create missing sequence for database tables containing column called id - postgresql

i'm trying to fix database issue related to creating missing sequence of the table after moving database from lower to higher version but i face 2 issues
first here is what i tried so far:
DO $$
DECLARE
i TEXT;
BEGIN
FOR i IN (select table_name from information_schema.tables where table_catalog='cst_sh' and table_schema='public') LOOP
IF EXISTS (SELECT count(*) FROM information_schema.columns WHERE table_name=table_name and column_name='id') THEN
EXECUTE 'CREATE SEQUENCE IF NOT EXISTS '''||i||'_id_seq''';
EXECUTE 'Select setval('''||i||'_id_seq'', (SELECT max(id) as a FROM ' || i ||')+1,true);';
end if;
END LOOP;
END$$;
1st problem is that the condition doesn't seem to work. First i check if the table has column called id then i start to create the sequence if exist and then set the value for it but some tables doesn't have id column so the second query fail.
2nd problem is with the 1st query that i use to create the sequence if it doesn't exist, it fails every time and i dont know why
the error is :
QUERY: CREATE SEQUENCE IF NOT EXISTS 'xxxx'
CONTEXT: PL/pgSQL function inline_code_block line 7 at EXECUTE

You should only loop over tables that actually have such a column. This can be achieved by using an EXISTS condition.
select t.table_name, t.table_schema
from information_schema.tables t
where t.table_schema = 'public'
and exists (select *
from information_schema.columns c
where t.table_name = c.table_name
and t.table_schema = c.table_schema
and c.column_name = 'id')
To create a safe SELECT statement you need to include the schema name of the table when getting the max() value.
Dynamic SQL is a lot easier to write if you use format() instead of string concatenation. You create a statement create sequence 'foo_id_seq' putting the sequence name in single quotes - but that's invalid for identifiers.
When you loop over a SELECT statement the loop variable should be a record, not a text value.
So putting that all together your code should look something like this:
DO $$
DECLARE
l_rec record;
l_seq_name text;
BEGIN
FOR l_rec IN select t.table_name, t.table_schema
from information_schema.tables t
where t.table_schema = 'stuff'
and exists (select *
from information_schema.columns c
where t.table_name = c.table_name
and t.table_schema = c.table_schema
and c.column_name = 'id')
LOOP
l_seq_name := l_rec.table_name||'_id_seq';
EXECUTE format('CREATE SEQUENCE IF NOT EXISTS %I', l_seq_name);
EXECUTE format('select setval(%L, max(id)) FROM %I.%I', l_seq_name, l_rec.table_schema, l_rec.table_name);
END LOOP;
END
$$;
You probably also want to make the sequence owned by the column, so you should add:
EXECUTE format('alter sequence %I owned by %I.%I.id', l_seq_name, l_rec.table_schema, l_rec.table_name);

Related

Find table names that contain a specific column entry from another table [duplicate]

Is it possible to search every column of every table for a particular value in PostgreSQL?
A similar question is available here for Oracle.
How about dumping the contents of the database, then using grep?
$ pg_dump --data-only --inserts -U postgres your-db-name > a.tmp
$ grep United a.tmp
INSERT INTO countries VALUES ('US', 'United States');
INSERT INTO countries VALUES ('GB', 'United Kingdom');
The same utility, pg_dump, can include column names in the output. Just change --inserts to --column-inserts. That way you can search for specific column names, too. But if I were looking for column names, I'd probably dump the schema instead of the data.
$ pg_dump --data-only --column-inserts -U postgres your-db-name > a.tmp
$ grep country_code a.tmp
INSERT INTO countries (iso_country_code, iso_country_name) VALUES ('US', 'United States');
INSERT INTO countries (iso_country_code, iso_country_name) VALUES ('GB', 'United Kingdom');
Here's a pl/pgsql function that locates records where any column contains a specific value.
It takes as arguments the value to search in text format, an array of table names to search into (defaults to all tables) and an array of schema names (defaults all schema names).
It returns a table structure with schema, name of table, name of column and pseudo-column ctid (non-durable physical location of the row in the table, see System Columns)
CREATE OR REPLACE FUNCTION search_columns(
needle text,
haystack_tables name[] default '{}',
haystack_schema name[] default '{}'
)
RETURNS table(schemaname text, tablename text, columnname text, rowctid text)
AS $$
begin
FOR schemaname,tablename,columnname IN
SELECT c.table_schema,c.table_name,c.column_name
FROM information_schema.columns c
JOIN information_schema.tables t ON
(t.table_name=c.table_name AND t.table_schema=c.table_schema)
JOIN information_schema.table_privileges p ON
(t.table_name=p.table_name AND t.table_schema=p.table_schema
AND p.privilege_type='SELECT')
JOIN information_schema.schemata s ON
(s.schema_name=t.table_schema)
WHERE (c.table_name=ANY(haystack_tables) OR haystack_tables='{}')
AND (c.table_schema=ANY(haystack_schema) OR haystack_schema='{}')
AND t.table_type='BASE TABLE'
LOOP
FOR rowctid IN
EXECUTE format('SELECT ctid FROM %I.%I WHERE cast(%I as text)=%L',
schemaname,
tablename,
columnname,
needle
)
LOOP
-- uncomment next line to get some progress report
-- RAISE NOTICE 'hit in %.%', schemaname, tablename;
RETURN NEXT;
END LOOP;
END LOOP;
END;
$$ language plpgsql;
See also the version on github based on the same principle but adding some speed and reporting improvements.
Examples of use in a test database:
Search in all tables within public schema:
select * from search_columns('foobar');
schemaname | tablename | columnname | rowctid
------------+-----------+------------+---------
public | s3 | usename | (0,11)
public | s2 | relname | (7,29)
public | w | body | (0,2)
(3 rows)
Search in a specific table:
select * from search_columns('foobar','{w}');
schemaname | tablename | columnname | rowctid
------------+-----------+------------+---------
public | w | body | (0,2)
(1 row)
Search in a subset of tables obtained from a select:
select * from search_columns('foobar', array(select table_name::name from information_schema.tables where table_name like 's%'), array['public']);
schemaname | tablename | columnname | rowctid
------------+-----------+------------+---------
public | s2 | relname | (7,29)
public | s3 | usename | (0,11)
(2 rows)
Get a result row with the corresponding base table and and ctid:
select * from public.w where ctid='(0,2)';
title | body | tsv
-------+--------+---------------------
toto | foobar | 'foobar':2 'toto':1
Variants
To test against a regular expression instead of strict equality, like grep, this part of the query:
SELECT ctid FROM %I.%I WHERE cast(%I as text)=%L
may be changed to:
SELECT ctid FROM %I.%I WHERE cast(%I as text) ~ %L
For case insensitive comparisons, you could write:
SELECT ctid FROM %I.%I WHERE lower(cast(%I as text)) = lower(%L)
to search every column of every table for a particular value
This does not define how to match exactly.
Nor does it define what to return exactly.
Assuming:
Find any row with any column containing the given value in its text representation - as opposed to equaling the given value.
Return the table name (regclass) and the tuple ID (ctid), because that's simplest.
Here is a dead simple, fast and slightly dirty way:
CREATE OR REPLACE FUNCTION search_whole_db(_like_pattern text)
RETURNS TABLE(_tbl regclass, _ctid tid) AS
$func$
BEGIN
FOR _tbl IN
SELECT c.oid::regclass
FROM pg_class c
JOIN pg_namespace n ON n.oid = relnamespace
WHERE c.relkind = 'r' -- only tables
AND n.nspname !~ '^(pg_|information_schema)' -- exclude system schemas
ORDER BY n.nspname, c.relname
LOOP
RETURN QUERY EXECUTE format(
'SELECT $1, ctid FROM %s t WHERE t::text ~~ %L'
, _tbl, '%' || _like_pattern || '%')
USING _tbl;
END LOOP;
END
$func$ LANGUAGE plpgsql;
Call:
SELECT * FROM search_whole_db('mypattern');
Provide the search pattern without enclosing %.
Why slightly dirty?
If separators and decorators for the row in text representation can be part of the search pattern, there can be false positives:
column separator: , by default
whole row is enclosed in parentheses:()
some values are enclosed in double quotes "
\ may be added as escape char
And the text representation of some columns may depend on local settings - but that ambiguity is inherent to the question, not to my solution.
Each qualifying row is returned once only, even when it matches multiple times (as opposed to other answers here).
This searches the whole DB except for system catalogs. Will typically take a long time to finish. You might want to restrict to certain schemas / tables (or even columns) like demonstrated in other answers. Or add notices and a progress indicator, also demonstrated in another answer.
The regclass object identifier type is represented as table name, schema-qualified where necessary to disambiguate according to the current search_path:
Find the referenced table name using table, field and schema name
What is the ctid?
How do I decompose ctid into page and row numbers?
You might want to escape characters with special meaning in the search pattern. See:
Escape function for regular expression or LIKE patterns
There is a way to achieve this without creating a function or using an external tool. By using Postgres' query_to_xml() function that can dynamically run a query inside another query, it's possible to search a text across many tables. This is based on my answer to retrieve the rowcount for all tables:
To search for the string foo across all tables in a schema, the following can be used:
with found_rows as (
select format('%I.%I', table_schema, table_name) as table_name,
query_to_xml(format('select to_jsonb(t) as table_row
from %I.%I as t
where t::text like ''%%foo%%'' ', table_schema, table_name),
true, false, '') as table_rows
from information_schema.tables
where table_schema = 'public'
)
select table_name, x.table_row
from found_rows f
left join xmltable('//table/row'
passing table_rows
columns
table_row text path 'table_row') as x on true
Note that the use of xmltable requires Postgres 10 or newer. For older Postgres version, this can be also done using xpath().
with found_rows as (
select format('%I.%I', table_schema, table_name) as table_name,
query_to_xml(format('select to_jsonb(t) as table_row
from %I.%I as t
where t::text like ''%%foo%%'' ', table_schema, table_name),
true, false, '') as table_rows
from information_schema.tables
where table_schema = 'public'
)
select table_name, x.table_row
from found_rows f
cross join unnest(xpath('/table/row/table_row/text()', table_rows)) as r(data)
The common table expression (WITH ...) is only used for convenience. It loops through all tables in the public schema. For each table the following query is run through the query_to_xml() function:
select to_jsonb(t)
from some_table t
where t::text like '%foo%';
The where clause is used to make sure the expensive generation of XML content is only done for rows that contain the search string. This might return something like this:
<table xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<row>
<table_row>{"id": 42, "some_column": "foobar"}</table_row>
</row>
</table>
The conversion of the complete row to jsonb is done, so that in the result one could see which value belongs to which column.
The above might return something like this:
table_name | table_row
-------------+----------------------------------------
public.foo | {"id": 1, "some_column": "foobar"}
public.bar | {"id": 42, "another_column": "barfoo"}
Online example for Postgres 10+
Online example for older Postgres versions
Without storing a new procedure you can use a code block and execute to obtain a table of occurences. You can filter results by schema, table or column name.
DO $$
DECLARE
value int := 0;
sql text := 'The constructed select statement';
rec1 record;
rec2 record;
BEGIN
DROP TABLE IF EXISTS _x;
CREATE TEMPORARY TABLE _x (
schema_name text,
table_name text,
column_name text,
found text
);
FOR rec1 IN
SELECT table_schema, table_name, column_name
FROM information_schema.columns
WHERE table_name <> '_x'
AND UPPER(column_name) LIKE UPPER('%%')
AND table_schema <> 'pg_catalog'
AND table_schema <> 'information_schema'
AND data_type IN ('character varying', 'text', 'character', 'char', 'varchar')
LOOP
sql := concat('SELECT ', rec1."column_name", ' AS "found" FROM ',rec1."table_schema" , '.',rec1."table_name" , ' WHERE UPPER(',rec1."column_name" , ') LIKE UPPER(''','%my_substring_to_find_goes_here%' , ''')');
RAISE NOTICE '%', sql;
BEGIN
FOR rec2 IN EXECUTE sql LOOP
RAISE NOTICE '%', sql;
INSERT INTO _x VALUES (rec1."table_schema", rec1."table_name", rec1."column_name", rec2."found");
END LOOP;
EXCEPTION WHEN OTHERS THEN
END;
END LOOP;
END; $$;
SELECT * FROM _x;
If you're using IntelliJ add your DB to Database view then right click on databases and select full text search, it will list all tables and all fields for your specific text.
And if someone think it could help. Here is #Daniel Vérité's function, with another param that accept names of columns that can be used in search. This way it decrease the time of processing. At least in my test it reduced a lot.
CREATE OR REPLACE FUNCTION search_columns(
needle text,
haystack_columns name[] default '{}',
haystack_tables name[] default '{}',
haystack_schema name[] default '{public}'
)
RETURNS table(schemaname text, tablename text, columnname text, rowctid text)
AS $$
begin
FOR schemaname,tablename,columnname IN
SELECT c.table_schema,c.table_name,c.column_name
FROM information_schema.columns c
JOIN information_schema.tables t ON
(t.table_name=c.table_name AND t.table_schema=c.table_schema)
WHERE (c.table_name=ANY(haystack_tables) OR haystack_tables='{}')
AND c.table_schema=ANY(haystack_schema)
AND (c.column_name=ANY(haystack_columns) OR haystack_columns='{}')
AND t.table_type='BASE TABLE'
LOOP
EXECUTE format('SELECT ctid FROM %I.%I WHERE cast(%I as text)=%L',
schemaname,
tablename,
columnname,
needle
) INTO rowctid;
IF rowctid is not null THEN
RETURN NEXT;
END IF;
END LOOP;
END;
$$ language plpgsql;
Bellow is an example of usage of the search_function created above.
SELECT * FROM search_columns('86192700'
, array(SELECT DISTINCT a.column_name::name FROM information_schema.columns AS a
INNER JOIN information_schema.tables as b ON (b.table_catalog = a.table_catalog AND b.table_schema = a.table_schema AND b.table_name = a.table_name)
WHERE
a.column_name iLIKE '%cep%'
AND b.table_type = 'BASE TABLE'
AND b.table_schema = 'public'
)
, array(SELECT b.table_name::name FROM information_schema.columns AS a
INNER JOIN information_schema.tables as b ON (b.table_catalog = a.table_catalog AND b.table_schema = a.table_schema AND b.table_name = a.table_name)
WHERE
a.column_name iLIKE '%cep%'
AND b.table_type = 'BASE TABLE'
AND b.table_schema = 'public')
);
Here's #Daniel Vérité's function with progress reporting functionality.
It reports progress in three ways:
by RAISE NOTICE;
by decreasing value of supplied {progress_seq} sequence from
{total number of colums to search in} down to 0;
by writing the progress along with found tables into text file,
located in c:\windows\temp\{progress_seq}.txt.
_
CREATE OR REPLACE FUNCTION search_columns(
needle text,
haystack_tables name[] default '{}',
haystack_schema name[] default '{public}',
progress_seq text default NULL
)
RETURNS table(schemaname text, tablename text, columnname text, rowctid text)
AS $$
DECLARE
currenttable text;
columnscount integer;
foundintables text[];
foundincolumns text[];
begin
currenttable='';
columnscount = (SELECT count(1)
FROM information_schema.columns c
JOIN information_schema.tables t ON
(t.table_name=c.table_name AND t.table_schema=c.table_schema)
WHERE (c.table_name=ANY(haystack_tables) OR haystack_tables='{}')
AND c.table_schema=ANY(haystack_schema)
AND t.table_type='BASE TABLE')::integer;
PERFORM setval(progress_seq::regclass, columnscount);
FOR schemaname,tablename,columnname IN
SELECT c.table_schema,c.table_name,c.column_name
FROM information_schema.columns c
JOIN information_schema.tables t ON
(t.table_name=c.table_name AND t.table_schema=c.table_schema)
WHERE (c.table_name=ANY(haystack_tables) OR haystack_tables='{}')
AND c.table_schema=ANY(haystack_schema)
AND t.table_type='BASE TABLE'
LOOP
EXECUTE format('SELECT ctid FROM %I.%I WHERE cast(%I as text)=%L',
schemaname,
tablename,
columnname,
needle
) INTO rowctid;
IF rowctid is not null THEN
RETURN NEXT;
foundintables = foundintables || tablename;
foundincolumns = foundincolumns || columnname;
RAISE NOTICE 'FOUND! %, %, %, %', schemaname,tablename,columnname, rowctid;
END IF;
IF (progress_seq IS NOT NULL) THEN
PERFORM nextval(progress_seq::regclass);
END IF;
IF(currenttable<>tablename) THEN
currenttable=tablename;
IF (progress_seq IS NOT NULL) THEN
RAISE NOTICE 'Columns left to look in: %; looking in table: %', currval(progress_seq::regclass), tablename;
EXECUTE 'COPY (SELECT unnest(string_to_array(''Current table (column ' || columnscount-currval(progress_seq::regclass) || ' of ' || columnscount || '): ' || tablename || '\n\nFound in tables/columns:\n' || COALESCE(
(SELECT string_agg(c1 || '/' || c2, '\n') FROM (SELECT unnest(foundintables) AS c1,unnest(foundincolumns) AS c2) AS t1)
, '') || ''',''\n''))) TO ''c:\WINDOWS\temp\' || progress_seq || '.txt''';
END IF;
END IF;
END LOOP;
END;
$$ language plpgsql;
-- Below function will list all the tables which contain a specific string in the database
select TablesCount(‘StringToSearch’);
--Iterates through all the tables in the database
CREATE OR REPLACE FUNCTION **TablesCount**(_searchText TEXT)
RETURNS text AS
$$ -- here start procedural part
DECLARE _tname text;
DECLARE cnt int;
BEGIN
FOR _tname IN SELECT table_name FROM information_schema.tables where table_schema='public' and table_type='BASE TABLE' LOOP
cnt= getMatchingCount(_tname,Columnames(_tname,_searchText));
RAISE NOTICE 'Count% ', CONCAT(' ',cnt,' Table name: ', _tname);
END LOOP;
RETURN _tname;
END;
$$ -- here finish procedural part
LANGUAGE plpgsql; -- language specification
-- Returns the count of tables for which the condition is met.
-- For example, if the intended text exists in any of the fields of the table,
-- then the count will be greater than 0. We can find the notifications
-- in the Messages section of the result viewer in postgres database.
CREATE OR REPLACE FUNCTION **getMatchingCount**(_tname TEXT, _clause TEXT)
RETURNS int AS
$$
Declare outpt text;
BEGIN
EXECUTE 'Select Count(*) from '||_tname||' where '|| _clause
INTO outpt;
RETURN outpt;
END;
$$ LANGUAGE plpgsql;
--Get the fields of each table. Builds the where clause with all columns of a table.
CREATE OR REPLACE FUNCTION **Columnames**(_tname text,st text)
RETURNS text AS
$$ -- here start procedural part
DECLARE
_name text;
_helper text;
BEGIN
FOR _name IN SELECT column_name FROM information_schema.Columns WHERE table_name =_tname LOOP
_name=CONCAT('CAST(',_name,' as VarChar)',' like ','''%',st,'%''', ' OR ');
_helper= CONCAT(_helper,_name,' ');
END LOOP;
RETURN CONCAT(_helper, ' 1=2');
END;
$$ -- here finish procedural part
LANGUAGE plpgsql; -- language specification

PostgreSQL function to update a serial key column for a variable table

I have a system that syncs various tables between servers at various times. It works fine, except that some tables have SERIAL key columns that get out of date because the sync doesn't update the sequences. So I'm trying to write a pl/pgsql function to make sure that if a table (named in the parameter) has a serial key, its next value is one greater than the greatest value in the table.
Actually, I think I've finally done it, but I figured I'd post the question anyhow, so people can use it or suggest improvements.
You don't really need a function for that. With a variation of this answer this can be done with a single statement:
First we need to find all columns that have use a sequence as a default value:
select table_schema, table_name, column_name,
pg_get_serial_sequence(format('%I.%I', table_schema, table_name), column_name)
from information_schema.columns
where table_schema = 'public'
and column_default like 'nextval%'
Then we can calculate the max value for each of those columns using query_to_xml() and use that result to call setval() for each sequence.
with sequences as (
select table_schema, table_name, column_name,
pg_get_serial_sequence(format('%I.%I', table_schema, table_name), column_name) as col_sequence
from information_schema.columns
where table_schema = 'public' --<< adjust for your schemas
and column_default like 'nextval%'
), maxvals as (
select table_schema, table_name, column_name, col_sequence,
(xpath('/row/max/text()',
query_to_xml(format('select coalesce(max(%I),0) from %I.%I', column_name, table_schema, table_name), true, true, ''))
)[1]::text::bigint as max_val
from sequences
where col_sequence is not null
)
select table_schema,
table_name,
column_name,
col_sequence,
max_val,
setval(col_sequence, max_val)
from maxvals;
This appears to work. It seems one needs to use EXECUTE a lot.
-- Update the serial key sequence of this given table, if appropriate.
CREATE OR REPLACE FUNCTION update_serial(i_table CHARACTER VARYING)
RETURNS CHARACTER VARYING AS $$
DECLARE
v_key_col CHARACTER VARYING;
v_seq_name CHARACTER VARYING;
v_max RECORD;
BEGIN
-- Get the name of the primary key, if any.
SELECT c.column_name, c.data_type INTO v_key_col
FROM information_schema.table_constraints tc
JOIN information_schema.constraint_column_usage AS ccu USING (constraint_schema, constraint_name)
JOIN information_schema.columns AS c
ON c.table_schema = tc.constraint_schema AND tc.table_name = c.table_name AND ccu.column_name = c.column_name
WHERE constraint_type = 'PRIMARY KEY' and tc.table_name = i_table;
IF v_key_col IS NULL THEN RETURN 'No key found';
END IF;
-- Get the name of the sequence that determines the next number for the primary key, if any.
SELECT pg_get_serial_sequence(i_table, v_key_col) INTO v_seq_name;
IF v_seq_name IS NULL THEN RETURN 'No sequence found';
END IF;
-- Get the maximum value in the primary key data, and add 1.
EXECUTE 'SELECT MAX(' || v_key_col || ') + 1 m FROM ' || i_table INTO v_max;
-- Set the value of the sequence, converting to regclass and back to text so as to clean up the name and remove
-- the schema. It needs to put its output somewhere though we're not using it, so it goes back into v_max.
SELECT SETVAL(quote_ident(v_seq_name::regclass::text), v_max.m) INTO v_max;
RETURN 'Done';
END;
$$ LANGUAGE 'plpgsql';
COMMENT ON FUNCTION update_serial(i_table CHARACTER VARYING) IS
'Update the serial key sequence of this given table, if appropriate.';

How to use variable as table name in plpgsql

I'm new to plpgsql. I'm trying to run a simple query in plpgsql using a variable as table name in plpgsql. But the variable is being interpreted as the table name instead of the value of the variable being interpreted as variable name.
DECLARE
v_table text;
z_table text;
max_id bigint;
BEGIN
FOR v_table IN
SELECT table_name
FROM information_schema.tables
WHERE table_catalog = 'my_database'
AND table_schema = 'public'
AND table_name not like 'z_%'
LOOP
z_table := 'z_' || v_table;
SELECT max(id) from z_table INTO max_id;
DELETE FROM v_table where id > max_id;
END LOOP;
Some background information. For every table in my database, I have another table starting with "z_". E.g. for a table called "employee" I have identical table called "z_employee". z_employee contains the same set of data as employee. I use it to restore the employee table at the start of every test.
When I run this function I get the following error:
ERROR: relation "z_table" does not exist
LINE 1: SELECT max(id) from z_table
My guess is that I'm not allowed to use the variable z_table in the SQL query. At least not the way I'm using it here. But I don't know how it's supposed to be done.
Use dynamic SQL with EXECUTE, simplify, and escape identifiers properly:
CREATE OR REPLACE FUNCTION f_test()
RETURNS void AS
$func$
DECLARE
v_table text;
BEGIN
FOR v_table IN
SELECT table_name
FROM information_schema.tables
WHERE table_catalog = 'my_database'
AND table_schema = 'public'
AND table_name NOT LIKE 'z_%'
LOOP
EXECUTE format('DELETE FROM %I v WHERE v.id > (SELECT max(id) FROM %I)'
, v_table, 'z_' || v_table);
END LOOP;
END
$func$ LANGUAGE plpgsql;
Table names may need to be quoted to defend against syntax errors or even SQL injection! I use the convenient format() to concatenate the DELETE statement and escape identifiers properly.
A separate SELECT would be more expensive. You can do it all with a single DELETE statement.
Related:
Table name as a PostgreSQL function parameter
Aside:
You might use the (slightly faster) system catalog pg_tables instead:
SELECT tablename
FROM pg_catalog.pg_tables
WHERE schemaname = 'public'
AND tablename NOT LIKE 'z_%'
See:
How to check if a table exists in a given schema
table_catalog in information_schema.tables has no equivalent here. Only tables of the current database are visible anyway. So the above predicate WHERE table_catalog = 'my_database' produces an empty result set when connected to the wrong database.

Update column in multiple tables

Let's say I have a column called partner in multiple tables within one schema:
select table_name from information_schema.columns where column_name = 'partner';
How would I update all columns where value partner = 100 to partner = 101?
For a one-time operation, a DO statement executing dynamic SQL should serve just fine:
DO
$do$
DECLARE
_tbl text;
BEGIN
FOR _tbl IN
SELECT quote_ident(table_name) -- escape identifier!
FROM information_schema.columns
WHERE table_schema = 'public' -- your schema (!!)
AND column_name = 'partner' -- your column name
LOOP
RAISE NOTICE '%',
-- EXECUTE
'UPDATE ' || _tbl || ' SET partner = 101 WHERE partner = 100';
END LOOP;
END
$do$
Inspect the generated code before you comment RAISE and uncomment the EXECUTE.
This is a largely simplified version of the more versatile function in this related answer with more explanation:
Changing all zeros (if any) across all columns (in a table) to... say 1
Information schema or system catalog?
How to check if a table exists in a given schema

Loop on tables with PL/pgSQL in Postgres 9.0+

I want to loop through all my tables to count rows in each of them. The following query gets me an error:
DO $$
DECLARE
tables CURSOR FOR
SELECT tablename FROM pg_tables
WHERE tablename NOT LIKE 'pg_%'
ORDER BY tablename;
tablename varchar(100);
nbRow int;
BEGIN
FOR tablename IN tables LOOP
EXECUTE 'SELECT count(*) FROM ' || tablename INTO nbRow;
-- Do something with nbRow
END LOOP;
END$$;
Errors:
ERROR: syntax error at or near ")"
LINE 1: SELECT count(*) FROM (sql_features)
^
QUERY: SELECT count(*) FROM (sql_features)
CONTEXT: PL/pgSQL function inline_code_block line 8 at EXECUTE statement
sql_features is a table's name in my DB. I already tried to use quote_ident() but to no avail.
I can't remember the last time I actually needed to use an explicit cursor for looping in PL/pgSQL.
Use the implicit cursor of a FOR loop, that's much cleaner:
DO
$$
DECLARE
rec record;
nbrow bigint;
BEGIN
FOR rec IN
SELECT *
FROM pg_tables
WHERE tablename NOT LIKE 'pg\_%'
ORDER BY tablename
LOOP
EXECUTE 'SELECT count(*) FROM '
|| quote_ident(rec.schemaname) || '.'
|| quote_ident(rec.tablename)
INTO nbrow;
-- Do something with nbrow
END LOOP;
END
$$;
You need to include the schema name to make this work for all schemas (including those not in your search_path).
Also, you actually need to use quote_ident() or format() with %I or a regclass variable to safeguard against SQL injection. A table name can be almost anything inside double quotes. See:
Table name as a PostgreSQL function parameter
Minor detail: escape the underscore (_) in the LIKE pattern to make it a literal underscore: tablename NOT LIKE 'pg\_%'
How I might do it:
DO
$$
DECLARE
tbl regclass;
nbrow bigint;
BEGIN
FOR tbl IN
SELECT c.oid
FROM pg_class c
JOIN pg_namespace n ON n.oid = c.relnamespace
WHERE c.relkind = 'r'
AND n.nspname NOT LIKE 'pg\_%' -- system schema(s)
AND n.nspname <> 'information_schema' -- information schema
ORDER BY n.nspname, c.relname
LOOP
EXECUTE 'SELECT count(*) FROM ' || tbl INTO nbrow;
-- raise notice '%: % rows', tbl, nbrow;
END LOOP;
END
$$;
Query pg_catalog.pg_class instead of tablename, it provides the OID of the table.
The object identifier type regclass is handy to simplify. n particular, table names are double-quoted and schema-qualified where necessary automatically (also prevents SQL injection).
This query also excludes temporary tables (temp schema is named pg_temp% internally).
To only include tables from a given schema:
AND n.nspname = 'public' -- schema name here, case-sensitive
The cursor returns a record, not a scalar value, so "tablename" is not a string variable.
The concatenation turns the record into a string that looks like this (sql_features). If you had selected e.g. the schemaname with the tablename, the text representation of the record would have been (public,sql_features).
So you need to access the column inside the record to create your SQL statement:
DO $$
DECLARE
tables CURSOR FOR
SELECT tablename
FROM pg_tables
WHERE tablename NOT LIKE 'pg_%'
ORDER BY tablename;
nbRow int;
BEGIN
FOR table_record IN tables LOOP
EXECUTE 'SELECT count(*) FROM ' || table_record.tablename INTO nbRow;
-- Do something with nbRow
END LOOP;
END$$;
You might want to use WHERE schemaname = 'public' instead of not like 'pg_%' to exclude the Postgres system tables.