使用Elasticsearch C#Mpdreamz / NEST客户端在嵌套字段上进行构面

时间:2012-11-04 12:03:49

标签: elasticsearch nest

如何使用Mpdreamz / NEST Elasticsearch客户端基于嵌套字段的属性列出构面?

我查看了Nest文档,但目前尚不清楚如何操作。

这是我尝试过的代码:

using System;
using System.Collections.Generic;
using System.Linq;
using Nest;

namespace Demo
{
    class Program
    {
        public class Movie
        {
            public int Id { get; set; }
            public string Title { get; set; }
            public string Description { get; set; }
            [ElasticProperty(Index = FieldIndexOption.analyzed, Type = FieldType.nested)]
            public List<Genre> Genres { get; set; }
            public int Year { get; set; }
        }

        public class Genre
        {
            //        public int Id { get; set; }
            [ElasticProperty(Index = FieldIndexOption.analyzed)]
            public string GenreTitle { get; set; }
        }

        static void Main(string[] args)
        {
            var setting = new ConnectionSettings("localhost", 9200);
            setting.SetDefaultIndex("default_index");
            var client = new ElasticClient(setting);

            // delete previous index with documents
            client.DeleteIndex<Movie>();

            // put documents to the index
            var genres = new List<Genre>();
            for (var i = 0; i < 100; i++)
                genres.Add(new Genre { GenreTitle = string.Format("Genre {0}", i) });
            for (var i = 0; i < 1000; i++)
            {
                client.Index(new Movie
                {
                    Id = i,
                    Description = string.Format("Some movie description {0}", i),
                    Title = string.Format("Movie Title {0}", i),
                    Year = 1980 + (i % 10),
                    Genres = genres.OrderBy(x => Guid.NewGuid()).Take(10).ToList()
                });
            }

            // query with facet on nested field property genres.genreTitle
            var queryResults = client.Search<Movie>(x => x
                    .From(0)
                    .Size(10)
                    .MatchAll()
                    .FacetTerm(t => t
                        .OnField(f => f.Year)
                        .Size(30))
                    .FacetTerm(t => t
                        .Size(5)
                        .OnField(f => f.Genres.Select(f1 => f1.GenreTitle) )
                    )
            );

            var yearFacetItems = queryResults.FacetItems<FacetItem>(p => p.Year);
            foreach (var item in yearFacetItems)
            {
                var termItem = item as TermItem;
                Console.WriteLine(string.Format("{0} ({1})", termItem.Term, termItem.Count));
            }
            /* Returns:
            1989 (90)
            1988 (90)
            1986 (90)
            1984 (90)
            1983 (90)
            1981 (90)
            1980 (90)
            1987 (89)
            1982 (89)
            1985 (88)
            and it's fine! */

            var genresFacetItems = queryResults.FacetItems<FacetItem>(p => p.Genres.Select(f => f.GenreTitle));
            foreach (var item in genresFacetItems)
            {
                var termItem = item as TermItem;
                Console.WriteLine(string.Format("{0} ({1})", termItem.Term, termItem.Count));
            }
            /* Return soemthing:
            genre (842)
            98 (47)
            51 (30)
            24 (29)
            46 (28)
            and it's BAD! 
            I expect the Genre Title to be listed as 
            string, not as some strange integer */
        }
    }
}

由于方面的结果,我得到了:

  • genre(842)
  • 98(47)
  • 51(30)
  • 24(29)
  • 46(28)

虽然我希望得到类似的东西:

  • 类型1(842)
  • 类型2(47)
  • 类型3(30)
  • 类型4(29)
  • 类型5(28)

我做错了什么?在哪里检查在Nest中使用嵌套字段的正确方法及其上的方面?

谢谢。

更新1:

我发现它与tokenizer / analyzer有关。如果流派名称没有空格或破折号 - 一切正常。 我也尝试过未分析的索引属性

[ElasticProperty(Index = FieldIndexOption.not_analyzed)]
public string GenreTitle { get; set; }

但它没有帮助

更新2: 我之前的索引删除后添加了流畅的索引映射而不是注释,如:

var settings = new IndexSettings();
            var typeMapping = new TypeMapping("movies");
            var type = new TypeMappingProperty
            {
                Type = "string",
                Index = "not_analyzed",
                Boost = 2.0
                // Many more options available
            };
            typeMapping.Properties = new Dictionary<string, TypeMappingProperty>();
            typeMapping.Properties.Add("genres.genreTitle", type);
            settings.Mappings.Add(typeMapping);
            client.CreateIndex("default_index", settings);

现在不确定注释有什么问题。是否需要使用注释进行索引设置?

1 个答案:

答案 0 :(得分:9)

你好NEST的作者,

如果使用注释,则需要手动调用

var createIndex = client.CreateIndex("default_index", new IndexSettings { });
client.Map<Movie>();

在第一次调用索引之前。 Nest不会在每个索引调用上应用映射,因为这会产生太多的开销。如果索引不存在而且不需要CreateIndex调用,那么旧版本的elasticsearch就会创建索引。

由于您希望在嵌套类型上进行构面,因此必须将.Nested("genres")传递给构面调用。

您看到的数字实际上是嵌套的docids:)

这是我修改过的program.cs:

using System;
using System.Collections.Generic;
using System.Linq;
using Nest;

namespace Demo
{
  class Program
  {
    public class Movie
    {
      public int Id { get; set; }
      public string Title { get; set; }
      public string Description { get; set; }
      [ElasticProperty(Type=FieldType.nested)]
      public List<Genre> Genres { get; set; }
      public int Year { get; set; }
    }

    public class Genre
    {
      //        public int Id { get; set; }
      [ElasticProperty(Index = FieldIndexOption.not_analyzed)]
      public string GenreTitle { get; set; }
    }

    static void Main(string[] args)
    {
      var setting = new ConnectionSettings("localhost", 9200);
      setting.SetDefaultIndex("default_index");
      var client = new ElasticClient(setting);

      // delete previous index with documents
      client.DeleteIndex<Movie>();

      var createIndexResult = client.CreateIndex("default_index", new IndexSettings { });
      var mapResult = client.Map<Movie>();

      // put documents to the index
      var genres = new List<Genre>();
      for (var i = 0; i < 100; i++)
        genres.Add(new Genre { GenreTitle = string.Format("Genre {0}", i) });
      for (var i = 0; i < 1000; i++)
      {
        client.Index(new Movie
        {
          Id = i,
          Description = string.Format("Some movie description {0}", i),
          Title = string.Format("Movie Title {0}", i),
          Year = 1980 + (i % 10),
          Genres = genres.OrderBy(x => Guid.NewGuid()).Take(10).ToList()
        });
      }

      // query with facet on nested field property genres.genreTitle
      var queryResults = client.Search<Movie>(x => x
              .From(0)
              .Size(10)
              .MatchAll()
              .FacetTerm(t => t
                  .OnField(f => f.Year)
                  .Size(30))
              .FacetTerm(t => t
                  .Size(5)
                  .OnField(f => f.Genres.Select(f1 => f1.GenreTitle))
                  .Nested("genres")
              )
      );

      var yearFacetItems = queryResults.FacetItems<FacetItem>(p => p.Year);
      foreach (var item in yearFacetItems)
      {
        var termItem = item as TermItem;
        Console.WriteLine(string.Format("{0} ({1})", termItem.Term, termItem.Count));
      }

      var genresFacetItems = queryResults.FacetItems<FacetItem>(p => p.Genres.Select(f => f.GenreTitle));
      foreach (var item in genresFacetItems)
      {
        var termItem = item as TermItem;
        Console.WriteLine(string.Format("{0} ({1})", termItem.Term, termItem.Count));
      }

    }
  }
}