Java DefaultDetector类代码示例

import org.apache.tika.detect.DefaultDetector; //导入依赖的package包/类
private static String getFullText(final String filepath) throws IOException, SAXException, TikaException {
    StringWriter writer = new StringWriter();
    
    final TikaInputStream inputStream =  TikaInputStream.get(new File(filepath));
    try {
        final Detector detector = new DefaultDetector();
        final Parser parser = new AutoDetectParser(detector);

        final Metadata metadata = new Metadata();
        final ParseContext parseContext = new ParseContext();
        parseContext.set(Parser.class, parser);

        
        ContentHandler contentHandler = new BodyContentHandler(writer);
        parser.parse(inputStream, contentHandler, metadata, parseContext);
    }
    finally {
        inputStream.close();
    }
    
    return writer.toString();
}
 

import org.apache.tika.detect.DefaultDetector; //导入依赖的package包/类
/**
 * Injects the TikaConfig to use
 * 
 * @param tikaConfig The Tika Config to use 
 */
public void setTikaConfig(TikaConfig tikaConfig)
{
    this.config = tikaConfig;
    
    // Setup the detector and parser
    detector = new DefaultDetector(config.getMimeRepository());
    parser = new AutoDetectParser(detector);
}
 

import org.apache.tika.detect.DefaultDetector; //导入依赖的package包/类
public String getMimeType() throws IOException
{
	TikaInputStream tikaIS = null;
	try
	{
		tikaIS = TikaInputStream.get(file);

		return new DefaultDetector(MimeTypes.getDefaultMimeTypes()).detect(tikaIS, new Metadata()).toString();
	} finally
	{
		if (tikaIS != null)
		{
			tikaIS.close();
		}
	}
}
 

import org.apache.tika.detect.DefaultDetector; //导入依赖的package包/类
@PostConstruct
public void initialise() {
    detector = new DefaultDetector();
    defaultDir = configurationService.getHome()+File.separator+"resources";

    log.debug("FileSystem Content Reader started (default directory: {})",defaultDir);

}
 

import org.apache.tika.detect.DefaultDetector; //导入依赖的package包/类
public MimeTypeUtils(InputStream mimeIs, boolean magic) {
	try {
		this.mimeTypes = MimeTypesFactory.create(mimeIs);
		this.mimeMagic = magic;
		this.tika = new Tika(new DefaultDetector(this.mimeTypes));
	}catch (Exception e) {
		LOG.log(Level.SEVERE, "Failed to load MimeType Registry : " + e.getMessage(), e);
	}
}
 

import org.apache.tika.detect.DefaultDetector; //导入依赖的package包/类
protected void doGet(HttpServletRequest request, HttpServletResponse response)
		throws ServletException, IOException {

	HttpSession session = request.getSession();

	// Pulls the candidateID of the candidate to retrieve photo of
	int candidateID = (int) session.getAttribute("candidateID");

	// Creates EntityManager to query database
	EntityManager em = EMFUtil.getEMFactory().createEntityManager();

	// Retrieves user from database based on userID
	Candidates candidate = em.find(Candidates.class, candidateID);

	// Retrieves resume from candidate's profile.
	byte[] pictureBlob = candidate.getPhoto();

	// If photo exists
	if (pictureBlob != null) {

		// Uses APACHE Tika api to obtain MIMETYPE
		String mimeType = "";
		MimeTypes allTypes = MimeTypes.getDefaultMimeTypes();
		final Detector DETECTOR = new DefaultDetector(allTypes);
		MimeType extension = null;

		TikaInputStream tikaIS = null;
		try {
			tikaIS = TikaInputStream.get(pictureBlob);
			final Metadata metadata = new Metadata();
			mimeType = DETECTOR.detect(tikaIS, metadata).toString();
			extension = allTypes.forName(mimeType);
		} catch (Exception e) {
			e.printStackTrace();
			System.out.println("Error getting MIME type");
		}

		// Tells web-page to prepare and download a picture file
		response.setContentType(mimeType);
		response.setContentLength(pictureBlob.length);
		response.getOutputStream().write(pictureBlob);
		response.setHeader("Content-Disposition", "attachment;filename=" + candidateID + extension);
	}
}
 

import org.apache.tika.detect.DefaultDetector; //导入依赖的package包/类
public AbstractExtractor(Path warcPath) {
    this.warcPath = warcPath;
    this.detector = new DefaultDetector();
    this.tikaConfig = TikaConfig.getDefaultConfig();
    extractorStats = new ExtractorStats();
}
 

import org.apache.tika.detect.DefaultDetector; //导入依赖的package包/类
/**
 * We don't currently support the .xlsb file format 
 *  (an OOXML container with binary blobs), but we 
 *  shouldn't break on these files either (TIKA-826)  
 */
@Test
public void testExcelXLSB() throws Exception {
   Detector detector = new DefaultDetector();
   AutoDetectParser parser = new AutoDetectParser();
   
   InputStream input = ExcelParserTest.class.getResourceAsStream(
         "/test-documents/testEXCEL.xlsb");
   Metadata m = new Metadata();
   m.add(Metadata.RESOURCE_NAME_KEY, "excel.xlsb");
   
   // Should be detected correctly
   MediaType type = null;
   try {
      type = detector.detect(input, m);
      assertEquals("application/vnd.ms-excel.sheet.binary.macroenabled.12", type.toString());
   } finally {
      input.close();
   }
   
   // OfficeParser won't handle it
   assertEquals(false, (new OfficeParser()).getSupportedTypes(new ParseContext()).contains(type));
   
   // OOXMLParser won't handle it
   assertEquals(false, (new OOXMLParser()).getSupportedTypes(new ParseContext()).contains(type));
   
   // AutoDetectParser doesn't break on it
   input = ExcelParserTest.class.getResourceAsStream("/test-documents/testEXCEL.xlsb");

   try {
      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();
      assertEquals("", content);
   } finally {
      input.close();
   }
}
 

import org.apache.tika.detect.DefaultDetector; //导入依赖的package包/类
/**
 * We don't currently support the old Excel 95 .xls file format, 
 *  but we shouldn't break on these files either (TIKA-976)  
 */
@Test
public void testExcel95() throws Exception {
   Detector detector = new DefaultDetector();
   AutoDetectParser parser = new AutoDetectParser();
   
   InputStream input = ExcelParserTest.class.getResourceAsStream(
         "/test-documents/testEXCEL_95.xls");
   Metadata m = new Metadata();
   m.add(Metadata.RESOURCE_NAME_KEY, "excel_95.xls");
   
   // Should be detected correctly
   MediaType type = null;
   try {
      type = detector.detect(input, m);
      assertEquals("application/vnd.ms-excel", type.toString());
   } finally {
      input.close();
   }
   
   // OfficeParser will claim to handle it
   assertEquals(true, (new OfficeParser()).getSupportedTypes(new ParseContext()).contains(type));
   
   // OOXMLParser won't handle it
   assertEquals(false, (new OOXMLParser()).getSupportedTypes(new ParseContext()).contains(type));
   
   // AutoDetectParser doesn't break on it
   input = ExcelParserTest.class.getResourceAsStream("/test-documents/testEXCEL_95.xls");

   try {
      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();
      assertEquals("", content);
   } finally {
      input.close();
   }
}
 

import org.apache.tika.detect.DefaultDetector; //导入依赖的package包/类
AssetMimeHandler() {
    detector = new DefaultDetector();
}
 

import org.apache.tika.detect.DefaultDetector; //导入依赖的package包/类
/**
 * Constructor which initialises tika
 *
 * @throws IOException
 */
public TikaIdentification() throws IOException {
    tika = new Tika();
    detector = new DefaultDetector();
}