Java Tika.detect方法代码示例

import org.apache.tika.Tika; //导入方法依赖的package包/类
/**
 * Creates a new {@link RepositoryLocationChooser} that allows to specify a media or MIME type
 * for the given data source.
 *
 * @param source
 *            the data source
 * @param initialDestination
 *            the initial location (optional)
 */
public BinaryImportDestinationChooser(BinaryDataSource source, String initialDestination) {
	super(null, null, initialDestination, true, false, true, true, Colors.WHITE);

	// Use generic mime type as default and try to guess more specific.
	String type = "application/octet-stream";
	Tika tika = new Tika();
	try {
		type = tika.detect(source.getLocation());
	} catch (IOException e) {
		// ignore
	}

	JLabel mediaTypelabel = new ResourceLabel("repository_chooser.mime_type");
	mediaType = new JTextArea(type);

	GridBagConstraints c = new GridBagConstraints();
	c.insets = new Insets(ButtonDialog.GAP, 0, 0, ButtonDialog.GAP);
	c.gridwidth = GridBagConstraints.RELATIVE;
	add(mediaTypelabel, c);

	c.insets = new Insets(ButtonDialog.GAP, 0, 0, 0);
	c.gridwidth = GridBagConstraints.REMAINDER;
	c.fill = GridBagConstraints.HORIZONTAL;
	add(mediaType, c);
}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
/**
 * 利用 Tika 分析 Mime Type
 * 因为 Tika 要解析 File 、 URL 数据流，所以解析需要一定时间。不要用解析扩展名的方法，无法动态判断，不准。
 * <p>
 * Parses the given file and returns the extracted text content.
 *
 * @param file
 * @return
 */
public static String detect(File file) throws Exception {

    //文件不存在
    if (!file.exists()) {
        throw new Exception("exception ! " + file.getAbsoluteFile() + " not existes.");
    }
    Tika t = new Tika();
    return t.detect(file);

}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
/**
  * return the mime type of a file, dont check extension
  * @param barr
  * @return mime type of the file
  * @throws IOException 
  */
 public static String getMimeType(byte[] barr, String defaultValue) {
     
 	//String mt = getMimeType(new ByteArrayInputStream(barr), null);
 	//if(!StringUtil.isEmpty(mt,true)) return mt;
 	
 	PrintStream out = System.out;
     try {
     	Tika tika = new Tika();
     	return tika.detect(barr);
     } 
     catch(Throwable t) {
     	ExceptionUtil.rethrowIfNecessary(t);
return defaultValue;
     }
 }
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
public String getMimeType() {
    try {
        Tika tika = new Tika();
        return tika.detect(Paths.get(getFilePath()));
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
private String getMimeType(String filename) {
    Path fullPath = Paths.get(filename);
    String mimeType = null;
    try {
        mimeType = Files.probeContentType(fullPath);
    } catch (IOException e) {
        e.printStackTrace();
    }
    if (mimeType == null) {
        Tika tika = new Tika();
        mimeType = tika.detect(filename);
    }
    return mimeType;
}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
/**
 * Detects the {@link MimeType} from the bytes stream
 * @see http://tika.apache.org/1.4/detection.html
 * @param is
 * @param fileName
 * @param contentType
 * @return
 * @throws IOException
 */
public static MimeType from(final InputStream is,
							final String fileName,final String contentType) throws IOException {
	Metadata md = new Metadata();
	if (Strings.isNOTNullOrEmpty(fileName)) md.add(TikaMetadataKeys.RESOURCE_NAME_KEY ,fileName);
	if (Strings.isNOTNullOrEmpty(contentType)) md.add(HttpHeaders.CONTENT_TYPE,contentType);
	
	Tika tika = new Tika();
	String mimeTypeStr = tika.detect(is,fileName);
	
	return MimeType.forName(mimeTypeStr);
}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
private boolean ensurePNG(byte[] array) {
    Tika tika = new Tika();
    try {
        String found = tika.detect(new ByteArrayInputStream(array));
        return "image/png".equals(found);
    } catch (IOException e) {
        logger.error("Image file cannot be analyzed", e);
    }
    return false;
}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
private String getContentType(final File file) {

        try {
            final Tika tika = new Tika();
            return tika.detect(file);

        } catch (final IOException e) {
            return ContentType.DEFAULT_BINARY.toString();
        }
    }
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
public static String getImageType(byte[] inputByteArray) throws Exception
{
	Tika tika = new Tika();
	return tika.detect(inputByteArray);
}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
public static String getMimeType(InputStream s, String fileName) throws IOException {
    final Tika t = new Tika();
    return t.detect(s, fileName);
}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
public static String getMimeTypeWithByteBuffer(java.nio.ByteBuffer buffer) throws IOException {
    byte[] b = buffer.array();

    Tika tika = new Tika();
    return tika.detect(b);
}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
public String extractText(InputStream input, String url,
    List<Outlink> outLinksList) throws IOException {
  String resultText = "";
  ZipInputStream zin = new ZipInputStream(input);
  ZipEntry entry;

  while ((entry = zin.getNextEntry()) != null) {

    if (!entry.isDirectory()) {
      int size = (int) entry.getSize();
      byte[] b = new byte[size];
      for (int x = 0; x < size; x++) {
        int err = zin.read();
        if (err != -1) {
          b[x] = (byte) err;
        }
      }
      String newurl = url + "/";
      String fname = entry.getName();
      newurl += fname;
      URL aURL = new URL(newurl);
      String base = aURL.toString();
      int i = fname.lastIndexOf('.');
      if (i != -1) {
        // Trying to resolve the Mime-Type
        Tika tika = new Tika();
        String contentType = tika.detect(fname);
        try {
          Metadata metadata = new Metadata();
          metadata.set(Response.CONTENT_LENGTH,
              Long.toString(entry.getSize()));
          metadata.set(Response.CONTENT_TYPE, contentType);
          Content content = new Content(newurl, base, b, contentType,
              metadata, this.conf);
          Parse parse = new ParseUtil(this.conf).parse(content).get(
              content.getUrl());
          ParseData theParseData = parse.getData();
          Outlink[] theOutlinks = theParseData.getOutlinks();

          for (int count = 0; count < theOutlinks.length; count++) {
            outLinksList.add(new Outlink(theOutlinks[count].getToUrl(),
                theOutlinks[count].getAnchor()));
          }

          resultText += entry.getName() + " " + parse.getText() + " ";
        } catch (ParseException e) {
          if (LOG.isInfoEnabled()) {
            LOG.info("fetch okay, but can't parse " + fname + ", reason: "
                + e.getMessage());
          }
        }
      }
    }
  }

  return resultText;
}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
private PhylogeneticTree doProcess(Multimedia item) throws Exception {
	logger.debug("doProcess " + item);
	Resource resource = resourceService.findByResourceUri(item.getIdentifier());
	PhylogeneticTree phylogeneticTree = null;
	if(resource == null) {
		logger.debug("No Resource prexisting for " + item.getIdentifier());
		Tika tika = new Tika();
		try {
			String mimeType = tika.detect(new URL(item.getIdentifier()));
			logger.debug("Mime type is " + mimeType);
			phylogeneticTree = conversionService.convert(item, PhylogeneticTree.class);
			resource = new Resource();
			resource.setOrganisation(getSource());
			resource.setIdentifier(UUID.randomUUID().toString());
			resource.setUri(item.getIdentifier());
			resource.setResourceType(ResourceType.PHYLOGENETIC_TREE);
			resource.setTitle("Resource " + item.getIdentifier());
			if(mimeType.equals("application/phyloxml+xml")) {
				resource.getParameters().put("input.file.extension", "xml");
				resourceService.saveOrUpdate(resource);
			} else if(mimeType.equals("application/newick")) {
				resource.getParameters().put("input.file.extension", "nwk");
				resourceService.saveOrUpdate(resource);
			} else if(mimeType.equals("application/nexus")) {
				resource.getParameters().put("input.file.extension", "nex");
				resourceService.saveOrUpdate(resource);
			} else if(mimeType.equals("application/new-hampshire-extended")) {
				resource.getParameters().put("input.file.extension", "nhx");
				resourceService.saveOrUpdate(resource);
			} else {
				logger.debug("Returning null");
				return null;
			}
		} catch (Exception e) {
			ImageRetrievalException ire = new ImageRetrievalException(item.getIdentifier());
			ire.initCause(e);
			throw ire;
		}
	} else if(resource.getResourceType().equals(ResourceType.PHYLOGENETIC_TREE)) {
		logger.debug("Resource " + resource + " exists for " + item.getIdentifier());
		phylogeneticTree = conversionService.convert(item, PhylogeneticTree.class);
	} else {
		return null;
	}
	logger.debug("Processing " + phylogeneticTree);
	phylogeneticTree = processor.process(phylogeneticTree);
	logger.debug("Processing delegate returned " + phylogeneticTree);

	if(phylogeneticTree != null) {
		try {
			resourceService.harvestResource(resource.getId(), true);
		} catch(ResourceAlreadyBeingHarvestedException rabhe) {
			logger.warn("Tried to harvest " + item.getIdentifier() + " but it is already being harvested");
		}
	}

	return phylogeneticTree;
}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
private IdentificationKey doProcess(Multimedia item) throws Exception {
	logger.debug("doProcess " + item);
	Resource resource = resourceService.findByResourceUri(item.getIdentifier());
	IdentificationKey identificationKey = null;
	if(resource == null) {
		logger.debug("No Resource prexisting for " + item.getIdentifier());
		Tika tika = new Tika();
		try {
			String mimeType = tika.detect(new URL(item.getIdentifier()));
			logger.debug("Mime type is " + mimeType);
			if(mimeType.equals("application/sdd+xml")) {
				identificationKey = conversionService.convert(item, IdentificationKey.class);
				resource = new Resource();
				resource.setOrganisation(getSource());
				resource.setIdentifier(UUID.randomUUID().toString());
				resource.setUri(item.getIdentifier());
				resource.setResourceType(ResourceType.IDENTIFICATION_KEY);
				resource.setTitle("Resource " + item.getIdentifier());
				resourceService.saveOrUpdate(resource);
			} else {
				logger.debug("Returning null");
				return null;
			}
		} catch (Exception e) {
			throw new ImageRetrievalException(item.getIdentifier());
		}
	} else if(resource.getResourceType().equals(ResourceType.IDENTIFICATION_KEY)) {
		logger.debug("Resource " + resource + " exists for " + item.getIdentifier());
		identificationKey = conversionService.convert(item, IdentificationKey.class);
	} else {
		return null;
	}
	logger.debug("Processing " + identificationKey);
	identificationKey = processor.process(identificationKey);

	if(identificationKey != null) {
		try {
			resourceService.harvestResource(resource.getId(), true);
		} catch(ResourceAlreadyBeingHarvestedException rabhe) {
			logger.warn("Tried to harvest " + item.getIdentifier() + " but it is already being harvested");
		}
	}
	return identificationKey;
}
 

import org.apache.tika.Tika; //导入方法依赖的package包/类
/**
 * Main function.
 */
public static void main(String[] args) {

        try {
                // Tika tika = new Tika();
                // File xpsFile = new File("/home/foo/a/temp/xlsx.xlsx");
                // InputStream inputStream = new FileInputStream(xpsFile);
                // String FileName = xpsFile.getName();
                // Metadata metadata = new Metadata();
                // if (FileName != null && FileName.length() > 0)
                // metadata.add(Metadata.RESOURCE_NAME_KEY, FileName);
                // String MimeType = tika.detect(inputStream, metadata);

                // metadata.add(Metadata.CONTENT_TYPE, MimeType);
                // inputStream.close();
                // inputStream = new FileInputStream(xpsFile);
                // Reader reader = tika.parse(inputStream, metadata);
                // String content = IOUtils.toString(reader);

                // System.out.println(new AutoDetectParser().getParsers().keySet());
                // System.out.println("shit: " + tika.getParser() + " " + MimeType);
                // System.out.println(content);
                // inputStream.close();

                ClassLoader loader = Thread.currentThread().getContextClassLoader();
                TikaConfig config = new TikaConfig(new File("/home/foo/a/code/big_bang/tika-1.5/"
                                + "tika-core/src/main/resources/org/apache/tika/mime/tika-mimetypes.xml"));

                final AutoDetectParser autoDetectParser = new AutoDetectParser(config);

                final Detector detector = config.getDetector();
                final Tika tika = new Tika();


                File xpsFile = new File("/home/foo/a/temp/xlsx.xlsx");
                InputStream inputStream = new FileInputStream(xpsFile);
                String FileName = xpsFile.getName();
                Metadata metadata = new Metadata();
                if (FileName != null && FileName.length() > 0)
                        metadata.add(Metadata.RESOURCE_NAME_KEY, FileName);

                String MimeType = tika.detect(inputStream, metadata);
                // metadata.add(Metadata.CONTENT_TYPE, MimeType);
                // ContentHandler handler = new XHTMLContentHandler(System.out);

                // ContentHandler bch = new BodyContentHandler(System.out);
                // ContentHandler handler = new BodyContentHandler();
                // ContentHandler xhtml = new XHTMLContentHandler(handler,
                // metadata);

                StringWriter sw = new StringWriter();

                SAXTransformerFactory factory = (SAXTransformerFactory) SAXTransformerFactory.newInstance();
                TransformerHandler handler = factory.newTransformerHandler();
                handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "xml");
                handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "no");
                handler.setResult(new StreamResult(sw));
                BodyContentHandler bch = new BodyContentHandler(handler);
                handler.startDocument();
                inputStream.close();
                inputStream = new FileInputStream(xpsFile);
                autoDetectParser.parse(inputStream, bch, metadata);
                String x = sw.toString();
                System.out.println(x);

                // Document doc = Jsoup.parse(x);

                // Elements elements = doc.getElementsByTag("p");
                // for (Element element : elements) {
                //         System.out.println(element.text());
                // }

        } catch (Exception e) {
                e.printStackTrace();
        }
}