Package org.apache.tika.metadata

Examples of org.apache.tika.metadata.Metadata.names()


      // now iterate on the metadata found by Tika and add them to the info
      if (docAnnotation.getFeatures()==null)
        docAnnotation.setFeatures((FSArray) cas.createArrayFS(md.size())) ;
     
      for (int i=0;i<md.size();i++){
        String name = md.names()[i];
        String value = md.get(name);
        FeatureValue fv = new FeatureValue(ptv);
        fv.setName(name);
        fv.setValue(value);
        docAnnotation.setFeatures(i,fv);
View Full Code Here


        if (tc == null) {
            return null;
        }
        Metadata metadata = tc.getMetadata();
        SearchBean bean = new SearchBean();
        for (final String property: metadata.names()) {
            bean.set(property, metadata.get(property));
        }
        return bean;
    }
    /**
 
View Full Code Here

        LOG.trace("found " + outlinks.length + " outlinks in " + base);
      }
    }

    // populate Nutch metadata with Tika metadata
    String[] TikaMDNames = tikamd.names();
    for (String tikaMDName : TikaMDNames) {
      if (tikaMDName.equalsIgnoreCase(TikaCoreProperties.TITLE.toString()))
      continue;
      // TODO what if multivalued?
      page.putToMetadata(new Utf8(tikaMDName), ByteBuffer.wrap(Bytes.toBytes(tikamd
View Full Code Here

        //make sure old metadata doesn't linger between objects
        assertFalse(Arrays.asList(meta_jpg.getValues("dc:subject")).contains("serbor"));
        assertEquals("false", meta_jpg.get(RTFMetadata.THUMBNAIL));
        assertEquals("false", meta_jpg_exif.get(RTFMetadata.THUMBNAIL));
       
        assertEquals(40, meta_jpg.names().length);
        assertEquals(105, meta_jpg.names().length);
    }
   
    //TIKA-1010 test linked embedded doc
    @Test
View Full Code Here

        assertFalse(Arrays.asList(meta_jpg.getValues("dc:subject")).contains("serbor"));
        assertEquals("false", meta_jpg.get(RTFMetadata.THUMBNAIL));
        assertEquals("false", meta_jpg_exif.get(RTFMetadata.THUMBNAIL));
       
        assertEquals(40, meta_jpg.names().length);
        assertEquals(105, meta_jpg.names().length);
    }
   
    //TIKA-1010 test linked embedded doc
    @Test
    public void testEmbeddedLinkedDocument() throws Exception {
View Full Code Here

                    new InMemoryBlob(xhtmlHandler.toString(),
                        "application/xhtml+xml")); //string -> no encoding
            }
            //add the extracted metadata
            if(log.isDebugEnabled()){
                for(String name : metadata.names()){
                    log.debug("{}: {}",name,Arrays.toString(metadata.getValues(name)));
                }
            }
            ci.getLock().writeLock().lock();
            try {
View Full Code Here

        iWorkParser.parse(input, handler, metadata, parseContext);

        // Make sure enough keys came through
        // (Exact numbers will vary based on composites)
        assertTrue("Insufficient metadata found " + metadata.size(), metadata.size() >= 6);
        List<String> metadataKeys = Arrays.asList(metadata.names());
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(Metadata.CONTENT_TYPE));
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(Metadata.SLIDE_COUNT.getName()));
//        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(Office.SLIDE_COUNT.getName()));
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(TikaCoreProperties.CREATOR.getName()));
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(TikaCoreProperties.TITLE.getName()));
View Full Code Here

        iWorkParser.parse(input, handler, metadata, parseContext);

        // Make sure enough keys came through
        // (Exact numbers will vary based on composites)
        assertTrue("Insufficient metadata found " + metadata.size(), metadata.size() >= 50);
        List<String> metadataKeys = Arrays.asList(metadata.names());
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(Metadata.CONTENT_TYPE));
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(Metadata.PAGE_COUNT.getName()));
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(TikaCoreProperties.CREATOR.getName()));
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(TikaCoreProperties.TITLE.getName()));
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(Metadata.LAST_MODIFIED.getName()));
View Full Code Here

        iWorkParser.parse(input, handler, metadata, parseContext);

        // Make sure enough keys came through
        // (Exact numbers will vary based on composites)
        assertTrue("Insufficient metadata found " + metadata.size(), metadata.size() >= 8);
        List<String> metadataKeys = Arrays.asList(metadata.names());
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(Metadata.CONTENT_TYPE));
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(Metadata.PAGE_COUNT.getName()));
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(TikaCoreProperties.CREATOR.getName()));
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(TikaCoreProperties.COMMENTS.getName()));
        assertTrue("Metadata not found in " + metadataKeys, metadataKeys.contains(Metadata.TITLE));
View Full Code Here

    parser.parse(is, new DefaultHandler(), metadata);

    return new StreamingOutput() {
      public void write(OutputStream outputStream) throws IOException, WebApplicationException {
        CSVWriter writer = new CSVWriter(new OutputStreamWriter(outputStream));
        for (String name : metadata.names()) {
          String[] values = metadata.getValues(name);
          ArrayList<String> list = new ArrayList<String>(values.length+1);
          list.add(name);
          list.addAll(Arrays.asList(values));
          writer.writeNext(list.toArray(values));
View Full Code Here

TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.