Elasticsearch 在热门点击聚合中按字段排序

Question

我正在尝试按搜索查询 Elasticsearch 中的 top_hits 参数对数据进行排序，但不知何故它没有影响任何内容。谁能帮我解决这个问题吗？

所以我尝试使用排序，就像有些人这样说的：

{
    "size" : 0,
    "from" : 0,
    "aggs": {
        "by_filter": {
            "filter": {
                "bool": {
                    "must": [
                    {
                        "range": {
                            "published_at": {
                                "gte": "2019-08-01 00:00:00",
                                "lte": "2023-10-30 23:59:59"
                            }
                        }
                    },
                    {
                        "match": {
                            "status": "published"
                        }
                    }
                    ]
                }
            },
            "aggs": {
                "by_created": {
                    "terms": {
                        "field": "created_by.id",
                        "size": 10
                    },
                    "aggs" : {
                        "count_data": {
                            "terms": {
                                "field": "created_by.id"
                            }
                        },
                        "hits": {
                            "top_hits": {
                                "sort": [                         <---- the sort query that I found
                                    {
                                        "created_by.id": {
                                            "order": "desc"
                                        }
                                    }
                                ],
                                "_source":["created_by.id"],
                                "size": 1
                            }
                        }
                    }
                }
            }
        }
    }
}

但结果没有改变:

"aggregations": {
    "by_filter": {
        "doc_count": 21,
        "by_created": {
            "doc_count_error_upper_bound": 0,
            "sum_other_doc_count": 3,
            "buckets": [
                {
                    "key": 34,
                    "doc_count": 3,
                    "hits": {
                        "hits": {
                            "total": {
                                "value": 3,
                                "relation": "eq"
                            },
                            "max_score": null,
                            "hits": [
                                {
                                    "_index": "re_article",
                                    "_id": "53822",
                                    "_score": null,
                                    "_source": {
                                        "created_by": {
                                            "id": 34
                                        }
                                    },
                                    "sort": [                <--- I think this is the result of the sort
                                        34
                                    ]
                                }
                            ]
                        }
                    },
                    "count_data": {
                        "doc_count_error_upper_bound": 0,
                        "sum_other_doc_count": 0,
                        "buckets": [
                            {
                                "key": 34,
                                "doc_count": 3
                            }
                        ]
                    }
                },
                {
                    "key": 52,
                    "doc_count": 3,
                    "hits": {
                        "hits": {
                            "total": {
                                "value": 3,
                                "relation": "eq"
                            },
                            "max_score": null,
                            "hits": [
                                {
                                    "_index": "re_article",
                                    "_id": "338610",
                                    "_score": null,
                                    "_source": {
                                        "created_by": {
                                            "id": 52
                                        }
                                    },
                                    "sort": [
                                        52
                                    ]
                                }
                            ]
                        }
                    },
                    "count_data": {
                        "doc_count_error_upper_bound": 0,
                        "sum_other_doc_count": 0,
                        "buckets": [
                            {
                                "key": 52,
                                "doc_count": 3
                            }
                        ]
                    }
                }
            ]
        }
    }
}

我期望的是存储桶先显示键 52，然后显示键 34，如下所示：

"aggregations": {
    "by_filter": {
        "doc_count": 21,
        "by_created": {
            "doc_count_error_upper_bound": 0,
            "sum_other_doc_count": 3,
            "buckets": [
                {
                    "key": 52,
                    "doc_count": 3,
                    "hits": {
                        "hits": {
                            "total": {
                                "value": 3,
                                "relation": "eq"
                            },
                            "max_score": null,
                            "hits": [
                                {
                                    "_index": "re_article",
                                    "_id": "338610",
                                    "_score": null,
                                    "_source": {
                                        "created_by": {
                                            "id": 52
                                        }
                                    }
                                }
                            ]
                        }
                    },
                    "count_data": {
                        "doc_count_error_upper_bound": 0,
                        "sum_other_doc_count": 0,
                        "buckets": [
                            {
                                "key": 52,
                                "doc_count": 3
                            }
                        ]
                    }
                },
                {
                    "key": 34,
                    "doc_count": 3,
                    "hits": {
                        "hits": {
                            "total": {
                                "value": 3,
                                "relation": "eq"
                            },
                            "max_score": null,
                            "hits": [
                                {
                                    "_index": "re_article",
                                    "_id": "53822",
                                    "_score": null,
                                    "_source": {
                                        "created_by": {
                                            "id": 34
                                        }
                                    }
                                }
                            ]
                        }
                    },
                    "count_data": {
                        "doc_count_error_upper_bound": 0,
                        "sum_other_doc_count": 0,
                        "buckets": [
                            {
                                "key": 34,
                                "doc_count": 3
                            }
                        ]
                    }
                }
            ]
        }
    }
}

我认为我选择了一个错误的例子，因为 top_hits 结果中有新的“排序”字段，但并不是我真正想要的

Answer 1

你已经很接近了，你只需要将

"order"

移动到你真正想要排序的聚合并稍微改变一下语法。

"order"

中的

top_hits

将对

hits

进行排序，如果您想对

by_created

聚合中的键进行排序，则需要将

"order"

添加到该聚合中：

{
    "size" : 0,
    "from" : 0,
    "aggs": {
        "by_filter": {
            "filter": {
                "bool": {
                    "must": [
                    {
                        "range": {
                            "published_at": {
                                "gte": "2019-08-01 00:00:00",
                                "lte": "2023-10-30 23:59:59"
                            }
                        }
                    },
                    {
                        "match": {
                            "status": "published"
                        }
                    }
                    ]
                }
            },
            "aggs": {
                "by_created": {
                    "terms": {
                        "field": "created_by.id",
                        "size": 10,
                        "order": {                      <--- try applying it here
                          "_key": "desc"
                        }
                    },
                    "aggs" : {
                        "count_data": {
                            "terms": {
                                "field": "created_by.id"
                            }
                        },
                        "hits": {
                            "top_hits": {
                                "sort": [                         <---- the sort query that I found
                                    {
                                        "created_by.id": {
                                            "order": "desc"
                                        }
                                    }
                                ],
                                "_source":["created_by.id"],
                                "size": 1
                            }
                        }
                    }
                }
            }
        }
    }
}

您可以在

terms

聚合文档中找到更多选项。如果您需要对其他聚合进行排序，您可能会发现

bucket_sort

聚合很有用。