ElasticSearch - choosing a different result for a simple query query and aggregation (NEST)

I have a search page that contains two types of search results: final result and specific result.

  • The final result page contains the top 3 results for each category (top hits)
  • The concrete results page contains all the results for the selected category.

To get the Summary page, I use the query:

var searchDescriptor = new SearchDescriptor<ElasticType>();
searchDescriptor.Index("index_name")
    .Query(q =>
      q.MultiMatch(m => m
        .Fields(fs => fs
          .Field(f => f.Content1, 3)
          .Field(f => f.Content2, 2)
          .Field(f => f.Content3, 1))
        .Fuzziness(Fuzziness.EditDistance(1))
        .Query(query)
        .Boost(1.1)
        .Slop(2)
        .PrefixLength(1)
        .MaxExpansions(100)
        .Operator(Operator.Or)
        .MinimumShouldMatch(2)
        .FuzzyRewrite(RewriteMultiTerm.ConstantScoreBoolean)
        .TieBreaker(1.0)
        .CutoffFrequency(0.5)
        .Lenient()
        .ZeroTermsQuery(ZeroTermsQuery.All))
    && (q.Terms(t => t.Field(f => f.LanguageId).Terms(1)) || q.Terms(t => t.Field(f => f.LanguageId).Terms(0))))
    .Aggregations(a => a
      .Terms("category", tagd => tagd
        .Field(f => f.Category)
        .Size(10)
        .Aggregations(aggs => aggs.TopHits("top_tag_hits", t => t.Size(3)))))
    .FielddataFields(fs => fs
      .Field(p => p.Content1, 3)
      .Field(p => p.Content2, 2)
      .Field(p => p.Content3, 1));

var elasticResult = _elasticClient.Search<ElasticType>(_ => searchDescriptor);

And I get a result like

{
    "aggregations": {
        "category": {
            "doc_count_error_upper_bound": 0,
            "sum_other_doc_count": 0,
            "buckets": [{
                "key": "category1",
                "doc_count": 40,
                "top_tag_hits": {
                    "hits": {
                        "total": 40,
                        "max_score": 5.4,
                        "hits": [{
                            "_index": "...",
                            "_type": "...",
                            "_id": "...",
                            "_score": 5.4,
                            "_source": {
                                "id": 1
                            }
                        },
                        {
                            "_index": "...",
                            "_type": "...",
                            "_id": "...",
                            "_score": 4.3,
                            "_source": {
                                "id": 3 // FAIL!
                            }
                        },
                        {
                            "_index": "...",
                            "_type": "...",
                            "_id": "...",
                            "_score": 4.3,
                            "_source": {
                                "id": 2
                            }
                        }]
                    }
                }
            }]
        }
    }
}

So, I get a few hits with the same _score.

To get a specific results page (by category), I use the query:

var searchDescriptor = new SearchDescriptor<ElasticType>();
searchDescriptor.Index("index_name")
    .Size(perPage <= 0 ? 100 : perPage)
    .From(page * perPage)
    .Query(q => q
      .MultiMatch(m => m
         .Fields(fs => fs
           .Field(f => f.Content1, 3)
           .Field(f => f.Content2, 2)
           .Field(f => f.Content3, 1)
           .Field(f => f.Category))
         .Fuzziness(Fuzziness.EditDistance(1))
         .Query(searchRequest.Query)
         .Boost(1.1)
         .Slop(2)
         .PrefixLength(1)
         .MaxExpansions(100)
         .Operator(Operator.Or)
         .MinimumShouldMatch(2)
         .FuzzyRewrite(RewriteMultiTerm.ConstantScoreBoolean)
         .TieBreaker(1.0)
         .CutoffFrequency(0.5)
         .Lenient()
         .ZeroTermsQuery(ZeroTermsQuery.All))
      && q.Term(t => t.Field(f => f.Category).Value(searchRequest.Category))
      && (q.Terms(t => t.Field(f => f.LanguageId).Terms(1)) || q.Terms(t => t.Field(f => f.LanguageId).Terms(0))))
    .FielddataFields(fs => fs
      .Field(p => p.Content1, 3)
      .Field(p => p.Content2, 2)
      .Field(p => p.Content3, 1))
    .Aggregations(a => a
      .Terms("category", tagd => tagd
        .Field(f => f.Category)));

And the result is something like this:

{
    "hits": {
        "total": 40,
        "max_score": 7.816723,
        "hits": [{
            "_index": "...",
            "_type": "...",
            "_id": "...",
            "_score": 7.816723,
            "_source": {
                "id": 1
            }
        },
        {
            "_index": "...",
            "_type": "...",
            "_id": "...",
            "_score": 6.514713,
            "_source": {
                "id": 2
            }
        },
        {
            "_index": "...",
            "_type": "...",
            "_id": "...",
            "_score": 6.514709,
            "_source": {
                "id": 3
            }
        }]
    }
}

, _score , . _score, , .

- , ? ? , ?

elasticsearch "5.3.0" NEST "5.0.0".

Update: :

{
    "fielddata_fields": [
        "content1^3",
        "content2^2",
        "content3^1"
    ],
    "aggs": {
        "category": {
            "terms": {
                "field": "category",
                "size": 10
            },
            "aggs": {
                "top_tag_hits": {
                    "top_hits": {
                        "size": 3
                    }
                }
            }
        }
    },
    "query": {
        "bool": {
            "must": [
                {
                    "multi_match": {
                        "boost": 1.1,
                        "query": "sparta",
                        "fuzzy_rewrite": "constant_score_boolean",
                        "fuzziness": 1,
                        "cutoff_frequency": 0.5,
                        "prefix_length": 1,
                        "max_expansions": 100,
                        "slop": 2,
                        "lenient": true,
                        "tie_breaker": 1.0,
                        "minimum_should_match": 2,
                        "operator": "or",
                        "fields": [
                            "content1^3",
                            "content2^2",
                            "content3^1"
                        ],
                        "zero_terms_query": "all"
                    }
                },
                {
                    "bool": {
                        "should": [
                            {
                                "terms": {
                                    "languageId": [
                                        1
                                    ]
                                }
                            },
                            {
                                "terms": {
                                    "languageId": [
                                        0
                                    ]
                                }
                            }
                        ]
                    }
                }
            ]
        }
    }
}

:

{
    "from": 0,
    "size": 100,
    "fielddata_fields": [
        "content1^3",
        "content2^2",
        "content3^1"
    ],
    "aggs": {
        "category": {
            "terms": {
                "field": "category"
            }
        }
    },
    "query": {
        "bool": {
            "must": [
                {
                    "bool": {
                        "must": [
                            {
                                "multi_match": {
                                    "boost": 1.1,
                                    "query": ".....",
                                    "fuzzy_rewrite": "constant_score_boolean",
                                    "fuzziness": 1,
                                    "cutoff_frequency": 0.5,
                                    "prefix_length": 1,
                                    "max_expansions": 100,
                                    "slop": 2,
                                    "lenient": true,
                                    "tie_breaker": 1.0,
                                    "minimum_should_match": 2,
                                    "operator": "or",
                                    "fields": [
                                        "content1^3",
                                        "content2^2",
                                        "content3^1",
                                        "category"
                                    ],
                                    "zero_terms_query": "all"
                                }
                            },
                            {
                                "term": {
                                    "category": {
                                        "value": "category1"
                                    }
                                }
                            }
                        ]
                    }
                },
                {
                    "bool": {
                        "should": [
                            {
                                "terms": {
                                    "languageId": [
                                        1
                                    ]
                                }
                            },
                            {
                                "terms": {
                                    "languageId": [
                                        0
                                    ]
                                }
                            }
                        ]
                    }
                }
            ]
        }
    }
}

:

var descriptor = new CreateIndexDescriptor(indexName)
    .Mappings(ms => ms
     .Map<ElasticType>(m => m
       .Properties(ps => ps
         .Keyword(s => s.Name(ecp => ecp.Title))
         .Text(s => s.Name(ecp => ecp.Content1))
         .Text(s => s.Name(ecp => ecp.Content2))
         .Text(s => s.Name(ecp => ecp.Content3))
         .Date(s => s.Name(ecp => ecp.Date))
         .Number(s => s.Name(ecp => ecp.LanguageId).Type(NumberType.Integer))
         .Keyword(s => s.Name(ecp => ecp.Category))
         .Text(s => s.Name(ecp => ecp.PreviewImageUrl).Index(false))
         .Text(s => s.Name(ecp => ecp.OptionalContent).Index(false))
         .Text(s => s.Name(ecp => ecp.Url).Index(false)))));

    _elasticClient.CreateIndex(indexName, _ => descriptor);
+6
1

.

  • , , must should must bool.

    , , must

    () ​​ .

    , . , , .

    should, must, Elasticsearch .

  • - , ?

    'explain': true . , .

  • ?

    , Elasticsearch , .

:

, should . .

, , should, , . :

{
  "from": 0,
  "size": 10,
  "_source": [
    "content1^3",
    "content2^2",
    "content3^1"
  ],
  "query": {
    "bool": {
      "should": [
        {
          "match": {
            "languageId": 1
          }
        },
        {
          "match": {
            "languageId": 0
          }
        }
      ],
      "must": [
        {
          "multi_match": {
            "boost": 1.1,
            "query": ".....",
            "fuzzy_rewrite": "constant_score_boolean",
            "fuzziness": 1,
            "cutoff_frequency": 0.5,
            "prefix_length": 1,
            "max_expansions": 100,
            "slop": 2,
            "lenient": true,
            "tie_breaker": 1,
            "minimum_should_match": 2,
            "operator": "or",
            "fields": [
              "content1^3",
              "content2^2",
              "content3^1",
              "category"
            ],
            "zero_terms_query": "all"
          }
        }
      ]
    }
  }
}

{
  "size": 0,
  "query": {
    "bool": {
      "should": [
        {
          "match": {
            "languageId": 1
          }
        },
        {
          "match": {
            "languageId": 0
          }
        }
      ],
      "must": [
        {
          "multi_match": {
            "boost": 1.1,
            "query": ".....",
            "fuzzy_rewrite": "constant_score_boolean",
            "fuzziness": 1,
            "cutoff_frequency": 0.5,
            "prefix_length": 1,
            "max_expansions": 100,
            "slop": 2,
            "lenient": true,
            "tie_breaker": 1,
            "minimum_should_match": 2,
            "operator": "or",
            "fields": [
              "content1^3",
              "content2^2",
              "content3^1",
              "category"
            ],
            "zero_terms_query": "all"
          }
        }
      ]
    }
  },
  "aggs": {
    "categories": {
      "terms": {
        "field": "category",
        "size": 10
      },
      "aggs": {
        "produdtcs": {
          "top_hits": {
            "_source": [
              "content1^3",
              "content2^2",
              "content3^1"
            ],
            "size": 3
          }
        }
      }
    }
  }
}
+3

All Articles