Package org.apache.poi.xwpf.usermodel

Examples of org.apache.poi.xwpf.usermodel.XWPFDocument

280
281
282
283
284
285
286
287
288
289
290
     * The output should not contain field codes, e.g. those specified in the
     * w:instrText tag (spec sec. 17.16.23)
     * @throws IOException
     */
    public void testNoFieldCodes() throws IOException {
        XWPFDocument doc = XWPFTestDataSamples.openSampleDocument("FieldCodes.docx");
        XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
        String text = extractor.getText();
        assertTrue(text.length() > 0);
        assertFalse(text.contains("AUTHOR"));
        assertFalse(text.contains("CREATEDATE"));
View Full Code Here
296
297
298
299
300
301
302
303
304
305
306
     * The output should contain the values of simple fields, those specified
     * with the fldSimple element (spec sec. 17.16.19)
     * @throws IOException
     */
    public void testFldSimpleContent() throws IOException {
        XWPFDocument doc = XWPFTestDataSamples.openSampleDocument("FldSimple.docx");
        XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
        String text = extractor.getText();
        assertTrue(text.length() > 0);
        assertTrue(text.contains("FldSimple.docx"));
       
View Full Code Here
310
311
312
313
314
315
316
317
318
319
320
    /**
     * Test for parsing document with drawings to prevent
     * NoClassDefFoundError for CTAnchor in XWPFRun
     */
    public void testDrawings() throws IOException {
        XWPFDocument doc = XWPFTestDataSamples.openSampleDocument("drawing.docx");
        XWPFWordExtractor extractor = new XWPFWordExtractor(doc);
        String text = extractor.getText();
        assertTrue(text.length() > 0);
       
        extractor.close();
View Full Code Here
323
324
325
326
327
328
329
330
331
332
333
    /**
     * Test for basic extraction of SDT content
     * @throws IOException
     */
    public void testSimpleControlContent() throws IOException {
        XWPFDocument doc = XWPFTestDataSamples.openSampleDocument("Bug54849.docx");
        String[] targs = new String[]{
                "header_rich_text",
                "rich_text",
                "rich_text_pre_table\nrich_text_cell1\t\t\t\n\t\t\t\n\t\t\t\n\nrich_text_post_table",
                "plain_text_no_newlines",
View Full Code Here
388
389
390
391
392
393
394
395
396
397
398
        ex.close();
    }

    /** No Header or Footer in document */
    public void testBug55733() throws Exception {
        XWPFDocument doc = XWPFTestDataSamples.openSampleDocument("55733.docx");
      XWPFWordExtractor extractor = new XWPFWordExtractor(doc);

        // Check it gives text without error
        extractor.getText();
        extractor.close();
View Full Code Here
29
30
31
32
33
34
35
36
37
38
39
    /**
     * Get text out of the simple file
     * @throws IOException
     */
    public void testFile() throws IOException {
        XWPFDocument doc = XWPFTestDataSamples.openSampleDocument("ExternalEntityInText.docx");
        XWPFWordExtractor extractor = new XWPFWordExtractor(doc);

        String text = extractor.getText();
       
        assertTrue(text.length() > 0);
View Full Code Here
52
53
54
55
56
57
58
  
  private XWPFDocument document;
  private boolean fetchHyperlinks = false;
 
  public XWPFWordExtractor(OPCPackage container) throws XmlException, OpenXML4JException, IOException {
    this(new XWPFDocument(container));
  }
View Full Code Here
58
59
60
61
62
63
64
65
66
67
68
        assertTrue("Unable to process: document is encrypted", d.verifyPassword("solrcell"));

        // Check we can read the word document in that
        InputStream dataStream = d.getDataStream(filesystem);
        OPCPackage opc = OPCPackage.open(dataStream);
        XWPFDocument doc = new XWPFDocument(opc);
        XWPFWordExtractor ex = new XWPFWordExtractor(doc);
        String text = ex.getText();
        assertNotNull(text);
        assertEquals("This is password protected Word document.", text.trim());
        ex.close();
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
        assertTrue("Unable to process: document is encrypted", d.verifyPassword("pass"));

        // Check we can read the word document in that
        InputStream dataStream = d.getDataStream(filesystem);
        OPCPackage opc = OPCPackage.open(dataStream);
        XWPFDocument doc = new XWPFDocument(opc);
        XWPFWordExtractor ex = new XWPFWordExtractor(doc);
        String text = ex.getText();
        assertNotNull(text);
        // I know ... a stupid typo, maybe next time ...
        assertEquals("The is a password protected document.", text.trim());
View Full Code Here
32
33
34
35
36
37
38
39
40
41
42
    /**
     * Get text out of the simple file
     * @throws IOException
     */
    public void testGetSimpleText() throws IOException {
        XWPFDocument doc = XWPFTestDataSamples.openSampleDocument("sample.docx");
        XWPFWordExtractor extractor = new XWPFWordExtractor(doc);

        String text = extractor.getText();
        assertTrue(text.length() > 0);

View Full Code Here
TOP

Related Classes of org.apache.poi.xwpf.usermodel.XWPFDocument

  • com.google.code.ftspc.lector.parsers.POI.XDocParser
  • org.apache.poi.openxml4j.opc.OPCPackage
  • org.apache.poi.openxml4j.opc.Package
  • org.apache.poi.openxml4j.opc.PackagePart
  • org.apache.poi.openxml4j.opc.PackagePartName
  • org.apache.poi.openxml4j.opc.PackageRelationship
  • org.apache.poi.openxml4j.opc.TargetMode
  • org.apache.poi.poifs.crypt.TestEncryptor
  • org.apache.poi.POIXMLDocumentPart
  • org.apache.poi.POIXMLRelation
    • 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.