Parse JSON structure in SQL - sql

I have written a code that reads information from JSON lines to table in SQL:
declare #pJSON varchar(max) = '
{
"School": "MiddleSchool",
"Password": "SchoolPassword",
"Attributes": [
{
"Type": "Exam",
"Value": "1"
},
{
"Type": "Class",
"Value": "11b"
},
{
"Type": "Math",
"Value": [
{
"ExamDate": "2019-01-01",
"Points": 100,
"Grade": 10,
"Notes": "Good"
}
]
}
]
} '
select ExamDate, Points, Grade, Notes
from OPENJSON(#pJSON, N'$.Attributes[2].Value')
cross apply openjson ([Value])
with
(
ExamDate date,
Points int,
Grade int,
Notes varchar(max)
) as [value]
Code works fine, but I really hate N'$.Attributes[2].Value' part. Exam information can be in the first, second, third place, so [2] doesn't really work for me. Do you have any suggestions for me, how I can improve this code? Thank you!

You could use JSON_QUERY:
select ExamDate, Points, Grade, Notes
from OPENJSON(JSON_QUERY(#pJSON, N'$.Attributes'))
with
(
ExamDate date N'$.Value[0].ExamDate', -- here 0 because Value is array too
Points int N'$.Value[0].Points',
Grade int N'$.Value[0].Grade',
Notes varchar(max) N'$.Value[0].Notes'
) as [value]
WHERE ExamDate IS NOT NULL;
db<>fiddle demo
EDIT:
In original question there was only one exam in array. If array could contain more than code should be adjusted:
SELECT s2.[key]
,ExamValue = JSON_VALUE(s2.value, '$.ExamDate')
,Points = JSON_VALUE(s2.value, '$.Points')
,Grade = JSON_VALUE(s2.value, '$.Grade')
,Notes = JSON_VALUE(s2.value, '$.Notes')
FROM OPENJSON(JSON_QUERY(#pJSON, N'$.Attributes')) s
CROSS APPLY OPENJSON(JSON_QUERY(s.value, N'$.Value')) s2;
-- or
SELECT [value].*
FROM OPENJSON(JSON_QUERY(#pJSON, N'$.Attributes'))
CROSS APPLY OPENJSON(JSON_QUERY(value, N'$.Value'))
with
(
ExamDate date N'$.ExamDate',
Points int N'$.Points',
Grade int N'$.Grade',
Notes varchar(max) N'$.Notes'
) as [value];
db<>fiddle demo

Related

Extract a JSON array items to a single column separated with comma

Struggling to find an answer to the below JSON problem. I would like to display the entire SKU/Quantity list in the "shipmentItems" array to their respective column with a comma-separated value. My example below only allows me to display the first SKU/quantity from the array but, my goal is to get all listed in the columns with comma-separated.
JSON example:
{"shipments": [
{
"shipmentId": 100003768,
"orderNumber": "9648219086",
"shipDate": "2021-10-28",
"serviceCode": "ups_ground",
"shipmentItems": [
{
"orderItemId": 1464643208,
"lineItemKey": "10322938560608",
"sku": "SCPXTSS-BAG-06",
"name": "SCOOP-PLATE-06 (1000ml)",
"weight": {
"value": 0,
"units": "ounces",
"WeightUnits": 1
},
"quantity": 1,
"unitPrice": 0,
"taxAmount": null
},
{
"orderItemId": 1464643207,
"lineItemKey": "10322938527840",
"sku": "SCPZRTS-TRAY-01",
"name": "Beef: Tray 3 (Fill 004)<br>",
"weight": {
"value": 60,
"units": "ounces",
"WeightUnits": 1
},
"quantity": 1,
"unitPrice": 102.72,
"taxAmount": null
}
],
"labelData": null,
"formData": null
}
]
}
SQL query I'm using:
DECLARE #JSON varchar(max)
SELECT #JSON = BulkColumn
FROM OPENROWSET (BULK 'C:\Users\XPS-LT\json\today\shipments_20211031.json', SINGLE_CLOB)
IMPORT
SELECT *
FROM OPENJSON (#JSON, '$.shipments')
WITH
(
[shipmentId] bigint,
[orderNumber] nvarchar(60),
[shipDate] date,
[serviceCode] nvarchar(30),
[sku] nvarchar(MAX) N'$.shipmentItems[0].sku',
[quantity] int N'$.shipmentItems[0].quantity'
)
;
The "shipmentItems" part of the input JSON is an array, so you need an AS JSON clause in the first explicit schema and an additional OPENJSON() call:
DECLARE #json nvarchar(max)
...
SELECT
j.[shipmentId], j.[orderNumber], j.[shipDate], j.[serviceCode],
a.[sku], a.[quantity]
FROM OPENJSON (#json, '$.shipments') WITH (
[shipmentId] bigint,
[orderNumber] nvarchar(60),
[shipDate] date,
[serviceCode] nvarchar(30),
[shipmentItems] nvarchar(max) AS JSON
) j
OUTER APPLY (
SELECT
STRING_AGG([sku], ',') WITHIN GROUP (ORDER BY [orderItemId]),
STRING_AGG([quantity], ',') WITHIN GROUP (ORDER BY [orderItemId])
FROM OPENJSON (j.shipmentItems) WITH (
[orderItemId] int '$.orderItemId',
[sku] nvarchar(max) '$.sku',
[quantity] int N'$.quantity'
)
) a ([sku], [quantity])
Result:
shipmentId orderNumber shipDate serviceCode sku quantity
100003768 9648219086 2021-10-28 ups_ground SCPZRTS-TRAY-01,SCPXTSS-BAG-06 1,1

How to Set OPENJSON Path to Nested Array

I'm trying to set the path for my OPENJSON function for the nested array, but it's not working. Tried different variations and examples/resources I found online and still cannot figure it out.
Any ideas?
EDIT:
To be clear, I know how to do this with CROSSAPPLY and other methods. My question is in regards on how to do this specifically with the OPENJSON function's path parameter if possible.
Here's my code:
DECLARE #json NVARCHAR(MAX);
SET #json = '
{
"orders": [
{
"id":"1",
"date":"7/4/2020",
"orderlines": [
{"id": "1", "amount": 100},
{"id": "2", "amount": 200}
]
},
{
"id":"2",
"date":"7/4/2020",
"orderlines": [
{"id": "3", "amount": 300},
{"id": "4", "amount": 400}
]
}
]
}
'
-- None of these return results. How do I specify the path to the "orderlines" array?
SELECT * FROM OPENJSON(#json,'$.orderlines');
SELECT * FROM OPENJSON(#json,'$.orderlines[1]');
SELECT * FROM OPENJSON(#json,'$.orders.orderlines');
SELECT * FROM OPENJSON(#json,'$.orders.orderlines[1]');
-- This works:
SELECT * FROM OPENJSON(#json,'$.orders');
You can use WITH and put a name on inside values and use CROSS APPLY to use them in another OPENJSON. Now you can have all inside objects together.
SELECT orderlines.id, orderlines.amount
FROM OPENJSON(#json, '$.orders') WITH (orderlines NVARCHAR(MAX) '$.orderlines' AS JSON) orders
CROSS APPLY OPENJSON(orders.orderlines) WITH (id INT '$.id', amount INT '$.amount') orderlines
Learn more here.
Also if need to get specific item in array:
SELECT * FROM OPENJSON(#json, '$.orders[0].orderlines[0]')
-- OR
SELECT JSON_VALUE(#json, '$.orders[0].orderlines[0].amount')
To make it clear for others who may be viewing this, the part of Iman Kazemi's response that was the answer was the following of what he wrote:
SELECT * FROM OPENJSON(#json, '$.orders[0].orderlines[0]')
I neglected to specify the index on the order's array.
Thanks again to Iman.
You can try the following:
SELECT *
FROM OPENJSON (#json, '$.orders')
WITH (
id INT '$.id',
[date] VARCHAR(10) '$.date',
orderlines_id1 INT '$.orderlines[0].id',
orderlines_amount1 MONEY '$.orderlines[0].amount',
orderlines_id2 INT '$.orderlines[1].id',
orderlines_amount2 MONEY '$.orderlines[1].amount'
) AS Orders
Please see the db<>fiddle here.

MSSQL Query JSON displays Null value

I have a table PublicRelations with a column called Students in a SQL Server database called Subjects.
[
{ "Label": "Name", "ColumnValue": "Trudie" },
{ "Label": "Class", "ColumnValue": "PublicRelations" },
{ "Label": "Room", "ColumnValue": "8049" },
{ "Label": "HttpPath", "ColumnValue": "https://www.google.com/" }
]
I only get NULL when I run the below query using the Json_value. I'd like to get it to display the value from the array. I believe this may have to do with the 4000 character limit?
SELECT [StuduentID],
[Students],
--JSON_VALUE([Students],'$.ColumnValue') AS Name --Only returns NULL
FROM [Subjects].[dbo].[PublicRelations] c
CROSS APPLY OPENJSON(c.Students)
WITH ( Name int '$.Name',
Value nvarchar(255) '$.ColmunValue'
) AS jsonValues
WHERE jsonValues.ColumnValue = 'Trudie'
The query works and I can find what I need, but again, I only get NULL when I want to display that part of the JSON column in my results.
The statement is wrong and you has the following issues (as #MartinSmith already mentioned):
Syntax error - '$.ColmunValue' should be '$.ColumnValue'.
Wrong schema definition (the WITH clause) - I can't see Name key in the input JSON.
Wrong use of JSON_VALUE() - this function extracts scalar value from a JSON string, so JSON_VALUE([Students],'$.ColumnValue') returns NULL with this JSON input in lax mode.
You may try with the following statement (based on the statement in the question):
Table:
CREATE TABLE PublicRelations (
StudentID int,
Students nvarchar(1000))
INSERT INTO PublicRelations (StudentID, Students)
VALUES (1, N'[
{ "Label": "Name", "ColumnValue": "Trudie" },
{ "Label": "Class", "ColumnValue": "PublicRelations" },
{ "Label": "Room", "ColumnValue": "8049" },
{ "Label": "HttpPath", "ColumnValue": "https://www.google.com/" }
]')
Statement:
SELECT p.StudentID, j.*
FROM [PublicRelations] p
CROSS APPLY OPENJSON(p.Students) WITH (
Name nvarchar(50) '$.Label',
Value nvarchar(255) '$.ColumnValue'
) j
WHERE EXISTS (
SELECT 1
FROM OPENJSON(p.Students) WITH (Value nvarchar(255) '$.ColumnValue')
WHERE Value = N'Trudie'
) AND (j.Name IN ('Name', 'Class', 'Room'))
Result:
StudentID Name Value
1 Name Trudie
1 Class PublicRelations
1 Room 8049

How to write a select query to get the index value from Json object

I have the below JSON object. I need to write a select query to get the index values of Object JSON array. Kind of getting the sequence value.
{
"Model": [
{
"ModelName": "Test Model",
"Object": [
{
"ID": 1,
"Name": "ABC",
},
{
"ID": 11,
"Name": "ABCD",
},
{
"ID": 15,
"Name": "ABCDE",
},
]
}]}
Expected Output:
Index_Value
1
2
3
If I understand the question correctly and you want to get the index of the items in the Object JSON array, you need to use OPENJSON() with default schema. The result is a table with columns key, value and type and in case of JSON array, the key column holds the index of each item in the array (0-based):
JSON:
DECLARE #json nvarchar(max) = N'{
"Model":[
{
"ModelName":"Test Model",
"Object":[
{
"ID":1,
"Name":"ABC"
},
{
"ID":11,
"Name":"ABCD"
},
{
"ID":15,
"Name":"ABCDE"
}
]
}
]
}'
Statement:
SELECT CONVERT(int, j2.[key]) + 1 AS item_id
FROM OPENJSON (#json, '$.Model') j1
CROSS APPLY OPENJSON(j1.[value], '$.Object') j2
But if you want to get the values of the ID keys in the Object JSON array, the statement is different:
SELECT j2.ID
FROM OPENJSON (#json, '$.Model') j1
CROSS APPLY OPENJSON(j1.[value], '$.Object') WITH (
ID int '$.ID'
) j2
Note, that you need two OPENJSON() calls, because the input JSON has nested array structure. Of course, if Model JSON array has always one item, you may simplify the statement using an appropriate path:
SELECT CONVERT(int, [key]) + 1 AS item_id
FROM OPENJSON (#json, '$.Model[0].Object')
Finally, to get index, ID and Name, you should use the following statement, which assumes, that $.Model JSON array has more than one item and defines ID and Name columns with the appropraite data types:
SELECT
CONVERT(int, j2.[key]) + 1 AS ItemID,
j3.ID, j3.Name
FROM OPENJSON (#json, '$.Model') j1
CROSS APPLY OPENJSON(j1.[value], '$.Object') j2
CROSS APPLY OPENJSON(j2.[value], '$') WITH (
ID int '$.ID',
Name varchar(50) '$.Name'
) j3
DECLARE #json nvarchar(max) = N'{
"Model":[
{
"ModelName":"Test Model",
"Object":[
{
"ID":1,
"Name":"ABC"
},
{
"ID":11,
"Name":"ABCD"
},
{
"ID":15,
"Name":"ABCDE"
}
]
}
]
}'
declare #i int=0;
SELECT
j2.ID, j2.Name
FROM OPENJSON (#json, '$.Model') j1
CROSS APPLY OPENJSON(j1.[value],concat('$.Object[',#i,']')) WITH (
ID i`enter code here`nt '$.ID', Name varchar(100) '$.Name'
) j2
Results:-
ID
Name
11
ABCD
you can select the key columns in select clause no need to mention in with of crossjoin.
SELECT
distinct t.id,
JSON_VALUE(AttsData.[value], '$.address') as address,
JSON_VALUE(AttsData.[value], '$.name') as name,
JSON_VALUE(AttsData.[value], '$.owner_name') as owner_name,
JSON_VALUE(AttsData.[value], '$.project') as project
,CONVERT(int, AttsData.[key]) index_id
FROM mytablewithjsonfeild t
CROSS APPLY OPENJSON (t."jsonfeild",N'$.parentkey') as AttsData
Above query, from the table I have cross joined the JSON field. and in select statement i have taken the specific keys.
and CONVERT(int, AttsData.[key]) to get the index of the elements

Parsing JSON data to find one element

I'm sifting through a JSON movie database and can get most of the data without a problem. For each film, I've put the raw JSON in an nvarchar(max) column called jsondata, then added other columns to populate for indexing and quick retrieval purposes.
With my UPDATE statement, I'm able to populate all columns except for one, in which I need to parse through and find an element.
Here's an example of the JSON:
{
"title": "Amnesia Love",
"genres": [{
"id": 35,
"name": "Comedy"
}],
"id": 508989,
"original_language": "tl",
"overview": "A guy is trying to discover his true identity after being found unconscious in a remote island.",
"popularity": 2.583,
"release_date": "2018-02-28",
"credits": {
"cast": [{
"cast_id": 2,
"character": "",
"credit_id": "5a9af6ecc3a3680b7d024627",
"gender": 0,
"id": 1230955,
"name": "Paolo Ballesteros",
"order": 1,
"profile_path": "/8Cey11JPMWBCGuIcKBXvb6OQ7Je.jpg"
},
{
"cast_id": 3,
"character": "",
"credit_id": "5a9af6f3c3a3680b57024465",
"gender": 0,
"id": 1166094,
"name": "Yam Concepcion",
"order": 2,
"profile_path": "/fiPaXTkq440VHXDqlMRHtOpoLWT.jpg"
}],
"crew": [{
"credit_id": "5a9af6cc0e0a260649024c6a",
"department": "Directing",
"gender": 0,
"id": 1989658,
"job": "Director",
"name": "Albert Langitan",
"profile_path": null
},
{
"credit_id": "5a9af6dec3a3680b2d01f152",
"department": "Writing",
"gender": 0,
"id": 1989658,
"job": "Screenplay",
"name": "Albert Langitan",
"profile_path": null
}]
},
}
Here's the table schema:
CREATE TABLE dbo.moviedb(
id int IDENTITY(1,1) NOT NULL,
jsondata nvarchar(max) NULL,
title nvarchar(200) NULL,
movie_id varchar(255) NULL,
original_language char(2) NULL,
overview nvarchar(1000) NULL,
popularity float NULL,
release_date datetime NULL,
genre nvarchar(100) NULL,
director nvarchar(100)
)
Here is an update statement to populate the columns:
UPDATE t
SET t.title = j.title, t.movie_id = j.id, t.original_language = j.original_language,
t.overview = j.overview, t.popularity = j.popularity, t.release_date = j.release_date,
t.genre = ISNULL(JSON_VALUE(t.jsondata,'$.genres[0].name'),''),
t.director = JSON_VALUE(t.jsondata,'$.credits.crew[0].name')
FROM tmdb t
CROSS APPLY OPENJSON(jsondata)
WITH(title nvarchar(200), id int, original_language char(2), overview nvarchar(max),
popularity float, release_date datetime,
genres nvarchar(max) as JSON,
credits nvarchar(max) as JSON
) AS j
My problem is getting the director name. Since within $.credits, there are cast and crew elements, and within those, potentially many entries each - I'm not clear how to parse through via JSON_QUERY or using CROSS APPLY to basically say, 'find the $.credits.crew.job = "Director", then give me the $.credits.crew.name'.
Ok, after the comments, I think I've got it now. I use OUTER APPLY for the Director, since I still want to get the movie info even if no Director is specified. This lead me to one other issue - when there was more than 1 Director on the movie. But I think I can deal with that.
UPDATE t
SET t.title = j.title, t.movie_id = j.id, t.original_language = j.original_language,
t.overview = j.overview, t.popularity = j.popularity, t.release_date = j.release_date,
t.genre = ISNULL(JSON_VALUE(t.jsondata,'$.genres[0].name'),''),
t.director = k.name
FROM tmdb t
CROSS APPLY OPENJSON(jsondata)
WITH (title nvarchar(200), id int, original_language char(2),
overview nvarchar(max), popularity float, release_date datetime,
credits nvarchar(max) as JSON
) AS j
OUTER APPLY OPENJSON(j.credits,'$.crew')
WITH (job nvarchar(50), name nvarchar(100)) AS k
WHERE k.job = 'Director' OR k.job IS NULL