Examples with POITextExtractor org.apache.poi.POITextExtractor used on opensource projects

Example 11 with POITextExtractor

use of org.apache.poi.POITextExtractor in project poi by apache.

the class OLE2ExtractorFactory method getEmbededDocsTextExtractors.

/**
     * 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 POITextExtractor[] getEmbededDocsTextExtractors(POIOLE2TextExtractor ext) throws IOException {
    // All the embedded directories we spotted
    List<Entry> dirs = new ArrayList<Entry>();
    // For anything else not directly held in as a POIFS directory
    List<InputStream> nonPOIFS = new ArrayList<InputStream>();
    // 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 ExcelExtractor) {
        // These are in MBD... under the root
        Iterator<Entry> it = root.getEntries();
        while (it.hasNext()) {
            Entry entry = it.next();
            if (entry.getName().startsWith("MBD")) {
                dirs.add(entry);
            }
        }
    } else {
        // Ask Scratchpad, or fail trying
        Class<?> cls = getScratchpadClass();
        try {
            Method m = cls.getDeclaredMethod("identifyEmbeddedResources", POIOLE2TextExtractor.class, List.class, List.class);
            m.invoke(null, ext, dirs, nonPOIFS);
        } catch (Exception e) {
            throw new IllegalArgumentException("Error checking for Scratchpad embedded resources", e);
        }
    }
    // Create the extractors
    if (dirs.size() == 0 && nonPOIFS.size() == 0) {
        return new POITextExtractor[0];
    }
    ArrayList<POITextExtractor> e = new ArrayList<POITextExtractor>();
    for (Entry dir : dirs) {
        e.add(createExtractor((DirectoryNode) dir));
    }
    for (InputStream nonPOIF : nonPOIFS) {
        try {
            e.add(createExtractor(nonPOIF));
        } catch (IllegalArgumentException ie) {
            // Ignore, just means it didn't contain
            //  a format we support as yet
            LOGGER.log(POILogger.WARN, ie);
        } catch (Exception xe) {
            // Ignore, invalid format
            LOGGER.log(POILogger.WARN, xe);
        }
    }
    return e.toArray(new POITextExtractor[e.size()]);
}

Example 12 with POITextExtractor

use of org.apache.poi.POITextExtractor in project poi by apache.

the class AbstractFileHandler method handleExtractingAsStream.

private void handleExtractingAsStream(File file) throws IOException, OpenXML4JException, XmlException {
    InputStream stream = new FileInputStream(file);
    try {
        POITextExtractor streamExtractor = ExtractorFactory.createExtractor(stream);
        try {
            assertNotNull(streamExtractor);
            assertNotNull(streamExtractor.getText());
        } finally {
            streamExtractor.close();
        }
    } finally {
        stream.close();
    }
}

Example 13 with POITextExtractor

use of org.apache.poi.POITextExtractor in project poi by apache.

the class TestExtractorFactory method testPreferEventBased.

@Test
public void testPreferEventBased() throws Exception {
    assertFalse(ExtractorFactory.getPreferEventExtractor());
    assertFalse(ExtractorFactory.getThreadPrefersEventExtractors());
    assertNull(ExtractorFactory.getAllThreadsPreferEventExtractors());
    ExtractorFactory.setThreadPrefersEventExtractors(true);
    assertTrue(ExtractorFactory.getPreferEventExtractor());
    assertTrue(ExtractorFactory.getThreadPrefersEventExtractors());
    assertNull(ExtractorFactory.getAllThreadsPreferEventExtractors());
    ExtractorFactory.setAllThreadsPreferEventExtractors(false);
    assertFalse(ExtractorFactory.getPreferEventExtractor());
    assertTrue(ExtractorFactory.getThreadPrefersEventExtractors());
    assertEquals(Boolean.FALSE, ExtractorFactory.getAllThreadsPreferEventExtractors());
    ExtractorFactory.setAllThreadsPreferEventExtractors(null);
    assertTrue(ExtractorFactory.getPreferEventExtractor());
    assertTrue(ExtractorFactory.getThreadPrefersEventExtractors());
    assertNull(ExtractorFactory.getAllThreadsPreferEventExtractors());
    // Check we get the right extractors now
    POITextExtractor extractor = ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(xls)));
    assertTrue(extractor instanceof EventBasedExcelExtractor);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(xls)));
    assertTrue(extractor.getText().length() > 200);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(OPCPackage.open(xlsx.toString(), PackageAccess.READ));
    assertTrue(extractor instanceof XSSFEventBasedExcelExtractor);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(OPCPackage.open(xlsx.toString(), PackageAccess.READ));
    assertTrue(extractor.getText().length() > 200);
    extractor.close();
    // Put back to normal
    ExtractorFactory.setThreadPrefersEventExtractors(false);
    assertFalse(ExtractorFactory.getPreferEventExtractor());
    assertFalse(ExtractorFactory.getThreadPrefersEventExtractors());
    assertNull(ExtractorFactory.getAllThreadsPreferEventExtractors());
    // And back
    extractor = ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(xls)));
    assertTrue(extractor instanceof ExcelExtractor);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(new POIFSFileSystem(new FileInputStream(xls)));
    assertTrue(extractor.getText().length() > 200);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(OPCPackage.open(xlsx.toString(), PackageAccess.READ));
    assertTrue(extractor instanceof XSSFExcelExtractor);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(OPCPackage.open(xlsx.toString()));
    assertTrue(extractor.getText().length() > 200);
    extractor.close();
}

Example 14 with POITextExtractor

use of org.apache.poi.POITextExtractor in project poi by apache.

the class TestExtractorFactory method test45565.

// This bug is currently open. This test will fail with "expected error not thrown" when the bug has been fixed.
// When this happens, change this from @Test(expected=...) to @Test
// bug 45565: text within TextBoxes is extracted by ExcelExtractor and WordExtractor
@Test(expected = AssertionError.class)
public void test45565() throws Exception {
    POITextExtractor extractor = ExtractorFactory.createExtractor(HSSFTestDataSamples.getSampleFile("45565.xls"));
    try {
        String text = extractor.getText();
        assertContains(text, "testdoc");
        assertContains(text, "test phrase");
    } finally {
        extractor.close();
    }
}

Example 15 with POITextExtractor

use of org.apache.poi.POITextExtractor in project poi by apache.

the class TestExtractorFactory method testFile.

@Test
public void testFile() throws Exception {
    // Excel
    POITextExtractor xlsExtractor = ExtractorFactory.createExtractor(xls);
    assertNotNull("Had empty extractor for " + xls, xlsExtractor);
    assertTrue("Expected instanceof ExcelExtractor, but had: " + xlsExtractor.getClass(), xlsExtractor instanceof ExcelExtractor);
    assertTrue(xlsExtractor.getText().length() > 200);
    xlsExtractor.close();
    POITextExtractor extractor = ExtractorFactory.createExtractor(xlsx);
    assertTrue(extractor.getClass().getName(), extractor instanceof XSSFExcelExtractor);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(xlsx);
    assertTrue(extractor.getText().length() > 200);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(xltx);
    assertTrue(extractor.getClass().getName(), extractor instanceof XSSFExcelExtractor);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(xlsb);
    assertContains(extractor.getText(), "test");
    extractor.close();
    extractor = ExtractorFactory.createExtractor(xltx);
    assertContains(extractor.getText(), "test");
    extractor.close();
    // TODO Support OOXML-Strict, see bug #57699
    try {
        /*extractor =*/
        ExtractorFactory.createExtractor(xlsxStrict);
        fail("OOXML-Strict isn't yet supported");
    } catch (POIXMLException e) {
    // Expected, for now
    }
    //        extractor = ExtractorFactory.createExtractor(xlsxStrict);
    //        assertTrue(
    //                extractor
    //                instanceof XSSFExcelExtractor
    //        );
    //        extractor.close();
    //
    //        extractor = ExtractorFactory.createExtractor(xlsxStrict);
    //        assertTrue(
    //                extractor.getText().contains("test")
    //        );
    //        extractor.close();
    // Word
    extractor = ExtractorFactory.createExtractor(doc);
    assertTrue(extractor instanceof WordExtractor);
    assertTrue(extractor.getText().length() > 120);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(doc6);
    assertTrue(extractor instanceof Word6Extractor);
    assertTrue(extractor.getText().length() > 20);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(doc95);
    assertTrue(extractor instanceof Word6Extractor);
    assertTrue(extractor.getText().length() > 120);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(docx);
    assertTrue(extractor instanceof XWPFWordExtractor);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(docx);
    assertTrue(extractor.getText().length() > 120);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(dotx);
    assertTrue(extractor instanceof XWPFWordExtractor);
    extractor.close();
    extractor = ExtractorFactory.createExtractor(dotx);
    assertContains(extractor.getText(), "Test");
    extractor.close();
    // PowerPoint (PPT)
    extractor = ExtractorFactory.createExtractor(ppt);
    assertTrue(extractor instanceof PowerPointExtractor);
    assertTrue(extractor.getText().length() > 120);
    extractor.close();
    // PowerPoint (PPTX)
    extractor = ExtractorFactory.createExtractor(pptx);
    assertTrue(extractor instanceof XSLFPowerPointExtractor);
    assertTrue(extractor.getText().length() > 120);
    extractor.close();
    // Visio - binary
    extractor = ExtractorFactory.createExtractor(vsd);
    assertTrue(extractor instanceof VisioTextExtractor);
    assertTrue(extractor.getText().length() > 50);
    extractor.close();
    // Visio - vsdx
    extractor = ExtractorFactory.createExtractor(vsdx);
    assertTrue(extractor instanceof XDGFVisioExtractor);
    assertTrue(extractor.getText().length() > 20);
    extractor.close();
    // Publisher
    extractor = ExtractorFactory.createExtractor(pub);
    assertTrue(extractor instanceof PublisherTextExtractor);
    assertTrue(extractor.getText().length() > 50);
    extractor.close();
    // Outlook msg
    extractor = ExtractorFactory.createExtractor(msg);
    assertTrue(extractor instanceof OutlookTextExtactor);
    assertTrue(extractor.getText().length() > 50);
    extractor.close();
    // Text
    try {
        ExtractorFactory.createExtractor(txt);
        fail();
    } catch (IllegalArgumentException e) {
    // Good
    }
}