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)}.

    Thread.sleep(5000);
  }


  public void testFindLeadDocument() throws Exception{
    reloadIndexDB();
    Document d = manager.findLeadDocument(urlHash);  
    assertNotNull(d);  
    String v = d.get(DocumentCreator.FIELD_INDEX_TYPE);
    assertEquals(DocumentCreator.INDEX_TYPE_LEAD,v);
    String id = d.get(DocumentCreator.FIELD_BOOKMARK_ID);
    assertEquals("112",id);
    testDestroy();
  }

View Full Code Here

    testDestroy();
  }
  
  public void testFindNonLeadDocument() throws Exception{
    reloadIndexDB();
    Document d = manager.findNonLeadDocument(urlHash);  
    assertNotNull(d);  
    String v = d.get(DocumentCreator.FIELD_INDEX_TYPE);
    assertNull(v);
    String id = d.get(DocumentCreator.FIELD_BOOKMARK_ID);
    assertEquals("111",id);
    testDestroy();
  }

View Full Code Here

    reloadIndexDB();
    doc2.add(DocumentCreator.createFieldTitle("some title"));
    //doc2.add(new Field(DocumentCreator.FIELD_TITLE,"some title",Field.Store.YES,Field.Index.TOKENIZED));
    manager.updateIndex(doc2);
    Thread.sleep(5000);
    Document leadDoc = manager.findLeadDocument(urlHash);
    assertEquals(leadDoc.get(DocumentCreator.FIELD_TITLE),"some title");
    testDestroy();
  }

View Full Code Here

    reloadIndexDB();    
    manager.deleteIndex(doc2);
    Thread.sleep(5000);
    // after deleting the current lead doc, the non-lead doc will
    // be promoted to be the lead doc.
    Document leadDoc = manager.findLeadDocument(urlHash);
    assertEquals(leadDoc.get(DocumentCreator.FIELD_BOOKMARK_ID),"111");
    testDestroy();
  }

View Full Code Here

  }


  public void testAddIndex() throws Exception {
    reloadIndexDB();
    String doc3UrlHash = "999aaa2222";
    Document doc3 = new Document();
    doc3.add(DocumentCreator.createFieldUrlHash(doc3UrlHash));
    //doc3.add(new Field(DocumentCreator.FIELD_URL_MD5,doc3UrlHash,Field.Store.YES,Field.Index.UN_TOKENIZED));
    doc3.add(DocumentCreator.createFieldBookmarkId(2000));
    //doc3.add(new Field(DocumentCreator.FIELD_BOOKMARK_ID,"2000",Field.Store.YES,Field.Index.UN_TOKENIZED));
    manager.addIndex(doc3);
    Thread.sleep(5000);
    Document leadDoc1 = manager.findLeadDocument(urlHash);
    Document leadDoc2 = manager.findLeadDocument(doc3UrlHash);
    assertEquals("112",leadDoc1.get(DocumentCreator.FIELD_BOOKMARK_ID));
    assertEquals("2000",leadDoc2.get(DocumentCreator.FIELD_BOOKMARK_ID));
    testDestroy();
  }

View Full Code Here

      BoboIndexReader subReader = _subReaders[readerIndex];
      return subReader.document(docid - _starts[readerIndex]);
    }
    else
    {
      Document doc = super.document(docid);
      Collection<FacetHandler<?>> facetHandlers = _facetHandlerMap.values();
      for (FacetHandler<?> facetHandler : facetHandlers)
      {
        String[] vals = facetHandler.getFieldValues(this,docid);
        if (vals != null)
        {
          String[] values = doc.getValues(facetHandler.getName());
          Set<String> storedVals = new HashSet<String>(Arrays.asList(values));
          
          for (String val : vals)
          {
          storedVals.add(val);
          }
          doc.removeField(facetHandler.getName());
          
          for (String val : storedVals){
            doc.add(new Field(facetHandler.getName(),
                      val,
                      Field.Store.NO,
                      Field.Index.NOT_ANALYZED));
          }
        }

View Full Code Here

    bmark1.setCreatedOn(createdOn);
    bmark1.setLastUpdated(lastUpdated);
  }


  public void testCreateDocument() throws Exception {
    Document doc1 = DocumentCreator.createDocument(bmark1);
    assertNotNull(doc1);
    
    String id = doc1.get(DocumentCreator.FIELD_BOOKMARK_ID);
    assertEquals("101",id);


    String username = doc1.get(DocumentCreator.FIELD_USER);
    assertEquals("jsmith",username);
    
    String title = doc1.get(DocumentCreator.FIELD_TITLE);
    assertEquals("Title of a Bookmark",title);
  
    String link = doc1.get(DocumentCreator.FIELD_URL);
    assertEquals("http://example.org/foo1.html",link);
    
    String md5 = doc1.get(DocumentCreator.FIELD_URL_MD5);
    assertEquals("123456789abcdefg",md5);
    
    String[] tags = doc1.getValues(DocumentCreator.FIELD_TAG);
    assertEquals(4,tags.length);
    List<String> tagList = Arrays.asList(tags);
    assertTrue(tagList.contains("tag1"));
    assertTrue(tagList.contains("tag2"));
    assertTrue(tagList.contains("foo.bar"));
    assertTrue(tagList.contains("machine:tag=233"));
    
    String cDate = doc1.get(DocumentCreator.FIELD_CREATED_ON);
    String lDate = doc1.get(DocumentCreator.FIELD_LAST_UPDATED);
    assertEquals("20080123",cDate);
    assertEquals("20080211",lDate);
    
    String txt = doc1.get(DocumentCreator.FIELD_TEXT);
    assertNotNull(txt);
  }

View Full Code Here

    String txt = doc1.get(DocumentCreator.FIELD_TEXT);
    assertNotNull(txt);
  }


  public void testRemoveIndexTypeLead() throws Exception{
    Document doc1 = new Document();
    doc1.add(new Field(DocumentCreator.FIELD_BOOKMARK_ID,"100",Field.Store.YES,Field.Index.UN_TOKENIZED));
    doc1.add(new Field(DocumentCreator.FIELD_INDEX_TYPE,DocumentCreator.INDEX_TYPE_LEAD,Field.Store.NO,Field.Index.UN_TOKENIZED));
    doc1.add(new Field(DocumentCreator.FIELD_INDEX_TYPE,"other-type",Field.Store.NO,Field.Index.UN_TOKENIZED));
    doc1 = DocumentCreator.removeIndexTypeLead(doc1);
    Field[] fields = doc1.getFields(DocumentCreator.FIELD_INDEX_TYPE);
    assertEquals(1,fields.length);
    assertEquals("other-type",fields[0].stringValue());
    fields = doc1.getFields(DocumentCreator.FIELD_BOOKMARK_ID);
    assertEquals(1,fields.length);  
  }

View Full Code Here

    fields = doc1.getFields(DocumentCreator.FIELD_BOOKMARK_ID);
    assertEquals(1,fields.length);  
  }
  
  public void testAddIndexTypeLead() throws Exception {
    Document doc1 = new Document();
    doc1.add(new Field(DocumentCreator.FIELD_BOOKMARK_ID,"100",Field.Store.YES,Field.Index.UN_TOKENIZED));
    doc1 = DocumentCreator.addIndexTypeLead(doc1);
    Field[] fields = doc1.getFields(DocumentCreator.FIELD_INDEX_TYPE);
    assertEquals(1,fields.length);
    assertEquals(DocumentCreator.INDEX_TYPE_LEAD,fields[0].stringValue());  
  }

View Full Code Here

  
  public static Document createDocument(Bookmark bookmark) {
    if (bookmark == null) {
      return null;
    }
    Document doc = new Document();
    if (bookmark.getId() <= 0) {
      logger.error("DocumentCreator detects an input Bookmark ID <= 0");
      return null;
    }
    doc.add(createFieldBookmarkId(bookmark.getId()));
    
    if (bookmark.getTitle() == null || bookmark.getTitle().length() == 0) {
      logger.error("DocumentCreator detects an input "
          + "Bookmark Title has length 0. BookmarkId="
          + bookmark.getId());
      return null;
    }
    doc.add(createFieldTitle(bookmark.getTitle()));
    doc.add(createFieldText(bookmark.getTitle()));


    
    // user:
    if (bookmark.getUser() == null
        || bookmark.getUser().getUsername() == null) {
      logger.error("DocumentCreator detects an input "
          + "Bookmark Username == null. BookmarkId="
          + bookmark.getId());
      return null;
    }
    doc.add(createFieldUser(bookmark.getUser().getUsername()));
    
    if (bookmark.getLink() == null || bookmark.getLink().getUrl() == null) {
      logger.error("DocumentCreator detects an input "
          + "Bookmark URL == null. BookmarkId=" + bookmark.getId());
      return null;
    }
    doc.add(createFieldUrl(bookmark.getLink().getUrl()));    
    
    // url: & urlMD5:
    if (bookmark.getLink() == null || bookmark.getLink().getUrlHash() == null) {
      logger.error("DocumentCreator detects an input "
          + "Bookmark URL Hash == null. BookmarkId=" + bookmark.getId());
      return null;
    }
    doc.add(createFieldUrlHash(bookmark.getLink().getUrlHash()));
    
    // notes:
    String notes = extractText(bookmark.getNotes());
    if (notes != null) {
      doc.add(createFieldNotes(bookmark.getNotes()));
      doc.add(createFieldText(bookmark.getNotes()));
    }
    // tag:
    List<String> tagList = bookmark.getTagList();
    for (String tag : tagList) {
      doc.add(createFieldTag(tag));
      doc.add(createFieldText(tag));
    }
    // createdOn:
    if (bookmark.getCreatedOn() == null) {
      logger.error("DocumentCreator detects an input "
          + "Bookmark createdOn == null. BookmarkId="
          + bookmark.getId());
      return null;
    }
    doc.add(createFieldCreatedOn(bookmark.getCreatedOn()));
    
    // lastUpdated:
    if (bookmark.getLastUpdated() == null) {
      logger.error("DocumentCreator detects an input "
          + "Bookmark lastUpdated == null. BookmarkId="
          + bookmark.getId());
      return null;
    }    
    doc.add(createFieldLastUpdated(bookmark.getLastUpdated()));    
    return doc;
  }

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.