I have SQL query:
WHERE A = 1 AND B = 2 AND C REGEXP (eee|fff|ggg)
How can I write this query in elasticsearch ?
Not tested but something like this QUERY-DSL you need for your case with filter and regexp,
GET /_search
{
"size": 10,
"query": {
"filter" : {
"bool" : {
"must" : [
{ "term" : {"A" : 1}},
{ "term" : {"B" : 2}}
]
}
},
"regexp": {
"C": {
"value": "eee|fff|ggg"
}
}
}
}
OR
GET /_search
{
"size": 10,
"query": {
"filter": {
"bool": {
"must": [
{
"term": {
"A": 1
}
},
{
"term": {
"B": 2
}
},
{
"regexp": {
"C": {
"value": "eee|fff|ggg"
}
}
}
]
}
}
}
}
Related
I am making a search query in Elastic Search and I want to treat the fields the same when they match. For example if I search for field field1 and it matches, then the _score is increase by 10(for example), same for the field2.
I was tried function_score but it's not working. It throws an error.
"caused_by": {
"type": "class_cast_exception",
"reason": "class
org.elasticsearch.index.fielddata.plain.SortedSetDVOrdinalsIndexFieldData
cannot be cast to class
org.elasticsearch.index.fielddata.IndexNumericFieldData
(org.elasticsearch.index.fielddata.plain.SortedSetDVOrdinalsIndexFieldData
and org.elasticsearch.index.fielddata.IndexNumericFieldData are in unnamed
module of loader 'app')"
}
The query:
{
"track_total_hits": true,
"size": 50,
"query": {
"function_score": {
"query": {
"bool": {
"must": [
{
"term": {
"field1": {
"value": "Value 1"
}
}
},
{
"term": {
"field2": {
"value": "value 2"
}
}
}
]
}
},
"functions": [
{
"field_value_factor": {
"field": "field1",
"factor": 10,
"missing": 0
}
},
{
"field_value_factor": {
"field": "field2",
"factor": 10,
"missing": 0
}
}
],
"boost_mode": "multiply"
}
}
}
You can use function score with filter function to boost.
assuming that your mapping looks like the one below
{
"mappings": {
"properties": {
"field_1": {
"type": "keyword"
},
"field_2": {
"type": "keyword"
}
}
}
}
with documents
{"index":{}}
{"field_1": "foo", "field_2": "bar"}
{"index":{}}
{"field_1": "foo", "field_2": "foo"}
{"index":{}}
{"field_1": "bar", "field_2": "bar"}
you can use weight parameter to boost the documents matched for each query.
{
"query": {
"function_score": {
"query": {
"match_all": {}
},
"functions": [
{
"filter": {
"term": {
"field_1": "foo"
}
},
"weight": 10
},
{
"filter": {
"term": {
"field_2": "foo"
}
},
"weight": 20
}
],
"score_mode": "multiply"
}
}
}
You can refer below solution if you want to provide manual weight for different field in query. This will always replace highest weight field on top of your query response -
Elasticsearch query different fields with different weight
I have a ES document like below :
{
"_id" : "test#domain.com",
"age" : 12,
"hobbiles" : ["Singing", "Dancing"]
},
{
"_id" : "test1#domain.com",
"age" : 7,
"hobbiles" : ["Coding", "Chess"]
}
I am storing email as id, age and hobbiles, hobbies is nested type, age is long I want to query with id, age and hobbiles, something like below :
Select * FROM tbl where _id IN ('val1', 'val2') AND age > 5 AND hobbiles should match with Chess or Dancing
How can I do in Elastic Search ? I am using OpenSearch 1.3 (latest) : AWS
I will suspect that field hobbiles is keyword, then the query suggested:
PUT test
{
"mappings": {
"properties": {
"age": {
"type": "long"
},
"hobbiles": {
"type": "keyword"
}
}
}
}
POST test/_doc/test#domain.com
{
"age": 12,
"hobbiles": [
"Singing",
"Dancing"
]
}
POST test/_doc/test1#domain.com
{
"age": 7,
"hobbiles": [
"Coding",
"Chess"
]
}
GET test/_search
{
"query": {
"bool": {
"filter": [
{
"terms": {
"_id": [
"test1#domain.com",
"test#domain.com"
]
}
}
],
"must": [
{
"range": {
"age": {
"gt": 5
}
}
},
{
"terms": {
"hobbiles": [
"Coding",
"Chess"
]
}
}
]
}
}
}
Hi I am trying to get a query based on the following documents.
document 1
{
"date" : "2021-05-19",
"items" : [
{
"keyA" : "ValueA"
}
]
}
document 2
{
"date" : "2021-05-19",
"items" : [
{
"keyB" : "ValueB"
}
]
}
Output I expect
{
"date" : "2021-05-19",
"items" : [
{
"keyA" : "ValueA"
},
{
"keyB" : "ValueB"
}
]
}
I don't want to update this structure in ES. Only when I query, I want the result to be in this format.
Is it possible? or should I handle it after receiving the result?
You can use a combination of terms and top_hits aggregation
{
"size": 0,
"aggs": {
"dateagg": {
"terms": {
"field": "date"
},
"aggs": {
"top_keys": {
"top_hits": {
"_source": {
"includes": [
"items.*"
]
}
}
}
}
}
}
}
Search Result will be
"aggregations": {
"dateagg": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": 1621382400000,
"key_as_string": "2021-05-19T00:00:00.000Z", // note this
"doc_count": 2,
"top_keys": {
"hits": {
"total": {
"value": 2,
"relation": "eq"
},
"max_score": 1.0,
"hits": [
{
"_index": "67598919",
"_type": "_doc",
"_id": "1",
"_score": 1.0,
"_source": {
"items": [
{
"keyA": "ValueA" // note this
}
]
}
},
{
"_index": "67598919",
"_type": "_doc",
"_id": "2",
"_score": 1.0,
"_source": {
"items": [
{
"keyB": "ValueB" // note this
}
]
}
}
]
}
}
}
]
}
}
I have this index:
{
"mappings": {
"records" : {
"properties" : {
"suggest" : {
"type" : "completion",
"contexts": [
{
"name": "year",
"type": "category",
"path": "year"
}
]
}
}
}
}
}
I put some records:
POST http://localhost:9200/example/records
{
"suggest": {
"input": "foo123" ,
"contexts": {
"year": "1999"
}
}
}
POST http://localhost:9200/example/records
{
"suggest": {
"input": "some123" ,
"contexts": {
"year": "1999"
}
}
}
POST http://localhost:9200/example/records
{
"suggest": {
"input": "thing123" ,
"contexts": {
"year": "2000"
}
}
}
Now I would do this query (sql like):
SELECT * FROM example WHERE SUGGEST LIKE %123% AND YEAR=1999
How can I do in Elastic Search?
I type:
POST http://localhost:9200/example/records/_search?pretty
{
"query": {
"bool": {
"must": [
{ "wildcard" : { "suggest" : "*123*" } }
],
"filter":[
{ "term" : { "year" : "1999" } }
]
}
}
}
I have returned this response with blank results:
{
"took": 1,
"timed_out": false,
"_shards": {
"total": 5,
"successful": 5,
"skipped": 0,
"failed": 0
},
"hits": {
"total": 0,
"max_score": null,
"hits": []
}
}
I am expecting to have returned this records:
foo123, year 1999
some123, year 1999
How can I do?
You need to use bool query with must if you care about score:
{
"query": {
"bool": {
"must": [
{ "wildcard" : { "name" : "*foo*" } },
{ "term" : { "year" : "1999" } }
]
}
}
}
or with filter if you just want to filter values and possibly cache the filter:
{
"query": {
"filter": {
"must": [
{ "wildcard" : { "name" : "*foo*" } },
{ "term" : { "year" : "1999" } }
]
}
}
}
I need to use $cond to combine differenet column, and one $cond I need to write is as following:
create_widget: {
$sum:{
$cond:[{$and: [ {$eq: ['$Method', 'POST']},
{Url:{$regex: /.*\/widgets$/}} ]}, 1, 0]
}
}
and this code is not right, it seems, regular expression can not be put here.Is there any other way to do this? I want to match Url and regular expression and put the code under $cond.
A sample data looks as
{"BrandId":"a","SessionId":"a1","Method":"POST","Url":"/sample/widgets"}
{"BrandId":"a","SessionId":"a2","Method":"POST","Url":"/sample/blog"}
{"BrandId":"b","SessionId":"b1","Method":"PUT","Url":"/sample/widgets"}
The whole code I wrote is as following:
db.tmpAll.aggregate([
{$group: {
_id: {BrandId:'$BrandId'},
SessionId: {$addToSet: '$SessionId'},
create_widget: {
$sum:{
$cond:[{$and: [ {$eq: ['$Method', 'POST']},
{} ]}, 1, 0]
}
}
}},
{$group: {
_id: '$_id.BrandId',
distinct_session: {$sum: {$size: '$SessionId'}},
create_widget: {$sum: '$create_widget'}
}}
]);
The expected result of sample code is
{ "_id" : "a", "distinct_session" : 2, "create_widget" : 1 }
{ "_id" : "b", "distinct_session" : 1, "create_widget" : 0 }
For MongoDB 4.2 and newer production releases, and in the 4.1.11 and newer development versions, use $regexMatch which is a syntactic sugar on top of $regexFind which can be used for regex matching and capturing.
db.tmpAll.aggregate([
{ "$group": {
"_id": {
"BrandId": "$BrandId",
"SessionId": "$SessionId"
},
"widget_count": {
"$sum": {
"$cond": [
{
"$and": [
{ "$eq": ["$Method", "POST"] },
{ "$regexMatch": {
"input": "$Url",
"regex": /widget/
} }
]
}, 1, 0
]
}
},
"session_count": { "$sum": 1 }
} },
{ "$group": {
"_id": "$_id.BrandId",
"create_widget": { "$sum": "$widget_count" },
"distinct_session": { "$sum": "$session_count" }
} }
]);
There is an open JIRA issue for this SERVER-8892 - Use $regex as the expression in a $cond. However, as a workaround, For older MongoDB versions which do not have the above features, use the following workaround in your aggregation pipeline.
It uses the $substr operator in the $project operator stage to extract the part of the URL and acts as a workaround for the regex. :
db.tmpAll.aggregate([
{ "$group": {
"_id": {
"BrandId": "$BrandId",
"SessionId": "$SessionId"
},
"widget_count": {
"$sum": {
"$cond": [
{
"$and": [
{ "$eq": ["$Method", "POST"] },
{ "$eq": [ { "$substr": [ "$Url", 8, -1 ] }, "widget"] }
]
}, 1, 0
]
}
},
"session_count": { "$sum": 1 }
} },
{ "$group": {
"_id": "$_id.BrandId",
"create_widget": { "$sum": "$widget_count" },
"distinct_session": { "$sum": "$session_count" }
} }
]);
Output
/* 1 */
{
"result" : [
{
"_id" : "a",
"create_widget" : 1,
"distinct_session" : 2
},
{
"_id" : "b",
"create_widget" : 0,
"distinct_session" : 1
}
],
"ok" : 1
}