SELECT cc.clientid
FROM customer_client cc
GROUP BY cc.clientid
HAVING SUM(CASE WHEN cc.customerid IN (4567, 5678) THEN 1 ELSE 0 END) = COUNT(*)
AND COUNT(*) = 2;
I'm calling this query in a Db2 stored procedure where in I've to pass the list of customer id - any working suggestion?
I've tried passing it as below in procedure
CREATE PROCEDURE Find_Client_Customers (
IN IN_CUSTIDS VARCHAR(1000),
IN IN_CUST_COUNT INT)
but this is passing the list as a string.
You may use a string tokenizer:
create function regexp_tokenize_number(
source varchar(1024)
, pattern varchar(128))
returns table (seq int, tok bigint)
contains sql
deterministic
no external action
return
select seq, tok
from xmltable('for $id in tokenize($s, $p) return <i>{string($id)}</i>'
passing
source as "s"
, pattern as "p"
columns
seq for ordinality
, tok bigint path 'if (. castable as xs:long) then xs:long(.) else ()'
) t;
select *
from table(regexp_tokenize_number('123, 456', ',')) t;
SEQ TOK
--- ---
1 123
2 456
In your case:
SELECT cc.clientid
FROM customer_client cc
GROUP BY cc.clientid
HAVING SUM(CASE WHEN cc.customerid IN
(
select t.tok
from table(regexp_tokenize_number('4567, 5678', ',')) t
) THEN 1 ELSE 0 END) = COUNT(*)
AND COUNT(*) = 2;
Related
I have columns in bigquery like this:
expected output:
I am trying to merge columns into json using bigquery.
I am taking letter before underscore(common name ) as column then converting.
I am trying this query:
with selectdata as (
SELECT a_firstname, a_middlename,a_lastname FROM `account_id.Dataset.Table_name`
)
select TO_JSON_STRING(t) AS json_data FROM selectdata AS t;
How can I join columns with condition or with case to achieve this output in bigquery
Consider below approach
create temp function extract_keys(input string) returns array<string> language js as """
return Object.keys(JSON.parse(input));
""";
create temp function extract_values(input string) returns array<string> language js as """
return Object.values(JSON.parse(input));
""";
select * except(row_id) from (
select format('%t',t) row_id,
split(key, '_')[offset(0)] as col,
'{' || string_agg(format('"%s":"%s"', split(key, '_')[safe_offset(1)], value)) || '}' as value
from your_table t, unnest(extract_keys(to_json_string(t))) key with offset
join unnest(extract_values(to_json_string(t))) value with offset
using(offset)
group by row_id, col
)
pivot (any_value(value) for col in ('a','b','c'))
if applied to sample data in your question - output is
There is a scenario where I receive a string to the bigquery function and need to use it as a column name.
here is the function
CREATE OR REPLACE FUNCTION METADATA.GET_VALUE(column STRING, row_number int64) AS (
(SELECT column from WORK.temp WHERE rownumber = row_number)
);
When I call this function as select METADATA.GET_VALUE("TXCAMP10",149); I get the value as TXCAMP10 so we can say that it is processed as SELECT "TXCAMP10" from WORK.temp WHERE rownumber = 149 but I need it as SELECT TXCAMP10 from WORK.temp WHERE rownumber = 149 which will return some value from temp table lets suppose the value as A
so ultimately I need value A instead of column name i.e. TXCAMP10.
I tried using execute immediate like execute immediate("SELECT" || column || "from WORK.temp WHERE rownumber =" ||row_number) from this stack overflow post to resolve this issue but turns out I can't use it in a function.
How do I achieve required result?
I don't think you can achieve this result with the help of UDF in standard SQL in BigQuery.
But it is possible to do this with stored procedures in BigQuery and EXECUTE IMMEDIATE statement. Consider this code, which simulates the situation you have:
create or replace table d1.temp(
c1 int64,
c2 int64
);
insert into d1.temp values (1, 1), (2, 2);
create or replace procedure d1.GET_VALUE(column STRING, row_number int64, out result int64)
BEGIN
EXECUTE IMMEDIATE 'SELECT ' || column || ' from d1.temp where c2 = ?' into result using row_number;
END;
BEGIN
DECLARE result_c1 INT64;
call d1.GET_VALUE("c1", 1, result_c1);
select result_c1;
END;
After some research and trial-error methods, I used this workaround to solve this issue. It may not be the best solution when you have too many columns but it surely works.
CREATE OR REPLACE FUNCTION METADATA.GET_VALUE(column STRING, row_number int64) AS (
(SELECT case
when column_name = 'a' then a
when column_name = 'b' then b
when column_name = 'c' then c
when column_name = 'd' then d
when column_name = 'e' then e
end from WORK.temp WHERE rownumber = row_number)
);
And this gives the required results.
Point to note: the number of columns you use in the case statement should be of the same datatype else it won't work
I have to calculate the total num of positive and (negative+null or empty values) from the table basically 2 values . I have the below query to list the negative and null and positive values .. but i want the entire count . please assist.
SELECT
ARRAY(
SELECT count(value),
FROM UNNEST(event_data_results) where REGEXP_CONTAINS(name, r'data.result.result') and ((REGEXP_CONTAINS(value, r'^-?\d+$') and SAFE_CAST(value AS INT64) <= 0 ))) AS negative_attributes,
ARRAY(
SELECT count(value) as neg_val,
FROM UNNEST(event_data_results) where value = 'null' or value='' ) AS null_attributes,
ARRAY(
SELECT count(value),
FROM UNNEST(event_data_results) where REGEXP_CONTAINS(name, r'data.result.result') and (REGEXP_CONTAINS(value, r'^-?\d+$') and SAFE_CAST(value AS INT64) > 0 )) AS positive_attributes
FROM `table` where EXISTS (SELECT 1 FROM UNNEST(event_keys) as keys , UNNEST(event_data_results) as results WHERE keys.value = "attribute")
event_keys,event_data_results , data_metrics all are repeatable struct
result should be postive : 4 negative+null :4
Below is for BigQuery Standard SQL
#standardSQL
SELECT
COUNTIF(result.value > 0) positive_attributes,
COUNTIF(result.value < 0) negative_attributes,
COUNTIF(IFNULL(result.value, 0) = 0) null_or_zero_attributes
FROM `project.dataset.table`,
UNNEST(event_data_results) AS result
WHERE EXISTS (
SELECT 1
FROM UNNEST(event_keys) AS key
WHERE key.value = "attribute"
)
you can add here whatever conditions you need
Also, if result.value is a string - you can use SAFE_CAST(result.value AS INT64) as you already do so i was not focusing on this aspect of your case
I am trying to write a sql in bigquery and I have a requirement to filter records based on a group by column and another column in the table
what I mean is I want to check if the group by column(column name:mnt) has more than one row then I have to check if col2 (col name: zel) value, then I have to apply a filter saying col2 ='X' and only pass that record else pass i.e dont filter the records if the col1 has only distinct one value per group
So I have written a sql to do this I have used row_number as well as rank , dense rank function but I noticed the value of rank and dense rank and row number functions return same value for a group
Please see the below code
#standardsql
with t1 as (SELECT mnt,
case when rank() over (partition by ltrim(rtrim(mnt)) order by
ltrim(rtrim(mnt)) asc) >1 then 'Y' else 'N' end
as flag,
rank() over (partition by mnt order by mnt) as rn,
dense_rank() over (partition by mnt order by mnt) as drn, FROM
projectname.datasetname.tablename1),
t2 as ( SELECT
mnt,
rel,
lif,
lts,
lokez FROM projectname.datasetname.tablename2
WHERE lts <> "" AND _PARTITIONTIME = TIMESTAMP(CURRENT_DATE()) ) ,
t3 as (SELECT
lif,
lifn,
lts,
par FROM `projectname.datasetname.tablename3`)
,t4 as (SELECT rcv FROM `projectname.datasetname.tablename4` WHERE mes
= 'PRO')
select * from (
SELECT t1.mnt as mnt,
t1.flag,
t1.rn,
t1.drn
t2.rel as zel,
t2.lokez as ZLOEKZ,
t4.rcv as Zrcv
FROM t1 left join t2 on replace(t1.mnt, '00000000', '') =
REPLACE(t2.mnt, '00000000', '') AND t1.lif = t2.lif and t2.lts <> ""
and
case when t1.flag = 'Y' and t2.rel ='X' then 1
when (t1.flag ='N' and t2.rel=t2.rel) or (t1.flag ='N' and t2.rel
is null) then 1
when t1.flag = 'Y' and t2.rel <>'X' then 2
else 3
end = 1
left join t3 ON t1.lif = t3.lif AND t2.lts = t3.lts AND
t3.par = 'BA' left join t4 on t4.rcv = t3.lifn and t2.lokez is null )
where ZLOEKZ is null order by mnt
As you can see I am using a case statement and even it seems to be not working fine. I am pasting the case condition below again
case when t1.flag = 'Y' and t2.rel ='X' then 1
when (t1.flag ='N' and t2.rel=t2.rel) or (t1.flag ='N' and
t2.rel
is null) then 1
when t1.flag = 'Y' and t2.rel <>'X' then 2
else 3
end = 1
But the expected record count did not match so I added the above sql lines to see if my analytical functions were giving me result I wanted
rank() over (partition by mnt order by mnt) as rn,
dense_rank() over (partition by mnt order by mnt) as drn
strangely for same mnt number the rank , dense rank and row_number function are assigning the same value what am i doing wrong here.
mnt flag rn drn rel lokez rcv
100 N 1 1 X abc 123
100 N 1 1 null xyz 123
100 N 1 1 null def 234
This is my output
I mean as per my code for same mnt number I am seeing flag set to N instead of Y and for the rank and dense rank are giving me same number for all 3 mnt it is generating 1 instead of 123 (note for rank function I understand) but dense rank should not do that
I tried to convey the issue as efficiently as I could please let me know if there is any clarifications I can provide.
any help appreciated
thanks
SELECT * EXCEPT(ct) FROM (
SELECT *, COUNT() OVER(PARTITION BY mnt) AS ct
) WHERE ct=1 or zel='X'
This is the code snippet for the problem you mentioned. Use this in your code according to the logic.
In one of the column I have role and organization position
Example postion is 1 and organization is 310492 ...
1|310492|1|12319|1|562548|1|5202558
I need to convert this string to multiple rows
1,310492
1,12319
1,562548
1,5202558
I can not use WITH clause as I need to have is as correlated subquery
SELECT EXTRACT (VALUE (d), '//row/text()').getstringval ()
FROM (SELECT XMLTYPE ( '<rows><row>' || REPLACE (USERPROF.FIELD1, '|', '</row><row>') || '</row></rows>' ) AS xmlval FROM USERPROF WHERE FIELD1 IS NOT NULL ) x, TABLE (XMLSEQUENCE (EXTRACT (x.xmlval, '/rows/row'))) d
however this is converting entire string to multiple rows.
I tried playing with regexp and connect which is not helping me but fetching content of entire table by ignore where condition.
select regexp_substr(FIELD1,'[^|]+', 1, LEVEL) from USERPROF WHERE USERS_ID = 23502
connect by regexp_substr(FIELD1, '[^|]+', 1, level ) is not null;
Thanks in advance.
The SQL below:
with data as
(select '1|310492|1|12319|1|562548|1|5202558' as x from dual)
select fin from(
select 1+level-1 as occurrence
, instr(x,'|',1,1+level-1) as pos
, nvl(lead(instr(x,'|',1,1+level-1),1) over (order by 1+level-1)
, length(x))
as xxxx
, case when
nvl(lead(instr(x,'|',1,1+level-1),1) over (order by 1+level-1)
, length(x)) = length(x)
then instr(x,'|',1,1+level-1)
else
nvl(lag(instr(x,'|',1,1+level-1),1) over (order by 1+level-1),1) end as yyyy
, substr(x
,case when
nvl(lead(instr(x,'|',1,1+level-1),1) over (order by 1+level-1)
, length(x)) = length(x)
then instr(x,'|',1,1+level-1)
else
nvl(lag(instr(x,'|',1,1+level-1),1) over (order by 1+level-1),1) end
,nvl(lead(instr(x,'|',1,1+level-1),1) over (order by 1+level-1)
, length(x))
- case when
nvl(lead(instr(x,'|',1,1+level-1),1) over (order by 1+level-1)
, length(x)) = length(x)
then instr(x,'|',1,1+level-1)
else
nvl(lag(instr(x,'|',1,1+level-1),1) over (order by 1+level-1),1) end
) as fin
, length(x) as lastrw
from data
connect by level <= length(x) - length(replace(x, '|')) - 1
order by 1) x
where mod(occurrence,2) = 1 or xxxx = lastrw
Results in:
FIN
1|310492
|1|12319
|1|562548
|1|520255
Note that I'm just using the with clause to use the data you gave as an example.