v9-0008-Make-pg_ndinstinct-a-proper-adt.patch

From 2ee4f9a778d4eec41ceb6af054d98dc08afad87c Mon Sep 17 00:00:00 2001
From: Corey Huinker <corey.huinker@gmail.com>
Date: Sun, 9 Nov 2025 22:49:03 -0500
Subject: [PATCH v9 8/9] Make pg_ndinstinct a proper adt.

Move the in/out/send/recv functions for pg_ndistinct to pg_ndistinct.c,
which allows mvdistinct.c to focus on the transformation from sample
data to the internal MVDistinct structure.
---
 src/backend/statistics/mvdistinct.c  | 529 --------------------------
 src/backend/utils/adt/Makefile       |   1 +
 src/backend/utils/adt/meson.build    |   1 +
 src/backend/utils/adt/pg_ndistinct.c | 550 +++++++++++++++++++++++++++
 4 files changed, 552 insertions(+), 529 deletions(-)
 create mode 100644 src/backend/utils/adt/pg_ndistinct.c

diff --git a/src/backend/statistics/mvdistinct.c b/src/backend/statistics/mvdistinct.c
index 09bec8ff718..f6bf68db01a 100644
--- a/src/backend/statistics/mvdistinct.c
+++ b/src/backend/statistics/mvdistinct.c
@@ -27,16 +27,7 @@
 
 #include "catalog/pg_statistic_ext.h"
 #include "catalog/pg_statistic_ext_data.h"
-#include "common/int.h"
-#include "common/jsonapi.h"
-#include "lib/stringinfo.h"
-#include "mb/pg_wchar.h"
-#include "nodes/miscnodes.h"
-#include "nodes/pg_list.h"
 #include "statistics/extended_stats_internal.h"
-#include "statistics/statistics.h"
-#include "utils/builtins.h"
-#include "utils/fmgrprotos.h"
 #include "utils/syscache.h"
 #include "utils/typcache.h"
 #include "varatt.h"
@@ -334,458 +325,6 @@ statext_ndistinct_deserialize(bytea *data)
 	return ndistinct;
 }
 
-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;
-
-	if (parse->state != NDIST_EXPECT_ITEM)
-	{
-		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;
-	}
-
-	/* Now we expect to see attributes/ndistinct keys */
-	parse->state = NDIST_EXPECT_KEY;
-	return JSON_SUCCESS;
-}
-
-/*
- * 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 \"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 \"ndistinct\" key")));
-		return JSON_SEM_ACTION_FAILED;
-	}
-
-	if (parse->attnum_list == NIL)
-	{
-		ereturn(parse->escontext, (Datum) 0,
-				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-				 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
-				 errdetail("The \"attributes\" key must be an non-empty array")));
-		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 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;
-
-	/* The attnum list is complete, look for more MVNDistinctItem keys */
-	if (parse->state == NDIST_EXPECT_ATTNUM)
-	{
-		parse->state = NDIST_EXPECT_KEY;
-		return JSON_SUCCESS;
-	}
-
-	if (parse->state == NDIST_EXPECT_ITEM)
-	{
-		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("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;
-
-	const char *attributes = "attributes";
-	const char *ndistinct = "ndistinct";
-
-	if (strcmp(fname, attributes) == 0)
-	{
-		parse->found_attributes = true;
-		parse->state = NDIST_EXPECT_ATTNUM_LIST;
-		return JSON_SUCCESS;
-	}
-
-	if (strcmp(fname, 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("Only allowed keys are \%s\" and \%s\".", attributes, ndistinct)));
-	return JSON_SEM_ACTION_FAILED;
-}
-
-/*
- *
- */
-static JsonParseErrorType
-ndistinct_array_element_start(void *state, bool isnull)
-{
-	ndistinctParseState *parse = state;
-
-	if (parse->state == NDIST_EXPECT_ATTNUM)
-	{
-		if (isnull)
-		{
-			ereturn(parse->escontext, (Datum) 0,
-					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-					 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
-					 errdetail("Attnum list elements cannot be null.")));
-
-			return JSON_SEM_ACTION_FAILED;
-		}
-		return JSON_SUCCESS;
-	}
-
-	if (parse->state == NDIST_EXPECT_ITEM)
-	{
-		if (isnull)
-		{
-			ereturn(parse->escontext, (Datum) 0,
-					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
-					 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
-					 errdetail("Item list elements cannot be null.")));
-
-			return JSON_SEM_ACTION_FAILED;
-		}
-
-		return JSON_SUCCESS;
-	}
-
-	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;
-
-	if (parse->state == NDIST_EXPECT_ATTNUM)
-	{
-		AttrNumber	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;
-	}
-
-	if (parse->state == 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;
-	}
-
-	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;
-}
-
-/*
- * pg_ndistinct_in
- *		input routine for type pg_ndistinct
- *
- * 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)
-{
-	char	   *str = PG_GETARG_CSTRING(0);
-
-	ndistinctParseState parse_state;
-	JsonParseErrorType result;
-	JsonLexContext *lex;
-	JsonSemAction sem_action;
-
-	/* 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)
-	{
-		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;
-
-			ndistinct->items[i].ndistinct = item->ndistinct;
-			ndistinct->items[i].nattributes = item->nattributes;
-			ndistinct->items[i].attributes = item->attributes;
-
-			/*
-			 * free the MVNDistinctItem, but not the attributes we're still
-			 * using
-			 */
-			pfree(item);
-		}
-		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();
-}
-
-/*
- * Free allocations of an MVNDistinct
- */
-void
-free_pg_ndistinct(MVNDistinct *ndistinct)
-{
-	for (int i = 0; i < ndistinct->nitems; i++)
-		pfree(ndistinct->items[i].attributes);
-
-	pfree(ndistinct);
-}
-
 /*
  * Validate an MVNDistinct against the extended statistics object definition.
  *
@@ -836,74 +375,6 @@ pg_ndistinct_validate_items(MVNDistinct *ndistinct, int2vector *stxkeys, int num
 }
 
 
-/*
- * pg_ndistinct
- *		output routine for type pg_ndistinct
- *
- * Produces a human-readable representation of the value, in the format:
- *   [{"attributes": [attnum,. ..], "ndistinct": int}, ...]
- *
- */
-Datum
-pg_ndistinct_out(PG_FUNCTION_ARGS)
-{
-	bytea	   *data = PG_GETARG_BYTEA_PP(0);
-	MVNDistinct *ndist = statext_ndistinct_deserialize(data);
-	int			i;
-	StringInfoData str;
-
-	initStringInfo(&str);
-	appendStringInfoChar(&str, '[');
-
-	for (i = 0; i < ndist->nitems; i++)
-	{
-		MVNDistinctItem item = ndist->items[i];
-
-		if (i > 0)
-			appendStringInfoString(&str, ", ");
-
-		if (item.nattributes <= 0)
-			elog(ERROR, "invalid zero-length attribute array in MVNDistinct");
-
-		appendStringInfo(&str, "{\"attributes\": [%d", item.attributes[0]);
-
-		for (int j = 1; j < item.nattributes; j++)
-			appendStringInfo(&str, ", %d", item.attributes[j]);
-
-		appendStringInfo(&str, "], \"ndistinct\": %d}", (int) item.ndistinct);
-	}
-
-	appendStringInfoChar(&str, ']');
-
-	PG_RETURN_CSTRING(str.data);
-}
-
-/*
- * pg_ndistinct_recv
- *		binary input routine for type pg_ndistinct
- */
-Datum
-pg_ndistinct_recv(PG_FUNCTION_ARGS)
-{
-	ereport(ERROR,
-			(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-			 errmsg("cannot accept a value of type %s", "pg_ndistinct")));
-
-	PG_RETURN_VOID();			/* keep compiler quiet */
-}
-
-/*
- * pg_ndistinct_send
- *		binary output routine for type pg_ndistinct
- *
- * n-distinct is serialized into a bytea value, so let's send that.
- */
-Datum
-pg_ndistinct_send(PG_FUNCTION_ARGS)
-{
-	return byteasend(fcinfo);
-}
-
 /*
  * ndistinct_for_combination
  *		Estimates number of distinct values in a combination of columns.
diff --git a/src/backend/utils/adt/Makefile b/src/backend/utils/adt/Makefile
index cc68ac545a5..70ff8e45516 100644
--- a/src/backend/utils/adt/Makefile
+++ b/src/backend/utils/adt/Makefile
@@ -85,6 +85,7 @@ OBJS = \
 	pg_locale_icu.o \
 	pg_locale_libc.o \
 	pg_lsn.o \
+	pg_ndistinct.o \
 	pg_upgrade_support.o \
 	pgstatfuncs.o \
 	pseudorandomfuncs.o \
diff --git a/src/backend/utils/adt/meson.build b/src/backend/utils/adt/meson.build
index 12fa0c20912..b6b642c77a0 100644
--- a/src/backend/utils/adt/meson.build
+++ b/src/backend/utils/adt/meson.build
@@ -81,6 +81,7 @@ backend_sources += files(
   'pg_locale_icu.c',
   'pg_locale_libc.c',
   'pg_lsn.c',
+  'pg_ndistinct.c',
   'pg_upgrade_support.c',
   'pgstatfuncs.c',
   'pseudorandomfuncs.c',
diff --git a/src/backend/utils/adt/pg_ndistinct.c b/src/backend/utils/adt/pg_ndistinct.c
new file mode 100644
index 00000000000..9dd24f06ecf
--- /dev/null
+++ b/src/backend/utils/adt/pg_ndistinct.c
@@ -0,0 +1,550 @@
+/*-------------------------------------------------------------------------
+ *
+ * pg_ndistinct.c
+ *		pg_ndistinct data type support.
+ *
+ * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * IDENTIFICATION
+ *	  src/backend/utils/adt/pg_ndistinct.c
+ *
+ *-------------------------------------------------------------------------
+ */
+#include "postgres.h"
+
+#include "common/int.h"
+#include "common/jsonapi.h"
+#include "mb/pg_wchar.h"
+#include "nodes/miscnodes.h"
+#include "nodes/pg_list.h"
+#include "statistics/statistics.h"
+#include "statistics/extended_stats_internal.h"
+#include "utils/builtins.h"
+#include "utils/syscache.h"
+
+/*
+ * The valid keys for the pg_ndistinct object:
+ */
+static const char *attributes = "attributes";
+static const char *ndistinct = "ndistinct";
+
+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 should 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;
+
+	if (parse->state != NDIST_EXPECT_ITEM)
+	{
+		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;
+	}
+
+	/* Now we expect to see attributes/ndistinct keys */
+	parse->state = NDIST_EXPECT_KEY;
+	return JSON_SUCCESS;
+}
+
+/*
+ * 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 \"%s\" key", attributes)));
+		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 \"%s\" key", ndistinct)));
+		return JSON_SEM_ACTION_FAILED;
+	}
+
+	if (parse->attnum_list == NIL)
+	{
+		ereturn(parse->escontext, (Datum) 0,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+				 errdetail("The \"%s\" key must be an non-empty array", attributes)));
+		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 \"%s\" key must contain an array of at least two attnums", attributes)));
+
+		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;
+
+	/* The attnum list is complete, look for more MVNDistinctItem keys */
+	if (parse->state == NDIST_EXPECT_ATTNUM)
+	{
+		parse->state = NDIST_EXPECT_KEY;
+		return JSON_SUCCESS;
+	}
+
+	if (parse->state == NDIST_EXPECT_ITEM)
+	{
+		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("Array found in unexpected place")));
+	return JSON_SEM_ACTION_FAILED;
+}
+
+
+/*
+ *
+ */
+static JsonParseErrorType
+ndistinct_object_field_start(void *state, char *fname, bool isnull)
+{
+	ndistinctParseState *parse = state;
+
+	if (strcmp(fname, attributes) == 0)
+	{
+		parse->found_attributes = true;
+		parse->state = NDIST_EXPECT_ATTNUM_LIST;
+		return JSON_SUCCESS;
+	}
+
+	if (strcmp(fname, 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("Only allowed keys are \%s\" and \%s\".", attributes, ndistinct)));
+	return JSON_SEM_ACTION_FAILED;
+}
+
+/*
+ *
+ */
+static JsonParseErrorType
+ndistinct_array_element_start(void *state, bool isnull)
+{
+	ndistinctParseState *parse = state;
+
+	if (parse->state == NDIST_EXPECT_ATTNUM)
+	{
+		if (isnull)
+		{
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					 errdetail("Attnum list elements cannot be null.")));
+
+			return JSON_SEM_ACTION_FAILED;
+		}
+		return JSON_SUCCESS;
+	}
+
+	if (parse->state == NDIST_EXPECT_ITEM)
+	{
+		if (isnull)
+		{
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed pg_ndistinct: \"%s\"", parse->str),
+					 errdetail("Item list elements cannot be null.")));
+
+			return JSON_SEM_ACTION_FAILED;
+		}
+
+		return JSON_SUCCESS;
+	}
+
+	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;
+
+	if (parse->state == NDIST_EXPECT_ATTNUM)
+	{
+		AttrNumber	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;
+	}
+
+	if (parse->state == 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;
+	}
+
+	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;
+}
+
+
+/*
+ * Free allocations of an MVNDistinct
+ */
+void
+free_pg_ndistinct(MVNDistinct *ndistinct)
+{
+	for (int i = 0; i < ndistinct->nitems; i++)
+		pfree(ndistinct->items[i].attributes);
+
+	pfree(ndistinct);
+}
+
+
+/*
+ * pg_ndistinct_in
+ *		input routine for type pg_ndistinct
+ *
+ * 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)
+{
+	char	   *str = PG_GETARG_CSTRING(0);
+
+	ndistinctParseState parse_state;
+	JsonParseErrorType result;
+	JsonLexContext *lex;
+	JsonSemAction sem_action;
+
+	/* 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)
+	{
+		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;
+
+			ndistinct->items[i].ndistinct = item->ndistinct;
+			ndistinct->items[i].nattributes = item->nattributes;
+			ndistinct->items[i].attributes = item->attributes;
+
+			/*
+			 * free the MVNDistinctItem, but not the attributes we're still
+			 * using
+			 */
+			pfree(item);
+		}
+		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
+ *		output routine for type pg_ndistinct
+ *
+ * Produces a human-readable representation of the value, in the format:
+ *   [{"attributes": [attnum,. ..], "ndistinct": int}, ...]
+ *
+ */
+Datum
+pg_ndistinct_out(PG_FUNCTION_ARGS)
+{
+	bytea	   *data = PG_GETARG_BYTEA_PP(0);
+	MVNDistinct *ndist = statext_ndistinct_deserialize(data);
+	int			i;
+	StringInfoData str;
+
+	initStringInfo(&str);
+	appendStringInfoChar(&str, '[');
+
+	for (i = 0; i < ndist->nitems; i++)
+	{
+		MVNDistinctItem item = ndist->items[i];
+
+		if (i > 0)
+			appendStringInfoString(&str, ", ");
+
+		if (item.nattributes <= 0)
+			elog(ERROR, "invalid zero-length attribute array in MVNDistinct");
+
+		appendStringInfo(&str, "{\"%s\": [%d", attributes, item.attributes[0]);
+
+		for (int j = 1; j < item.nattributes; j++)
+			appendStringInfo(&str, ", %d", item.attributes[j]);
+
+		appendStringInfo(&str, "], \"%s\": %d}", ndistinct, (int) item.ndistinct);
+	}
+
+	appendStringInfoChar(&str, ']');
+
+	PG_RETURN_CSTRING(str.data);
+}
+
+/*
+ * pg_ndistinct_recv
+ *		binary input routine for type pg_ndistinct
+ */
+Datum
+pg_ndistinct_recv(PG_FUNCTION_ARGS)
+{
+	ereport(ERROR,
+			(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+			 errmsg("cannot accept a value of type %s", "pg_ndistinct")));
+
+	PG_RETURN_VOID();			/* keep compiler quiet */
+}
+
+/*
+ * pg_ndistinct_send
+ *		binary output routine for type pg_ndistinct
+ *
+ * n-distinct is serialized into a bytea value, so let's send that.
+ */
+Datum
+pg_ndistinct_send(PG_FUNCTION_ARGS)
+{
+	return byteasend(fcinfo);
+}
-- 
2.51.1