Java Metadata.add方法代碼示例

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
/**
 * 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) {
            ;
        }
    }
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
/**
 * Converts a .docx document into HTML markup. This code
 * is based on <a href="http://stackoverflow.com/a/9053258/313554">this StackOverflow</a> answer.
 *
 * @param wordDocument  The converted .docx document.
 * @return
 */
public ConvertedDocumentDTO convertWordDocumentIntoHtml(MultipartFile wordDocument) {
    LOGGER.info("Converting word document: {} into HTML", wordDocument.getOriginalFilename());
    try {
        InputStream input = wordDocument.getInputStream();
        Parser parser = new OOXMLParser();

        StringWriter sw = new StringWriter();
        SAXTransformerFactory factory = (SAXTransformerFactory)
                SAXTransformerFactory.newInstance();
        TransformerHandler handler = factory.newTransformerHandler();
        handler.getTransformer().setOutputProperty(OutputKeys.ENCODING, "utf-8");
        handler.getTransformer().setOutputProperty(OutputKeys.METHOD, "html");
        handler.getTransformer().setOutputProperty(OutputKeys.INDENT, "yes");
        handler.setResult(new StreamResult(sw));

        Metadata metadata = new Metadata();
        metadata.add(Metadata.CONTENT_TYPE, "text/html;charset=utf-8");
        parser.parse(input, handler, metadata, new ParseContext());
        return new ConvertedDocumentDTO(wordDocument.getOriginalFilename(), sw.toString());
    }
    catch (IOException | SAXException | TransformerException | TikaException ex) {
        LOGGER.error("Conversion failed because an exception was thrown", ex);
        throw new DocumentConversionException(ex.getMessage(), ex);
    }
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
public static String getMimeType(byte[] data, String fileName) throws Throwable {
	TikaInputStream tikaStream = null;
	Metadata metadata = new Metadata();
	metadata.add(Metadata.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) {
			}
		}
	}
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
private void init(String _name, String _ext, InputStream is) {
	if (Strings.isEmpty(_ext)) {
		int idx = _name.lastIndexOf('.');
		name = idx < 0 ? _name : _name.substring(0, idx);
		ext = getFileExt(_name);
	} else {
		name = _name;
		ext = _ext.toLowerCase();
	}
	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);
	}
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
public String parse(ImportDocument doc) throws IOException, SAXException, TikaException {
	String data = doc.getData();
	InputStream is = new ByteArrayInputStream(data.getBytes("UTF-8"));
	try {
		ContentHandler handler = new ToTextContentHandler();
		Metadata metadata = new Metadata();
		
		metadata.add(Metadata.RESOURCE_NAME_KEY, doc.getUrl().toExternalForm());
		metadata.add(Metadata.CONTENT_ENCODING, new InputStreamReader(is).getEncoding());
		
		parser.parse(is, handler, metadata); //, new ParseContext()
		handler.endDocument();
		
		return handler.toString();
	} finally {
		is.close();
	}
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
@Override
protected void process(URL parseUrl, ObjectOutputStream out)
		throws IOException, SAXException, TikaException {
	URL url = URLTools.getAuthenticatedUrl(parseUrl);
	URLConnection conn = url.openConnection();
	InputStream in = conn.getInputStream();
	InputStreamReader ir = new InputStreamReader(in);
	try {
		AutoDetectParser parser = new AutoDetectParser();
		ContentHandler handler = new StreamingToRDFContentHandler(writer, out);

		Metadata metadata = new Metadata();
		metadata.add(Metadata.RESOURCE_NAME_KEY, url.toExternalForm());
		metadata.add(Metadata.CONTENT_ENCODING, ir.getEncoding());

		parser.parse(in, handler, metadata, new ParseContext());
	} catch(Exception e) {
		throw new TikaException(e.getMessage(), e);
	} finally {
		in.close();
		out.close();
		ir.close();
	}
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
@Override
public void prepareMetadataWithConfigParams(Metadata metadata)
{
    if (metadata == null)
    {
        return;
    }
    boolean shouldParseShapes = getBooleanProperty(PARSE_SHAPE_PROP_STRING, TIKA_PARSER_PARSE_SHAPES_DEFAULT_VALUE);
    metadata.add(TikaMetadataKeys.TIKA_PARSER_PARSE_SHAPES_KEY, Boolean.toString(shouldParseShapes));
    
    if (logger.isDebugEnabled())
    {
        logger.debug("Tika metadata options passed to tika parser: " + metadata);
    }
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
static Metadata getMetadata() {
  Metadata m = new Metadata();
  m.add("Author", "BeamTikaUser");
  m.add("Author", "BeamTikaUser2");
  m.add("Date", "2017-09-01");
  return m;
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
public void parse(InputStream inputStream, ContentHandler contentHandler,
  Metadata metadata, ParseContext parseContext)
  throws IOException, SAXException, TikaException {

  this.config = parseContext.get(ProfileParserConfig.class, config);
  initialize(this.config.getAgeProfilerModelUrl(),
    this.config.getGenderProfilerModelUrl());
  if (!isAvailable()) {
    return;
  }
  ProfileExtractor extractor = null;

  try {
    extractor = new ProfileExtractor(this.ageProfiler, this.genderProfiler);
  } catch (Exception e) {
    LOG.warning("Profiler setup failed: " + e);
    return;
  }

  Profile profile = extractor.getProfileFromInput(inputStream);

  metadata.add("Author_AGE", profile.getAgeRange());
  metadata.add("Author_GENDER", profile.getGender());
  metadata.add("Author_"+ TraitProfiler.TRAITS.TRAIT_AGREEABLE.name(),
    Double.toString(profile.getTraits().get(0)));
  metadata.add("Author_"+ TraitProfiler.TRAITS.TRAIT_CONSCIENTIOUS.name(),
    Double.toString(profile.getTraits().get(1)));
  metadata.add("Author_"+ TraitProfiler.TRAITS.TRAIT_EXTROVERT.name(),
    Double.toString(profile.getTraits().get(2)));
  metadata.add("Author_"+ TraitProfiler.TRAITS.TRAIT_OPEN.name(),
    Double.toString(profile.getTraits().get(3)));
  metadata.add("Author_"+ TraitProfiler.TRAITS.TRAIT_STABLE.name(),
    Double.toString(profile.getTraits().get(4)));

}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
/**
 * 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.metadata.Metadata; //導入方法依賴的package包/類
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;
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
/**
 * 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());
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
@Override
public void parse(InputStream stream, ContentHandler handler,
		Metadata metadata, ParseContext context) throws IOException,
		SAXException, TikaException {

	/*----------------configure this parser by ParseContext Object---------------------*/
	GeoParserConfig localconfig = context.get(GeoParserConfig.class,
			defaultconfig);
	String nerModelPath = localconfig.getNERPath();
	gazetteerPath = localconfig.getGazetterPath();

	/*----------------get locationNameEntities and best nameEntity for the input stream---------------------*/
	NameEntityExtractor extractor = new NameEntityExtractor(nerModelPath);
	extractor.getAllNameEntitiesfromInput(stream);
	extractor.getBestNameEntity();
	ArrayList<String> locationNameEntities = extractor.locationNameEntities;
	String bestner = extractor.bestNameEntity;

	/*----------------build lucene search engine for the gazetteer file, 
	 *------------------------resolve geonames for each ner, store results in a hashmap---------------------*/
	GeoNameResolver resolver = new GeoNameResolver();
	resolver.buildIndex(gazetteerPath);
	HashMap<String, ArrayList<String>> resolvedGeonames = resolver
			.searchGeoName(locationNameEntities);

	/*----------------store locationNameEntities and their geonames in a geotag, each input has one geotag---------------------*/
	GeoTag geotag = new GeoTag();
	geotag.toGeoTag(resolvedGeonames, bestner);

	/* add resolved entities in metadata */

	metadata.add("Geographic_NAME", geotag.Geographic_NAME);
	metadata.add("Geographic_LONGITUDE", geotag.Geographic_LONGTITUDE);
	metadata.add("Geographic_LATITUDE", geotag.Geographic_LATITUDE);
	for (int i = 0; i < geotag.alternatives.size(); ++i) {
		GeoTag alter = (GeoTag) geotag.alternatives.get(i);
		metadata.add("Optional_NAME" + (i + 1), alter.Geographic_NAME);
		metadata.add("Optional_LONGITUDE" + (i + 1),
				alter.Geographic_LONGTITUDE);
		metadata.add("Optional_LATITUDE" + (i + 1),
				alter.Geographic_LATITUDE);
	}
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
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);
}
 

import org.apache.tika.metadata.Metadata; //導入方法依賴的package包/類
public static MediaType getMimeType(File file) throws IOException {
	Metadata md = new Metadata();
	md.add(Metadata.RESOURCE_NAME_KEY, file.getAbsolutePath());
	return getMimeType(new FileInputStream(file), md);
}