agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH 2/7] Write WAL for empty nbtree index build
137+ messages / 11 participants
[nested] [flat]

* [PATCH 2/7] Write WAL for empty nbtree index build
@ 2018-10-11 01:03 Kyotaro Horiguchi <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Kyotaro Horiguchi @ 2018-10-11 01:03 UTC (permalink / raw)

After relation truncation indexes are also rebuild. It doesn't emit
WAL in minimal mode and if truncation happened within its creation
transaction, crash recovery leaves an empty index heap, which is
considered broken. This patch forces to emit WAL when an index_build
turns into empty nbtree index.
---
 src/backend/access/nbtree/nbtsort.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/src/backend/access/nbtree/nbtsort.c b/src/backend/access/nbtree/nbtsort.c
index 2762a2d548..70fe3bec32 100644
--- a/src/backend/access/nbtree/nbtsort.c
+++ b/src/backend/access/nbtree/nbtsort.c
@@ -622,8 +622,15 @@ _bt_blwritepage(BTWriteState *wstate, Page page, BlockNumber blkno)
 	/* Ensure rd_smgr is open (could have been closed by relcache flush!) */
 	RelationOpenSmgr(wstate->index);
 
-	/* XLOG stuff */
-	if (wstate->btws_use_wal)
+	/* XLOG stuff
+	 *
+	 * Even if minimal mode, WAL is required here if truncation happened after
+	 * being created in the same transaction. It is not needed otherwise but
+	 * we don't bother identifying the case precisely.
+	 */
+	if (wstate->btws_use_wal ||
+		(RelationNeedsWAL(wstate->index) &&
+		 (blkno == BTREE_METAPAGE && BTPageGetMeta(page)->btm_root == 0)))
 	{
 		/* We use the heap NEWPAGE record type for this */
 		log_newpage(&wstate->index->rd_node, MAIN_FORKNUM, blkno, page, true);
-- 
2.16.3


----Next_Part(Mon_Mar_25_21_32_04_2019_838)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v8-0003-Move-XLOG-stuff-from-heap_insert-and-heap_delete.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH 2/3] Add operator <->(box, point) to GiST box_ops
@ 2019-03-07 20:49 Nikita Glukhov <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Nikita Glukhov @ 2019-03-07 20:49 UTC (permalink / raw)

---
 doc/src/sgml/gist.sgml             |  1 +
 src/backend/access/gist/gistproc.c | 53 ++++++++++++++++++--------
 src/include/catalog/pg_amop.dat    |  3 ++
 src/include/catalog/pg_amproc.dat  |  2 +
 src/include/catalog/pg_proc.dat    |  4 ++
 src/test/regress/expected/gist.out | 76 ++++++++++++++++++++++++++++++++++++++
 src/test/regress/sql/gist.sql      | 16 ++++++++
 7 files changed, 140 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/gist.sgml b/doc/src/sgml/gist.sgml
index 44a3b2c..e903319 100644
--- a/doc/src/sgml/gist.sgml
+++ b/doc/src/sgml/gist.sgml
@@ -83,6 +83,7 @@
        <literal>~=</literal>
       </entry>
       <entry>
+       <literal>&lt;-&gt;</literal>
       </entry>
      </row>
      <row>
diff --git a/src/backend/access/gist/gistproc.c b/src/backend/access/gist/gistproc.c
index 1826b51..89bd656 100644
--- a/src/backend/access/gist/gistproc.c
+++ b/src/backend/access/gist/gistproc.c
@@ -1464,26 +1464,13 @@ gist_point_distance(PG_FUNCTION_ARGS)
 	PG_RETURN_FLOAT8(distance);
 }
 
-/*
- * The inexact GiST distance method for geometric types that store bounding
- * boxes.
- *
- * Compute lossy distance from point to index entries.  The result is inexact
- * because index entries are bounding boxes, not the exact shapes of the
- * indexed geometric types.  We use distance from point to MBR of index entry.
- * This is a lower bound estimate of distance from point to indexed geometric
- * type.
- */
 static float8
-gist_bbox_distance(GISTENTRY *entry, Datum query,
-				   StrategyNumber strategy, bool *recheck)
+gist_box_distance_helper(GISTENTRY *entry, Datum query,
+						 StrategyNumber strategy)
 {
 	float8		distance;
 	StrategyNumber strategyGroup = strategy / GeoStrategyNumberOffset;
 
-	/* Bounding box distance is always inexact. */
-	*recheck = true;
-
 	switch (strategyGroup)
 	{
 		case PointStrategyNumberGroup:
@@ -1500,6 +1487,42 @@ gist_bbox_distance(GISTENTRY *entry, Datum query,
 }
 
 Datum
+gist_box_distance(PG_FUNCTION_ARGS)
+{
+	GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
+	Datum		query = PG_GETARG_DATUM(1);
+	StrategyNumber strategy = (StrategyNumber) PG_GETARG_UINT16(2);
+
+	/* Oid subtype = PG_GETARG_OID(3); */
+	/* bool	   *recheck = (bool *) PG_GETARG_POINTER(4); */
+	float8		distance;
+
+	distance = gist_box_distance_helper(entry, query, strategy);
+
+	PG_RETURN_FLOAT8(distance);
+}
+
+/*
+ * The inexact GiST distance method for geometric types that store bounding
+ * boxes.
+ *
+ * Compute lossy distance from point to index entries.  The result is inexact
+ * because index entries are bounding boxes, not the exact shapes of the
+ * indexed geometric types.  We use distance from point to MBR of index entry.
+ * This is a lower bound estimate of distance from point to indexed geometric
+ * type.
+ */
+static float8
+gist_bbox_distance(GISTENTRY *entry, Datum query,
+				   StrategyNumber strategy, bool *recheck)
+{
+	/* Bounding box distance is always inexact. */
+	*recheck = true;
+
+	return gist_box_distance_helper(entry, query, strategy);
+}
+
+Datum
 gist_circle_distance(PG_FUNCTION_ARGS)
 {
 	GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
diff --git a/src/include/catalog/pg_amop.dat b/src/include/catalog/pg_amop.dat
index cf63eb7..ebc38ae 100644
--- a/src/include/catalog/pg_amop.dat
+++ b/src/include/catalog/pg_amop.dat
@@ -1081,6 +1081,9 @@
   amopstrategy => '13', amopopr => '~(box,box)', amopmethod => 'gist' },
 { amopfamily => 'gist/box_ops', amoplefttype => 'box', amoprighttype => 'box',
   amopstrategy => '14', amopopr => '@(box,box)', amopmethod => 'gist' },
+{ amopfamily => 'gist/box_ops', amoplefttype => 'box', amoprighttype => 'point',
+  amopstrategy => '15', amoppurpose => 'o', amopopr => '<->(box,point)',
+  amopmethod => 'gist', amopsortfamily => 'btree/float_ops' },
 
 # gist point_ops
 { amopfamily => 'gist/point_ops', amoplefttype => 'point',
diff --git a/src/include/catalog/pg_amproc.dat b/src/include/catalog/pg_amproc.dat
index 020b741..5567b7e 100644
--- a/src/include/catalog/pg_amproc.dat
+++ b/src/include/catalog/pg_amproc.dat
@@ -419,6 +419,8 @@
   amprocrighttype => 'box', amprocnum => '6', amproc => 'gist_box_picksplit' },
 { amprocfamily => 'gist/box_ops', amproclefttype => 'box',
   amprocrighttype => 'box', amprocnum => '7', amproc => 'gist_box_same' },
+{ amprocfamily => 'gist/box_ops', amproclefttype => 'box',
+  amprocrighttype => 'box', amprocnum => '8', amproc => 'gist_box_distance' },
 { amprocfamily => 'gist/poly_ops', amproclefttype => 'polygon',
   amprocrighttype => 'polygon', amprocnum => '1',
   amproc => 'gist_poly_consistent' },
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 54327bf..d15f94a 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -7816,6 +7816,10 @@
 { oid => '2584', descr => 'GiST support',
   proname => 'gist_box_same', prorettype => 'internal',
   proargtypes => 'box box internal', prosrc => 'gist_box_same' },
+{ oid => '3998', descr => 'GiST support',
+  proname => 'gist_box_distance', prorettype => 'float8',
+  proargtypes => 'internal box int2 oid internal',
+  prosrc => 'gist_box_distance' },
 { oid => '2585', descr => 'GiST support',
   proname => 'gist_poly_consistent', prorettype => 'bool',
   proargtypes => 'internal polygon int2 oid internal',
diff --git a/src/test/regress/expected/gist.out b/src/test/regress/expected/gist.out
index 0a43449..2234876 100644
--- a/src/test/regress/expected/gist.out
+++ b/src/test/regress/expected/gist.out
@@ -203,6 +203,82 @@ select b from gist_tbl where b <@ box(point(5,5), point(6,6));
  (6,6),(6,6)
 (21 rows)
 
+-- Also test an index-only knn-search
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+                      QUERY PLAN                      
+------------------------------------------------------
+ Index Only Scan using gist_tbl_box_index on gist_tbl
+   Index Cond: (b <@ '(6,6),(5,5)'::box)
+   Order By: (b <-> '(5.2,5.91)'::point)
+(3 rows)
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+            b            
+-------------------------
+ (5.55,5.55),(5.55,5.55)
+ (5.6,5.6),(5.6,5.6)
+ (5.5,5.5),(5.5,5.5)
+ (5.65,5.65),(5.65,5.65)
+ (5.45,5.45),(5.45,5.45)
+ (5.7,5.7),(5.7,5.7)
+ (5.4,5.4),(5.4,5.4)
+ (5.75,5.75),(5.75,5.75)
+ (5.35,5.35),(5.35,5.35)
+ (5.8,5.8),(5.8,5.8)
+ (5.3,5.3),(5.3,5.3)
+ (5.85,5.85),(5.85,5.85)
+ (5.25,5.25),(5.25,5.25)
+ (5.9,5.9),(5.9,5.9)
+ (5.2,5.2),(5.2,5.2)
+ (5.95,5.95),(5.95,5.95)
+ (5.15,5.15),(5.15,5.15)
+ (6,6),(6,6)
+ (5.1,5.1),(5.1,5.1)
+ (5.05,5.05),(5.05,5.05)
+ (5,5),(5,5)
+(21 rows)
+
+-- Check commuted case as well
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+                      QUERY PLAN                      
+------------------------------------------------------
+ Index Only Scan using gist_tbl_box_index on gist_tbl
+   Index Cond: (b <@ '(6,6),(5,5)'::box)
+   Order By: (b <-> '(5.2,5.91)'::point)
+(3 rows)
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+            b            
+-------------------------
+ (5.55,5.55),(5.55,5.55)
+ (5.6,5.6),(5.6,5.6)
+ (5.5,5.5),(5.5,5.5)
+ (5.65,5.65),(5.65,5.65)
+ (5.45,5.45),(5.45,5.45)
+ (5.7,5.7),(5.7,5.7)
+ (5.4,5.4),(5.4,5.4)
+ (5.75,5.75),(5.75,5.75)
+ (5.35,5.35),(5.35,5.35)
+ (5.8,5.8),(5.8,5.8)
+ (5.3,5.3),(5.3,5.3)
+ (5.85,5.85),(5.85,5.85)
+ (5.25,5.25),(5.25,5.25)
+ (5.9,5.9),(5.9,5.9)
+ (5.2,5.2),(5.2,5.2)
+ (5.95,5.95),(5.95,5.95)
+ (5.15,5.15),(5.15,5.15)
+ (6,6),(6,6)
+ (5.1,5.1),(5.1,5.1)
+ (5.05,5.05),(5.05,5.05)
+ (5,5),(5,5)
+(21 rows)
+
 drop index gist_tbl_box_index;
 -- Test that an index-only scan is not chosen, when the query involves the
 -- circle column (the circle opclass does not support index-only scans).
diff --git a/src/test/regress/sql/gist.sql b/src/test/regress/sql/gist.sql
index 657b195..b9d398e 100644
--- a/src/test/regress/sql/gist.sql
+++ b/src/test/regress/sql/gist.sql
@@ -109,6 +109,22 @@ select b from gist_tbl where b <@ box(point(5,5), point(6,6));
 -- execute the same
 select b from gist_tbl where b <@ box(point(5,5), point(6,6));
 
+-- Also test an index-only knn-search
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+
+-- Check commuted case as well
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+
 drop index gist_tbl_box_index;
 
 -- Test that an index-only scan is not chosen, when the query involves the
-- 
2.7.4


--------------07EE9595454874974EAD75E7
Content-Type: text/x-patch;
 name="0003-Add-operator-box-point-to-SP-GiST-box_ops-v02.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="0003-Add-operator-box-point-to-SP-GiST-box_ops-v02.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH 2/3] Add operator <->(box, point) to GiST box_ops
@ 2019-03-07 20:49 Nikita Glukhov <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Nikita Glukhov @ 2019-03-07 20:49 UTC (permalink / raw)

---
 doc/src/sgml/gist.sgml             |  1 +
 src/backend/access/gist/gistproc.c | 49 +++++++++++++++---------
 src/include/catalog/pg_amop.dat    |  3 ++
 src/include/catalog/pg_amproc.dat  |  2 +
 src/include/catalog/pg_proc.dat    |  4 ++
 src/test/regress/expected/gist.out | 76 ++++++++++++++++++++++++++++++++++++++
 src/test/regress/sql/gist.sql      | 16 ++++++++
 7 files changed, 134 insertions(+), 17 deletions(-)

diff --git a/doc/src/sgml/gist.sgml b/doc/src/sgml/gist.sgml
index 763b8cf..2b43dfc 100644
--- a/doc/src/sgml/gist.sgml
+++ b/doc/src/sgml/gist.sgml
@@ -83,6 +83,7 @@
        <literal>~=</literal>
       </entry>
       <entry>
+       <literal>&lt;-&gt;</literal>
       </entry>
      </row>
      <row>
diff --git a/src/backend/access/gist/gistproc.c b/src/backend/access/gist/gistproc.c
index 1826b51..a668283 100644
--- a/src/backend/access/gist/gistproc.c
+++ b/src/backend/access/gist/gistproc.c
@@ -1464,26 +1464,13 @@ gist_point_distance(PG_FUNCTION_ARGS)
 	PG_RETURN_FLOAT8(distance);
 }
 
-/*
- * The inexact GiST distance method for geometric types that store bounding
- * boxes.
- *
- * Compute lossy distance from point to index entries.  The result is inexact
- * because index entries are bounding boxes, not the exact shapes of the
- * indexed geometric types.  We use distance from point to MBR of index entry.
- * This is a lower bound estimate of distance from point to indexed geometric
- * type.
- */
 static float8
-gist_bbox_distance(GISTENTRY *entry, Datum query,
-				   StrategyNumber strategy, bool *recheck)
+gist_box_distance_helper(GISTENTRY *entry, Datum query,
+						 StrategyNumber strategy)
 {
 	float8		distance;
 	StrategyNumber strategyGroup = strategy / GeoStrategyNumberOffset;
 
-	/* Bounding box distance is always inexact. */
-	*recheck = true;
-
 	switch (strategyGroup)
 	{
 		case PointStrategyNumberGroup:
@@ -1500,6 +1487,32 @@ gist_bbox_distance(GISTENTRY *entry, Datum query,
 }
 
 Datum
+gist_box_distance(PG_FUNCTION_ARGS)
+{
+	GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
+	Datum		query = PG_GETARG_DATUM(1);
+	StrategyNumber strategy = (StrategyNumber) PG_GETARG_UINT16(2);
+
+	/* Oid subtype = PG_GETARG_OID(3); */
+	/* bool	   *recheck = (bool *) PG_GETARG_POINTER(4); */
+	float8		distance;
+
+	distance = gist_box_distance_helper(entry, query, strategy);
+
+	PG_RETURN_FLOAT8(distance);
+}
+
+/*
+ * The inexact GiST distance methods for geometric types that store bounding
+ * boxes.
+ *
+ * Compute lossy distance from point to index entries.  The result is inexact
+ * because index entries are bounding boxes, not the exact shapes of the
+ * indexed geometric types.  We use distance from point to MBR of index entry.
+ * This is a lower bound estimate of distance from point to indexed geometric
+ * type.
+ */
+Datum
 gist_circle_distance(PG_FUNCTION_ARGS)
 {
 	GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
@@ -1510,7 +1523,8 @@ gist_circle_distance(PG_FUNCTION_ARGS)
 	bool	   *recheck = (bool *) PG_GETARG_POINTER(4);
 	float8		distance;
 
-	distance = gist_bbox_distance(entry, query, strategy, recheck);
+	distance = gist_box_distance_helper(entry, query, strategy);
+	*recheck = true;
 
 	PG_RETURN_FLOAT8(distance);
 }
@@ -1526,7 +1540,8 @@ gist_poly_distance(PG_FUNCTION_ARGS)
 	bool	   *recheck = (bool *) PG_GETARG_POINTER(4);
 	float8		distance;
 
-	distance = gist_bbox_distance(entry, query, strategy, recheck);
+	distance = gist_box_distance_helper(entry, query, strategy);
+	*recheck = true;
 
 	PG_RETURN_FLOAT8(distance);
 }
diff --git a/src/include/catalog/pg_amop.dat b/src/include/catalog/pg_amop.dat
index cf63eb7..ebc38ae 100644
--- a/src/include/catalog/pg_amop.dat
+++ b/src/include/catalog/pg_amop.dat
@@ -1081,6 +1081,9 @@
   amopstrategy => '13', amopopr => '~(box,box)', amopmethod => 'gist' },
 { amopfamily => 'gist/box_ops', amoplefttype => 'box', amoprighttype => 'box',
   amopstrategy => '14', amopopr => '@(box,box)', amopmethod => 'gist' },
+{ amopfamily => 'gist/box_ops', amoplefttype => 'box', amoprighttype => 'point',
+  amopstrategy => '15', amoppurpose => 'o', amopopr => '<->(box,point)',
+  amopmethod => 'gist', amopsortfamily => 'btree/float_ops' },
 
 # gist point_ops
 { amopfamily => 'gist/point_ops', amoplefttype => 'point',
diff --git a/src/include/catalog/pg_amproc.dat b/src/include/catalog/pg_amproc.dat
index 020b741..5567b7e 100644
--- a/src/include/catalog/pg_amproc.dat
+++ b/src/include/catalog/pg_amproc.dat
@@ -419,6 +419,8 @@
   amprocrighttype => 'box', amprocnum => '6', amproc => 'gist_box_picksplit' },
 { amprocfamily => 'gist/box_ops', amproclefttype => 'box',
   amprocrighttype => 'box', amprocnum => '7', amproc => 'gist_box_same' },
+{ amprocfamily => 'gist/box_ops', amproclefttype => 'box',
+  amprocrighttype => 'box', amprocnum => '8', amproc => 'gist_box_distance' },
 { amprocfamily => 'gist/poly_ops', amproclefttype => 'polygon',
   amprocrighttype => 'polygon', amprocnum => '1',
   amproc => 'gist_poly_consistent' },
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index e0852b8..762c099 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -7844,6 +7844,10 @@
 { oid => '2584', descr => 'GiST support',
   proname => 'gist_box_same', prorettype => 'internal',
   proargtypes => 'box box internal', prosrc => 'gist_box_same' },
+{ oid => '3998', descr => 'GiST support',
+  proname => 'gist_box_distance', prorettype => 'float8',
+  proargtypes => 'internal box int2 oid internal',
+  prosrc => 'gist_box_distance' },
 { oid => '2585', descr => 'GiST support',
   proname => 'gist_poly_consistent', prorettype => 'bool',
   proargtypes => 'internal polygon int2 oid internal',
diff --git a/src/test/regress/expected/gist.out b/src/test/regress/expected/gist.out
index 0a43449..2234876 100644
--- a/src/test/regress/expected/gist.out
+++ b/src/test/regress/expected/gist.out
@@ -203,6 +203,82 @@ select b from gist_tbl where b <@ box(point(5,5), point(6,6));
  (6,6),(6,6)
 (21 rows)
 
+-- Also test an index-only knn-search
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+                      QUERY PLAN                      
+------------------------------------------------------
+ Index Only Scan using gist_tbl_box_index on gist_tbl
+   Index Cond: (b <@ '(6,6),(5,5)'::box)
+   Order By: (b <-> '(5.2,5.91)'::point)
+(3 rows)
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+            b            
+-------------------------
+ (5.55,5.55),(5.55,5.55)
+ (5.6,5.6),(5.6,5.6)
+ (5.5,5.5),(5.5,5.5)
+ (5.65,5.65),(5.65,5.65)
+ (5.45,5.45),(5.45,5.45)
+ (5.7,5.7),(5.7,5.7)
+ (5.4,5.4),(5.4,5.4)
+ (5.75,5.75),(5.75,5.75)
+ (5.35,5.35),(5.35,5.35)
+ (5.8,5.8),(5.8,5.8)
+ (5.3,5.3),(5.3,5.3)
+ (5.85,5.85),(5.85,5.85)
+ (5.25,5.25),(5.25,5.25)
+ (5.9,5.9),(5.9,5.9)
+ (5.2,5.2),(5.2,5.2)
+ (5.95,5.95),(5.95,5.95)
+ (5.15,5.15),(5.15,5.15)
+ (6,6),(6,6)
+ (5.1,5.1),(5.1,5.1)
+ (5.05,5.05),(5.05,5.05)
+ (5,5),(5,5)
+(21 rows)
+
+-- Check commuted case as well
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+                      QUERY PLAN                      
+------------------------------------------------------
+ Index Only Scan using gist_tbl_box_index on gist_tbl
+   Index Cond: (b <@ '(6,6),(5,5)'::box)
+   Order By: (b <-> '(5.2,5.91)'::point)
+(3 rows)
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+            b            
+-------------------------
+ (5.55,5.55),(5.55,5.55)
+ (5.6,5.6),(5.6,5.6)
+ (5.5,5.5),(5.5,5.5)
+ (5.65,5.65),(5.65,5.65)
+ (5.45,5.45),(5.45,5.45)
+ (5.7,5.7),(5.7,5.7)
+ (5.4,5.4),(5.4,5.4)
+ (5.75,5.75),(5.75,5.75)
+ (5.35,5.35),(5.35,5.35)
+ (5.8,5.8),(5.8,5.8)
+ (5.3,5.3),(5.3,5.3)
+ (5.85,5.85),(5.85,5.85)
+ (5.25,5.25),(5.25,5.25)
+ (5.9,5.9),(5.9,5.9)
+ (5.2,5.2),(5.2,5.2)
+ (5.95,5.95),(5.95,5.95)
+ (5.15,5.15),(5.15,5.15)
+ (6,6),(6,6)
+ (5.1,5.1),(5.1,5.1)
+ (5.05,5.05),(5.05,5.05)
+ (5,5),(5,5)
+(21 rows)
+
 drop index gist_tbl_box_index;
 -- Test that an index-only scan is not chosen, when the query involves the
 -- circle column (the circle opclass does not support index-only scans).
diff --git a/src/test/regress/sql/gist.sql b/src/test/regress/sql/gist.sql
index 657b195..b9d398e 100644
--- a/src/test/regress/sql/gist.sql
+++ b/src/test/regress/sql/gist.sql
@@ -109,6 +109,22 @@ select b from gist_tbl where b <@ box(point(5,5), point(6,6));
 -- execute the same
 select b from gist_tbl where b <@ box(point(5,5), point(6,6));
 
+-- Also test an index-only knn-search
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+
+-- Check commuted case as well
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+
 drop index gist_tbl_box_index;
 
 -- Test that an index-only scan is not chosen, when the query involves the
-- 
2.7.4


--------------C466D744B1EAB9FA85D22553
Content-Type: text/x-patch;
 name="0003-Add-operator-box-point-to-SP-GiST-box_ops-v03.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename="0003-Add-operator-box-point-to-SP-GiST-box_ops-v03.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH 2/3] Add operator <->(box, point) to GiST box_ops
@ 2019-03-07 20:49 Nikita Glukhov <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Nikita Glukhov @ 2019-03-07 20:49 UTC (permalink / raw)

---
 doc/src/sgml/gist.sgml             |  1 +
 src/backend/access/gist/gistproc.c | 53 ++++++++++++++++++--------
 src/include/catalog/pg_amop.dat    |  3 ++
 src/include/catalog/pg_amproc.dat  |  2 +
 src/include/catalog/pg_proc.dat    |  4 ++
 src/test/regress/expected/gist.out | 76 ++++++++++++++++++++++++++++++++++++++
 src/test/regress/sql/gist.sql      | 16 ++++++++
 7 files changed, 140 insertions(+), 15 deletions(-)

diff --git a/doc/src/sgml/gist.sgml b/doc/src/sgml/gist.sgml
index 44a3b2c..e903319 100644
--- a/doc/src/sgml/gist.sgml
+++ b/doc/src/sgml/gist.sgml
@@ -83,6 +83,7 @@
        <literal>~=</literal>
       </entry>
       <entry>
+       <literal>&lt;-&gt;</literal>
       </entry>
      </row>
      <row>
diff --git a/src/backend/access/gist/gistproc.c b/src/backend/access/gist/gistproc.c
index c9da230..89643b4 100644
--- a/src/backend/access/gist/gistproc.c
+++ b/src/backend/access/gist/gistproc.c
@@ -1464,26 +1464,13 @@ gist_point_distance(PG_FUNCTION_ARGS)
 	PG_RETURN_FLOAT8(distance);
 }
 
-/*
- * The inexact GiST distance method for geometric types that store bounding
- * boxes.
- *
- * Compute lossy distance from point to index entries.  The result is inexact
- * because index entries are bounding boxes, not the exact shapes of the
- * indexed geometric types.  We use distance from point to MBR of index entry.
- * This is a lower bound estimate of distance from point to indexed geometric
- * type.
- */
 static float8
-gist_bbox_distance(GISTENTRY *entry, Datum query,
-				   StrategyNumber strategy, bool *recheck)
+gist_box_distance_helper(GISTENTRY *entry, Datum query,
+						 StrategyNumber strategy)
 {
 	float8		distance;
 	StrategyNumber strategyGroup = strategy / GeoStrategyNumberOffset;
 
-	/* Bounding box distance is always inexact. */
-	*recheck = true;
-
 	switch (strategyGroup)
 	{
 		case PointStrategyNumberGroup:
@@ -1500,6 +1487,42 @@ gist_bbox_distance(GISTENTRY *entry, Datum query,
 }
 
 Datum
+gist_box_distance(PG_FUNCTION_ARGS)
+{
+	GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
+	Datum		query = PG_GETARG_DATUM(1);
+	StrategyNumber strategy = (StrategyNumber) PG_GETARG_UINT16(2);
+
+	/* Oid subtype = PG_GETARG_OID(3); */
+	/* bool	   *recheck = (bool *) PG_GETARG_POINTER(4); */
+	float8		distance;
+
+	distance = gist_box_distance_helper(entry, query, strategy);
+
+	PG_RETURN_FLOAT8(distance);
+}
+
+/*
+ * The inexact GiST distance method for geometric types that store bounding
+ * boxes.
+ *
+ * Compute lossy distance from point to index entries.  The result is inexact
+ * because index entries are bounding boxes, not the exact shapes of the
+ * indexed geometric types.  We use distance from point to MBR of index entry.
+ * This is a lower bound estimate of distance from point to indexed geometric
+ * type.
+ */
+static float8
+gist_bbox_distance(GISTENTRY *entry, Datum query,
+				   StrategyNumber strategy, bool *recheck)
+{
+	/* Bounding box distance is always inexact. */
+	*recheck = true;
+
+	return gist_box_distance_helper(entry, query, strategy);
+}
+
+Datum
 gist_circle_distance(PG_FUNCTION_ARGS)
 {
 	GISTENTRY  *entry = (GISTENTRY *) PG_GETARG_POINTER(0);
diff --git a/src/include/catalog/pg_amop.dat b/src/include/catalog/pg_amop.dat
index 0ab95d8..8e74f86 100644
--- a/src/include/catalog/pg_amop.dat
+++ b/src/include/catalog/pg_amop.dat
@@ -1081,6 +1081,9 @@
   amopstrategy => '13', amopopr => '~(box,box)', amopmethod => 'gist' },
 { amopfamily => 'gist/box_ops', amoplefttype => 'box', amoprighttype => 'box',
   amopstrategy => '14', amopopr => '@(box,box)', amopmethod => 'gist' },
+{ amopfamily => 'gist/box_ops', amoplefttype => 'box', amoprighttype => 'point',
+  amopstrategy => '15', amoppurpose => 'o', amopopr => '<->(box,point)',
+  amopmethod => 'gist', amopsortfamily => 'btree/float_ops' },
 
 # gist point_ops
 { amopfamily => 'gist/point_ops', amoplefttype => 'point',
diff --git a/src/include/catalog/pg_amproc.dat b/src/include/catalog/pg_amproc.dat
index 020b741..5567b7e 100644
--- a/src/include/catalog/pg_amproc.dat
+++ b/src/include/catalog/pg_amproc.dat
@@ -419,6 +419,8 @@
   amprocrighttype => 'box', amprocnum => '6', amproc => 'gist_box_picksplit' },
 { amprocfamily => 'gist/box_ops', amproclefttype => 'box',
   amprocrighttype => 'box', amprocnum => '7', amproc => 'gist_box_same' },
+{ amprocfamily => 'gist/box_ops', amproclefttype => 'box',
+  amprocrighttype => 'box', amprocnum => '8', amproc => 'gist_box_distance' },
 { amprocfamily => 'gist/poly_ops', amproclefttype => 'polygon',
   amprocrighttype => 'polygon', amprocnum => '1',
   amproc => 'gist_poly_consistent' },
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 3800150..d6477a3 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -7760,6 +7760,10 @@
 { oid => '2584', descr => 'GiST support',
   proname => 'gist_box_same', prorettype => 'internal',
   proargtypes => 'box box internal', prosrc => 'gist_box_same' },
+{ oid => '3998', descr => 'GiST support',
+  proname => 'gist_box_distance', prorettype => 'float8',
+  proargtypes => 'internal box int2 oid internal',
+  prosrc => 'gist_box_distance' },
 { oid => '2585', descr => 'GiST support',
   proname => 'gist_poly_consistent', prorettype => 'bool',
   proargtypes => 'internal polygon int2 oid internal',
diff --git a/src/test/regress/expected/gist.out b/src/test/regress/expected/gist.out
index f5a2993..e8c2685 100644
--- a/src/test/regress/expected/gist.out
+++ b/src/test/regress/expected/gist.out
@@ -205,6 +205,82 @@ select b from gist_tbl where b <@ box(point(5,5), point(6,6));
  (6,6),(6,6)
 (21 rows)
 
+-- Also test an index-only knn-search
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+                      QUERY PLAN                      
+------------------------------------------------------
+ Index Only Scan using gist_tbl_box_index on gist_tbl
+   Index Cond: (b <@ '(6,6),(5,5)'::box)
+   Order By: (b <-> '(5.2,5.91)'::point)
+(3 rows)
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+            b            
+-------------------------
+ (5.55,5.55),(5.55,5.55)
+ (5.6,5.6),(5.6,5.6)
+ (5.5,5.5),(5.5,5.5)
+ (5.65,5.65),(5.65,5.65)
+ (5.45,5.45),(5.45,5.45)
+ (5.7,5.7),(5.7,5.7)
+ (5.4,5.4),(5.4,5.4)
+ (5.75,5.75),(5.75,5.75)
+ (5.35,5.35),(5.35,5.35)
+ (5.8,5.8),(5.8,5.8)
+ (5.3,5.3),(5.3,5.3)
+ (5.85,5.85),(5.85,5.85)
+ (5.25,5.25),(5.25,5.25)
+ (5.9,5.9),(5.9,5.9)
+ (5.2,5.2),(5.2,5.2)
+ (5.95,5.95),(5.95,5.95)
+ (5.15,5.15),(5.15,5.15)
+ (6,6),(6,6)
+ (5.1,5.1),(5.1,5.1)
+ (5.05,5.05),(5.05,5.05)
+ (5,5),(5,5)
+(21 rows)
+
+-- Check commuted case as well
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+                      QUERY PLAN                      
+------------------------------------------------------
+ Index Only Scan using gist_tbl_box_index on gist_tbl
+   Index Cond: (b <@ '(6,6),(5,5)'::box)
+   Order By: (b <-> '(5.2,5.91)'::point)
+(3 rows)
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+            b            
+-------------------------
+ (5.55,5.55),(5.55,5.55)
+ (5.6,5.6),(5.6,5.6)
+ (5.5,5.5),(5.5,5.5)
+ (5.65,5.65),(5.65,5.65)
+ (5.45,5.45),(5.45,5.45)
+ (5.7,5.7),(5.7,5.7)
+ (5.4,5.4),(5.4,5.4)
+ (5.75,5.75),(5.75,5.75)
+ (5.35,5.35),(5.35,5.35)
+ (5.8,5.8),(5.8,5.8)
+ (5.3,5.3),(5.3,5.3)
+ (5.85,5.85),(5.85,5.85)
+ (5.25,5.25),(5.25,5.25)
+ (5.9,5.9),(5.9,5.9)
+ (5.2,5.2),(5.2,5.2)
+ (5.95,5.95),(5.95,5.95)
+ (5.15,5.15),(5.15,5.15)
+ (6,6),(6,6)
+ (5.1,5.1),(5.1,5.1)
+ (5.05,5.05),(5.05,5.05)
+ (5,5),(5,5)
+(21 rows)
+
 drop index gist_tbl_box_index;
 -- Test that an index-only scan is not chosen, when the query involves the
 -- circle column (the circle opclass does not support index-only scans).
diff --git a/src/test/regress/sql/gist.sql b/src/test/regress/sql/gist.sql
index bae722f..406fb83 100644
--- a/src/test/regress/sql/gist.sql
+++ b/src/test/regress/sql/gist.sql
@@ -111,6 +111,22 @@ select b from gist_tbl where b <@ box(point(5,5), point(6,6));
 -- execute the same
 select b from gist_tbl where b <@ box(point(5,5), point(6,6));
 
+-- Also test an index-only knn-search
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by b <-> point(5.2, 5.91);
+
+-- Check commuted case as well
+explain (costs off)
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+
+select b from gist_tbl where b <@ box(point(5,5), point(6,6))
+order by point(5.2, 5.91) <-> b;
+
 drop index gist_tbl_box_index;
 
 -- Test that an index-only scan is not chosen, when the query involves the
-- 
2.7.4


--------------B01ADF66983FA504E371CA13
Content-Type: text/x-patch;
 name="0003-Add-box-point-distance-operator-to-SP-GiST-box_ops-v01.patch"
Content-Transfer-Encoding: 7bit
Content-Disposition: attachment;
 filename*0="0003-Add-box-point-distance-operator-to-SP-GiST-box_ops-v01.";
 filename*1="patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v1 4/7] Row pattern recognition patch (executor).
@ 2023-06-25 11:48 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-06-25 11:48 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 223 +++++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  | 274 ++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat      |   9 +
 src/include/nodes/execnodes.h        |  12 ++
 src/include/windowapi.h              |   9 +
 5 files changed, 517 insertions(+), 10 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..ae997dff86 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -48,6 +48,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +160,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -195,9 +204,9 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
 
 /*
  * initialize_windowaggregate
@@ -2388,6 +2397,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2498,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2692,69 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+			if (func->winfnoid != F_RPR)
+				continue;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "RPR must have 1 argument but function %d has %d args", func->winfnoid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "RPR's arg is not Var");
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2762,76 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2849,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2900,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3242,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3420,14 +3582,53 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3583,15 +3784,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3821,9 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..63b225271c 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -39,7 +42,9 @@ typedef struct
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
-
+static bool get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos);
+static int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+							int relpos, char *vname, char *quantifier, bool *result);
 
 /*
  * utility routine for *_rank functions.
@@ -713,3 +718,270 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * rpr
+ * allow to use "Row pattern recognition: WINDOW clause" (SQL:2016 R020) in
+ * the target list.
+ * Usage: SELECT rpr(colname) OVER (..)
+ * where colname is defined in PATTERN clause.
+ */
+Datum
+window_rpr(PG_FUNCTION_ARGS)
+{
+#define	MAX_PATTERNS	16	/* max variables in PATTERN clause */
+
+	WindowObject winobj = PG_WINDOW_OBJECT();
+	WindowAggState	*winstate = WinGetAggState(winobj);
+	Datum		result;
+	bool		expression_result;
+	bool		isnull;
+	int			relpos;
+	int64		curr_pos, markpos;
+	ListCell	*lc, *lc1;
+
+	curr_pos = WinGetCurrentPosition(winobj);
+	elog(DEBUG1, "rpr is called. row: " INT64_FORMAT, curr_pos);
+
+	/*
+	 * Evaluate PATTERN until one of expressions is not true or out of frame.
+	 */
+	relpos = 0;
+
+	forboth(lc, winstate->patternVariableList, lc1, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc));
+		char	*quantifier = strVal(lfirst(lc1));
+
+		elog(DEBUG1, "relpos: %d pattern vname: %s quantifier: %s", relpos, vname, quantifier);
+
+		/* evaluate row pattern against current row */
+		relpos = evaluate_pattern(winobj, winstate, relpos, vname, quantifier, &expression_result);
+
+		/*
+		 * If the expression did not match, we are done.
+		 */
+		if (!expression_result)
+			break;
+
+		/* out of frame? */
+		if (relpos < 0)
+			break;
+
+		/* count up relative row position */
+		relpos++;
+	}
+
+	elog(DEBUG1, "relpos: %d", relpos);
+
+	/*
+	 * If current row satified the pattern, return argument expression.
+	 */
+	if (expression_result)
+	{
+		result = WinGetFuncArgInFrame(winobj, 0,
+									  0, WINDOW_SEEK_HEAD, false,
+									  &isnull, NULL);
+	}
+
+	/*
+	 * At this point we can set mark down to current pos -2.
+	 */
+	markpos = curr_pos -2;
+	elog(DEBUG1, "markpos: " INT64_FORMAT, markpos);
+	if (markpos >= 0)
+		WinSetMarkPosition(winobj, markpos);
+
+	if (expression_result)
+		PG_RETURN_DATUM(result);
+
+	PG_RETURN_NULL();
+}
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match relative row position
+ * -1: current row is out of frame
+ */
+static
+int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+					 int relpos, char *vname, char *quantifier, bool *result)
+{
+	ExprContext	*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell	*lc1, *lc2;
+	ExprState	*pat;
+	Datum		eval_result;
+	int			sts;
+	bool		out_of_frame = false;
+	bool		isnull;
+	StringInfo	encoded_str = makeStringInfo();
+	char		pattern_str[128];
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+		bool	second_try_match = false;
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		for (;;)
+		{
+			if (!get_slots(winobj, winstate, relpos))
+			{
+				out_of_frame = true;
+				break;	/* current row is out of frame */
+			}
+
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: %d", vname, relpos);
+				break;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: %d", vname, relpos);
+					break;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: %d", vname, relpos);
+					appendStringInfoChar(encoded_str, vname[0]);
+
+					/* If quantifier is "+", we need to look for more matching row */
+					if (quantifier && !strcmp(quantifier, "+"))
+					{
+						/* remember that we want to try another row */
+						second_try_match = true;
+						relpos++;
+					}
+					else
+						break;
+				}
+			}
+		}
+		if (second_try_match)
+			relpos--;
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+
+		/* build regular expression */
+		snprintf(pattern_str, sizeof(pattern_str), "%c%s", vname[0], quantifier);
+
+		/*
+		 * Do regular expression matching against sequence of rows satisfying
+		 * the expression using regexp_instr().
+		 */
+		sts = DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+													PointerGetDatum(cstring_to_text(encoded_str->data)),
+													PointerGetDatum(cstring_to_text(pattern_str))));
+		elog(DEBUG1, "regexp_instr returned: %d. str: %s regexp: %s",
+			 sts, encoded_str->data, pattern_str);
+		*result = (sts > 0)? true : false;
+	}
+	return relpos;
+}
+
+/*
+ * Get current, previous and next tuple.
+ * Returns true if still within frame.
+ */
+static bool
+get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos)
+{
+	TupleTableSlot *slot;
+	bool	isnull, isout;
+	int		sts;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* for current row */
+	slot = winstate->temp_slot_1;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "current row is out of frame");
+		econtext->ecxt_scantuple = winstate->null_slot;
+		return false;
+	}
+	else
+		econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		sts = WinGetSlotInFrame(winobj, slot,
+								current_pos - 1, WINDOW_SEEK_HEAD, false,
+								&isnull, &isout);
+		if (sts < 0)
+		{
+			elog(DEBUG1, "previous row out of frame at: %d", current_pos);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		econtext->ecxt_outertuple = slot;
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos + 1, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "next row out of frame at: %d", current_pos);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+		econtext->ecxt_innertuple = slot;
+
+	return true;
+}
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..e3a9e0ffeb 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,15 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'row pattern recognition in window',
+  proname => 'rpr', prokind => 'w', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_rpr' },
+{ oid => '6123', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6124', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..bc95c5fe9b 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,13 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('*', '+' or '?'. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2562,11 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..a0facf38fe 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,16 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Sun_Jun_25_21_05_09_2023_126)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v1-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v1 4/7] Row pattern recognition patch (executor).
@ 2023-06-25 11:48 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-06-25 11:48 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 223 +++++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  | 274 ++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat      |   9 +
 src/include/nodes/execnodes.h        |  12 ++
 src/include/windowapi.h              |   9 +
 5 files changed, 517 insertions(+), 10 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..ae997dff86 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -48,6 +48,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +160,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -195,9 +204,9 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
 
 /*
  * initialize_windowaggregate
@@ -2388,6 +2397,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2498,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2692,69 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+			if (func->winfnoid != F_RPR)
+				continue;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "RPR must have 1 argument but function %d has %d args", func->winfnoid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "RPR's arg is not Var");
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2762,76 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2849,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2900,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3242,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3420,14 +3582,53 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3583,15 +3784,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3821,9 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..63b225271c 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -39,7 +42,9 @@ typedef struct
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
-
+static bool get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos);
+static int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+							int relpos, char *vname, char *quantifier, bool *result);
 
 /*
  * utility routine for *_rank functions.
@@ -713,3 +718,270 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * rpr
+ * allow to use "Row pattern recognition: WINDOW clause" (SQL:2016 R020) in
+ * the target list.
+ * Usage: SELECT rpr(colname) OVER (..)
+ * where colname is defined in PATTERN clause.
+ */
+Datum
+window_rpr(PG_FUNCTION_ARGS)
+{
+#define	MAX_PATTERNS	16	/* max variables in PATTERN clause */
+
+	WindowObject winobj = PG_WINDOW_OBJECT();
+	WindowAggState	*winstate = WinGetAggState(winobj);
+	Datum		result;
+	bool		expression_result;
+	bool		isnull;
+	int			relpos;
+	int64		curr_pos, markpos;
+	ListCell	*lc, *lc1;
+
+	curr_pos = WinGetCurrentPosition(winobj);
+	elog(DEBUG1, "rpr is called. row: " INT64_FORMAT, curr_pos);
+
+	/*
+	 * Evaluate PATTERN until one of expressions is not true or out of frame.
+	 */
+	relpos = 0;
+
+	forboth(lc, winstate->patternVariableList, lc1, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc));
+		char	*quantifier = strVal(lfirst(lc1));
+
+		elog(DEBUG1, "relpos: %d pattern vname: %s quantifier: %s", relpos, vname, quantifier);
+
+		/* evaluate row pattern against current row */
+		relpos = evaluate_pattern(winobj, winstate, relpos, vname, quantifier, &expression_result);
+
+		/*
+		 * If the expression did not match, we are done.
+		 */
+		if (!expression_result)
+			break;
+
+		/* out of frame? */
+		if (relpos < 0)
+			break;
+
+		/* count up relative row position */
+		relpos++;
+	}
+
+	elog(DEBUG1, "relpos: %d", relpos);
+
+	/*
+	 * If current row satified the pattern, return argument expression.
+	 */
+	if (expression_result)
+	{
+		result = WinGetFuncArgInFrame(winobj, 0,
+									  0, WINDOW_SEEK_HEAD, false,
+									  &isnull, NULL);
+	}
+
+	/*
+	 * At this point we can set mark down to current pos -2.
+	 */
+	markpos = curr_pos -2;
+	elog(DEBUG1, "markpos: " INT64_FORMAT, markpos);
+	if (markpos >= 0)
+		WinSetMarkPosition(winobj, markpos);
+
+	if (expression_result)
+		PG_RETURN_DATUM(result);
+
+	PG_RETURN_NULL();
+}
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match relative row position
+ * -1: current row is out of frame
+ */
+static
+int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+					 int relpos, char *vname, char *quantifier, bool *result)
+{
+	ExprContext	*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell	*lc1, *lc2;
+	ExprState	*pat;
+	Datum		eval_result;
+	int			sts;
+	bool		out_of_frame = false;
+	bool		isnull;
+	StringInfo	encoded_str = makeStringInfo();
+	char		pattern_str[128];
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+		bool	second_try_match = false;
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		for (;;)
+		{
+			if (!get_slots(winobj, winstate, relpos))
+			{
+				out_of_frame = true;
+				break;	/* current row is out of frame */
+			}
+
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: %d", vname, relpos);
+				break;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: %d", vname, relpos);
+					break;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: %d", vname, relpos);
+					appendStringInfoChar(encoded_str, vname[0]);
+
+					/* If quantifier is "+", we need to look for more matching row */
+					if (quantifier && !strcmp(quantifier, "+"))
+					{
+						/* remember that we want to try another row */
+						second_try_match = true;
+						relpos++;
+					}
+					else
+						break;
+				}
+			}
+		}
+		if (second_try_match)
+			relpos--;
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+
+		/* build regular expression */
+		snprintf(pattern_str, sizeof(pattern_str), "%c%s", vname[0], quantifier);
+
+		/*
+		 * Do regular expression matching against sequence of rows satisfying
+		 * the expression using regexp_instr().
+		 */
+		sts = DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+													PointerGetDatum(cstring_to_text(encoded_str->data)),
+													PointerGetDatum(cstring_to_text(pattern_str))));
+		elog(DEBUG1, "regexp_instr returned: %d. str: %s regexp: %s",
+			 sts, encoded_str->data, pattern_str);
+		*result = (sts > 0)? true : false;
+	}
+	return relpos;
+}
+
+/*
+ * Get current, previous and next tuple.
+ * Returns true if still within frame.
+ */
+static bool
+get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos)
+{
+	TupleTableSlot *slot;
+	bool	isnull, isout;
+	int		sts;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* for current row */
+	slot = winstate->temp_slot_1;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "current row is out of frame");
+		econtext->ecxt_scantuple = winstate->null_slot;
+		return false;
+	}
+	else
+		econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		sts = WinGetSlotInFrame(winobj, slot,
+								current_pos - 1, WINDOW_SEEK_HEAD, false,
+								&isnull, &isout);
+		if (sts < 0)
+		{
+			elog(DEBUG1, "previous row out of frame at: %d", current_pos);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		econtext->ecxt_outertuple = slot;
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos + 1, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "next row out of frame at: %d", current_pos);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+		econtext->ecxt_innertuple = slot;
+
+	return true;
+}
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..e3a9e0ffeb 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,15 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'row pattern recognition in window',
+  proname => 'rpr', prokind => 'w', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_rpr' },
+{ oid => '6123', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6124', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..bc95c5fe9b 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,13 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('*', '+' or '?'. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2562,11 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..a0facf38fe 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,16 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Sun_Jun_25_21_05_09_2023_126)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v1-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v1 4/7] Row pattern recognition patch (executor).
@ 2023-06-25 11:48 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-06-25 11:48 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 223 +++++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  | 274 ++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat      |   9 +
 src/include/nodes/execnodes.h        |  12 ++
 src/include/windowapi.h              |   9 +
 5 files changed, 517 insertions(+), 10 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..ae997dff86 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -48,6 +48,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +160,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -195,9 +204,9 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
 
 /*
  * initialize_windowaggregate
@@ -2388,6 +2397,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2498,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2692,69 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+			if (func->winfnoid != F_RPR)
+				continue;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "RPR must have 1 argument but function %d has %d args", func->winfnoid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "RPR's arg is not Var");
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2762,76 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2849,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2900,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3242,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3420,14 +3582,53 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3583,15 +3784,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3821,9 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..63b225271c 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -39,7 +42,9 @@ typedef struct
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
-
+static bool get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos);
+static int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+							int relpos, char *vname, char *quantifier, bool *result);
 
 /*
  * utility routine for *_rank functions.
@@ -713,3 +718,270 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * rpr
+ * allow to use "Row pattern recognition: WINDOW clause" (SQL:2016 R020) in
+ * the target list.
+ * Usage: SELECT rpr(colname) OVER (..)
+ * where colname is defined in PATTERN clause.
+ */
+Datum
+window_rpr(PG_FUNCTION_ARGS)
+{
+#define	MAX_PATTERNS	16	/* max variables in PATTERN clause */
+
+	WindowObject winobj = PG_WINDOW_OBJECT();
+	WindowAggState	*winstate = WinGetAggState(winobj);
+	Datum		result;
+	bool		expression_result;
+	bool		isnull;
+	int			relpos;
+	int64		curr_pos, markpos;
+	ListCell	*lc, *lc1;
+
+	curr_pos = WinGetCurrentPosition(winobj);
+	elog(DEBUG1, "rpr is called. row: " INT64_FORMAT, curr_pos);
+
+	/*
+	 * Evaluate PATTERN until one of expressions is not true or out of frame.
+	 */
+	relpos = 0;
+
+	forboth(lc, winstate->patternVariableList, lc1, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc));
+		char	*quantifier = strVal(lfirst(lc1));
+
+		elog(DEBUG1, "relpos: %d pattern vname: %s quantifier: %s", relpos, vname, quantifier);
+
+		/* evaluate row pattern against current row */
+		relpos = evaluate_pattern(winobj, winstate, relpos, vname, quantifier, &expression_result);
+
+		/*
+		 * If the expression did not match, we are done.
+		 */
+		if (!expression_result)
+			break;
+
+		/* out of frame? */
+		if (relpos < 0)
+			break;
+
+		/* count up relative row position */
+		relpos++;
+	}
+
+	elog(DEBUG1, "relpos: %d", relpos);
+
+	/*
+	 * If current row satified the pattern, return argument expression.
+	 */
+	if (expression_result)
+	{
+		result = WinGetFuncArgInFrame(winobj, 0,
+									  0, WINDOW_SEEK_HEAD, false,
+									  &isnull, NULL);
+	}
+
+	/*
+	 * At this point we can set mark down to current pos -2.
+	 */
+	markpos = curr_pos -2;
+	elog(DEBUG1, "markpos: " INT64_FORMAT, markpos);
+	if (markpos >= 0)
+		WinSetMarkPosition(winobj, markpos);
+
+	if (expression_result)
+		PG_RETURN_DATUM(result);
+
+	PG_RETURN_NULL();
+}
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match relative row position
+ * -1: current row is out of frame
+ */
+static
+int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+					 int relpos, char *vname, char *quantifier, bool *result)
+{
+	ExprContext	*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell	*lc1, *lc2;
+	ExprState	*pat;
+	Datum		eval_result;
+	int			sts;
+	bool		out_of_frame = false;
+	bool		isnull;
+	StringInfo	encoded_str = makeStringInfo();
+	char		pattern_str[128];
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+		bool	second_try_match = false;
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		for (;;)
+		{
+			if (!get_slots(winobj, winstate, relpos))
+			{
+				out_of_frame = true;
+				break;	/* current row is out of frame */
+			}
+
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: %d", vname, relpos);
+				break;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: %d", vname, relpos);
+					break;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: %d", vname, relpos);
+					appendStringInfoChar(encoded_str, vname[0]);
+
+					/* If quantifier is "+", we need to look for more matching row */
+					if (quantifier && !strcmp(quantifier, "+"))
+					{
+						/* remember that we want to try another row */
+						second_try_match = true;
+						relpos++;
+					}
+					else
+						break;
+				}
+			}
+		}
+		if (second_try_match)
+			relpos--;
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+
+		/* build regular expression */
+		snprintf(pattern_str, sizeof(pattern_str), "%c%s", vname[0], quantifier);
+
+		/*
+		 * Do regular expression matching against sequence of rows satisfying
+		 * the expression using regexp_instr().
+		 */
+		sts = DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+													PointerGetDatum(cstring_to_text(encoded_str->data)),
+													PointerGetDatum(cstring_to_text(pattern_str))));
+		elog(DEBUG1, "regexp_instr returned: %d. str: %s regexp: %s",
+			 sts, encoded_str->data, pattern_str);
+		*result = (sts > 0)? true : false;
+	}
+	return relpos;
+}
+
+/*
+ * Get current, previous and next tuple.
+ * Returns true if still within frame.
+ */
+static bool
+get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos)
+{
+	TupleTableSlot *slot;
+	bool	isnull, isout;
+	int		sts;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* for current row */
+	slot = winstate->temp_slot_1;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "current row is out of frame");
+		econtext->ecxt_scantuple = winstate->null_slot;
+		return false;
+	}
+	else
+		econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		sts = WinGetSlotInFrame(winobj, slot,
+								current_pos - 1, WINDOW_SEEK_HEAD, false,
+								&isnull, &isout);
+		if (sts < 0)
+		{
+			elog(DEBUG1, "previous row out of frame at: %d", current_pos);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		econtext->ecxt_outertuple = slot;
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos + 1, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "next row out of frame at: %d", current_pos);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+		econtext->ecxt_innertuple = slot;
+
+	return true;
+}
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..e3a9e0ffeb 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,15 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'row pattern recognition in window',
+  proname => 'rpr', prokind => 'w', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_rpr' },
+{ oid => '6123', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6124', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..bc95c5fe9b 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,13 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('*', '+' or '?'. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2562,11 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..a0facf38fe 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,16 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Sun_Jun_25_21_05_09_2023_126)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v1-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v1 4/7] Row pattern recognition patch (executor).
@ 2023-06-25 11:48 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-06-25 11:48 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 223 +++++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  | 274 ++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat      |   9 +
 src/include/nodes/execnodes.h        |  12 ++
 src/include/windowapi.h              |   9 +
 5 files changed, 517 insertions(+), 10 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..ae997dff86 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -48,6 +48,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +160,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -195,9 +204,9 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
 
 /*
  * initialize_windowaggregate
@@ -2388,6 +2397,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2498,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2692,69 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+			if (func->winfnoid != F_RPR)
+				continue;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "RPR must have 1 argument but function %d has %d args", func->winfnoid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "RPR's arg is not Var");
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2762,76 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2849,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2900,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3242,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3420,14 +3582,53 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3583,15 +3784,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3821,9 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..63b225271c 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -39,7 +42,9 @@ typedef struct
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
-
+static bool get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos);
+static int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+							int relpos, char *vname, char *quantifier, bool *result);
 
 /*
  * utility routine for *_rank functions.
@@ -713,3 +718,270 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * rpr
+ * allow to use "Row pattern recognition: WINDOW clause" (SQL:2016 R020) in
+ * the target list.
+ * Usage: SELECT rpr(colname) OVER (..)
+ * where colname is defined in PATTERN clause.
+ */
+Datum
+window_rpr(PG_FUNCTION_ARGS)
+{
+#define	MAX_PATTERNS	16	/* max variables in PATTERN clause */
+
+	WindowObject winobj = PG_WINDOW_OBJECT();
+	WindowAggState	*winstate = WinGetAggState(winobj);
+	Datum		result;
+	bool		expression_result;
+	bool		isnull;
+	int			relpos;
+	int64		curr_pos, markpos;
+	ListCell	*lc, *lc1;
+
+	curr_pos = WinGetCurrentPosition(winobj);
+	elog(DEBUG1, "rpr is called. row: " INT64_FORMAT, curr_pos);
+
+	/*
+	 * Evaluate PATTERN until one of expressions is not true or out of frame.
+	 */
+	relpos = 0;
+
+	forboth(lc, winstate->patternVariableList, lc1, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc));
+		char	*quantifier = strVal(lfirst(lc1));
+
+		elog(DEBUG1, "relpos: %d pattern vname: %s quantifier: %s", relpos, vname, quantifier);
+
+		/* evaluate row pattern against current row */
+		relpos = evaluate_pattern(winobj, winstate, relpos, vname, quantifier, &expression_result);
+
+		/*
+		 * If the expression did not match, we are done.
+		 */
+		if (!expression_result)
+			break;
+
+		/* out of frame? */
+		if (relpos < 0)
+			break;
+
+		/* count up relative row position */
+		relpos++;
+	}
+
+	elog(DEBUG1, "relpos: %d", relpos);
+
+	/*
+	 * If current row satified the pattern, return argument expression.
+	 */
+	if (expression_result)
+	{
+		result = WinGetFuncArgInFrame(winobj, 0,
+									  0, WINDOW_SEEK_HEAD, false,
+									  &isnull, NULL);
+	}
+
+	/*
+	 * At this point we can set mark down to current pos -2.
+	 */
+	markpos = curr_pos -2;
+	elog(DEBUG1, "markpos: " INT64_FORMAT, markpos);
+	if (markpos >= 0)
+		WinSetMarkPosition(winobj, markpos);
+
+	if (expression_result)
+		PG_RETURN_DATUM(result);
+
+	PG_RETURN_NULL();
+}
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match relative row position
+ * -1: current row is out of frame
+ */
+static
+int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+					 int relpos, char *vname, char *quantifier, bool *result)
+{
+	ExprContext	*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell	*lc1, *lc2;
+	ExprState	*pat;
+	Datum		eval_result;
+	int			sts;
+	bool		out_of_frame = false;
+	bool		isnull;
+	StringInfo	encoded_str = makeStringInfo();
+	char		pattern_str[128];
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+		bool	second_try_match = false;
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		for (;;)
+		{
+			if (!get_slots(winobj, winstate, relpos))
+			{
+				out_of_frame = true;
+				break;	/* current row is out of frame */
+			}
+
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: %d", vname, relpos);
+				break;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: %d", vname, relpos);
+					break;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: %d", vname, relpos);
+					appendStringInfoChar(encoded_str, vname[0]);
+
+					/* If quantifier is "+", we need to look for more matching row */
+					if (quantifier && !strcmp(quantifier, "+"))
+					{
+						/* remember that we want to try another row */
+						second_try_match = true;
+						relpos++;
+					}
+					else
+						break;
+				}
+			}
+		}
+		if (second_try_match)
+			relpos--;
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+
+		/* build regular expression */
+		snprintf(pattern_str, sizeof(pattern_str), "%c%s", vname[0], quantifier);
+
+		/*
+		 * Do regular expression matching against sequence of rows satisfying
+		 * the expression using regexp_instr().
+		 */
+		sts = DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+													PointerGetDatum(cstring_to_text(encoded_str->data)),
+													PointerGetDatum(cstring_to_text(pattern_str))));
+		elog(DEBUG1, "regexp_instr returned: %d. str: %s regexp: %s",
+			 sts, encoded_str->data, pattern_str);
+		*result = (sts > 0)? true : false;
+	}
+	return relpos;
+}
+
+/*
+ * Get current, previous and next tuple.
+ * Returns true if still within frame.
+ */
+static bool
+get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos)
+{
+	TupleTableSlot *slot;
+	bool	isnull, isout;
+	int		sts;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* for current row */
+	slot = winstate->temp_slot_1;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "current row is out of frame");
+		econtext->ecxt_scantuple = winstate->null_slot;
+		return false;
+	}
+	else
+		econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		sts = WinGetSlotInFrame(winobj, slot,
+								current_pos - 1, WINDOW_SEEK_HEAD, false,
+								&isnull, &isout);
+		if (sts < 0)
+		{
+			elog(DEBUG1, "previous row out of frame at: %d", current_pos);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		econtext->ecxt_outertuple = slot;
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos + 1, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "next row out of frame at: %d", current_pos);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+		econtext->ecxt_innertuple = slot;
+
+	return true;
+}
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..e3a9e0ffeb 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,15 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'row pattern recognition in window',
+  proname => 'rpr', prokind => 'w', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_rpr' },
+{ oid => '6123', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6124', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..bc95c5fe9b 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,13 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('*', '+' or '?'. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2562,11 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..a0facf38fe 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,16 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Sun_Jun_25_21_05_09_2023_126)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v1-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v1 4/7] Row pattern recognition patch (executor).
@ 2023-06-25 11:48 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-06-25 11:48 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 223 +++++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  | 274 ++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat      |   9 +
 src/include/nodes/execnodes.h        |  12 ++
 src/include/windowapi.h              |   9 +
 5 files changed, 517 insertions(+), 10 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..ae997dff86 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -48,6 +48,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +160,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -195,9 +204,9 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
 
 /*
  * initialize_windowaggregate
@@ -2388,6 +2397,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2498,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2692,69 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+			if (func->winfnoid != F_RPR)
+				continue;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "RPR must have 1 argument but function %d has %d args", func->winfnoid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "RPR's arg is not Var");
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2762,76 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2849,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2900,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3242,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3420,14 +3582,53 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3583,15 +3784,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3821,9 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..63b225271c 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -39,7 +42,9 @@ typedef struct
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
-
+static bool get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos);
+static int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+							int relpos, char *vname, char *quantifier, bool *result);
 
 /*
  * utility routine for *_rank functions.
@@ -713,3 +718,270 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * rpr
+ * allow to use "Row pattern recognition: WINDOW clause" (SQL:2016 R020) in
+ * the target list.
+ * Usage: SELECT rpr(colname) OVER (..)
+ * where colname is defined in PATTERN clause.
+ */
+Datum
+window_rpr(PG_FUNCTION_ARGS)
+{
+#define	MAX_PATTERNS	16	/* max variables in PATTERN clause */
+
+	WindowObject winobj = PG_WINDOW_OBJECT();
+	WindowAggState	*winstate = WinGetAggState(winobj);
+	Datum		result;
+	bool		expression_result;
+	bool		isnull;
+	int			relpos;
+	int64		curr_pos, markpos;
+	ListCell	*lc, *lc1;
+
+	curr_pos = WinGetCurrentPosition(winobj);
+	elog(DEBUG1, "rpr is called. row: " INT64_FORMAT, curr_pos);
+
+	/*
+	 * Evaluate PATTERN until one of expressions is not true or out of frame.
+	 */
+	relpos = 0;
+
+	forboth(lc, winstate->patternVariableList, lc1, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc));
+		char	*quantifier = strVal(lfirst(lc1));
+
+		elog(DEBUG1, "relpos: %d pattern vname: %s quantifier: %s", relpos, vname, quantifier);
+
+		/* evaluate row pattern against current row */
+		relpos = evaluate_pattern(winobj, winstate, relpos, vname, quantifier, &expression_result);
+
+		/*
+		 * If the expression did not match, we are done.
+		 */
+		if (!expression_result)
+			break;
+
+		/* out of frame? */
+		if (relpos < 0)
+			break;
+
+		/* count up relative row position */
+		relpos++;
+	}
+
+	elog(DEBUG1, "relpos: %d", relpos);
+
+	/*
+	 * If current row satified the pattern, return argument expression.
+	 */
+	if (expression_result)
+	{
+		result = WinGetFuncArgInFrame(winobj, 0,
+									  0, WINDOW_SEEK_HEAD, false,
+									  &isnull, NULL);
+	}
+
+	/*
+	 * At this point we can set mark down to current pos -2.
+	 */
+	markpos = curr_pos -2;
+	elog(DEBUG1, "markpos: " INT64_FORMAT, markpos);
+	if (markpos >= 0)
+		WinSetMarkPosition(winobj, markpos);
+
+	if (expression_result)
+		PG_RETURN_DATUM(result);
+
+	PG_RETURN_NULL();
+}
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match relative row position
+ * -1: current row is out of frame
+ */
+static
+int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+					 int relpos, char *vname, char *quantifier, bool *result)
+{
+	ExprContext	*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell	*lc1, *lc2;
+	ExprState	*pat;
+	Datum		eval_result;
+	int			sts;
+	bool		out_of_frame = false;
+	bool		isnull;
+	StringInfo	encoded_str = makeStringInfo();
+	char		pattern_str[128];
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+		bool	second_try_match = false;
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		for (;;)
+		{
+			if (!get_slots(winobj, winstate, relpos))
+			{
+				out_of_frame = true;
+				break;	/* current row is out of frame */
+			}
+
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: %d", vname, relpos);
+				break;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: %d", vname, relpos);
+					break;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: %d", vname, relpos);
+					appendStringInfoChar(encoded_str, vname[0]);
+
+					/* If quantifier is "+", we need to look for more matching row */
+					if (quantifier && !strcmp(quantifier, "+"))
+					{
+						/* remember that we want to try another row */
+						second_try_match = true;
+						relpos++;
+					}
+					else
+						break;
+				}
+			}
+		}
+		if (second_try_match)
+			relpos--;
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+
+		/* build regular expression */
+		snprintf(pattern_str, sizeof(pattern_str), "%c%s", vname[0], quantifier);
+
+		/*
+		 * Do regular expression matching against sequence of rows satisfying
+		 * the expression using regexp_instr().
+		 */
+		sts = DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+													PointerGetDatum(cstring_to_text(encoded_str->data)),
+													PointerGetDatum(cstring_to_text(pattern_str))));
+		elog(DEBUG1, "regexp_instr returned: %d. str: %s regexp: %s",
+			 sts, encoded_str->data, pattern_str);
+		*result = (sts > 0)? true : false;
+	}
+	return relpos;
+}
+
+/*
+ * Get current, previous and next tuple.
+ * Returns true if still within frame.
+ */
+static bool
+get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos)
+{
+	TupleTableSlot *slot;
+	bool	isnull, isout;
+	int		sts;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* for current row */
+	slot = winstate->temp_slot_1;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "current row is out of frame");
+		econtext->ecxt_scantuple = winstate->null_slot;
+		return false;
+	}
+	else
+		econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		sts = WinGetSlotInFrame(winobj, slot,
+								current_pos - 1, WINDOW_SEEK_HEAD, false,
+								&isnull, &isout);
+		if (sts < 0)
+		{
+			elog(DEBUG1, "previous row out of frame at: %d", current_pos);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		econtext->ecxt_outertuple = slot;
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos + 1, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "next row out of frame at: %d", current_pos);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+		econtext->ecxt_innertuple = slot;
+
+	return true;
+}
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..e3a9e0ffeb 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,15 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'row pattern recognition in window',
+  proname => 'rpr', prokind => 'w', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_rpr' },
+{ oid => '6123', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6124', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..bc95c5fe9b 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,13 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('*', '+' or '?'. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2562,11 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..a0facf38fe 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,16 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Sun_Jun_25_21_05_09_2023_126)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v1-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v2 4/7] Row pattern recognition patch (executor).
@ 2023-06-26 08:05 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-06-26 08:05 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 225 +++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  | 302 ++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat      |   9 +
 src/include/nodes/execnodes.h        |  13 ++
 src/include/windowapi.h              |   9 +
 5 files changed, 548 insertions(+), 10 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..bef2bc62b2 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -48,6 +48,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +160,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -195,9 +204,9 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
 
 /*
  * initialize_windowaggregate
@@ -2388,6 +2397,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2498,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2692,71 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up SKIP TO type */
+	winstate->rpSkipTo = node->rpSkipTo;
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+			if (func->winfnoid != F_RPR)
+				continue;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "RPR must have 1 argument but function %d has %d args", func->winfnoid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "RPR's arg is not Var");
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2764,76 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2851,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2902,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3244,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3420,14 +3584,53 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3583,15 +3786,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3823,9 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..74ef11ce55 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -36,10 +39,21 @@ typedef struct
 	int64		remainder;		/* (total rows) % (bucket num) */
 } ntile_context;
 
+/*
+ * rpr process information.
+ * Used for AFTER MATCH SKIP PAST LAST ROW
+ */
+typedef struct SkipContext
+{
+	int64		pos;	/* last row absolute position */
+} SkipContext;
+
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
-
+static bool get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos);
+static int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+							int relpos, char *vname, char *quantifier, bool *result);
 
 /*
  * utility routine for *_rank functions.
@@ -713,3 +727,289 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * rpr
+ * allow to use "Row pattern recognition: WINDOW clause" (SQL:2016 R020) in
+ * the target list.
+ * Usage: SELECT rpr(colname) OVER (..)
+ * where colname is defined in PATTERN clause.
+ */
+Datum
+window_rpr(PG_FUNCTION_ARGS)
+{
+#define	MAX_PATTERNS	16	/* max variables in PATTERN clause */
+
+	WindowObject winobj = PG_WINDOW_OBJECT();
+	WindowAggState	*winstate = WinGetAggState(winobj);
+	Datum		result;
+	bool		expression_result;
+	bool		isnull;
+	int			relpos;
+	int64		curr_pos, markpos;
+	ListCell	*lc, *lc1;
+	SkipContext	*context = NULL;
+
+	curr_pos = WinGetCurrentPosition(winobj);
+	elog(DEBUG1, "rpr is called. row: " INT64_FORMAT, curr_pos);
+
+	if (winstate->rpSkipTo == ST_PAST_LAST_ROW)
+	{
+		context = (SkipContext *) WinGetPartitionLocalMemory(winobj, sizeof(SkipContext));
+		if (curr_pos < context->pos)
+		{
+			elog(DEBUG1, "skip this row: curr_pos: " INT64_FORMAT "context->pos: " INT64_FORMAT,
+				 curr_pos, context->pos);
+			PG_RETURN_NULL();
+		}
+	}
+
+	/*
+	 * Evaluate PATTERN until one of expressions is not true or out of frame.
+	 */
+	relpos = 0;
+
+	forboth(lc, winstate->patternVariableList, lc1, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc));
+		char	*quantifier = strVal(lfirst(lc1));
+
+		elog(DEBUG1, "relpos: %d pattern vname: %s quantifier: %s", relpos, vname, quantifier);
+
+		/* evaluate row pattern against current row */
+		relpos = evaluate_pattern(winobj, winstate, relpos, vname, quantifier, &expression_result);
+
+		/*
+		 * If the expression did not match, we are done.
+		 */
+		if (!expression_result)
+			break;
+
+		/* out of frame? */
+		if (relpos < 0)
+			break;
+
+		/* count up relative row position */
+		relpos++;
+	}
+
+	elog(DEBUG1, "relpos: %d", relpos);
+
+	/*
+	 * If current row satified the pattern, return argument expression.
+	 */
+	if (expression_result)
+	{
+		result = WinGetFuncArgInFrame(winobj, 0,
+									  0, WINDOW_SEEK_HEAD, false,
+									  &isnull, NULL);
+	}
+
+	/*
+	 * At this point we can set mark down to current pos -2.
+	 */
+	markpos = curr_pos -2;
+	elog(DEBUG1, "markpos: " INT64_FORMAT, markpos);
+	if (markpos >= 0)
+		WinSetMarkPosition(winobj, markpos);
+
+	if (expression_result)
+	{
+		if (winstate->rpSkipTo == ST_PAST_LAST_ROW)
+		{
+			context->pos += relpos;
+			elog(DEBUG1, "context->pos: " INT64_FORMAT, context->pos);
+		}
+		PG_RETURN_DATUM(result);
+	}
+
+	PG_RETURN_NULL();
+}
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match relative row position
+ * -1: current row is out of frame
+ */
+static
+int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+					 int relpos, char *vname, char *quantifier, bool *result)
+{
+	ExprContext	*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell	*lc1, *lc2;
+	ExprState	*pat;
+	Datum		eval_result;
+	int			sts;
+	bool		out_of_frame = false;
+	bool		isnull;
+	StringInfo	encoded_str = makeStringInfo();
+	char		pattern_str[128];
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+		bool	second_try_match = false;
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		for (;;)
+		{
+			if (!get_slots(winobj, winstate, relpos))
+			{
+				out_of_frame = true;
+				break;	/* current row is out of frame */
+			}
+
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: %d", vname, relpos);
+				break;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: %d", vname, relpos);
+					break;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: %d", vname, relpos);
+					appendStringInfoChar(encoded_str, vname[0]);
+
+					/* If quantifier is "+", we need to look for more matching row */
+					if (quantifier && !strcmp(quantifier, "+"))
+					{
+						/* remember that we want to try another row */
+						second_try_match = true;
+						relpos++;
+					}
+					else
+						break;
+				}
+			}
+		}
+		if (second_try_match)
+			relpos--;
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+
+		/* build regular expression */
+		snprintf(pattern_str, sizeof(pattern_str), "%c%s", vname[0], quantifier);
+
+		/*
+		 * Do regular expression matching against sequence of rows satisfying
+		 * the expression using regexp_instr().
+		 */
+		sts = DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+													PointerGetDatum(cstring_to_text(encoded_str->data)),
+													PointerGetDatum(cstring_to_text(pattern_str))));
+		elog(DEBUG1, "regexp_instr returned: %d. str: %s regexp: %s",
+			 sts, encoded_str->data, pattern_str);
+		*result = (sts > 0)? true : false;
+	}
+	return relpos;
+}
+
+/*
+ * Get current, previous and next tuple.
+ * Returns true if still within frame.
+ */
+static bool
+get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos)
+{
+	TupleTableSlot *slot;
+	bool	isnull, isout;
+	int		sts;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* for current row */
+	slot = winstate->temp_slot_1;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "current row is out of frame");
+		econtext->ecxt_scantuple = winstate->null_slot;
+		return false;
+	}
+	else
+		econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		sts = WinGetSlotInFrame(winobj, slot,
+								current_pos - 1, WINDOW_SEEK_HEAD, false,
+								&isnull, &isout);
+		if (sts < 0)
+		{
+			elog(DEBUG1, "previous row out of frame at: %d", current_pos);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		econtext->ecxt_outertuple = slot;
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos + 1, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "next row out of frame at: %d", current_pos);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+		econtext->ecxt_innertuple = slot;
+
+	return true;
+}
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..e3a9e0ffeb 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,15 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'row pattern recognition in window',
+  proname => 'rpr', prokind => 'w', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_rpr' },
+{ oid => '6123', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6124', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..1643eaa6f1 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,14 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */	
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('+' or ''. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2563,11 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..a0facf38fe 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,16 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Mon_Jun_26_17_45_07_2023_724)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v2-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v2 4/7] Row pattern recognition patch (executor).
@ 2023-06-26 08:05 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-06-26 08:05 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 225 +++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  | 302 ++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat      |   9 +
 src/include/nodes/execnodes.h        |  13 ++
 src/include/windowapi.h              |   9 +
 5 files changed, 548 insertions(+), 10 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..bef2bc62b2 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -48,6 +48,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +160,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -195,9 +204,9 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
 
 /*
  * initialize_windowaggregate
@@ -2388,6 +2397,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2498,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2692,71 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up SKIP TO type */
+	winstate->rpSkipTo = node->rpSkipTo;
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+			if (func->winfnoid != F_RPR)
+				continue;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "RPR must have 1 argument but function %d has %d args", func->winfnoid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "RPR's arg is not Var");
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2764,76 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2851,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2902,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3244,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3420,14 +3584,53 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3583,15 +3786,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3823,9 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..74ef11ce55 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -36,10 +39,21 @@ typedef struct
 	int64		remainder;		/* (total rows) % (bucket num) */
 } ntile_context;
 
+/*
+ * rpr process information.
+ * Used for AFTER MATCH SKIP PAST LAST ROW
+ */
+typedef struct SkipContext
+{
+	int64		pos;	/* last row absolute position */
+} SkipContext;
+
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
-
+static bool get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos);
+static int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+							int relpos, char *vname, char *quantifier, bool *result);
 
 /*
  * utility routine for *_rank functions.
@@ -713,3 +727,289 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * rpr
+ * allow to use "Row pattern recognition: WINDOW clause" (SQL:2016 R020) in
+ * the target list.
+ * Usage: SELECT rpr(colname) OVER (..)
+ * where colname is defined in PATTERN clause.
+ */
+Datum
+window_rpr(PG_FUNCTION_ARGS)
+{
+#define	MAX_PATTERNS	16	/* max variables in PATTERN clause */
+
+	WindowObject winobj = PG_WINDOW_OBJECT();
+	WindowAggState	*winstate = WinGetAggState(winobj);
+	Datum		result;
+	bool		expression_result;
+	bool		isnull;
+	int			relpos;
+	int64		curr_pos, markpos;
+	ListCell	*lc, *lc1;
+	SkipContext	*context = NULL;
+
+	curr_pos = WinGetCurrentPosition(winobj);
+	elog(DEBUG1, "rpr is called. row: " INT64_FORMAT, curr_pos);
+
+	if (winstate->rpSkipTo == ST_PAST_LAST_ROW)
+	{
+		context = (SkipContext *) WinGetPartitionLocalMemory(winobj, sizeof(SkipContext));
+		if (curr_pos < context->pos)
+		{
+			elog(DEBUG1, "skip this row: curr_pos: " INT64_FORMAT "context->pos: " INT64_FORMAT,
+				 curr_pos, context->pos);
+			PG_RETURN_NULL();
+		}
+	}
+
+	/*
+	 * Evaluate PATTERN until one of expressions is not true or out of frame.
+	 */
+	relpos = 0;
+
+	forboth(lc, winstate->patternVariableList, lc1, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc));
+		char	*quantifier = strVal(lfirst(lc1));
+
+		elog(DEBUG1, "relpos: %d pattern vname: %s quantifier: %s", relpos, vname, quantifier);
+
+		/* evaluate row pattern against current row */
+		relpos = evaluate_pattern(winobj, winstate, relpos, vname, quantifier, &expression_result);
+
+		/*
+		 * If the expression did not match, we are done.
+		 */
+		if (!expression_result)
+			break;
+
+		/* out of frame? */
+		if (relpos < 0)
+			break;
+
+		/* count up relative row position */
+		relpos++;
+	}
+
+	elog(DEBUG1, "relpos: %d", relpos);
+
+	/*
+	 * If current row satified the pattern, return argument expression.
+	 */
+	if (expression_result)
+	{
+		result = WinGetFuncArgInFrame(winobj, 0,
+									  0, WINDOW_SEEK_HEAD, false,
+									  &isnull, NULL);
+	}
+
+	/*
+	 * At this point we can set mark down to current pos -2.
+	 */
+	markpos = curr_pos -2;
+	elog(DEBUG1, "markpos: " INT64_FORMAT, markpos);
+	if (markpos >= 0)
+		WinSetMarkPosition(winobj, markpos);
+
+	if (expression_result)
+	{
+		if (winstate->rpSkipTo == ST_PAST_LAST_ROW)
+		{
+			context->pos += relpos;
+			elog(DEBUG1, "context->pos: " INT64_FORMAT, context->pos);
+		}
+		PG_RETURN_DATUM(result);
+	}
+
+	PG_RETURN_NULL();
+}
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match relative row position
+ * -1: current row is out of frame
+ */
+static
+int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+					 int relpos, char *vname, char *quantifier, bool *result)
+{
+	ExprContext	*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell	*lc1, *lc2;
+	ExprState	*pat;
+	Datum		eval_result;
+	int			sts;
+	bool		out_of_frame = false;
+	bool		isnull;
+	StringInfo	encoded_str = makeStringInfo();
+	char		pattern_str[128];
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+		bool	second_try_match = false;
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		for (;;)
+		{
+			if (!get_slots(winobj, winstate, relpos))
+			{
+				out_of_frame = true;
+				break;	/* current row is out of frame */
+			}
+
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: %d", vname, relpos);
+				break;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: %d", vname, relpos);
+					break;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: %d", vname, relpos);
+					appendStringInfoChar(encoded_str, vname[0]);
+
+					/* If quantifier is "+", we need to look for more matching row */
+					if (quantifier && !strcmp(quantifier, "+"))
+					{
+						/* remember that we want to try another row */
+						second_try_match = true;
+						relpos++;
+					}
+					else
+						break;
+				}
+			}
+		}
+		if (second_try_match)
+			relpos--;
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+
+		/* build regular expression */
+		snprintf(pattern_str, sizeof(pattern_str), "%c%s", vname[0], quantifier);
+
+		/*
+		 * Do regular expression matching against sequence of rows satisfying
+		 * the expression using regexp_instr().
+		 */
+		sts = DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+													PointerGetDatum(cstring_to_text(encoded_str->data)),
+													PointerGetDatum(cstring_to_text(pattern_str))));
+		elog(DEBUG1, "regexp_instr returned: %d. str: %s regexp: %s",
+			 sts, encoded_str->data, pattern_str);
+		*result = (sts > 0)? true : false;
+	}
+	return relpos;
+}
+
+/*
+ * Get current, previous and next tuple.
+ * Returns true if still within frame.
+ */
+static bool
+get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos)
+{
+	TupleTableSlot *slot;
+	bool	isnull, isout;
+	int		sts;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* for current row */
+	slot = winstate->temp_slot_1;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "current row is out of frame");
+		econtext->ecxt_scantuple = winstate->null_slot;
+		return false;
+	}
+	else
+		econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		sts = WinGetSlotInFrame(winobj, slot,
+								current_pos - 1, WINDOW_SEEK_HEAD, false,
+								&isnull, &isout);
+		if (sts < 0)
+		{
+			elog(DEBUG1, "previous row out of frame at: %d", current_pos);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		econtext->ecxt_outertuple = slot;
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos + 1, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "next row out of frame at: %d", current_pos);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+		econtext->ecxt_innertuple = slot;
+
+	return true;
+}
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..e3a9e0ffeb 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,15 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'row pattern recognition in window',
+  proname => 'rpr', prokind => 'w', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_rpr' },
+{ oid => '6123', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6124', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..1643eaa6f1 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,14 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */	
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('+' or ''. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2563,11 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..a0facf38fe 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,16 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Mon_Jun_26_17_45_07_2023_724)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v2-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v2 4/7] Row pattern recognition patch (executor).
@ 2023-06-26 08:05 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-06-26 08:05 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 225 +++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  | 302 ++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat      |   9 +
 src/include/nodes/execnodes.h        |  13 ++
 src/include/windowapi.h              |   9 +
 5 files changed, 548 insertions(+), 10 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..bef2bc62b2 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -48,6 +48,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +160,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -195,9 +204,9 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
 
 /*
  * initialize_windowaggregate
@@ -2388,6 +2397,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2498,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2692,71 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up SKIP TO type */
+	winstate->rpSkipTo = node->rpSkipTo;
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+			if (func->winfnoid != F_RPR)
+				continue;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "RPR must have 1 argument but function %d has %d args", func->winfnoid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "RPR's arg is not Var");
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2764,76 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2851,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2902,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3244,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3420,14 +3584,53 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3583,15 +3786,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3823,9 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..74ef11ce55 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -36,10 +39,21 @@ typedef struct
 	int64		remainder;		/* (total rows) % (bucket num) */
 } ntile_context;
 
+/*
+ * rpr process information.
+ * Used for AFTER MATCH SKIP PAST LAST ROW
+ */
+typedef struct SkipContext
+{
+	int64		pos;	/* last row absolute position */
+} SkipContext;
+
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
-
+static bool get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos);
+static int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+							int relpos, char *vname, char *quantifier, bool *result);
 
 /*
  * utility routine for *_rank functions.
@@ -713,3 +727,289 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * rpr
+ * allow to use "Row pattern recognition: WINDOW clause" (SQL:2016 R020) in
+ * the target list.
+ * Usage: SELECT rpr(colname) OVER (..)
+ * where colname is defined in PATTERN clause.
+ */
+Datum
+window_rpr(PG_FUNCTION_ARGS)
+{
+#define	MAX_PATTERNS	16	/* max variables in PATTERN clause */
+
+	WindowObject winobj = PG_WINDOW_OBJECT();
+	WindowAggState	*winstate = WinGetAggState(winobj);
+	Datum		result;
+	bool		expression_result;
+	bool		isnull;
+	int			relpos;
+	int64		curr_pos, markpos;
+	ListCell	*lc, *lc1;
+	SkipContext	*context = NULL;
+
+	curr_pos = WinGetCurrentPosition(winobj);
+	elog(DEBUG1, "rpr is called. row: " INT64_FORMAT, curr_pos);
+
+	if (winstate->rpSkipTo == ST_PAST_LAST_ROW)
+	{
+		context = (SkipContext *) WinGetPartitionLocalMemory(winobj, sizeof(SkipContext));
+		if (curr_pos < context->pos)
+		{
+			elog(DEBUG1, "skip this row: curr_pos: " INT64_FORMAT "context->pos: " INT64_FORMAT,
+				 curr_pos, context->pos);
+			PG_RETURN_NULL();
+		}
+	}
+
+	/*
+	 * Evaluate PATTERN until one of expressions is not true or out of frame.
+	 */
+	relpos = 0;
+
+	forboth(lc, winstate->patternVariableList, lc1, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc));
+		char	*quantifier = strVal(lfirst(lc1));
+
+		elog(DEBUG1, "relpos: %d pattern vname: %s quantifier: %s", relpos, vname, quantifier);
+
+		/* evaluate row pattern against current row */
+		relpos = evaluate_pattern(winobj, winstate, relpos, vname, quantifier, &expression_result);
+
+		/*
+		 * If the expression did not match, we are done.
+		 */
+		if (!expression_result)
+			break;
+
+		/* out of frame? */
+		if (relpos < 0)
+			break;
+
+		/* count up relative row position */
+		relpos++;
+	}
+
+	elog(DEBUG1, "relpos: %d", relpos);
+
+	/*
+	 * If current row satified the pattern, return argument expression.
+	 */
+	if (expression_result)
+	{
+		result = WinGetFuncArgInFrame(winobj, 0,
+									  0, WINDOW_SEEK_HEAD, false,
+									  &isnull, NULL);
+	}
+
+	/*
+	 * At this point we can set mark down to current pos -2.
+	 */
+	markpos = curr_pos -2;
+	elog(DEBUG1, "markpos: " INT64_FORMAT, markpos);
+	if (markpos >= 0)
+		WinSetMarkPosition(winobj, markpos);
+
+	if (expression_result)
+	{
+		if (winstate->rpSkipTo == ST_PAST_LAST_ROW)
+		{
+			context->pos += relpos;
+			elog(DEBUG1, "context->pos: " INT64_FORMAT, context->pos);
+		}
+		PG_RETURN_DATUM(result);
+	}
+
+	PG_RETURN_NULL();
+}
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match relative row position
+ * -1: current row is out of frame
+ */
+static
+int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+					 int relpos, char *vname, char *quantifier, bool *result)
+{
+	ExprContext	*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell	*lc1, *lc2;
+	ExprState	*pat;
+	Datum		eval_result;
+	int			sts;
+	bool		out_of_frame = false;
+	bool		isnull;
+	StringInfo	encoded_str = makeStringInfo();
+	char		pattern_str[128];
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+		bool	second_try_match = false;
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		for (;;)
+		{
+			if (!get_slots(winobj, winstate, relpos))
+			{
+				out_of_frame = true;
+				break;	/* current row is out of frame */
+			}
+
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: %d", vname, relpos);
+				break;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: %d", vname, relpos);
+					break;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: %d", vname, relpos);
+					appendStringInfoChar(encoded_str, vname[0]);
+
+					/* If quantifier is "+", we need to look for more matching row */
+					if (quantifier && !strcmp(quantifier, "+"))
+					{
+						/* remember that we want to try another row */
+						second_try_match = true;
+						relpos++;
+					}
+					else
+						break;
+				}
+			}
+		}
+		if (second_try_match)
+			relpos--;
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+
+		/* build regular expression */
+		snprintf(pattern_str, sizeof(pattern_str), "%c%s", vname[0], quantifier);
+
+		/*
+		 * Do regular expression matching against sequence of rows satisfying
+		 * the expression using regexp_instr().
+		 */
+		sts = DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+													PointerGetDatum(cstring_to_text(encoded_str->data)),
+													PointerGetDatum(cstring_to_text(pattern_str))));
+		elog(DEBUG1, "regexp_instr returned: %d. str: %s regexp: %s",
+			 sts, encoded_str->data, pattern_str);
+		*result = (sts > 0)? true : false;
+	}
+	return relpos;
+}
+
+/*
+ * Get current, previous and next tuple.
+ * Returns true if still within frame.
+ */
+static bool
+get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos)
+{
+	TupleTableSlot *slot;
+	bool	isnull, isout;
+	int		sts;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* for current row */
+	slot = winstate->temp_slot_1;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "current row is out of frame");
+		econtext->ecxt_scantuple = winstate->null_slot;
+		return false;
+	}
+	else
+		econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		sts = WinGetSlotInFrame(winobj, slot,
+								current_pos - 1, WINDOW_SEEK_HEAD, false,
+								&isnull, &isout);
+		if (sts < 0)
+		{
+			elog(DEBUG1, "previous row out of frame at: %d", current_pos);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		econtext->ecxt_outertuple = slot;
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos + 1, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "next row out of frame at: %d", current_pos);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+		econtext->ecxt_innertuple = slot;
+
+	return true;
+}
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..e3a9e0ffeb 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,15 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'row pattern recognition in window',
+  proname => 'rpr', prokind => 'w', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_rpr' },
+{ oid => '6123', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6124', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..1643eaa6f1 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,14 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */	
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('+' or ''. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2563,11 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..a0facf38fe 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,16 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Mon_Jun_26_17_45_07_2023_724)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v2-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v2 4/7] Row pattern recognition patch (executor).
@ 2023-06-26 08:05 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-06-26 08:05 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 225 +++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  | 302 ++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat      |   9 +
 src/include/nodes/execnodes.h        |  13 ++
 src/include/windowapi.h              |   9 +
 5 files changed, 548 insertions(+), 10 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..bef2bc62b2 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -48,6 +48,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +160,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -195,9 +204,9 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
 
 /*
  * initialize_windowaggregate
@@ -2388,6 +2397,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2498,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2692,71 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up SKIP TO type */
+	winstate->rpSkipTo = node->rpSkipTo;
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+			if (func->winfnoid != F_RPR)
+				continue;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "RPR must have 1 argument but function %d has %d args", func->winfnoid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "RPR's arg is not Var");
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2764,76 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2851,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2902,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3244,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3420,14 +3584,53 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3583,15 +3786,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3823,9 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..74ef11ce55 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -36,10 +39,21 @@ typedef struct
 	int64		remainder;		/* (total rows) % (bucket num) */
 } ntile_context;
 
+/*
+ * rpr process information.
+ * Used for AFTER MATCH SKIP PAST LAST ROW
+ */
+typedef struct SkipContext
+{
+	int64		pos;	/* last row absolute position */
+} SkipContext;
+
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
-
+static bool get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos);
+static int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+							int relpos, char *vname, char *quantifier, bool *result);
 
 /*
  * utility routine for *_rank functions.
@@ -713,3 +727,289 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * rpr
+ * allow to use "Row pattern recognition: WINDOW clause" (SQL:2016 R020) in
+ * the target list.
+ * Usage: SELECT rpr(colname) OVER (..)
+ * where colname is defined in PATTERN clause.
+ */
+Datum
+window_rpr(PG_FUNCTION_ARGS)
+{
+#define	MAX_PATTERNS	16	/* max variables in PATTERN clause */
+
+	WindowObject winobj = PG_WINDOW_OBJECT();
+	WindowAggState	*winstate = WinGetAggState(winobj);
+	Datum		result;
+	bool		expression_result;
+	bool		isnull;
+	int			relpos;
+	int64		curr_pos, markpos;
+	ListCell	*lc, *lc1;
+	SkipContext	*context = NULL;
+
+	curr_pos = WinGetCurrentPosition(winobj);
+	elog(DEBUG1, "rpr is called. row: " INT64_FORMAT, curr_pos);
+
+	if (winstate->rpSkipTo == ST_PAST_LAST_ROW)
+	{
+		context = (SkipContext *) WinGetPartitionLocalMemory(winobj, sizeof(SkipContext));
+		if (curr_pos < context->pos)
+		{
+			elog(DEBUG1, "skip this row: curr_pos: " INT64_FORMAT "context->pos: " INT64_FORMAT,
+				 curr_pos, context->pos);
+			PG_RETURN_NULL();
+		}
+	}
+
+	/*
+	 * Evaluate PATTERN until one of expressions is not true or out of frame.
+	 */
+	relpos = 0;
+
+	forboth(lc, winstate->patternVariableList, lc1, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc));
+		char	*quantifier = strVal(lfirst(lc1));
+
+		elog(DEBUG1, "relpos: %d pattern vname: %s quantifier: %s", relpos, vname, quantifier);
+
+		/* evaluate row pattern against current row */
+		relpos = evaluate_pattern(winobj, winstate, relpos, vname, quantifier, &expression_result);
+
+		/*
+		 * If the expression did not match, we are done.
+		 */
+		if (!expression_result)
+			break;
+
+		/* out of frame? */
+		if (relpos < 0)
+			break;
+
+		/* count up relative row position */
+		relpos++;
+	}
+
+	elog(DEBUG1, "relpos: %d", relpos);
+
+	/*
+	 * If current row satified the pattern, return argument expression.
+	 */
+	if (expression_result)
+	{
+		result = WinGetFuncArgInFrame(winobj, 0,
+									  0, WINDOW_SEEK_HEAD, false,
+									  &isnull, NULL);
+	}
+
+	/*
+	 * At this point we can set mark down to current pos -2.
+	 */
+	markpos = curr_pos -2;
+	elog(DEBUG1, "markpos: " INT64_FORMAT, markpos);
+	if (markpos >= 0)
+		WinSetMarkPosition(winobj, markpos);
+
+	if (expression_result)
+	{
+		if (winstate->rpSkipTo == ST_PAST_LAST_ROW)
+		{
+			context->pos += relpos;
+			elog(DEBUG1, "context->pos: " INT64_FORMAT, context->pos);
+		}
+		PG_RETURN_DATUM(result);
+	}
+
+	PG_RETURN_NULL();
+}
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match relative row position
+ * -1: current row is out of frame
+ */
+static
+int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+					 int relpos, char *vname, char *quantifier, bool *result)
+{
+	ExprContext	*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell	*lc1, *lc2;
+	ExprState	*pat;
+	Datum		eval_result;
+	int			sts;
+	bool		out_of_frame = false;
+	bool		isnull;
+	StringInfo	encoded_str = makeStringInfo();
+	char		pattern_str[128];
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+		bool	second_try_match = false;
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		for (;;)
+		{
+			if (!get_slots(winobj, winstate, relpos))
+			{
+				out_of_frame = true;
+				break;	/* current row is out of frame */
+			}
+
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: %d", vname, relpos);
+				break;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: %d", vname, relpos);
+					break;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: %d", vname, relpos);
+					appendStringInfoChar(encoded_str, vname[0]);
+
+					/* If quantifier is "+", we need to look for more matching row */
+					if (quantifier && !strcmp(quantifier, "+"))
+					{
+						/* remember that we want to try another row */
+						second_try_match = true;
+						relpos++;
+					}
+					else
+						break;
+				}
+			}
+		}
+		if (second_try_match)
+			relpos--;
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+
+		/* build regular expression */
+		snprintf(pattern_str, sizeof(pattern_str), "%c%s", vname[0], quantifier);
+
+		/*
+		 * Do regular expression matching against sequence of rows satisfying
+		 * the expression using regexp_instr().
+		 */
+		sts = DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+													PointerGetDatum(cstring_to_text(encoded_str->data)),
+													PointerGetDatum(cstring_to_text(pattern_str))));
+		elog(DEBUG1, "regexp_instr returned: %d. str: %s regexp: %s",
+			 sts, encoded_str->data, pattern_str);
+		*result = (sts > 0)? true : false;
+	}
+	return relpos;
+}
+
+/*
+ * Get current, previous and next tuple.
+ * Returns true if still within frame.
+ */
+static bool
+get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos)
+{
+	TupleTableSlot *slot;
+	bool	isnull, isout;
+	int		sts;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* for current row */
+	slot = winstate->temp_slot_1;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "current row is out of frame");
+		econtext->ecxt_scantuple = winstate->null_slot;
+		return false;
+	}
+	else
+		econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		sts = WinGetSlotInFrame(winobj, slot,
+								current_pos - 1, WINDOW_SEEK_HEAD, false,
+								&isnull, &isout);
+		if (sts < 0)
+		{
+			elog(DEBUG1, "previous row out of frame at: %d", current_pos);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		econtext->ecxt_outertuple = slot;
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos + 1, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "next row out of frame at: %d", current_pos);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+		econtext->ecxt_innertuple = slot;
+
+	return true;
+}
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..e3a9e0ffeb 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,15 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'row pattern recognition in window',
+  proname => 'rpr', prokind => 'w', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_rpr' },
+{ oid => '6123', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6124', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..1643eaa6f1 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,14 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */	
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('+' or ''. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2563,11 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..a0facf38fe 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,16 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Mon_Jun_26_17_45_07_2023_724)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v2-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v2 4/7] Row pattern recognition patch (executor).
@ 2023-06-26 08:05 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-06-26 08:05 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 225 +++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  | 302 ++++++++++++++++++++++++++-
 src/include/catalog/pg_proc.dat      |   9 +
 src/include/nodes/execnodes.h        |  13 ++
 src/include/windowapi.h              |   9 +
 5 files changed, 548 insertions(+), 10 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..bef2bc62b2 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -48,6 +48,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +160,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -195,9 +204,9 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
 
 /*
  * initialize_windowaggregate
@@ -2388,6 +2397,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2498,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2692,71 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up SKIP TO type */
+	winstate->rpSkipTo = node->rpSkipTo;
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+			if (func->winfnoid != F_RPR)
+				continue;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "RPR must have 1 argument but function %d has %d args", func->winfnoid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "RPR's arg is not Var");
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2764,76 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2851,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2902,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3244,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3420,14 +3584,53 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3583,15 +3786,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3823,9 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..74ef11ce55 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -36,10 +39,21 @@ typedef struct
 	int64		remainder;		/* (total rows) % (bucket num) */
 } ntile_context;
 
+/*
+ * rpr process information.
+ * Used for AFTER MATCH SKIP PAST LAST ROW
+ */
+typedef struct SkipContext
+{
+	int64		pos;	/* last row absolute position */
+} SkipContext;
+
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
-
+static bool get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos);
+static int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+							int relpos, char *vname, char *quantifier, bool *result);
 
 /*
  * utility routine for *_rank functions.
@@ -713,3 +727,289 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * rpr
+ * allow to use "Row pattern recognition: WINDOW clause" (SQL:2016 R020) in
+ * the target list.
+ * Usage: SELECT rpr(colname) OVER (..)
+ * where colname is defined in PATTERN clause.
+ */
+Datum
+window_rpr(PG_FUNCTION_ARGS)
+{
+#define	MAX_PATTERNS	16	/* max variables in PATTERN clause */
+
+	WindowObject winobj = PG_WINDOW_OBJECT();
+	WindowAggState	*winstate = WinGetAggState(winobj);
+	Datum		result;
+	bool		expression_result;
+	bool		isnull;
+	int			relpos;
+	int64		curr_pos, markpos;
+	ListCell	*lc, *lc1;
+	SkipContext	*context = NULL;
+
+	curr_pos = WinGetCurrentPosition(winobj);
+	elog(DEBUG1, "rpr is called. row: " INT64_FORMAT, curr_pos);
+
+	if (winstate->rpSkipTo == ST_PAST_LAST_ROW)
+	{
+		context = (SkipContext *) WinGetPartitionLocalMemory(winobj, sizeof(SkipContext));
+		if (curr_pos < context->pos)
+		{
+			elog(DEBUG1, "skip this row: curr_pos: " INT64_FORMAT "context->pos: " INT64_FORMAT,
+				 curr_pos, context->pos);
+			PG_RETURN_NULL();
+		}
+	}
+
+	/*
+	 * Evaluate PATTERN until one of expressions is not true or out of frame.
+	 */
+	relpos = 0;
+
+	forboth(lc, winstate->patternVariableList, lc1, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc));
+		char	*quantifier = strVal(lfirst(lc1));
+
+		elog(DEBUG1, "relpos: %d pattern vname: %s quantifier: %s", relpos, vname, quantifier);
+
+		/* evaluate row pattern against current row */
+		relpos = evaluate_pattern(winobj, winstate, relpos, vname, quantifier, &expression_result);
+
+		/*
+		 * If the expression did not match, we are done.
+		 */
+		if (!expression_result)
+			break;
+
+		/* out of frame? */
+		if (relpos < 0)
+			break;
+
+		/* count up relative row position */
+		relpos++;
+	}
+
+	elog(DEBUG1, "relpos: %d", relpos);
+
+	/*
+	 * If current row satified the pattern, return argument expression.
+	 */
+	if (expression_result)
+	{
+		result = WinGetFuncArgInFrame(winobj, 0,
+									  0, WINDOW_SEEK_HEAD, false,
+									  &isnull, NULL);
+	}
+
+	/*
+	 * At this point we can set mark down to current pos -2.
+	 */
+	markpos = curr_pos -2;
+	elog(DEBUG1, "markpos: " INT64_FORMAT, markpos);
+	if (markpos >= 0)
+		WinSetMarkPosition(winobj, markpos);
+
+	if (expression_result)
+	{
+		if (winstate->rpSkipTo == ST_PAST_LAST_ROW)
+		{
+			context->pos += relpos;
+			elog(DEBUG1, "context->pos: " INT64_FORMAT, context->pos);
+		}
+		PG_RETURN_DATUM(result);
+	}
+
+	PG_RETURN_NULL();
+}
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match relative row position
+ * -1: current row is out of frame
+ */
+static
+int evaluate_pattern(WindowObject winobj, WindowAggState *winstate,
+					 int relpos, char *vname, char *quantifier, bool *result)
+{
+	ExprContext	*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell	*lc1, *lc2;
+	ExprState	*pat;
+	Datum		eval_result;
+	int			sts;
+	bool		out_of_frame = false;
+	bool		isnull;
+	StringInfo	encoded_str = makeStringInfo();
+	char		pattern_str[128];
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+		bool	second_try_match = false;
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		for (;;)
+		{
+			if (!get_slots(winobj, winstate, relpos))
+			{
+				out_of_frame = true;
+				break;	/* current row is out of frame */
+			}
+
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: %d", vname, relpos);
+				break;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: %d", vname, relpos);
+					break;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: %d", vname, relpos);
+					appendStringInfoChar(encoded_str, vname[0]);
+
+					/* If quantifier is "+", we need to look for more matching row */
+					if (quantifier && !strcmp(quantifier, "+"))
+					{
+						/* remember that we want to try another row */
+						second_try_match = true;
+						relpos++;
+					}
+					else
+						break;
+				}
+			}
+		}
+		if (second_try_match)
+			relpos--;
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+
+		/* build regular expression */
+		snprintf(pattern_str, sizeof(pattern_str), "%c%s", vname[0], quantifier);
+
+		/*
+		 * Do regular expression matching against sequence of rows satisfying
+		 * the expression using regexp_instr().
+		 */
+		sts = DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+													PointerGetDatum(cstring_to_text(encoded_str->data)),
+													PointerGetDatum(cstring_to_text(pattern_str))));
+		elog(DEBUG1, "regexp_instr returned: %d. str: %s regexp: %s",
+			 sts, encoded_str->data, pattern_str);
+		*result = (sts > 0)? true : false;
+	}
+	return relpos;
+}
+
+/*
+ * Get current, previous and next tuple.
+ * Returns true if still within frame.
+ */
+static bool
+get_slots(WindowObject winobj, WindowAggState *winstate, int current_pos)
+{
+	TupleTableSlot *slot;
+	bool	isnull, isout;
+	int		sts;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* for current row */
+	slot = winstate->temp_slot_1;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "current row is out of frame");
+		econtext->ecxt_scantuple = winstate->null_slot;
+		return false;
+	}
+	else
+		econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		sts = WinGetSlotInFrame(winobj, slot,
+								current_pos - 1, WINDOW_SEEK_HEAD, false,
+								&isnull, &isout);
+		if (sts < 0)
+		{
+			elog(DEBUG1, "previous row out of frame at: %d", current_pos);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		econtext->ecxt_outertuple = slot;
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	sts = WinGetSlotInFrame(winobj, slot,
+							current_pos + 1, WINDOW_SEEK_HEAD, false,
+							&isnull, &isout);
+	if (sts < 0)
+	{
+		elog(DEBUG1, "next row out of frame at: %d", current_pos);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+		econtext->ecxt_innertuple = slot;
+
+	return true;
+}
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..e3a9e0ffeb 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,15 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'row pattern recognition in window',
+  proname => 'rpr', prokind => 'w', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_rpr' },
+{ oid => '6123', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6124', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..1643eaa6f1 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,14 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */	
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('+' or ''. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2563,11 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..a0facf38fe 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,16 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Mon_Jun_26_17_45_07_2023_724)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v2-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v3 4/7] Row pattern recognition patch (executor).
@ 2023-07-26 10:49 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-07-26 10:49 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 701 ++++++++++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  |  38 +-
 src/include/catalog/pg_proc.dat      |   6 +
 src/include/nodes/execnodes.h        |  18 +
 src/include/windowapi.h              |   8 +
 5 files changed, 758 insertions(+), 13 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..0586bf57d6 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -36,6 +36,7 @@
 #include "access/htup_details.h"
 #include "catalog/objectaccess.h"
 #include "catalog/pg_aggregate.h"
+#include "catalog/pg_collation_d.h"
 #include "catalog/pg_proc.h"
 #include "executor/executor.h"
 #include "executor/nodeWindowAgg.h"
@@ -48,6 +49,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +161,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -182,8 +192,9 @@ static void begin_partition(WindowAggState *winstate);
 static void spool_tuples(WindowAggState *winstate, int64 pos);
 static void release_partition(WindowAggState *winstate);
 
-static int	row_is_in_frame(WindowAggState *winstate, int64 pos,
+static int  row_is_in_frame(WindowAggState *winstate, int64 pos,
 							TupleTableSlot *slot);
+
 static void update_frameheadpos(WindowAggState *winstate);
 static void update_frametailpos(WindowAggState *winstate);
 static void update_grouptailpos(WindowAggState *winstate);
@@ -195,9 +206,19 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
+static int row_is_in_reduced_frame(WindowObject winobj, int64 pos);
+
+static int64 evaluate_pattern(WindowObject winobj, int64 current_pos, 
+							  char *vname, StringInfo encoded_str, bool *result);
+
+static bool get_slots(WindowObject winobj, int64 current_pos);
+
+static int search_str_set(char *pattern, StringInfo *str_set, int set_size);
+static void search_str_set_recurse(char *pattern, StringInfo *str_set, int set_size, int set_index,
+								   char *encoded_str, int *resultlen);
 
 /*
  * initialize_windowaggregate
@@ -673,6 +694,9 @@ eval_windowaggregates(WindowAggState *winstate)
 	WindowObject agg_winobj;
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot;
+	bool		reduced_frame_set;
+	bool		check_reduced_frame;
+	int			num_rows_in_reduced_frame;
 
 	numaggs = winstate->numaggs;
 	if (numaggs == 0)
@@ -790,6 +814,7 @@ eval_windowaggregates(WindowAggState *winstate)
 			(winstate->frameOptions & FRAMEOPTION_EXCLUSION) ||
 			winstate->aggregatedupto <= winstate->frameheadpos)
 		{
+			elog(DEBUG1, "peraggstate->restart  is set");
 			peraggstate->restart = true;
 			numaggs_restart++;
 		}
@@ -861,8 +886,10 @@ eval_windowaggregates(WindowAggState *winstate)
 	 * If we created a mark pointer for aggregates, keep it pushed up to frame
 	 * head, so that tuplestore can discard unnecessary rows.
 	 */
+#ifdef NOT_USED
 	if (agg_winobj->markptr >= 0)
 		WinSetMarkPosition(agg_winobj, winstate->frameheadpos);
+#endif
 
 	/*
 	 * Now restart the aggregates that require it.
@@ -919,6 +946,10 @@ eval_windowaggregates(WindowAggState *winstate)
 		ExecClearTuple(agg_row_slot);
 	}
 
+	reduced_frame_set = false;
+	check_reduced_frame = false;
+	num_rows_in_reduced_frame = 0;
+
 	/*
 	 * Advance until we reach a row not in frame (or end of partition).
 	 *
@@ -930,12 +961,18 @@ eval_windowaggregates(WindowAggState *winstate)
 	{
 		int			ret;
 
+		elog(DEBUG1, "===== loop in frame starts: " INT64_FORMAT, winstate->aggregatedupto);
+
 		/* Fetch next row if we didn't already */
 		if (TupIsNull(agg_row_slot))
 		{
 			if (!window_gettupleslot(agg_winobj, winstate->aggregatedupto,
 									 agg_row_slot))
+			{
+				if (check_reduced_frame)
+					winstate->aggregatedupto--;
 				break;			/* must be end of partition */
+			}
 		}
 
 		/*
@@ -944,10 +981,47 @@ eval_windowaggregates(WindowAggState *winstate)
 		 */
 		ret = row_is_in_frame(winstate, winstate->aggregatedupto, agg_row_slot);
 		if (ret < 0)
+		{
+			if (winstate->patternVariableList != NIL && check_reduced_frame)
+				winstate->aggregatedupto--;
 			break;
+		}
 		if (ret == 0)
 			goto next_tuple;
 
+		if (winstate->patternVariableList != NIL)
+		{
+			if (!reduced_frame_set)
+			{
+				num_rows_in_reduced_frame = row_is_in_reduced_frame(winstate->agg_winobj, winstate->aggregatedupto);
+				reduced_frame_set = true;
+				elog(DEBUG1, "set num_rows_in_reduced_frame: %d pos: " INT64_FORMAT,
+					 num_rows_in_reduced_frame, winstate->aggregatedupto);
+
+				if (num_rows_in_reduced_frame <= 0)
+					break;
+
+				else if (num_rows_in_reduced_frame > 0)
+					check_reduced_frame = true;
+			}
+
+			if (check_reduced_frame)
+			{
+				elog(DEBUG1, "decrease num_rows_in_reduced_frame: %d pos: " INT64_FORMAT,
+					 num_rows_in_reduced_frame, winstate->aggregatedupto);
+				num_rows_in_reduced_frame--;
+				if (num_rows_in_reduced_frame < 0)
+				{
+					/*
+					 * No more rows remain in the reduced frame. Finish
+					 * accumulating row into the aggregates.
+					 */
+					winstate->aggregatedupto--;
+					break;
+				}
+			}
+		}
+
 		/* Set tuple context for evaluation of aggregate arguments */
 		winstate->tmpcontext->ecxt_outertuple = agg_row_slot;
 
@@ -976,6 +1050,8 @@ next_tuple:
 		ExecClearTuple(agg_row_slot);
 	}
 
+	elog(DEBUG1, "===== break loop in frame starts: " INT64_FORMAT, winstate->aggregatedupto);
+
 	/* The frame's end is not supposed to move backwards, ever */
 	Assert(aggregatedupto_nonrestarted <= winstate->aggregatedupto);
 
@@ -2053,6 +2129,8 @@ ExecWindowAgg(PlanState *pstate)
 
 	CHECK_FOR_INTERRUPTS();
 
+	elog(DEBUG1, "ExecWindowAgg called. pos: " INT64_FORMAT , winstate->currentpos);
+
 	if (winstate->status == WINDOWAGG_DONE)
 		return NULL;
 
@@ -2388,6 +2466,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2567,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2761,69 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up SKIP TO type */
+	winstate->rpSkipTo = node->rpSkipTo;
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (nargs != 1)
+				continue;
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				continue;
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2831,77 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			elog(DEBUG1, "walker: varattno: %d varattnosyn: %d",attno, attnosyn);
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2919,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2970,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3312,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3100,7 +3332,7 @@ window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 		return false;
 
 	if (pos < winobj->markpos)
-		elog(ERROR, "cannot fetch row before WindowObject's mark position");
+		elog(ERROR, "cannot fetch row: " INT64_FORMAT " before WindowObject's mark position: " INT64_FORMAT,  pos, winobj->markpos );
 
 	oldcontext = MemoryContextSwitchTo(winstate->ss.ps.ps_ExprContext->ecxt_per_query_memory);
 
@@ -3420,14 +3652,54 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+	int			num_reduced_frame;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3494,6 +3766,12 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 						 winstate->frameOptions);
 					break;
 			}
+			num_reduced_frame = row_is_in_reduced_frame(winobj, winstate->frameheadpos);
+			if (num_reduced_frame < 0)
+				goto out_of_frame;
+			else if (num_reduced_frame > 0)
+				if (relpos >= num_reduced_frame)
+					goto out_of_frame;
 			break;
 		case WINDOW_SEEK_TAIL:
 			/* rejecting relpos > 0 is easy and simplifies code below */
@@ -3565,6 +3843,12 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 					mark_pos = 0;	/* keep compiler quiet */
 					break;
 			}
+
+			num_reduced_frame = row_is_in_reduced_frame(winobj, winstate->frameheadpos + relpos);
+			if (num_reduced_frame < 0)
+				goto out_of_frame;
+			else if (num_reduced_frame > 0)
+				abs_pos = winstate->frameheadpos + relpos + num_reduced_frame - 1;
 			break;
 		default:
 			elog(ERROR, "unrecognized window seek type: %d", seektype);
@@ -3583,15 +3867,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3904,400 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
+
+/*
+ * row_is_in_reduced_frame
+ * Determine whether a row is in the current row's reduced window frame according
+ * to row pattern matching
+ *
+ * The row must has been already determined that it is in a full window frame
+ * and fetched it into slot.
+ *
+ * Returns:
+ * = 0, RPR is not defined.
+ * >0, if the row is the first in the reduced frame. Return the number of rows in the reduced frame.
+ * -1, if the row is unmatched row
+ * -2, if the row is in the reduced frame but needed to be skipped because of
+ * AFTER MATCH SKIP PAST LAST ROW
+ */
+static
+int row_is_in_reduced_frame(WindowObject winobj, int64 pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	ListCell	*lc1, *lc2;
+	bool		expression_result;
+	int			num_matched_rows;
+	int64		original_pos;
+	bool		anymatch;
+	StringInfo	encoded_str;
+	StringInfo	pattern_str = makeStringInfo();
+
+	/*
+	 * Array of pattern variables evaluted to true.
+	 * Each character corresponds to pattern variable.
+	 * Example:
+	 * str_set[0] = "AB";
+	 * str_set[1] = "AC";
+	 * In this case at row 0 A and B are true, and A and C are true in row 1.
+	 */
+	#define ENCODED_STR_ARRAY_ALLOC_SIZE	128
+	StringInfo	*str_set = NULL;
+	int		str_set_index;
+	int		str_set_size;
+
+	if (winstate->patternVariableList == NIL)
+	{
+		/*
+		 * RPR is not defined. Assume that we are always in the the reduced
+		 * window frame.
+		 */
+		return 0;
+	}
+
+	/* save original pos */
+	original_pos = pos;
+
+	/*
+	 * Check whether the row speicied by pos is in the reduced frame. The
+	 * second and subsequent rows need to be recognized as "unmatched" rows if
+	 * AFTER MATCH SKIP PAST LAST ROW is defined.
+	 */
+	if (winstate->rpSkipTo == ST_PAST_LAST_ROW &&
+		pos > winstate->headpos_in_reduced_frame &&
+		pos < (winstate->headpos_in_reduced_frame + winstate->num_rows_in_reduced_frame))
+		return -2;
+		
+	/*
+	 * Loop over until none of pattern matches or encounters end of frame.
+	 */
+	for (;;)
+	{
+		int64	result_pos = -1;
+
+		/*
+		 * Loop over each PATTERN variable.
+		 */
+		anymatch = false;
+		encoded_str = makeStringInfo();
+
+		forboth(lc1, winstate->patternVariableList, lc2, winstate->patternRegexpList)
+		{
+			char	*vname = strVal(lfirst(lc1));
+			char	*quantifier = strVal(lfirst(lc2));
+
+			elog(DEBUG1, "pos: " INT64_FORMAT " pattern vname: %s quantifier: %s", pos, vname, quantifier);
+
+			expression_result = false;
+
+			/* evaluate row pattern against current row */
+			result_pos = evaluate_pattern(winobj, pos, vname, encoded_str, &expression_result);
+			if (expression_result)
+			{
+				elog(DEBUG1, "expression result is true");
+				anymatch = true;
+			}
+
+			/*
+			 * If out of frame, we are done.
+			 */
+			 if (result_pos < 0)
+				 break;
+		}
+
+		if (!anymatch)
+		{
+			/* none of patterns matched. */
+			break;
+		}
+
+		/* build encoded string array */
+		if (str_set == NULL)
+		{
+			str_set_index = 0;
+			str_set_size = ENCODED_STR_ARRAY_ALLOC_SIZE * sizeof(StringInfo);
+			str_set = palloc(str_set_size);
+		}
+
+		str_set[str_set_index++] = encoded_str;
+
+		elog(DEBUG1, "pos: " INT64_FORMAT " str_set_index: %d encoded_str: %s", pos, str_set_index, encoded_str->data);
+
+		if (str_set_index >= str_set_size)
+		{
+			str_set_size *= 2;
+			str_set = repalloc(str_set, str_set_size);
+		}
+
+		/* move to next row */
+		pos++;
+
+		if (result_pos < 0)
+		{
+			/* out of frame */
+			break;
+		}
+	}
+
+	if (str_set == NULL)
+	{
+		/* no matches found in the first row */
+		return -1;
+	}
+
+	elog(DEBUG1, "pos: " INT64_FORMAT " encoded_str: %s", pos, encoded_str->data);
+
+	/* build regular expression */
+	pattern_str = makeStringInfo();
+	appendStringInfoChar(pattern_str, '^');
+	forboth(lc1, winstate->patternVariableList, lc2, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc1));
+		char	*quantifier = strVal(lfirst(lc2));
+
+		appendStringInfoChar(pattern_str, vname[0]);
+		if (quantifier[0])
+			appendStringInfoChar(pattern_str, quantifier[0]);
+		elog(DEBUG1, "vname: %s quantifier: %s", vname, quantifier);
+	}
+
+	elog(DEBUG1, "pos: " INT64_FORMAT " pattern: %s", pos, pattern_str->data);
+
+	/* look for matching pattern variable sequence */
+	num_matched_rows = search_str_set(pattern_str->data, str_set, str_set_index);
+	if (num_matched_rows <= 0)
+		return -1;
+
+	/*
+	 * We are at the first row in the reduced frame.  Save the number of
+	 * matched rows as the number of rows in the reduced frame.
+	 */
+	winstate->headpos_in_reduced_frame = original_pos;
+	winstate->num_rows_in_reduced_frame = num_matched_rows;
+
+	return num_matched_rows;
+}
+
+/*
+ * search set of encode_str.
+ * set_size: size of set_str array.
+ */
+static
+int search_str_set(char *pattern, StringInfo *str_set, int set_size)
+{
+	char		*encoded_str = palloc0(set_size+1);
+	int			resultlen = 0;
+
+	search_str_set_recurse(pattern, str_set, set_size, 0, encoded_str, &resultlen);
+	elog(DEBUG1, "search_str_set returns %d", resultlen);
+	return resultlen;
+}
+
+static
+void search_str_set_recurse(char *pattern, StringInfo *str_set, int set_size, int set_index, char *encoded_str, int *resultlen)
+{
+	char	*p;
+
+	if (set_index >= set_size)
+	{
+		Datum	d;
+		text	*res;
+		char	*substr;
+
+		/*
+		 * We first perform pattern matching using regexp_instr, then call
+		 * textregexsubstr to get matched substring to know how log the
+		 * matched string is. That is the number of rows in the reduced window
+		 * frame.  The reason why we can't call textregexsubstr is, it error
+		 * out if pattern is not match.
+		 */
+		if (DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+												  PointerGetDatum(cstring_to_text(encoded_str)),
+												  PointerGetDatum(cstring_to_text(pattern)))) > 0)
+		{
+			d = DirectFunctionCall2Coll(textregexsubstr,
+										DEFAULT_COLLATION_OID,
+										PointerGetDatum(cstring_to_text(encoded_str)),
+										PointerGetDatum(cstring_to_text(pattern)));
+			if (d != 0)
+			{
+				int		len;
+
+				res = DatumGetTextPP(d);
+				substr = text_to_cstring(res);
+				len = strlen(substr);
+				if (len > *resultlen)
+					/* remember the longest match */
+					*resultlen = len;
+			}
+		}
+		return;
+	}
+
+	p = str_set[set_index]->data;
+	while (*p)
+	{
+		encoded_str[set_index] = *p;
+		p++;
+		search_str_set_recurse(pattern, str_set, set_size, set_index + 1, encoded_str, resultlen);
+	}
+}
+
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match absolute row position
+ * other wise out of frame.
+ */
+static
+int64 evaluate_pattern(WindowObject winobj, int64 current_pos, 
+						char *vname, StringInfo encoded_str, bool *result)
+{
+	WindowAggState	*winstate = winobj->winstate;
+	ExprContext		*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell		*lc1, *lc2;
+	ExprState		*pat;
+	Datum			eval_result;
+	bool			out_of_frame = false;
+	bool			isnull;
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		/* get current, previous and next tuples */
+		if (!get_slots(winobj, current_pos))
+		{
+			out_of_frame = true;
+		}
+		else
+		{
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: " INT64_FORMAT, vname, current_pos);
+				*result = false;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: " INT64_FORMAT, vname, current_pos);
+					*result = false;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: " INT64_FORMAT, vname, current_pos);
+					appendStringInfoChar(encoded_str, vname[0]);
+					*result = true;
+				}
+			}
+			break;
+		}
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+	}
+	return current_pos;
+}
+
+/*
+ * Get current, previous and next tuples.
+ * Returns false if current row is out of partition/full frame.
+ */
+static
+bool get_slots(WindowObject winobj, int64 current_pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	TupleTableSlot *slot;
+	int		ret;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* set up current row tuple slot */
+	slot = winstate->temp_slot_1;
+	if (!window_gettupleslot(winobj, current_pos, slot))
+	{
+		elog(DEBUG1, "current row is out of partition at:" INT64_FORMAT, current_pos);
+		return false;
+
+		ret = row_is_in_frame(winstate, current_pos, slot);
+		if (ret <= 0)
+		{
+			elog(DEBUG1, "current row is out of frame at: " INT64_FORMAT, current_pos);
+			return false;
+		}
+	}
+	econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		if (!window_gettupleslot(winobj, current_pos - 1, slot))
+		{
+			elog(DEBUG1, "previous row is out of partition at: " INT64_FORMAT, current_pos - 1);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		else
+		{
+			ret = row_is_in_frame(winstate, current_pos - 1, slot);
+			if (ret <= 0)
+			{
+				elog(DEBUG1, "previous row is out of frame at: " INT64_FORMAT, current_pos - 1);
+				econtext->ecxt_outertuple = winstate->null_slot;
+			}
+			else
+			{
+				econtext->ecxt_outertuple = slot;
+			}
+		}
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	if (!window_gettupleslot(winobj, current_pos + 1, slot))
+	{
+		elog(DEBUG1, "next row is out of partiton at: " INT64_FORMAT, current_pos + 1);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+	{
+		ret = row_is_in_frame(winstate, current_pos + 1, slot);
+		if (ret <= 0)
+		{
+			elog(DEBUG1, "next row is out of frame at: " INT64_FORMAT, current_pos + 1);
+			econtext->ecxt_innertuple = winstate->null_slot;
+		}
+		else
+			econtext->ecxt_innertuple = slot;
+	}
+	return true;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..e4cab36ec9 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -36,11 +39,19 @@ typedef struct
 	int64		remainder;		/* (total rows) % (bucket num) */
 } ntile_context;
 
+/*
+ * rpr process information.
+ * Used for AFTER MATCH SKIP PAST LAST ROW
+ */
+typedef struct SkipContext
+{
+	int64		pos;	/* last row absolute position */
+} SkipContext;
+
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
 
-
 /*
  * utility routine for *_rank functions.
  */
@@ -673,7 +684,7 @@ window_last_value(PG_FUNCTION_ARGS)
 	bool		isnull;
 
 	result = WinGetFuncArgInFrame(winobj, 0,
-								  0, WINDOW_SEEK_TAIL, true,
+								  0, WINDOW_SEEK_TAIL, false,
 								  &isnull, NULL);
 	if (isnull)
 		PG_RETURN_NULL();
@@ -713,3 +724,26 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..fa100b2665 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,12 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6123', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..4fd3bd1a93 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,14 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */	
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('+' or ''. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2563,16 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
+
+	/* head of the reduced window frame */
+	int64		headpos_in_reduced_frame;
+	/* number of rows in the reduced window frame */
+	int64		num_rows_in_reduced_frame;
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..1e292648e9 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,15 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Wed_Jul_26_21_21_34_2023_317)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v3-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread

* [PATCH v3 4/7] Row pattern recognition patch (executor).
@ 2023-07-26 10:49 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 137+ messages in thread

From: Tatsuo Ishii @ 2023-07-26 10:49 UTC (permalink / raw)

---
 src/backend/executor/nodeWindowAgg.c | 701 ++++++++++++++++++++++++++-
 src/backend/utils/adt/windowfuncs.c  |  38 +-
 src/include/catalog/pg_proc.dat      |   6 +
 src/include/nodes/execnodes.h        |  18 +
 src/include/windowapi.h              |   8 +
 5 files changed, 758 insertions(+), 13 deletions(-)

diff --git a/src/backend/executor/nodeWindowAgg.c b/src/backend/executor/nodeWindowAgg.c
index 310ac23e3a..0586bf57d6 100644
--- a/src/backend/executor/nodeWindowAgg.c
+++ b/src/backend/executor/nodeWindowAgg.c
@@ -36,6 +36,7 @@
 #include "access/htup_details.h"
 #include "catalog/objectaccess.h"
 #include "catalog/pg_aggregate.h"
+#include "catalog/pg_collation_d.h"
 #include "catalog/pg_proc.h"
 #include "executor/executor.h"
 #include "executor/nodeWindowAgg.h"
@@ -48,6 +49,7 @@
 #include "utils/acl.h"
 #include "utils/builtins.h"
 #include "utils/datum.h"
+#include "utils/fmgroids.h"
 #include "utils/expandeddatum.h"
 #include "utils/lsyscache.h"
 #include "utils/memutils.h"
@@ -159,6 +161,14 @@ typedef struct WindowStatePerAggData
 	bool		restart;		/* need to restart this agg in this cycle? */
 } WindowStatePerAggData;
 
+/*
+ * Map between Var attno in a target list and the parsed attno.
+ */
+typedef struct AttnoMap {
+	List		*attno;			/* att number in target list (list of AttNumber) */
+	List		*attnosyn;		/* parsed att number (list of AttNumber) */
+} AttnoMap;
+
 static void initialize_windowaggregate(WindowAggState *winstate,
 									   WindowStatePerFunc perfuncstate,
 									   WindowStatePerAgg peraggstate);
@@ -182,8 +192,9 @@ static void begin_partition(WindowAggState *winstate);
 static void spool_tuples(WindowAggState *winstate, int64 pos);
 static void release_partition(WindowAggState *winstate);
 
-static int	row_is_in_frame(WindowAggState *winstate, int64 pos,
+static int  row_is_in_frame(WindowAggState *winstate, int64 pos,
 							TupleTableSlot *slot);
+
 static void update_frameheadpos(WindowAggState *winstate);
 static void update_frametailpos(WindowAggState *winstate);
 static void update_grouptailpos(WindowAggState *winstate);
@@ -195,9 +206,19 @@ static Datum GetAggInitVal(Datum textInitVal, Oid transtype);
 
 static bool are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
 					  TupleTableSlot *slot2);
-static bool window_gettupleslot(WindowObject winobj, int64 pos,
-								TupleTableSlot *slot);
 
+static void attno_map(Node *node, AttnoMap *map);
+static bool attno_map_walker(Node *node, void *context);
+static int row_is_in_reduced_frame(WindowObject winobj, int64 pos);
+
+static int64 evaluate_pattern(WindowObject winobj, int64 current_pos, 
+							  char *vname, StringInfo encoded_str, bool *result);
+
+static bool get_slots(WindowObject winobj, int64 current_pos);
+
+static int search_str_set(char *pattern, StringInfo *str_set, int set_size);
+static void search_str_set_recurse(char *pattern, StringInfo *str_set, int set_size, int set_index,
+								   char *encoded_str, int *resultlen);
 
 /*
  * initialize_windowaggregate
@@ -673,6 +694,9 @@ eval_windowaggregates(WindowAggState *winstate)
 	WindowObject agg_winobj;
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot;
+	bool		reduced_frame_set;
+	bool		check_reduced_frame;
+	int			num_rows_in_reduced_frame;
 
 	numaggs = winstate->numaggs;
 	if (numaggs == 0)
@@ -790,6 +814,7 @@ eval_windowaggregates(WindowAggState *winstate)
 			(winstate->frameOptions & FRAMEOPTION_EXCLUSION) ||
 			winstate->aggregatedupto <= winstate->frameheadpos)
 		{
+			elog(DEBUG1, "peraggstate->restart  is set");
 			peraggstate->restart = true;
 			numaggs_restart++;
 		}
@@ -861,8 +886,10 @@ eval_windowaggregates(WindowAggState *winstate)
 	 * If we created a mark pointer for aggregates, keep it pushed up to frame
 	 * head, so that tuplestore can discard unnecessary rows.
 	 */
+#ifdef NOT_USED
 	if (agg_winobj->markptr >= 0)
 		WinSetMarkPosition(agg_winobj, winstate->frameheadpos);
+#endif
 
 	/*
 	 * Now restart the aggregates that require it.
@@ -919,6 +946,10 @@ eval_windowaggregates(WindowAggState *winstate)
 		ExecClearTuple(agg_row_slot);
 	}
 
+	reduced_frame_set = false;
+	check_reduced_frame = false;
+	num_rows_in_reduced_frame = 0;
+
 	/*
 	 * Advance until we reach a row not in frame (or end of partition).
 	 *
@@ -930,12 +961,18 @@ eval_windowaggregates(WindowAggState *winstate)
 	{
 		int			ret;
 
+		elog(DEBUG1, "===== loop in frame starts: " INT64_FORMAT, winstate->aggregatedupto);
+
 		/* Fetch next row if we didn't already */
 		if (TupIsNull(agg_row_slot))
 		{
 			if (!window_gettupleslot(agg_winobj, winstate->aggregatedupto,
 									 agg_row_slot))
+			{
+				if (check_reduced_frame)
+					winstate->aggregatedupto--;
 				break;			/* must be end of partition */
+			}
 		}
 
 		/*
@@ -944,10 +981,47 @@ eval_windowaggregates(WindowAggState *winstate)
 		 */
 		ret = row_is_in_frame(winstate, winstate->aggregatedupto, agg_row_slot);
 		if (ret < 0)
+		{
+			if (winstate->patternVariableList != NIL && check_reduced_frame)
+				winstate->aggregatedupto--;
 			break;
+		}
 		if (ret == 0)
 			goto next_tuple;
 
+		if (winstate->patternVariableList != NIL)
+		{
+			if (!reduced_frame_set)
+			{
+				num_rows_in_reduced_frame = row_is_in_reduced_frame(winstate->agg_winobj, winstate->aggregatedupto);
+				reduced_frame_set = true;
+				elog(DEBUG1, "set num_rows_in_reduced_frame: %d pos: " INT64_FORMAT,
+					 num_rows_in_reduced_frame, winstate->aggregatedupto);
+
+				if (num_rows_in_reduced_frame <= 0)
+					break;
+
+				else if (num_rows_in_reduced_frame > 0)
+					check_reduced_frame = true;
+			}
+
+			if (check_reduced_frame)
+			{
+				elog(DEBUG1, "decrease num_rows_in_reduced_frame: %d pos: " INT64_FORMAT,
+					 num_rows_in_reduced_frame, winstate->aggregatedupto);
+				num_rows_in_reduced_frame--;
+				if (num_rows_in_reduced_frame < 0)
+				{
+					/*
+					 * No more rows remain in the reduced frame. Finish
+					 * accumulating row into the aggregates.
+					 */
+					winstate->aggregatedupto--;
+					break;
+				}
+			}
+		}
+
 		/* Set tuple context for evaluation of aggregate arguments */
 		winstate->tmpcontext->ecxt_outertuple = agg_row_slot;
 
@@ -976,6 +1050,8 @@ next_tuple:
 		ExecClearTuple(agg_row_slot);
 	}
 
+	elog(DEBUG1, "===== break loop in frame starts: " INT64_FORMAT, winstate->aggregatedupto);
+
 	/* The frame's end is not supposed to move backwards, ever */
 	Assert(aggregatedupto_nonrestarted <= winstate->aggregatedupto);
 
@@ -2053,6 +2129,8 @@ ExecWindowAgg(PlanState *pstate)
 
 	CHECK_FOR_INTERRUPTS();
 
+	elog(DEBUG1, "ExecWindowAgg called. pos: " INT64_FORMAT , winstate->currentpos);
+
 	if (winstate->status == WINDOWAGG_DONE)
 		return NULL;
 
@@ -2388,6 +2466,12 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	TupleDesc	scanDesc;
 	ListCell   *l;
 
+	TargetEntry	*te;
+	Expr		*expr;
+	Var			*var;
+	int			nargs;
+	AttnoMap	attnomap;
+
 	/* check for unsupported flags */
 	Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));
 
@@ -2483,6 +2567,16 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->temp_slot_2 = ExecInitExtraTupleSlot(estate, scanDesc,
 												   &TTSOpsMinimalTuple);
 
+	winstate->prev_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->next_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+
+	winstate->null_slot = ExecInitExtraTupleSlot(estate, scanDesc,
+												 &TTSOpsMinimalTuple);
+	winstate->null_slot = ExecStoreAllNullTuple(winstate->null_slot);
+
 	/*
 	 * create frame head and tail slots only if needed (must create slots in
 	 * exactly the same cases that update_frameheadpos and update_frametailpos
@@ -2667,6 +2761,69 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	winstate->inRangeAsc = node->inRangeAsc;
 	winstate->inRangeNullsFirst = node->inRangeNullsFirst;
 
+	/* Set up SKIP TO type */
+	winstate->rpSkipTo = node->rpSkipTo;
+	/* Set up row pattern recognition PATTERN clause */
+	winstate->patternVariableList = node->patternVariable;
+	winstate->patternRegexpList = node->patternRegexp;
+
+	/* Set up row pattern recognition DEFINE clause */
+
+	/*
+	 * Collect mapping between varattno and varattnosyn in the targetlist.
+	 * XXX: For now we only check RPR's argument. Eventually we have to
+	 * recurse the targetlist to find out all mappings in Var nodes.
+	 */
+	attnomap.attno = NIL;
+	attnomap.attnosyn = NIL;
+
+	foreach (l, node->plan.targetlist)
+	{
+		te = lfirst(l);
+		if (IsA(te->expr, WindowFunc))
+		{
+			WindowFunc	*func = (WindowFunc *)te->expr;
+
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (nargs != 1)
+				continue;
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				continue;
+
+			var = (Var *)expr;
+			elog(DEBUG1, "resname: %s varattno: %d varattnosyn: %d",
+				 te->resname, var->varattno, var->varattnosyn);
+			attnomap.attno = lappend_int(attnomap.attno, var->varattno);
+			attnomap.attnosyn = lappend_int(attnomap.attnosyn, var->varattnosyn);
+		}
+	}
+
+	winstate->defineVariableList = NIL;
+	winstate->defineClauseList = NIL;
+	if (node->defineClause != NIL)
+	{
+		foreach(l, node->defineClause)
+		{
+			char		*name;
+			ExprState	*exps;
+
+			te = lfirst(l);
+			name = te->resname;
+			expr = te->expr;
+
+			elog(DEBUG1, "defineVariable name: %s", name);
+			winstate->defineVariableList = lappend(winstate->defineVariableList,
+												   makeString(pstrdup(name)));
+			/* tweak expr so that it referes to outer slot */
+			attno_map((Node *)expr, &attnomap);
+			exps = ExecInitExpr(expr, (PlanState *) winstate);
+			winstate->defineClauseList = lappend(winstate->defineClauseList, exps);
+		}
+	}
+
 	winstate->all_first = true;
 	winstate->partition_spooled = false;
 	winstate->more_partitions = false;
@@ -2674,6 +2831,77 @@ ExecInitWindowAgg(WindowAgg *node, EState *estate, int eflags)
 	return winstate;
 }
 
+/*
+ * Rewrite Var node's varattno to the varattno which is used in the target
+ * list using AttnoMap.  We also rewrite varno so that it sees outer tuple
+ * (PREV) or inner tuple (NEXT).
+ */
+static void
+attno_map(Node *node, AttnoMap *map)
+{
+	(void) expression_tree_walker(node, attno_map_walker, (void *) map);
+}
+
+static bool
+attno_map_walker(Node *node, void *context)
+{
+	FuncExpr	*func;
+	int			nargs;
+	Expr		*expr;
+	Var			*var;
+	AttnoMap	*attnomap;
+	ListCell	*lc1, *lc2;
+	
+	if (node == NULL)
+		return false;
+
+	attnomap = (AttnoMap *) context;
+
+	if (IsA(node, FuncExpr))
+	{
+		func = (FuncExpr *)node;
+
+		if (func->funcid == F_PREV || func->funcid == F_NEXT)
+		{
+			/* sanity check */
+			nargs = list_length(func->args);
+			if (list_length(func->args) != 1)
+				elog(ERROR, "PREV/NEXT must have 1 argument but function %d has %d args", func->funcid, nargs);
+
+			expr = (Expr *) lfirst(list_head(func->args));
+			if (!IsA(expr, Var))
+				elog(ERROR, "PREV/NEXT's arg is not Var");	/* XXX: is it possible that arg type is Const? */
+			var = (Var *)expr;
+
+			if (func->funcid == F_PREV)
+				var->varno = OUTER_VAR;
+			else
+				var->varno = INNER_VAR;
+		}
+		return expression_tree_walker(node, attno_map_walker, (void *) context);
+	}
+	else if (IsA(node, Var))
+	{
+		var = (Var *)node;	 
+
+		elog(DEBUG1, "original varno: %d varattno: %d", var->varno, var->varattno);
+
+		forboth(lc1, attnomap->attno, lc2, attnomap->attnosyn)
+		{
+			int	attno = lfirst_int(lc1);
+			int	attnosyn = lfirst_int(lc2);
+
+			elog(DEBUG1, "walker: varattno: %d varattnosyn: %d",attno, attnosyn);
+			if (var->varattno == attnosyn)
+			{
+				elog(DEBUG1, "loc: %d rewrite varattno from: %d to %d", var->location, attnosyn, attno);
+				var->varattno = attno;
+			}
+		}
+	}
+	return expression_tree_walker(node, attno_map_walker, (void *) context);
+}
+
 /* -----------------
  * ExecEndWindowAgg
  * -----------------
@@ -2691,6 +2919,8 @@ ExecEndWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -2740,6 +2970,8 @@ ExecReScanWindowAgg(WindowAggState *node)
 	ExecClearTuple(node->agg_row_slot);
 	ExecClearTuple(node->temp_slot_1);
 	ExecClearTuple(node->temp_slot_2);
+	ExecClearTuple(node->prev_slot);
+	ExecClearTuple(node->next_slot);
 	if (node->framehead_slot)
 		ExecClearTuple(node->framehead_slot);
 	if (node->frametail_slot)
@@ -3080,7 +3312,7 @@ are_peers(WindowAggState *winstate, TupleTableSlot *slot1,
  *
  * Returns true if successful, false if no such row
  */
-static bool
+bool
 window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 {
 	WindowAggState *winstate = winobj->winstate;
@@ -3100,7 +3332,7 @@ window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot)
 		return false;
 
 	if (pos < winobj->markpos)
-		elog(ERROR, "cannot fetch row before WindowObject's mark position");
+		elog(ERROR, "cannot fetch row: " INT64_FORMAT " before WindowObject's mark position: " INT64_FORMAT,  pos, winobj->markpos );
 
 	oldcontext = MemoryContextSwitchTo(winstate->ss.ps.ps_ExprContext->ecxt_per_query_memory);
 
@@ -3420,14 +3652,54 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 	WindowAggState *winstate;
 	ExprContext *econtext;
 	TupleTableSlot *slot;
-	int64		abs_pos;
-	int64		mark_pos;
 
 	Assert(WindowObjectIsValid(winobj));
 	winstate = winobj->winstate;
 	econtext = winstate->ss.ps.ps_ExprContext;
 	slot = winstate->temp_slot_1;
 
+	if (WinGetSlotInFrame(winobj, slot,
+						  relpos, seektype, set_mark,
+						  isnull, isout) == 0)
+	{
+		econtext->ecxt_outertuple = slot;
+		return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
+							econtext, isnull);
+	}
+
+	if (isout)
+		*isout = true;
+	*isnull = true;
+	return (Datum) 0;
+}
+
+/*
+ * WinGetSlotInFrame
+ * slot: TupleTableSlot to store the result
+ * relpos: signed rowcount offset from the seek position
+ * seektype: WINDOW_SEEK_HEAD or WINDOW_SEEK_TAIL
+ * set_mark: If the row is found/in frame and set_mark is true, the mark is
+ *		moved to the row as a side-effect.
+ * isnull: output argument, receives isnull status of result
+ * isout: output argument, set to indicate whether target row position
+ *		is out of frame (can pass NULL if caller doesn't care about this)
+ *
+ * Returns 0 if we successfullt got the slot. false if out of frame.
+ * (also isout is set)
+ */
+int
+WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+					 int relpos, int seektype, bool set_mark,
+					 bool *isnull, bool *isout)
+{
+	WindowAggState *winstate;
+	int64		abs_pos;
+	int64		mark_pos;
+	int			num_reduced_frame;
+
+	Assert(WindowObjectIsValid(winobj));
+	winstate = winobj->winstate;
+
 	switch (seektype)
 	{
 		case WINDOW_SEEK_CURRENT:
@@ -3494,6 +3766,12 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 						 winstate->frameOptions);
 					break;
 			}
+			num_reduced_frame = row_is_in_reduced_frame(winobj, winstate->frameheadpos);
+			if (num_reduced_frame < 0)
+				goto out_of_frame;
+			else if (num_reduced_frame > 0)
+				if (relpos >= num_reduced_frame)
+					goto out_of_frame;
 			break;
 		case WINDOW_SEEK_TAIL:
 			/* rejecting relpos > 0 is easy and simplifies code below */
@@ -3565,6 +3843,12 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 					mark_pos = 0;	/* keep compiler quiet */
 					break;
 			}
+
+			num_reduced_frame = row_is_in_reduced_frame(winobj, winstate->frameheadpos + relpos);
+			if (num_reduced_frame < 0)
+				goto out_of_frame;
+			else if (num_reduced_frame > 0)
+				abs_pos = winstate->frameheadpos + relpos + num_reduced_frame - 1;
 			break;
 		default:
 			elog(ERROR, "unrecognized window seek type: %d", seektype);
@@ -3583,15 +3867,13 @@ WinGetFuncArgInFrame(WindowObject winobj, int argno,
 		*isout = false;
 	if (set_mark)
 		WinSetMarkPosition(winobj, mark_pos);
-	econtext->ecxt_outertuple = slot;
-	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
-						econtext, isnull);
+	return 0;
 
 out_of_frame:
 	if (isout)
 		*isout = true;
 	*isnull = true;
-	return (Datum) 0;
+	return -1;
 }
 
 /*
@@ -3622,3 +3904,400 @@ WinGetFuncArgCurrent(WindowObject winobj, int argno, bool *isnull)
 	return ExecEvalExpr((ExprState *) list_nth(winobj->argstates, argno),
 						econtext, isnull);
 }
+
+WindowAggState *
+WinGetAggState(WindowObject winobj)
+{
+	return winobj->winstate;
+}
+
+/*
+ * row_is_in_reduced_frame
+ * Determine whether a row is in the current row's reduced window frame according
+ * to row pattern matching
+ *
+ * The row must has been already determined that it is in a full window frame
+ * and fetched it into slot.
+ *
+ * Returns:
+ * = 0, RPR is not defined.
+ * >0, if the row is the first in the reduced frame. Return the number of rows in the reduced frame.
+ * -1, if the row is unmatched row
+ * -2, if the row is in the reduced frame but needed to be skipped because of
+ * AFTER MATCH SKIP PAST LAST ROW
+ */
+static
+int row_is_in_reduced_frame(WindowObject winobj, int64 pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	ListCell	*lc1, *lc2;
+	bool		expression_result;
+	int			num_matched_rows;
+	int64		original_pos;
+	bool		anymatch;
+	StringInfo	encoded_str;
+	StringInfo	pattern_str = makeStringInfo();
+
+	/*
+	 * Array of pattern variables evaluted to true.
+	 * Each character corresponds to pattern variable.
+	 * Example:
+	 * str_set[0] = "AB";
+	 * str_set[1] = "AC";
+	 * In this case at row 0 A and B are true, and A and C are true in row 1.
+	 */
+	#define ENCODED_STR_ARRAY_ALLOC_SIZE	128
+	StringInfo	*str_set = NULL;
+	int		str_set_index;
+	int		str_set_size;
+
+	if (winstate->patternVariableList == NIL)
+	{
+		/*
+		 * RPR is not defined. Assume that we are always in the the reduced
+		 * window frame.
+		 */
+		return 0;
+	}
+
+	/* save original pos */
+	original_pos = pos;
+
+	/*
+	 * Check whether the row speicied by pos is in the reduced frame. The
+	 * second and subsequent rows need to be recognized as "unmatched" rows if
+	 * AFTER MATCH SKIP PAST LAST ROW is defined.
+	 */
+	if (winstate->rpSkipTo == ST_PAST_LAST_ROW &&
+		pos > winstate->headpos_in_reduced_frame &&
+		pos < (winstate->headpos_in_reduced_frame + winstate->num_rows_in_reduced_frame))
+		return -2;
+		
+	/*
+	 * Loop over until none of pattern matches or encounters end of frame.
+	 */
+	for (;;)
+	{
+		int64	result_pos = -1;
+
+		/*
+		 * Loop over each PATTERN variable.
+		 */
+		anymatch = false;
+		encoded_str = makeStringInfo();
+
+		forboth(lc1, winstate->patternVariableList, lc2, winstate->patternRegexpList)
+		{
+			char	*vname = strVal(lfirst(lc1));
+			char	*quantifier = strVal(lfirst(lc2));
+
+			elog(DEBUG1, "pos: " INT64_FORMAT " pattern vname: %s quantifier: %s", pos, vname, quantifier);
+
+			expression_result = false;
+
+			/* evaluate row pattern against current row */
+			result_pos = evaluate_pattern(winobj, pos, vname, encoded_str, &expression_result);
+			if (expression_result)
+			{
+				elog(DEBUG1, "expression result is true");
+				anymatch = true;
+			}
+
+			/*
+			 * If out of frame, we are done.
+			 */
+			 if (result_pos < 0)
+				 break;
+		}
+
+		if (!anymatch)
+		{
+			/* none of patterns matched. */
+			break;
+		}
+
+		/* build encoded string array */
+		if (str_set == NULL)
+		{
+			str_set_index = 0;
+			str_set_size = ENCODED_STR_ARRAY_ALLOC_SIZE * sizeof(StringInfo);
+			str_set = palloc(str_set_size);
+		}
+
+		str_set[str_set_index++] = encoded_str;
+
+		elog(DEBUG1, "pos: " INT64_FORMAT " str_set_index: %d encoded_str: %s", pos, str_set_index, encoded_str->data);
+
+		if (str_set_index >= str_set_size)
+		{
+			str_set_size *= 2;
+			str_set = repalloc(str_set, str_set_size);
+		}
+
+		/* move to next row */
+		pos++;
+
+		if (result_pos < 0)
+		{
+			/* out of frame */
+			break;
+		}
+	}
+
+	if (str_set == NULL)
+	{
+		/* no matches found in the first row */
+		return -1;
+	}
+
+	elog(DEBUG1, "pos: " INT64_FORMAT " encoded_str: %s", pos, encoded_str->data);
+
+	/* build regular expression */
+	pattern_str = makeStringInfo();
+	appendStringInfoChar(pattern_str, '^');
+	forboth(lc1, winstate->patternVariableList, lc2, winstate->patternRegexpList)
+	{
+		char	*vname = strVal(lfirst(lc1));
+		char	*quantifier = strVal(lfirst(lc2));
+
+		appendStringInfoChar(pattern_str, vname[0]);
+		if (quantifier[0])
+			appendStringInfoChar(pattern_str, quantifier[0]);
+		elog(DEBUG1, "vname: %s quantifier: %s", vname, quantifier);
+	}
+
+	elog(DEBUG1, "pos: " INT64_FORMAT " pattern: %s", pos, pattern_str->data);
+
+	/* look for matching pattern variable sequence */
+	num_matched_rows = search_str_set(pattern_str->data, str_set, str_set_index);
+	if (num_matched_rows <= 0)
+		return -1;
+
+	/*
+	 * We are at the first row in the reduced frame.  Save the number of
+	 * matched rows as the number of rows in the reduced frame.
+	 */
+	winstate->headpos_in_reduced_frame = original_pos;
+	winstate->num_rows_in_reduced_frame = num_matched_rows;
+
+	return num_matched_rows;
+}
+
+/*
+ * search set of encode_str.
+ * set_size: size of set_str array.
+ */
+static
+int search_str_set(char *pattern, StringInfo *str_set, int set_size)
+{
+	char		*encoded_str = palloc0(set_size+1);
+	int			resultlen = 0;
+
+	search_str_set_recurse(pattern, str_set, set_size, 0, encoded_str, &resultlen);
+	elog(DEBUG1, "search_str_set returns %d", resultlen);
+	return resultlen;
+}
+
+static
+void search_str_set_recurse(char *pattern, StringInfo *str_set, int set_size, int set_index, char *encoded_str, int *resultlen)
+{
+	char	*p;
+
+	if (set_index >= set_size)
+	{
+		Datum	d;
+		text	*res;
+		char	*substr;
+
+		/*
+		 * We first perform pattern matching using regexp_instr, then call
+		 * textregexsubstr to get matched substring to know how log the
+		 * matched string is. That is the number of rows in the reduced window
+		 * frame.  The reason why we can't call textregexsubstr is, it error
+		 * out if pattern is not match.
+		 */
+		if (DatumGetInt32(DirectFunctionCall2Coll(regexp_instr, DEFAULT_COLLATION_OID,
+												  PointerGetDatum(cstring_to_text(encoded_str)),
+												  PointerGetDatum(cstring_to_text(pattern)))) > 0)
+		{
+			d = DirectFunctionCall2Coll(textregexsubstr,
+										DEFAULT_COLLATION_OID,
+										PointerGetDatum(cstring_to_text(encoded_str)),
+										PointerGetDatum(cstring_to_text(pattern)));
+			if (d != 0)
+			{
+				int		len;
+
+				res = DatumGetTextPP(d);
+				substr = text_to_cstring(res);
+				len = strlen(substr);
+				if (len > *resultlen)
+					/* remember the longest match */
+					*resultlen = len;
+			}
+		}
+		return;
+	}
+
+	p = str_set[set_index]->data;
+	while (*p)
+	{
+		encoded_str[set_index] = *p;
+		p++;
+		search_str_set_recurse(pattern, str_set, set_size, set_index + 1, encoded_str, resultlen);
+	}
+}
+
+
+/*
+ * Evaluate expression associated with PATTERN variable vname.
+ * relpos is relative row position in a frame (starting from 0).
+ * "quantifier" is the quatifier part of the PATTERN regular expression.
+ * Currently only '+' is allowed.
+ * result is out paramater representing the expression evaluation result
+ * is true of false.
+ * Return values are:
+ * >=0: the last match absolute row position
+ * other wise out of frame.
+ */
+static
+int64 evaluate_pattern(WindowObject winobj, int64 current_pos, 
+						char *vname, StringInfo encoded_str, bool *result)
+{
+	WindowAggState	*winstate = winobj->winstate;
+	ExprContext		*econtext = winstate->ss.ps.ps_ExprContext;
+	ListCell		*lc1, *lc2;
+	ExprState		*pat;
+	Datum			eval_result;
+	bool			out_of_frame = false;
+	bool			isnull;
+
+	forboth (lc1, winstate->defineVariableList, lc2, winstate->defineClauseList)
+	{
+		char	*name = strVal(lfirst(lc1));
+
+		if (strcmp(vname, name))
+			continue;
+
+		/* set expression to evaluate */
+		pat = lfirst(lc2);
+
+		/* get current, previous and next tuples */
+		if (!get_slots(winobj, current_pos))
+		{
+			out_of_frame = true;
+		}
+		else
+		{
+			/* evaluate the expression */
+			eval_result = ExecEvalExpr(pat, econtext, &isnull);
+			if (isnull)
+			{
+				/* expression is NULL */
+				elog(DEBUG1, "expression for %s is NULL at row: " INT64_FORMAT, vname, current_pos);
+				*result = false;
+			}
+			else
+			{
+				if (!DatumGetBool(eval_result))
+				{
+					/* expression is false */
+					elog(DEBUG1, "expression for %s is false at row: " INT64_FORMAT, vname, current_pos);
+					*result = false;
+				}
+				else
+				{
+					/* expression is true */
+					elog(DEBUG1, "expression for %s is true at row: " INT64_FORMAT, vname, current_pos);
+					appendStringInfoChar(encoded_str, vname[0]);
+					*result = true;
+				}
+			}
+			break;
+		}
+
+		if (out_of_frame)
+		{
+			*result = false;
+			return -1;
+		}
+	}
+	return current_pos;
+}
+
+/*
+ * Get current, previous and next tuples.
+ * Returns false if current row is out of partition/full frame.
+ */
+static
+bool get_slots(WindowObject winobj, int64 current_pos)
+{
+	WindowAggState *winstate = winobj->winstate;
+	TupleTableSlot *slot;
+	int		ret;
+	ExprContext *econtext;
+
+	econtext = winstate->ss.ps.ps_ExprContext;
+
+	/* set up current row tuple slot */
+	slot = winstate->temp_slot_1;
+	if (!window_gettupleslot(winobj, current_pos, slot))
+	{
+		elog(DEBUG1, "current row is out of partition at:" INT64_FORMAT, current_pos);
+		return false;
+
+		ret = row_is_in_frame(winstate, current_pos, slot);
+		if (ret <= 0)
+		{
+			elog(DEBUG1, "current row is out of frame at: " INT64_FORMAT, current_pos);
+			return false;
+		}
+	}
+	econtext->ecxt_scantuple = slot;
+
+	/* for PREV */
+	if (current_pos > 0)
+	{
+		slot = winstate->prev_slot;
+		if (!window_gettupleslot(winobj, current_pos - 1, slot))
+		{
+			elog(DEBUG1, "previous row is out of partition at: " INT64_FORMAT, current_pos - 1);
+			econtext->ecxt_outertuple = winstate->null_slot;
+		}
+		else
+		{
+			ret = row_is_in_frame(winstate, current_pos - 1, slot);
+			if (ret <= 0)
+			{
+				elog(DEBUG1, "previous row is out of frame at: " INT64_FORMAT, current_pos - 1);
+				econtext->ecxt_outertuple = winstate->null_slot;
+			}
+			else
+			{
+				econtext->ecxt_outertuple = slot;
+			}
+		}
+	}
+	else
+		econtext->ecxt_outertuple = winstate->null_slot;
+
+	/* for NEXT */
+	slot = winstate->next_slot;
+	if (!window_gettupleslot(winobj, current_pos + 1, slot))
+	{
+		elog(DEBUG1, "next row is out of partiton at: " INT64_FORMAT, current_pos + 1);
+		econtext->ecxt_innertuple = winstate->null_slot;
+	}
+	else
+	{
+		ret = row_is_in_frame(winstate, current_pos + 1, slot);
+		if (ret <= 0)
+		{
+			elog(DEBUG1, "next row is out of frame at: " INT64_FORMAT, current_pos + 1);
+			econtext->ecxt_innertuple = winstate->null_slot;
+		}
+		else
+			econtext->ecxt_innertuple = slot;
+	}
+	return true;
+}
diff --git a/src/backend/utils/adt/windowfuncs.c b/src/backend/utils/adt/windowfuncs.c
index b87a624fb2..e4cab36ec9 100644
--- a/src/backend/utils/adt/windowfuncs.c
+++ b/src/backend/utils/adt/windowfuncs.c
@@ -13,6 +13,9 @@
  */
 #include "postgres.h"
 
+#include "catalog/pg_collation_d.h"
+#include "executor/executor.h"
+#include "nodes/execnodes.h"
 #include "nodes/supportnodes.h"
 #include "utils/builtins.h"
 #include "windowapi.h"
@@ -36,11 +39,19 @@ typedef struct
 	int64		remainder;		/* (total rows) % (bucket num) */
 } ntile_context;
 
+/*
+ * rpr process information.
+ * Used for AFTER MATCH SKIP PAST LAST ROW
+ */
+typedef struct SkipContext
+{
+	int64		pos;	/* last row absolute position */
+} SkipContext;
+
 static bool rank_up(WindowObject winobj);
 static Datum leadlag_common(FunctionCallInfo fcinfo,
 							bool forward, bool withoffset, bool withdefault);
 
-
 /*
  * utility routine for *_rank functions.
  */
@@ -673,7 +684,7 @@ window_last_value(PG_FUNCTION_ARGS)
 	bool		isnull;
 
 	result = WinGetFuncArgInFrame(winobj, 0,
-								  0, WINDOW_SEEK_TAIL, true,
+								  0, WINDOW_SEEK_TAIL, false,
 								  &isnull, NULL);
 	if (isnull)
 		PG_RETURN_NULL();
@@ -713,3 +724,26 @@ window_nth_value(PG_FUNCTION_ARGS)
 
 	PG_RETURN_DATUM(result);
 }
+
+/*
+ * prev
+ * Dummy function to invoke RPR's navigation operator "PREV".
+ * This is *not* a window function.
+ */
+Datum
+window_prev(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
+/*
+ * next
+ * Dummy function to invoke RPR's navigation operation "NEXT".
+ * This is *not* a window function.
+ */
+Datum
+window_next(PG_FUNCTION_ARGS)
+{
+	PG_RETURN_DATUM(PG_GETARG_DATUM(0));
+}
+
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index 6996073989..fa100b2665 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -10397,6 +10397,12 @@
 { oid => '3114', descr => 'fetch the Nth row value',
   proname => 'nth_value', prokind => 'w', prorettype => 'anyelement',
   proargtypes => 'anyelement int4', prosrc => 'window_nth_value' },
+{ oid => '6122', descr => 'previous value',
+  proname => 'prev', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_prev' },
+{ oid => '6123', descr => 'next value',
+  proname => 'next', provolatile => 's', prorettype => 'anyelement',
+  proargtypes => 'anyelement', prosrc => 'window_next' },
 
 # functions for range types
 { oid => '3832', descr => 'I/O',
diff --git a/src/include/nodes/execnodes.h b/src/include/nodes/execnodes.h
index cb714f4a19..4fd3bd1a93 100644
--- a/src/include/nodes/execnodes.h
+++ b/src/include/nodes/execnodes.h
@@ -2519,6 +2519,14 @@ typedef struct WindowAggState
 	int64		groupheadpos;	/* current row's peer group head position */
 	int64		grouptailpos;	/* " " " " tail position (group end+1) */
 
+	/* these fields are used in Row pattern recognition: */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */	
+	List	   *patternVariableList;	/* list of row pattern variables names (list of String) */
+	List	   *patternRegexpList;	/* list of row pattern regular expressions ('+' or ''. list of String) */
+	List	   *defineVariableList;	/* list of row pattern definition variables (list of String) */
+	List	   *defineClauseList;	/* expression for row pattern definition
+									 * search conditions ExprState list */
+
 	MemoryContext partcontext;	/* context for partition-lifespan data */
 	MemoryContext aggcontext;	/* shared context for aggregate working data */
 	MemoryContext curaggcontext;	/* current aggregate's working data */
@@ -2555,6 +2563,16 @@ typedef struct WindowAggState
 	TupleTableSlot *agg_row_slot;
 	TupleTableSlot *temp_slot_1;
 	TupleTableSlot *temp_slot_2;
+
+	/* temporary slots for RPR */
+	TupleTableSlot *prev_slot;	/* PREV row navigation operator */
+	TupleTableSlot *next_slot;	/* NEXT row navigation operator */
+	TupleTableSlot *null_slot;	/* all NULL slot */
+
+	/* head of the reduced window frame */
+	int64		headpos_in_reduced_frame;
+	/* number of rows in the reduced window frame */
+	int64		num_rows_in_reduced_frame;
 } WindowAggState;
 
 /* ----------------
diff --git a/src/include/windowapi.h b/src/include/windowapi.h
index b8c2c565d1..1e292648e9 100644
--- a/src/include/windowapi.h
+++ b/src/include/windowapi.h
@@ -58,7 +58,15 @@ extern Datum WinGetFuncArgInFrame(WindowObject winobj, int argno,
 								  int relpos, int seektype, bool set_mark,
 								  bool *isnull, bool *isout);
 
+extern int WinGetSlotInFrame(WindowObject winobj, TupleTableSlot *slot,
+							 int relpos, int seektype, bool set_mark,
+							 bool *isnull, bool *isout);
+
 extern Datum WinGetFuncArgCurrent(WindowObject winobj, int argno,
 								  bool *isnull);
 
+extern WindowAggState *WinGetAggState(WindowObject winobj);
+
+extern bool window_gettupleslot(WindowObject winobj, int64 pos, TupleTableSlot *slot);
+
 #endif							/* WINDOWAPI_H */
-- 
2.25.1


----Next_Part(Wed_Jul_26_21_21_34_2023_317)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v3-0005-Row-pattern-recognition-patch-docs.patch"



^ permalink  raw  reply  [nested|flat] 137+ messages in thread