = metadata.get(PASSWORD);
                    if (password == null) {
                        password = "";
                    }
                    pdfDocument.decrypt(password);
                } catch (Exception e) {
                    // Ignore
                }
            }
            metadata.set(Metadata.CONTENT_TYPE, "application/pdf");
            extractMetadata(pdfDocument, metadata);
            PDF2XHTML.process(pdfDocument, handler, metadata);
        } finally {
            pdfDocument.close();
        }
    }
View Full Code Here
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
            {
               if (is == null)
               {
                  throw new NullPointerException("InputStream is null.");
               }
               PDDocument pdDocument = null;
               StringWriter sw = new StringWriter();
               try
               {
                  if (is.available() == 0)
                     return "";

                  try
                  {
                     pdDocument = PDDocument.load(is);
                  }
                  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
                     {
                        pdDocument.close();
                     }
                     catch (IOException e)
                     {
                     }
                  if (is != null)
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
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
    if (obj instanceof byte[]) {
      is = new ByteArrayInputStream((byte[]) obj);
    } else {
      throw new IllegalArgumentException("Parameter must be instance of byte[]");
    }
    PDDocument pdfDocument = null;
    String contents = null;

    try {
      pdfDocument = PDDocument.load(is);

      if (pdfDocument.isEncrypted()) {
        //Just try using the default password and move on
        pdfDocument.decrypt("");
      }

      //create a writer where to append the text content.
      StringWriter writer = new StringWriter();
      if (stripper == null) {
        stripper = new PDFTextStripper();
      } else {
        stripper.resetEngine();
      }
      stripper.writeText(pdfDocument, writer);

      // Note: the buffer to string operation is costless;
      // the char array value of the writer buffer and the content string
      // is shared as long as the buffer content is not modified, which will
      // not occur here.
      contents = writer.getBuffer().toString();

    } catch (IOException e) {
      throw new CRException(e);
    } catch (CryptographyException e) {
      throw new CRException(e);
    } catch (InvalidPasswordException e) {
      throw new CRException(e);
    } catch (Exception e) {
      //Catch all Exceptions happening here to not disturb the indexer
      e.printStackTrace();
    } finally {
      if (pdfDocument != null) {
        try {
          pdfDocument.close();
        } catch (IOException e) {
          // TODO Auto-generated catch block
          e.printStackTrace();
        }
      }
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
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
      
        PDDocument pdfDocument = null;
        TemporaryResources tmp = new TemporaryResources();
        //config from context, or default if not set via context
        PDFParserConfig localConfig = context.get(PDFParserConfig.class, defaultConfig);
        try {
            // PDFBox can process entirely in memory, or can use a temp file
            //  for unpacked / processed resources
            // Decide which to do based on if we're reading from a file or not already
            TikaInputStream tstream = TikaInputStream.cast(stream);
            if (tstream != null && tstream.hasFile()) {
                // File based, take that as a cue to use a temporary file
                RandomAccess scratchFile = new RandomAccessFile(tmp.createTemporaryFile(), "rw");
                if (localConfig.getUseNonSequentialParser() == true){
                    pdfDocument = PDDocument.loadNonSeq(new CloseShieldInputStream(stream), scratchFile);
                } else {
                    pdfDocument = PDDocument.load(new CloseShieldInputStream(stream), scratchFile, true);
                }
            } else {
                // Go for the normal, stream based in-memory parsing
                if (localConfig.getUseNonSequentialParser() == true){
                    pdfDocument = PDDocument.loadNonSeq(new CloseShieldInputStream(stream), new RandomAccessBuffer());
                } else {
                    pdfDocument = PDDocument.load(new CloseShieldInputStream(stream), true);
                }
            }
           
          
            if (pdfDocument.isEncrypted()) {
                String password = null;
               
                // Did they supply a new style Password Provider?
                PasswordProvider passwordProvider = context.get(PasswordProvider.class);
                if (passwordProvider != null) {
                   password = passwordProvider.getPassword(metadata);
                }
               
                // Fall back on the old style metadata if set
                if (password == null && metadata.get(PASSWORD) != null) {
                   password = metadata.get(PASSWORD);
                }
               
                // If no password is given, use an empty string as the default
                if (password == null) {
                   password = "";
                }
              
                try {
                    pdfDocument.decrypt(password);
                } catch (Exception e) {
                    // Ignore
                }
            }
            metadata.set(Metadata.CONTENT_TYPE, "application/pdf");
            extractMetadata(pdfDocument, metadata);
            PDF2XHTML.process(pdfDocument, handler, context, metadata, localConfig);
           
        } finally {
            if (pdfDocument != null) {
               pdfDocument.close();
            }
            tmp.dispose();
        }
        handler.endDocument();
    }
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
    public void parse(
            InputStream stream, ContentHandler handler,
            Metadata metadata, ParseContext context)
            throws IOException, SAXException, TikaException {
        PDDocument pdfDocument = PDDocument.load(stream, true);
        try {
            if (pdfDocument.isEncrypted()
                    && !pdfDocument.getCurrentAccessPermission().canExtractContent()) {
                try {
                    String password = metadata.get(PASSWORD);
                    if (password == null) {
                        password = "";
                    }
                    pdfDocument.decrypt(password);
                } catch (Exception e) {
                    // Ignore
                }
            }
            metadata.set(Metadata.CONTENT_TYPE, "application/pdf");
            extractMetadata(pdfDocument, metadata);
            PDF2XHTML.process(pdfDocument, handler, metadata);
        } finally {
            pdfDocument.close();
        }
    }
View Full Code Here
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
     * @throws IOException If there is an error saving the document.
     * @throws COSVisitorException If an error occurs while saving the destination file.
     */
    public void mergeDocuments() throws IOException, COSVisitorException
    {
        PDDocument destination = null;
        File sourceFile;
        PDDocument source;
        if (sources != null && sources.size() > 0)
        {
            try
            {
                Iterator sit = sources.iterator();
                sourceFile = (File) sit.next();
                destination = PDDocument.load(sourceFile);
                while (sit.hasNext())
                {
                    sourceFile = (File) sit.next();
                    source = PDDocument.load(sourceFile);
                    try
                    {
                        appendDocument(destination, source);
                    }
                    finally
                    {
                        if (source != null)
                        {
                            source.close();
                        }
                    }
                }
                destination.save(destinationFileName);
            }
View Full Code Here
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
     * @throws Exception when there is an exception
     */
    public void doTestFile(File file, boolean bLogResult, String inDir, String outDir)
        throws Exception
    {
        PDDocument document = null;

        log.info("Preparing to convert " + file.getName());
        try
        {
            document =  PDDocument.load(file);
            writer.writeImage(document, "png", "", 1, Integer.MAX_VALUE, outDir + file.getName() + "-");
        }
        catch(Exception e)
        {
            this.bFail=true;
            log.error("Error converting file " + file.getName(), e);
        }
        finally
        {
            document.close();
        }

        //Now check the resulting files ... did we get identical PNG(s)?
        try
        {
View Full Code Here
TOP

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

  • br.net.woodstock.rockframework.office.pdf.impl.PDFBoxManager
  • cx.fbn.nevernote.gui.PDFPreview
  • de.pdf_scrutinizer.API.app.doc.Info
  • gov.nysenate.openleg.converter.pdf.BillTextPDFConverter
  • gov.nysenate.openleg.converter.pdf.PDFConverter
  • ir.Indexer
  • org.apache.camel.component.fop.FopEndpointTest
  • org.apache.padaf.preflight.helpers.CatalogValidationHelper
  • org.apache.padaf.preflight.helpers.TrailerValidationHelper
  • org.apache.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.