Package org.apache.tika.metadata

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


        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


                UriRef xhtmlBlobUri = new UriRef("urn:tika:xhtml:"+random);
                ci.addPart(xhtmlBlobUri,  xhtmlSink.getBlob());
            }
            //add the extracted metadata
            if(log.isInfoEnabled()){
                for(String name : metadata.names()){
                    log.info("{}: {}",name,Arrays.toString(metadata.getValues(name)));
                }
            }
            ci.getLock().writeLock().lock();
            try {
View Full Code Here

            try {
                MGraph graph = ci.getMetadata();
                UriRef id = ci.getUri();
                Set<String> mapped = ontologyMappings.apply(graph, id, metadata);
                if(includeUnmappedProperties){
                    Set<String> unmapped = new HashSet<String>(Arrays.asList(metadata.names()));
                    unmapped.removeAll(mapped);
                    for(String name : unmapped){
                        if(name.indexOf(':') >=0 || includeAllUnmappedProperties){ //only mapped
                            UriRef prop = new UriRef(new StringBuilder(TIKA_URN_PREFIX).append(name).toString());
                            for(String value : metadata.getValues(name)){
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

            input = new ProgressMonitorInputStream(
                    this, "Parsing file " + file.getName(), input);
            parser.parse(input, handler, md);

            String[] names = md.names();
            Arrays.sort(names);
            for (String name : names) {
                metadataBuffer.append(name);
                metadataBuffer.append(": ");
                metadataBuffer.append(md.get(name));
View Full Code Here

        metadata.add("json_escapes", "the: \"quick\" brown, fox");
       
        StringWriter writer = new StringWriter();
        JsonMetadata.toJson(metadata, writer);
        Metadata deserialized = JsonMetadata.fromJson(new StringReader(writer.toString()));
        assertEquals(7, deserialized.names().length);
        assertEquals(metadata, deserialized);

        //test that this really is 6 Chinese characters
        assertEquals(6, deserialized.get("alma_mater").length());
    }
View Full Code Here

            document.add(getContentField(documentMetadata, content.getContent()));
        }
       
        if (extractMetadata) {
            Metadata metadata = content.getMetadata();
            for (final String property: metadata.names()) {
                document.add(getField(documentMetadata, property, metadata.get(property)));
            }
        }
       
        if (!StringUtils.isEmpty(documentMetadata.getSource())) {
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

            input = new ProgressMonitorInputStream(
                    this, "Parsing file " + file.getName(), input);
            parser.parse(input, handler, md);

            String[] names = md.names();
            Arrays.sort(names);
            for (String name : names) {
                metadataBuffer.append(name);
                metadataBuffer.append(": ");
                metadataBuffer.append(md.get(name));
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

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.