c# - 列表项上的ElasticSearch聚合

Question

如何按列表项(哈希文本)进行汇总

这是我的代码

public class Tweet
{
     public ulong id { get; set; }
     public string text { get; set; }
     [Nest.Nested]
     public List<hashtags> hashtags { get; set; }
}


public class hashtags
{ 
     public string hashtext { get; set; } 
}

我的索引数据示例如下:

 "hashtags" : [
        {
          "hashtext" : "aaaa"
        },
        {
          "hashtext" : "bbbb"
        },
        {
          "hashtext" : "ccccc"
        }
      ],
    }



.Aggregations(childAggs => childAggs
                .Nested("project_tags", n => n
                    .Path(p => p.hashtags)
                    .Aggregations(nestedAggs => nestedAggs
                        .Terms("by_tags", t => t
                            .Field(f => f.hashtags.First().hashtext)
                    )
                )
            ))

如何仅对哈希文本属性进行聚合查询
例如我想获取所有带有计数的哈希文本

aaaa     3   times 
ccccc    5  times

Answer 1

只要将hashtext上的hashtags映射为keyword数据类型(或使用fielddata enabled映射为text数据类型，并附带相应的注意事项)，您所拥有的将起作用。

这是一个有效的例子

private static void Main()
{
    var defaultIndex = "my_index";
    var pool = new SingleNodeConnectionPool(new Uri("http://localhost:9200"));

    var settings = new ConnectionSettings(pool)
        .DefaultIndex(defaultIndex);

    var client = new ElasticClient(settings);

    if (client.IndexExists(defaultIndex).Exists)
        client.DeleteIndex(defaultIndex);

    var createIndexResponse = client.CreateIndex(defaultIndex, c => c
        .Mappings(m => m
            .Map<Tweet>(mm => mm
                .AutoMap()
            )
        )
    );

    var bulkResponse = client.Bulk(b => b
        .IndexMany(new []
        {
            new Tweet 
            { 
                id = 1, 
                text = "foo",
                hashtags = new List<hashtags>
                { 
                    new hashtags { hashtext = "aaaa" },
                    new hashtags { hashtext = "bbbb" },
                    new hashtags { hashtext = "cccc" }
                }
            }, 
            new Tweet
            {
                id = 2,
                text = "bar",
                hashtags = new List<hashtags>
                {
                    new hashtags { hashtext = "aaaa" },
                    new hashtags { hashtext = "bbbb" }
                }
            },
            new Tweet
            {
                id = 3,
                text = "baz",
                hashtags = new List<hashtags>
                {
                    new hashtags { hashtext = "aaaa" },
                    new hashtags { hashtext = "cccc" }
                }
            }
        })
        .Refresh(Refresh.WaitFor)
    );

    var searchResponse = client.Search<Tweet>(s => s
        .Size(0)
        .Aggregations(childAggs => childAggs
                .Nested("hashtags", n => n
                    .Path(p => p.hashtags)
                    .Aggregations(nestedAggs => nestedAggs
                        .Terms("by_tags", t => t
                            .Field(f => f.hashtags.First().hashtext)
                        )
                    )
                )
            )
        );

    var hashtagBuckets = searchResponse.Aggregations.Nested("hashtags").Terms("by_tags").Buckets;

    foreach(var bucket in hashtagBuckets)
    {
        Console.WriteLine($"{bucket.Key}\t{bucket.DocCount} times");
    }
}

public class Tweet
{
    public ulong id { get; set; }
    public string text { get; set; }
    [Nested]
    public List<hashtags> hashtags { get; set; }
}


public class hashtags
{
    [Keyword]
    public string hashtext { get; set; }
}

将以下内容写入控制台

aaaa  3 times
bbbb  2 times
cccc  2 times