v12-0003-Add-working-input-function-for-pg_ndistinct.patch

From 27fa60cf482bcf98253ee488f34f935e2211d728 Mon Sep 17 00:00:00 2001
From: Michael Paquier <michael@paquier.xyz>
Date: Tue, 11 Nov 2025 16:47:00 +0900
Subject: [PATCH v12 3/7] Add working input function for pg_ndistinct.

This will consume the format that was established when the output
function for pg_ndistinct was recently changed.

This will be needed for importing extended statistics.
---
 src/backend/utils/adt/pg_ndistinct.c       | 595 ++++++++++++++++++++-
 src/test/regress/expected/pg_ndistinct.out | 109 ++++
 src/test/regress/parallel_schedule         |   2 +-
 src/test/regress/sql/pg_ndistinct.sql      |  34 ++
 4 files changed, 732 insertions(+), 8 deletions(-)
 create mode 100644 src/test/regress/expected/pg_ndistinct.out
 create mode 100644 src/test/regress/sql/pg_ndistinct.sql

diff --git a/src/backend/utils/adt/pg_ndistinct.c b/src/backend/utils/adt/pg_ndistinct.c
index 97efc290ef5..96eaa09b4ed 100644
--- a/src/backend/utils/adt/pg_ndistinct.c
+++ b/src/backend/utils/adt/pg_ndistinct.c
@@ -14,34 +14,615 @@
 
 #include "postgres.h"
 
+#include "common/int.h"
+#include "common/jsonapi.h"
 #include "lib/stringinfo.h"
+#include "mb/pg_wchar.h"
+#include "nodes/miscnodes.h"
 #include "statistics/extended_stats_internal.h"
 #include "statistics/statistics_format.h"
+#include "utils/builtins.h"
 #include "utils/fmgrprotos.h"
 
+typedef enum
+{
+	NDIST_EXPECT_START = 0,
+	NDIST_EXPECT_ITEM,
+	NDIST_EXPECT_KEY,
+	NDIST_EXPECT_ATTNUM_LIST,
+	NDIST_EXPECT_ATTNUM,
+	NDIST_EXPECT_NDISTINCT,
+	NDIST_EXPECT_COMPLETE
+} NDistinctSemanticState;
+
+typedef struct
+{
+	const char *str;
+	NDistinctSemanticState state;
+
+	List	   *distinct_items; /* Accumulated complete MVNDistinctItems */
+	Node	   *escontext;
+
+	bool		found_attributes;	/* Item has an attributes key */
+	bool		found_ndistinct;	/* Item has ndistinct key */
+	List	   *attnum_list;	/* Accumulated attributes attnums */
+	int64		ndistinct;
+} NDistinctParseState;
+
+/*
+ * Invoked at the start of each MVNDistinctItem.
+ *
+ * The entire JSON document shoul be one array of MVNDistinctItem objects.
+ *
+ * If we're anywhere else in the document, it's an error.
+ */
+static JsonParseErrorType
+ndistinct_object_start(void *state)
+{
+	NDistinctParseState *parse = state;
+
+	switch(parse->state)
+	{
+		case NDIST_EXPECT_ITEM:
+			/* Now we expect to see attributes/ndistinct keys */
+			parse->state = NDIST_EXPECT_KEY;
+			return JSON_SUCCESS;
+			break;
+
+		default:
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					errdetail("Expected Item object.")));
+	}
+
+	return JSON_SEM_ACTION_FAILED;
+}
+
+/*
+ * Routine to allow qsorting of AttNumbers
+ */
+static int
+attnum_compare(const void *aptr, const void *bptr)
+{
+	AttrNumber	a = *(const AttrNumber *) aptr;
+	AttrNumber	b = *(const AttrNumber *) bptr;
+
+	return pg_cmp_s16(a, b);
+}
+
+
+/*
+ * Invoked at the end of an object.
+ *
+ * Check to ensure that it was a complete MVNDistinctItem
+ *
+ */
+static JsonParseErrorType
+ndistinct_object_end(void *state)
+{
+	NDistinctParseState *parse = state;
+
+	int			natts = 0;
+	AttrNumber *attrsort;
+
+	MVNDistinctItem *item;
+
+	if (!parse->found_attributes)
+	{
+		ereturn(parse->escontext, (Datum) 0,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+				 errdetail("Item must contain \"" PG_NDISTINCT_KEY_ATTRIBUTES "\" key.")));
+		return JSON_SEM_ACTION_FAILED;
+	}
+
+	if (!parse->found_ndistinct)
+	{
+		ereturn(parse->escontext, (Datum) 0,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+				 errdetail("Item must contain \"" PG_NDISTINCT_KEY_NDISTINCT "\" key.")));
+		return JSON_SEM_ACTION_FAILED;
+	}
+
+	/*
+	 * We need at least 2 attnums for a ndistinct item, anything less is
+	 * malformed.
+	 */
+	natts = parse->attnum_list->length;
+	if (natts < 2)
+	{
+		ereturn(parse->escontext, (Datum) 0,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+				 errdetail("The \"" PG_NDISTINCT_KEY_ATTRIBUTES
+						   "\" key must contain an array of at least two attnums.")));
+
+		return JSON_SEM_ACTION_FAILED;
+	}
+	attrsort = palloc0(natts * sizeof(AttrNumber));
+
+	/* Create the MVNDistinctItem */
+	item = palloc(sizeof(MVNDistinctItem));
+	item->nattributes = natts;
+	item->attributes = palloc0(natts * sizeof(AttrNumber));
+	item->ndistinct = (double) parse->ndistinct;
+
+	/* fill out both attnum list and sortable list */
+	for (int i = 0; i < natts; i++)
+	{
+		attrsort[i] = (AttrNumber) parse->attnum_list->elements[i].int_value;
+		item->attributes[i] = attrsort[i];
+	}
+
+	/* Check attrsort for uniqueness */
+	qsort(attrsort, natts, sizeof(AttrNumber), attnum_compare);
+	for (int i = 1; i < natts; i++)
+	{
+		if (attrsort[i] == attrsort[i - 1])
+		{
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					 errdetail("attnum list duplicate value found: %d.", attrsort[i])));
+
+			return JSON_SEM_ACTION_FAILED;
+		}
+	}
+	pfree(attrsort);
+
+	parse->distinct_items = lappend(parse->distinct_items, (void *) item);
+
+	/* reset item state vars */
+	list_free(parse->attnum_list);
+	parse->attnum_list = NIL;
+	parse->ndistinct = 0;
+	parse->found_attributes = false;
+	parse->found_ndistinct = false;
+
+	/* Now we are looking for the next MVNDistinctItem */
+	parse->state = NDIST_EXPECT_ITEM;
+	return JSON_SUCCESS;
+}
+
+
+/*
+ * ndsitinct input format has two types of arrays, the outer MVNDistinctItem
+ * array, and the attnum list array within each MVNDistinctItem.
+ */
+static JsonParseErrorType
+ndistinct_array_start(void *state)
+{
+	NDistinctParseState *parse = state;
+
+	switch (parse->state)
+	{
+		case NDIST_EXPECT_ATTNUM_LIST:
+			parse->state = NDIST_EXPECT_ATTNUM;
+			break;
+
+		case NDIST_EXPECT_START:
+			parse->state = NDIST_EXPECT_ITEM;
+			break;
+
+		default:
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					 errdetail("Array found in unexpected place.")));
+			return JSON_SEM_ACTION_FAILED;
+	}
+
+	return JSON_SUCCESS;
+}
+
+
+static JsonParseErrorType
+ndistinct_array_end(void *state)
+{
+	NDistinctParseState *parse = state;
+
+	switch (parse->state)
+	{
+		case NDIST_EXPECT_ATTNUM:
+			if (parse->attnum_list != NIL)
+			{
+				/* The attnum list is complete, look for more MVNDistinctItem keys */
+				parse->state = NDIST_EXPECT_KEY;
+				return JSON_SUCCESS;
+			}
+
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					errdetail("The \"" PG_NDISTINCT_KEY_ATTRIBUTES
+							"\" key must be an non-empty array.")));
+			return JSON_SEM_ACTION_FAILED;
+			break;
+
+		case NDIST_EXPECT_ITEM:
+			if (parse->distinct_items != NIL)
+			{
+				/* Item list is complete, we're done. */
+				parse->state = NDIST_EXPECT_COMPLETE;
+				return JSON_SUCCESS;
+			}
+
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					errdetail("Item array cannot be empty.")));
+
+			return JSON_SEM_ACTION_FAILED;
+			break;
+		default:
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					errdetail("Array found in unexpected place.")));
+	}
+	return JSON_SEM_ACTION_FAILED;
+}
+
+
+/*
+ * The valid keys for the MVNDistinctItem object are:
+ *   - attributes
+ *   - ndistinct
+ */
+static JsonParseErrorType
+ndistinct_object_field_start(void *state, char *fname, bool isnull)
+{
+	NDistinctParseState *parse = state;
+
+	if (strcmp(fname, PG_NDISTINCT_KEY_ATTRIBUTES) == 0)
+	{
+		parse->found_attributes = true;
+		parse->state = NDIST_EXPECT_ATTNUM_LIST;
+		return JSON_SUCCESS;
+	}
+
+	if (strcmp(fname, PG_NDISTINCT_KEY_NDISTINCT) == 0)
+	{
+		parse->found_ndistinct = true;
+		parse->state = NDIST_EXPECT_NDISTINCT;
+		return JSON_SUCCESS;
+	}
+
+	ereturn(parse->escontext, (Datum) 0,
+			(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+			 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+			 errdetail("Invalid key \"%s\". Only allowed keys are \""
+					   PG_NDISTINCT_KEY_ATTRIBUTES "\" and \""
+					   PG_NDISTINCT_KEY_NDISTINCT "\".", fname)));
+	return JSON_SEM_ACTION_FAILED;
+}
+
+/*
+ *
+ */
+static JsonParseErrorType
+ndistinct_array_element_start(void *state, bool isnull)
+{
+	NDistinctParseState *parse = state;
+
+	switch(parse->state)
+	{
+		case NDIST_EXPECT_ATTNUM:
+			if (!isnull)
+				return JSON_SUCCESS;
+
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					 errdetail("Attnum list elements cannot be null.")));
+
+			break;
+
+		case NDIST_EXPECT_ITEM:
+			if (!isnull)
+				return JSON_SUCCESS;
+
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					 errdetail("Item list elements cannot be null.")));
+
+			break;
+
+		default:
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					errdetail("Unexpected array element.")));
+	}
+
+	return JSON_SEM_ACTION_FAILED;
+}
+
+/*
+ * Handle scalar events from the ndistinct input parser.
+ *
+ */
+static JsonParseErrorType
+ndistinct_scalar(void *state, char *token, JsonTokenType tokentype)
+{
+	NDistinctParseState *parse = state;
+	AttrNumber	attnum;
+
+	switch(parse->state)
+	{
+		case NDIST_EXPECT_ATTNUM:
+			attnum = pg_strtoint16_safe(token, parse->escontext);
+
+			if (SOFT_ERROR_OCCURRED(parse->escontext))
+				return JSON_SEM_ACTION_FAILED;
+
+			parse->attnum_list = lappend_int(parse->attnum_list, (int) attnum);
+			return JSON_SUCCESS;
+			break;
+
+		case NDIST_EXPECT_NDISTINCT:
+			/*
+			* While the structure dictates that ndistinct in a double precision
+			* floating point, in practice it has always been an integer, and it
+			* is output as such. Therefore, we follow usage precendent over the
+			* actual storage structure, and read it in as an integer.
+			*/
+			parse->ndistinct = pg_strtoint64_safe(token, parse->escontext);
+
+			if (SOFT_ERROR_OCCURRED(parse->escontext))
+				return JSON_SEM_ACTION_FAILED;
+
+			parse->state = NDIST_EXPECT_KEY;
+			return JSON_SUCCESS;
+			break;
+
+		default:
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					errdetail("Unexpected scalar.")));
+	}
+
+	return JSON_SEM_ACTION_FAILED;
+}
+
+/*
+ * Compare the attribute arrays of two MVNDistinctItem values,
+ * looking for duplicate sets.
+ */
+static
+bool has_duplicate_attributes(const MVNDistinctItem *a,
+							  const MVNDistinctItem *b)
+{
+	int		i;
+
+	if (a->nattributes != b->nattributes)
+		return false;
+
+	for (i = 0; i < a->nattributes; i++)
+	{
+		if (a->attributes[i] != b->attributes[i])
+			return false;
+	}
+
+	return true;
+}
+
+/*
+ * Ensure that an attnum appears as one of the attnums in a given
+ * MVNDistinctItem.
+ */
+static
+bool item_has_attnum(const MVNDistinctItem *item, AttrNumber attnum)
+{
+	for (int i = 0; i < item->nattributes; i++)
+	{
+		if (attnum == item->attributes[i])
+			return true;
+	}
+	return false;
+}
+
+/*
+ * Ensure that the attributes of one MVNDistinctItem A are a proper subset
+ * of the reference MVNDistinctItem B.
+ */
+static
+bool item_is_attnum_subset(const MVNDistinctItem *item,
+						   const MVNDistinctItem *refitem)
+{
+	for (int i = 0; i < item->nattributes; i++)
+	{
+		if (!item_has_attnum(refitem,item->attributes[i]))
+			return false;
+	}
+	return true;
+}
+
+/*
+ * Generate a string representing an array of attnum.
+ *
+ * Freeing the allocated string is responsibility of the caller.
+ */
+static
+const char *item_attnum_list(const MVNDistinctItem *item)
+{
+	StringInfoData	str;
+
+	initStringInfo(&str);
+
+	appendStringInfo(&str, "%d", item->attributes[0]);
+
+	for (int i = 1; i < item->nattributes; i++)
+		appendStringInfo(&str, ", %d", item->attributes[i]);
+
+	return str.data;
+}
 
 /*
  * pg_ndistinct_in
  *		input routine for type pg_ndistinct
  *
- * pg_ndistinct is real enough to be a table column, but it has no
- * operations of its own, and disallows input (just like pg_node_tree).
+ * example input:
+ *     [{"attributes": [6, -1], "ndistinct": 14},
+ *      {"attributes": [6, -2], "ndistinct": 9143},
+ *      {"attributes": [-1,-2], "ndistinct": 13454},
+ *      {"attributes": [6, -1, -2], "ndistinct": 14549}]
  */
 Datum
 pg_ndistinct_in(PG_FUNCTION_ARGS)
 {
-	ereport(ERROR,
-			(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-			 errmsg("cannot accept a value of type %s", "pg_ndistinct")));
+	char	   *str = PG_GETARG_CSTRING(0);
 
-	PG_RETURN_VOID();			/* keep compiler quiet */
+	NDistinctParseState parse_state;
+	JsonParseErrorType result;
+	JsonLexContext *lex;
+	JsonSemAction sem_action;
+
+	int		item_most_attrs = 0;
+	int		item_most_attrs_idx = 0;
+
+	/* initialize semantic state */
+	parse_state.str = str;
+	parse_state.state = NDIST_EXPECT_START;
+	parse_state.distinct_items = NIL;
+	parse_state.escontext = fcinfo->context;
+	parse_state.found_attributes = false;
+	parse_state.found_ndistinct = false;
+	parse_state.attnum_list = NIL;
+	parse_state.ndistinct = 0;
+
+	/* set callbacks */
+	sem_action.semstate = (void *) &parse_state;
+	sem_action.object_start = ndistinct_object_start;
+	sem_action.object_end = ndistinct_object_end;
+	sem_action.array_start = ndistinct_array_start;
+	sem_action.array_end = ndistinct_array_end;
+	sem_action.object_field_start = ndistinct_object_field_start;
+	sem_action.object_field_end = NULL;
+	sem_action.array_element_start = ndistinct_array_element_start;
+	sem_action.array_element_end = NULL;
+	sem_action.scalar = ndistinct_scalar;
+
+	lex = makeJsonLexContextCstringLen(NULL, str, strlen(str),
+									   PG_UTF8, true);
+	result = pg_parse_json(lex, &sem_action);
+	freeJsonLexContext(lex);
+
+	if (result == JSON_SUCCESS &&
+		parse_state.distinct_items != NIL)
+	{
+		MVNDistinct *ndistinct;
+		int			nitems = parse_state.distinct_items->length;
+		bytea	   *bytes;
+
+
+		ndistinct = palloc(offsetof(MVNDistinct, items) +
+						   nitems * sizeof(MVNDistinctItem));
+
+		ndistinct->magic = STATS_NDISTINCT_MAGIC;
+		ndistinct->type = STATS_NDISTINCT_TYPE_BASIC;
+		ndistinct->nitems = nitems;
+
+		for (int i = 0; i < nitems; i++)
+		{
+			MVNDistinctItem *item = parse_state.distinct_items->elements[i].ptr_value;
+
+			/*
+			 * Ensure that this item does not duplicate the attributes of any
+			 * pre-existing item.
+			 */
+			for (int j = 0; j < i; j++)
+			{
+				if (has_duplicate_attributes(item, &ndistinct->items[j]))
+				{
+					ereturn(parse_state.escontext, (Datum) 0,
+							(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+							errmsg("malformed pg_ndistinct: \"%s\"", str),
+							errdetail("Duplicate \"" PG_NDISTINCT_KEY_ATTRIBUTES "\" array : [%s]",
+										item_attnum_list(item))));
+					PG_RETURN_NULL();
+				}
+			}
+
+			ndistinct->items[i].ndistinct = item->ndistinct;
+			ndistinct->items[i].nattributes = item->nattributes;
+			ndistinct->items[i].attributes = item->attributes;
+
+			/*
+			 * Keep track of the first longest attribute list. All other attribute
+			 * lists must be a subset of this list.
+			 */
+			if (item->nattributes > item_most_attrs)
+			{
+				item_most_attrs = item->nattributes;
+				item_most_attrs_idx = i;
+			}
+
+			/*
+			 * Free the MVNDistinctItem, but not the attributes we're still
+			 * using.
+			 */
+			pfree(item);
+		}
+
+		/*
+		 * Verify that all attnum sets are a proper subset of the first longest
+		 * attnum set.
+		 */
+		for (int i = 0; i < nitems; i++)
+		{
+			if (i == item_most_attrs_idx)
+				continue;
+
+			if (!item_is_attnum_subset(&ndistinct->items[i],
+									   &ndistinct->items[item_most_attrs_idx]))
+			{
+				const MVNDistinctItem  *item = &ndistinct->items[i];
+				const MVNDistinctItem  *refitem = &ndistinct->items[item_most_attrs_idx];
+				const char *item_list = item_attnum_list(item);
+				const char *refitem_list = item_attnum_list(refitem);
+
+				ereturn(parse_state.escontext, (Datum) 0,
+						(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+						errmsg("malformed pg_ndistinct: \"%s\"", str),
+						errdetail("\"" PG_NDISTINCT_KEY_ATTRIBUTES "\" array: [%s]"
+								  "must be a subset of array: [%s]",
+								  item_list, refitem_list)));
+				PG_RETURN_NULL();
+			}
+		}
+
+		bytes = statext_ndistinct_serialize(ndistinct);
+
+		list_free(parse_state.distinct_items);
+		for (int i = 0; i < nitems; i++)
+			pfree(ndistinct->items[i].attributes);
+		pfree(ndistinct);
+
+		PG_RETURN_BYTEA_P(bytes);
+	}
+	else if (result == JSON_SEM_ACTION_FAILED)
+		PG_RETURN_NULL();		/* escontext already set */
+
+	/* Anything else is a generic JSON parse error */
+	ereturn(parse_state.escontext, (Datum) 0,
+			(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+			 errmsg("malformed pg_ndistinct: \"%s\"", str),
+			 errdetail("Must be valid JSON.")));
+	PG_RETURN_NULL();
 }
 
 /*
  * pg_ndistinct_out
  *		output routine for type pg_ndistinct
  *
- * Produces a human-readable representation of the value.
+ * Produces a human-readable representation of the value, in the format:
+ *   [{"attributes": [attnum,. ..], "ndistinct": int}, ...]
+ *
  */
 Datum
 pg_ndistinct_out(PG_FUNCTION_ARGS)
diff --git a/src/test/regress/expected/pg_ndistinct.out b/src/test/regress/expected/pg_ndistinct.out
new file mode 100644
index 00000000000..d99e84a2bce
--- /dev/null
+++ b/src/test/regress/expected/pg_ndistinct.out
@@ -0,0 +1,109 @@
+-- Tests for type pg_distinct
+-- Invalid inputs
+SELECT '[]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[]"
+LINE 1: SELECT '[]'::pg_ndistinct;
+               ^
+DETAIL:  Item array cannot be empty.
+SELECT '[null]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[null]"
+LINE 1: SELECT '[null]'::pg_ndistinct;
+               ^
+DETAIL:  Item list elements cannot be null.
+-- Invalid keys
+SELECT '[{"attributes_invalid" : [2,3], "ndistinct" : 4}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes_invalid" : [2,3], "ndistinct" : 4}]"
+LINE 1: SELECT '[{"attributes_invalid" : [2,3], "ndistinct" : 4}]'::...
+               ^
+DETAIL:  Invalid key "attributes_invalid". Only allowed keys are "attributes" and "ndistinct".
+SELECT '[{"attributes" : [2,3], "invalid" : 3, "ndistinct" : 4}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : [2,3], "invalid" : 3, "ndistinct" : 4}]"
+LINE 1: SELECT '[{"attributes" : [2,3], "invalid" : 3, "ndistinct" :...
+               ^
+DETAIL:  Invalid key "invalid". Only allowed keys are "attributes" and "ndistinct".
+-- Missing key
+SELECT '[{"attributes" : [2,3]}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : [2,3]}]"
+LINE 1: SELECT '[{"attributes" : [2,3]}]'::pg_ndistinct;
+               ^
+DETAIL:  Item must contain "ndistinct" key.
+SELECT '[{"ndistinct" : 4}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"ndistinct" : 4}]"
+LINE 1: SELECT '[{"ndistinct" : 4}]'::pg_ndistinct;
+               ^
+DETAIL:  Item must contain "attributes" key.
+-- Valid keys, invalid values
+SELECT '[{"attributes" : null, "ndistinct" : 4}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : null, "ndistinct" : 4}]"
+LINE 1: SELECT '[{"attributes" : null, "ndistinct" : 4}]'::pg_ndisti...
+               ^
+DETAIL:  Unexpected scalar.
+SELECT '[{"attributes" : [2,null], "ndistinct" : 4}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : [2,null], "ndistinct" : 4}]"
+LINE 1: SELECT '[{"attributes" : [2,null], "ndistinct" : 4}]'::pg_nd...
+               ^
+DETAIL:  Attnum list elements cannot be null.
+SELECT '[{"attributes" : [2,3], "ndistinct" : null}]'::pg_ndistinct;
+ERROR:  invalid input syntax for type bigint: "null"
+LINE 1: SELECT '[{"attributes" : [2,3], "ndistinct" : null}]'::pg_nd...
+               ^
+SELECT '[{"attributes" : [2,"a"], "ndistinct" : 4}]'::pg_ndistinct;
+ERROR:  invalid input syntax for type smallint: "a"
+LINE 1: SELECT '[{"attributes" : [2,"a"], "ndistinct" : 4}]'::pg_ndi...
+               ^
+SELECT '[{"attributes" : [2,3], "ndistinct" : "a"}]'::pg_ndistinct;
+ERROR:  invalid input syntax for type bigint: "a"
+LINE 1: SELECT '[{"attributes" : [2,3], "ndistinct" : "a"}]'::pg_ndi...
+               ^
+SELECT '[{"attributes" : [2,3], "ndistinct" : []}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : [2,3], "ndistinct" : []}]"
+LINE 1: SELECT '[{"attributes" : [2,3], "ndistinct" : []}]'::pg_ndis...
+               ^
+DETAIL:  Array found in unexpected place.
+SELECT '[{"attributes" : [2,3], "ndistinct" : [null]}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : [2,3], "ndistinct" : [null]}]"
+LINE 1: SELECT '[{"attributes" : [2,3], "ndistinct" : [null]}]'::pg_...
+               ^
+DETAIL:  Array found in unexpected place.
+SELECT '[{"attributes" : [2,3], "ndistinct" : [1,null]}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : [2,3], "ndistinct" : [1,null]}]"
+LINE 1: SELECT '[{"attributes" : [2,3], "ndistinct" : [1,null]}]'::p...
+               ^
+DETAIL:  Array found in unexpected place.
+SELECT '[{"attributes" : 1, "ndistinct" : 4}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : 1, "ndistinct" : 4}]"
+LINE 1: SELECT '[{"attributes" : 1, "ndistinct" : 4}]'::pg_ndistinct...
+               ^
+DETAIL:  Unexpected scalar.
+SELECT '[{"attributes" : "a", "ndistinct" : 4}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : "a", "ndistinct" : 4}]"
+LINE 1: SELECT '[{"attributes" : "a", "ndistinct" : 4}]'::pg_ndistin...
+               ^
+DETAIL:  Unexpected scalar.
+-- Duplicated attributes
+SELECT '[{"attributes" : [2,2], "ndistinct" : 4}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : [2,2], "ndistinct" : 4}]"
+LINE 1: SELECT '[{"attributes" : [2,2], "ndistinct" : 4}]'::pg_ndist...
+               ^
+DETAIL:  attnum list duplicate value found: 2.
+-- Valid inputs
+-- Duplicated attribute lists.
+SELECT '[{"attributes" : [2,3], "ndistinct" : 4},
+         {"attributes" : [2,3], "ndistinct" : 4}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : [2,3], "ndistinct" : 4},
+         {"attributes" : [2,3], "ndistinct" : 4}]"
+LINE 1: SELECT '[{"attributes" : [2,3], "ndistinct" : 4},
+               ^
+DETAIL:  Duplicate "attributes" array : [2, 3]
+-- Partially-covered attribute lists.
+SELECT '[{"attributes" : [2,3], "ndistinct" : 4},
+         {"attributes" : [2,-1], "ndistinct" : 4},
+         {"attributes" : [2,3,-1], "ndistinct" : 4},
+         {"attributes" : [1,3,-1,-2], "ndistinct" : 4}]'::pg_ndistinct;
+ERROR:  malformed pg_ndistinct: "[{"attributes" : [2,3], "ndistinct" : 4},
+         {"attributes" : [2,-1], "ndistinct" : 4},
+         {"attributes" : [2,3,-1], "ndistinct" : 4},
+         {"attributes" : [1,3,-1,-2], "ndistinct" : 4}]"
+LINE 1: SELECT '[{"attributes" : [2,3], "ndistinct" : 4},
+               ^
+DETAIL:  "attributes" array: [2, 3]must be a subset of array: [1, 3, -1, -2]
diff --git a/src/test/regress/parallel_schedule b/src/test/regress/parallel_schedule
index f56482fb9f1..f3f0b5f2f31 100644
--- a/src/test/regress/parallel_schedule
+++ b/src/test/regress/parallel_schedule
@@ -28,7 +28,7 @@ test: strings md5 numerology point lseg line box path polygon circle date time t
 # geometry depends on point, lseg, line, box, path, polygon, circle
 # horology depends on date, time, timetz, timestamp, timestamptz, interval
 # ----------
-test: geometry horology tstypes regex type_sanity opr_sanity misc_sanity comments expressions unicode xid mvcc database stats_import
+test: geometry horology tstypes regex type_sanity opr_sanity misc_sanity comments expressions unicode xid mvcc database stats_import pg_ndistinct
 
 # ----------
 # Load huge amounts of data
diff --git a/src/test/regress/sql/pg_ndistinct.sql b/src/test/regress/sql/pg_ndistinct.sql
new file mode 100644
index 00000000000..ca89fed6fe2
--- /dev/null
+++ b/src/test/regress/sql/pg_ndistinct.sql
@@ -0,0 +1,34 @@
+-- Tests for type pg_distinct
+
+-- Invalid inputs
+SELECT '[]'::pg_ndistinct;
+SELECT '[null]'::pg_ndistinct;
+-- Invalid keys
+SELECT '[{"attributes_invalid" : [2,3], "ndistinct" : 4}]'::pg_ndistinct;
+SELECT '[{"attributes" : [2,3], "invalid" : 3, "ndistinct" : 4}]'::pg_ndistinct;
+-- Missing key
+SELECT '[{"attributes" : [2,3]}]'::pg_ndistinct;
+SELECT '[{"ndistinct" : 4}]'::pg_ndistinct;
+-- Valid keys, invalid values
+SELECT '[{"attributes" : null, "ndistinct" : 4}]'::pg_ndistinct;
+SELECT '[{"attributes" : [2,null], "ndistinct" : 4}]'::pg_ndistinct;
+SELECT '[{"attributes" : [2,3], "ndistinct" : null}]'::pg_ndistinct;
+SELECT '[{"attributes" : [2,"a"], "ndistinct" : 4}]'::pg_ndistinct;
+SELECT '[{"attributes" : [2,3], "ndistinct" : "a"}]'::pg_ndistinct;
+SELECT '[{"attributes" : [2,3], "ndistinct" : []}]'::pg_ndistinct;
+SELECT '[{"attributes" : [2,3], "ndistinct" : [null]}]'::pg_ndistinct;
+SELECT '[{"attributes" : [2,3], "ndistinct" : [1,null]}]'::pg_ndistinct;
+SELECT '[{"attributes" : 1, "ndistinct" : 4}]'::pg_ndistinct;
+SELECT '[{"attributes" : "a", "ndistinct" : 4}]'::pg_ndistinct;
+-- Duplicated attributes
+SELECT '[{"attributes" : [2,2], "ndistinct" : 4}]'::pg_ndistinct;
+
+-- Valid inputs
+-- Duplicated attribute lists.
+SELECT '[{"attributes" : [2,3], "ndistinct" : 4},
+         {"attributes" : [2,3], "ndistinct" : 4}]'::pg_ndistinct;
+-- Partially-covered attribute lists.
+SELECT '[{"attributes" : [2,3], "ndistinct" : 4},
+         {"attributes" : [2,-1], "ndistinct" : 4},
+         {"attributes" : [2,3,-1], "ndistinct" : 4},
+         {"attributes" : [1,3,-1,-2], "ndistinct" : 4}]'::pg_ndistinct;
-- 
2.51.1