Package org.pdfbox.pdmodel

Examples of org.pdfbox.pdmodel.PDDocument

45
46
47
48
49
50
51
52
53
54
55
56
57
58
    public Reader convertToPlainText(InputStream source, WVTDocumentInfo d) {

        String plainText = null;
        try {
            PDDocument document = PDDocument.load(source);
            PDFTextStripper stripper = new PDFTextStripper();
            plainText = stripper.getText(document);
            document.close();
        } catch (IOException e) {
            WVToolLogger.getGlobalLogger().logException("Could not read or convert PDF Document", e);
            plainText = new String();
        }
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
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
    if (contentType != null && !contentType.startsWith("application/pdf"))
      return new ParseStatus(ParseStatus.FAILED, ParseStatus.FAILED_INVALID_FORMAT,
        "Content-Type not application/pdf: " + contentType).getEmptyParse();

    // in memory representation of pdf file
    PDDocument pdf = null;

    String text = null;
    String title = null;

    try {

      byte[] raw = content.getContent();

      String contentLength = content.get("Content-Length");
      if (contentLength != null
            && raw.length != Integer.parseInt(contentLength)) {
          return new ParseStatus(ParseStatus.FAILED, ParseStatus.FAILED_TRUNCATED,
                  "Content truncated at "+raw.length
            +" bytes. Parser can't handle incomplete pdf file.").getEmptyParse();
      }

      PDFParser parser = new PDFParser(
        new ByteArrayInputStream(raw));
      parser.parse();

      pdf = parser.getPDDocument();

      if (pdf.isEncrypted()) {
        DocumentEncryption decryptor = new DocumentEncryption(pdf);
        //Just try using the default password and move on
        decryptor.decryptDocument("");
      }

      // collect text
      PDFTextStripper stripper = new PDFTextStripper();
      text = stripper.getText(pdf);

      // collect title
      PDDocumentInformation info = pdf.getDocumentInformation();
      title = info.getTitle();
      // more useful info, currently not used. please keep them for future use.
      // pdf.getPageCount();
      // info.getAuthor()
      // info.getSubject()
      // info.getKeywords()
      // info.getCreator()
      // info.getProducer()
      // info.getTrapped()
      // formatDate(info.getCreationDate())
      // formatDate(info.getModificationDate())

    } catch (CryptographyException e) {
      return new ParseStatus(ParseStatus.FAILED,
              "Error decrypting document. " + e).getEmptyParse();
    } catch (InvalidPasswordException e) {
      return new ParseStatus(ParseStatus.FAILED,
              "Can't decrypt document - invalid password. " + e).getEmptyParse();
    } catch (Exception e) { // run time exception
      return new ParseStatus(ParseStatus.FAILED,
              "Can't be handled as pdf document. " + e).getEmptyParse();
    } finally {
      try {
        if (pdf != null)
          pdf.close();
        } catch (IOException e) {
          // nothing to do
        }
    }
View Full Code Here
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
    if (contentType != null && !contentType.startsWith("application/pdf"))
      throw new ParseException(
        "Content-Type not application/pdf: "+contentType);

    // in memory representation of pdf file
    PDDocument pdf = null;

    String text = null;
    String title = null;

    try {

      byte[] raw = content.getContent();

      String contentLength = content.get("Content-Length");
      if (contentLength != null
            && raw.length != Integer.parseInt(contentLength)) {
          throw new ParseException("Content truncated at "+raw.length
            +" bytes. Parser can't handle incomplete pdf file.");
      }

      PDFParser parser = new PDFParser(
        new ByteArrayInputStream(raw));
      parser.parse();

      pdf = parser.getPDDocument();

      if (pdf.isEncrypted()) {
        DocumentEncryption decryptor = new DocumentEncryption(pdf);
        //Just try using the default password and move on
        decryptor.decryptDocument("");
      }

      // collect text
      PDFTextStripper stripper = new PDFTextStripper();
      text = stripper.getText(pdf);

      // collect title
      PDDocumentInformation info = pdf.getDocumentInformation();
      title = info.getTitle();
      // more useful info, currently not used. please keep them for future use.
      // pdf.getPageCount();
      // info.getAuthor()
      // info.getSubject()
      // info.getKeywords()
      // info.getCreator()
      // info.getProducer()
      // info.getTrapped()
      // formatDate(info.getCreationDate())
      // formatDate(info.getModificationDate())

    } catch (ParseException e) {
      throw e;
    } catch (CryptographyException e) {
      throw new ParseException("Error decrypting document. "+e);
    } catch (InvalidPasswordException e) {
      throw new ParseException("Can't decrypt document. "+e);
    } catch (Exception e) { // run time exception
      throw new ParseException("Can't be handled as pdf document. "+e);
    } finally {
      try {
        if (pdf != null)
          pdf.close();
        } catch (IOException e) {
          // nothing to do
        }
    }
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
        try
        {
            PDFParser parser = new PDFParser( content );
            parser.parse();

            PDDocument document = parser.getPDDocument();

            CharArrayWriter writer = new CharArrayWriter();

            PDFTextStripper stripper = new PDFTextStripper();
            stripper.setLineSeparator("\n");
            stripper.writeText(document, writer);

            document.close();
            writer.close();

            return new CharArrayReader(writer.toCharArray());
        }
        catch(Exception e )
View Full Code Here
78
79
80
81
82
83
84
85
86
87
88
89
90
        try {
            PDFTextStripper stripper = new PDFTextStripper();
            PDFParser parser = new PDFParser(this.content.getInputStream());
            parser.parse();
            PDDocument doc = parser.getPDDocument();
            String text = stripper.getText(doc);
            doc.close();
            char[] chars = text.toCharArray();
            this.contentHandler.characters(chars, 0, chars.length);
        } catch (Exception e) {
            throw new ProcessingException(e);
        }
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
                              String encoding) throws IOException {
        try {
            PDFParser parser = new PDFParser(new BufferedInputStream(stream));
            try {
                parser.parse();
                PDDocument document = parser.getPDDocument();
                CharArrayWriter writer = new CharArrayWriter();

                PDFTextStripper stripper = new PDFTextStripper();
                stripper.setLineSeparator("\n");
                stripper.writeText(document, writer);

                return new CharArrayReader(writer.toCharArray());
            } finally {
                try {
                    PDDocument doc = parser.getPDDocument();
                    if (doc != null) {
                        doc.close();
                    }
                } catch (IOException e) {
                    // ignore
                }
            }
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
                              String encoding) throws IOException {
        try {
            PDFParser parser = new PDFParser(new BufferedInputStream(stream));
            try {
                parser.parse();
                PDDocument document = parser.getPDDocument();
                CharArrayWriter writer = new CharArrayWriter();

                PDFTextStripper stripper = new PDFTextStripper();
                stripper.setLineSeparator("\n");
                stripper.writeText(document, writer);

                return new CharArrayReader(writer.toCharArray());
            } finally {
                try {
                    PDDocument doc = parser.getPDDocument();
                    if (doc != null) {
                        doc.close();
                    }
                } catch (IOException e) {
                    // ignore
                }
            }
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
                    try {
                        parser = new PDFParser(new BufferedInputStream(in));
                        parser.parse();

                        PDDocument document = parser.getPDDocument();
                        try {
                            CharArrayWriter writer = new CharArrayWriter();

                            PDFTextStripper stripper = new PDFTextStripper();
                            stripper.setLineSeparator("\n");
                            stripper.writeText(document, writer);

                            delegate = new CharArrayReader(writer.toCharArray());
                        } finally {
                            document.close();
                        }
                    } catch (Exception e) {
                        // it may happen that PDFParser throws a runtime
                        // exception when parsing certain pdf documents
View Full Code Here
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
    if (contentType != null && !contentType.startsWith("application/pdf"))
      return new ParseStatus(ParseStatus.FAILED, ParseStatus.FAILED_INVALID_FORMAT,
        "Content-Type not application/pdf: " + contentType).getEmptyParse();

    // in memory representation of pdf file
    PDDocument pdf = null;

    String text = null;
    String title = null;

    try {

      byte[] raw = content.getContent();

      String contentLength = content.get("Content-Length");
      if (contentLength != null
            && raw.length != Integer.parseInt(contentLength)) {
          return new ParseStatus(ParseStatus.FAILED, ParseStatus.FAILED_TRUNCATED,
                  "Content truncated at "+raw.length
            +" bytes. Parser can't handle incomplete pdf file.").getEmptyParse();
      }

      PDFParser parser = new PDFParser(
        new ByteArrayInputStream(raw));
      parser.parse();

      pdf = parser.getPDDocument();

      if (pdf.isEncrypted()) {
        DocumentEncryption decryptor = new DocumentEncryption(pdf);
        //Just try using the default password and move on
        decryptor.decryptDocument("");
      }

      // collect text
      PDFTextStripper stripper = new PDFTextStripper();
      text = stripper.getText(pdf);

      // collect title
      PDDocumentInformation info = pdf.getDocumentInformation();
      title = info.getTitle();
      // more useful info, currently not used. please keep them for future use.
      // pdf.getPageCount();
      // info.getAuthor()
      // info.getSubject()
      // info.getKeywords()
      // info.getCreator()
      // info.getProducer()
      // info.getTrapped()
      // formatDate(info.getCreationDate())
      // formatDate(info.getModificationDate())

    } catch (CryptographyException e) {
      return new ParseStatus(ParseStatus.FAILED,
              "Error decrypting document. " + e).getEmptyParse();
    } catch (InvalidPasswordException e) {
      return new ParseStatus(ParseStatus.FAILED,
              "Can't decrypt document - invalid password. " + e).getEmptyParse();
    } catch (Exception e) { // run time exception
      return new ParseStatus(ParseStatus.FAILED,
              "Can't be handled as pdf document. " + e).getEmptyParse();
    } finally {
      try {
        if (pdf != null)
          pdf.close();
        } catch (IOException e) {
          // nothing to do
        }
    }
View Full Code Here
40
41
42
43
44
45
46
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
}

public Reader getText(InputStream is,TempFiles tempFiles,Charset charset) throws ExtractionException  {
     logger.debug("extracting pdf file");
   File file = null;
     PDDocument document = null;
     try {
       PDFParser parser = new PDFParser(is);
       parser.parse();
       document = parser.getPDDocument();
       if (document.isEncrypted()) {
           DocumentEncryption decryptor = new DocumentEncryption(document);
           if (logger.isDebugEnabled()) {
               logger.debug("pdf document appears to be encrypted (will attempt decryption)");
          
           }
           decryptor.decryptDocument("");
       }
       file = File.createTempFile("extract", ".tmp");
       tempFiles.markForDeletion(file);
       Writer output = null;
       output = new OutputStreamWriter(new FileOutputStream(file), "UTF-8");
       PDFTextStripper stripper = new PDFTextStripper();
       stripper.writeText(document, output);
       output.close();
      /*logger.debug("PDF extraction completed");
       BufferedReader reader;
       try {
         reader = new BufferedReader(new FileReader(file));
        String line = null;
        while( (line=reader.readLine()) != null) {
          logger.debug("PDF>"+line);
        }
        reader.close();
       } catch(Exception e) {
         logger.error("failed to open txt file",e);
       }*/
     } catch (Exception e) {
         throw new ExtractionException("failed to extract pdf (probable password protected document)",e,logger,Level.DEBUG);
     } finally {
       try {
         if(document != null)
             document.close();
       } catch (IOException io) {}
     }
     try {
         logger.debug("returning extracted PDF data");
          return new FileReader(file);
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.