Lucene .NET Update data

Question

I started use Lucene several days ago, but in debug my solution I found one trouble in Lucene. For try solve this problem I create new custom project and started test different solutions, but after 2 days of searching solution with Lucene I surrender...

My problem :

I create one custom class, create standard array of this class. Create Document objects and index it by IndexWriter. Its all works fine. Search working great. But when I try to update any document by using IndexWriter.UpdateDocument and say it update document with, for example, index '5', its create new document with id = 5. And finally I have 2 documents with id=5, and old, and new. If in constructor of IndexWriter 'true' in replace id, so when I update it same code its save only 1 updated document, and remove all indexed before. Exactly, I can't update all base all time, because my base is large (about 600 internet resources on my constructor), I need update only changed data (replace it new), and save indexed before. May be some one know what I doing wrong?

P.S. Sorry for my english.

class mydoc
{
    public string id;
    public string name;
    public string content;

    public mydoc(string ID, string Name, string Content)
    {
        id = ID;
        name = Name;
        this.content = Content;
    }
}

class Program
{
    static void Main(string[] args)
    {
        Console.WriteLine("Create data array...");
        mydoc[] docs = new mydoc[11];
        docs[0] = new mydoc("0", "Name0", "tet 5");
        docs[1] = new mydoc("1", "Name1", "aaaa text");
        docs[2] = new mydoc("2", "Name2", "and me test ");
        docs[3] = new mydoc("3", "Name3", "I am new tes 3");
        docs[4] = new mydoc("4", "Name4", "I am new tes 4");
        docs[5] = new mydoc("5", "Name5", "I am new test 5");
        docs[6] = new mydoc("6", "Name6", "I am new text 6");
        docs[7] = new mydoc("7", "Name7", "I am new text 7");
        docs[8] = new mydoc("8", "Name8", "I am new text 8");
        docs[9] = new mydoc("9", "Name9", "I am new text 9");
        docs[10] = new mydoc("10", "Name10", "I am new test 10");

        Console.WriteLine("index processing...");
        var dir = new DirectoryInfo("tmp");
        FSDirectory fsdir = FSDirectory.Open(dir);
        Analyzer analyzer = new StandardAnalyzer(Net.Util.Version.LUCENE_29);
        IndexWriter writer = new IndexWriter(fsdir , analyzer,true, IndexWriter.MaxFieldLength.UNLIMITED);

        for (int i = 0; i < docs.Length; i++)
        {
            writer.AddDocument(Convert(docs[i]));
        }
        writer.Optimize(true);

        writer.Close(true);

        Console.WriteLine("index done !");

        IndexReader reader = IndexReader.Open(fsdir, true);
        for (int i = 0; i < reader.MaxDoc;i++)
        {
            Document doc = reader.Document(i);
            Console.WriteLine("id = \"{0}\", Name = \"{1}\", Context = \"{2}\"", doc.Get("ID"),doc.Get("Name"),doc.Get("Content"));
        }
        reader.Close();

        // Update custom base
        IndexWriter updater = new IndexWriter(fsdir, analyzer, true, IndexWriter.MaxFieldLength.UNLIMITED);
        updater.UpdateDocument(new Term("0"), Convert(new mydoc("0", "New name 0", "prosto obitr test")), new StandardAnalyzer(Net.Util.Version.LUCENE_30));
        updater.UpdateDocument(new Term("1"), Convert(new mydoc("1", "New name 1", "prosto obitr test")),new StandardAnalyzer(Net.Util.Version.LUCENE_30));
        updater.UpdateDocument(new Term("2"), Convert(new mydoc("2", "New name 2", "prosto obitr test")), new StandardAnalyzer(Net.Util.Version.LUCENE_30));
        updater.UpdateDocument(new Term("3"), Convert(new mydoc("3", "New name 3", "prosto obitr test")), new StandardAnalyzer(Net.Util.Version.LUCENE_30));
        updater.UpdateDocument(new Term("4"), Convert(new mydoc("4", "New name 4", "prosto obitr test")), new StandardAnalyzer(Net.Util.Version.LUCENE_30));
        updater.UpdateDocument(new Term("5"), Convert(new mydoc("5", "New name 5", "prosto obitr test")), new StandardAnalyzer(Net.Util.Version.LUCENE_30));
        updater.UpdateDocument(new Term("6"), Convert(new mydoc("6", "New name 6", "prosto obitr test")), new StandardAnalyzer(Net.Util.Version.LUCENE_30));
        updater.UpdateDocument(new Term("7"), Convert(new mydoc("7", "New name 7", "prosto obitr test")), new StandardAnalyzer(Net.Util.Version.LUCENE_30));
        updater.UpdateDocument(new Term("8"), Convert(new mydoc("8", "New name 8", "prosto obitr test")), new StandardAnalyzer(Net.Util.Version.LUCENE_30));
        updater.UpdateDocument(new Term("9"), Convert(new mydoc("9", "New name 9", "prosto obitr test")), new StandardAnalyzer(Net.Util.Version.LUCENE_30));

        updater.Optimize();
        updater.Close(true);

        reader = IndexReader.Open(fsdir, true);
        Console.WriteLine("New updated data:");
        for (int i = 0; i < reader.MaxDoc; i++)
        {
            Document doc = reader.Document(i);
            Console.WriteLine("id = \"{0}\", Name = \"{1}\", Context = \"{2}\"", doc.Get("ID"), doc.Get("Name"), doc.Get("Content"));
        }

        Console.ReadKey();


        Console.WriteLine("search processing...");
        string query = "test";
        fsdir = FSDirectory.Open(dir);
        IndexSearcher searcher = new IndexSearcher(fsdir, true);
        Console.WriteLine("Searching phrase \"{0}\"", query);
        List<KeyValuePair<int, int>> results = find(query, searcher);

        searcher.Close();
        fsdir.Close();

        Console.WriteLine("Results:");
        for (int i = 0; i < results.Count; i++)
        {
            try
            {
                // Display founded id
                Console.WriteLine(results[i].Value);
            }
            catch (Exception ex)
            {
                continue;
            }
        }
        Console.WriteLine("\n\rDone !");
        Console.ReadKey();

    }

    static List<KeyValuePair<int,int>> find(string query, IndexSearcher searcher)
    {
        var parser = new MultiFieldQueryParser(Net.Util.Version.LUCENE_30, new[] { "Name", "Content" }, new SimpleAnalyzer());
        var score = searcher.Search(parser.Parse(query), 99).ScoreDocs;
        var docIDs = score.Select(x => new KeyValuePair<int, int>
            (
                x.Doc, int.Parse(searcher.Doc(x.Doc).Get("ID"))
            )
            ).ToList();
        return docIDs;
    }


    static Document Convert(mydoc doc)
    {
        var document = new Document();
        document.Add(new Field("ID", doc.id, Field.Store.YES, Field.Index.NOT_ANALYZED));
        document.Add(new Field("Name", doc.name, Field.Store.YES, Field.Index.ANALYZED));
        document.Add(new Field("Content", doc.content, Field.Store.YES, Field.Index.ANALYZED));

        return document;
    }
}

In this case doc[10] just disapear from index. if in

IndexWriter updater = new IndexWriter(fsdir, analyzer, true, IndexWriter.MaxFieldLength.UNLIMITED);   

'true' replace to 'false', it create new documents instead replace old.

updater.commit() also did not help.

Answer 1

Problem solved. My fault was in not correct understanding of type Term in:

IndexUpdater.UpdateDocument(Term term, Document doc);

Its need to create new instance of Term like this (in my case):

updater.UpdateDocument(new Term("ID", "5"), Convert(new mydoc("5", "New name 5", "simple new test text")), new StandardAnalyzer(Net.Util.Version.LUCENE_30));

Where in Term constructor field "ID" is my unique field with no index flag and "5" is text of old value field "ID" in old document in index.