Package org.pdfbox.pdfparser

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
76
77
78
79
80
81
82
83
84
85
86
87
88
        this.contentHandler.startElement(NAMESPACE, "document", PREFIX + ":document",
                new AttributesImpl());

        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) {
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
     */
    public Reader extractText(InputStream stream,
                              String type,
                              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
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
     */
    public Reader extractText(InputStream stream,
                              String type,
                              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
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
        InternalValue[] values = data.getValues();
        if (values.length > 0) {
            final BLOBFileValue blob = (BLOBFileValue) values[0].internalValue();
            LazyReader reader = new LazyReader() {
                protected void initializeReader() throws IOException {
                    PDFParser parser = null;
                    InputStream in;
                    try {
                        in = blob.getStream();
                    } catch (RepositoryException e) {
                        throw new IOException(e.getMessage());
                    }

                    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

                        // JCR-764: Check if document is still open and
                        // close it appropriately. Otherwise some temporary
                        // files may get left behind and document finalization
                        // will log a warning.
                        if (parser != null) {
                            try {
                                parser.getDocument().close();
                            } catch (Exception ioe) {
                                // ignore, this means doc has not been generated
                            }
                        }
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
          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
42
43
44
45
46
47
48
49
50
51
52
53
54
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)");
          
View Full Code Here
269
270
271
272
273
274
275
276
277
278
279
280
281
    {
        COSDocument cos = null;

        try
        {
            PDFParser parser = new PDFParser(metadata);
            parser.parse();
            cos = parser.getDocument();

            // sanity check: PDFBox breaks on encrypted documents, so give up.
            if(cos.getEncryptionDictionary() != null)
                throw new MetadataValidationException("This packager cannot accept an encrypted PDF document.");
View Full Code Here
24
25
26
27
28
29
30
31
32
33
34
35
36
37
    public static void main(String[] args) {
        try {
            String infile = args[0];
            String outfile = args[1];
            FileWriter out = new FileWriter(outfile);
            PDFParser parser =
                    new PDFParser(new FileInputStream(infile));
            parser.parse();
            PDDocument document = parser.getPDDocument();
            PDDocumentCatalog catalog = document.getDocumentCatalog();
            int i = 0;
            for (Object page: catalog.getAllPages()) {
                i++;
                out.write("/Page " + i + " " + "/Rotate "
View Full Code Here
84
85
86
87
88
89
90
91
92
93
94
95
96
97
          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
TOP

Related Classes of org.pdfbox.pdfparser.PDFParser

  • com.stimulus.archiva.extraction.PDFExtractor
  • com.stimulus.archiva.persistence.textextraction.PDFExtractor
  • de.spotnik.mail.core.message.content.PDFHandler
  • ExtractRotate
  • net.nutch.parse.pdf.PdfParser
  • org.apache.jackrabbit.core.query.PdfTextFilter
  • org.apache.jackrabbit.extractor.PdfTextExtractor
  • org.apache.lenya.modules.resource.PdfToTextGenerator
  • org.apache.nutch.parse.pdf.PdfParser
  • org.apache.slide.extractor.PDFExtractor
    • 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.