Examples of org.apache.lucene.document.Document

org.apache.lucene.document.Document
Documents are the unit of indexing and search. A Document is a set of fields. Each field has a name and a textual value. A field may be {@link Fieldable#isStored() stored} with the document, in whichcase it is returned with search hits on the document. Thus each document should typically contain one or more stored fields which uniquely identify it.
Note that fields which are not {@link Fieldable#isStored() stored} arenot available in documents retrieved from the index, e.g. with {@link ScoreDoc#doc}, {@link Searcher#doc(int)} or {@link IndexReader#document(int)}.

  }


  //*-- create the Lucene Index
  public void loadIndex(IndexWriter ramIW, boolean storeTermVector) throws IOException
  {
   Document doc = new Document();
   doc.add( new Field("key", getFileName(), Field.Store.YES, Field.Index.NO) );
   doc.add(new Field("contents", getContents().toString(), Field.Store.NO, Field.Index.TOKENIZED) );
   doc.add( new Field("type", getFileType(), Field.Store.YES, Field.Index.NO) );
   doc.add( new Field("category", getTextType(), Field.Store.YES, Field.Index.NO) );
   ramIW.addDocument(doc);
  }

View Full Code Here

     for (int j = 0; j < ranks.length; j++) if (ranks[j] == i) foundHit = true;
     if (!foundHit) continue LOOP;
     
     retv.append("Document: " + i + Constants.NEWLINE); 
     explanation = is.explain(query, hits.id(i));  
     Document doc = hits.doc(i); 
     String key = doc.get("key");
     DatabaseEntry data = new DatabaseEntry();
     if (!dbt.fetch(key, data)) continue LOOP;


     //*-- extract the text
     IndexableDoc idoc = new IndexableDoc();

View Full Code Here

   setTextType(cdoc.classifyTextContents(this)); }


 //*-- create the Lucene Index
 public void loadIndex(IndexWriter ramIW, boolean storeTermVector) throws IOException
 {
  Document doc = new Document();
  doc.add( new Field("key", getFileName(), Field.Store.YES, Field.Index.NO) );
  doc.add(new Field("contents", getContents().toString(), Field.Store.NO, Field.Index.TOKENIZED) );
  doc.add( new Field("type", getFileType(), Field.Store.YES, Field.Index.NO) );
  doc.add( new Field("category", getTextType(), Field.Store.YES, Field.Index.NO) );
  ramIW.addDocument(doc);
 }

View Full Code Here

  }


  //*-- create the Lucene Index
  public void loadIndex(IndexWriter ramIW, boolean storeTermVector) throws IOException
  {
   Document doc = new Document();
   doc.add( new Field("key", getFileName(), Field.Store.YES, Field.Index.NO) );
   doc.add(new Field("contents", getContents().toString(), Field.Store.NO, Field.Index.TOKENIZED) );
   doc.add( new Field("type", getFileType(), Field.Store.YES, Field.Index.NO) );
   doc.add( new Field("category", getTextType(), Field.Store.YES, Field.Index.NO) );
   ramIW.addDocument(doc);
  }

View Full Code Here

   DbTools dbt = Constants.getDbt();
   if (hits.length() == 0)  results[j++] = " Try " + getAlt();
   LOOP: for (int i = 0; i < hits.length(); i++)
   { 
    //*-- use the key to fetch the matching database entry
    Document doc = hits.doc(i);
    String key = doc.get("key");
    String ftype = doc.get("type");
    DatabaseEntry data = new DatabaseEntry();


    String dbname = (ftype.equalsIgnoreCase("email")) ? Constants.EXT_MESSAGES_DB: Constants.EXT_FILES_DB;
    dbt.openDB(dbname, true, false); //*-- no create and no dups             
    dbt.fetch(key, data);

View Full Code Here

   * @param type
   */
  public SearchDocument(T type) {
    Assert.isLegal(type != null);
    fType = type;
    fDocument = new Document();
  }

View Full Code Here

      final List<SearchHit<NewsReference>> resultList = new ArrayList<SearchHit<NewsReference>>();
      HitCollector collector = new HitCollector() {
        @Override
        public void collect(int doc, float score) {
          try {
            Document document = fSearcher.doc(doc);


            /* Receive Stored Fields */
            long newsId = Long.valueOf(document.get(SearchDocument.ENTITY_ID_TEXT));
            INews.State newsState = NEWS_STATES[Integer.parseInt(document.get(NewsDocument.STATE_ID_TEXT))];


            Map<Integer, INews.State> data = new HashMap<Integer, INews.State>(1);
            data.put(INews.STATE, newsState);


            /* Add to List */

View Full Code Here

   * @param type
   */
  public SearchDocument(T type) {
    Assert.isLegal(type != null);
    fType = type;
    fDocument = new Document();
  }

View Full Code Here

      /* Use custom hit collector for performance reasons */
      HitCollector collector = new HitCollector() {
        @Override
        public void collect(int doc, float score) {
          try {
            Document document = currentSearcher.doc(doc);


            /* Receive Stored Fields */
            long newsId = Long.parseLong(document.get(SearchDocument.ENTITY_ID_TEXT));
            INews.State newsState = NEWS_STATES[Integer.parseInt(document.get(NewsDocument.STATE_ID_TEXT))];


            Map<Integer, INews.State> data = new HashMap<Integer, INews.State>(1);
            data.put(INews.STATE, newsState);


            /*

View Full Code Here

    }


    @Override
    public void collect(int doc, float score) {
      try {
        Document document = fSearcher.doc(doc);


        /* Receive Stored Fields */
        long newsId = Long.parseLong(document.get(SearchDocument.ENTITY_ID_TEXT));


        /*
         * Under some circumstances the index might contain the same news twice.
         * This can happen in situations where RSSOwl is quitting in an emergent
         * way (e.g. the OS shutting down while RSSOwl is running). To avoid

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.apache.lucene.document.Document

com.bericotech.clavin.gazetteer.query.LuceneGazetteer

com.browseengine.bobo.test.BasicIndexingTest

com.browseengine.bobo.test.BoboTestCase

com.browseengine.bobo.test.FacetNotValuesTest

com.gentics.cr.lucene.autocomplete.Autocompleter

com.gentics.cr.lucene.indexer.index.CRLuceneIndexJob

com.gentics.cr.lucene.indexer.index.LuceneIndexUpdateChecker

com.gentics.cr.lucene.search.CRSearcher

com.gentics.cr.lucene.search.query.mocks.SimpleLucene

com.tamingtext.classifier.mlt.TrainMoreLikeThis

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.