Package org.apache.poi.hwpf

Examples of org.apache.poi.hwpf.HWPFOldDocument

678
679
680
681
682
683
684
685
    /**
     * Bug 51944 - PAPFormattedDiskPage.getPAPX - IndexOutOfBounds
     */
    public void testBug51944() throws Exception
    {
        HWPFOldDocument doc = HWPFTestDataSamples.openOldSampleFile( "Bug51944.doc" );
        WordToTextConverter.getText( doc );
    }
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
         HWPFTestDataSamples.openSampleFile("Word6.doc");
         fail("Shouldn't be openable");
      } catch(OldFileFormatException e) {}
     
      // Open
      HWPFOldDocument doc = HWPFTestDataSamples.openOldSampleFile("Word6.doc");
     
      // Check
      assertEquals(1, doc.getRange().numSections());
      assertEquals(1, doc.getRange().numParagraphs());
      assertEquals(2, doc.getRange().numCharacterRuns());
     
      assertEquals(
            "The quick brown fox jumps over the lazy dog\r",
            doc.getRange().getParagraph(0).text()
      );
   }
View Full Code Here
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
         HWPFTestDataSamples.openSampleFile("Word95.doc");
         fail("Shouldn't be openable");
      } catch(OldFileFormatException e) {}
     
      // Open
      HWPFOldDocument doc = HWPFTestDataSamples.openOldSampleFile("Word95.doc");
     
      // Check
      assertEquals(1, doc.getRange().numSections());
      assertEquals(7, doc.getRange().numParagraphs());
     
      assertEquals(
            "The quick brown fox jumps over the lazy dog\r",
            doc.getRange().getParagraph(0).text()
      );
      assertEquals("\r", doc.getRange().getParagraph(1).text());
      assertEquals(
            "Paragraph 2\r",
            doc.getRange().getParagraph(2).text()
      );
      assertEquals("\r", doc.getRange().getParagraph(3).text());
      assertEquals(
            "Paragraph 3. Has some RED text and some " +
            "BLUE BOLD text in it.\r",
            doc.getRange().getParagraph(4).text()
      );
      assertEquals("\r", doc.getRange().getParagraph(5).text());
      assertEquals(
            "Last (4th) paragraph.\r",
            doc.getRange().getParagraph(6).text()
      );
     
      assertEquals(1, doc.getRange().getParagraph(0).numCharacterRuns());
      assertEquals(1, doc.getRange().getParagraph(1).numCharacterRuns());
      assertEquals(1, doc.getRange().getParagraph(2).numCharacterRuns());
      assertEquals(1, doc.getRange().getParagraph(3).numCharacterRuns());
      // Normal, red, normal, blue+bold, normal
      assertEquals(5, doc.getRange().getParagraph(4).numCharacterRuns());
      assertEquals(1, doc.getRange().getParagraph(5).numCharacterRuns());
      // Normal, superscript for 4th, normal
      assertEquals(4, doc.getRange().getParagraph(6).numCharacterRuns());
   }
View Full Code Here
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
   /**
    * Test a word document that has sections,
    *  as well as the usual paragraph stuff.
    */
   public void testWord6Sections() throws Exception {
      HWPFOldDocument doc = HWPFTestDataSamples.openOldSampleFile("Word6_sections.doc");
     
      assertEquals(3, doc.getRange().numSections());
      assertEquals(6, doc.getRange().numParagraphs());
     
      assertEquals(
            "This is a test.\r",
            doc.getRange().getParagraph(0).text()
      );
      assertEquals("\r", doc.getRange().getParagraph(1).text());
      assertEquals("\u000c", doc.getRange().getParagraph(2).text()); // Section line?
      assertEquals("This is a new section.\r", doc.getRange().getParagraph(3).text());
      assertEquals("\u000c", doc.getRange().getParagraph(4).text()); // Section line?
      assertEquals("\r", doc.getRange().getParagraph(5).text());
   }
View Full Code Here
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
   /**
    * Another word document with sections, this time with a
    *  few more section properties set on it
    */
   public void testWord6Sections2() throws Exception {
      HWPFOldDocument doc = HWPFTestDataSamples.openOldSampleFile("Word6_sections2.doc");
     
      assertEquals(1, doc.getRange().numSections());
      assertEquals(57, doc.getRange().numParagraphs());
     
      assertEquals(
            "\r",
            doc.getRange().getParagraph(0).text()
      );
      assertEquals(
            "STATEMENT  OF  INSOLVENCY  PRACTICE  10  (SCOTLAND)\r",
            doc.getRange().getParagraph(1).text()
      );
   }
View Full Code Here
95
96
97
98
99
100
101
102
        {
            return new HWPFDocument( poifsFileSystem );
        }
        catch ( OldWordFileFormatException exc )
        {
            return new HWPFOldDocument( poifsFileSystem );
        }
    }
View Full Code Here
472
473
474
475
476
477
478
479
480
481
482
        assertTableStructures( expected, actual );
    }

    public void test49933()
    {
        HWPFOldDocument document = HWPFTestDataSamples
                .openOldSampleFile( "Bug49933.doc" );

        Word6Extractor word6Extractor = new Word6Extractor( document );
        String text = word6Extractor.getText();
View Full Code Here
496
497
498
499
500
501
502
503
504
505
506
     */
    public void test50955()
    {
        try
        {
            HWPFOldDocument doc = HWPFTestDataSamples
                    .openOldSampleFile( "Bug50955.doc" );
            Word6Extractor extractor = new Word6Extractor( doc );
            extractor.getText();

            fixed( "50955" );
View Full Code Here
428
429
430
431
432
433
434
435
436
437
438
    }

    protected void parseWord6(
            DirectoryNode root, XHTMLContentHandler xhtml)
            throws IOException, SAXException, TikaException {
        HWPFOldDocument doc = new HWPFOldDocument(root);
        Word6Extractor extractor = new Word6Extractor(doc);
       
        for(String p : extractor.getParagraphText()) {
            xhtml.element("p", p);
        }
View Full Code Here
457
458
459
460
461
462
463
464
465
466
467
    }

    protected void parseWord6(
            DirectoryNode root, XHTMLContentHandler xhtml)
            throws IOException, SAXException, TikaException {
        HWPFOldDocument doc = new HWPFOldDocument(root);
        Word6Extractor extractor = new Word6Extractor(doc);
       
        for(String p : extractor.getParagraphText()) {
            xhtml.element("p", p);
        }
View Full Code Here
TOP

Related Classes of org.apache.poi.hwpf.HWPFOldDocument

  • com.google.code.ftspc.lector.parsers.POI.DocParser
  • org.apache.poi.hwpf.converter.AbstractWordUtils
  • org.apache.poi.hwpf.dev.HWPFLister
  • org.apache.poi.hwpf.extractor.Word6Extractor
  • org.apache.poi.hwpf.model.ComplexFileTable
  • org.apache.poi.hwpf.model.OldCHPBinTable
  • org.apache.poi.hwpf.model.OldPAPBinTable
  • org.apache.poi.hwpf.model.OldSectionTable
  • org.apache.poi.hwpf.model.PieceDescriptor
  • org.apache.poi.hwpf.model.TextPiece
    • 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.