I have a query which updates the records based on variables old_id and new_id. But condition is I need to fetch the variables dynamically. Here is simple query which I am using.
do
$$
declare
old_id bigint = 1561049391647687270;
declare new_id bigint = 2068236279446765699;
begin
update songs set poet_id = new_id where poet_id = old_id;
update poets set active = true where id = new_id;
update poets set deleted = true where id = old_id;
end
$$;
I need to assign the old_id and new_id dynamically
do
$$
declare
su record;
pc record;
old_id bigint;
new_id bigint;
begin
for pc in select name, count(name)
from poets
where deleted = false
group by name
having count(name) > 1
order by name
loop
for su in select * from poets where name ilike pc.name
loop
-- old_id could be null where I have 2 continue the flow without update
for old_id in (select id from su where su.link is null)
loop
raise notice 'old: %', old_id;
end loop;
-- new_id could be more than 2 skip this condition as well
for new_id in (select id from su where su.link is not null)
loop
raise notice 'new: %', new_id;
end loop;
end loop;
-- run the statement_1 example if new_id and old_id is not null
end loop;
end
$$;
The expected problem statement (to assign variable and use it in further execution) is with in comment.
(a) In your first "simple query", the update of the table poets could be automatically executed by a trigger function defined on the table songs :
CREATE OR REPLACE FUNCTION songs_update_id ()
RETURNS trigger LANGUAGE plpgsql AS
$$
BEGIN
UPDATE poets SET active = true WHERE id = NEW.poet_id ;
UPDATE poets SET deleted = true WHERE id = OLD.poet_id ; -- SET active = false to be added ?
END ;
$$ ;
CREATE OR REPLACE TRIGGER songs_update_id AFTER UPDATE OF id ON songs
FOR EACH ROW EXECUTE songs_update_id () ;
Your first query can then be reduced as :
do
$$
declare
old_id bigint = 1561049391647687270;
declare new_id bigint = 2068236279446765699;
begin
update songs set poet_id = new_id where poet_id = old_id;
end
$$;
(b) The tables update could be performed with a sql query instead of a plpgsql loop and with better performances :
do
$$
BEGIN
UPDATE songs
SET poet_id = list.new_id[1]
FROM
( SELECT b.name
, array_agg(b.id) FILTER (WHERE b.link IS NULL) AS old_id
, array_agg(b.id) FILTER (WHERE b.link IS NOT NULL) AS new_id
FROM
( SELECT name
FROM poets
WHERE deleted = false
GROUP BY name
HAVING COUNT(*) > 1
-- ORDER BY name -- this ORDER BY sounds like useless and resource-intensive
) AS a
INNER JOIN poets AS b
ON b.name ilike a.name
GROUP BY b.name
HAVING array_length(old_id, 1) = 1
AND array_length(new_id, 1) = 1
) AS list
WHERE poet_id = list.old_id[1] ;
END ;
$$;
This solution is not tested yet and could have to be adjusted in order to work correctly. Please provide the tables definition of songs and poets and a sample of data in dbfiddle so that I can test and adjust the proposed solution.
I have this select statement inside a trigger procedure:
SELECT 1 FROM some_table WHERE "user_id" = new."user_id"
AND created >= now()::date;
How can i store result in a variable and reuse it in IF statement like this:
IF NOT EXISTS (var_name) THEN ...;
procedure (for now i have select right in IF statement, but i want it separately)
CREATE OR REPLACE FUNCTION add_row() RETURNS TRIGGER AS $$
BEGIN
//need to check if row was created around today
IF NOT EXISTS (SELECT 1 FROM some_table WHERE "user_id" = new."user_id"
AND created >= now()::date) THEN
INSERT INTO another_table VALUES(1, 2, 3);
END IF;
END;
$$ LANGUAGE plpgsql;
To store the result of a query into a variable, you need to declare a variable. Then you can use select .. into .. to store the result. But I would use a boolean and an exists condition for this purpose.
CREATE OR REPLACE FUNCTION add_row()
RETURNS TRIGGER
AS $$
declare
l_row_exists boolean;
BEGIN
select exists (SELECT *
FROM some_table
WHERE user_id = new.user_id
AND created >= current_date)
into l_row_exists;
IF NOT l_row_exists THEN
INSERT INTO another_table (col1, col2, col3)
VALUES(1, 2, 3);
END IF;
END;
$$ LANGUAGE plpgsql;
However, you don't really need an IF statement to begin with. You can simplify this to a single INSERT statement:
INSERT INTO another_table (col1, col2, col3)
SELECT 1,2,3
WHERE NOT EXISTS (SELECT *
FROM some_table
WHERE user_id = new.user_id
AND created >= current_date);
this is my function:
CREATE OR REPLACE FUNCTION SANDBOX.DAILYVERIFY_DATE(TABLE_NAME regclass, DATE_DIFF INTEGER)
RETURNS void AS $$
DECLARE
RESULT BOOLEAN;
DATE DATE;
BEGIN
EXECUTE 'SELECT VORHANDENES_DATUM AS DATE, CASE WHEN DATUM IS NULL THEN FALSE ELSE TRUE END AS UPDATED FROM
(SELECT DISTINCT DATE VORHANDENES_DATUM FROM ' || TABLE_NAME ||
' WHERE DATE > CURRENT_DATE -14-'||DATE_DIFF|| '
) A
RIGHT JOIN
(
WITH compras AS (
SELECT ( NOW() + (s::TEXT || '' day'')::INTERVAL )::TIMESTAMP(0) AS DATUM
FROM generate_series(-14, -1, 1) AS s
)
SELECT DATUM::DATE
FROM compras)
B
ON DATUM = VORHANDENES_DATUM'
INTO date,result;
RAISE NOTICE '%', result;
INSERT INTO SANDBOX.UPDATED_TODAY VALUES (TABLE_NAME, DATE, RESULT);
END;
$$ LANGUAGE plpgsql;
It is supposed to upload rows into the table SANDBOX.UPDATED_TODAY, which contains table name, a date and a boolean.
The boolean shows, whether there was an entry for that date in the table. The whole part, which is inside of EXECUTE ... INTO works fine and gives me those days.
However, this code only inserts the first row of the query's result. What I want is that all 14 rows get inserted. Obviously, I need to change it into something like a loop or something completely different, but how exactly would that work?
Side note: I removed some unnecessary parts regarding those 2 parameters you can see. It does not have to do with that at all.
Put the INSERT statement inside the EXECUTE. You don't need the result of the SELECT for anything other than inserting it into that table, right? So just insert it directly as part of the same query:
CREATE OR REPLACE FUNCTION SANDBOX.DAILYVERIFY_DATE(TABLE_NAME regclass, DATE_DIFF INTEGER)
RETURNS void AS
$$
BEGIN
EXECUTE
'INSERT INTO SANDBOX.UPDATED_TODAY
SELECT ' || QUOTE_LITERAL(TABLE_NAME) || ', VORHANDENES_DATUM, CASE WHEN DATUM IS NULL THEN FALSE ELSE TRUE END
FROM (
SELECT DISTINCT DATE VORHANDENES_DATUM FROM ' || TABLE_NAME ||
' WHERE DATE > CURRENT_DATE -14-'||DATE_DIFF|| '
) A
RIGHT JOIN (
WITH compras AS (
SELECT ( NOW() + (s::TEXT || '' day'')::INTERVAL )::TIMESTAMP(0) AS DATUM
FROM generate_series(-14, -1, 1) AS s
)
SELECT DATUM::DATE
FROM compras
) B
ON DATUM = VORHANDENES_DATUM';
END;
$$ LANGUAGE plpgsql;
The idiomatic way to loop through dynamic query results would be
FOR date, result IN
EXECUTE 'SELECT ...'
LOOP
INSERT INTO ...
END LOOP;
DROP FUNCTION IF EXISTS top_5(customers.customerid%TYPE, products.prod_id%TYPE, orderlines.quantity%TYPE) CASCADE;
CREATE OR REPLACE FUNCTION top_5(c_id customers.customerid%TYPE, p_id products.prod_id%TYPE, quant orderlines.quantity%TYPE)
RETURNS orders.orderid%TYPE AS $$
DECLARE
top_prod CURSOR IS
SELECT inv.prod_id
FROM inventory AS inv, products AS prod
WHERE inv.prod_id=prod.prod_id
ORDER BY inv.quan_in_stock desc, inv.sales
limit 5;
ord_id orders.orderid%TYPE;
ord_date orders.orderdate%TYPE:= current_date;
ordln_id orderlines.orderlineid%TYPE:=1;
BEGIN
SELECT nova_orderid() INTO ord_id;
INSERT INTO orders(orderid, orderdate,customerid,netamount,tax,totalamount) VALUES(ord_id,ord_date,c_id,0,0,0);
PERFORM compra(c_id, p_id, 1::smallint, ord_id, ordln_id, ord_date);
IF (p_id = top_prod) THEN
UPDATE orders
SET totalamount = totalamount - (totalamount*0.2)
WHERE ord_id = (SELECT MAX(ord_id) FROM orders);
END IF;
END;
$$ LANGUAGE plpgsql;
I have the following code and when i try to execute this
SELECT top_5(1,1,'2');
i have this error
ERROR: operator does not exist: integer = refcursor
LINE 1: SELECT (p_id = top_prod)
You need to get the 'prod_id' value from the cursor 'top_prod'.
You cannot compare two types.
Try this,
DECLARE
top_prod_id top_prod%ROWTYPE;
BEGIN
OPEN top_prod;
LOOP
FETCH top_prod INTO top_prod_id;
EXIT WHEN top_prod %NOTFOUND;
IF (p_id = top_prod_id) THEN
UPDATE orders
SET totalamount = totalamount - (totalamount*0.2)
WHERE ord_id = (SELECT MAX(ord_id) FROM orders);
END IF;
END LOOP;
CLOSE top_prod;
END;
Assuming a schema like the following:
CREATE TABLE node (
id SERIAL PRIMARY KEY,
name VARCHAR,
parentid INT REFERENCES node(id)
);
Further, let's assume the following data is present:
INSERT INTO node (name,parentid) VALUES
('A',NULL),
('B',1),
('C',1);
Is there a way to prevent cycles from being created? Example:
UPDATE node SET parentid = 2 WHERE id = 1;
This would create a cycle of 1->2->1->...
Your trigger simplified and optimized, should be considerably faster:
CREATE OR REPLACE FUNCTION detect_cycle()
RETURNS TRIGGER
LANGUAGE plpgsql AS
$func$
BEGIN
IF EXISTS (
WITH RECURSIVE search_graph(parentid, path, cycle) AS ( -- relevant columns
-- check ahead, makes 1 step less
SELECT g.parentid, ARRAY[g.id, g.parentid], (g.id = g.parentid)
FROM node g
WHERE g.id = NEW.id -- only test starting from new row
UNION ALL
SELECT g.parentid, sg.path || g.parentid, g.parentid = ANY(sg.path)
FROM search_graph sg
JOIN node g ON g.id = sg.parentid
WHERE NOT sg.cycle
)
SELECT FROM search_graph
WHERE cycle
LIMIT 1 -- stop evaluation at first find
)
THEN
RAISE EXCEPTION 'Loop detected!';
ELSE
RETURN NEW;
END IF;
END
$func$;
You don't need dynamic SQL, you don't need to count, you don't need all the columns and you don't need to test the whole table for every single row.
CREATE TRIGGER detect_cycle_after_update
AFTER INSERT OR UPDATE ON node
FOR EACH ROW EXECUTE PROCEDURE detect_cycle();
An INSERT like this has to be prohibited, too:
INSERT INTO node (id, name,parentid) VALUES (8,'D',9), (9,'E',8);
To answer my own question, I came up with a trigger that prevents this:
CREATE OR REPLACE FUNCTION detect_cycle() RETURNS TRIGGER AS
$func$
DECLARE
loops INTEGER;
BEGIN
EXECUTE 'WITH RECURSIVE search_graph(id, parentid, name, depth, path, cycle) AS (
SELECT g.id, g.parentid, g.name, 1,
ARRAY[g.id],
false
FROM node g
UNION ALL
SELECT g.id, g.parentid, g.name, sg.depth + 1,
path || g.id,
g.id = ANY(path)
FROM node g, search_graph sg
WHERE g.id = sg.parentid AND NOT cycle
)
SELECT count(*) FROM search_graph where cycle = TRUE' INTO loops;
IF loops > 0 THEN
RAISE EXCEPTION 'Loop detected!';
ELSE
RETURN NEW;
END IF;
END
$func$ LANGUAGE plpgsql;
CREATE TRIGGER detect_cycle_after_update
AFTER UPDATE ON node
FOR EACH ROW EXECUTE PROCEDURE detect_cycle();
So, if you try to create a loop, like in the question:
UPDATE node SET parentid = 2 WHERE id = 1;
You get an EXCEPTION:
ERROR: Loop detected!
CREATE OR REPLACE FUNCTION detect_cycle()
RETURNS TRIGGER AS
$func$
DECLARE
cycle int[];
BEGIN
EXECUTE format('WITH RECURSIVE search_graph(%4$I, path, cycle) AS (
SELECT g.%4$I, ARRAY[g.%3$I, g.%4$I], (g.%3$I = g.%4$I)
FROM %1$I.%2$I g
WHERE g.%3$I = $1.%3$I
UNION ALL
SELECT g.%4$I, sg.path || g.%4$I, g.%4$I = ANY(sg.path)
FROM search_graph sg
JOIN %1$I.%2$I g ON g.%3$I = sg.%4$I
WHERE NOT sg.cycle)
SELECT path
FROM search_graph
WHERE cycle
LIMIT 1', TG_TABLE_SCHEMA, TG_TABLE_NAME, quote_ident(TG_ARGV[0]), quote_ident(TG_ARGV[1]))
INTO cycle
USING NEW;
IF cycle IS NULL
THEN
RETURN NEW;
ELSE
RAISE EXCEPTION 'Loop in %.% detected: %', TG_TABLE_SCHEMA, TG_TABLE_NAME, array_to_string(cycle, ' -> ');
END IF;
END
$func$ LANGUAGE plpgsql;
CREATE TRIGGER detect_cycle_after_update
AFTER INSERT OR UPDATE ON node
FOR EACH ROW EXECUTE PROCEDURE detect_cycle('id', 'parent_id');
While the current accepted answer by #Erwin Brandstetter is ok when you process one update/insert at a time, it still can fail when considering concurrent execution.
Assume the table content defined by
INSERT INTO node VALUES
(1, 'A', NULL),
(2, 'B', 1),
(3, 'C', NULL),
(4, 'D', 3);
and then in one transaction, execute
-- transaction A
UPDATE node SET parentid = 2 where id = 3;
and in another
-- transaction B
UPDATE node SET parentid = 4 where id = 1;
Both UPDATE commands will succeed, and you can afterwards commit both transactions.
-- transaction A
COMMIT;
-- transaction B
COMMIT;
You will then have a cycle 1->4->3->2->1 in the table.
To make it work, you will either have to use isolation level SERIALIZABLE or use explicit locking in the trigger.
slightly different from Erwin's
CREATE OR REPLACE FUNCTION detect_cycle ()
RETURNS TRIGGER
LANGUAGE plpgsql
AS $func$
BEGIN
IF EXISTS ( WITH RECURSIVE search_graph (
id,
name,
parentid,
is_cycle,
path
) AS (
SELECT *, FALSE,ARRAY[ROW (n.id,n.parentid)]
FROM
node n
WHERE
n.id = NEW.id
UNION ALL
SELECT
n.*,
ROW (n.id,n.parentid) = ANY (path),
path || ROW (n.id,n.parentid)
FROM
node n,
search_graph sg
WHERE
n.id = sg.parentid
AND NOT is_cycle
)
SELECT *
FROM
search_graph
WHERE
is_cycle
LIMIT 1) THEN
RAISE EXCEPTION 'Loop detected!';
ELSE
RETURN new;
END IF;
END
$func$;