Add SP-GiST support for range types.

The implementation is a quad-tree, largely copied from the quad-tree
implementation for points. The lower and upper bound of ranges are the 2d
coordinates, with some extra code to handle empty ranges.

I left out the support for adjacent operator, -|-, from the original patch.
Not because there was necessarily anything wrong with it, but it was more
complicated than the other operators, and I only have limited time for
reviewing. That will follow as a separate patch.

Alexander Korotkov, reviewed by Jeff Davis and me.

src/backend/utils/adt/Makefile

@@ -30,7 +30,7 @@ OBJS = acl.o arrayfuncs.o array_selfuncs.o array_typanalyze.o \
 	tsginidx.o tsgistidx.o tsquery.o tsquery_cleanup.o tsquery_gist.o \
 	tsquery_op.o tsquery_rewrite.o tsquery_util.o tsrank.o \
 	tsvector.o tsvector_op.o tsvector_parser.o \
-	txid.o uuid.o windowfuncs.o xml.o
+	txid.o uuid.o windowfuncs.o xml.o rangetypes_spgist.o
 
 like.o: like.c like_match.c
 

src/backend/utils/adt/rangetypes_gist.c

@@ -21,19 +21,6 @@
 #include "utils/rangetypes.h"
 
 
-/* Operator strategy numbers used in the GiST range opclass */
-/* Numbers are chosen to match up operator names with existing usages */
-#define RANGESTRAT_BEFORE				1
-#define RANGESTRAT_OVERLEFT				2
-#define RANGESTRAT_OVERLAPS				3
-#define RANGESTRAT_OVERRIGHT			4
-#define RANGESTRAT_AFTER				5
-#define RANGESTRAT_ADJACENT				6
-#define RANGESTRAT_CONTAINS				7
-#define RANGESTRAT_CONTAINED_BY			8
-#define RANGESTRAT_CONTAINS_ELEM		16
-#define RANGESTRAT_EQ					18
-
 /*
  * Range class properties used to segregate different classes of ranges in
  * GiST.  Each unique combination of properties is a class.  CLS_EMPTY cannot

src/include/catalog/catversion.h

@@ -53,6 +53,6 @@
  */
 
 /*							yyyymmddN */
-#define CATALOG_VERSION_NO	201208071
+#define CATALOG_VERSION_NO	201208161
 
 #endif

src/include/catalog/pg_amop.h

@@ -767,4 +767,17 @@ DATA(insert (	4017   25 25 12 s	665 4000 0 ));
 DATA(insert (	4017   25 25 14 s	667 4000 0 ));
 DATA(insert (	4017   25 25 15 s	666 4000 0 ));
 
+/*
+ * SP-GiST range_ops
+ */
+DATA(insert (	3474   3831 3831 1 s	3893 4000 0 ));
+DATA(insert (	3474   3831 3831 2 s	3895 4000 0 ));
+DATA(insert (	3474   3831 3831 3 s	3888 4000 0 ));
+DATA(insert (	3474   3831 3831 4 s	3896 4000 0 ));
+DATA(insert (	3474   3831 3831 5 s	3894 4000 0 ));
+DATA(insert (	3474   3831 3831 7 s	3890 4000 0 ));
+DATA(insert (	3474   3831 3831 8 s	3892 4000 0 ));
+DATA(insert (	3474   3831 2283 16 s	3889 4000 0 ));
+DATA(insert (	3474   3831 3831 18 s	3882 4000 0 ));
+
 #endif   /* PG_AMOP_H */

src/include/catalog/pg_amproc.h

@@ -373,5 +373,10 @@ DATA(insert (	4017   25 25 2 4028 ));
 DATA(insert (	4017   25 25 3 4029 ));
 DATA(insert (	4017   25 25 4 4030 ));
 DATA(insert (	4017   25 25 5 4031 ));
+DATA(insert (	3474   3831 3831 1 3469 ));
+DATA(insert (	3474   3831 3831 2 3470 ));
+DATA(insert (	3474   3831 3831 3 3471 ));
+DATA(insert (	3474   3831 3831 4 3472 ));
+DATA(insert (	3474   3831 3831 5 3473 ));
 
 #endif   /* PG_AMPROC_H */

src/include/catalog/pg_opclass.h

@@ -223,6 +223,7 @@ DATA(insert (	783		tsquery_ops			PGNSP PGUID 3702  3615 t 20 ));
 DATA(insert (	403		range_ops			PGNSP PGUID 3901  3831 t 0 ));
 DATA(insert (	405		range_ops			PGNSP PGUID 3903  3831 t 0 ));
 DATA(insert (	783		range_ops			PGNSP PGUID 3919  3831 t 0 ));
+DATA(insert (	4000	range_ops			PGNSP PGUID 3474  3831 t 0 ));
 DATA(insert (	4000	quad_point_ops		PGNSP PGUID 4015  600 t 0 ));
 DATA(insert (	4000	kd_point_ops		PGNSP PGUID 4016  600 f 0 ));
 DATA(insert (	4000	text_ops			PGNSP PGUID 4017  25 t 0 ));

src/include/catalog/pg_opfamily.h

@@ -142,6 +142,7 @@ DATA(insert OID = 3702 (	783		tsquery_ops		PGNSP PGUID ));
 DATA(insert OID = 3901 (	403		range_ops		PGNSP PGUID ));
 DATA(insert OID = 3903 (	405		range_ops		PGNSP PGUID ));
 DATA(insert OID = 3919 (	783		range_ops		PGNSP PGUID ));
+DATA(insert OID = 3474 (	4000	range_ops		PGNSP PGUID ));
 DATA(insert OID = 4015 (	4000	quad_point_ops	PGNSP PGUID ));
 DATA(insert OID = 4016 (	4000	kd_point_ops	PGNSP PGUID ));
 DATA(insert OID = 4017 (	4000	text_ops		PGNSP PGUID ));

src/include/catalog/pg_proc.h

@@ -4653,6 +4653,17 @@ DESCR("SP-GiST support for suffix tree over text");
 DATA(insert OID = 4031 (  spg_text_leaf_consistent	PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 16 "2281 2281" _null_ _null_ _null_ _null_  spg_text_leaf_consistent _null_ _null_ _null_ ));
 DESCR("SP-GiST support for suffix tree over text");
 
+DATA(insert OID = 3469 (  spg_range_quad_config	PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 2278 "2281 2281" _null_ _null_ _null_ _null_  spg_range_quad_config _null_ _null_ _null_ ));
+DESCR("SP-GiST support for quad tree over range");
+DATA(insert OID = 3470 (  spg_range_quad_choose	PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 2278 "2281 2281" _null_ _null_ _null_ _null_  spg_range_quad_choose _null_ _null_ _null_ ));
+DESCR("SP-GiST support for quad tree over range");
+DATA(insert OID = 3471 (  spg_range_quad_picksplit	PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 2278 "2281 2281" _null_ _null_ _null_ _null_  spg_range_quad_picksplit _null_ _null_ _null_ ));
+DESCR("SP-GiST support for quad tree over range");
+DATA(insert OID = 3472 (  spg_range_quad_inner_consistent	PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 2278 "2281 2281" _null_ _null_ _null_ _null_  spg_range_quad_inner_consistent _null_ _null_ _null_ ));
+DESCR("SP-GiST support for quad tree over range");
+DATA(insert OID = 3473 (  spg_range_quad_leaf_consistent	PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 16 "2281 2281" _null_ _null_ _null_ _null_  spg_range_quad_leaf_consistent _null_ _null_ _null_ ));
+DESCR("SP-GiST support for quad tree over range");
+
 
 /*
  * Symbolic values for provolatile column: these indicate whether the result

src/include/utils/rangetypes.h

@@ -75,6 +75,19 @@ typedef struct
 #define PG_GETARG_RANGE_COPY(n)		DatumGetRangeTypeCopy(PG_GETARG_DATUM(n))
 #define PG_RETURN_RANGE(x)			return RangeTypeGetDatum(x)
 
+/* Operator strategy numbers used in the GiST and SP-GiST range opclasses */
+/* Numbers are chosen to match up operator names with existing usages */
+#define RANGESTRAT_BEFORE				1
+#define RANGESTRAT_OVERLEFT				2
+#define RANGESTRAT_OVERLAPS				3
+#define RANGESTRAT_OVERRIGHT			4
+#define RANGESTRAT_AFTER				5
+#define RANGESTRAT_ADJACENT				6
+#define RANGESTRAT_CONTAINS				7
+#define RANGESTRAT_CONTAINED_BY			8
+#define RANGESTRAT_CONTAINS_ELEM		16
+#define RANGESTRAT_EQ					18
+
 /*
  * prototypes for functions defined in rangetypes.c
  */

src/test/regress/expected/opr_sanity.out

@@ -1068,12 +1068,16 @@ ORDER BY 1, 2, 3;
        2742 |            4 | =
        4000 |            1 | <<
        4000 |            1 | ~<~
+       4000 |            2 | &<
        4000 |            2 | ~<=~
+       4000 |            3 | &&
        4000 |            3 | =
+       4000 |            4 | &>
        4000 |            4 | ~>=~
        4000 |            5 | >>
        4000 |            5 | ~>~
        4000 |            6 | ~=
+       4000 |            7 | @>
        4000 |            8 | <@
        4000 |           10 | <^
        4000 |           11 | <
@@ -1081,7 +1085,9 @@ ORDER BY 1, 2, 3;
        4000 |           12 | <=
        4000 |           14 | >=
        4000 |           15 | >
-(55 rows)
+       4000 |           16 | @>
+       4000 |           18 | =
+(61 rows)
 
 -- Check that all opclass search operators have selectivity estimators.
 -- This is not absolutely required, but it seems a reasonable thing

src/test/regress/expected/rangetypes.out

@@ -821,6 +821,225 @@ select count(*) from test_range_gist where ir -|- int4range(100,500);
      5
 (1 row)
 
+-- test SP-GiST index that's been built incrementally
+create table test_range_spgist(ir int4range);
+create index test_range_spgist_idx on test_range_spgist using spgist (ir);
+insert into test_range_spgist select int4range(g, g+10) from generate_series(1,2000) g;
+insert into test_range_spgist select 'empty'::int4range from generate_series(1,500) g;
+insert into test_range_spgist select int4range(g, g+10000) from generate_series(1,1000) g;
+insert into test_range_spgist select 'empty'::int4range from generate_series(1,500) g;
+insert into test_range_spgist select int4range(NULL,g*10,'(]') from generate_series(1,100) g;
+insert into test_range_spgist select int4range(g*10,NULL,'(]') from generate_series(1,100) g;
+insert into test_range_spgist select int4range(g, g+10) from generate_series(1,2000) g;
+-- first, verify non-indexed results
+SET enable_seqscan    = t;
+SET enable_indexscan  = f;
+SET enable_bitmapscan = f;
+select count(*) from test_range_spgist where ir @> 'empty'::int4range;
+ count 
+-------
+  6200
+(1 row)
+
+select count(*) from test_range_spgist where ir = int4range(10,20);
+ count 
+-------
+     2
+(1 row)
+
+select count(*) from test_range_spgist where ir @> 10;
+ count 
+-------
+   130
+(1 row)
+
+select count(*) from test_range_spgist where ir @> int4range(10,20);
+ count 
+-------
+   111
+(1 row)
+
+select count(*) from test_range_spgist where ir && int4range(10,20);
+ count 
+-------
+   158
+(1 row)
+
+select count(*) from test_range_spgist where ir <@ int4range(10,50);
+ count 
+-------
+  1062
+(1 row)
+
+select count(*) from test_range_spgist where ir << int4range(100,500);
+ count 
+-------
+   189
+(1 row)
+
+select count(*) from test_range_spgist where ir >> int4range(100,500);
+ count 
+-------
+  3554
+(1 row)
+
+select count(*) from test_range_spgist where ir &< int4range(100,500);
+ count 
+-------
+  1029
+(1 row)
+
+select count(*) from test_range_spgist where ir &> int4range(100,500);
+ count 
+-------
+  4794
+(1 row)
+
+select count(*) from test_range_spgist where ir -|- int4range(100,500);
+ count 
+-------
+     5
+(1 row)
+
+-- now check same queries using index
+SET enable_seqscan    = f;
+SET enable_indexscan  = t;
+SET enable_bitmapscan = f;
+select count(*) from test_range_spgist where ir @> 'empty'::int4range;
+ count 
+-------
+  6200
+(1 row)
+
+select count(*) from test_range_spgist where ir = int4range(10,20);
+ count 
+-------
+     2
+(1 row)
+
+select count(*) from test_range_spgist where ir @> 10;
+ count 
+-------
+   130
+(1 row)
+
+select count(*) from test_range_spgist where ir @> int4range(10,20);
+ count 
+-------
+   111
+(1 row)
+
+select count(*) from test_range_spgist where ir && int4range(10,20);
+ count 
+-------
+   158
+(1 row)
+
+select count(*) from test_range_spgist where ir <@ int4range(10,50);
+ count 
+-------
+  1062
+(1 row)
+
+select count(*) from test_range_spgist where ir << int4range(100,500);
+ count 
+-------
+   189
+(1 row)
+
+select count(*) from test_range_spgist where ir >> int4range(100,500);
+ count 
+-------
+  3554
+(1 row)
+
+select count(*) from test_range_spgist where ir &< int4range(100,500);
+ count 
+-------
+  1029
+(1 row)
+
+select count(*) from test_range_spgist where ir &> int4range(100,500);
+ count 
+-------
+  4794
+(1 row)
+
+select count(*) from test_range_spgist where ir -|- int4range(100,500);
+ count 
+-------
+     5
+(1 row)
+
+-- now check same queries using a bulk-loaded index
+drop index test_range_spgist_idx;
+create index test_range_spgist_idx on test_range_spgist using spgist (ir);
+select count(*) from test_range_spgist where ir @> 'empty'::int4range;
+ count 
+-------
+  6200
+(1 row)
+
+select count(*) from test_range_spgist where ir = int4range(10,20);
+ count 
+-------
+     2
+(1 row)
+
+select count(*) from test_range_spgist where ir @> 10;
+ count 
+-------
+   130
+(1 row)
+
+select count(*) from test_range_spgist where ir @> int4range(10,20);
+ count 
+-------
+   111
+(1 row)
+
+select count(*) from test_range_spgist where ir && int4range(10,20);
+ count 
+-------
+   158
+(1 row)
+
+select count(*) from test_range_spgist where ir <@ int4range(10,50);
+ count 
+-------
+  1062
+(1 row)
+
+select count(*) from test_range_spgist where ir << int4range(100,500);
+ count 
+-------
+   189
+(1 row)
+
+select count(*) from test_range_spgist where ir >> int4range(100,500);
+ count 
+-------
+  3554
+(1 row)
+
+select count(*) from test_range_spgist where ir &< int4range(100,500);
+ count 
+-------
+  1029
+(1 row)
+
+select count(*) from test_range_spgist where ir &> int4range(100,500);
+ count 
+-------
+  4794
+(1 row)
+
+select count(*) from test_range_spgist where ir -|- int4range(100,500);
+ count 
+-------
+     5
+(1 row)
+
 RESET enable_seqscan;
 RESET enable_indexscan;
 RESET enable_bitmapscan;

src/test/regress/expected/sanity_check.out

@@ -157,6 +157,7 @@ SELECT relname, relhasindex
  tenk2                   | t
  test_range_excl         | t
  test_range_gist         | t
+ test_range_spgist       | t
  test_tsvector           | f
  text_tbl                | f
  time_tbl                | f
@@ -165,7 +166,7 @@ SELECT relname, relhasindex
  timetz_tbl              | f
  tinterval_tbl           | f
  varchar_tbl             | f
-(154 rows)
+(155 rows)
 
 --
 -- another sanity check: every system catalog that has OIDs should have

src/test/regress/output/misc.source

@@ -675,6 +675,7 @@ SELECT user_relns() AS user_relns
  tenk2
  test_range_excl
  test_range_gist
+ test_range_spgist
  test_tsvector
  text_tbl
  time_tbl
@@ -685,7 +686,7 @@ SELECT user_relns() AS user_relns
  toyemp
  varchar_tbl
  xacttest
-(107 rows)
+(108 rows)
 
 SELECT name(equipment(hobby_construct(text 'skywalking', text 'mer')));
  name 

src/test/regress/sql/rangetypes.sql

@@ -220,6 +220,68 @@ select count(*) from test_range_gist where ir &< int4range(100,500);
 select count(*) from test_range_gist where ir &> int4range(100,500);
 select count(*) from test_range_gist where ir -|- int4range(100,500);
 
+-- test SP-GiST index that's been built incrementally
+create table test_range_spgist(ir int4range);
+create index test_range_spgist_idx on test_range_spgist using spgist (ir);
+
+insert into test_range_spgist select int4range(g, g+10) from generate_series(1,2000) g;
+insert into test_range_spgist select 'empty'::int4range from generate_series(1,500) g;
+insert into test_range_spgist select int4range(g, g+10000) from generate_series(1,1000) g;
+insert into test_range_spgist select 'empty'::int4range from generate_series(1,500) g;
+insert into test_range_spgist select int4range(NULL,g*10,'(]') from generate_series(1,100) g;
+insert into test_range_spgist select int4range(g*10,NULL,'(]') from generate_series(1,100) g;
+insert into test_range_spgist select int4range(g, g+10) from generate_series(1,2000) g;
+
+-- first, verify non-indexed results
+SET enable_seqscan    = t;
+SET enable_indexscan  = f;
+SET enable_bitmapscan = f;
+
+select count(*) from test_range_spgist where ir @> 'empty'::int4range;
+select count(*) from test_range_spgist where ir = int4range(10,20);
+select count(*) from test_range_spgist where ir @> 10;
+select count(*) from test_range_spgist where ir @> int4range(10,20);
+select count(*) from test_range_spgist where ir && int4range(10,20);
+select count(*) from test_range_spgist where ir <@ int4range(10,50);
+select count(*) from test_range_spgist where ir << int4range(100,500);
+select count(*) from test_range_spgist where ir >> int4range(100,500);
+select count(*) from test_range_spgist where ir &< int4range(100,500);
+select count(*) from test_range_spgist where ir &> int4range(100,500);
+select count(*) from test_range_spgist where ir -|- int4range(100,500);
+
+-- now check same queries using index
+SET enable_seqscan    = f;
+SET enable_indexscan  = t;
+SET enable_bitmapscan = f;
+
+select count(*) from test_range_spgist where ir @> 'empty'::int4range;
+select count(*) from test_range_spgist where ir = int4range(10,20);
+select count(*) from test_range_spgist where ir @> 10;
+select count(*) from test_range_spgist where ir @> int4range(10,20);
+select count(*) from test_range_spgist where ir && int4range(10,20);
+select count(*) from test_range_spgist where ir <@ int4range(10,50);
+select count(*) from test_range_spgist where ir << int4range(100,500);
+select count(*) from test_range_spgist where ir >> int4range(100,500);
+select count(*) from test_range_spgist where ir &< int4range(100,500);
+select count(*) from test_range_spgist where ir &> int4range(100,500);
+select count(*) from test_range_spgist where ir -|- int4range(100,500);
+
+-- now check same queries using a bulk-loaded index
+drop index test_range_spgist_idx;
+create index test_range_spgist_idx on test_range_spgist using spgist (ir);
+
+select count(*) from test_range_spgist where ir @> 'empty'::int4range;
+select count(*) from test_range_spgist where ir = int4range(10,20);
+select count(*) from test_range_spgist where ir @> 10;
+select count(*) from test_range_spgist where ir @> int4range(10,20);
+select count(*) from test_range_spgist where ir && int4range(10,20);
+select count(*) from test_range_spgist where ir <@ int4range(10,50);
+select count(*) from test_range_spgist where ir << int4range(100,500);
+select count(*) from test_range_spgist where ir >> int4range(100,500);
+select count(*) from test_range_spgist where ir &< int4range(100,500);
+select count(*) from test_range_spgist where ir &> int4range(100,500);
+select count(*) from test_range_spgist where ir -|- int4range(100,500);
+
 RESET enable_seqscan;
 RESET enable_indexscan;
 RESET enable_bitmapscan;