Table source contains integer column. Its values should be passed to Postgresql 12 function for selecting data from other table.
I tried to use array
CREATE OR REPLACE FUNCTION public.TestAddAssetTransactions(dokumnrs int[])
RETURNS int AS
$BODY$
with i1 as (
INSERT INTO bilkaib (dokumnr)
select dokumnr from dok where dokumnr in (select * from unnest(dokumnrs))
returning *
)
select count(*) from i1;
$BODY$ language sql;
create temp table bilkaib (dokumnr int ) on commit drop;
create temp table dok (dokumnr serial primary key ) on commit drop;
create temp table source (dokumnr int ) on commit drop;
insert into source values (1),(2);
select TestAddAssetTransactions( (select ARRAY[dokumnr] from source)::int[] )
but got error
ERROR: more than one row returned by a subquery used as an expression
How to pass single column values from table rows to function? Should array, table type or temp table used?
Using Postgresql 12+
You need to aggregate the ints in your function call. Otherwise you're just casting each value to a single-element array and they try to cast a column to an array of int.
select TestAddAssetTransactions( (select array_agg(dokumnr)::int[] from source) );
online demo
Related
I have a table
CREATE TABLE items(
id SERIAL PRIMARY KEY,
group_id INT NOT NULL,
item_id INT NOT NULL,
name TEXT,
.....
.....
);
I am creating a function that
takes set of row values for a single group_id, fail if multiple group_ids present in in input rows
compares it with matching values in the table (only for that group_id
updates changed values (only for the input group_id)
inserts new values
deletes table rows that are absent in the row input (compare rows with group_id and item_id)(only for the input group_id)
this is my function definition
CREATE OR REPLACE FUNCTION update_items(rows_input items[]) RETURNS boolean as $$
DECLARE
rows items[];
group_id_input integer;
BEGIN
-- get single group_id from input rows, fail if multiple group_id's present in input
-- read items of that group_id in table
-- compare input rows and table rows (of the same group_id)
-- create transaction
-- delete absent rows
-- upsert
-- return success of transaction (boolean)
END;
$$ LANGUAGE plpgsql;
I am trying to call the function in a query
select update_items(
(38,1,1283,"Name1"),
(39,1,1471,"Name2"),
(40,1,1333,"Name3")
);
I get the following error
Failed to run sql query: column "Name1" does not exist
I tried removing the id column values: that gives me the same error
What is the correct way to pass row values to a function that accepts table type array as arguments?
updates changed values
inserts new values deletes table rows that are
absent in the row input (compare rows with group_id and item_id)
If you want do upsert, you must upsert with unique constraint.
So there is two unique constraints. primary key(id), (group_id, item_id).
insert on conflict need consider these two unique constraint.
Since You want pass items[] type to the functions. So it also means that any id that is not in the input function arguments will also be deleted.
drop table if exists items cascade;
begin;
CREATE TABLE items(
id bigint GENERATED BY DEFAULT as identity PRIMARY KEY,
group_id INT NOT NULL,
item_id INT NOT NULL,
name TEXT
,unique(group_id,item_id)
);
insert into items values
(38,1,1283,'original_38'),
(39,1,1471,'original_39'),
(40,1,1333,'original_40'),
(42,1,1332,'original_42');
end;
main function:
CREATE OR REPLACE FUNCTION update_items (in_items items[])
RETURNS boolean
AS $FUNC$
DECLARE
iter items;
saved_ids bigint[];
BEGIN
saved_ids := (SELECT ARRAY (SELECT (unnest(in_items)).id));
DELETE FROM items
WHERE NOT (id = ANY (saved_ids));
FOREACH iter IN ARRAY in_items LOOP
INSERT INTO items
SELECT
iter.*
ON CONFLICT (id)
DO NOTHING;
INSERT INTO items
SELECT
iter.*
ON CONFLICT (group_id,
item_id)
DO UPDATE SET
name = EXCLUDED.name;
RAISE NOTICE 'rec.groupid: %, rec.items_id:%', iter.group_id, iter.item_id;
END LOOP;
RETURN TRUE;
END
$FUNC$
LANGUAGE plpgsql;
call it:
SELECT
*
FROM
update_items ('{"(38, 1, 1283, Name1) "," (39, 1, 1471, Name2) "," (40, 1, 1333, Name3)"}'::items[]);
references:
Iterating over integer[] in PL/pgSQL
How to match elements in an array of composite type?
IN vs ANY operator in PostgreSQL
Here's how I achieved UPSERT with DELETE missing rows, if anyone is looking to do the same.
CREATE OR REPLACE FUNCTION update_items(in_rows items[]) RETURNS INT AS $$
DECLARE
in_groups INTEGER[];
in_group_id INTEGER;
in_item_ids INTEGER[];
BEGIN
-- get single group id from input rows, fail if multiple group ids present in input
in_groups = (SELECT ARRAY (SELECT distinct(group_id) FROM UNNEST(in_rows)));
IF ARRAY_LENGTH(in_groups,1)>1 THEN
RAISE EXCEPTION 'Multiple group_ids found in input items: %', in_groups;
END IF;
in_group_id = in_groups[1];
-- delete items of this group that are absent in in_rows
in_item_ids := (SELECT ARRAY (SELECT (UNNEST(in_rows)).item_id));
DELETE FROM items
WHERE
master_code <> ANY (in_item_ids)
AND group_id = in_group_id;
-- upsert in_rows
INSERT INTO items
SELECT * FROM UNNEST(in_rows)
ON CONFLICT (group_id,item_d)
DO UPDATE SET
parent_group_id = EXCLUDED.parent_group_id,
mat_centre_id = EXCLUDED.mat_centre_id,
NAME = EXCLUDED.NAME,
opening_date = EXCLUDED.opening_date;
RETURN in_group_id;
-- return success of transaction (boolean)
END;
$$ LANGUAGE plpgsql;
This function removes rows that are missing from your in_rows
This MWE is NOT how you would typically solve this problem, however, it is as simple as I can explain the problem I am encountering. I am merely trying to point out 2 things
I am doing more than simply returning the contents of a Table
What is being returned is NOT being returned as a Table but a String
Supporting SQL Statements:
DROP DATABASE IF EXISTS test;
CREATE DATABASE test;
\c test
CREATE TABLE credit_card(
id BIGSERIAL PRIMARY KEY,
balance BIGINT
);
Functions:
CREATE FUNCTION get_credit_card(
p_id BIGINT
)
RETURNS TABLE(
id BIGINT,
balance BIGINT
)
AS $$
DECLARE
BEGIN
RETURN QUERY
SELECT
credit_card.id,
credit_card.balance
FROM
credit_card
WHERE
credit_card.id = p_id;
END $$ LAnguage 'plpgsql';
CREATE FUNCTION pay_with_card(
p_id BIGINT,
p_amount BIGINT
)
RETURNS TABLE(
id BIGINT,
balance BIGINT
)
AS $$
DECLARE
v_balance BIGINT;
BEGIN
SELECT
credit_card.balance
FROM
credit_card
INTO
v_balance
WHERE
credit_card.id = p_id;
IF v_balance < p_amount
THEN
RETURN;
END IF;
UPDATE
credit_card
SET
balance = credit_card.balance - p_amount;
RETURN QUERY
SELECT get_credit_card (p_id);
END $$ LAnguage 'plpgsql';
Populate Table and Call function:
INSERT INTO credit_card
(balance)
VALUES
(100);
SELECT
pay_with_card (1, 100);
Error:
DROP DATABASE
CREATE DATABASE
You are now connected to database "test" as user "postgres".
CREATE TABLE
CREATE FUNCTION
CREATE FUNCTION
INSERT 0 1
psql:test.sql:74: ERROR: structure of query does not match function result type
DETAIL: Returned type record does not match expected type bigint in column 1.
CONTEXT: PL/pgSQL function pay_with_card(bigint,bigint) line 24 at RETURN QUERY
It took me a long time to figure out that pay_with_card is returning a String, or what appears to be a String, instead of a TABLE(id BIGINT, balance BIGINT). With the Python psycopg2 library, the returned query is
[('(1,100)'),]
So my entire code is breaking because I can't get the values (unless I hack it and use string manipulation.
Question:
How can I fix it so that it returns the correct query like so
[(1,100),]
An alternative to the hint in horse_with_no_name's comment, you can replace
RETURN QUERY
SELECT get_credit_card (p_id);
with
RETURN QUERY SELECT (get_credit_card(p_id)).*;
You need some way of expanding the returned record back into its constituent fields. (I think horse’s SELECT * … has the same effect.)
I'm using a function that inserts a row to a table if it doesn't exist, then returns the id of the row.
Whenever I put the function inside a SELECT statement, with values that don't exist in the table yet, e.g.:
SELECT * FROM table WHERE id = function(123);
... it returns an empty row. However, running it again with the same values will return the row with the values I want to see.
Why does this happen? Is the INSERT running behind the SELECT speed? Or does PostgreSQL cache the table when it didn't exist, and at next run, it displays the result?
Here's a ready to use example of how this issue can occur:
CREATE TABLE IF NOT EXISTS test_table(
id INTEGER,
tvalue boolean
);
CREATE OR REPLACE FUNCTION test_function(user_id INTEGER)
RETURNS integer
LANGUAGE 'plpgsql'
AS $$
DECLARE
__user_id INTEGER;
BEGIN
EXECUTE format('SELECT * FROM test_table WHERE id = $1')
USING user_id
INTO __user_id;
IF __user_id IS NOT NULL THEN
RETURN __user_id;
ELSE
INSERT INTO test_table(id, tvalue)
VALUES (user_id, TRUE)
RETURNING id
INTO __user_id;
RETURN __user_id;
END IF;
END;
$$;
Call:
SELECT * FROM test_table WHERE id = test_function(4);
To reproduce the issue, pass any integer that doesn't exist in the table, yet.
The example is broken in multiple places.
No need for dynamic SQL with EXECUTE.
SELECT * in the function is wrong.
Your table definition should have a UNIQUE or PRIMARY KEY constraint on (id).
Most importantly, the final SELECT statement is bound to fail. Since the function is VOLATILE (has to be), it is evaluated once for every existing row in the table. Even if that worked, it would be a performance nightmare. But it does not. Like #user2864740 commented, there is also a problem with visibility. Postgres checks every existing row against the result of the function, which in turn adds 1 or more rows, and those rows are not yet in the snapshot the SELECT is operating on.
SELECT * FROM test_table WHERE id = test_function(4);
This would work (but see below!):
CREATE TABLE test_table (
id int PRIMARY KEY --!
, tvalue bool
);
CREATE OR REPLACE FUNCTION test_function(_user_id int)
RETURNS test_table LANGUAGE sql AS
$func$
WITH ins AS (
INSERT INTO test_table(id, tvalue)
VALUES (_user_id, TRUE)
ON CONFLICT DO NOTHING
RETURNING *
)
TABLE ins
UNION ALL
SELECT * FROM test_table WHERE id = _user_id
LIMIT 1
$func$;
And replace your SELECT with just:
SELECT * FROM test_function(1);
db<>fiddle here
Related:
Return a value if no record is found
How to use RETURNING with ON CONFLICT in PostgreSQL?
There is still a race condition for concurrent calls. If that can happen, consider:
Is SELECT or INSERT in a function prone to race conditions?
I can't find a clear explanation of the syntax to create (and use) tables just for the inside calculations of a function. Could anyone give me a syntax exemple please ?
From what I've found, I have tried this (with and without # before temp_table) :
CREATE FUNCTION test.myfunction()
RETURNS SETOF test.out_table
AS $$
DECLARE #temp_table TABLE
(
id int,
value text
)
BEGIN
INSERT INTO #temp_table
SELECT id, value
FROM test.another_table;
INSERT INTO test.out_table
SELECT id, value
FROM #temp_table;
RETURN END
$$ LANGUAGE SQL;
I get :
ERROR: syntax error at or near "DECLARE"
LINE 5: DECLARE #temp_table TABLE
-
I also tried the CREATE TABLE approach suggested here, this way :
CREATE FUNCTION test.myfunction()
RETURNS SETOF test.out_table
AS $$
CREATE TABLE temp_table AS
SELECT id, value
FROM test.another_table;
INSERT INTO test.out_table
SELECT id, value
FROM temp_table;
$$ LANGUAGE SQL;
And I get this :
ERROR: relation "temp_table " does not exist
LINE 11: FROM temp_table
(Obviously, I'm aware the temp_table is not necessary for what I'm doing in the code above, but that's not the point :) => I want to understand the syntax to get it to work)
The appropriate syntax for creating a temp table is
create temp table...
but you have to be sure to drop the temp table before existing out of the function. Also, I'd suggest this syntax instead:
CREATE TEMP TABLE IF NOT EXISTS temp_table AS
SELECT id, value
FROM test.another_table;
Thus your function will be like this:
CREATE FUNCTION test.myfunction()
RETURNS SETOF test.out_table
AS $$
CREATE TEMP TABLE IF NOT EXISTS temp_table AS
SELECT id, value
FROM test.another_table;
INSERT INTO test.out_table
SELECT id, value
FROM temp_table;
DROP TABLE temp_table;
$$ LANGUAGE SQL;
But if I can be so kind, I'd like to rewrite this function so it is more correct:
CREATE FUNCTION test.myfunction()
RETURNS TABLE (id int, value varchar) -- change your datatype as needed
AS $$
BEGIN;
CREATE TEMP TABLE IF NOT EXISTS temp_table AS
SELECT id, value
FROM test.another_table;
INSERT INTO test.out_table
SELECT id, value
FROM temp_table;
DROP TABLE temp_table;
RETURN QUERY
SELECT id, value
from temp_table;
END;
$$ LANGUAGE plpgsql;
Untested; let me know if this fails.
We have a huge Oracle SQL query in our project which is using many views and tables for source data.
Is there any way to find the list of rows fetched from each source table by this big query when I run it?
Basically what we are trying to do is to create the bare minimum number of rows in the source tables so that the outer most big query returns at least a single record.
I have tried to run the smaller queries individually. But it is really time consuming and tedious. So I was wondering if there is a smarter way of doing this.
You can use Fine Grained Access Control. Here is how you might do it:
Step 1: Create a table to hold the list of rowids (i.e., the results you are looking for in this exercise)
CREATE TABLE matt_selected_rowids ( row_id rowid );
Step 2: Create a FGAC handler that will add a predicate whenever a base table is selected.
CREATE OR REPLACE PACKAGE matt_fgac_handler IS
FUNCTION record_rowid ( p_rowid rowid ) RETURN NUMBER DETERMINISTIC;
FUNCTION add_rowid_predicate (d1 varchar2, d2 varchar2 ) RETURN VARCHAR2;
END matt_fgac_handler;
CREATE OR REPLACE PACKAGE BODY matt_fgac_handler IS
FUNCTION record_rowid ( p_rowid rowid ) RETURN NUMBER DETERMINISTIC IS
PRAGMA AUTONOMOUS_TRANSACTION;
BEGIN
INSERT INTO matt_selected_rowids( row_id ) values ( p_rowid );
COMMIT;
RETURN -1;
END record_rowid;
FUNCTION add_rowid_predicate (d1 varchar2, d2 varchar2 ) RETURN VARCHAR2 IS
BEGIN
RETURN 'matt_fgac_handler.record_rowid (rowid) = -1';
END add_rowid_predicate;
END matt_fgac_handler;
Step 3: Add a policy to each base table used by your view (you can get the list by using DBA_DEPENDENCIES recursively, or just doing an explain plan and eyeballing it).
E.g.,
CREATE TABLE matt_table ( a number, b varchar2(80) );
CREATE INDEX matt_table_n1 on matt_table(a);
insert into matt_table values (1,'A');
insert into matt_table values (2,'B');
insert into matt_table values (3,'C');
insert into matt_table values (3,'D');
insert into matt_table values (3,'E');
insert into matt_table values (3,'F');
insert into matt_table values (4,'G');
insert into matt_table values (4,'H');
COMMIT;
BEGIN
DBMS_RLS.ADD_POLICY('APPS','MATT_TABLE','record_rowids_policy', NULL, 'matt_fgac_handler.add_rowid_predicate', 'select');
END;
So, at this point, whenever a user selects from my table, Oracle is automatically going to add a condition that calls my record_rowid function for each rowid.
For example:
delete from matt_selected_rowids;
SELECT /*+ INDEX */ * FROM matt_table where a = 2;
-- This gives your the rowids selected...
select r.row_id, o.object_name from matt_selected_rowids r left join dba_objects o on o.object_id =dbms_rowid.rowid_object(row_id);