Package org.apache.poi.hwpf.extractor

Examples of org.apache.poi.hwpf.extractor.WordExtractor

446
447
448
449
450
451
452
453
454
455
456
    public void test47742() throws Exception
    {

        // (1) extract text from MS Word document via POI
        HWPFDocument doc = HWPFTestDataSamples.openSampleFile( "Bug47742.doc" );
        String foundText = new WordExtractor( doc ).getText();

        // (2) read text from text document (retrieved by saving the word
        // document as text file using encoding UTF-8)
        InputStream is = POIDataSamples.getDocumentInstance()
                .openResourceAsStream( "Bug47742-text.txt" );
View Full Code Here
692
693
694
695
696
697
698
699
700
        {
            String href = "http://domex.nps.edu/corp/files/govdocs1/007/007488.doc";
            HWPFDocument hwpfDocument = HWPFTestDataSamples
                    .openRemoteFile( href );

            WordExtractor wordExtractor = new WordExtractor( hwpfDocument );
            wordExtractor.getText();
        }
    }
View Full Code Here
220
221
222
223
224
225
226
227
228
229
230
        }

        if (poifsDir.hasEntry("WordDocument")) {
            // Old or new style word document?
            try {
                return new WordExtractor(poifsDir);
            } catch (OldWordFileFormatException e) {
                return new Word6Extractor(poifsDir);
            }
        }
View Full Code Here
119
120
121
122
123
124
125
126
127
128
129
     
      if(entry.getName().equals("Workbook")) {
        return new ExcelExtractor(poifsDir, fs);
      }
      if(entry.getName().equals("WordDocument")) {
        return new WordExtractor(poifsDir, fs);
      }
      if(entry.getName().equals("PowerPoint Document")) {
        return new PowerPointExtractor(poifsDir, fs);
      }
      if(entry.getName().equals("VisioDocument")) {
View Full Code Here
128
129
130
131
132
133
134
135
136
137
138
     
      if(entry.getName().equals("Workbook")) {
        return new ExcelExtractor(poifsDir, fs);
      }
      if(entry.getName().equals("WordDocument")) {
        return new WordExtractor(poifsDir, fs);
      }
      if(entry.getName().equals("PowerPoint Document")) {
        return new PowerPointExtractor(poifsDir, fs);
      }
      if(entry.getName().equals("VisioDocument")) {
View Full Code Here
216
217
218
219
220
221
222
223
224
225
226
         } else {
            return new ExcelExtractor(poifsDir, fs);
         }
      }
      if(entry.getName().equals("WordDocument")) {
        return new WordExtractor(poifsDir, fs);
      }
      if(entry.getName().equals("PowerPoint Document")) {
        return new PowerPointExtractor(poifsDir, fs);
      }
      if(entry.getName().equals("VisioDocument")) {
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
     */
    public Reader extractText(InputStream stream,
                              String type,
                              String encoding) throws IOException {
        try {
            return new StringReader(new WordExtractor(stream).getText());
        } catch (Exception e) {
            logger.warn("Failed to extract Word text content", e);
            return new StringReader("");
        } finally {
            stream.close();
View Full Code Here
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
            } else if (SUMMARY_INFORMATION.equals(name)
                    || DOCUMENT_SUMMARY_INFORMATION.equals(name)) {
                parse((DocumentEntry) entry, metadata);
            } else if ("WordDocument".equals(name)) {
                setType(metadata, "application/msword");
                WordExtractor extractor = new WordExtractor(filesystem);
                for (String paragraph : extractor.getParagraphText()) {
                    xhtml.element("p", paragraph);
                }
            } else if ("PowerPoint Document".equals(name)) {
                setType(metadata, "application/vnd.ms-powerpoint");
                PowerPointExtractor extractor =
                    new PowerPointExtractor(filesystem);
                xhtml.element("p", extractor.getText(true, true));
            } else if ("Workbook".equals(name)) {
                setType(metadata, "application/vnd.ms-excel");
                new ExcelExtractor().parse(filesystem, xhtml);
            } else if ("VisioDocument".equals(name)) {
                setType(metadata, "application/vnd.visio");
                VisioTextExtractor extractor =
                    new VisioTextExtractor(filesystem);
                for (String text : extractor.getAllText()) {
                    xhtml.element("p", text);
                }
            } else if (name.startsWith("__substg1.0_")) {
                setType(metadata, "application/vnd.ms-outlook");
                new OutlookExtractor(filesystem).parse(xhtml, metadata);
View Full Code Here
113
114
115
116
117
118
119
120
121
122
123
     
      if(entry.getName().equals("Workbook")) {
        return new ExcelExtractor(fs);
      }
      if(entry.getName().equals("WordDocument")) {
        return new WordExtractor(fs);
      }
      if(entry.getName().equals("PowerPoint Document")) {
        return new PowerPointExtractor(fs);
      }
      if(entry.getName().equals("VisioDocument")) {
View Full Code Here
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
            } else if (SUMMARY_INFORMATION.equals(name)
                    || DOCUMENT_SUMMARY_INFORMATION.equals(name)) {
                parse((DocumentEntry) entry, metadata);
            } else if ("WordDocument".equals(name)) {
                setType(metadata, "application/msword");
                WordExtractor extractor = new WordExtractor(filesystem);
                for (String paragraph : extractor.getParagraphText()) {
                    xhtml.element("p", paragraph);
                }
            } else if ("PowerPoint Document".equals(name)) {
                setType(metadata, "application/vnd.ms-powerpoint");
                PowerPointExtractor extractor =
                    new PowerPointExtractor(filesystem);
                xhtml.element("p", extractor.getText(true, true));
            } else if ("Workbook".equals(name)) {
                setType(metadata, "application/vnd.ms-excel");
                new ExcelExtractor().parse(filesystem, xhtml);
            } else if ("VisioDocument".equals(name)) {
                setType(metadata, "application/vnd.visio");
                VisioTextExtractor extractor =
                    new VisioTextExtractor(filesystem);
                for (String text : extractor.getAllText()) {
                    xhtml.element("p", text);
                }
            } else if (!outlookExtracted && name.startsWith("__substg1.0_")) {
                // TODO: Cleaner mechanism for detecting Outlook
                outlookExtracted = true;
View Full Code Here
TOP

Related Classes of org.apache.poi.hwpf.extractor.WordExtractor

  • com.gentics.cr.lucene.indexer.transformer.doc.DOCContentTransformer
  • com.google.code.ftspc.lector.parsers.POI.DocParser
  • net.yacy.document.parser.docParser
  • org.apache.jackrabbit.extractor.MsWordTextExtractor
  • org.apache.poi.extractor.ExtractorFactory
  • org.apache.poi.hwpf.converter.WordToTextConverter
  • org.apache.poi.hwpf.HWPFDocument
  • org.apache.poi.hwpf.model.TextPiece
  • org.apache.poi.hwpf.usermodel.HeaderStories
  • org.apache.poi.hwpf.usermodel.Paragraph
    • 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.