[英]How to access the date_histogram key field in the child aggregation in elasticsearch?
I want to apply some filters on the bucket response generated by the date_histogram
, that filter is dependent on the key of the date_histogram
output buckets.我想对
date_histogram
生成的桶响应应用一些过滤器,该过滤器取决于date_histogram
output 桶的键。
Suppose I have following data in假设我有以下数据
{
"entryTime":"",
"soldTime:""
}
the elastic query is something like this弹性查询是这样的
{
"aggs": {
"date": {
"date_histogram": {
"field": "entryTime",
"interval": "month",
"keyed": true
},
"aggs": {
"filter_try": {
"filter": {
"bool": {
"must": [
{
"range": {
"entryTime": {
"lte": 1588840533000
}
}
},
{
"bool": {
"should": [
{
"bool": {
"must": [
{
"exists": {
"field": "soldTime"
}
},
{
"range": {
"soldTime": {
"gt": 1588840533000
}
}
}
]
}
},
{
"bool": {
"must_not": [
{
"exists": {
"field": "soldTime"
}
}
]
}
}
]
}
}
]
}
}
}
}
}
}
}
so here in that bool query, I want to use the date generated for the specific bucket by date_histogram
aggregation in both the range clauses instead of the hardcoded epoch time.因此,在该布尔查询中,我想在两个范围子句中使用
date_histogram
聚合为特定存储桶生成的日期,而不是硬编码的纪元时间。
Even if we can access using script then also it's fine.即使我们可以使用脚本访问也可以。
for further clarification, this is the boolean query and in the query want to replace this "DATE"
with the date_histogram
bucket key.为了进一步说明,这是 boolean 查询,在查询中想用
date_histogram
桶键替换这个"DATE"
。
# (entryTime < DATE)
# AND
# (
# (soldTime != null AND soldTime > DATE)
# OR
# (soldTime == NULL)
# )
Consider below 10 Document I have:考虑以下我拥有的 10 个文档:
"hits" : [
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "1",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1577869200000",
"soldTime" : "1578646800000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "2",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1578214800000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "3",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1578560400000",
"soldTime" : "1579942800000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "4",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1579683600000",
"soldTime" : "1581325200000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "5",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1580893200000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "6",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1582189200000",
"soldTime" : "1582362000000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "7",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1582621200000",
"soldTime" : "1584349200000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "8",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1583053200000",
"soldTime" : "1583830800000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "9",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1584262800000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "10",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1585472400000"
}
}
]
Now the end of January 2020 in epoch is -> 1580515199000
现在 2020 年 1 月结束的纪元是 ->
1580515199000
So if I apply on the above-mentioned bool query,因此,如果我申请上述布尔查询,
Will get the output as the将获得 output 作为
"hits" : [
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "4",
"_score" : 3.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1579683600000",
"soldTime" : "1581325200000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "2",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1578214800000"
}
}
]
As document with ID 4 satisfy (soldTime != null AND soldTime > DATE)
and document with ID 2 satisfy (soldTime == null)
condition from OR part.由于 ID 为 4 的文档满足
(soldTime != null AND soldTime > DATE)
并且 ID 为 2 的文档满足 OR 部分的(soldTime == null)
条件。
Now for the same bool request If I use the date of end February 2020 -> 1583020799000
, will get the hits as follows现在对于相同的布尔请求如果我使用 2020 年二月结束的日期 ->
1583020799000
,将获得如下点击
"hits" : [
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "7",
"_score" : 3.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1582621200000",
"soldTime" : "1584349200000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "2",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1578214800000"
}
},
{
"_index" : "vi_test",
"_type" : "_doc",
"_id" : "5",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1580893200000"
}
}
]
Now the same data required for each end of the month of a whole year to plot the trend.现在同样的数据需要全年每个月底来plot的走势。
Thank you谢谢
I couldn't find a way using normal queries as parent aggregation key is not available in sub aggregation.我找不到使用普通查询的方法,因为父聚合键在子聚合中不可用。 I have written a script for this which selects documents where soldTime is either null or doesnot fall in same month as entryTime
我为此编写了一个脚本,它选择 soldTime 为 null 或不与 entryTime 同月的文档
Query:
询问:
{
"query": {
"script": {
"script": """
ZonedDateTime entry;
ZonedDateTime sold;
if(doc['entryTime'].size()>0)
{
entry= doc['entryTime'].value;
}
if(doc['soldTime'].size()>0)
{
sold = doc['soldTime'].value;
}
if(sold==null || ( entry.getMonthValue()!==sold.getMonthValue()|| entry.getYear()!==sold.getYear()))
{
return true;
}
else false;
"""
}
},
"size": 10,
"aggs": {
"monthly_trend": {
"date_histogram": {
"field": "entryTime",
"interval": "month"
},
"aggs": {
"docs": {
"top_hits": {
"size": 10
}
}
}
}
}
}
Result:
结果:
"hits" : [
{
"_index" : "index22",
"_type" : "_doc",
"_id" : "55Kv83EB8a54AbXfngYU",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1578214800000"
}
}
]
},
"aggregations" : {
"monthly_trend" : {
"buckets" : [
{
"key_as_string" : "2020-01-01T00:00:00.000Z",
"key" : 1577836800000,
"doc_count" : 1,
"docs" : {
"hits" : {
"total" : {
"value" : 1,
"relation" : "eq"
},
"max_score" : 1.0,
"hits" : [
{
"_index" : "index22",
"_type" : "_doc",
"_id" : "55Kv83EB8a54AbXfngYU",
"_score" : 1.0,
"_source" : {
"deaerId" : "4",
"entryTime" : "1578214800000"
}
}
]
}
}
}
]
}
}
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.