Package org.pdfbox.util

Examples of org.pdfbox.util.PDFTextStripper

622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
        final List fragments = new ArrayList();

        final StringWriter output = new StringWriter();
        try
        {
            final PDFTextStripper textStripper = new PDFTextStripper()
            {
                protected void showCharacter(TextPosition textPosition) {
                    fragments.add(textPosition);
                }
            };
            textStripper.setLineSeparator(lineSeparator);
            textStripper.setStartPage(page);
            textStripper.setEndPage(page);
            textStripper.writeText(getPDFDocument(), output);
            return fragments;
        }
        catch (final Exception e)
        {
            throw new RuntimeException("Error while extracting text from document.", e);
View Full Code Here
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
        this.contentHandler.startPrefixMapping(PREFIX, NAMESPACE);
        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) {
            throw new ProcessingException(e);
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
            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();
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
79
80
            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();
View Full Code Here
84
85
86
87
88
89
90
91
92
93
94
95
96
                        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();
                        }
View Full Code Here
117
118
119
120
121
122
123
124
125
126
127
128
        //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.
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
68
       }
       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));
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
        {
            boolean useTemporaryFile = ConfigurationManager.getBooleanProperty("pdffilter.largepdfs", false);

            // get input stream from bitstream
            // pass to filter, get string back
            PDFTextStripper pts = new PDFTextStripper();
            PDDocument pdfDoc = null;
            Writer writer = null;
            File tempTextFile = null;
            ByteArrayOutputStream byteStream = null;

            if (useTemporaryFile)
            {
                tempTextFile = File.createTempFile("dspacepdfextract" + source.hashCode(), ".txt");
                tempTextFile.deleteOnExit();
                writer = new OutputStreamWriter(new FileOutputStream(tempTextFile));
            }
            else
            {
                byteStream = new ByteArrayOutputStream();
                writer = new OutputStreamWriter(byteStream);
            }
           
            try
            {
                pdfDoc = PDDocument.load(source);
                pts.writeText(pdfDoc, writer);
            }
            finally
            {
                try
                {
View Full Code Here
167
168
169
170
171
172
173
174
175
176
177
178
                pdfDocument.decrypt( "" );
            }
           
            //create a writer where to append the text content.
            StringWriter writer = new StringWriter();
            PDFTextStripper stripper = new PDFTextStripper();
            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.
View Full Code Here
96
97
98
99
100
101
102
103
104
105
106
107
        //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.
View Full Code Here
TOP

Related Classes of org.pdfbox.util.PDFTextStripper

  • br.com.caelum.stella.boleto.transformer.BoletoTransformerIntegrationTest
  • com.canoo.webtest.plugins.pdftest.htmlunit.pdfbox.PdfBoxPDFPage
  • com.stimulus.archiva.extraction.PDFExtractor
  • com.stimulus.archiva.persistence.textextraction.PDFExtractor
  • de.spotnik.mail.core.message.content.PDFHandler
  • edu.udo.cs.wvtool.generic.inputfilter.PDFInputFilter
  • eu.lsem.bakalarka.filetypeprocess.document.PdfDocumentParser
  • eu.planets_project.services.migration.pdfbox.TextExtractor
  • it.unimi.dsi.mg4j.document.PdfDocumentFactory
  • net.fp.rp.search.back.extractor.PdfDataExtractor
    • 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.