Track more precisely query locations for nested statements

Previously, a Query generated through the transform phase would have
unset stmt_location, tracking the starting point of a query string.

Extensions relying on the statement location to extract its relevant
parts in the source text string would fallback to use the whole
statement instead, leading to confusing results like in
pg_stat_statements for queries relying on nested queries, like:
- EXPLAIN, with top-level and nested query using the same query string,
and a query ID coming from the nested query when the non-top-level
entry.
- Multi-statements, with only partial portions of queries being
normalized.
- COPY TO with a query, SELECT or DMLs.

This patch improves things by keeping track of the statement locations
and propagate it to Query during transform, allowing PGSS to only show
the relevant part of the query for nested query.  This leads to less
bloat in entries for non-top-level entries, as queries can now be
grouped within the same (toplevel, queryid) duos in pg_stat_statements.
The result gives a stricter one-one mapping between query IDs and its
query strings.

The regression tests introduced in 45e0ba30fc40 produce differences
reflecting the new logic.

Author: Anthonin Bonnefoy
Reviewed-by: Michael Paquier, Jian He
Discussion: https://postgr.es/m/CAO6_XqqM6S9bQ2qd=75W+yKATwoazxSNhv5sjW06fjGAtHbTUA@mail.gmail.com

diff --git a/contrib/pg_stat_statements/expected/level_tracking.out b/contrib/pg_stat_statements/expected/level_tracking.out
index 8f008f8bfd1c4f3417113cafe4ca326c3aec5fac..489dc7143f7aa821579489674c067ba557461ff0 100644 (file)
--- a/contrib/pg_stat_statements/expected/level_tracking.out
+++ b/contrib/pg_stat_statements/expected/level_tracking.out
@@ -206,37 +206,37 @@ EXPLAIN (COSTS OFF) SELECT 1 UNION SELECT 2;
 
 SELECT toplevel, calls, query FROM pg_stat_statements
   ORDER BY query COLLATE "C";
- toplevel | calls |                                query                                
-----------+-------+---------------------------------------------------------------------
+ toplevel | calls |                               query                                
+----------+-------+--------------------------------------------------------------------
+ f        |     1 | DELETE FROM stats_track_tab
  t        |     1 | EXPLAIN (COSTS OFF) (SELECT $1, $2)
- f        |     1 | EXPLAIN (COSTS OFF) (SELECT $1, $2);
  t        |     1 | EXPLAIN (COSTS OFF) (TABLE test_table)
- f        |     1 | EXPLAIN (COSTS OFF) (TABLE test_table);
  t        |     1 | EXPLAIN (COSTS OFF) (VALUES ($1, $2))
- f        |     1 | EXPLAIN (COSTS OFF) (VALUES ($1, $2));
  t        |     1 | EXPLAIN (COSTS OFF) DELETE FROM stats_track_tab
- f        |     1 | EXPLAIN (COSTS OFF) DELETE FROM stats_track_tab;
  t        |     1 | EXPLAIN (COSTS OFF) INSERT INTO stats_track_tab VALUES (($1))
- f        |     1 | EXPLAIN (COSTS OFF) INSERT INTO stats_track_tab VALUES (($1));
- t        |     1 | EXPLAIN (COSTS OFF) MERGE INTO stats_track_tab                     +
-          |       |   USING (SELECT id FROM generate_series($1, $2) id) ON x = id      +
-          |       |   WHEN MATCHED THEN UPDATE SET x = id                              +
+ t        |     1 | EXPLAIN (COSTS OFF) MERGE INTO stats_track_tab                    +
+          |       |   USING (SELECT id FROM generate_series($1, $2) id) ON x = id     +
+          |       |   WHEN MATCHED THEN UPDATE SET x = id                             +
           |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id)
- f        |     1 | EXPLAIN (COSTS OFF) MERGE INTO stats_track_tab                     +
-          |       |   USING (SELECT id FROM generate_series($1, $2) id) ON x = id      +
-          |       |   WHEN MATCHED THEN UPDATE SET x = id                              +
-          |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id);
  t        |     1 | EXPLAIN (COSTS OFF) SELECT $1
  t        |     1 | EXPLAIN (COSTS OFF) SELECT $1 UNION SELECT $2
- f        |     1 | EXPLAIN (COSTS OFF) SELECT $1 UNION SELECT $2;
- f        |     1 | EXPLAIN (COSTS OFF) SELECT $1;
  t        |     1 | EXPLAIN (COSTS OFF) TABLE stats_track_tab
- f        |     1 | EXPLAIN (COSTS OFF) TABLE stats_track_tab;
  t        |     1 | EXPLAIN (COSTS OFF) UPDATE stats_track_tab SET x = $1 WHERE x = $2
- f        |     1 | EXPLAIN (COSTS OFF) UPDATE stats_track_tab SET x = $1 WHERE x = $2;
  t        |     1 | EXPLAIN (COSTS OFF) VALUES ($1)
- f        |     1 | EXPLAIN (COSTS OFF) VALUES ($1);
+ f        |     1 | INSERT INTO stats_track_tab VALUES (($1))
+ f        |     1 | MERGE INTO stats_track_tab                                        +
+          |       |   USING (SELECT id FROM generate_series($1, $2) id) ON x = id     +
+          |       |   WHEN MATCHED THEN UPDATE SET x = id                             +
+          |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id)
+ f        |     1 | SELECT $1
+ f        |     1 | SELECT $1 UNION SELECT $2
+ f        |     1 | SELECT $1, $2
  t        |     1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+ f        |     1 | TABLE stats_track_tab
+ f        |     1 | TABLE test_table
+ f        |     1 | UPDATE stats_track_tab SET x = $1 WHERE x = $2
+ f        |     1 | VALUES ($1)
+ f        |     1 | VALUES ($1, $2)
 (23 rows)
 
 -- EXPLAIN - top-level tracking.
@@ -405,20 +405,20 @@ EXPLAIN (COSTS OFF) SELECT 1, 2 UNION SELECT 3, 4\; EXPLAIN (COSTS OFF) (SELECT
 
 SELECT toplevel, calls, query FROM pg_stat_statements
   ORDER BY query COLLATE "C";
- toplevel | calls |                                                        query                                                        
-----------+-------+---------------------------------------------------------------------------------------------------------------------
+ toplevel | calls |                              query                              
+----------+-------+-----------------------------------------------------------------
+ f        |     1 | (SELECT $1, $2, $3) UNION SELECT $4, $5, $6
  t        |     1 | EXPLAIN (COSTS OFF) (SELECT $1, $2, $3)
  t        |     1 | EXPLAIN (COSTS OFF) (SELECT $1, $2, $3) UNION SELECT $4, $5, $6
- f        |     1 | EXPLAIN (COSTS OFF) (SELECT $1, $2, $3); EXPLAIN (COSTS OFF) (SELECT 1, 2, 3, 4);
  t        |     1 | EXPLAIN (COSTS OFF) (SELECT $1, $2, $3, $4)
- f        |     1 | EXPLAIN (COSTS OFF) (SELECT 1, 2, 3); EXPLAIN (COSTS OFF) (SELECT $1, $2, $3, $4);
  t        |     1 | EXPLAIN (COSTS OFF) SELECT $1
  t        |     1 | EXPLAIN (COSTS OFF) SELECT $1, $2
  t        |     1 | EXPLAIN (COSTS OFF) SELECT $1, $2 UNION SELECT $3, $4
- f        |     1 | EXPLAIN (COSTS OFF) SELECT $1, $2 UNION SELECT $3, $4; EXPLAIN (COSTS OFF) (SELECT 1, 2, 3) UNION SELECT 3, 4, 5;
- f        |     1 | EXPLAIN (COSTS OFF) SELECT $1; EXPLAIN (COSTS OFF) SELECT 1, 2;
- f        |     1 | EXPLAIN (COSTS OFF) SELECT 1, 2 UNION SELECT 3, 4; EXPLAIN (COSTS OFF) (SELECT $1, $2, $3) UNION SELECT $4, $5, $6;
- f        |     1 | EXPLAIN (COSTS OFF) SELECT 1; EXPLAIN (COSTS OFF) SELECT $1, $2;
+ f        |     1 | SELECT $1
+ f        |     1 | SELECT $1, $2
+ f        |     1 | SELECT $1, $2 UNION SELECT $3, $4
+ f        |     1 | SELECT $1, $2, $3
+ f        |     1 | SELECT $1, $2, $3, $4
  t        |     1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
 (13 rows)
 
@@ -494,29 +494,29 @@ EXPLAIN (COSTS OFF) INSERT INTO stats_track_tab VALUES ((1))\; EXPLAIN (COSTS OF
 
 SELECT toplevel, calls, query FROM pg_stat_statements
   ORDER BY query COLLATE "C";
- toplevel | calls |                                                              query                                                               
-----------+-------+----------------------------------------------------------------------------------------------------------------------------------
+ toplevel | calls |                               query                                
+----------+-------+--------------------------------------------------------------------
+ f        |     1 | DELETE FROM stats_track_tab
+ f        |     1 | DELETE FROM stats_track_tab WHERE x = $1
  t        |     1 | EXPLAIN (COSTS OFF) (TABLE test_table)
  t        |     1 | EXPLAIN (COSTS OFF) (VALUES ($1, $2))
  t        |     1 | EXPLAIN (COSTS OFF) DELETE FROM stats_track_tab
  t        |     1 | EXPLAIN (COSTS OFF) DELETE FROM stats_track_tab WHERE x = $1
- f        |     1 | EXPLAIN (COSTS OFF) DELETE FROM stats_track_tab; EXPLAIN (COSTS OFF) DELETE FROM stats_track_tab WHERE x = $1;
- f        |     1 | EXPLAIN (COSTS OFF) DELETE FROM stats_track_tab; EXPLAIN (COSTS OFF) DELETE FROM stats_track_tab WHERE x = 1;
  t        |     1 | EXPLAIN (COSTS OFF) INSERT INTO stats_track_tab VALUES ($1), ($2)
  t        |     1 | EXPLAIN (COSTS OFF) INSERT INTO stats_track_tab VALUES (($1))
- f        |     1 | EXPLAIN (COSTS OFF) INSERT INTO stats_track_tab VALUES (($1)); EXPLAIN (COSTS OFF) INSERT INTO stats_track_tab VALUES (1), (2);
- f        |     1 | EXPLAIN (COSTS OFF) INSERT INTO stats_track_tab VALUES ((1)); EXPLAIN (COSTS OFF) INSERT INTO stats_track_tab VALUES ($1), ($2);
  t        |     1 | EXPLAIN (COSTS OFF) TABLE stats_track_tab
- f        |     1 | EXPLAIN (COSTS OFF) TABLE stats_track_tab; EXPLAIN (COSTS OFF) (TABLE test_table);
- f        |     1 | EXPLAIN (COSTS OFF) TABLE stats_track_tab; EXPLAIN (COSTS OFF) (TABLE test_table);
  t        |     1 | EXPLAIN (COSTS OFF) UPDATE stats_track_tab SET x = $1
  t        |     1 | EXPLAIN (COSTS OFF) UPDATE stats_track_tab SET x = $1 WHERE x = $2
- f        |     1 | EXPLAIN (COSTS OFF) UPDATE stats_track_tab SET x = $1 WHERE x = $2; EXPLAIN (COSTS OFF) UPDATE stats_track_tab SET x = 1;
- f        |     1 | EXPLAIN (COSTS OFF) UPDATE stats_track_tab SET x = 1 WHERE x = 1; EXPLAIN (COSTS OFF) UPDATE stats_track_tab SET x = $1;
  t        |     1 | EXPLAIN (COSTS OFF) VALUES ($1)
- f        |     1 | EXPLAIN (COSTS OFF) VALUES ($1); EXPLAIN (COSTS OFF) (VALUES (1, 2));
- f        |     1 | EXPLAIN (COSTS OFF) VALUES (1); EXPLAIN (COSTS OFF) (VALUES ($1, $2));
+ f        |     1 | INSERT INTO stats_track_tab VALUES ($1), ($2)
+ f        |     1 | INSERT INTO stats_track_tab VALUES (($1))
  t        |     1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+ f        |     1 | TABLE stats_track_tab
+ f        |     1 | TABLE test_table
+ f        |     1 | UPDATE stats_track_tab SET x = $1
+ f        |     1 | UPDATE stats_track_tab SET x = $1 WHERE x = $2
+ f        |     1 | VALUES ($1)
+ f        |     1 | VALUES ($1, $2)
 (21 rows)
 
 SELECT pg_stat_statements_reset() IS NOT NULL AS t;
@@ -547,21 +547,18 @@ EXPLAIN (COSTS OFF) MERGE INTO stats_track_tab
 
 SELECT toplevel, calls, query FROM pg_stat_statements
   ORDER BY query COLLATE "C";
- toplevel | calls |                                             query                                              
-----------+-------+------------------------------------------------------------------------------------------------
- t        |     1 | EXPLAIN (COSTS OFF) MERGE INTO stats_track_tab                                                +
-          |       |   USING (SELECT id FROM generate_series($1, $2) id) ON x = id                                 +
-          |       |   WHEN MATCHED THEN UPDATE SET x = id                                                         +
+ toplevel | calls |                             query                             
+----------+-------+---------------------------------------------------------------
+ t        |     1 | EXPLAIN (COSTS OFF) MERGE INTO stats_track_tab               +
+          |       |   USING (SELECT id FROM generate_series($1, $2) id) ON x = id+
+          |       |   WHEN MATCHED THEN UPDATE SET x = id                        +
           |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id)
- f        |     1 | EXPLAIN (COSTS OFF) MERGE INTO stats_track_tab                                                +
-          |       |   USING (SELECT id FROM generate_series($1, $2) id) ON x = id                                 +
-          |       |   WHEN MATCHED THEN UPDATE SET x = id                                                         +
-          |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id); EXPLAIN (COSTS OFF) SELECT 1, 2, 3, 4, 5;
- f        |     1 | EXPLAIN (COSTS OFF) MERGE INTO stats_track_tab                                                +
-          |       |   USING (SELECT id FROM generate_series(1, 10) id) ON x = id                                  +
-          |       |   WHEN MATCHED THEN UPDATE SET x = id                                                         +
-          |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id); EXPLAIN (COSTS OFF) SELECT $1, $2, $3, $4, $5;
  t        |     1 | EXPLAIN (COSTS OFF) SELECT $1, $2, $3, $4, $5
+ f        |     1 | MERGE INTO stats_track_tab                                   +
+          |       |   USING (SELECT id FROM generate_series($1, $2) id) ON x = id+
+          |       |   WHEN MATCHED THEN UPDATE SET x = id                        +
+          |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id)
+ f        |     1 | SELECT $1, $2, $3, $4, $5
  t        |     1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
 (5 rows)
 
@@ -789,29 +786,29 @@ EXPLAIN (COSTS OFF) WITH a AS (select 4) SELECT 1 UNION SELECT 2;
 
 SELECT toplevel, calls, query FROM pg_stat_statements
   ORDER BY query COLLATE "C";
- toplevel | calls |                                           query                                           
-----------+-------+-------------------------------------------------------------------------------------------
+ toplevel | calls |                                          query                                           
+----------+-------+------------------------------------------------------------------------------------------
  t        |     1 | EXPLAIN (COSTS OFF) (WITH a AS (SELECT $1) (SELECT $2, $3))
- f        |     1 | EXPLAIN (COSTS OFF) (WITH a AS (SELECT $1) (SELECT $2, $3));
  t        |     1 | EXPLAIN (COSTS OFF) WITH a AS (SELECT $1) DELETE FROM stats_track_tab
- f        |     1 | EXPLAIN (COSTS OFF) WITH a AS (SELECT $1) DELETE FROM stats_track_tab;
  t        |     1 | EXPLAIN (COSTS OFF) WITH a AS (SELECT $1) INSERT INTO stats_track_tab VALUES (($2))
- f        |     1 | EXPLAIN (COSTS OFF) WITH a AS (SELECT $1) INSERT INTO stats_track_tab VALUES (($2));
- t        |     1 | EXPLAIN (COSTS OFF) WITH a AS (SELECT $1) MERGE INTO stats_track_tab                     +
-          |       |   USING (SELECT id FROM generate_series($2, $3) id) ON x = id                            +
-          |       |   WHEN MATCHED THEN UPDATE SET x = id                                                    +
+ t        |     1 | EXPLAIN (COSTS OFF) WITH a AS (SELECT $1) MERGE INTO stats_track_tab                    +
+          |       |   USING (SELECT id FROM generate_series($2, $3) id) ON x = id                           +
+          |       |   WHEN MATCHED THEN UPDATE SET x = id                                                   +
           |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id)
- f        |     1 | EXPLAIN (COSTS OFF) WITH a AS (SELECT $1) MERGE INTO stats_track_tab                     +
-          |       |   USING (SELECT id FROM generate_series($2, $3) id) ON x = id                            +
-          |       |   WHEN MATCHED THEN UPDATE SET x = id                                                    +
-          |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id);
  t        |     1 | EXPLAIN (COSTS OFF) WITH a AS (SELECT $1) SELECT $2
- f        |     1 | EXPLAIN (COSTS OFF) WITH a AS (SELECT $1) SELECT $2;
  t        |     1 | EXPLAIN (COSTS OFF) WITH a AS (SELECT $1) UPDATE stats_track_tab SET x = $2 WHERE x = $3
- f        |     1 | EXPLAIN (COSTS OFF) WITH a AS (SELECT $1) UPDATE stats_track_tab SET x = $2 WHERE x = $3;
  t        |     1 | EXPLAIN (COSTS OFF) WITH a AS (select $1) SELECT $2 UNION SELECT $3
- f        |     1 | EXPLAIN (COSTS OFF) WITH a AS (select $1) SELECT $2 UNION SELECT $3;
  t        |     1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+ f        |     1 | WITH a AS (SELECT $1) (SELECT $2, $3)
+ f        |     1 | WITH a AS (SELECT $1) DELETE FROM stats_track_tab
+ f        |     1 | WITH a AS (SELECT $1) INSERT INTO stats_track_tab VALUES (($2))
+ f        |     1 | WITH a AS (SELECT $1) MERGE INTO stats_track_tab                                        +
+          |       |   USING (SELECT id FROM generate_series($2, $3) id) ON x = id                           +
+          |       |   WHEN MATCHED THEN UPDATE SET x = id                                                   +
+          |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id)
+ f        |     1 | WITH a AS (SELECT $1) SELECT $2
+ f        |     1 | WITH a AS (SELECT $1) UPDATE stats_track_tab SET x = $2 WHERE x = $3
+ f        |     1 | WITH a AS (select $1) SELECT $2 UNION SELECT $3
 (15 rows)
 
 -- EXPLAIN with CTEs - top-level tracking
@@ -921,12 +918,12 @@ EXPLAIN (ANALYZE, COSTS OFF, SUMMARY OFF, TIMING OFF)
 
 SELECT toplevel, calls, query FROM pg_stat_statements
   ORDER BY query COLLATE "C";
- toplevel | calls |                              query                               
-----------+-------+------------------------------------------------------------------
- t        |     1 | EXPLAIN (ANALYZE, COSTS OFF, SUMMARY OFF, TIMING OFF)           +
+ toplevel | calls |                              query                              
+----------+-------+-----------------------------------------------------------------
+ t        |     1 | EXPLAIN (ANALYZE, COSTS OFF, SUMMARY OFF, TIMING OFF)          +
           |       |   DECLARE foocur CURSOR FOR SELECT * FROM stats_track_tab
  t        |     1 | EXPLAIN (ANALYZE, COSTS OFF, SUMMARY OFF, TIMING OFF) SELECT $1
- f        |     1 | EXPLAIN (ANALYZE, COSTS OFF, SUMMARY OFF, TIMING OFF) SELECT $1;
+ f        |     1 | SELECT $1
  t        |     1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
 (4 rows)
 
@@ -1050,8 +1047,8 @@ SELECT toplevel, calls, query FROM pg_stat_statements
 ----------+-------+-----------------------------------------------------------------
  t        |     1 | CREATE TEMPORARY TABLE pgss_ctas_1 AS SELECT $1
  t        |     1 | CREATE TEMPORARY TABLE pgss_ctas_2 AS EXECUTE test_prepare_pgss
- f        |     1 | PREPARE test_prepare_pgss AS select generate_series($1, $2)
  t        |     1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+ f        |     1 | select generate_series($1, $2)
 (4 rows)
 
 -- CREATE TABLE AS, top-level tracking.
@@ -1202,25 +1199,25 @@ COPY (DELETE FROM stats_track_tab WHERE x = 2 RETURNING x) TO stdout;
 2
 SELECT toplevel, calls, query FROM pg_stat_statements
   ORDER BY query COLLATE "C";
- toplevel | calls |                                    query                                    
-----------+-------+-----------------------------------------------------------------------------
- f        |     1 | COPY (DELETE FROM stats_track_tab WHERE x = $1 RETURNING x) TO stdout
+ toplevel | calls |                                   query                                   
+----------+-------+---------------------------------------------------------------------------
  t        |     1 | COPY (DELETE FROM stats_track_tab WHERE x = 2 RETURNING x) TO stdout
- f        |     1 | COPY (INSERT INTO stats_track_tab (x) VALUES ($1) RETURNING x) TO stdout
  t        |     1 | COPY (INSERT INTO stats_track_tab (x) VALUES (1) RETURNING x) TO stdout
- f        |     1 | COPY (MERGE INTO stats_track_tab USING (SELECT $1 id) ON x = id            +
-          |       |   WHEN MATCHED THEN UPDATE SET x = id                                      +
-          |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id) RETURNING x) TO stdout
- t        |     1 | COPY (MERGE INTO stats_track_tab USING (SELECT 1 id) ON x = id             +
-          |       |   WHEN MATCHED THEN UPDATE SET x = id                                      +
+ t        |     1 | COPY (MERGE INTO stats_track_tab USING (SELECT 1 id) ON x = id           +
+          |       |   WHEN MATCHED THEN UPDATE SET x = id                                    +
           |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id) RETURNING x) TO stdout
- f        |     1 | COPY (SELECT $1 UNION SELECT $2) TO stdout
- f        |     1 | COPY (SELECT $1) TO stdout
  t        |     1 | COPY (SELECT 1 UNION SELECT 2) TO stdout
  t        |     1 | COPY (SELECT 1) TO stdout
- f        |     1 | COPY (UPDATE stats_track_tab SET x = $1 WHERE x = $2 RETURNING x) TO stdout
  t        |     1 | COPY (UPDATE stats_track_tab SET x = 2 WHERE x = 1 RETURNING x) TO stdout
+ f        |     1 | DELETE FROM stats_track_tab WHERE x = $1 RETURNING x
+ f        |     1 | INSERT INTO stats_track_tab (x) VALUES ($1) RETURNING x
+ f        |     1 | MERGE INTO stats_track_tab USING (SELECT $1 id) ON x = id                +
+          |       |   WHEN MATCHED THEN UPDATE SET x = id                                    +
+          |       |   WHEN NOT MATCHED THEN INSERT (x) VALUES (id) RETURNING x
+ f        |     1 | SELECT $1
+ f        |     1 | SELECT $1 UNION SELECT $2
  t        |     1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+ f        |     1 | UPDATE stats_track_tab SET x = $1 WHERE x = $2 RETURNING x
 (13 rows)
 
 -- COPY - top-level tracking.

diff --git a/contrib/pg_stat_statements/expected/planning.out b/contrib/pg_stat_statements/expected/planning.out
index 9effd11fdc8593b29da747f80e06029a8755eb8a..3ee1928cbe94abee298848235239e1f5e43e4fcb 100644 (file)
--- a/contrib/pg_stat_statements/expected/planning.out
+++ b/contrib/pg_stat_statements/expected/planning.out
@@ -58,7 +58,7 @@ SELECT 42;
 (1 row)
 
 SELECT plans, calls, rows, query FROM pg_stat_statements
-  WHERE query NOT LIKE 'PREPARE%' ORDER BY query COLLATE "C";
+  WHERE query NOT LIKE 'SELECT COUNT%' ORDER BY query COLLATE "C";
  plans | calls | rows |                          query                           
 -------+-------+------+----------------------------------------------------------
      0 |     1 |    0 | ALTER TABLE stats_plan_test ADD COLUMN x int
@@ -72,10 +72,10 @@ SELECT plans, calls, rows, query FROM pg_stat_statements
 -- for the prepared statement we expect at least one replan, but cache
 -- invalidations could force more
 SELECT plans >= 2 AND plans <= calls AS plans_ok, calls, rows, query FROM pg_stat_statements
-  WHERE query LIKE 'PREPARE%' ORDER BY query COLLATE "C";
- plans_ok | calls | rows |                         query                         
-----------+-------+------+-------------------------------------------------------
- t        |     4 |    4 | PREPARE prep1 AS SELECT COUNT(*) FROM stats_plan_test
+  WHERE query LIKE 'SELECT COUNT%' ORDER BY query COLLATE "C";
+ plans_ok | calls | rows |                query                 
+----------+-------+------+--------------------------------------
+ t        |     4 |    4 | SELECT COUNT(*) FROM stats_plan_test
 (1 row)
 
 -- Cleanup

diff --git a/contrib/pg_stat_statements/expected/select.out b/contrib/pg_stat_statements/expected/select.out
index e0e2fa265c9d947428875c500ecac98b2524ca58..37a30af034a6bd81363198b5000b28a694cfc82a 100644 (file)
--- a/contrib/pg_stat_statements/expected/select.out
+++ b/contrib/pg_stat_statements/expected/select.out
@@ -128,7 +128,6 @@ DEALLOCATE pgss_test;
 SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
  calls | rows |                                    query                                     
 -------+------+------------------------------------------------------------------------------
-     1 |    1 | PREPARE pgss_test (int) AS SELECT $1, $2 LIMIT $3
      4 |    4 | SELECT $1                                                                   +
        |      |   -- but this one will appear                                               +
        |      |   AS "text"
@@ -138,6 +137,7 @@ SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
      2 |    2 | SELECT $1 AS "int"
      1 |    2 | SELECT $1 AS i UNION SELECT $2 ORDER BY i
      1 |    1 | SELECT $1 || $2
+     1 |    1 | SELECT $1, $2 LIMIT $3
      0 |    0 | SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C"
      1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
      1 |    2 | WITH t(f) AS (                                                              +

diff --git a/contrib/pg_stat_statements/expected/utility.out b/contrib/pg_stat_statements/expected/utility.out
index 060d4416dd749a8c6c4dda77de52d5e6c6c779df..aa4f0f7e62805637d9530990ed14cb399b2346d4 100644 (file)
--- a/contrib/pg_stat_statements/expected/utility.out
+++ b/contrib/pg_stat_statements/expected/utility.out
@@ -540,7 +540,7 @@ SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
 -------+------+----------------------------------------------------
      2 |    0 | DEALLOCATE $1
      2 |    0 | DEALLOCATE ALL
-     2 |    2 | PREPARE stat_select AS SELECT $1 AS a
+     2 |    2 | SELECT $1 AS a
      1 |    1 | SELECT $1 as a
      1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
 (5 rows)

diff --git a/contrib/pg_stat_statements/sql/planning.sql b/contrib/pg_stat_statements/sql/planning.sql
index 46f5d9b951c459d51ce7b376a00e80871ae0ba7d..9cfe206b3b049648aa92f6aeae2d6fbbcc3b6865 100644 (file)
--- a/contrib/pg_stat_statements/sql/planning.sql
+++ b/contrib/pg_stat_statements/sql/planning.sql
@@ -20,11 +20,11 @@ SELECT 42;
 SELECT 42;
 SELECT 42;
 SELECT plans, calls, rows, query FROM pg_stat_statements
-  WHERE query NOT LIKE 'PREPARE%' ORDER BY query COLLATE "C";
+  WHERE query NOT LIKE 'SELECT COUNT%' ORDER BY query COLLATE "C";
 -- for the prepared statement we expect at least one replan, but cache
 -- invalidations could force more
 SELECT plans >= 2 AND plans <= calls AS plans_ok, calls, rows, query FROM pg_stat_statements
-  WHERE query LIKE 'PREPARE%' ORDER BY query COLLATE "C";
+  WHERE query LIKE 'SELECT COUNT%' ORDER BY query COLLATE "C";
 
 -- Cleanup
 DROP TABLE stats_plan_test;

diff --git a/src/backend/parser/analyze.c b/src/backend/parser/analyze.c
index 8a6ba1692e83b316be5e340c3ff9316aba749a3c..506e0631615f3df01b63d30c2fc83548050e55e5 100644 (file)
--- a/src/backend/parser/analyze.c
+++ b/src/backend/parser/analyze.c
@@ -238,24 +238,108 @@ parse_sub_analyze(Node *parseTree, ParseState *parentParseState,
    return query;
 }
 
+/*
+ * setQueryLocationAndLength
+ *         Set query's location and length from statement and ParseState
+ *
+ * Some statements, like PreparableStmt, can be located within parentheses.
+ * For example "(SELECT 1)" or "COPY (UPDATE ...) to x;".  For those, we
+ * cannot use the whole string from the statement's location or the SQL
+ * string would yield incorrectly.  The parser will set stmt_len, reflecting
+ * the size of the statement within the parentheses.  Thus, when stmt_len is
+ * available, we need to use it for the Query's stmt_len.
+ *
+ * For other cases, the parser can't provide the length of individual
+ * statements.  However, we have the statement's location plus the length
+ * (p_stmt_len) and location (p_stmt_location) of the top level RawStmt,
+ * stored in pstate.  Thus, the statement's length is the RawStmt's length
+ * minus how much we've advanced in the RawStmt's string.
+ */
+static void
+setQueryLocationAndLength(ParseState *pstate, Query *qry, Node *parseTree)
+{
+   ParseLoc    stmt_len = 0;
+
+   /*
+    * If there is no information about the top RawStmt's length, leave it at
+    * 0 to use the whole string.
+    */
+   if (pstate->p_stmt_len == 0)
+       return;
+
+   switch (nodeTag(parseTree))
+   {
+       case T_InsertStmt:
+           qry->stmt_location = ((InsertStmt *) parseTree)->stmt_location;
+           stmt_len = ((InsertStmt *) parseTree)->stmt_len;
+           break;
+
+       case T_DeleteStmt:
+           qry->stmt_location = ((DeleteStmt *) parseTree)->stmt_location;
+           stmt_len = ((DeleteStmt *) parseTree)->stmt_len;
+           break;
+
+       case T_UpdateStmt:
+           qry->stmt_location = ((UpdateStmt *) parseTree)->stmt_location;
+           stmt_len = ((UpdateStmt *) parseTree)->stmt_len;
+           break;
+
+       case T_MergeStmt:
+           qry->stmt_location = ((MergeStmt *) parseTree)->stmt_location;
+           stmt_len = ((MergeStmt *) parseTree)->stmt_len;
+           break;
+
+       case T_SelectStmt:
+           qry->stmt_location = ((SelectStmt *) parseTree)->stmt_location;
+           stmt_len = ((SelectStmt *) parseTree)->stmt_len;
+           break;
+
+       case T_PLAssignStmt:
+           qry->stmt_location = ((PLAssignStmt *) parseTree)->location;
+           break;
+
+       default:
+           qry->stmt_location = pstate->p_stmt_location;
+           break;
+   }
+
+   if (stmt_len > 0)
+   {
+       /* Statement's length is known, use it */
+       qry->stmt_len = stmt_len;
+   }
+   else
+   {
+       /*
+        * Compute the statement's length from the statement's location and
+        * the RawStmt's length and location.
+        */
+       qry->stmt_len = pstate->p_stmt_len - (qry->stmt_location - pstate->p_stmt_location);
+   }
+
+   /* The calculated statement length should be calculated as positive. */
+   Assert(qry->stmt_len >= 0);
+}
+
 /*
  * transformTopLevelStmt -
  *   transform a Parse tree into a Query tree.
  *
- * This function is just responsible for transferring statement location data
- * from the RawStmt into the finished Query.
+ * This function is just responsible for storing location data
+ * from the RawStmt into the ParseState.
  */
 Query *
 transformTopLevelStmt(ParseState *pstate, RawStmt *parseTree)
 {
    Query      *result;
 
+   /* Store RawStmt's length and location in pstate */
+   pstate->p_stmt_len = parseTree->stmt_len;
+   pstate->p_stmt_location = parseTree->stmt_location;
+
    /* We're at top level, so allow SELECT INTO */
    result = transformOptionalSelectInto(pstate, parseTree->stmt);
 
-   result->stmt_location = parseTree->stmt_location;
-   result->stmt_len = parseTree->stmt_len;
-
    return result;
 }
 
@@ -424,6 +508,7 @@ transformStmt(ParseState *pstate, Node *parseTree)
    /* Mark as original query until we learn differently */
    result->querySource = QSRC_ORIGINAL;
    result->canSetTag = true;
+   setQueryLocationAndLength(pstate, result, parseTree);
 
    return result;
 }

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 4bab2117d9632cde028a5a44c5603bef2453a202..baca4059d2ec31d2de91f0e22aac07ef78449dd7 100644 (file)
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -153,6 +153,7 @@ static void base_yyerror(YYLTYPE *yylloc, core_yyscan_t yyscanner,
                         const char *msg);
 static RawStmt *makeRawStmt(Node *stmt, int stmt_location);
 static void updateRawStmtEnd(RawStmt *rs, int end_location);
+static void updatePreparableStmtEnd(Node *n, int end_location);
 static Node *makeColumnRef(char *colname, List *indirection,
                           int location, core_yyscan_t yyscanner);
 static Node *makeTypeCast(Node *arg, TypeName *typename, int location);
@@ -176,7 +177,7 @@ static void insertSelectOptions(SelectStmt *stmt,
                                SelectLimit *limitClause,
                                WithClause *withClause,
                                core_yyscan_t yyscanner);
-static Node *makeSetOp(SetOperation op, bool all, Node *larg, Node *rarg);
+static Node *makeSetOp(SetOperation op, bool all, Node *larg, Node *rarg, int location);
 static Node *doNegate(Node *n, int location);
 static void doNegateFloat(Float *v);
 static Node *makeAndExpr(Node *lexpr, Node *rexpr, int location);
@@ -3383,6 +3384,7 @@ CopyStmt: COPY opt_binary qualified_name opt_column_list
                {
                    CopyStmt *n = makeNode(CopyStmt);
 
+                   updatePreparableStmtEnd($3, @4);
                    n->relation = NULL;
                    n->query = $3;
                    n->attlist = NIL;
@@ -12150,6 +12152,7 @@ InsertStmt:
                    $5->onConflictClause = $6;
                    $5->returningList = $7;
                    $5->withClause = $1;
+                   $5->stmt_location = @$;
                    $$ = (Node *) $5;
                }
        ;
@@ -12303,6 +12306,7 @@ DeleteStmt: opt_with_clause DELETE_P FROM relation_expr_opt_alias
                    n->whereClause = $6;
                    n->returningList = $7;
                    n->withClause = $1;
+                   n->stmt_location = @$;
                    $$ = (Node *) n;
                }
        ;
@@ -12377,6 +12381,7 @@ UpdateStmt: opt_with_clause UPDATE relation_expr_opt_alias
                    n->whereClause = $7;
                    n->returningList = $8;
                    n->withClause = $1;
+                   n->stmt_location = @$;
                    $$ = (Node *) n;
                }
        ;
@@ -12454,6 +12459,7 @@ MergeStmt:
                    m->joinCondition = $8;
                    m->mergeWhenClauses = $9;
                    m->returningList = $10;
+                   m->stmt_location = @$;
 
                    $$ = (Node *) m;
                }
@@ -12694,7 +12700,20 @@ SelectStmt: select_no_parens           %prec UMINUS
        ;
 
 select_with_parens:
-           '(' select_no_parens ')'                { $$ = $2; }
+           '(' select_no_parens ')'
+               {
+                   SelectStmt *n = (SelectStmt *) $2;
+
+                   /*
+                    * As SelectStmt's location starts at the SELECT keyword,
+                    * we need to track the length of the SelectStmt within
+                    * parentheses to be able to extract the relevant part
+                    * of the query.  Without this, the RawStmt's length would
+                    * be used and would include the closing parenthesis.
+                    */
+                   n->stmt_len = @3 - @2;
+                   $$ = $2;
+               }
            | '(' select_with_parens ')'            { $$ = $2; }
        ;
 
@@ -12816,6 +12835,7 @@ simple_select:
                    n->groupDistinct = ($7)->distinct;
                    n->havingClause = $8;
                    n->windowClause = $9;
+                   n->stmt_location = @1;
                    $$ = (Node *) n;
                }
            | SELECT distinct_clause target_list
@@ -12833,6 +12853,7 @@ simple_select:
                    n->groupDistinct = ($7)->distinct;
                    n->havingClause = $8;
                    n->windowClause = $9;
+                   n->stmt_location = @1;
                    $$ = (Node *) n;
                }
            | values_clause                         { $$ = $1; }
@@ -12853,19 +12874,20 @@ simple_select:
 
                    n->targetList = list_make1(rt);
                    n->fromClause = list_make1($2);
+                   n->stmt_location = @1;
                    $$ = (Node *) n;
                }
            | select_clause UNION set_quantifier select_clause
                {
-                   $$ = makeSetOp(SETOP_UNION, $3 == SET_QUANTIFIER_ALL, $1, $4);
+                   $$ = makeSetOp(SETOP_UNION, $3 == SET_QUANTIFIER_ALL, $1, $4, @1);
                }
            | select_clause INTERSECT set_quantifier select_clause
                {
-                   $$ = makeSetOp(SETOP_INTERSECT, $3 == SET_QUANTIFIER_ALL, $1, $4);
+                   $$ = makeSetOp(SETOP_INTERSECT, $3 == SET_QUANTIFIER_ALL, $1, $4, @1);
                }
            | select_clause EXCEPT set_quantifier select_clause
                {
-                   $$ = makeSetOp(SETOP_EXCEPT, $3 == SET_QUANTIFIER_ALL, $1, $4);
+                   $$ = makeSetOp(SETOP_EXCEPT, $3 == SET_QUANTIFIER_ALL, $1, $4, @1);
                }
        ;
 
@@ -13423,6 +13445,7 @@ values_clause:
                {
                    SelectStmt *n = makeNode(SelectStmt);
 
+                   n->stmt_location = @1;
                    n->valuesLists = list_make1($3);
                    $$ = (Node *) n;
                }
@@ -18565,6 +18588,47 @@ updateRawStmtEnd(RawStmt *rs, int end_location)
    rs->stmt_len = end_location - rs->stmt_location;
 }
 
+/*
+ * Adjust a PreparableStmt to reflect that it doesn't run to the end of the
+ * string.
+ */
+static void
+updatePreparableStmtEnd(Node *n, int end_location)
+{
+   if (IsA(n, SelectStmt))
+   {
+       SelectStmt *stmt = (SelectStmt *)n;
+
+       stmt->stmt_len = end_location - stmt->stmt_location;
+   }
+   else if (IsA(n, InsertStmt))
+   {
+       InsertStmt *stmt = (InsertStmt *)n;
+
+       stmt->stmt_len = end_location - stmt->stmt_location;
+   }
+   else if (IsA(n, UpdateStmt))
+   {
+       UpdateStmt *stmt = (UpdateStmt *)n;
+
+       stmt->stmt_len = end_location - stmt->stmt_location;
+   }
+   else if (IsA(n, DeleteStmt))
+   {
+       DeleteStmt *stmt = (DeleteStmt *)n;
+
+       stmt->stmt_len = end_location - stmt->stmt_location;
+   }
+   else if (IsA(n, MergeStmt))
+   {
+       MergeStmt *stmt = (MergeStmt *)n;
+
+       stmt->stmt_len = end_location - stmt->stmt_location;
+   }
+   else
+       elog(ERROR, "unexpected node type %d", (int) n->type);
+}
+
 static Node *
 makeColumnRef(char *colname, List *indirection,
              int location, core_yyscan_t yyscanner)
@@ -18943,11 +19007,14 @@ insertSelectOptions(SelectStmt *stmt,
                     errmsg("multiple WITH clauses not allowed"),
                     parser_errposition(exprLocation((Node *) withClause))));
        stmt->withClause = withClause;
+
+       /* Update SelectStmt's location to the start of the WITH clause */
+       stmt->stmt_location = withClause->location;
    }
 }
 
 static Node *
-makeSetOp(SetOperation op, bool all, Node *larg, Node *rarg)
+makeSetOp(SetOperation op, bool all, Node *larg, Node *rarg, int location)
 {
    SelectStmt *n = makeNode(SelectStmt);
 
@@ -18955,6 +19022,7 @@ makeSetOp(SetOperation op, bool all, Node *larg, Node *rarg)
    n->all = all;
    n->larg = (SelectStmt *) larg;
    n->rarg = (SelectStmt *) rarg;
+   n->stmt_location = location;
    return (Node *) n;
 }
 

diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index c92cef3d16de45fc2c925c9b6a832b687a8a5ec4..b40b661ec8a17314470407dc43ef65adbec3f293 100644 (file)
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -2046,6 +2046,8 @@ typedef struct InsertStmt
    List       *returningList;  /* list of expressions to return */
    WithClause *withClause;     /* WITH clause */
    OverridingKind override;    /* OVERRIDING clause */
+   ParseLoc    stmt_location;  /* start location, or -1 if unknown */
+   ParseLoc    stmt_len;       /* length in bytes; 0 means "rest of string" */
 } InsertStmt;
 
 /* ----------------------
@@ -2060,6 +2062,8 @@ typedef struct DeleteStmt
    Node       *whereClause;    /* qualifications */
    List       *returningList;  /* list of expressions to return */
    WithClause *withClause;     /* WITH clause */
+   ParseLoc    stmt_location;  /* start location, or -1 if unknown */
+   ParseLoc    stmt_len;       /* length in bytes; 0 means "rest of string" */
 } DeleteStmt;
 
 /* ----------------------
@@ -2075,6 +2079,8 @@ typedef struct UpdateStmt
    List       *fromClause;     /* optional from clause for more tables */
    List       *returningList;  /* list of expressions to return */
    WithClause *withClause;     /* WITH clause */
+   ParseLoc    stmt_location;  /* start location, or -1 if unknown */
+   ParseLoc    stmt_len;       /* length in bytes; 0 means "rest of string" */
 } UpdateStmt;
 
 /* ----------------------
@@ -2090,6 +2096,8 @@ typedef struct MergeStmt
    List       *mergeWhenClauses;   /* list of MergeWhenClause(es) */
    List       *returningList;  /* list of expressions to return */
    WithClause *withClause;     /* WITH clause */
+   ParseLoc    stmt_location;  /* start location, or -1 if unknown */
+   ParseLoc    stmt_len;       /* length in bytes; 0 means "rest of string" */
 } MergeStmt;
 
 /* ----------------------
@@ -2159,6 +2167,8 @@ typedef struct SelectStmt
    bool        all;            /* ALL specified? */
    struct SelectStmt *larg;    /* left child */
    struct SelectStmt *rarg;    /* right child */
+   ParseLoc    stmt_location;  /* start location, or -1 if unknown */
+   ParseLoc    stmt_len;       /* length in bytes; 0 means "rest of string" */
    /* Eventually add fields for CORRESPONDING spec here */
 } SelectStmt;
 

diff --git a/src/include/parser/parse_node.h b/src/include/parser/parse_node.h
index 543df568147a2e9a2e2c3d1320695ef8c065d67f..2375e95c107790bb326da7ac8ff86cc42f1aa7cc 100644 (file)
--- a/src/include/parser/parse_node.h
+++ b/src/include/parser/parse_node.h
@@ -108,6 +108,20 @@ typedef Node *(*CoerceParamHook) (ParseState *pstate, Param *param,
  * byte-wise locations in parse structures to character-wise cursor
  * positions.)
  *
+ * p_stmt_location: location of the top level RawStmt's start.  During
+ * transformation, the Query's location will be set to the statement's
+ * location if available.  Otherwise, the RawStmt's start location will
+ * be used.  Propagating the location through ParseState is needed for
+ * the Query length calculation (see p_stmt_len below).
+ *
+ * p_stmt_len: length of the top level RawStmt.  Most of the time, the
+ * statement's length is not provided by the parser, with the exception
+ * of SelectStmt within parentheses and PreparableStmt in COPY.  If the
+ * statement's location is provided by the parser, the top-level location
+ * and length are needed to accurately compute the Query's length.  If the
+ * statement's location is not provided, the RawStmt's length can be used
+ * directly.
+ *
  * p_rtable: list of RTEs that will become the rangetable of the query.
  * Note that neither relname nor refname of these entries are necessarily
  * unique; searching the rtable by name is a bad idea.
@@ -193,6 +207,8 @@ struct ParseState
 {
    ParseState *parentParseState;   /* stack link */
    const char *p_sourcetext;   /* source text, or NULL if not available */
+   ParseLoc    p_stmt_location;    /* start location, or -1 if unknown */
+   ParseLoc    p_stmt_len;     /* length in bytes; 0 means "rest of string" */
    List       *p_rtable;       /* range table so far */
    List       *p_rteperminfos; /* list of RTEPermissionInfo nodes for each
                                 * RTE_RELATION entry in rtable */