Extended statistics on expressions

Allow defining extended statistics on expressions, not just just on
simple column references.  With this commit, expressions are supported
by all existing extended statistics kinds, improving the same types of
estimates. A simple example may look like this:

  CREATE TABLE t (a int);
  CREATE STATISTICS s ON mod(a,10), mod(a,20) FROM t;
  ANALYZE t;

The collected statistics are useful e.g. to estimate queries with those
expressions in WHERE or GROUP BY clauses:

  SELECT * FROM t WHERE mod(a,10) = 0 AND mod(a,20) = 0;

  SELECT 1 FROM t GROUP BY mod(a,10), mod(a,20);

This introduces new internal statistics kind 'e' (expressions) which is
built automatically when the statistics object definition includes any
expressions. This represents single-expression statistics, as if there
was an expression index (but without the index maintenance overhead).
The statistics is stored in pg_statistics_ext_data as an array of
composite types, which is possible thanks to 79f6a942bd.

CREATE STATISTICS allows building statistics on a single expression, in
which case in which case it's not possible to specify statistics kinds.

A new system view pg_stats_ext_exprs can be used to display expression
statistics, similarly to pg_stats and pg_stats_ext views.

ALTER TABLE ... ALTER COLUMN ... TYPE now treats indexes the same way it
treats indexes, i.e. it drops and recreates the statistics. This means
all statistics are reset, and we no longer try to preserve at least the
functional dependencies. This should not be a major issue in practice,
as the functional dependencies actually rely on per-column statistics,
which were always reset anyway.

Author: Tomas Vondra
Reviewed-by: Justin Pryzby, Dean Rasheed, Zhihong Yu
Discussion: https://postgr.es/m/ad7891d2-e90c-b446-9fe2-7419143847d7%40enterprisedb.com

1 files changed, 225 insertions, 56 deletions

diff --git a/src/backend/utils/adt/ruleutils.c b/src/backend/utils/adt/ruleutils.c
index f0de2a25c96..3de98d2333e 100644
--- a/src/backend/utils/adt/ruleutils.c
+++ b/src/backend/utils/adt/ruleutils.c
@@ -336,7 +336,8 @@ static char *pg_get_indexdef_worker(Oid indexrelid, int colno,
 									bool attrsOnly, bool keysOnly,
 									bool showTblSpc, bool inherits,
 									int prettyFlags, bool missing_ok);
-static char *pg_get_statisticsobj_worker(Oid statextid, bool missing_ok);
+static char *pg_get_statisticsobj_worker(Oid statextid, bool columns_only,
+										 bool missing_ok);
 static char *pg_get_partkeydef_worker(Oid relid, int prettyFlags,
 									  bool attrsOnly, bool missing_ok);
 static char *pg_get_constraintdef_worker(Oid constraintId, bool fullCommand,
@@ -1507,7 +1508,36 @@ pg_get_statisticsobjdef(PG_FUNCTION_ARGS)
 	Oid			statextid = PG_GETARG_OID(0);
 	char	   *res;
 
-	res = pg_get_statisticsobj_worker(statextid, true);
+	res = pg_get_statisticsobj_worker(statextid, false, true);
+
+	if (res == NULL)
+		PG_RETURN_NULL();
+
+	PG_RETURN_TEXT_P(string_to_text(res));
+}
+
+/*
+ * Internal version for use by ALTER TABLE.
+ * Includes a tablespace clause in the result.
+ * Returns a palloc'd C string; no pretty-printing.
+ */
+char *
+pg_get_statisticsobjdef_string(Oid statextid)
+{
+	return pg_get_statisticsobj_worker(statextid, false, false);
+}
+
+/*
+ * pg_get_statisticsobjdef_columns
+ *		Get columns and expressions for an extended statistics object
+ */
+Datum
+pg_get_statisticsobjdef_columns(PG_FUNCTION_ARGS)
+{
+	Oid			statextid = PG_GETARG_OID(0);
+	char	   *res;
+
+	res = pg_get_statisticsobj_worker(statextid, true, true);
 
 	if (res == NULL)
 		PG_RETURN_NULL();
@@ -1519,7 +1549,7 @@ pg_get_statisticsobjdef(PG_FUNCTION_ARGS)
  * Internal workhorse to decompile an extended statistics object.
  */
 static char *
-pg_get_statisticsobj_worker(Oid statextid, bool missing_ok)
+pg_get_statisticsobj_worker(Oid statextid, bool columns_only, bool missing_ok)
 {
 	Form_pg_statistic_ext statextrec;
 	HeapTuple	statexttup;
@@ -1534,6 +1564,11 @@ pg_get_statisticsobj_worker(Oid statextid, bool missing_ok)
 	bool		dependencies_enabled;
 	bool		mcv_enabled;
 	int			i;
+	List	   *context;
+	ListCell   *lc;
+	List	   *exprs = NIL;
+	bool		has_exprs;
+	int			ncolumns;
 
 	statexttup = SearchSysCache1(STATEXTOID, ObjectIdGetDatum(statextid));
 
@@ -1544,75 +1579,114 @@ pg_get_statisticsobj_worker(Oid statextid, bool missing_ok)
 		elog(ERROR, "cache lookup failed for statistics object %u", statextid);
 	}
 
-	statextrec = (Form_pg_statistic_ext) GETSTRUCT(statexttup);
+	/* has the statistics expressions? */
+	has_exprs = !heap_attisnull(statexttup, Anum_pg_statistic_ext_stxexprs, NULL);
 
-	initStringInfo(&buf);
-
-	nsp = get_namespace_name(statextrec->stxnamespace);
-	appendStringInfo(&buf, "CREATE STATISTICS %s",
-					 quote_qualified_identifier(nsp,
-												NameStr(statextrec->stxname)));
+	statextrec = (Form_pg_statistic_ext) GETSTRUCT(statexttup);
 
 	/*
-	 * Decode the stxkind column so that we know which stats types to print.
+	 * Get the statistics expressions, if any.  (NOTE: we do not use the
+	 * relcache versions of the expressions, because we want to display
+	 * non-const-folded expressions.)
 	 */
-	datum = SysCacheGetAttr(STATEXTOID, statexttup,
-							Anum_pg_statistic_ext_stxkind, &isnull);
-	Assert(!isnull);
-	arr = DatumGetArrayTypeP(datum);
-	if (ARR_NDIM(arr) != 1 ||
-		ARR_HASNULL(arr) ||
-		ARR_ELEMTYPE(arr) != CHAROID)
-		elog(ERROR, "stxkind is not a 1-D char array");
-	enabled = (char *) ARR_DATA_PTR(arr);
-
-	ndistinct_enabled = false;
-	dependencies_enabled = false;
-	mcv_enabled = false;
-
-	for (i = 0; i < ARR_DIMS(arr)[0]; i++)
+	if (has_exprs)
 	{
-		if (enabled[i] == STATS_EXT_NDISTINCT)
-			ndistinct_enabled = true;
-		if (enabled[i] == STATS_EXT_DEPENDENCIES)
-			dependencies_enabled = true;
-		if (enabled[i] == STATS_EXT_MCV)
-			mcv_enabled = true;
+		Datum		exprsDatum;
+		bool		isnull;
+		char	   *exprsString;
+
+		exprsDatum = SysCacheGetAttr(STATEXTOID, statexttup,
+									 Anum_pg_statistic_ext_stxexprs, &isnull);
+		Assert(!isnull);
+		exprsString = TextDatumGetCString(exprsDatum);
+		exprs = (List *) stringToNode(exprsString);
+		pfree(exprsString);
 	}
+	else
+		exprs = NIL;
 
-	/*
-	 * If any option is disabled, then we'll need to append the types clause
-	 * to show which options are enabled.  We omit the types clause on purpose
-	 * when all options are enabled, so a pg_dump/pg_restore will create all
-	 * statistics types on a newer postgres version, if the statistics had all
-	 * options enabled on the original version.
-	 */
-	if (!ndistinct_enabled || !dependencies_enabled || !mcv_enabled)
+	/* count the number of columns (attributes and expressions) */
+	ncolumns = statextrec->stxkeys.dim1 + list_length(exprs);
+
+	initStringInfo(&buf);
+
+	if (!columns_only)
 	{
-		bool		gotone = false;
+		nsp = get_namespace_name(statextrec->stxnamespace);
+		appendStringInfo(&buf, "CREATE STATISTICS %s",
+						 quote_qualified_identifier(nsp,
+													NameStr(statextrec->stxname)));
 
-		appendStringInfoString(&buf, " (");
+		/*
+		 * Decode the stxkind column so that we know which stats types to
+		 * print.
+		 */
+		datum = SysCacheGetAttr(STATEXTOID, statexttup,
+								Anum_pg_statistic_ext_stxkind, &isnull);
+		Assert(!isnull);
+		arr = DatumGetArrayTypeP(datum);
+		if (ARR_NDIM(arr) != 1 ||
+			ARR_HASNULL(arr) ||
+			ARR_ELEMTYPE(arr) != CHAROID)
+			elog(ERROR, "stxkind is not a 1-D char array");
+		enabled = (char *) ARR_DATA_PTR(arr);
 
-		if (ndistinct_enabled)
+		ndistinct_enabled = false;
+		dependencies_enabled = false;
+		mcv_enabled = false;
+
+		for (i = 0; i < ARR_DIMS(arr)[0]; i++)
 		{
-			appendStringInfoString(&buf, "ndistinct");
-			gotone = true;
+			if (enabled[i] == STATS_EXT_NDISTINCT)
+				ndistinct_enabled = true;
+			else if (enabled[i] == STATS_EXT_DEPENDENCIES)
+				dependencies_enabled = true;
+			else if (enabled[i] == STATS_EXT_MCV)
+				mcv_enabled = true;
+
+			/* ignore STATS_EXT_EXPRESSIONS (it's built automatically) */
 		}
 
-		if (dependencies_enabled)
+		/*
+		 * If any option is disabled, then we'll need to append the types
+		 * clause to show which options are enabled.  We omit the types clause
+		 * on purpose when all options are enabled, so a pg_dump/pg_restore
+		 * will create all statistics types on a newer postgres version, if
+		 * the statistics had all options enabled on the original version.
+		 *
+		 * But if the statistics is defined on just a single column, it has to
+		 * be an expression statistics. In that case we don't need to specify
+		 * kinds.
+		 */
+		if ((!ndistinct_enabled || !dependencies_enabled || !mcv_enabled) &&
+			(ncolumns > 1))
 		{
-			appendStringInfo(&buf, "%sdependencies", gotone ? ", " : "");
-			gotone = true;
-		}
+			bool		gotone = false;
 
-		if (mcv_enabled)
-			appendStringInfo(&buf, "%smcv", gotone ? ", " : "");
+			appendStringInfoString(&buf, " (");
 
-		appendStringInfoChar(&buf, ')');
-	}
+			if (ndistinct_enabled)
+			{
+				appendStringInfoString(&buf, "ndistinct");
+				gotone = true;
+			}
+
+			if (dependencies_enabled)
+			{
+				appendStringInfo(&buf, "%sdependencies", gotone ? ", " : "");
+				gotone = true;
+			}
 
-	appendStringInfoString(&buf, " ON ");
+			if (mcv_enabled)
+				appendStringInfo(&buf, "%smcv", gotone ? ", " : "");
+
+			appendStringInfoChar(&buf, ')');
+		}
+
+		appendStringInfoString(&buf, " ON ");
+	}
 
+	/* decode simple column references */
 	for (colno = 0; colno < statextrec->stxkeys.dim1; colno++)
 	{
 		AttrNumber	attnum = statextrec->stxkeys.values[colno];
@@ -1626,8 +1700,33 @@ pg_get_statisticsobj_worker(Oid statextid, bool missing_ok)
 		appendStringInfoString(&buf, quote_identifier(attname));
 	}
 
-	appendStringInfo(&buf, " FROM %s",
-					 generate_relation_name(statextrec->stxrelid, NIL));
+	context = deparse_context_for(get_relation_name(statextrec->stxrelid),
+								  statextrec->stxrelid);
+
+	foreach(lc, exprs)
+	{
+		Node	   *expr = (Node *) lfirst(lc);
+		char	   *str;
+		int			prettyFlags = PRETTYFLAG_INDENT;
+
+		str = deparse_expression_pretty(expr, context, false, false,
+										prettyFlags, 0);
+
+		if (colno > 0)
+			appendStringInfoString(&buf, ", ");
+
+		/* Need parens if it's not a bare function call */
+		if (looks_like_function(expr))
+			appendStringInfoString(&buf, str);
+		else
+			appendStringInfo(&buf, "(%s)", str);
+
+		colno++;
+	}
+
+	if (!columns_only)
+		appendStringInfo(&buf, " FROM %s",
+						 generate_relation_name(statextrec->stxrelid, NIL));
 
 	ReleaseSysCache(statexttup);
 
@@ -1635,6 +1734,76 @@ pg_get_statisticsobj_worker(Oid statextid, bool missing_ok)
 }
 
 /*
+ * Generate text array of expressions for statistics object.
+ */
+Datum
+pg_get_statisticsobjdef_expressions(PG_FUNCTION_ARGS)
+{
+	Oid			statextid = PG_GETARG_OID(0);
+	Form_pg_statistic_ext statextrec;
+	HeapTuple	statexttup;
+	Datum		datum;
+	bool		isnull;
+	List	   *context;
+	ListCell   *lc;
+	List	   *exprs = NIL;
+	bool		has_exprs;
+	char	   *tmp;
+	ArrayBuildState *astate = NULL;
+
+	statexttup = SearchSysCache1(STATEXTOID, ObjectIdGetDatum(statextid));
+
+	if (!HeapTupleIsValid(statexttup))
+		elog(ERROR, "cache lookup failed for statistics object %u", statextid);
+
+	/* has the statistics expressions? */
+	has_exprs = !heap_attisnull(statexttup, Anum_pg_statistic_ext_stxexprs, NULL);
+
+	/* no expressions? we're done */
+	if (!has_exprs)
+	{
+		ReleaseSysCache(statexttup);
+		PG_RETURN_NULL();
+	}
+
+	statextrec = (Form_pg_statistic_ext) GETSTRUCT(statexttup);
+
+	/*
+	 * Get the statistics expressions, and deparse them into text values.
+	 */
+	datum = SysCacheGetAttr(STATEXTOID, statexttup,
+							Anum_pg_statistic_ext_stxexprs, &isnull);
+
+	Assert(!isnull);
+	tmp = TextDatumGetCString(datum);
+	exprs = (List *) stringToNode(tmp);
+	pfree(tmp);
+
+	context = deparse_context_for(get_relation_name(statextrec->stxrelid),
+								  statextrec->stxrelid);
+
+	foreach(lc, exprs)
+	{
+		Node	   *expr = (Node *) lfirst(lc);
+		char	   *str;
+		int			prettyFlags = PRETTYFLAG_INDENT;
+
+		str = deparse_expression_pretty(expr, context, false, false,
+										prettyFlags, 0);
+
+		astate = accumArrayResult(astate,
+								  PointerGetDatum(cstring_to_text(str)),
+								  false,
+								  TEXTOID,
+								  CurrentMemoryContext);
+	}
+
+	ReleaseSysCache(statexttup);
+
+	PG_RETURN_DATUM(makeArrayResult(astate, CurrentMemoryContext));
+}
+
+/*
  * pg_get_partkeydef
  *
  * Returns the partition key specification, ie, the following: