Examples with AutoDetectParser org.apache.tika.parser.AutoDetectParser used on opensource projects

Example 21 with AutoDetectParser

use of org.apache.tika.parser.AutoDetectParser in project tika by apache.

the class SXWPFExtractorTest method testEncrypted.

@Test
public void testEncrypted() throws Exception {
    Map<String, String> tests = new HashMap<String, String>();
    tests.put("testWORD_protected_passtika.docx", "This is an encrypted Word 2007 File");
    Parser parser = new AutoDetectParser();
    Metadata m = new Metadata();
    PasswordProvider passwordProvider = new PasswordProvider() {

        @Override
        public String getPassword(Metadata metadata) {
            return "tika";
        }
    };
    OfficeParserConfig opc = new OfficeParserConfig();
    opc.setUseSAXDocxExtractor(true);
    ParseContext passwordContext = new ParseContext();
    passwordContext.set(org.apache.tika.parser.PasswordProvider.class, passwordProvider);
    passwordContext.set(OfficeParserConfig.class, opc);
    for (Map.Entry<String, String> e : tests.entrySet()) {
        assertContains(e.getValue(), getXML(e.getKey(), passwordContext).xml);
    }
    //now try with no password
    for (Map.Entry<String, String> e : tests.entrySet()) {
        boolean exc = false;
        try {
            getXML(e.getKey(), parseContext);
        } catch (EncryptedDocumentException ex) {
            exc = true;
        }
        assertTrue(exc);
    }
}

Example 22 with AutoDetectParser

use of org.apache.tika.parser.AutoDetectParser in project tika by apache.

the class OOXMLParserTest method testMasterText.

/**
     * TIKA-712 Master Slide Text from PPT and PPTX files
     * should be extracted too
     */
@Test
public void testMasterText() throws Exception {
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    try (InputStream stream = OOXMLParserTest.class.getResourceAsStream("/test-documents/testPPT_masterText.pptx")) {
        new AutoDetectParser().parse(stream, handler, metadata, new ParseContext());
    }
    String content = handler.toString();
    assertContains("Text that I added to the master slide", content);
}

Example 23 with AutoDetectParser

use of org.apache.tika.parser.AutoDetectParser in project tika by apache.

the class OOXMLParserTest method testMacrosInPptm.

@Test
public void testMacrosInPptm() throws Exception {
    //test default is "don't extract macros"
    for (Metadata metadata : getRecursiveMetadata("testPPT_macros.pptm")) {
        if (metadata.get(Metadata.CONTENT_TYPE).equals("text/x-vbasic")) {
            fail("Shouldn't have extracted macros as default");
        }
    }
    //now test that they were extracted
    ParseContext context = new ParseContext();
    OfficeParserConfig officeParserConfig = new OfficeParserConfig();
    officeParserConfig.setExtractMacros(true);
    context.set(OfficeParserConfig.class, officeParserConfig);
    Metadata minExpected = new Metadata();
    minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Embolden()");
    minExpected.add(RecursiveParserWrapper.TIKA_CONTENT.getName(), "Sub Italicize()");
    minExpected.add(Metadata.CONTENT_TYPE, "text/x-vbasic");
    minExpected.add(TikaCoreProperties.EMBEDDED_RESOURCE_TYPE, TikaCoreProperties.EmbeddedResourceType.MACRO.toString());
    assertContainsAtLeast(minExpected, getRecursiveMetadata("testPPT_macros.pptm", context));
    //test configuring via config file
    TikaConfig tikaConfig = new TikaConfig(this.getClass().getResourceAsStream("tika-config-dom-macros.xml"));
    AutoDetectParser parser = new AutoDetectParser(tikaConfig);
    assertContainsAtLeast(minExpected, getRecursiveMetadata("testPPT_macros.pptm", parser));
}

Example 24 with AutoDetectParser

use of org.apache.tika.parser.AutoDetectParser in project tika by apache.

the class OOXMLParserTest method testExcelXLSB.

@Test
public void testExcelXLSB() throws Exception {
    Detector detector = new DefaultDetector();
    AutoDetectParser parser = new AutoDetectParser();
    Metadata m = new Metadata();
    m.add(Metadata.RESOURCE_NAME_KEY, "excel.xlsb");
    // Should be detected correctly
    MediaType type;
    try (InputStream input = ExcelParserTest.class.getResourceAsStream("/test-documents/testEXCEL.xlsb")) {
        type = detector.detect(input, m);
        assertEquals("application/vnd.ms-excel.sheet.binary.macroenabled.12", type.toString());
    }
    // OfficeParser won't handle it
    assertEquals(false, (new OfficeParser()).getSupportedTypes(new ParseContext()).contains(type));
    // OOXMLParser will (soon) handle it
    assertTrue((new OOXMLParser()).getSupportedTypes(new ParseContext()).contains(type));
    // AutoDetectParser doesn't break on it
    try (InputStream input = ExcelParserTest.class.getResourceAsStream("/test-documents/testEXCEL.xlsb")) {
        ContentHandler handler = new BodyContentHandler(-1);
        ParseContext context = new ParseContext();
        context.set(Locale.class, Locale.US);
        parser.parse(input, handler, m, context);
        String content = handler.toString();
        assertContains("This is an example spreadsheet", content);
    }
}

Example 25 with AutoDetectParser

use of org.apache.tika.parser.AutoDetectParser in project tika by apache.

the class OOXMLParserTest method testProtectedExcelSheets.

/**
     * Documents with some sheets are protected, but not all.
     * See TIKA-364.
     */
@Test
public void testProtectedExcelSheets() throws Exception {
    Parser parser = new AutoDetectParser();
    Metadata metadata = new Metadata();
    ContentHandler handler = new BodyContentHandler();
    ParseContext context = new ParseContext();
    try (InputStream input = OOXMLParserTest.class.getResourceAsStream("/test-documents/protectedSheets.xlsx")) {
        parser.parse(input, handler, metadata, context);
        assertEquals("application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", metadata.get(Metadata.CONTENT_TYPE));
        assertEquals("true", metadata.get(TikaMetadataKeys.PROTECTED));
    }
}