mirror of
https://git.postgresql.org/git/postgresql.git
synced 2024-07-15 23:01:08 +02:00
64d0b8b05f
version of crosstab. This fixes a major deficiency in real-world use of the original version. Easiest to undestand with an illustration: Data: ------------------------------------------------------------------- select * from cth; id | rowid | rowdt | attribute | val ----+-------+---------------------+----------------+--------------- 1 | test1 | 2003-03-01 00:00:00 | temperature | 42 2 | test1 | 2003-03-01 00:00:00 | test_result | PASS 3 | test1 | 2003-03-01 00:00:00 | volts | 2.6987 4 | test2 | 2003-03-02 00:00:00 | temperature | 53 5 | test2 | 2003-03-02 00:00:00 | test_result | FAIL 6 | test2 | 2003-03-02 00:00:00 | test_startdate | 01 March 2003 7 | test2 | 2003-03-02 00:00:00 | volts | 3.1234 (7 rows) Original crosstab: ------------------------------------------------------------------- SELECT * FROM crosstab( 'SELECT rowid, attribute, val FROM cth ORDER BY 1,2',4) AS c(rowid text, temperature text, test_result text, test_startdate text, volts text); rowid | temperature | test_result | test_startdate | volts -------+-------------+-------------+----------------+-------- test1 | 42 | PASS | 2.6987 | test2 | 53 | FAIL | 01 March 2003 | 3.1234 (2 rows) Hashed crosstab: ------------------------------------------------------------------- SELECT * FROM crosstab( 'SELECT rowid, attribute, val FROM cth ORDER BY 1', 'SELECT DISTINCT attribute FROM cth ORDER BY 1') AS c(rowid text, temperature int4, test_result text, test_startdate timestamp, volts float8); rowid | temperature | test_result | test_startdate | volts -------+-------------+-------------+---------------------+-------- test1 | 42 | PASS | | 2.6987 test2 | 53 | FAIL | 2003-03-01 00:00:00 | 3.1234 (2 rows) Notice that the original crosstab slides data over to the left in the result tuple when it encounters missing data. In order to work around this you have to be make your source sql do all sorts of contortions (cartesian join of distinct rowid with distinct attribute; left join that back to the real source data). The new version avoids this by building a hash table using a second distinct attribute query. The new version also allows for "extra" columns (see the README) and allows the result columns to be coerced into differing datatypes if they are suitable (as shown above). In testing a "real-world" data set (69 distinct rowid's, 27 distinct categories/attributes, multiple missing data points) I saw about a 5-fold improvement in execution time (from about 2200 ms old, to 440 ms new). I left the original version intact because: 1) BC, 2) it is probably slightly faster if you know that you have no missing attributes. README and regression test adjustments included. If there are no objections, please apply. Joe Conway
69 lines
1.5 KiB
MySQL
69 lines
1.5 KiB
MySQL
-- Adjust this setting to control where the objects get created.
|
|
SET search_path = public;
|
|
|
|
SET autocommit TO 'on';
|
|
|
|
CREATE OR REPLACE FUNCTION normal_rand(int4, float8, float8, int4)
|
|
RETURNS setof float8
|
|
AS 'MODULE_PATHNAME','normal_rand'
|
|
LANGUAGE 'C' VOLATILE STRICT;
|
|
|
|
CREATE TYPE tablefunc_crosstab_2 AS
|
|
(
|
|
row_name TEXT,
|
|
category_1 TEXT,
|
|
category_2 TEXT
|
|
);
|
|
|
|
CREATE TYPE tablefunc_crosstab_3 AS
|
|
(
|
|
row_name TEXT,
|
|
category_1 TEXT,
|
|
category_2 TEXT,
|
|
category_3 TEXT
|
|
);
|
|
|
|
CREATE TYPE tablefunc_crosstab_4 AS
|
|
(
|
|
row_name TEXT,
|
|
category_1 TEXT,
|
|
category_2 TEXT,
|
|
category_3 TEXT,
|
|
category_4 TEXT
|
|
);
|
|
|
|
CREATE OR REPLACE FUNCTION crosstab2(text)
|
|
RETURNS setof tablefunc_crosstab_2
|
|
AS 'MODULE_PATHNAME','crosstab'
|
|
LANGUAGE 'C' STABLE STRICT;
|
|
|
|
CREATE OR REPLACE FUNCTION crosstab3(text)
|
|
RETURNS setof tablefunc_crosstab_3
|
|
AS 'MODULE_PATHNAME','crosstab'
|
|
LANGUAGE 'C' STABLE STRICT;
|
|
|
|
CREATE OR REPLACE FUNCTION crosstab4(text)
|
|
RETURNS setof tablefunc_crosstab_4
|
|
AS 'MODULE_PATHNAME','crosstab'
|
|
LANGUAGE 'C' STABLE STRICT;
|
|
|
|
CREATE OR REPLACE FUNCTION crosstab(text,int)
|
|
RETURNS setof record
|
|
AS 'MODULE_PATHNAME','crosstab'
|
|
LANGUAGE 'C' STABLE STRICT;
|
|
|
|
CREATE OR REPLACE FUNCTION crosstab(text,text)
|
|
RETURNS setof record
|
|
AS 'MODULE_PATHNAME','crosstab_hash'
|
|
LANGUAGE 'C' STABLE STRICT;
|
|
|
|
CREATE OR REPLACE FUNCTION connectby(text,text,text,text,int,text)
|
|
RETURNS setof record
|
|
AS 'MODULE_PATHNAME','connectby_text'
|
|
LANGUAGE 'C' STABLE STRICT;
|
|
|
|
CREATE OR REPLACE FUNCTION connectby(text,text,text,text,int)
|
|
RETURNS setof record
|
|
AS 'MODULE_PATHNAME','connectby_text'
|
|
LANGUAGE 'C' STABLE STRICT;
|