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

Example 46 with ParseContext

use of org.apache.tika.parser.ParseContext 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 47 with ParseContext

use of org.apache.tika.parser.ParseContext 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 48 with ParseContext

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

the class OOXMLParserTest method testNoFormat.

/**
     * TIKA-1044 - Handle word documents where parts of the
     * text have no formatting or styles applied to them
     */
@Test
public void testNoFormat() throws Exception {
    ContentHandler handler = new BodyContentHandler();
    Metadata metadata = new Metadata();
    try (InputStream stream = WordParserTest.class.getResourceAsStream("/test-documents/testWORD_no_format.docx")) {
        new OOXMLParser().parse(stream, handler, metadata, new ParseContext());
    }
    String content = handler.toString();
    assertContains("This is a piece of text that causes an exception", content);
}

Example 49 with ParseContext

use of org.apache.tika.parser.ParseContext 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));
    }
}

Example 50 with ParseContext

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

the class OOXMLParserTest method testPowerPointMetadataEarly.

/**
     * Test that the metadata is already extracted when the body is processed.
     * See TIKA-1109
     */
@Test
public void testPowerPointMetadataEarly() throws Exception {
    String[] extensions = new String[] { "pptx", "pptm", "ppsm", "ppsx", "potm" };
    final String[] mimeTypes = new String[] { "application/vnd.openxmlformats-officedocument.presentationml.presentation", "application/vnd.ms-powerpoint.presentation.macroenabled.12", "application/vnd.ms-powerpoint.slideshow.macroenabled.12", "application/vnd.openxmlformats-officedocument.presentationml.slideshow", "application/vnd.ms-powerpoint.template.macroenabled.12" };
    for (int i = 0; i < extensions.length; i++) {
        String extension = extensions[i];
        final String filename = "testPPT." + extension;
        Parser parser = new AutoDetectParser();
        final Metadata metadata = new Metadata();
        // Allow the value to be access from the inner class
        final int currentI = i;
        ContentHandler handler = new BodyContentHandler() {

            public void startDocument() {
                assertEquals("Mime-type checking for " + filename, mimeTypes[currentI], metadata.get(Metadata.CONTENT_TYPE));
                assertEquals("Attachment Test", metadata.get(TikaCoreProperties.TITLE));
                assertEquals("Rajiv", metadata.get(TikaCoreProperties.CREATOR));
                assertEquals("Rajiv", metadata.get(Metadata.AUTHOR));
            }
        };
        ParseContext context = new ParseContext();
        try (InputStream input = getTestDocument(filename)) {
            parser.parse(input, handler, metadata, context);
        }
    }
}