使用 Elasticsearch 過濾嵌套字段
[英]Filter on nested field with Elasticsearch
問題描述
我的項目、用戶和日程表中有 2 個實體
我需要創建一個頁面，以每周日歷的形式顯示所有員工及其每天的班次
示例： https : //monosnap.com/file/tEb3rUYNRmredPWOdfxRBTBpqkh36H
為此，我創建了一個新索引，其中我為所有員工編制了索引。 每個員工都有一個嵌套字段，用於存儲他的班次
問題是我無法弄清楚聚合和過濾器。
我需要
- 總是有一個按日期過濾，它指的是班次字段屬性。
- 是否有合適的班次並不重要，我們向所有員工展示
- 還會顯示以下 2 個聚合、用戶角色和班次類型。
- 用戶角色過濾員工列表
- 班次類型，顯示或隱藏相關班次
我的請求的一個例子
{
"aggs": {
"shifts.ref_type": {
"nested": {
"path": "shifts"
},
"aggs": {
"shifts.ref_type": {
"terms": {
"field": "shifts.ref_type",
"size": 1000
}
}
}
},
"role": {
"terms": {
"field": "role",
"size": 1000
}
},
"name": {
"terms": {
"field": "name",
"size": 1000
}
}
},
"query": {
"bool": {
"must": [
{
"term": {
"_routing": "1"
}
}
],
"should": [
{
"range": {
"shifts.date_from": {
"lte": 1636923600,
"gte": 1636318800
}
}
}
]
}
},
"sort": [
{
"created": "ASC"
}
],
"size": 1
}
樣本響應
{
"took": 3,
"timed_out": false,
"_shards": {
"total": 4,
"successful": 4,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 36,
"relation": "eq"
},
"max_score": null,
"hits": [
{
"_index": "employee_shift",
"_type": "_doc",
"_id": "a8abf060-25c8-45ee-a50e-02a2e2ad1c40",
"_score": null,
"_routing": "1",
"_source": {
"created": 1633967157,
"type": "user",
"title": null,
"description": "",
"uuid": "a8abf060-25c8-45ee-a50e-02a2e2ad1c40",
"author": "System",
"author:name": "System",
"author:role": "",
"acc": 1,
"property": [
1
],
"status": "Enabled",
"class": [
""
],
"weight": "",
"tags": [],
"language": "en",
"ref_source_id": null,
"ref_source_helper": null,
"ref_property": [
"test hostel2"
],
"ref_property_default": "test hostel2",
"name": "Housekeeper 1",
"role": [
"Housekeeper"
],
"role:weight": "2",
"role:id": [
5
],
"pay_rate": null,
"experience": null,
"supervisor": null,
"gender": null,
"units": [
"102",
"103",
"106",
"107",
"110",
"111",
"116",
"117",
"120",
"121",
"124",
"125",
"128",
"129",
"132",
"133",
"136",
"137"
],
"task_inspection": "All tasks",
"shifts": [
{
"uuid": "f48ae398-0668-4693-b335-2fee3baa2941",
"ref_type": "Work",
"ref_type:color": "",
"date_from": "1635196500",
"date_to": "1635197400",
"notes": null
},
{
"uuid": "8b4d8148-2583-4ccf-a1cc-ae5e6d1e728e",
"ref_type": "Work",
"ref_type:color": "",
"date_from": "1635287400",
"date_to": "1635289200",
"notes": null
},
{
"uuid": "3f5520d8-8108-4abd-8e2a-70c00faf6994",
"ref_type": "Work",
"ref_type:color": "",
"date_from": "1635369300",
"date_to": "1635373800",
"notes": null
},
{
"uuid": "d4009660-447c-47de-b0f3-3c1f2d8d8f99",
"ref_type": "Work",
"ref_type:color": "",
"date_from": "1635286500",
"date_to": "1635288300",
"notes": null
},
{
"uuid": "b3d883f0-b71f-4df7-bb63-a50f137528a4",
"ref_type": "Work",
"ref_type:color": "",
"date_from": "1635370200",
"date_to": "1635372900",
"notes": null
}
]
},
"sort": [
1633967157000
]
}
]
},
"aggregations": {
"role": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "Houseman",
"doc_count": 4
},
{
"key": "Maintenance",
"doc_count": 4
},
{
"key": "Supervisor",
"doc_count": 4
},
{
"key": "Supervisor HSKP",
"doc_count": 4
},
{
"key": "Supervisor Maintenance",
"doc_count": 4
},
{
"key": "Administrator",
"doc_count": 3
},
{
"key": "Concierge dispatcher",
"doc_count": 3
},
{
"key": "Frontdesk",
"doc_count": 3
},
{
"key": "General manager",
"doc_count": 3
},
{
"key": "HKeeper",
"doc_count": 3
},
{
"key": "Housekeeper",
"doc_count": 3
},
{
"key": "Manager",
"doc_count": 3
}
]
},
"shifts.ref_type": {
"doc_count": 21,
"shifts.ref_type": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "Work",
"doc_count": 19
},
{
"key": "test",
"doc_count": 2
}
]
}
},
"name": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "Administrator 123",
"doc_count": 1
},
{
"key": "Administrator 223",
"doc_count": 1
},
{
"key": "Administrator 3",
"doc_count": 1
},
{
"key": "Concierge dispatcher 1",
"doc_count": 1
},
{
"key": "Concierge dispatcher 2",
"doc_count": 1
},
{
"key": "Concierge dispatcher 3",
"doc_count": 1
},
{
"key": "Frontdesk 1",
"doc_count": 1
},
{
"key": "Frontdesk 2",
"doc_count": 1
},
{
"key": "Frontdesk 3",
"doc_count": 1
},
{
"key": "General manager 1",
"doc_count": 1
},
{
"key": "General manager 2",
"doc_count": 1
},
{
"key": "General manager 3",
"doc_count": 1
},
{
"key": "HKeeper 1",
"doc_count": 1
},
{
"key": "HKeeper 2",
"doc_count": 1
},
{
"key": "HKeeper 3",
"doc_count": 1
},
{
"key": "Housekeeper 1",
"doc_count": 1
},
{
"key": "Housekeeper 2",
"doc_count": 1
},
{
"key": "Housekeeper 3",
"doc_count": 1
},
{
"key": "Houseman 1",
"doc_count": 1
},
{
"key": "Houseman 2",
"doc_count": 1
},
{
"key": "Houseman 3",
"doc_count": 1
},
{
"key": "Maintenance 1",
"doc_count": 1
},
{
"key": "Maintenance 2",
"doc_count": 1
},
{
"key": "Maintenance 3",
"doc_count": 1
},
{
"key": "Manager 1222",
"doc_count": 1
},
{
"key": "Manager 2",
"doc_count": 1
},
{
"key": "Manager 3",
"doc_count": 1
},
{
"key": "Supervisor 1",
"doc_count": 1
},
{
"key": "Supervisor 2",
"doc_count": 1
},
{
"key": "Supervisor 3",
"doc_count": 1
},
{
"key": "Supervisor HSKP 1",
"doc_count": 1
},
{
"key": "Supervisor HSKP 2",
"doc_count": 1
},
{
"key": "Supervisor HSKP 3",
"doc_count": 1
},
{
"key": "Supervisor Maintenance 1",
"doc_count": 1
},
{
"key": "Supervisor Maintenance 2",
"doc_count": 1
},
{
"key": "Supervisor Maintenance 3",
"doc_count": 1
}
]
}
}
}
目前，除了一點之外，一切似乎都在正常工作。 按班次類型聚合總是輸出數據，盡管它們不應該被日期的過濾器找到。
有什么建議嗎？ 謝謝你
1 個解決方案
解決方案1
0 2021-11-17 15:08:16
我根據我的評論中的假設做出答案：
- 您希望您的查詢返回所有員工
- 您希望 ref_type 聚合僅包括與您的日期范圍匹配的班次
- 您希望結果下的“班次”集合同樣只包括與您的日期范圍相匹配的班次
如果我誤解了你的問題，我深表歉意。
首先要讓開的一件事是，盡管您可能已經意識到：查詢的should部分不會限制結果，它只會影響分數，因為您已經有了must 。
作為推論，它不會影響聚合結果，為此您需要使用過濾器聚合：
"aggs": {
"shifts.ref_type": {
"nested": {
"path": "shifts"
},
"aggs": {
"shifts.ref_type": {
"filter": {
"range": {
"shifts.date_from": {
"gte": 1635370100,
"lte": 1635370300
}
}
},
"aggs": {
"shifts.ref_type": {
"terms": {
"field": "shifts.ref_type",
"size": 1000
}
}
}
}
}
},
這將為您提供聚合中的過濾計數，但這仍然不會過濾您的結果 - 您將獲得點擊中的所有“變化”。 因此，對於嵌套文檔需要注意的一點是，您的查詢將根據嵌套文檔中的匹配限制返回的文檔，但實際上不會過濾掉不匹配的嵌套文檔。 為了做到這一點，您有另一個功能， 嵌套內部命中，它可以讓您准確找出匹配的嵌套文檔。 在您的情況下，這仍然不夠，因為您不想完全過濾掉結果（因此即使沒有“內部命中”，您仍然希望返回文檔，或者至少讓它成為聚合的一部分）。 所以現在您還有另一個功能， post-filter ，您可以使用它在聚合后過濾文檔。 將兩者結合起來：
"post_filter": {
"nested": {
"path": "shifts",
"query": {
"bool": {
"must": [
{
"range": {
"shifts.date_from": {
"lte": 635370200,
"gte": 635370200
}
}
}
]
}
},
"inner_hits": {}
}
},
如果您現在設置_source: false ，您將不會有命中，您只會得到匹配的班次（然后您的聚合結果中仍然有員工姓名和角色）：
{
"took": 3,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"failed": 0
},
"hits": {
"total": {
"value": 1,
"relation": "eq"
},
"max_score": 0.08701137,
"hits": [
{
"_index": "employee_shift",
"_type": "_doc",
"_id": "-tRnLn0B5PjpsgKgGXlB",
"_score": 0.08701137,
"inner_hits": {
"shifts": {
"hits": {
"total": {
"value": 1,
"relation": "eq"
},
"max_score": 1,
"hits": [
{
"_index": "employee_shift",
"_type": "_doc",
"_id": "-tRnLn0B5PjpsgKgGXlB",
"_nested": {
"field": "shifts",
"offset": 4
},
"_score": 1,
"_source": {
"notes": null,
"ref_type:color": "",
"date_to": 635372900,
"ref_type": "Work",
"uuid": "b3d883f0-b71f-4df7-bb63-a50f137528a4",
"date_from": 635370200
}
}
]
}
}
}
}
]
},
"aggregations": {
"role": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "Housekeeper",
"doc_count": 5
}
]
},
"shifts.ref_type": {
"doc_count": 25,
"shifts.ref_type": {
"doc_count": 4,
"shifts.ref_type": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "Work",
"doc_count": 3
},
{
"key": "Work2",
"doc_count": 1
}
]
}
}
},
"name": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "Housekeeper 4",
"doc_count": 2
},
{
"key": "Housekeeper 1",
"doc_count": 1
},
{
"key": "Housekeeper 2",
"doc_count": 1
},
{
"key": "Housekeeper 3",
"doc_count": 1
}
]
}
}
}
過濾文檔以匹配嵌套Elasticsearch字段中的兩個字段中的一個
[英]Filter document to match either of the two fields in nested elasticsearch field
使用過濾器根據嵌套字段值修改 elasticsearch 分數
[英]Modify elasticsearch score based on nested field value with filter
Rails ElasticSearch Tire - 同時過濾多個參數的嵌套字段
[英]Rails ElasticSearch Tire - filter nested field on multiple parameters the same time
如何在ElasticSearch中使用_index字段包裝帶有過濾器的嵌套查詢？
[英]How to wrap nested query with filter by _index field in ElasticSearch?
聲明:本站的技術帖子網頁，遵循CC BY-SA 4.0協議，如果您需要轉載，請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.
相關問題
如何在 Elasticsearch 過濾器腳本中使用嵌套字段
過濾文檔以匹配嵌套Elasticsearch字段中的兩個字段中的一個
ElasticSearch 2.x存在用於嵌套字段的過濾器不起作用
使用過濾器根據嵌套字段值修改 elasticsearch 分數
Rails ElasticSearch Tire - 同時過濾多個參數的嵌套字段
如何在ElasticSearch中使用_index字段包裝帶有過濾器的嵌套查詢？
ElasticSearch - 過濾嵌套聚合
嵌套數組上的彈性搜索過濾器
Elasticsearch 按嵌套字段過濾
ElasticSearch中的復雜嵌套過濾器
相關標簽