Package org.apache.tika.metadata

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


                }
                catch (SAXException | TikaException e) {
                    System.out.println("Unable to extract file content: " + e.getMessage());
                }

                for (final String key : metadata.names()) {
                    System.out.println(key + " -> " + metadata.get(key));
                }
                System.out.println(" ---------------------- ");
            }
View Full Code Here


              parser.parse(is, contenthandler, metadata,new ParseContext());             
              String contentType =  metadata.get(Metadata.CONTENT_TYPE);
               if (StringUtils.isEmpty(contentType)) contentType="application/octet-stream";
              
              HashMap<String,Object> extractedMetaData = new HashMap<String,Object>();
              for (String key:metadata.names()){
                try{
                if (metadata.isMultiValued(key)){
                  if (Logger.isDebugEnabled()) Logger.debug(key + ": ");
                  for (String value: metadata.getValues(key)){
                    if (Logger.isDebugEnabled()) Logger.debug("   " + value);
View Full Code Here

            + content.getUrl());
      }
    }

    // populate Nutch metadata with Tika metadata
    String[] TikaMDNames = tikamd.names();
    for (String tikaMDName : TikaMDNames) {
      if (tikaMDName.equalsIgnoreCase(Metadata.TITLE))
        continue;
      // TODO what if multivalued?
      nutchMetadata.add(tikaMDName, tikamd.get(tikaMDName));
View Full Code Here

            + content.getUrl());
      }
    }

    // populate Nutch metadata with Tika metadata
    String[] TikaMDNames = tikamd.names();
    for (String tikaMDName : TikaMDNames) {
      if (tikaMDName.equalsIgnoreCase(Metadata.TITLE))
        continue;
      // TODO what if multivalued?
      nutchMetadata.add(tikaMDName, tikamd.get(tikaMDName));
View Full Code Here

      try
      {
        docCopy.setBinary(is,newBinaryLength);

        // Set up all metadata from Tika.  We may want to run this through a mapper eventually...
        String[] metaNames = metadata.names();
        for(String mName : metaNames){
          String value = metadata.get(mName);
          String target = sp.getMapping(mName);
          if(target!=null)
          {
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(Metadata.TITLE)) continue;
      // TODO what if multivalued?
      page.putToMetadata(new Utf8(tikaMDName), ByteBuffer.wrap(Bytes.toBytes(tikamd
          .get(tikaMDName))));
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

        docAnnotation.setFeatures((FSArray) cas
          .createArrayFS(md.size()+1)) ;
      }
      int i=0;
      for (;i<md.size();i++){
        String name = md.names()[i];
        String value = md.get(name);
        FeatureValue fv = new FeatureValue(cas.getJCas());
        fv.setName(name);
        fv.setValue(value);
        // getLogger().log(Level.FINER,URI+"\t"+name+"\t"+value);
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.