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

Example 16 with AutoDetectParser

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

the class TikaCLI method configure.

private void configure(String configFilePath) throws Exception {
    this.configFilePath = configFilePath;
    config = new TikaConfig(new File(configFilePath));
    parser = new AutoDetectParser(config);
    if (digester != null) {
        parser = new DigestingParser(parser, digester);
    }
    detector = config.getDetector();
    context.set(Parser.class, parser);
}

Example 17 with AutoDetectParser

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

the class DigestingAutoDetectParserFactory method getParser.

@Override
public Parser getParser(TikaConfig config) {
    Parser p = new AutoDetectParser(config);
    if (digester == null) {
        return p;
    }
    DigestingParser d = new DigestingParser(p, digester);
    return d;
}

Example 18 with AutoDetectParser

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

the class SXSLFExtractorTest method testMacrosInPptm.

@Test
public void testMacrosInPptm() throws Exception {
    Metadata parsedBy = new Metadata();
    parsedBy.add("X-Parsed-By", "org.apache.tika.parser.microsoft.ooxml.xslf.XSLFEventBasedPowerPointExtractor");
    List<Metadata> metadataList = getRecursiveMetadata("testPPT_macros.pptm", parseContext);
    //test default is "don't extract macros"
    for (Metadata metadata : metadataList) {
        if (metadata.get(Metadata.CONTENT_TYPE).equals("text/x-vbasic")) {
            fail("Shouldn't have extracted macros as default");
        }
    }
    assertContainsAtLeast(parsedBy, metadataList);
    //now test that they are extracted
    ParseContext context = new ParseContext();
    OfficeParserConfig officeParserConfig = new OfficeParserConfig();
    officeParserConfig.setExtractMacros(true);
    officeParserConfig.setUseSAXPptxExtractor(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());
    metadataList = getRecursiveMetadata("testPPT_macros.pptm", context);
    assertContainsAtLeast(minExpected, metadataList);
    assertContainsAtLeast(parsedBy, metadataList);
    //test configuring via config file
    TikaConfig tikaConfig = new TikaConfig(this.getClass().getResourceAsStream("tika-config-sax-macros.xml"));
    AutoDetectParser parser = new AutoDetectParser(tikaConfig);
    metadataList = getRecursiveMetadata("testPPT_macros.pptm", parser);
    assertContainsAtLeast(minExpected, metadataList);
    assertContainsAtLeast(parsedBy, metadataList);
}

Example 19 with AutoDetectParser

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

the class SXSLFExtractorTest method testPowerPoint.

/**
     * We have a number of different powerpoint files,
     * such as presentation, macro-enabled etc
     */
@Test
public void testPowerPoint() throws Exception {
    String[] extensions = new String[] { "pptx", "pptm", "ppsm", "ppsx", "potm" };
    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];
        String filename = "testPPT." + extension;
        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        ContentHandler handler = new BodyContentHandler();
        try (InputStream input = getResourceAsStream("/test-documents/" + filename)) {
            parser.parse(input, handler, metadata, parseContext);
            assertEquals("Mime-type checking for " + filename, mimeTypes[i], metadata.get(Metadata.CONTENT_TYPE));
            assertEquals("Attachment Test", metadata.get(TikaCoreProperties.TITLE));
            assertEquals("Rajiv", metadata.get(TikaCoreProperties.CREATOR));
            assertEquals("Rajiv", metadata.get(Metadata.AUTHOR));
            String content = handler.toString();
            // Theme files don't have the text in them
            if (extension.equals("thmx")) {
                assertEquals("", content);
            } else {
                assertTrue("Text missing for " + filename + "\n" + content, content.contains("Attachment Test"));
                assertTrue("Text missing for " + filename + "\n" + content, content.contains("This is a test file data with the same content"));
                assertTrue("Text missing for " + filename + "\n" + content, content.contains("content parsing"));
                assertTrue("Text missing for " + filename + "\n" + content, content.contains("Different words to test against"));
                assertTrue("Text missing for " + filename + "\n" + content, content.contains("Mystery"));
            }
        }
    }
}

Example 20 with AutoDetectParser

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

the class SXSLFExtractorTest method testUnsupportedPowerPoint.

/**
     * For the PowerPoint formats we don't currently support, ensure that
     * we don't break either
     */
@Test
public void testUnsupportedPowerPoint() throws Exception {
    String[] extensions = new String[] { "xps", "thmx" };
    String[] mimeTypes = new String[] { "application/vnd.ms-xpsdocument", // Is this right?
    "application/vnd.openxmlformats-officedocument" };
    for (int i = 0; i < extensions.length; i++) {
        String extension = extensions[i];
        String filename = "testPPT." + extension;
        Parser parser = new AutoDetectParser();
        Metadata metadata = new Metadata();
        metadata.set(Metadata.RESOURCE_NAME_KEY, filename);
        ContentHandler handler = new BodyContentHandler();
        try (InputStream input = getResourceAsStream("/test-documents/" + filename)) {
            parser.parse(input, handler, metadata, parseContext);
            // Should get the metadata
            assertEquals("Mime-type checking for " + filename, mimeTypes[i], metadata.get(Metadata.CONTENT_TYPE));
        // But that's about it
        }
    }
}