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


    IndexWriter iw = new IndexWriter(dir, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.UNLIMITED);
    Document doc = new Document();
    doc.add(new Field("foo", "bar rab abr bra rba", Field.Store.NO, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
    doc.add(new Field("moo", "bar rab abr bra rba", Field.Store.YES, Field.Index.ANALYZED, Field.TermVector.WITH_POSITIONS_OFFSETS));
    iw.addDocument(doc);
    iw.close();


    IndexReader ir = IndexReader.open(dir, false);
    InstantiatedIndex ii = new InstantiatedIndex(ir);
    ir.close();

View Full Code Here

        {
            Document d1 = new Document();
            d1.add(new Field("id", "d1", Field.Store.YES, Field.Index.NOT_ANALYZED));//Field.Keyword("id", "d1"));
            d1.add(new Field("hed", "elephant", Field.Store.YES, Field.Index.ANALYZED));//Field.Text("hed", "elephant"));
            d1.add(new Field("dek", "elephant", Field.Store.YES, Field.Index.ANALYZED));//Field.Text("dek", "elephant"));
            writer.addDocument(d1);
        }


        // d2 is a "good" match for:  albino elephant
        {
            Document d2 = new Document();

View Full Code Here

            Document d2 = new Document();
            d2.add(new Field("id", "d2", Field.Store.YES, Field.Index.NOT_ANALYZED));//Field.Keyword("id", "d2"));
            d2.add(new Field("hed", "elephant", Field.Store.YES, Field.Index.ANALYZED));//Field.Text("hed", "elephant"));
            d2.add(new Field("dek", "albino", Field.Store.YES, Field.Index.ANALYZED));//Field.Text("dek", "albino"));
            d2.add(new Field("dek", "elephant", Field.Store.YES, Field.Index.ANALYZED));//Field.Text("dek", "elephant"));
            writer.addDocument(d2);
        }


        // d3 is a "better" match for:  albino elephant
        {
            Document d3 = new Document();

View Full Code Here

        {
            Document d3 = new Document();
            d3.add(new Field("id", "d3", Field.Store.YES, Field.Index.NOT_ANALYZED));//Field.Keyword("id", "d3"));
            d3.add(new Field("hed", "albino", Field.Store.YES, Field.Index.ANALYZED));//Field.Text("hed", "albino"));
            d3.add(new Field("hed", "elephant", Field.Store.YES, Field.Index.ANALYZED));//Field.Text("hed", "elephant"));
            writer.addDocument(d3);
        }


        // d4 is the "best" match for:  albino elephant
        {
            Document d4 = new Document();

View Full Code Here

            Document d4 = new Document();
            d4.add(new Field("id", "d4", Field.Store.YES, Field.Index.NOT_ANALYZED));//Field.Keyword("id", "d4"));
            d4.add(new Field("hed", "albino", Field.Store.YES, Field.Index.ANALYZED));//Field.Text("hed", "albino"));
            d4.add(new Field("hed", "elephant", Field.Store.YES, Field.Index.ANALYZED));//Field.Text("hed", "elephant"));
            d4.add(new Field("dek", "albino", Field.Store.YES, Field.Index.ANALYZED));//Field.Text("dek", "albino"));
            writer.addDocument(d4);
        }


        writer.close();


        r = IndexReader.open(index, true);

View Full Code Here

        writer.setUseCompoundFile(false);
        for(int i=0;i<37;i++) {
          Document doc = new Document();
          doc.add(new Field("content", "aaa bbb ccc ddd" + i, Field.Store.YES, Field.Index.ANALYZED));
          doc.add(new Field("id", "" + i, Field.Store.YES, Field.Index.ANALYZED));
          writer.addDocument(doc);
        }
        writer.close();


        dir.allIndexInputs.clear();

View Full Code Here

    IndexWriter iw = new IndexWriter(ramDir, new WhitespaceAnalyzer(), true,
        IndexWriter.MaxFieldLength.LIMITED);
    Document doc = new Document();
    doc.add(new Field("content", "\u0633\u0627\u0628", Field.Store.YES,
        Field.Index.NOT_ANALYZED));
    iw.addDocument(doc);
    iw.close();
    IndexSearcher is = new IndexSearcher(ramDir, true);


    QueryParserWrapper qp = new QueryParserWrapper("content",
        new WhitespaceAnalyzer());

View Full Code Here

                  if ((++row % mod) == 0)
                  {
                      o.println("\trow=" + row + "/" + word2Nums.size() + " doc= " + doc);
                      mod *= 2;
                  }
                  writer.addDocument(doc);
              } // else degenerate
          }
          o.println( "Optimizing..");
          writer.optimize();
          writer.close();

View Full Code Here

                                         true, IndexWriter.MaxFieldLength.LIMITED);


    Document doc = new Document();
    doc.add(new Field("partnum", "Q36", Field.Store.YES, Field.Index.NOT_ANALYZED));
    doc.add(new Field("description", "Illidium Space Modulator", Field.Store.YES, Field.Index.ANALYZED));
    writer.addDocument(doc);


    writer.close();


    searcher = new IndexSearcher(directory, true);
  }

View Full Code Here

  public void testMutipleDocument() throws Exception {
    RAMDirectory dir = new RAMDirectory();
    IndexWriter writer = new IndexWriter(dir,new KeywordAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
    Document doc = new Document();
    doc.add(new Field("partnum", "Q36", Field.Store.YES, Field.Index.ANALYZED));
    writer.addDocument(doc);
    doc = new Document();
    doc.add(new Field("partnum", "Q37", Field.Store.YES, Field.Index.ANALYZED));
    writer.addDocument(doc);
    writer.close();

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.