Examples of WordExtractor

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

53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
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
    public Document[] parse(final MultiProtocolURI location, final String mimeType,
            final String charset, final InputStream source)
            throws Parser.Failure, InterruptedException {

        final WordExtractor extractor;

        try {
            extractor = new WordExtractor(source);
        } catch (Exception e) {
            throw new Parser.Failure("error in docParser, WordTextExtractorFactory: " + e.getMessage(), location);
        }

        final StringBuilder contents = new StringBuilder(80);
        try {
            contents.append(extractor.getText().trim());
            contents.append(' ');
            contents.append(extractor.getHeaderText());
            contents.append(' ');
            contents.append(extractor.getFooterText());
        } catch (Exception e) {
            throw new Parser.Failure("error in docParser, getText: " + e.getMessage(), location);
        }
        String title = (contents.length() > 240) ? contents.substring(0,240) : contents.toString().trim();
        title.replaceAll("\r"," ").replaceAll("\n"," ").replaceAll("\t"," ").trim();
        if (title.length() > 80) title = title.substring(0, 80);
        int l = title.length();
        while (true) {
            title = title.replaceAll("  ", " ");
            if (title.length() == l) break;
            l = title.length();
        }

        Document[] docs;
        docs = new Document[]{new Document(
                  location,
                  mimeType,
                  "UTF-8",
                  this,
                  null,
                  null,
                  title,
                  "", // TODO: AUTHOR
                  extractor.getDocSummaryInformation().getCompany(), // publisher
                  null,
                  null,
                  0.0f, 0.0f,
                  UTF8.getBytes(contents.toString()),
                  null,
View Full Code Here

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

83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
    }
  }
 
  private void collectWordDocument(POIFSFileSystem filesystem, StringBuilder sb)
    throws IOException {
    WordExtractor extractor = new WordExtractor(filesystem);
    addTextIfAny(sb, extractor.getHeaderText());
    for (String paragraph : extractor.getParagraphText()) {
        sb.append(paragraph).append(' ');
    }

    for (String paragraph : extractor.getFootnoteText()) {
        sb.append(paragraph).append(' ');
    }

    for (String paragraph : extractor.getCommentsText()) {
        sb.append(paragraph).append(' ');
    }

    for (String paragraph : extractor.getEndnoteText()) {
        sb.append(paragraph).append(' ');
    }
    addTextIfAny(sb, extractor.getFooterText());
  }
View Full Code Here

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

25
26
27
28
29
30
31
32
33
34
35
36
37
    @Override
    public void run() {
        InputStream isr = null;
        try {
            isr = new FileInputStream(pathToFile);
            WordExtractor word = new WordExtractor(isr);
            String fileContent = "";
            String[] paragraphes = word.getParagraphText();
            for (String paragraph : paragraphes) {
                fileContent += " " + paragraph;
            }
            AddDataToIndex AddDataToIndex = new AddDataToIndex(null);
            AddDataToIndex.doAddData(fileContent, pathToFile, fileName);
View Full Code Here

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

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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
            String name = entry.getName();
            if (!(entry instanceof DocumentEntry)) {
                // Skip directory entries
            } else if ("WordDocument".equals(name)) {
                setType(metadata, "application/msword");
                WordExtractor extractor = new WordExtractor(filesystem);

                addTextIfAny(xhtml, "header", extractor.getHeaderText());

                for (String paragraph : extractor.getParagraphText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getFootnoteText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getCommentsText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getEndnoteText()) {
                    xhtml.element("p", paragraph);
                }

                addTextIfAny(xhtml, "footer", extractor.getFooterText());
            } 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");
                Locale locale = context.get(Locale.class, Locale.getDefault());
                new ExcelExtractor().parse(filesystem, xhtml, locale);
            } 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

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

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

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

90
91
92
93
94
95
96
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
                  xhtml.element("p", extractor.getText());
               }
            } else if (entry instanceof DocumentEntry) {
               if ("WordDocument".equals(name)) {
                   setType(metadata, "application/msword");
                   WordExtractor extractor = new WordExtractor(filesystem);

                   addTextIfAny(xhtml, "header", extractor.getHeaderText());

                   for (String paragraph : extractor.getParagraphText()) {
                       xhtml.element("p", paragraph);
                   }

                   for (String paragraph : extractor.getFootnoteText()) {
                       xhtml.element("p", paragraph);
                   }

                   for (String paragraph : extractor.getCommentsText()) {
                       xhtml.element("p", paragraph);
                   }

                   for (String paragraph : extractor.getEndnoteText()) {
                       xhtml.element("p", paragraph);
                   }

                   addTextIfAny(xhtml, "footer", extractor.getFooterText());
               } 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");
                   Locale locale = context.get(Locale.class, Locale.getDefault());
                   new ExcelExtractor().parse(filesystem, xhtml, locale);
               } 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

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

44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
    } else {
      throw new IllegalArgumentException("Parameter must be instance of byte[]");
    }
    String ret = null;
    try {
      WordExtractor docextractor = new WordExtractor(is);
      ret = docextractor.getText();
    } catch (OldWordFileFormatException e) {
      try {
        is.reset();
        Word6Extractor docextractor = new Word6Extractor(is);
        ret = docextractor.getText();
      } catch (IOException e1) {
        throw new CRException(e1);
      }

    } catch (IOException e) {
View Full Code Here

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

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

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

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
113
114
115
116
117
118
119
120
121
122
123
124
            String name = entry.getName();
            if (!(entry instanceof DocumentEntry)) {
                // Skip directory entries
            } else if ("WordDocument".equals(name)) {
                setType(metadata, "application/msword");
                WordExtractor extractor = new WordExtractor(filesystem);

                addTextIfAny(xhtml, "header", extractor.getHeaderText());

                for (String paragraph : extractor.getParagraphText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getFootnoteText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getCommentsText()) {
                    xhtml.element("p", paragraph);
                }

                for (String paragraph : extractor.getEndnoteText()) {
                    xhtml.element("p", paragraph);
                }

                addTextIfAny(xhtml, "footer", extractor.getFooterText());
            } 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

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

113
114
115
116
117
118
119
120
     * Bug 33519 - HWPF fails to read a file
     */
    public void test33519()
    {
        HWPFDocument doc = HWPFTestDataSamples.openSampleFile( "Bug33519.doc" );
        WordExtractor extractor = new WordExtractor( doc );
        extractor.getText();
    }
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.