Examples of PDFParser

Examples of org.pdfbox.pdfparser.PDFParser

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
   * @return Reader a reader that is fed to an indexer.
   */
  protected Reader getReader(InputStream docStream)
  {
   
    PDFParser parser = null; PDDocument document = null; PDFTextStripper stripper = null;
    CharArrayWriter writer = null;
    try{
      parser = new PDFParser(docStream);
      parser.parse();
      document = parser.getPDDocument();
      writer = new CharArrayWriter();
      stripper = new PDFTextStripper();
      stripper.setLineSeparator("\n");
      stripper.writeText(document, writer);
      document.close();
      writer.close();
      parser.getDocument().close();
      return new CharArrayReader(writer.toCharArray());
    }catch (Exception e){
        //logger.warn("WARNING: Problem converting PDF: ",e);
      try{
        document.close();       
      }catch(Exception e1){
        //logger.warn("WARNING: Problem converting PDF: ",e1);
      }
      try{
        writer.close();
      }catch(Exception e2){
        //logger.warn("WARNING: Problem converting PDF: ",e2);
      }
      try{
        parser.getDocument().close();
      }catch(Exception e3){
        //logger.warn("WARNING: Problem converting PDF: ",e3); 
      }
      parser = null; document = null; writer = null; stripper = null;
      EOD=true;
View Full Code Here

Examples of org.pdfbox.pdfparser.PDFParser

111
112
113
114
115
116
117
118
119
120
121
122
123
124
      // FileOutputStream fout = new FileOutputStream("/home/nutchwax/lixo/"+System.currentTimeMillis()+".pdf");
      // fout.write(raw);
      // fout.close();
      // TODO MC

      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("");
View Full Code Here

Examples of org.pdfbox.pdfparser.PDFParser

57
58
59
60
61
62
63
64
65
66
67
68
69
70
        InternalValue[] values = data.getValues();
        if (values.length > 0) {
            BLOBFileValue blob = (BLOBFileValue) values[0].internalValue();
               
            try {
                PDFParser parser = new PDFParser(blob.getStream());
                parser.parse();
   
                PDDocument document = parser.getPDDocument();
   
                CharArrayWriter writer = new CharArrayWriter();
   
                PDFTextStripper stripper = new PDFTextStripper();
                stripper.setLineSeparator("\n");
View Full Code Here

Examples of org.pdfbox.pdfparser.PDFParser

85
86
87
88
89
90
91
92
93
94
95
96
97
98
          return new ParseStatus(ParseStatus.FAILED, ParseStatus.FAILED_TRUNCATED,
                  "Content truncated at "+raw.length
            +" bytes. Parser can't handle incomplete pdf file.").getEmptyParse(getConf());
      }

      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("");
View Full Code Here

Examples of org.pdfbox.pdfparser.PDFParser

18
19
20
21
22
23
24
25
26
27
28
29
30
 
  public static final Log log = LogFactory.getLog(PDFIndexer.class);

  public IndexDocument getIndexedDocument(File2Index fileData) throws SolrException {
    try {
      PDFParser parser = new PDFParser(new ByteArrayInputStream(fileData.data));
      parser.parse();
      COSDocument cosDoc = parser.getDocument();

      PDFTextStripper stripper = new PDFTextStripper();
      String docText = stripper.getText(new PDDocument(cosDoc));
      cosDoc.close();
View Full Code Here

Examples of org.pdfbox.pdfparser.PDFParser

183
184
185
186
187
188
189
190
191
192
193
194
195
                validateForLocalUrl(url);
                resourceURL = new URL(url);
                is = resourceURL.openStream();
            }

            PDFParser parser = new PDFParser(is);
            parser.parse();
            COSDocument cosDoc = parser.getDocument();

            PDFTextStripper stripper = new PDFTextStripper();
            String docText = stripper.getText(new PDDocument(cosDoc));
            cosDoc.close();
            Document document = new Document();
View Full Code Here

Examples of org.pdfbox.pdfparser.PDFParser

143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
        try {
            // get file as stream
            input = new FileInputStream(filename);

            // init PDFParser with stream
            PDFParser parser = new PDFParser(input);
            parser.setTempDirectory(new File(System.getProperty("java.io.tmpdir")));

            // parse
            parser.parse();

            // return Document
            return parser.getPDDocument();
        }
        finally {
            IOUtils.closeQuietly(input);
        }
    }
View Full Code Here

Examples of org.pdfbox.pdfparser.PDFParser

105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
          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("");
View Full Code Here

Examples of org.pdfbox.pdfparser.PDFParser

89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
            && 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("");
View Full Code Here

Examples of org.pdfbox.pdfparser.PDFParser

44
45
46
47
48
49
50
51
52
53
54
55
56
57
    public Reader extract(InputStream content)  throws ExtractorException
    {
        try
        {
            PDFParser parser = new PDFParser( content );
            parser.parse();

            PDDocument document = parser.getPDDocument();

            CharArrayWriter writer = new CharArrayWriter();

            PDFTextStripper stripper = new PDFTextStripper();
            stripper.setLineSeparator("\n");
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.