Examples with WordExtractor org.apache.poi.hwpf.extractor.WordExtractor used on opensource projects

Example 6 with WordExtractor

use of org.apache.poi.hwpf.extractor.WordExtractor in project poi by apache.

the class TestBugs method test51678And51524.

/**
     * Bug 51678 - Extracting text from Bug51524.zip is slow Bug 51524 -
     * PapBinTable constructor is slow
     */
@Test
public void test51678And51524() throws IOException {
    // TODO: refactor into something nicer!
    if (System.getProperty("poi.test.remote") != null) {
        String href = "http://domex.nps.edu/corp/files/govdocs1/007/007488.doc";
        HWPFDocument hwpfDocument = HWPFTestDataSamples.openRemoteFile(href);
        WordExtractor wordExtractor = new WordExtractor(hwpfDocument);
        try {
            wordExtractor.getText();
        } finally {
            wordExtractor.close();
        }
    }
}

Example 7 with WordExtractor

use of org.apache.poi.hwpf.extractor.WordExtractor in project poi by apache.

the class TestBugs method getText.

private String getText(String samplefile) throws IOException {
    HWPFDocument doc = HWPFTestDataSamples.openSampleFile(samplefile);
    WordExtractor extractor = new WordExtractor(doc);
    try {
        return extractor.getText();
    } finally {
        extractor.close();
        doc.close();
    }
}

Example 8 with WordExtractor

use of org.apache.poi.hwpf.extractor.WordExtractor in project poi by apache.

the class TestBugs method test44431.

/**
     * Bug 44331 - HWPFDocument.write destroys fields
     */
@SuppressWarnings("deprecation")
@Test
public void test44431() throws IOException {
    HWPFDocument doc1 = HWPFTestDataSamples.openSampleFile("Bug44431.doc");
    WordExtractor extractor1 = new WordExtractor(doc1);
    try {
        HWPFDocument doc2 = HWPFTestDataSamples.writeOutAndReadBack(doc1);
        WordExtractor extractor2 = new WordExtractor(doc2);
        try {
            assertEqualsIgnoreNewline(extractor1.getFooterText(), extractor2.getFooterText());
            assertEqualsIgnoreNewline(extractor1.getHeaderText(), extractor2.getHeaderText());
            assertEqualsIgnoreNewline(Arrays.toString(extractor1.getParagraphText()), Arrays.toString(extractor2.getParagraphText()));
            assertEqualsIgnoreNewline(extractor1.getText(), extractor2.getText());
        } finally {
            extractor2.close();
        }
    } finally {
        extractor1.close();
        doc1.close();
    }
}

Example 9 with WordExtractor

use of org.apache.poi.hwpf.extractor.WordExtractor in project poi by apache.

the class TestProblems method testProblemHeaderStories49936.

/**
     * Bug #49936 - Problems with reading the header out of the Header Stories
     */
@SuppressWarnings("deprecation")
@Test
public void testProblemHeaderStories49936() throws IOException {
    HWPFDocument doc = HWPFTestDataSamples.openSampleFile("HeaderFooterProblematic.doc");
    HeaderStories hs = new HeaderStories(doc);
    assertEquals("", hs.getFirstHeader());
    assertEquals("\r", hs.getEvenHeader());
    assertEquals("", hs.getOddHeader());
    assertEquals("", hs.getFirstFooter());
    assertEquals("", hs.getEvenFooter());
    assertEquals("", hs.getOddFooter());
    WordExtractor ext = new WordExtractor(doc);
    assertEquals("\n", ext.getHeaderText());
    assertEquals("", ext.getFooterText());
    ext.close();
    doc.close();
}

Example 10 with WordExtractor

use of org.apache.poi.hwpf.extractor.WordExtractor in project poi by apache.

the class OLE2ScratchpadExtractorFactory method identifyEmbeddedResources.

/**
     * Returns an array of text extractors, one for each of
     *  the embedded documents in the file (if there are any).
     * If there are no embedded documents, you'll get back an
     *  empty array. Otherwise, you'll get one open
     *  {@link POITextExtractor} for each embedded file.
     */
public static void identifyEmbeddedResources(POIOLE2TextExtractor ext, List<Entry> dirs, List<InputStream> nonPOIFS) throws IOException {
    // Find all the embedded directories
    DirectoryEntry root = ext.getRoot();
    if (root == null) {
        throw new IllegalStateException("The extractor didn't know which POIFS it came from!");
    }
    if (ext instanceof WordExtractor) {
        // These are in ObjectPool -> _... under the root
        try {
            DirectoryEntry op = (DirectoryEntry) root.getEntry("ObjectPool");
            Iterator<Entry> it = op.getEntries();
            while (it.hasNext()) {
                Entry entry = it.next();
                if (entry.getName().startsWith("_")) {
                    dirs.add(entry);
                }
            }
        } catch (FileNotFoundException e) {
        // ignored here
        }
    //} else if(ext instanceof PowerPointExtractor) {
    // Tricky, not stored directly in poifs
    // TODO
    } else if (ext instanceof OutlookTextExtactor) {
        // Stored in the Attachment blocks
        MAPIMessage msg = ((OutlookTextExtactor) ext).getMAPIMessage();
        for (AttachmentChunks attachment : msg.getAttachmentFiles()) {
            if (attachment.getAttachData() != null) {
                byte[] data = attachment.getAttachData().getValue();
                nonPOIFS.add(new ByteArrayInputStream(data));
            } else if (attachment.getAttachmentDirectory() != null) {
                dirs.add(attachment.getAttachmentDirectory().getDirectory());
            }
        }
    }
}