I have the following SQL:
SELECT * FROM (SELECT t.id, t.summary, null as worker, tt.worked from ticket t
INNER JOIN (SELECT ticket, sum(seconds_worked)/3600.0 as worked FROM ticket_time GROUP BY ticket) tt ON tt.ticket=t.id
UNION ALL
SELECT ticket,null, tt.worker, sum(tt.seconds_worked)/3600.0 from ticket_time tt GROUP BY ticket,worker) as foo
WHERE id in ('9755, 9759') ORDER BY id
The ids string '9755, 9759' in the last line can and will change whenever the sql executed.
I can convert the sting to an array like this:
string_to_array('9755, 9759', ',')
But is there a way to convert this array of strings into array of integers?
Just cast the resulting array to an int[]
where id = ANY ( string_to_array('9755, 9759', ',')::int[] )
Related
I currently have a JSON output as an array in Athena:
This is the query Im running
WITH dataset AS (SELECT
Items
FROM
(SELECT * FROM (
SELECT
JSON_EXTRACT(message, '$.items') AS Items
FROM kafka.database
)))
select * from dataset
LIMIT 10
And this is the current Ouput
["item0","item1","item2","item3"]
But would like to generate the Ouput from AWS Athena in this way:
"item0,item1,item2,item3"
I have tried to follow this steps from Athena documentation but it's not working:
WITH dataset AS (SELECT
Items
FROM
(SELECT * FROM (
SELECT
array_join(JSON_EXTRACT(message, '$.items'),' ') AS Items
FROM kafka.database
)))
select * from dataset
LIMIT 10
But for example, in this way, I am able to select the first Item in the JSON output.
WITH dataset AS (SELECT
Items
FROM
(SELECT * FROM (
SELECT
json_array_get(JSON_EXTRACT(message, '$.items'),0) AS Items
FROM kafka.database
)))
select * from dataset
LIMIT 10
JSON_EXTRACT does not return an array, it returns value of json type, so directly manipulating it as an array is not supported. One way to handle it is to cast it to array(varchar) and use array_join on it:
-- sample data
WITH dataset (json_arr) AS (
VALUES (json '["item0","item1","item2","item3"]')
)
-- query
select array_join(cast(json_arr as array(varchar)), ', ')
from dataset;
Output:
_col0
item0, item1, item2, item3
I have a BigQuery column which contains STRING values like
col1
[{"a":1,"b":2},{"a":2,"b":3}]
[{"a":3,"b":4},{"a":5,"b":6}]
Now when doing a SELECT for each I want to get just the max. value of "a" in each json array for example here I would want the output of the SELECT on the table to be
2
5
Any ideas please? Thanks!
Use JSON_EXTRACT_ARRAY() to retrieve each array element. Then JSON_EXTRACT_VALUE():
with t as (
select '[{"a":1,"b":2},{"a":2,"b":3}]' as col union all
select '[{"a":3,"b":4},{"a":5,"b":6}]'
)
select t.*,
(select max(json_value(el, '$.a'))
from unnest(JSON_QUERY_ARRAY(col, '$')) el
)
from t;
I have a table that contains comma-separated values in a column In Postgres.
ID PRODS
--------------------------------------
1 ,142,10,75,
2 ,142,87,63,
3 ,75,73,2,58,
4 ,142,2,
Now I want a query where I can give a comma-separated string and it will tell me the number of matches between the input string and the string present in the row.
For instance, for input value ',142,87,', I want the output like
ID PRODS No. of Match
------------------------------------------------------------------------
1 ,142,10,75, 1
2 ,142,87,63, 2
3 ,75,73,2,58, 0
4 ,142,2, 1
Try this:
SELECT
*,
ARRAY(
SELECT
*
FROM
unnest(string_to_array(trim(both ',' from prods), ','))
WHERE
unnest = ANY(string_to_array(',142,87,', ','))
)
FROM
prods_table;
Output is:
1 ,142,10,75, {142}
2 ,142,87,63, {142,87}
3 ,75,73,2,58, {}
4 ,142,2, {142}
Add the cardinality(anyarray) function to the last column to get just a number of matches.
And consider changing your database design.
Check This.
select T.*,
COALESCE(No_of_Match,'0')
from TT T Left join
(
select ID,count(ID) No_of_Match
from (
select ID,unnest(string_to_array(trim(t.prods, ','), ',')) A
from TT t)a
Where A in ('142','87')
group by ID
)B
On T.Id=b.id
Demo Here
OutPut
If you install the intarray extension, this gets quite easy:
select id, prods, cardinality(string_to_array(trim(prods, ','), ',')::int[] & array[142,87])
from bad_design;
Otherwise it's a bit more complicated:
select bd.id, bd.prods, m.matches
from bad_design bd
join lateral (
select bd.id, count(v.p) as matches
from unnest(string_to_array(trim(bd.prods, ','), ',')) as l(p)
left join (
values ('142'),('87') --<< these are your input values
) v(p) on l.p = v.p
group by bd.id
) m on m.id = bd.id
order by bd.id;
Online example: http://rextester.com/ZIYS97736
But you should really fix your data model.
with data as
(
select *,
unnest(string_to_array(trim(both ',' from prods), ',') ) as v
from myTable
),
counts as
(
select id, count(t) as c from data
left join
( select unnest(string_to_array(',142,87,', ',') ) as t) tmp on tmp.t = data.v
group by id
order by id
)
select t1.id, t1.prods, t2.c as "No. of Match"
from myTable t1
inner join counts t2 on t1.id = t2.id;
I'm trying to pull an array of INT64 s in BigQuery standard SQL from a column which is a long string of numbers separated by commas (for example, 2013,1625,1297,7634). I can pull an array of strings easily with:
SELECT
SPLIT(string_col,",")
FROM
table
However, I want to return an array of INT64 s, not an array of strings. How can I do that? I've tried
CAST(SPLIT(string_col,",") AS ARRAY<INT64>)
but that doesn't work.
Below is for BigQuery Standard SQL
#standardSQL
WITH yourTable AS (
SELECT 1 AS id, '2013,1625,1297,7634' AS string_col UNION ALL
SELECT 2, '1,2,3,4,5'
)
SELECT id,
(SELECT ARRAY_AGG(CAST(num AS INT64))
FROM UNNEST(SPLIT(string_col)) AS num
) AS num,
ARRAY(SELECT CAST(num AS INT64)
FROM UNNEST(SPLIT(string_col)) AS num
) AS num_2
FROM yourTable
Mikhail beat me to it and his answer is more extensive but adding this as a more minimal repro:
SELECT CAST(num as INT64) from unnest(SPLIT("2013,1625,1297,7634",",")) as num;
I use the bellow query to extract a value from a column that stores JSON objects.
The issue with it, it does only pull the first value matching to the regex inside SUBSTRING which is -$4,000.00, is there's a parameter to pass to the SUBSTRING to pull the value -$1,990.00 as well in another column.
SELECT attribute_actions_text
, SUBSTRING(attribute_actions_text FROM '"Member [Dd]iscount:":"(.+?)"') AS column_1
, '' AS column_2
FROM (
VALUES
('[{"Member Discount:":"-$4,000.00"},{"Member discount:":"-$1,990.00"}]')
, (NULL)
) ls(attribute_actions_text)
Desired result :
column_1 column_2
-$4,000.00 -$1,990.00
Try this
WITH data(id,attribute_actions_text) as (
VALUES
(1,'[{"Member Discount:":"-$4,000.00"},{"Member Discount:":"-$1,990.00"}]')
, (2,'[{"Member Discount:":"-$4,200.00"},{"Member Discount:":"-$1,890.00"}]')
, (3,NULL)
), match as (
SELECT
id,
m,
ROW_NUMBER()
OVER (PARTITION BY id) AS r
FROM data, regexp_matches(data.attribute_actions_text, '"Member [Dd]iscount:":"(.+?)"', 'g') AS m
)
SELECT
id
,(select m from match where id = d.id AND r=1) as col1
,(select m from match where id = d.id AND r=2) as col2
FROM data d
Result
1,"{-$4,000.00}","{-$1,990.00}"
2,"{-$4,200.00}","{-$1,890.00}"
3,NULL,NULL