Package org.pdfbox.util

Examples of org.pdfbox.util.PDFTextStripper

22
23
24
25
26
27
28
29
30
31
32
33
    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();

      return new IndexDocument(fileData.path, docText, null);
    } catch (IOException e) {
      String msg = "Failed to write to the index";
View Full Code Here
187
188
189
190
191
192
193
194
195
196
197
198
            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();
            document.add(new Field("id", id, Field.Store.YES, Field.Index.TOKENIZED));
            document.add(
                    new Field("content", docText, Field.Store.NO, Field.Index.TOKENIZED));
View Full Code Here
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
            PDDocument document = null;

           
            try {

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


             
              //load the document
                document = PDDocument.load(in);

                String author = "";
                String title = "";
                String summary = "";

                //get the additional data
                try {
                    PDDocumentInformation pdfinfo = document.getDocumentInformation();

                    if (!Util.isEmpty(pdfinfo.getAuthor())) {
                        author = pdfinfo.getAuthor();
                    }

                    if (!Util.isEmpty(pdfinfo.getTitle())) {
                        title = pdfinfo.getTitle();
                    }

                    if (!Util.isEmpty(pdfinfo.getSubject())) {
                        summary = pdfinfo.getSubject();
                    }
                } catch (Exception eR) {
                    String message = MessageUtil.getMessage("extractor.pdf.metadatamissing",
                            new Object[] { info.getUri() });
                    logger.info(message);
                }

                //set the buffer
                bout = new ByteArrayOutputStream();
                writer = new OutputStreamWriter(bout);

                //strip the document to the buffer
                stripper.writeText(document, writer);
                bout.flush();
                writer.flush();

                //construct the patterns (to not ignore and replace)
                Pattern notIgnorePattern = Pattern.compile(getNotIgnoreChars());
View Full Code Here
81
82
83
84
85
86
87
88
89
90
91
92
            try {
                log.debug("parse() Attempting to extract text from (" + filename + ")");

                output = new StringWriter();

                PDFTextStripper stripper = new PDFTextStripper();
                stripper.writeText(document, output);

                log.debug("parse() Successfully stripped out text from (" + filename + ")");
            }
            catch (IOException ioe) {
                log.error("parse() failed", ioe);
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
57
    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
118
119
120
121
122
123
124
125
126
127
128
129
        //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
102
103
104
105
106
107
108
109
110
111
112
113
        //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
51
52
53
54
55
56
57
58
59
60
61
62
63
            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());
View Full Code Here
196
197
198
199
200
201
202
203
204
205
206
207
208
    return getTextInternal(startPage, endPage);
  }

  protected String getTextInternal(int startPage, int endPage) {
    try {
      final PDFTextStripper textStripper = new PDFTextStripper();
      textStripper.setStartPage(startPage);
      textStripper.setEndPage(endPage);
      return textStripper.getText(getPDFDocument());
    } catch (final IOException e) {
      throw new RuntimeException("Problem extracting text", e);
    }
  }
View Full Code Here
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
        final String lineSeparator, final String pageSeparator)
    {
        final StringWriter output = new StringWriter();
        try
        {
            final PDFTextStripper textStripper = new PDFTextStripper();
            textStripper.setPageSeparator(pageSeparator);
            textStripper.setLineSeparator(lineSeparator);
            textStripper.setStartPage(startPage);
            textStripper.setEndPage(endPage);
            textStripper.writeText(getPDFDocument(), output);
            return output.toString();
        }
        catch (final Exception e)
        {
            throw new RuntimeException("Error while extracting text from document.", e);
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.