From d0836e27fb4e3163eccee51e2580fac1fac071b9 Mon Sep 17 00:00:00 2001 From: Corey Huinker Date: Thu, 24 Sep 2026 01:53:04 -0400 Subject: [PATCH v1] Fix import of range statistics for domains. WIP --- src/backend/statistics/attribute_stats.c | 59 +++++--- src/backend/statistics/extended_stats_funcs.c | 56 +++++--- src/test/regress/expected/stats_import.out | 130 +++++++++++++++++- src/test/regress/sql/stats_import.sql | 109 +++++++++++++++ 4 files changed, 314 insertions(+), 40 deletions(-) diff --git a/src/backend/statistics/attribute_stats.c b/src/backend/statistics/attribute_stats.c index c35892ce6d0..2539e097ac3 100644 --- a/src/backend/statistics/attribute_stats.c +++ b/src/backend/statistics/attribute_stats.c @@ -229,6 +229,8 @@ attribute_statistics_update_internal(Oid reloid, Oid elemtypid = InvalidOid; Oid elem_eq_opr = InvalidOid; + Oid bounds_typid = InvalidOid; + FmgrInfo array_in_fn; bool do_mcv = !PG_ARGISNULL(MOST_COMMON_FREQS_ARG) && @@ -333,18 +335,47 @@ attribute_statistics_update_internal(Oid reloid, } /* only range types can have range stats */ - if ((do_range_length_histogram || do_bounds_histogram) && - !(atttyptype == TYPTYPE_RANGE || atttyptype == TYPTYPE_MULTIRANGE)) + if (do_range_length_histogram || do_bounds_histogram) { - ereport(WARNING, - (errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("column \"%s\" is not a range type", attname), - errdetail("Cannot set %s or %s.", - "STATISTIC_KIND_RANGE_LENGTH_HISTOGRAM", "STATISTIC_KIND_BOUNDS_HISTOGRAM"))); + char bounds_typtype = atttyptype; - do_bounds_histogram = false; - do_range_length_histogram = false; - result = false; + bounds_typid = atttypid; + + /* + * If attribute type is a domain, step down to the base type, which + * should be the expected range or multirange type. + */ + if (bounds_typtype == TYPTYPE_DOMAIN) + { + bounds_typid = getBaseType(bounds_typid); + bounds_typtype = get_typtype(bounds_typid); + } + + switch (bounds_typtype) + { + case TYPTYPE_RANGE: + /* Yes, it can have range stats */ + break; + case TYPTYPE_MULTIRANGE: + + /* + * Yes, but we need to step down to the range type, as is done + * by multirange_typanalyze(). + */ + bounds_typid = get_multirange_range(bounds_typid); + break; + default: + ereport(WARNING, + errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("column \"%s\" is not a range type", attname), + errdetail("Cannot set %s or %s.", + "STATISTIC_KIND_RANGE_LENGTH_HISTOGRAM", + "STATISTIC_KIND_BOUNDS_HISTOGRAM")); + + do_bounds_histogram = false; + do_range_length_histogram = false; + result = false; + } } fmgr_info(F_ARRAY_IN, &array_in_fn); @@ -498,14 +529,6 @@ attribute_statistics_update_internal(Oid reloid, { bool converted = false; Datum stavalues; - Oid bounds_typid = atttypid; - - /* - * If it's a multirange, step down to the range type, as is done by - * multirange_typanalyze(). - */ - if (type_is_multirange(atttypid)) - bounds_typid = get_multirange_range(atttypid); stavalues = statatt_build_stavalues("range_bounds_histogram", &array_in_fn, diff --git a/src/backend/statistics/extended_stats_funcs.c b/src/backend/statistics/extended_stats_funcs.c index cb965fdb868..b62b10a0dea 100644 --- a/src/backend/statistics/extended_stats_funcs.c +++ b/src/backend/statistics/extended_stats_funcs.c @@ -1125,6 +1125,7 @@ import_pg_statistic(Relation pgsd, JsonbContainer *cont, Oid elemeqopr = InvalidOid; bool found[NUM_ATTRIBUTE_STATS_ELEMS] = {0}; JsonbValue val[NUM_ATTRIBUTE_STATS_ELEMS] = {0}; + Oid bounds_typid = InvalidOid; /* Assume the worst by default. */ *pg_statistic_ok = false; @@ -1253,24 +1254,45 @@ import_pg_statistic(Relation pgsd, JsonbContainer *cont, /* * These three fields can only be set if dealing with a range or - * multi-range type. + * multi-range type, or a domain of either. */ if (found[RANGE_LENGTH_HISTOGRAM_ELEM] || found[RANGE_EMPTY_FRAC_ELEM] || found[RANGE_BOUNDS_HISTOGRAM_ELEM]) { - if (typcache->typtype != TYPTYPE_RANGE && - typcache->typtype != TYPTYPE_MULTIRANGE) + char bounds_typtype = typcache->typtype; + + bounds_typid = typid; + + if (bounds_typtype == TYPTYPE_DOMAIN) { - ereport(WARNING, - errcode(ERRCODE_INVALID_PARAMETER_VALUE), - errmsg("could not parse \"%s\": invalid data in expression %d", - argname, exprnum), - errhint("\"%s\", \"%s\", and \"%s\" can only be set for a range type.", - extexprargname[RANGE_LENGTH_HISTOGRAM_ELEM], - extexprargname[RANGE_EMPTY_FRAC_ELEM], - extexprargname[RANGE_BOUNDS_HISTOGRAM_ELEM])); - goto pg_statistic_error; + bounds_typid = getBaseType(typid); + bounds_typtype = get_typtype(bounds_typid); + } + + switch (bounds_typtype) + { + case TYPTYPE_RANGE: + bounds_typid = typid; + break; + case TYPTYPE_MULTIRANGE: + + /* + * If it's a multirange, step down to the range type, as is + * done by multirange_typanalyze(). + */ + bounds_typid = get_multirange_range(bounds_typid); + break; + default: + ereport(WARNING, + errcode(ERRCODE_INVALID_PARAMETER_VALUE), + errmsg("could not parse \"%s\": invalid data in expression %d", + argname, exprnum), + errhint("\"%s\", \"%s\", and \"%s\" can only be set for a range type.", + extexprargname[RANGE_LENGTH_HISTOGRAM_ELEM], + extexprargname[RANGE_EMPTY_FRAC_ELEM], + extexprargname[RANGE_BOUNDS_HISTOGRAM_ELEM])); + goto pg_statistic_error; } } @@ -1476,18 +1498,10 @@ import_pg_statistic(Relation pgsd, JsonbContainer *cont, Datum stavalues; bool val_ok = false; char *s; - Oid rtypid = typid; - - /* - * If it's a multirange, step down to the range type, as is done by - * multirange_typanalyze(). - */ - if (type_is_multirange(typid)) - rtypid = get_multirange_range(typid); s = jbv_string_get_cstr(&val[RANGE_BOUNDS_HISTOGRAM_ELEM]); - stavalues = array_in_safe(array_in_fn, s, rtypid, typmod, exprnum, + stavalues = array_in_safe(array_in_fn, s, bounds_typid, typmod, exprnum, extexprargname[RANGE_BOUNDS_HISTOGRAM_ELEM], &val_ok); diff --git a/src/test/regress/expected/stats_import.out b/src/test/regress/expected/stats_import.out index 4ce176c2667..f615ec94ed1 100644 --- a/src/test/regress/expected/stats_import.out +++ b/src/test/regress/expected/stats_import.out @@ -3827,8 +3827,133 @@ SELECT COUNT(*) FROM stats_import.test_range_expr_null 19 (1 row) +-- BUG #19715 +CREATE DOMAIN stats_import.restore_stats_mr AS int4multirange; +CREATE TABLE stats_import.mr_domain (u integer, v stats_import.restore_stats_mr); +CREATE TABLE stats_import.mr_domain_clone (u integer, v stats_import.restore_stats_mr); +-- Create statistics that force an expression +CREATE STATISTICS stats_import.mr_domain_stat +ON u, (stats_import.restore_stats_mr(v + '{[-10,-5)}'::stats_import.restore_stats_mr)) +FROM stats_import.mr_domain; +CREATE STATISTICS stats_import.mr_domain_stat_clone +ON u, (stats_import.restore_stats_mr(v + '{[-10,-5)}'::stats_import.restore_stats_mr)) +FROM stats_import.mr_domain_clone; +INSERT INTO stats_import.mr_domain VALUES + (1, '{[1,3)}'), (2, '{[5,9)}'), (3, '{[11,15)}'); +ANALYZE stats_import.mr_domain; +-- Confirm both table and expression index have rows +SELECT COUNT(*) +FROM pg_stats +WHERE schemaname = 'stats_import' +AND tablename = 'mr_domain' +AND inherited = false; + count +------- + 2 +(1 row) + +SELECT COUNT(*) +FROM pg_stats_ext_exprs AS e +WHERE e.statistics_schemaname = 'stats_import' +AND e.statistics_name = 'mr_domain_stat'; + count +------- + 1 +(1 row) + +-- +-- Copy stats from test to mr_domain to mr_domain_clone +-- +SELECT s.schemaname, s.tablename, s.attname, s.inherited, r.* +FROM pg_catalog.pg_stats AS s +CROSS JOIN LATERAL + pg_catalog.pg_restore_attribute_stats( + 'schemaname', 'stats_import', + 'relname', 'mr_domain_clone', + 'attname', s.attname::text, + 'inherited', s.inherited, + 'version', 150000, + 'null_frac', s.null_frac, + 'avg_width', s.avg_width, + 'n_distinct', s.n_distinct, + 'most_common_vals', s.most_common_vals::text, + 'most_common_freqs', s.most_common_freqs, + 'histogram_bounds', s.histogram_bounds::text, + 'correlation', s.correlation, + 'most_common_elems', s.most_common_elems::text, + 'most_common_elem_freqs', s.most_common_elem_freqs, + 'elem_count_histogram', s.elem_count_histogram, + 'range_bounds_histogram', s.range_bounds_histogram::text, + 'range_empty_frac', s.range_empty_frac, + 'range_length_histogram', s.range_length_histogram::text) AS r +WHERE s.schemaname = 'stats_import' +AND s.tablename IN ('mr_domain') +ORDER BY s.tablename, s.attname, s.inherited; + schemaname | tablename | attname | inherited | r +--------------+-----------+---------+-----------+--- + stats_import | mr_domain | u | f | t + stats_import | mr_domain | v | f | t +(2 rows) + +SELECT relname, (stats).* +FROM stats_import.pg_statistic_get_difference('mr_domain', 'mr_domain_clone') +\gx +(0 rows) + +-- Copy stats from mr_domain_stat to mr_domain_stat_clone +SELECT e.statistics_name, + pg_catalog.pg_restore_extended_stats( + 'schemaname', e.statistics_schemaname::text, + 'relname', 'mr_domain_clone', + 'statistics_schemaname', e.statistics_schemaname::text, + 'statistics_name', 'mr_domain_stat_clone', + 'inherited', e.inherited, + 'n_distinct', e.n_distinct, + 'dependencies', e.dependencies, + 'most_common_vals', e.most_common_vals, + 'most_common_freqs', e.most_common_freqs, + 'most_common_base_freqs', e.most_common_base_freqs, + 'exprs', x.exprs) +FROM pg_stats_ext AS e +CROSS JOIN LATERAL ( + SELECT jsonb_agg(jsonb_strip_nulls(jsonb_build_object( + 'null_frac', ee.null_frac::text, + 'avg_width', ee.avg_width::text, + 'n_distinct', ee.n_distinct::text, + 'most_common_vals', ee.most_common_vals::text, + 'most_common_freqs', ee.most_common_freqs::text, + 'histogram_bounds', ee.histogram_bounds::text, + 'correlation', ee.correlation::text, + 'most_common_elems', ee.most_common_elems::text, + 'most_common_elem_freqs', ee.most_common_elem_freqs::text, + 'elem_count_histogram', ee.elem_count_histogram::text, + 'range_length_histogram', ee.range_length_histogram::text, + 'range_empty_frac', ee.range_empty_frac::text, + 'range_bounds_histogram', ee.range_bounds_histogram::text))) + FROM pg_stats_ext_exprs AS ee + WHERE ee.statistics_schemaname = e.statistics_schemaname AND + ee.statistics_name = e.statistics_name AND + ee.inherited = e.inherited + ) AS x(exprs) +WHERE e.statistics_schemaname = 'stats_import' +AND e.statistics_name = 'mr_domain_stat'; + statistics_name | pg_restore_extended_stats +-----------------+--------------------------- + mr_domain_stat | t +(1 row) + +SELECT statname, (stats).* +FROM stats_import.pg_stats_ext_get_difference('mr_domain_stat', 'mr_domain_stat_clone') +\gx +(0 rows) + +SELECT statname, (stats).* +FROM stats_import.pg_stats_ext_exprs_get_difference('mr_domain_stat', 'mr_domain_stat_clone') +\gx +(0 rows) + DROP SCHEMA stats_import CASCADE; -NOTICE: drop cascades to 19 other objects +NOTICE: drop cascades to 22 other objects DETAIL: drop cascades to view stats_import.pg_stats_stable drop cascades to view stats_import.pg_statistic_flat_t drop cascades to function stats_import.pg_statistic_flat(text) @@ -3848,3 +3973,6 @@ drop cascades to view stats_import.testview drop cascades to table stats_import.test_clone drop cascades to table stats_import.test_mr_clone drop cascades to table stats_import.test_range_expr_null +drop cascades to type stats_import.restore_stats_mr +drop cascades to table stats_import.mr_domain +drop cascades to table stats_import.mr_domain_clone diff --git a/src/test/regress/sql/stats_import.sql b/src/test/regress/sql/stats_import.sql index 748c9a2e000..74012ff5678 100644 --- a/src/test/regress/sql/stats_import.sql +++ b/src/test/regress/sql/stats_import.sql @@ -2647,4 +2647,113 @@ SELECT * FROM stats_import.test_range_expr_null SELECT COUNT(*) FROM stats_import.test_range_expr_null WHERE (rng * int4range(50, 150)) && '[60,70)'::int4range; +-- BUG #19715 +CREATE DOMAIN stats_import.restore_stats_mr AS int4multirange; +CREATE TABLE stats_import.mr_domain (u integer, v stats_import.restore_stats_mr); +CREATE TABLE stats_import.mr_domain_clone (u integer, v stats_import.restore_stats_mr); + +-- Create statistics that force an expression +CREATE STATISTICS stats_import.mr_domain_stat +ON u, (stats_import.restore_stats_mr(v + '{[-10,-5)}'::stats_import.restore_stats_mr)) +FROM stats_import.mr_domain; +CREATE STATISTICS stats_import.mr_domain_stat_clone +ON u, (stats_import.restore_stats_mr(v + '{[-10,-5)}'::stats_import.restore_stats_mr)) +FROM stats_import.mr_domain_clone; + +INSERT INTO stats_import.mr_domain VALUES + (1, '{[1,3)}'), (2, '{[5,9)}'), (3, '{[11,15)}'); +ANALYZE stats_import.mr_domain; + +-- Confirm both table and expression index have rows +SELECT COUNT(*) +FROM pg_stats +WHERE schemaname = 'stats_import' +AND tablename = 'mr_domain' +AND inherited = false; + +SELECT COUNT(*) +FROM pg_stats_ext_exprs AS e +WHERE e.statistics_schemaname = 'stats_import' +AND e.statistics_name = 'mr_domain_stat'; + + +-- +-- Copy stats from test to mr_domain to mr_domain_clone +-- +SELECT s.schemaname, s.tablename, s.attname, s.inherited, r.* +FROM pg_catalog.pg_stats AS s +CROSS JOIN LATERAL + pg_catalog.pg_restore_attribute_stats( + 'schemaname', 'stats_import', + 'relname', 'mr_domain_clone', + 'attname', s.attname::text, + 'inherited', s.inherited, + 'version', 150000, + 'null_frac', s.null_frac, + 'avg_width', s.avg_width, + 'n_distinct', s.n_distinct, + 'most_common_vals', s.most_common_vals::text, + 'most_common_freqs', s.most_common_freqs, + 'histogram_bounds', s.histogram_bounds::text, + 'correlation', s.correlation, + 'most_common_elems', s.most_common_elems::text, + 'most_common_elem_freqs', s.most_common_elem_freqs, + 'elem_count_histogram', s.elem_count_histogram, + 'range_bounds_histogram', s.range_bounds_histogram::text, + 'range_empty_frac', s.range_empty_frac, + 'range_length_histogram', s.range_length_histogram::text) AS r +WHERE s.schemaname = 'stats_import' +AND s.tablename IN ('mr_domain') +ORDER BY s.tablename, s.attname, s.inherited; + +SELECT relname, (stats).* +FROM stats_import.pg_statistic_get_difference('mr_domain', 'mr_domain_clone') +\gx + +-- Copy stats from mr_domain_stat to mr_domain_stat_clone +SELECT e.statistics_name, + pg_catalog.pg_restore_extended_stats( + 'schemaname', e.statistics_schemaname::text, + 'relname', 'mr_domain_clone', + 'statistics_schemaname', e.statistics_schemaname::text, + 'statistics_name', 'mr_domain_stat_clone', + 'inherited', e.inherited, + 'n_distinct', e.n_distinct, + 'dependencies', e.dependencies, + 'most_common_vals', e.most_common_vals, + 'most_common_freqs', e.most_common_freqs, + 'most_common_base_freqs', e.most_common_base_freqs, + 'exprs', x.exprs) +FROM pg_stats_ext AS e +CROSS JOIN LATERAL ( + SELECT jsonb_agg(jsonb_strip_nulls(jsonb_build_object( + 'null_frac', ee.null_frac::text, + 'avg_width', ee.avg_width::text, + 'n_distinct', ee.n_distinct::text, + 'most_common_vals', ee.most_common_vals::text, + 'most_common_freqs', ee.most_common_freqs::text, + 'histogram_bounds', ee.histogram_bounds::text, + 'correlation', ee.correlation::text, + 'most_common_elems', ee.most_common_elems::text, + 'most_common_elem_freqs', ee.most_common_elem_freqs::text, + 'elem_count_histogram', ee.elem_count_histogram::text, + 'range_length_histogram', ee.range_length_histogram::text, + 'range_empty_frac', ee.range_empty_frac::text, + 'range_bounds_histogram', ee.range_bounds_histogram::text))) + FROM pg_stats_ext_exprs AS ee + WHERE ee.statistics_schemaname = e.statistics_schemaname AND + ee.statistics_name = e.statistics_name AND + ee.inherited = e.inherited + ) AS x(exprs) +WHERE e.statistics_schemaname = 'stats_import' +AND e.statistics_name = 'mr_domain_stat'; + +SELECT statname, (stats).* +FROM stats_import.pg_stats_ext_get_difference('mr_domain_stat', 'mr_domain_stat_clone') +\gx + +SELECT statname, (stats).* +FROM stats_import.pg_stats_ext_exprs_get_difference('mr_domain_stat', 'mr_domain_stat_clone') +\gx + DROP SCHEMA stats_import CASCADE; base-commit: 4545cee303c257e58195e3d033c05bf38e2cd4d6 -- 2.55.0