c# - Lucene.NET:如何使用 BlockJoinQuery？

Question

我正在尝试使用 Lucene.NET 4.8 进行关系搜索(实际上我是使用 latest sources 编译的)，方法是遵循 this post .我引用了 Lucene.Net、Lucene.Net.Analysis.Common、Lucene.Net.Grouping、Lucene.Net.Join 和 Lucene.Net.QueryParser。

问题是:我没有得到任何结果。在我下面的示例中，我认为 blog 是 parent 而 comments 是 children。我想找到一个包含 first 且评论包含 like 的博客(即带有 Id 1 的评论)。

如何修复此示例代码？

    static void BlockJoinQueryTest(string dbFolder)
    {
        var analyzer = new StandardAnalyzer(LuceneVersion.LUCENE_48);
        var config = new IndexWriterConfig(LuceneVersion.LUCENE_48, analyzer);
        config.SetOpenMode(IndexWriterConfig.OpenMode_e.CREATE_OR_APPEND);

        var indexPathBlog = dbFolder + "\\blog_db";
        if (System.IO.Directory.Exists(indexPathBlog))
        {
            System.IO.Directory.Delete(indexPathBlog, true);
        }
        System.IO.Directory.CreateDirectory(indexPathBlog);
        var indexDirectoryBlog = FSDirectory.Open(new System.IO.DirectoryInfo(indexPathBlog));
        var indexWriterBlog = new IndexWriter(indexDirectoryBlog, config);

        Document comment = new Document();
        comment.Add(new TextField("BlogId", "1", Field.Store.YES));
        comment.Add(new TextField("CommentContent", "I like your first blog!", Field.Store.YES));
        comment.Add(new TextField("Type", "comment", Field.Store.YES));
        comment.Add(new TextField("Note", "child", Field.Store.YES));
        indexWriterBlog.AddDocument(comment);

        comment = new Document();
        comment.Add(new TextField("BlogId", "1", Field.Store.YES));
        comment.Add(new TextField("CommentContent", "Not that great.", Field.Store.YES));
        comment.Add(new TextField("Type", "comment", Field.Store.YES));
        comment.Add(new TextField("Note", "child", Field.Store.YES));
        indexWriterBlog.AddDocument(comment);

        Document blog = new Document();
        blog.Add(new TextField("Id", "1", Field.Store.YES));
        blog.Add(new TextField("BlogContent", "Content of first blog", Field.Store.YES));
        blog.Add(new TextField("Type", "blog", Field.Store.YES));
        blog.Add(new TextField("Note", "parent", Field.Store.YES));
        indexWriterBlog.AddDocument(blog);

        blog = new Document();
        blog.Add(new TextField("Id", "2", Field.Store.YES));
        blog.Add(new TextField("BlogContent", "This is the second blog!", Field.Store.YES));
        blog.Add(new TextField("Type", "blog", Field.Store.YES));
        blog.Add(new TextField("Note", "parent", Field.Store.YES));
        indexWriterBlog.AddDocument(blog);

        indexWriterBlog.Commit();

        var searcher = new IndexSearcher(DirectoryReader.Open(indexDirectoryBlog));

        Console.WriteLine("Begin content enumeration:");
        for (int i = 0; i < searcher.IndexReader.MaxDoc; i++)
        {
            var doc = searcher.IndexReader.Document(i);
            Console.WriteLine("Document " + i + ": " + doc.ToString());
        }
        Console.WriteLine("End content enumeration.");

        Filter blogs = new CachingWrapperFilter(
                new QueryWrapperFilter(
                  new TermQuery(
                    new Term("Type", "blog"))));
        BooleanQuery commentQuery = new BooleanQuery();
        commentQuery.Add(new TermQuery(new Term("CommentContent", "like")), BooleanClause.Occur.MUST);
        //commentQuery.Add(new TermQuery(new Term("BlogId", "1")), BooleanClause.Occur.MUST);

        var commentJoinQuery = new ToParentBlockJoinQuery(
            commentQuery,
            blogs,
            ScoreMode.None);

        BooleanQuery query = new BooleanQuery();
        query.Add(new TermQuery(new Term("BlogContent", "first")), BooleanClause.Occur.MUST);
        query.Add(commentQuery, BooleanClause.Occur.MUST);
        var c = new ToParentBlockJoinCollector(
            Sort.RELEVANCE, // sort
            10,             // numHits
            true,           // trackScores
            false           // trackMaxScore
            );
        searcher.Search(query, c);
        int maxDocsPerGroup = 10;
        var hits = c.GetTopGroups(
            commentJoinQuery,
            Sort.INDEXORDER,
            0,   // offset
            maxDocsPerGroup,  // maxDocsPerGroup
            0,   // withinGroupOffset
            true // fillSortFields
          );
        if (hits != null)
        {
            Console.WriteLine("Found " + hits.TotalGroupCount + " groups:");
            for (int i = 0; i < hits.TotalGroupCount; i++)
            {
                var group = hits.Groups[i];
                Console.WriteLine("Group " + i + ": " + group.ToString());

                for (int j = 0; j < group.TotalHits && j < maxDocsPerGroup; j++)
                {
                    Document doc = searcher.Doc(group.ScoreDocs[j].Doc);
                    Console.WriteLine("Hit " + i + ": " + doc.ToString());
                }
            }
        }
        else
        {
            Console.WriteLine("No hits.");
        }

        Console.WriteLine("Done.");

Answer 1

难道您不必一次性添加 Documents 作为 IEnumerable 以便它们被“阻止”吗？

http://blog.mikemccandless.com/2012/01/searching-relational-content-with.html解释更多

编辑:

我试着用下面的代码来做这件事，但似乎也不起作用，如果有人能解释一下，我将不胜感激？

        var analyzer = new StandardAnalyzer(LuceneVersion.LUCENE_48);
        var config = new IndexWriterConfig(LuceneVersion.LUCENE_48, analyzer);
        config.SetOpenMode(IndexWriterConfig.OpenMode_e.CREATE_OR_APPEND);

        var indexPathBlog = "D:\\Test";
        if (System.IO.Directory.Exists(indexPathBlog))
        {
            System.IO.Directory.Delete(indexPathBlog, true);
        }

        System.IO.Directory.CreateDirectory(indexPathBlog);
        var indexDirectoryBlog = FSDirectory.Open(new System.IO.DirectoryInfo(indexPathBlog));
        var indexWriterBlog = new IndexWriter(indexDirectoryBlog, config);

        var one = new List<Document>();
        var two = new List<Document>();

        var blogOne = new Document();
        blogOne.Add(new TextField("Id", "1", Field.Store.YES));
        blogOne.Add(new TextField("BlogContent", "Content of first blog", Field.Store.YES));
        blogOne.Add(new TextField("Type", "blog", Field.Store.YES));
        blogOne.Add(new TextField("Note", "parent", Field.Store.YES));
        one.Add(blogOne);

        Document commentOne = new Document();
        commentOne.Add(new TextField("BlogId", "1", Field.Store.YES));
        commentOne.Add(new TextField("CommentContent", "I like your first blog!", Field.Store.YES));
        commentOne.Add(new TextField("Type", "comment", Field.Store.YES));
        commentOne.Add(new TextField("Note", "child", Field.Store.YES));
        one.Add(commentOne);

        Document blogTwo = new Document();
        blogTwo.Add(new TextField("Id", "2", Field.Store.YES));
        blogTwo.Add(new TextField("BlogContent", "This is the second blog!", Field.Store.YES));
        blogTwo.Add(new TextField("Type", "blog", Field.Store.YES));
        blogTwo.Add(new TextField("Note", "parent", Field.Store.YES));
        two.Add(blogTwo);

        var commentTwo = new Document();
        commentTwo.Add(new TextField("BlogId", "2", Field.Store.YES));
        commentTwo.Add(new TextField("CommentContent", "Not that great.", Field.Store.YES));
        commentTwo.Add(new TextField("Type", "comment", Field.Store.YES));
        commentTwo.Add(new TextField("Note", "child", Field.Store.YES));
        two.Add(commentTwo);

        indexWriterBlog.AddDocuments(one);
        indexWriterBlog.AddDocuments(two);

        indexWriterBlog.Commit();

        var searcher = new IndexSearcher(DirectoryReader.Open(indexDirectoryBlog));

        Filter parentQuery = 
                new QueryWrapperFilter(
                  new TermQuery(
                    new Term("type", "blog")));

        BooleanQuery childQuery = new BooleanQuery();
        childQuery.Add(new TermQuery(new Term("CommentContent", "I like your first blog!")), BooleanClause.Occur.MUST);

        var commentJoinQuery = new ToParentBlockJoinQuery(
            childQuery,
            parentQuery,
            ScoreMode.None);

        BooleanQuery query = new BooleanQuery();
        //query.Add(new TermQuery(new Term("Type", "blog")), BooleanClause.Occur.MUST);
        query.Add(commentJoinQuery, BooleanClause.Occur.MUST);

        var c = new ToParentBlockJoinCollector(
            Sort.RELEVANCE, // sort
            10,             // numHits
            false,           // trackScores
            false           // trackMaxScore
            );

        searcher.Search(commentJoinQuery, c);

        int maxDocsPerGroup = 10;
        var hits = c.GetTopGroups(
            commentJoinQuery,
            Sort.INDEXORDER,
            0,   // offset
            maxDocsPerGroup,  // maxDocsPerGroup
            0,   // withinGroupOffset
            true // fillSortFields
          );

        if (hits != null)
        {
            Console.WriteLine("Found " + hits.TotalGroupCount + " groups:");
            for (int i = 0; i < hits.TotalGroupCount; i++)
            {
                var group = hits.Groups[i];
                Console.WriteLine("Group " + i + ": " + group.ToString());

                for (int j = 0; j < group.TotalHits && j < maxDocsPerGroup; j++)
                {
                    Document doc = searcher.Doc(group.ScoreDocs[j].Doc);
                    Console.WriteLine("Hit " + i + ": " + doc.ToString());
                }
            }
        }
        else
        {
            Console.WriteLine("No hits.");
        }

        Console.WriteLine("Done.");