Java Code Examples for org.apache.tika.metadata.Metadata#add()

public static String getMimeType(byte[] data, String fileName) throws Throwable {
	TikaInputStream tikaStream = null;
	Metadata metadata = new Metadata();
	metadata.add(TikaMetadataKeys.RESOURCE_NAME_KEY, fileName);
	try {
		tikaStream = TikaInputStream.get(data, metadata);
		return detector.detect(tikaStream, metadata).toString();
	} catch (Throwable t) {
		throw t;
	} finally {
		if (tikaStream != null) {
			try {
				tikaStream.close();
			} catch (IOException e) {
			}
		}
	}
}
 

public static String getMimeType(File file) throws Throwable {
	TikaInputStream tikaStream = null;
	Metadata metadata = new Metadata();
	metadata.add(TikaMetadataKeys.RESOURCE_NAME_KEY, file.getName());
	try {
		tikaStream = TikaInputStream.get(file, metadata);
		return detector.detect(tikaStream, metadata).toString();
	} catch (Throwable t) {
		throw t;
	} finally {
		if (tikaStream != null) {
			try {
				tikaStream.close();
			} catch (IOException e) {
			}
		}
	}
}
 

/**
 * Finds media type (through Apache Tika library), based on filename and magic numbers.
 * @throws IOException
 */
public static MediaType findMediaType(InputStream is, String fileName) throws IOException {
    BufferedInputStream bis = new BufferedInputStream(is);
    try {
        AutoDetectParser parser = new AutoDetectParser();
        Detector detector = parser.getDetector();
        Metadata md = new Metadata();
        md.add(Metadata.RESOURCE_NAME_KEY, fileName);
        MediaType mediaType = detector.detect(bis, md);
        return mediaType;
    } finally {
        try {
            bis.close();
        } catch (IOException e) {
            ;
        }
    }
}
 

private void init(String inName, String inExt, InputStream is) {
	if (Strings.isEmpty(inExt)) {
		int idx = inName.lastIndexOf('.');
		name = idx < 0 ? inName : inName.substring(0, idx);
		ext = getFileExt(inName);
	} else {
		name = inName;
		ext = inExt.toLowerCase(Locale.ROOT);
	}
	Metadata md = new Metadata();
	md.add(RESOURCE_NAME_KEY, String.format(FILE_NAME_FMT, name, ext));
	try {
		mime = tika.getDetector().detect(is == null ? null : TikaInputStream.get(is), md);
	} catch (Throwable e) {
		mime = null;
		log.error("Unexpected exception while detecting mime type", e);
	}
}
 

public static String detectContentType(String uri) throws FileNotFoundException, IOException, TikaException {
	final Detector detector = config.getDetector();
	final TikaInputStream inputStream = createInputStream(uri);
	final Metadata metadata = new Metadata();

	// Set the file name. This provides some level of type-hinting.
	metadata.add(TikaMetadataKeys.RESOURCE_NAME_KEY, new File(uri).getName());

	// Detect the content type.
	String contentType = detector.detect(inputStream, metadata).toString();

	inputStream.close();

	// Return the default content-type if undetermined.
	if (contentType == null || contentType.isEmpty()) {
		return MediaType.OCTET_STREAM.toString();
	}

	return contentType;
}
 

public static boolean isSupported(File file) throws FileNotFoundException, IOException
{
	FileInputStream fis = fileToInputStream(file);
	BufferedInputStream bif = new BufferedInputStream(fis);
	Metadata metadata = new Metadata();
	metadata.add(Metadata.RESOURCE_NAME_KEY, file.getName());
	boolean supported = isSupported(bif, metadata);
	bif.close();
	fis.close();
	return supported;
	
}
 

/**
 * 
 * @param file
 * @return Null if the file is not supported
 * @throws Exception 
 */
public static FileContent extractText(File file) throws Exception
{
	FileInputStream fis = fileToInputStream(file);
	BufferedInputStream bif = new BufferedInputStream(fis);
	Metadata metadata = new Metadata();
	metadata.add(Metadata.RESOURCE_NAME_KEY, file.getName());
	FileContent fileContent = extractText(bif, metadata);
	bif.close();
	fis.close();
	return fileContent;
}
 

static Metadata getMetadata() {
  Metadata m = new Metadata();
  m.add("Author", "BeamTikaUser");
  m.add("Author", "BeamTikaUser2");
  m.add("Date", "2017-09-01");
  return m;
}
 

private Metadata createMetadata(String fileName, String contentType) {
    Metadata metadata = new Metadata();
    if(fileName != null) {
        metadata.add(Metadata.RESOURCE_NAME_KEY, fileName);
    }
    if(contentType != null) {
        metadata.add(Metadata.CONTENT_TYPE, contentType);
    }
    return metadata;
}
 

/**
 * Test method for {@link crawlercommons.fetcher.FetchedResult#report()}.
 * This does not actually test anything but simply allows us to see what a
 * generated report would look like.
 * @throws UnsupportedEncodingException 
 */
@Test
public void testPrintReport() throws UnsupportedEncodingException {
    Metadata headerMetadata = new Metadata();
    headerMetadata.add(Metadata.CONTENT_DISPOSITION, "This is content disposition");
    headerMetadata.add(Metadata.CONTENT_ENCODING, "This is the encoding");
    headerMetadata.add(Metadata.CONTENT_LANGUAGE, "This is some language");
    headerMetadata.add(Metadata.CONTENT_LENGTH, "This is the length");

    Payload load = new Payload();
    load.put("Item 1", 1234);
    load.put("Item 2", 5678);
    load.put("Item 3", 1357);
    load.put("Item 4", 2468);

    FetchedResult result = new FetchedResult
    // (, , , headers, content, contentType, responseRate, payload,
    // newBaseUrl, numRedirects, hostAddress, statusCode, reasonPhrase)
    (
                    "http://en.wikipedia.org/wiki/Glasgow", // baseUrl
                    "http://en.wikipedia.org/wiki/Glasgow", // redirectedUrl
                    System.currentTimeMillis(), // fetchTime
                    headerMetadata, new String("Glasgow (/ˈɡlɑːzɡoʊ, ˈɡlæz-/;[4] Scots: Glesca; Scottish Gaelic: Glaschu) "
                                    + "is the largest city in Scotland, and the third largest in the United Kingdom.").getBytes("UTF-8"), "ScotsText", 2014, load, "http://en.wikipedia.org/wiki/Glasgow",
                    0, "wikipedia.org", 200, "");
    LOG.error(result.report());
}
 

public static List<List<String>> getRows(InputStream rawContent, String encoding, long limit) {
  SimpleValuesContentHandler valuesContentHandler = new SimpleValuesContentHandler(-1, limit);

  HtmlParser htmlParser = new HtmlParser();
  Metadata metadata = new Metadata();
  metadata.add(Metadata.CONTENT_ENCODING, encoding);
  try {
    htmlParser.parse(rawContent, valuesContentHandler, metadata, new ParseContext());
  } catch (Exception e) {
    LOGGER.debug("Failed to parse the excel html format document.", e);
  }

  return valuesContentHandler.getValues();
}
 

private static void fillMetadata(Metadata metadata, String contentType, String uri) {

		// Set the file name.
		if (uri != null) {
			metadata.set(TikaMetadataKeys.RESOURCE_NAME_KEY, new File(uri).getName());
		}

		// Normalise the content-type.
		contentType = normalizeContentType(contentType);

		// Set the content-type.
		if (contentType != null) {
			metadata.add(HttpHeaders.CONTENT_TYPE, contentType);
		}
	}
 

public static String detectContentTypeAndCharset(String uri) throws FileNotFoundException, IOException, TikaException {
	final Detector detector = config.getDetector();
	final TikaInputStream inputStream = createInputStream(uri);
	final Metadata metadata = new Metadata();

	// Set the file name. This provides some level of type-hinting.
	metadata.add(TikaMetadataKeys.RESOURCE_NAME_KEY, new File(uri).getName());

	// Detect the content type.
	String contentType = detector.detect(inputStream, metadata).toString();

	// Use metadata to provide type-hinting to the AutoDetectReader.
	fillMetadata(metadata, contentType, uri);

	// Detect the character set.
	final AutoDetectReader reader = new AutoDetectReader(inputStream, metadata);
	String charset = reader.getCharset().toString();

	inputStream.close();

	// Return the default content-type if undetermined.
	if (contentType == null || contentType.isEmpty()) {
		return MediaType.OCTET_STREAM.toString();
	}

	// Append the charset if the content-type was determined.
	if (charset != null && !charset.isEmpty()) {
		return contentType + "; charset=" + charset;
	}

	return contentType;
}
 

private org.springframework.http.MediaType detect(final TikaInputStream stream, final String fileName) throws IOException {
    final Metadata metadata = new Metadata();
    metadata.add(RESOURCE_NAME_KEY, fileName);
    final MediaType mediaType = detector.detect(requireNonNull(stream), metadata);
    return toSpringMediaType(mediaType);
}