Query a JSONB object array - json

I did a DB Fiddle of what the table is kinda looking like https://www.db-fiddle.com/f/4jyoMCicNSZpjMt4jFYoz5/3382
Data in the table looks like this
[
{
"id": 1,
"form_id": 1,
"questionnaire_response": [
{
"id": "1",
"title": "Are you alive?",
"value": "Yes",
"form_id": 0,
"shortTitle": "",
"description": ""
},
{
"id": "2",
"title": "Did you sleep good?",
"value": "No",
"form_id": 0,
"shortTitle": "",
"description": ""
},
{
"id": "3",
"title": "Whats favorite color(s)?",
"value": [
"Red",
"Blue"
],
"form_id": 0,
"shortTitle": "",
"description": ""
}
]
},
{
"id": 2,
"form_id": 1,
"questionnaire_response": [
{
"id": "1",
"title": "Are you alive?",
"value": "Yes",
"form_id": 0,
"shortTitle": "",
"description": ""
},
{
"id": "2",
"title": "Did you sleep good?",
"value": "Yes",
"form_id": 0,
"shortTitle": "",
"description": ""
},
{
"id": "3",
"title": "Whats favorite color(s)?",
"value": "Black",
"form_id": 0,
"shortTitle": "",
"description": ""
}
]
},
{
"id": 3,
"form_id": 1,
"questionnaire_response": [
{
"id": "1",
"title": "Are you alive?",
"value": "Yes",
"form_id": 0,
"shortTitle": "",
"description": ""
},
{
"id": "2",
"title": "Did you sleep good?",
"value": "No",
"form_id": 0,
"shortTitle": "",
"description": ""
},
{
"id": "3",
"title": "Whats favorite color(s)?",
"value": [
"Black",
"Red"
],
"form_id": 0,
"shortTitle": "",
"description": ""
}
]
}
]
I have a query select * from form_responses,jsonb_to_recordset(form_responses.questionnaire_response) as items(value text, id text) where (items.id = '3' AND items.value like '%Black%');
But unable to do more than one object like select * from form_responses,jsonb_to_recordset(form_responses.questionnaire_response) as items(value text, id text) where (items.id = '3' AND items.value like '%Black%') AND (items.id = '2' AND items.value like '%Yes%');
The value field in the object could be an array or a single value also.. unpredictable.. I feel like I'm close but also not sure if im using the correct query in the first place.
Any help would be appreciated!
EDIT
select * from form_responses where(
questionnaire_response #> '[{"id": "2", "value":"No"},{"id": "3", "value":["Red"]}]')
Seems to work but not sure if this is the best way to do it

Your current query returns one result row per item. None of these rows has both id = 3 and id = 2. If your goal is to select the entire form response, you need to use a subquery (or rather, two of them):
SELECT *
FROM form_responses
WHERE EXISTS(
SELECT *
FROM jsonb_to_recordset(form_responses.questionnaire_response) as items(value text, id text)
WHERE items.id = '3'
AND items.value like '%Black%'
)
AND EXISTS(
SELECT *
FROM jsonb_to_recordset(form_responses.questionnaire_response) as items(value text, id text)
WHERE items.id = '2'
AND items.value like '%Yes%'
);
or alternatively
SELECT *
FROM form_responses
WHERE (
SELECT value
FROM jsonb_to_recordset(form_responses.questionnaire_response) as items(value text, id text)
WHERE items.id = '3'
) like '%Black%'
AND (
SELECT value
FROM jsonb_to_recordset(form_responses.questionnaire_response) as items(value text, id text)
WHERE items.id = '2'
) like '%Yes%';
A nicer alternative would be using json path queries:
SELECT *
FROM form_responses
WHERE questionnaire_response ## '$[*]?(#.id == "1").value == "Yes"'
AND questionnaire_response ## '$[*]?(#.id == "3").value[*] == "Black"'
-- in one:
SELECT *
FROM form_responses
WHERE questionnaire_response ## '$[*]?(#.id == "1").value == "Yes" && $[*]?(#.id == "3").value[*] == "Black"'
The [*] even has the correct semantics for that sometimes-string-sometimes-array value. And if you know the indices of the items with those ids, you can even simplify to
SELECT *
FROM form_responses
WHERE questionnaire_response ## '$[0].value == "Yes" && $[2].value[*] == "Black"'
(dbfiddle demo)

Related

Select from mysql array of objects with integer number and value null or source to file without duplicates

Let's say I have a table with rows like number, image. But image is not mandatory, It can be null and when I'm selecting I want to prioritize the row with image over the one with null so i could get clean array with only one row per number.
SELECT DISTINCT number, image FROM table ORDER BY number ASC
What's now with SELECT DISTINCT:
[
{
"number": 1,
"image": null
},
{
"number": 1,
"image": "https://example.com/image1.png"
},
{
"number": 2,
"image": null
},
{
"number": 2,
"image": "https://example.com/image2.png"
},
{
"number": 3,
"image": "https://example.com/image3.png"
},
{
"number": 3,
"image": null
},
{
"number": 4,
"image": null
}
]
What I want to get:
[
{
"number": 1,
"image": "https://example.com/image1.png"
},
{
"number": 2,
"image": "https://example.com/image2.png"
},
{
"number": 3,
"image": "https://example.com/image3.png"
},
{
"number": 4,
"image": null
}
]
Try this:
SELECT number, image FROM table ORDER BY ISNULL(LEFT(image,0));

couchbase N1QL group-by in sub-document

given the below data model:
{
"events": [
{
"customerId": "a",
"type": "credit" ,
"value": 10
},
{
"customerId": "a",
"type": "credit" ,
"value": 10
},
{
"customerId": "b",
"type": "credit" ,
"value": 5
},
{
"customerId": "b",
"type": "credit" ,
"value": 5
}
]
}
how can i query the sum of credits by customerId ? i.e:
{
{
"customerId": "a",
"total": "20
},
{
"customerId": "b",
"total": "10
}
}
Use SUBQUERY expression per document aggregation
SELECT d.*,
(SELECT e.customerId, SUM(e.`value`) AS total
FROM d.events AS e
WHERE ......
GROUP BY e.customerId) AS events
FROM default AS d
WHERE ...........;
For Whole Query
SELECT e.customerId, SUM(e.`value`) AS total
FROM default AS d
UNNEST d.events AS e
WHERE ......
GROUP BY e.customerId;

Select Json formatted like a report to a table using T-SQL

I have JSON stored in a SQL Server database table in the below format. I have been able to fudge a way to get the values I need but feel like there must be a better way to do it using T-SQL. The JSON is output from a report in the below format where the column names in "columns" correspond to the "rows"-"data" array values.
So column "Fiscal Month" corresponds to data value "11", "Fiscal Year" to "2019", etc.
{
"report": "Property ETL",
"id": 2648,
"columns": [
{
"name": "Fiscal Month",
"dataType": "int"
},
{
"name": "Fiscal Year",
"dataType": "int"
},
{
"name": "Portfolio",
"dataType": "varchar(50)"
},
{
"name": "Rent",
"dataType": "int"
}
],
"rows": [
{
"rowName": "1",
"type": "Detail",
"data": [
11,
2019,
"West Group",
10
]
},
{
"rowName": "2",
"type": "Detail",
"data": [
11,
2019,
"East Group",
10
]
},
{
"rowName": "3",
"type": "Detail",
"data": [
11,
2019,
"East Group",
10
]
},
{
"rowName": "Totals: ",
"type": "Total",
"data": [
null,
null,
null,
30
]
}
]
}
In order to get at the data in the 'data' array I currently have a 2 step process in T-SQL where I create a temp table, and insert the row key/values from '$.Rows' there. Then I can then select the individual columns for each row
CREATE TABLE #TempData
(
Id INT,
JsonData VARCHAR(MAX)
)
DECLARE #json VARCHAR(MAX);
DECLARE #LineageKey INT;
SET #json = (SELECT JsonString FROM Stage.Report);
SET #LineageKey = (SELECT LineageKey FROM Stage.Report);
INSERT INTO #TempData(Id, JsonData)
(SELECT [key], value FROM OPENJSON(#json, '$.rows'))
MERGE [dbo].[DestinationTable] TARGET
USING
(
SELECT
JSON_VALUE(JsonData, '$.data[0]') AS FiscalMonth,
JSON_VALUE(JsonData, '$.data[1]') AS FiscalYear,
JSON_VALUE(JsonData, '$.data[2]') AS Portfolio,
JSON_VALUE(JsonData, '$.data[3]') AS Rent
FROM #TempData
WHERE JSON_VALUE(JsonData, '$.data[0]') is not null
) AS SOURCE
...
etc., etc.
This works, but I want to know if there is a way to directly select the data values without the intermediate step of putting it into the temp table. The documentation and examples I've read seem to all require that the data have a name associated with it in order to access it. When I try and access the data directly at a position by index I just get Null.
I hope I understand your question correctly. If you know the columns names you need one OPENJSON() call with explicit schema, but if you want to read the JSON structure from $.columns, you need a dynamic statement.
JSON:
DECLARE #json nvarchar(max) = N'{
"report": "Property ETL",
"id": 2648,
"columns": [
{
"name": "Fiscal Month",
"dataType": "int"
},
{
"name": "Fiscal Year",
"dataType": "int"
},
{
"name": "Portfolio",
"dataType": "varchar(50)"
},
{
"name": "Rent",
"dataType": "int"
}
],
"rows": [
{
"rowName": "1",
"type": "Detail",
"data": [
11,
2019,
"West Group",
10
]
},
{
"rowName": "2",
"type": "Detail",
"data": [
11,
2019,
"East Group",
10
]
},
{
"rowName": "3",
"type": "Detail",
"data": [
11,
2019,
"East Group",
10
]
},
{
"rowName": "Totals: ",
"type": "Total",
"data": [
null,
null,
null,
30
]
}
]
}'
Statement for fixed structure:
SELECT *
FROM OPENJSON(#json, '$.rows') WITH (
[Fiscal Month] int '$.data[0]',
[Fiscal Year] int '$.data[1]',
[Portfolio] varchar(50) '$.data[2]',
[Rent] int '$.data[3]'
)
Dynamic statement:
DECLARE #stm nvarchar(max) = N''
SELECT #stm = CONCAT(
#stm,
N',',
QUOTENAME(j2.name),
N' ',
j2.dataType,
N' ''$.data[',
j1.[key],
N']'''
)
FROM OPENJSON(#json, '$.columns') j1
CROSS APPLY OPENJSON(j1.value) WITH (
name varchar(50) '$.name',
dataType varchar(50) '$.dataType'
) j2
SELECT #stm = CONCAT(
N'SELECT * FROM OPENJSON(#json, ''$.rows'') WITH (',
STUFF(#stm, 1, 1, N''),
N')'
)
PRINT #stm
EXEC sp_executesql #stm, N'#json nvarchar(max)', #json
Result:
--------------------------------------------
Fiscal Month Fiscal Year Portfolio Rent
--------------------------------------------
11 2019 West Group 10
11 2019 East Group 10
11 2019 East Group 10
30
Yes, it is possible without temporary table:
DECLARE #json NVARCHAR(MAX) =
N'
{
"report": "Property ETL",
"id": 2648,
"columns": [
{
"name": "Fiscal Month",
"dataType": "int"
},
{
"name": "Fiscal Year",
"dataType": "int"
},
{
"name": "Portfolio",
"dataType": "varchar(50)"
},
{
"name": "Rent",
"dataType": "int"
}
],
"rows": [
{
"rowName": "1",
"type": "Detail",
"data": [
11,
2019,
"West Group",
10
]
},
{
"rowName": "2",
"type": "Detail",
"data": [
11,
2019,
"East Group",
10
]
},
{
"rowName": "3",
"type": "Detail",
"data": [
11,
2019,
"East Group",
10
]
},
{
"rowName": "Totals: ",
"type": "Total",
"data": [
null,
null,
null,
30
]
}
]
}
}';
And query:
SELECT s.value,
rowName = JSON_VALUE(s.value, '$.rowName'),
[type] = JSON_VALUE(s.value, '$.type'),
s2.[key],
s2.value
FROM OPENJSON(JSON_QUERY(#json, '$.rows')) s
CROSS APPLY OPENJSON(JSON_QUERY(s.value, '$.data')) s2;
db<>fiddle demo
Or as a single row per detail:
SELECT s.value,
rowName = JSON_VALUE(s.value, '$.rowName'),
[type] = JSON_VALUE(s.value, '$.type'),
JSON_VALUE(s.value, '$.data[0]') AS FiscalMonth,
JSON_VALUE(s.value, '$.data[1]') AS FiscalYear,
JSON_VALUE(s.value, '$.data[2]') AS Portfolio,
JSON_VALUE(s.value, '$.data[3]') AS Rent
FROM OPENJSON(JSON_QUERY(#json, '$.rows')) s;
db<>fiddle demo 2

Couchbase array index not getting used in the query

I have the following document structure:
{
"customerId": "",
"schemeId": "scheme-a",
"type": "account",
"events": [
{
"dateTime": "2019-03-14T02:23:58.573Z",
"id": "72998bbf-94a6-4031-823b-6c304707ad49",
"type": "DebitDisabled",
"authorisedId": ""
},
{
"dateTime": "2018-05-04T12:40:15.439Z",
"transactionReference": "005171-15-1054-7571-60990-20180503165536",
"id": "005171-15-1054-7571-60990-20180503165536-1",
"type": "Credit",
"authorisedId": ",
"value": 34,
"funder": "funder-a"
},
{
"dateTime": "2019-03-06T04:14:54.564Z",
"transactionReference": "000000922331",
"eventDescription": {
"language": "en-gb",
"text": "
},
"id": "000000922331",
"type": "Credit",
"authorisedId": "",
"value": 16,
"funder": "funder-b"
},
{
"dateTime": "2019-03-10T04:24:17.903Z",
"transactionReference": "000001510154",
"eventDescription": {
"language": "en-gb",
"text": ""
},
"id": "000001510154",
"type": "Credit",
"authorisedId": "",
"value": 10,
"funder": "funder-c"
}
]
}
And the following indexes :
CREATE INDEX `scheme-a_customers_index`
ON `default`(`type`,`schemeId`,`customerId`)
WHERE ((`schemeId` = "scheme-a") and (`type` = "account"))
WITH { "num_replica":1 }
CREATE INDEX `scheme-a_credits_index`
ON `default`(
`type`,
`schemeId`,
`customerId`,
(distinct (array (`e`.`funder`) for `e` in `events` when ((`e`.`type`) = "Credit") end))
)
WHERE ((`type` = "scheme") and (`schemeId` = "scheme-a"))
WITH { "num_replica":1 }
I am trying to query all the customerIds and events for each where type="credit" and funder like "funder%"
below is my query :
SELECT
customerId,
(ARRAY v.`value` FOR v IN p.events WHEN v.type = "Credit" AND v.funder like "funder%" END) AS credits
FROM default AS p
WHERE p.type = "account" AND p.schemeId = "scheme-a"
AND (ANY e IN p.events SATISFIES e.funder = "funder-a" END)
I am expecting the query to use the index scheme-a_credits_index, instead it is using scheme-a_customers_index. Can't understand why ! isn't the query supposed to use scheme-a_credits_index ?
Your query doesn't have predicate on customerId. So query can only push two predicates to indexers and both indexes are qualify. scheme-a_customers_index is more efficient because of number of entries in the index due to non array index.
You should try the following.
CREATE INDEX `ix1` ON `default`
(DISTINCT ARRAY e.funder FOR e IN events WHEN e.type = "Credit" END, `customerId`)
WHERE ((`schemeId` = "scheme-a") and (`type` = "account")) ;
SELECT
customerId,
(ARRAY v.`value` FOR v IN p.events WHEN v.type = "Credit" AND v.funder like "funder%" END) AS credits
FROM default AS p
WHERE p.type = "account" AND p.schemeId = "scheme-a"
AND (ANY e IN p.events SATISFIES e.funder LIKE "funder%" AND e.type = "Credit" END);

json_agg() with pseudo row

CREATE TABLE content
(
code INTEGER NOT NULL
, nameid TEXT NOT NULL
)
INSERT INTO content(code, nameid) VALUES
( 0, 'Support')
, ( 1, 'Adrenaline')
, ( 2, 'Aquapark')
;
Need select all content as JSON array-object named 'content' with pseudo row with code = '' and nameid = 'All'
What i did:
1) Simple select
SELECT
json_build_object('content', (SELECT json_agg(json_build_object(
'code', s.code::TEXT
, 'nameid', s.nameid::TEXT
))
FROM content s
)
);
Result is
{
"content": [{
"code": "0",
"nameid": "Support"
},
{
"code": "1",
"nameid": "Adrenaline"
},
{
"code": "2",
"nameid": "Aquapark"
}
]
}
All fine, but how to add pseudo row?
2) Best i can did
SELECT
json_build_object('content', json_build_array(
json_build_object(
'code', ''
, 'nameid', 'All'::TEXT),
(SELECT json_agg(json_build_object(
'code', s.code::TEXT
, 'nameid', s.nameid::TEXT
))
FROM content s
))
);
Result is
{
"content": [{
"code": "",
"nameid": "All"
},
[{
"code": "0",
"nameid": "Support"
},
{
"code": "1",
"nameid": "Adrenaline"
},
{
"code": "2",
"nameid": "Aquapark"
}
]
]
}
And we have array in array, as in sql as in json, but i can not understand how to combine json_agg with pseudo row.
Use to_json() and union all:
select jsonb_build_object('content', json_agg(to_json))
from (
select to_json(c)
from (select '' as code, 'All' as nameid) c
union all
select to_json(c)
from content c
) s
Output:
{
"content": [
{
"code": "",
"nameid": "All"
},
{
"code": 0,
"nameid": "Support"
},
{
"code": 1,
"nameid": "Adrenaline"
},
{
"code": 2,
"nameid": "Aquapark"
}
]
}
The version with an alias in the derived table:
select jsonb_build_object('content', json_agg(codes))
from (
select to_json(c) as codes
from (select '' as code, 'All' as nameid) c
union all
select to_json(c)
from content c
) s