在代码中使Lucene.Net线程安全

Question

我正在使用Lucene.Net进行搜索,并想知道如何处理这个线程问题.

我有一个类Test的实例,但搜索器在这种情况下不是线程安全的,因为定时器线程可以在提供请求的同时更新索引,并且我确实看到了异常.关于如何使其线程安全的任何指针.

public class Test 
{
    private static object syncObj = new object();

    private System.Threading.Timer timer;

    private Searcher searcher;

    private RAMDirectory idx = new RAMDirectory();

    public Test()
    {
        this.timer = new System.Threading.Timer(this.Timer_Elapsed, null, TimeSpan.Zero, TimeSpan.FromMinutes(3));
    }


    private Searcher ESearcher
    {
        get
        {
            return this.searcher;
        }

        set
        {
            lock (syncObj)
            {
                this.searcher = value;
            }
        }
    }

    public Document CreateDocument(string title, string content)
    {
        Document doc = new Document();
        doc.Add(new Field("A", title, Field.Store.YES, Field.Index.NO));
        doc.Add(new Field("B", content, Field.Store.YES, Field.Index.ANALYZED));
        return doc;
    }

    public List<Document> Search(Searcher searcher, string queryString)
    {
        List<Document> documents = new List<Document>();
        QueryParser parser = new QueryParser(Lucene.Net.Util.Version.LUCENE_30, "B", new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30));
        Query query = parser.Parse(queryString);
        int hitsPerPage = 5;
        TopScoreDocCollector collector = TopScoreDocCollector.Create(2 * hitsPerPage, true);
        this.ESearcher.Search(query, collector);

        ScoreDoc[] hits = collector.TopDocs().ScoreDocs;

        int hitCount = collector.TotalHits > 10 ? 10 : collector.TotalHits;
        for (int i = 0; i < hitCount; i++)
        {
            ScoreDoc scoreDoc = hits[i];
            int docId = scoreDoc.Doc;
            float docScore = scoreDoc.Score;
            Document doc = searcher.Doc(docId);
            documents.Add(doc);
        }

        return documents;
    }

    private void Timer_Elapsed(object sender)
    {
        this.Log("Started Updating the Search Indexing");
        // Get New data to Index
        using (IndexWriter writer = new IndexWriter(this.idx, new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30), true, IndexWriter.MaxFieldLength.LIMITED))
        {
            foreach (var e in es)
            {
                writer.AddDocument(this.CreateDocument(e.Value.ToString(), e.Key));
            }

            writer.Optimize();
        }

        this.ESearcher = new IndexSearcher(this.idx);
        this.Log("Completed Updating the Search Indexing");
    }

    public Result ServeRequest()
    {
        var documents = this.Search(this.EntitySearcher, searchTerm);
        //somelogic
        return result;

    }

}

Answer 1

很多事情都是"错误的".

如前所述,锁定不安全(您需要锁定读取和写入).

更重要的是,在Lucene中有更好的处理方法.首先,IndexWriter它本身就是线程安全的.应该是的所有者Directory.打开/关闭目录的不同部分通常是"不好的做法".

NRT(近实时)索引的样式涉及IndexReader从IW 获取,而不是包装目录.

如果索引基本上是只读的,并且可以每天/每周批量重新生成,那么您的示例中使用的样式实际上只是"好".

我重写了这个例子来展示一些方法.显然,由于这只是测试代码,因此根据用例需要重构/增强的细微差别......

public class Test
{
    private static object syncObj = new object();

    private System.Threading.Timer timer;

    private Searcher searcher;

    private IndexWriter writer;
    private IndexReader reader;

    public Test()
    {
        writer = new IndexWriter(new RAMDirectory(), new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30), true, IndexWriter.MaxFieldLength.LIMITED);
        reader = writer.GetReader();
        searcher = new IndexSearcher(reader);
        timer = new System.Threading.Timer(Timer_Elapsed, null, TimeSpan.Zero, TimeSpan.FromMinutes(3));
    }


    public void CreateDocument(string title, string content)
    {
        var doc = new Document();
        doc.Add(new Field("A", title, Field.Store.YES, Field.Index.NO));
        doc.Add(new Field("B", content, Field.Store.YES, Field.Index.ANALYZED));

        writer.AddDocument(doc);
    }

    public void ReplaceAll(Dictionary<string, string> es)
    {
        // pause timer
        timer.Change(Timeout.Infinite, Timeout.Infinite);

        writer.DeleteAll();
        foreach (var e in es)
        {
            AddDocument(e.Value.ToString(), e.Key);
        }

        // restart timer
        timer.Change(TimeSpan.Zero, TimeSpan.FromMinutes(3));
    }

    public List<Document> Search(string queryString)
    {
        var documents = new List<Document>();
        var parser = new QueryParser(Lucene.Net.Util.Version.LUCENE_30, "B", new StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_30));
        Query query = parser.Parse(queryString);
        int hitsPerPage = 5;
        var collector = TopScoreDocCollector.Create(2 * hitsPerPage, true);
        searcher.Search(query, collector);

        ScoreDoc[] hits = collector.TopDocs().ScoreDocs;

        int hitCount = collector.TotalHits > 10 ? 10 : collector.TotalHits;
        for (int i = 0; i < hitCount; i++)
        {
            ScoreDoc scoreDoc = hits[i];
            int docId = scoreDoc.Doc;
            float docScore = scoreDoc.Score;
            Document doc = searcher.Doc(docId);
            documents.Add(doc);
        }

        return documents;
    }

    private void Timer_Elapsed(object sender)
    {
        if (reader.IsCurrent())
            return;

        reader = writer.GetReader();
        var newSearcher = new IndexSearcher(reader);
        Interlocked.Exchange(ref searcher, newSearcher);
        Debug.WriteLine("Searcher updated");
    }

    public Result ServeRequest(string searchTerm)
    {
        var documents = Search(searchTerm);
        //somelogic
        var result = new Result();

        return result;

    }
}

注意:

• 作家"拥有"该目录
• 如果这是一个文件库目录,那么你将拥有Open和Close创建/处理编写器(处理lock文件处理)的方法.RamDirectory可以只是GC'd
• 使用Interlocked.Exchange而不是lock.因此使用searcher会员时零成本(这里是龙!)
• 新文档直接添加到作者
• IsCurrent()如果没有添加新文档,则允许零成本.根据您添加文档的频率,您可能根本不需要计时器(只需调用Timer_Elapsed- 显然重命名 - 位于顶部Search).
• 不要使用Optimize()它是以前版本的宿醉,并且非常不鼓励使用它(性能和磁盘I/O原因)

最后,如果您使用的是Lucene.net v4.8,那么您应该使用SearcherManager(如另一个答案所示).但是使用ctor并将其IndexWriter保持为"单身"(与范围相同writer).它将为您处理锁定和获取新读者.