Enable hash partitioning of text arrays

hash_array_extended() needs to pass PG_GET_COLLATION() to the hash
function of the element type.  Otherwise, the hash function of a
collation-aware data type such as text will error out, since the
introduction of nondeterministic collation made hash functions require
a collation, too.

The consequence of this is that before this change, hash partitioning
using an array over text in the partition key would not work.

Reviewed-by: Heikki Linnakangas <hlinnaka@iki.fi>
Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us>
Reviewed-by: Michael Paquier <michael@paquier.xyz>
Discussion: https://www.postgresql.org/message-id/flat/32c1fdae-95c6-5dc6-058a-a90330a3b621%40enterprisedb.com

3 files changed, 77 insertions, 1 deletions

diff --git a/src/backend/utils/adt/arrayfuncs.c b/src/backend/utils/adt/arrayfuncs.c
index 392445ea032..a7ea7656c75 100644
--- a/src/backend/utils/adt/arrayfuncs.c
+++ b/src/backend/utils/adt/arrayfuncs.c
@@ -4071,7 +4071,7 @@ hash_array_extended(PG_FUNCTION_ARGS)
 	typalign = typentry->typalign;
 
 	InitFunctionCallInfoData(*locfcinfo, &typentry->hash_extended_proc_finfo, 2,
-							 InvalidOid, NULL, NULL);
+							 PG_GET_COLLATION(), NULL, NULL);
 
 	/* Loop over source data */
 	nitems = ArrayGetNItems(ndims, dims);
diff --git a/src/test/regress/expected/collate.icu.utf8.out b/src/test/regress/expected/collate.icu.utf8.out
index 16b4d9e2cdc..bc3752e9236 100644
--- a/src/test/regress/expected/collate.icu.utf8.out
+++ b/src/test/regress/expected/collate.icu.utf8.out
@@ -1212,6 +1212,30 @@ SELECT * FROM test6 WHERE b = 'äbc' COLLATE ctest_nondet;
  2 | äbc
 (2 rows)
 
+-- same with arrays
+CREATE TABLE test6a (a int, b text[]);
+INSERT INTO test6a VALUES (1, ARRAY[U&'\00E4bc']);
+INSERT INTO test6a VALUES (2, ARRAY[U&'\0061\0308bc']);
+SELECT * FROM test6a;
+ a |   b   
+---+-------
+ 1 | {äbc}
+ 2 | {äbc}
+(2 rows)
+
+SELECT * FROM test6a WHERE b = ARRAY['äbc'] COLLATE ctest_det;
+ a |   b   
+---+-------
+ 1 | {äbc}
+(1 row)
+
+SELECT * FROM test6a WHERE b = ARRAY['äbc'] COLLATE ctest_nondet;
+ a |   b   
+---+-------
+ 1 | {äbc}
+ 2 | {äbc}
+(2 rows)
+
 CREATE COLLATION case_sensitive (provider = icu, locale = '');
 CREATE COLLATION case_insensitive (provider = icu, locale = '@colStrength=secondary', deterministic = false);
 SELECT 'abc' <= 'ABC' COLLATE case_sensitive, 'abc' >= 'ABC' COLLATE case_sensitive;
@@ -1839,6 +1863,19 @@ SELECT (SELECT count(*) FROM test22_0) = (SELECT count(*) FROM test22_1);
  t
 (1 row)
 
+-- same with arrays
+CREATE TABLE test22a (a int, b text[] COLLATE case_sensitive) PARTITION BY HASH (b);
+CREATE TABLE test22a_0 PARTITION OF test22a FOR VALUES WITH (MODULUS 2, REMAINDER 0);
+CREATE TABLE test22a_1 PARTITION OF test22a FOR VALUES WITH (MODULUS 2, REMAINDER 1);
+INSERT INTO test22a VALUES (1, ARRAY['def']);
+INSERT INTO test22a VALUES (2, ARRAY['DEF']);
+-- they end up in different partitions
+SELECT (SELECT count(*) FROM test22a_0) = (SELECT count(*) FROM test22a_1);
+ ?column? 
+----------
+ t
+(1 row)
+
 CREATE TABLE test23 (a int, b text COLLATE case_insensitive) PARTITION BY HASH (b);
 CREATE TABLE test23_0 PARTITION OF test23 FOR VALUES WITH (MODULUS 2, REMAINDER 0);
 CREATE TABLE test23_1 PARTITION OF test23 FOR VALUES WITH (MODULUS 2, REMAINDER 1);
@@ -1851,6 +1888,19 @@ SELECT (SELECT count(*) FROM test23_0) <> (SELECT count(*) FROM test23_1);
  t
 (1 row)
 
+-- same with arrays
+CREATE TABLE test23a (a int, b text[] COLLATE case_insensitive) PARTITION BY HASH (b);
+CREATE TABLE test23a_0 PARTITION OF test23a FOR VALUES WITH (MODULUS 2, REMAINDER 0);
+CREATE TABLE test23a_1 PARTITION OF test23a FOR VALUES WITH (MODULUS 2, REMAINDER 1);
+INSERT INTO test23a VALUES (1, ARRAY['def']);
+INSERT INTO test23a VALUES (2, ARRAY['DEF']);
+-- they end up in the same partition (but it's platform-dependent which one)
+SELECT (SELECT count(*) FROM test23a_0) <> (SELECT count(*) FROM test23a_1);
+ ?column? 
+----------
+ t
+(1 row)
+
 CREATE TABLE test30 (a int, b char(3) COLLATE case_insensitive) PARTITION BY LIST (b);
 CREATE TABLE test30_1 PARTITION OF test30 FOR VALUES IN ('abc');
 INSERT INTO test30 VALUES (1, 'abc');
diff --git a/src/test/regress/sql/collate.icu.utf8.sql b/src/test/regress/sql/collate.icu.utf8.sql
index 4714c044d53..0de2ed8d856 100644
--- a/src/test/regress/sql/collate.icu.utf8.sql
+++ b/src/test/regress/sql/collate.icu.utf8.sql
@@ -478,6 +478,14 @@ SELECT * FROM test6;
 SELECT * FROM test6 WHERE b = 'äbc' COLLATE ctest_det;
 SELECT * FROM test6 WHERE b = 'äbc' COLLATE ctest_nondet;
 
+-- same with arrays
+CREATE TABLE test6a (a int, b text[]);
+INSERT INTO test6a VALUES (1, ARRAY[U&'\00E4bc']);
+INSERT INTO test6a VALUES (2, ARRAY[U&'\0061\0308bc']);
+SELECT * FROM test6a;
+SELECT * FROM test6a WHERE b = ARRAY['äbc'] COLLATE ctest_det;
+SELECT * FROM test6a WHERE b = ARRAY['äbc'] COLLATE ctest_nondet;
+
 CREATE COLLATION case_sensitive (provider = icu, locale = '');
 CREATE COLLATION case_insensitive (provider = icu, locale = '@colStrength=secondary', deterministic = false);
 
@@ -680,6 +688,15 @@ INSERT INTO test22 VALUES (2, 'DEF');
 -- they end up in different partitions
 SELECT (SELECT count(*) FROM test22_0) = (SELECT count(*) FROM test22_1);
 
+-- same with arrays
+CREATE TABLE test22a (a int, b text[] COLLATE case_sensitive) PARTITION BY HASH (b);
+CREATE TABLE test22a_0 PARTITION OF test22a FOR VALUES WITH (MODULUS 2, REMAINDER 0);
+CREATE TABLE test22a_1 PARTITION OF test22a FOR VALUES WITH (MODULUS 2, REMAINDER 1);
+INSERT INTO test22a VALUES (1, ARRAY['def']);
+INSERT INTO test22a VALUES (2, ARRAY['DEF']);
+-- they end up in different partitions
+SELECT (SELECT count(*) FROM test22a_0) = (SELECT count(*) FROM test22a_1);
+
 CREATE TABLE test23 (a int, b text COLLATE case_insensitive) PARTITION BY HASH (b);
 CREATE TABLE test23_0 PARTITION OF test23 FOR VALUES WITH (MODULUS 2, REMAINDER 0);
 CREATE TABLE test23_1 PARTITION OF test23 FOR VALUES WITH (MODULUS 2, REMAINDER 1);
@@ -688,6 +705,15 @@ INSERT INTO test23 VALUES (2, 'DEF');
 -- they end up in the same partition (but it's platform-dependent which one)
 SELECT (SELECT count(*) FROM test23_0) <> (SELECT count(*) FROM test23_1);
 
+-- same with arrays
+CREATE TABLE test23a (a int, b text[] COLLATE case_insensitive) PARTITION BY HASH (b);
+CREATE TABLE test23a_0 PARTITION OF test23a FOR VALUES WITH (MODULUS 2, REMAINDER 0);
+CREATE TABLE test23a_1 PARTITION OF test23a FOR VALUES WITH (MODULUS 2, REMAINDER 1);
+INSERT INTO test23a VALUES (1, ARRAY['def']);
+INSERT INTO test23a VALUES (2, ARRAY['DEF']);
+-- they end up in the same partition (but it's platform-dependent which one)
+SELECT (SELECT count(*) FROM test23a_0) <> (SELECT count(*) FROM test23a_1);
+
 CREATE TABLE test30 (a int, b char(3) COLLATE case_insensitive) PARTITION BY LIST (b);
 CREATE TABLE test30_1 PARTITION OF test30 FOR VALUES IN ('abc');
 INSERT INTO test30 VALUES (1, 'abc');