Examples of org.apache.lucene.index.IndexWriter.addDocument()

Class org.apache.lucene.index.IndexWriter

Examples of org.apache.lucene.index.IndexWriter.addDocument()

org.apache.lucene.index.IndexWriter.addDocument()
Adds a document to this index. If the document contains more than {@link #setMaxFieldLength(int)} terms for a given field, the remainder arediscarded.
Note that if an Exception is hit (for example disk full) then the index will be consistent, but this document may not have been added. Furthermore, it's possible the index will have one segment in non-compound format even when using compound files (when a merge has partially succeeded).

This method periodically flushes pending documents to the Directory (see above), and also periodically triggers segment merges in the index according to the {@link MergePolicy} in use.
Merges temporarily consume space in the directory. The amount of space required is up to 1X the size of all segments being merged, when no readers/searchers are open against the index, and up to 2X the size of all segments being merged when readers/searchers are open against the index (see {@link #optimize()} for details). The sequence ofprimitive merge operations performed is governed by the merge policy.
Note that each term in the document can be no longer than 16383 characters, otherwise an IllegalArgumentException will be thrown.

Note that it's possible to create an invalid Unicode string in java if a UTF16 surrogate pair is malformed. In this case, the invalid characters are silently replaced with the Unicode replacement character U+FFFD.

NOTE: if this method hits an OutOfMemoryError you should immediately close the writer. See above for details.
@throws CorruptIndexException if the index is corrupt @throws IOException if there is a low-level IO error

    doc.add(new Field("author", "����IBM OSIһһ����", Field.Store.YES, Field.Index.TOKENIZED));
    doc.add(new Field("time", Long.toString(System.currentTimeMillis()), Field.Store.YES, Field.Index.UN_TOKENIZED));
    doc.add(new Field("content", "��֪����ʲôʱ��ʼ����ʲô�������涼�и����ڣ��ﵶ�����ڣ����ͷ����ڣ�������ֽ������ڣ��ҿ�ʼ���ɣ�����������ϣ�����ʲô�����ǲ�����ڵģ�", Field.Store.NO, Field.Index.TOKENIZED));
    IndexWriter writer = getWriter();
    try {
        writer.addDocument(doc);
        writer.optimize();
    }finally {
        writer.close();
    }
    System.out.println("doc count = " + writer.docCount());

View Full Code Here

      lucene_doc.add(UnStored(indexFields[i], propertyValue));
    }
    //Write document
    IndexWriter writer = getWriter(doc.name());
    try {
        writer.addDocument(lucene_doc);
        writer.optimize();
    }finally {
      try{
        writer.close();
      }catch(Exception e){

View Full Code Here

                doc.add(new Field("hostname", resultSet.getString("hostname"), true, true, true));
                doc.add(new Field("message", resultSet.getString("message"), true, true, true));


                try
                {
                  writer.addDocument(doc, getAnalyzer());
                }
                catch (IOException e)
                {
                  Logger
                    .getLogger("com.uwyn.drone.tools")

View Full Code Here

    }


    private void indexArticle(Article article) throws IOException {
        Document doc = article.getOveriewDocument();
        IndexWriter writer = new IndexWriter( forum.getArticleOverview(), ws, true );
        writer.addDocument( doc );
        writer.close();
    }
}

View Full Code Here

  public void testIndexReaderReopen() throws Exception{
    Directory idxDir = new RAMDirectory();
    Document[] docs = buildData();
    
    IndexWriter writer = new IndexWriter(idxDir,new StandardAnalyzer(Version.LUCENE_29),MaxFieldLength.UNLIMITED);
    writer.addDocument(docs[0]);
    writer.optimize();
    writer.commit();
    
    IndexReader idxReader = IndexReader.open(idxDir,true);
    BoboIndexReader boboReader = BoboIndexReader.getInstance(idxReader,_fconf);

View Full Code Here

      BoboIndexReader reader = (BoboIndexReader)boboReader.reopen(true);
      assertSame(boboReader,reader);
      
      Directory tmpDir = new RAMDirectory();
      IndexWriter subWriter = new IndexWriter(tmpDir,new StandardAnalyzer(Version.LUCENE_29),MaxFieldLength.UNLIMITED);
      subWriter.addDocument(doc);
      subWriter.optimize();
      subWriter.close();
      writer.addIndexesNoOptimize(new Directory[]{tmpDir});
      writer.commit();
      reader = (BoboIndexReader)boboReader.reopen();

View Full Code Here

    DecimalFormat df = new DecimalFormat(DynamicTimeRangeFacetHandler.NUMBER_FORMAT);
    for(long l=0; l<53; l++)
    {
      Document d = new Document();
      d.add(buildMetaField("timeinmillis", df.format(now - l*3500000)));
      writer.addDocument(d);
      writer.optimize();
      writer.commit();
    }
    IndexReader idxReader = IndexReader.open(idxDir,true);
    BoboIndexReader boboReader = BoboIndexReader.getInstance(idxReader,facetHandlers);

View Full Code Here

      directory = new RAMDirectory();
      analyzer = new WhitespaceAnalyzer();
      IndexWriter writer = new IndexWriter(directory, analyzer, true, MaxFieldLength.UNLIMITED);
      Document doc = new Document();
      addMetaDataField(doc,PathHandlerName,new String[]{"/a/b/c","/a/b/d"});
      writer.addDocument(doc);
      writer.commit();
      
      PathFacetHandler pathHandler = new PathFacetHandler("path",true);
      facetHandlers.add(pathHandler);
  }

View Full Code Here

          true);
      for (Tag tag : tags) {
        String t = tag.getLabel();
        if (t.length() >= 3) {
          Document doc = createDocument(t);
          indexWriter.addDocument(doc);
        }
      }
      indexWriter.optimize();
    } finally {
      if (indexWriter != null) {

View Full Code Here

              "\n\r\f", false);
          while (tokenizer.hasMoreTokens()) {
            String token = tokenizer.nextToken().trim();
            if (token != null) {
              Document doc = createDocument(token);
              indexWriter.addDocument(doc);
            }
          }
          aline = dataReader.readLine();
        }
        indexWriter.optimize();

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

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.