V5 patch. I've added more tests with different bytea sizes
--
With best regards,
Marat Bukharov
чт, 4 июл. 2024 г. в 15:29, Aleksander Alekseev <aleksan...@timescale.com>:
>
> Hi Marat,
>
> > V4 path with fixed usage PG_GETARG_BYTEA_PP instead of PG_GETARG_TEXT_PP
>
> Thanks for the patch.
>
> Please add it to the nearest open commitfest [1].
>
> ```
> +select min(v) from bytea_test_table;
> + min
> +------
> + \xaa
> +(1 row)
> +
> +select max(v) from bytea_test_table;
> + max
> +------
> + \xff
> +(1 row)
> ```
>
> If I understand correctly, all the v's are of the same size. If this
> is the case you should add more test cases.
>
> [1]: https://commitfest.postgresql.org/
>
> --
> Best regards,
> Aleksander Alekseev
From 3bc3786ede117442b06d6cbe36a7b015d76a7cf4 Mon Sep 17 00:00:00 2001
From: Marat Bukharov <mara...@yandex-team.ru>
Date: Wed, 24 Jul 2024 17:37:31 +0300
Subject: [PATCH v5] add bytea agg funcs
---
doc/src/sgml/func.sgml | 4 +--
src/backend/utils/adt/varlena.c | 38 ++++++++++++++++++++++++
src/include/catalog/pg_aggregate.dat | 6 ++++
src/include/catalog/pg_proc.dat | 13 ++++++++
src/test/regress/expected/aggregates.out | 28 ++++++++++++++++-
src/test/regress/expected/opr_sanity.out | 2 ++
src/test/regress/sql/aggregates.sql | 11 ++++++-
7 files changed, 98 insertions(+), 4 deletions(-)
diff --git a/doc/src/sgml/func.sgml b/doc/src/sgml/func.sgml
index f1f22a1960..891f7a4259 100644
--- a/doc/src/sgml/func.sgml
+++ b/doc/src/sgml/func.sgml
@@ -21976,7 +21976,7 @@ SELECT NULLIF(value, '(none)') ...
<para>
Computes the maximum of the non-null input
values. Available for any numeric, string, date/time, or enum type,
- as well as <type>inet</type>, <type>interval</type>,
+ as well as <type>bytea</type>, <type>inet</type>, <type>interval</type>,
<type>money</type>, <type>oid</type>, <type>pg_lsn</type>,
<type>tid</type>, <type>xid8</type>,
and arrays of any of these types.
@@ -21995,7 +21995,7 @@ SELECT NULLIF(value, '(none)') ...
<para>
Computes the minimum of the non-null input
values. Available for any numeric, string, date/time, or enum type,
- as well as <type>inet</type>, <type>interval</type>,
+ as well as <type>bytea</type>, <type>inet</type>, <type>interval</type>,
<type>money</type>, <type>oid</type>, <type>pg_lsn</type>,
<type>tid</type>, <type>xid8</type>,
and arrays of any of these types.
diff --git a/src/backend/utils/adt/varlena.c b/src/backend/utils/adt/varlena.c
index d2e2e9bbba..e80c789442 100644
--- a/src/backend/utils/adt/varlena.c
+++ b/src/backend/utils/adt/varlena.c
@@ -3956,6 +3956,44 @@ byteacmp(PG_FUNCTION_ARGS)
PG_RETURN_INT32(cmp);
}
+Datum
+bytea_larger(PG_FUNCTION_ARGS)
+{
+ bytea *arg1 = PG_GETARG_BYTEA_PP(0);
+ bytea *arg2 = PG_GETARG_BYTEA_PP(1);
+ bytea *result;
+ int len1,
+ len2;
+ int cmp;
+
+ len1 = VARSIZE_ANY_EXHDR(arg1);
+ len2 = VARSIZE_ANY_EXHDR(arg2);
+
+ cmp = memcmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), Min(len1, len2));
+ result = ((cmp > 0) || ((cmp == 0) && (len1 > len2)) ? arg1 : arg2);
+
+ PG_RETURN_BYTEA_P(result);
+}
+
+Datum
+bytea_smaller(PG_FUNCTION_ARGS)
+{
+ bytea *arg1 = PG_GETARG_BYTEA_PP(0);
+ bytea *arg2 = PG_GETARG_BYTEA_PP(1);
+ bytea *result;
+ int len1,
+ len2;
+ int cmp;
+
+ len1 = VARSIZE_ANY_EXHDR(arg1);
+ len2 = VARSIZE_ANY_EXHDR(arg2);
+
+ cmp = memcmp(VARDATA_ANY(arg1), VARDATA_ANY(arg2), Min(len1, len2));
+ result = ((cmp < 0) || ((cmp == 0) && (len1 < len2)) ? arg1 : arg2);
+
+ PG_RETURN_BYTEA_P(result);
+}
+
Datum
bytea_sortsupport(PG_FUNCTION_ARGS)
{
diff --git a/src/include/catalog/pg_aggregate.dat b/src/include/catalog/pg_aggregate.dat
index 5f13532abc..970d9a70fd 100644
--- a/src/include/catalog/pg_aggregate.dat
+++ b/src/include/catalog/pg_aggregate.dat
@@ -158,6 +158,9 @@
{ aggfnoid => 'max(xid8)', aggtransfn => 'xid8_larger',
aggcombinefn => 'xid8_larger', aggsortop => '>(xid8,xid8)',
aggtranstype => 'xid8' },
+{ aggfnoid => 'max(bytea)', aggtransfn => 'bytea_larger',
+ aggcombinefn => 'bytea_larger', aggsortop => '>(bytea,bytea)',
+ aggtranstype => 'bytea' },
# min
{ aggfnoid => 'min(int8)', aggtransfn => 'int8smaller',
@@ -226,6 +229,9 @@
{ aggfnoid => 'min(xid8)', aggtransfn => 'xid8_smaller',
aggcombinefn => 'xid8_smaller', aggsortop => '<(xid8,xid8)',
aggtranstype => 'xid8' },
+{ aggfnoid => 'min(bytea)', aggtransfn => 'bytea_smaller',
+ aggcombinefn => 'bytea_smaller', aggsortop => '<(bytea,bytea)',
+ aggtranstype => 'bytea' },
# count
{ aggfnoid => 'count(any)', aggtransfn => 'int8inc_any',
diff --git a/src/include/catalog/pg_proc.dat b/src/include/catalog/pg_proc.dat
index d4ac578ae6..f16f17ef3a 100644
--- a/src/include/catalog/pg_proc.dat
+++ b/src/include/catalog/pg_proc.dat
@@ -1278,6 +1278,13 @@
proname => 'text_smaller', proleakproof => 't', prorettype => 'text',
proargtypes => 'text text', prosrc => 'text_smaller' },
+{ oid => '6347', descr => 'larger of two',
+ proname => 'bytea_larger', proleakproof => 't', prorettype => 'bytea',
+ proargtypes => 'bytea bytea', prosrc => 'bytea_larger' },
+{ oid => '6348', descr => 'smaller of two',
+ proname => 'bytea_smaller', proleakproof => 't', prorettype => 'bytea',
+ proargtypes => 'bytea bytea', prosrc => 'bytea_smaller' },
+
{ oid => '460', descr => 'I/O',
proname => 'int8in', prorettype => 'int8', proargtypes => 'cstring',
prosrc => 'int8in' },
@@ -6764,6 +6771,9 @@
{ oid => '5099', descr => 'maximum value of all xid8 input values',
proname => 'max', prokind => 'a', proisstrict => 'f', prorettype => 'xid8',
proargtypes => 'xid8', prosrc => 'aggregate_dummy' },
+{ oid => '6349', descr => 'maximum value of all bytea input values',
+ proname => 'max', prokind => 'a', proisstrict => 'f', prorettype => 'bytea',
+ proargtypes => 'bytea', prosrc => 'aggregate_dummy' },
{ oid => '2131', descr => 'minimum value of all bigint input values',
proname => 'min', prokind => 'a', proisstrict => 'f', prorettype => 'int8',
@@ -6834,6 +6844,9 @@
{ oid => '5100', descr => 'minimum value of all xid8 input values',
proname => 'min', prokind => 'a', proisstrict => 'f', prorettype => 'xid8',
proargtypes => 'xid8', prosrc => 'aggregate_dummy' },
+{ oid => '6350', descr => 'minimum value of all bytea input values',
+ proname => 'min', prokind => 'a', proisstrict => 'f', prorettype => 'bytea',
+ proargtypes => 'bytea', prosrc => 'aggregate_dummy' },
# count has two forms: count(any) and count(*)
{ oid => '2147',
diff --git a/src/test/regress/expected/aggregates.out b/src/test/regress/expected/aggregates.out
index 1c1ca7573a..69d91df779 100644
--- a/src/test/regress/expected/aggregates.out
+++ b/src/test/regress/expected/aggregates.out
@@ -1925,7 +1925,7 @@ select string_agg(distinct f1::text, ',' order by f1::text) from varchar_tbl; -
a,ab,abcd
(1 row)
--- string_agg bytea tests
+-- string_agg, min, max bytea tests
create table bytea_test_table(v bytea);
select string_agg(v, '') from bytea_test_table;
string_agg
@@ -1959,6 +1959,32 @@ select string_agg(v, decode('ee', 'hex')) from bytea_test_table;
\xffeeaa
(1 row)
+select min(v) from bytea_test_table;
+ min
+------
+ \xaa
+(1 row)
+
+select max(v) from bytea_test_table;
+ max
+------
+ \xff
+(1 row)
+
+insert into bytea_test_table values(decode('ffff','hex'));
+insert into bytea_test_table values(decode('aaaa','hex'));
+select min(v) from bytea_test_table;
+ min
+------
+ \xaa
+(1 row)
+
+select max(v) from bytea_test_table;
+ max
+--------
+ \xffff
+(1 row)
+
drop table bytea_test_table;
-- Test parallel string_agg and array_agg
create table pagg_test (x int, y int) with (autovacuum_enabled = off);
diff --git a/src/test/regress/expected/opr_sanity.out b/src/test/regress/expected/opr_sanity.out
index 9d047b21b8..087e349894 100644
--- a/src/test/regress/expected/opr_sanity.out
+++ b/src/test/regress/expected/opr_sanity.out
@@ -874,6 +874,8 @@ xid8ne(xid8,xid8)
xid8cmp(xid8,xid8)
uuid_extract_timestamp(uuid)
uuid_extract_version(uuid)
+bytea_larger(bytea,bytea)
+bytea_smaller(bytea,bytea)
-- restore normal output mode
\a\t
-- List of functions used by libpq's fe-lobj.c
diff --git a/src/test/regress/sql/aggregates.sql b/src/test/regress/sql/aggregates.sql
index 1a18ca3d8f..935e7360c6 100644
--- a/src/test/regress/sql/aggregates.sql
+++ b/src/test/regress/sql/aggregates.sql
@@ -741,7 +741,7 @@ select string_agg(distinct f1::text, ',' order by f1) from varchar_tbl; -- not
select string_agg(distinct f1, ',' order by f1::text) from varchar_tbl; -- not ok
select string_agg(distinct f1::text, ',' order by f1::text) from varchar_tbl; -- ok
--- string_agg bytea tests
+-- string_agg, min, max bytea tests
create table bytea_test_table(v bytea);
select string_agg(v, '') from bytea_test_table;
@@ -756,6 +756,15 @@ select string_agg(v, '') from bytea_test_table;
select string_agg(v, NULL) from bytea_test_table;
select string_agg(v, decode('ee', 'hex')) from bytea_test_table;
+select min(v) from bytea_test_table;
+select max(v) from bytea_test_table;
+
+insert into bytea_test_table values(decode('ffff','hex'));
+insert into bytea_test_table values(decode('aaaa','hex'));
+
+select min(v) from bytea_test_table;
+select max(v) from bytea_test_table;
+
drop table bytea_test_table;
-- Test parallel string_agg and array_agg
--
2.44.2
