v5-0004-Add-working-input-function-for-pg_dependencies.patch

From 5d39e2bae4d952205c4952e23a41220b940ccbd4 Mon Sep 17 00:00:00 2001
From: Corey Huinker <corey.huinker@gmail.com>
Date: Tue, 4 Nov 2025 16:12:44 -0500
Subject: [PATCH v5 4/7] Add working input function for pg_dependencies.

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

This will be needed for importing extended statistics.
---
 src/backend/statistics/dependencies.c   | 463 +++++++++++++++++++++++-
 src/test/regress/expected/stats_ext.out |  22 ++
 src/test/regress/sql/stats_ext.sql      |  12 +
 3 files changed, 487 insertions(+), 10 deletions(-)

diff --git a/src/backend/statistics/dependencies.c b/src/backend/statistics/dependencies.c
index c150ddfb594..573d0f722de 100644
--- a/src/backend/statistics/dependencies.c
+++ b/src/backend/statistics/dependencies.c
@@ -13,18 +13,26 @@
  */
 #include "postgres.h"
 
+#include "access/attnum.h"
 #include "access/htup_details.h"
 #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/nodeFuncs.h"
 #include "nodes/nodes.h"
 #include "nodes/pathnodes.h"
+#include "nodes/pg_list.h"
 #include "optimizer/clauses.h"
 #include "optimizer/optimizer.h"
 #include "parser/parsetree.h"
 #include "statistics/extended_stats_internal.h"
 #include "statistics/statistics.h"
+#include "utils/builtins.h"
+#include "utils/float.h"
 #include "utils/fmgroids.h"
 #include "utils/fmgrprotos.h"
 #include "utils/lsyscache.h"
@@ -643,24 +651,459 @@ statext_dependencies_load(Oid mvoid, bool inh)
 	return result;
 }
 
+typedef enum
+{
+	DEPS_EXPECT_START = 0,
+	DEPS_EXPECT_ITEM,
+	DEPS_EXPECT_KEY,
+	DEPS_EXPECT_ATTNUM_LIST,
+	DEPS_EXPECT_ATTNUM,
+	DEPS_EXPECT_DEPENDENCY,
+	DEPS_EXPECT_DEGREE,
+	DEPS_PARSE_COMPLETE
+}			depsParseSemanticState;
+
+typedef struct
+{
+	const char *str;
+	depsParseSemanticState state;
+
+	List	   *dependency_list;
+	Node	   *escontext;
+
+	bool		found_attributes;	/* Item has an attributes key */
+	bool		found_dependency;	/* Item has an dependency key */
+	bool		found_degree;	/* Item has degree key */
+	List	   *attnum_list;	/* Accumulated attributes attnums */
+	AttrNumber	dependency;
+	double		degree;
+}			dependenciesParseState;
+
+/*
+ * Invoked at the start of each MVDependency object.
+ *
+ * The entire JSON document shoul be one array of MVDependency objects.
+ *
+ * If we're anywhere else in the document, it's an error.
+ */
+static JsonParseErrorType
+dependencies_object_start(void *state)
+{
+	dependenciesParseState *parse = state;
+
+	if (parse->state != DEPS_EXPECT_ITEM)
+	{
+		ereturn(parse->escontext, (Datum) 0,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+				 errdetail("Expected Item object")));
+		return JSON_SEM_ACTION_FAILED;
+	}
+
+	/* Now we expect to see attributes/dependency/degree keys */
+	parse->state = DEPS_EXPECT_KEY;
+	return JSON_SUCCESS;
+}
+
+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);
+}
+
+static JsonParseErrorType
+dependencies_object_end(void *state)
+{
+	dependenciesParseState *parse = state;
+
+	MVDependency *dep;
+	AttrNumber *attrsort;
+
+	int			natts = 0;
+
+	if (!parse->found_attributes)
+	{
+		ereturn(parse->escontext, (Datum) 0,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+				 errdetail("Item must contain \"attributes\" key")));
+		return JSON_SEM_ACTION_FAILED;
+	}
+
+	if (!parse->found_dependency)
+	{
+		ereturn(parse->escontext, (Datum) 0,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+				 errdetail("Item must contain \"dependencies\" key")));
+		return JSON_SEM_ACTION_FAILED;
+	}
+
+	if (!parse->found_degree)
+	{
+		ereturn(parse->escontext, (Datum) 0,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+				 errdetail("Item must contain \"degree\" key")));
+		return JSON_SEM_ACTION_FAILED;
+	}
+
+	if (parse->attnum_list == NIL)
+	{
+		ereturn(parse->escontext, (Datum) 0,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+				 errdetail("The \"attributes\" key must be an non-empty array")));
+		return JSON_SEM_ACTION_FAILED;
+	}
+
+	/*
+	 * We need at least 1 attnum for a dependencies item, anything less is
+	 * malformed.
+	 */
+	natts = parse->attnum_list->length;
+	if (natts < 1)
+	{
+		ereturn(parse->escontext, (Datum) 0,
+				(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+				 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+				 errdetail("The attributes key must contain an array of at least one attnum")));
+
+		return JSON_SEM_ACTION_FAILED;
+	}
+	attrsort = palloc0(natts * sizeof(AttrNumber));
+
+	/*
+	 * Allocate enough space for the dependency, the attnums in the list, plus
+	 * the final attnum
+	 */
+	dep = palloc0(offsetof(MVDependency, attributes) + ((natts + 1) * sizeof(AttrNumber)));
+	dep->nattributes = natts + 1;
+
+	dep->attributes[natts] = parse->dependency;
+	dep->degree = parse->degree;
+
+	attrsort = palloc0(dep->nattributes * sizeof(AttrNumber));
+	attrsort[natts] = parse->dependency;
+
+	for (int i = 0; i < natts; i++)
+	{
+		attrsort[i] = (AttrNumber) parse->attnum_list->elements[i].int_value;
+		dep->attributes[i] = attrsort[i];
+	}
+
+	/* Check attrsort for uniqueness */
+	qsort(attrsort, natts + 1, sizeof(AttrNumber), attnum_compare);
+	for (int i = 1; i < dep->nattributes; i++)
+		if (attrsort[i] == attrsort[i - 1])
+		{
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+					 errdetail("attnum list duplicate value found: %d", attrsort[i])));
+
+			return JSON_SEM_ACTION_FAILED;
+		}
+	pfree(attrsort);
+
+	parse->dependency_list = lappend(parse->dependency_list, (void *) dep);
+
+	/* reset dep item state vars */
+	list_free(parse->attnum_list);
+	parse->attnum_list = NIL;
+	parse->dependency = 0;
+	parse->degree = 0.0;
+	parse->found_attributes = false;
+	parse->found_dependency = false;
+	parse->found_degree = false;
+
+	/* Now we are looking for the next MVDependency */
+	parse->state = DEPS_EXPECT_ITEM;
+	return JSON_SUCCESS;
+}
+
+/*
+ * dependencies input format does not have arrays, so any array elements encountered
+ * are an error.
+ */
+static JsonParseErrorType
+dependencies_array_start(void *state)
+{
+	dependenciesParseState *parse = state;
+
+	switch (parse->state)
+	{
+		case DEPS_EXPECT_ATTNUM_LIST:
+			parse->state = DEPS_EXPECT_ATTNUM;
+			break;
+		case DEPS_EXPECT_START:
+			parse->state = DEPS_EXPECT_ITEM;
+			break;
+		default:
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+					 errdetail("Array found in unexpected place")));
+			return JSON_SEM_ACTION_FAILED;
+	}
+
+	return JSON_SUCCESS;
+}
+
+/*
+ * Either the end of an attnum list or the whole object
+ */
+static JsonParseErrorType
+dependencies_array_end(void *state)
+{
+	dependenciesParseState *parse = state;
+
+	switch (parse->state)
+	{
+		case DEPS_EXPECT_ATTNUM:
+			parse->state = DEPS_EXPECT_KEY;
+			break;
+
+		case DEPS_EXPECT_ITEM:
+			parse->state = DEPS_PARSE_COMPLETE;
+			break;
+
+		default:
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+					 errdetail("Array found in unexpected place")));
+			return JSON_SEM_ACTION_FAILED;
+	}
+	return JSON_SUCCESS;
+}
+
+/*
+ * The valid keys for the MVDependency object are:
+ *   - attributes
+ *   - depeendency
+ *   - degree
+ */
+static JsonParseErrorType
+dependencies_object_field_start(void *state, char *fname, bool isnull)
+{
+	dependenciesParseState *parse = state;
+
+	const char *attributes = "attributes";
+	const char *dependency = "dependency";
+	const char *degree = "degree";
+
+	if (strcmp(fname, attributes) == 0)
+	{
+		parse->found_attributes = true;
+		parse->state = DEPS_EXPECT_ATTNUM_LIST;
+		return JSON_SUCCESS;
+	}
+
+	if (strcmp(fname, dependency) == 0)
+	{
+		parse->found_dependency = true;
+		parse->state = DEPS_EXPECT_DEPENDENCY;
+		return JSON_SUCCESS;
+	}
+
+	if (strcmp(fname, degree) == 0)
+	{
+		parse->found_degree = true;
+		parse->state = DEPS_EXPECT_DEGREE;
+		return JSON_SUCCESS;
+	}
+
+	ereturn(parse->escontext, (Datum) 0,
+			(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+			 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+			 errdetail("Only allowed keys are \%s\", \"%s\" and \%s\".",
+					   attributes, dependency, degree)));
+	return JSON_SEM_ACTION_FAILED;
+}
+
+/*
+ * ndsitinct input format does not have arrays, so any array elements encountered
+ * are an error.
+ */
+static JsonParseErrorType
+dependencies_array_element_start(void *state, bool isnull)
+{
+	dependenciesParseState *parse = state;
+
+	if (parse->state == DEPS_EXPECT_ATTNUM)
+	{
+		if (isnull)
+		{
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+					 errdetail("Attnum list elements cannot be null.")));
+
+			return JSON_SEM_ACTION_FAILED;
+		}
+		return JSON_SUCCESS;
+	}
+
+	if (parse->state == DEPS_EXPECT_ITEM)
+	{
+		if (isnull)
+		{
+			ereturn(parse->escontext, (Datum) 0,
+					(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+					 errmsg("malformed pg_dependencies: \"%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_dependencies: \"%s\"", parse->str),
+			 errdetail("Unexpected array element.")));
+
+	return JSON_SEM_ACTION_FAILED;
+}
+
+/*
+ * Handle scalar events from the dependencies input parser.
+ *
+ * There is only one case where we will encounter a scalar, and that is the
+ * dependency degree for the previous object key.
+ */
+static JsonParseErrorType
+dependencies_scalar(void *state, char *token, JsonTokenType tokentype)
+{
+	dependenciesParseState *parse = state;
+
+	if (parse->state == DEPS_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 == DEPS_EXPECT_DEPENDENCY)
+	{
+		parse->dependency = (AttrNumber) pg_strtoint16_safe(token, parse->escontext);
+
+		if (SOFT_ERROR_OCCURRED(parse->escontext))
+			return JSON_SEM_ACTION_FAILED;
+
+		return JSON_SUCCESS;
+	}
+
+
+	if (parse->state == DEPS_EXPECT_DEGREE)
+	{
+		parse->degree = float8in_internal(token, NULL, "double",
+										  token, parse->escontext);
+
+		if (SOFT_ERROR_OCCURRED(parse->escontext))
+			return JSON_SEM_ACTION_FAILED;
+
+		return JSON_SUCCESS;
+	}
+
+	ereturn(parse->escontext, (Datum) 0,
+			(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+			 errmsg("malformed pg_dependencies: \"%s\"", parse->str),
+			 errdetail("Unexpected scalar.")));
+	return JSON_SEM_ACTION_FAILED;
+}
+
 /*
  * pg_dependencies_in		- input routine for type pg_dependencies.
  *
- * pg_dependencies is real enough to be a table column, but it has no operations
- * of its own, and disallows input too
+ * This format is valid JSON, with the expected format:
+ *    [{"attributes": [1,2], "dependency": -1, "degree": 1.0000},
+ *     {"attributes": [1,-1], "dependency": 2, "degree": 0.0000},
+ *     {"attributes": [2,-1], "dependency": 1, "degree": 1.0000}]
+ *
  */
 Datum
 pg_dependencies_in(PG_FUNCTION_ARGS)
 {
-	/*
-	 * pg_node_list stores the data in binary form and parsing text input is
-	 * not needed, so disallow this.
-	 */
-	ereport(ERROR,
-			(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-			 errmsg("cannot accept a value of type %s", "pg_dependencies")));
+	char	   *str = PG_GETARG_CSTRING(0);
 
-	PG_RETURN_VOID();			/* keep compiler quiet */
+	dependenciesParseState parse_state;
+	JsonParseErrorType result;
+	JsonLexContext *lex;
+	JsonSemAction sem_action;
+
+	/* initialize the semantic state */
+	parse_state.str = str;
+	parse_state.state = DEPS_EXPECT_START;
+	parse_state.dependency_list = NIL;
+	parse_state.attnum_list = NIL;
+	parse_state.dependency = 0;
+	parse_state.degree = 0.0;
+	parse_state.found_attributes = false;
+	parse_state.found_dependency = false;
+	parse_state.found_degree = false;
+	parse_state.escontext = fcinfo->context;
+
+	/* set callbacks */
+	sem_action.semstate = (void *) &parse_state;
+	sem_action.object_start = dependencies_object_start;
+	sem_action.object_end = dependencies_object_end;
+	sem_action.array_start = dependencies_array_start;
+	sem_action.array_end = dependencies_array_end;
+	sem_action.array_element_start = dependencies_array_element_start;
+	sem_action.array_element_end = NULL;
+	sem_action.object_field_start = dependencies_object_field_start;
+	sem_action.object_field_end = NULL;
+	sem_action.scalar = dependencies_scalar;
+
+	lex = makeJsonLexContextCstringLen(NULL, str, strlen(str), PG_UTF8, true);
+
+	result = pg_parse_json(lex, &sem_action);
+	freeJsonLexContext(lex);
+
+	if (result == JSON_SUCCESS)
+	{
+		List	   *list = parse_state.dependency_list;
+		int			ndeps = list->length;
+		MVDependencies *mvdeps;
+		bytea	   *bytes;
+
+		mvdeps = palloc0(offsetof(MVDependencies, deps) + ndeps * sizeof(MVDependency));
+		mvdeps->magic = STATS_DEPS_MAGIC;
+		mvdeps->type = STATS_DEPS_TYPE_BASIC;
+		mvdeps->ndeps = ndeps;
+
+		/* copy MVDependency structs out of the list into the MVDependencies */
+		for (int i = 0; i < ndeps; i++)
+			mvdeps->deps[i] = list->elements[i].ptr_value;
+		bytes = statext_dependencies_serialize(mvdeps);
+
+		list_free(list);
+		for (int i = 0; i < ndeps; i++)
+			pfree(mvdeps->deps[i]);
+		pfree(mvdeps);
+
+		PG_RETURN_BYTEA_P(bytes);
+	}
+	else if (result == JSON_SEM_ACTION_FAILED)
+		PG_RETURN_NULL();
+
+	/* Anything else is a generic JSON parse error */
+	ereturn(parse_state.escontext, (Datum) 0,
+			(errcode(ERRCODE_INVALID_TEXT_REPRESENTATION),
+			 errmsg("malformed pg_dependencies: \"%s\"", str),
+			 errdetail("Must be valid JSON.")));
+
+	PG_RETURN_NULL();			/* keep compiler quiet */
 }
 
 /*
diff --git a/src/test/regress/expected/stats_ext.out b/src/test/regress/expected/stats_ext.out
index 8cea29de314..6219b9674b0 100644
--- a/src/test/regress/expected/stats_ext.out
+++ b/src/test/regress/expected/stats_ext.out
@@ -3788,6 +3788,28 @@ ERROR:  malformed pg_ndistinct: "[{"attributes" : [2,3], "ndistinct" : 4},
 LINE 1: SELECT '[{"attributes" : [2,3], "ndistinct" : 4},
                ^
 DETAIL:  attnum list duplicate value found: 2
+-- Test input function of pg_dependencies.
+SELECT '[{"attributes" : [2,3], "dependency" : 4, "degree": 1.0000},
+         {"attributes" : [2,-1], "dependency" : 4, "degree": 0.0000},
+         {"attributes" : [2,3,-1], "dependency" : 4, "degree": 0.5000},
+         {"attributes" : [1,3,-1,-2], "dependency" : 4, "degree": 1.0000}]'::pg_dependencies;
+                                                                                                                          pg_dependencies                                                                                                                          
+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
+ [{"attributes": [2, 3], "dependency": 4, "degree": 1.000000}, {"attributes": [2, -1], "dependency": 4, "degree": 0.000000}, {"attributes": [2, 3, -1], "dependency": 4, "degree": 0.500000}, {"attributes": [1, 3, -1, -2], "dependency": 4, "degree": 1.000000}]
+(1 row)
+
+-- error, cannot duplicate attribute
+SELECT '[{"attributes": [6], "dependency": 6, "degree": 0.292508},
+         {"attributes": [-2], "dependency": -1, "degree": 0.113999},
+         {"attributes": [6, -2], "dependency": -1, "degree": 0.348479},
+         {"attributes": [-1, -2], "dependency": 6, "degree": 0.839691}]'::pg_dependencies;
+ERROR:  malformed pg_dependencies: "[{"attributes": [6], "dependency": 6, "degree": 0.292508},
+         {"attributes": [-2], "dependency": -1, "degree": 0.113999},
+         {"attributes": [6, -2], "dependency": -1, "degree": 0.348479},
+         {"attributes": [-1, -2], "dependency": 6, "degree": 0.839691}]"
+LINE 1: SELECT '[{"attributes": [6], "dependency": 6, "degree": 0.29...
+               ^
+DETAIL:  attnum list duplicate value found: 6
 -- Tidy up
 DROP TABLE sb_1, sb_2 CASCADE;
 DROP FUNCTION extstat_small(x numeric);
diff --git a/src/test/regress/sql/stats_ext.sql b/src/test/regress/sql/stats_ext.sql
index e8aa6b58009..6a5fbfd31ad 100644
--- a/src/test/regress/sql/stats_ext.sql
+++ b/src/test/regress/sql/stats_ext.sql
@@ -1844,6 +1844,18 @@ SELECT '[{"attributes" : [2,3], "ndistinct" : 4},
          {"attributes" : [2,3,2], "ndistinct" : 4},
          {"attributes" : [1,3,-1,-2], "ndistinct" : 4}]'::pg_ndistinct;
 
+-- Test input function of pg_dependencies.
+SELECT '[{"attributes" : [2,3], "dependency" : 4, "degree": 1.0000},
+         {"attributes" : [2,-1], "dependency" : 4, "degree": 0.0000},
+         {"attributes" : [2,3,-1], "dependency" : 4, "degree": 0.5000},
+         {"attributes" : [1,3,-1,-2], "dependency" : 4, "degree": 1.0000}]'::pg_dependencies;
+
+-- error, cannot duplicate attribute
+SELECT '[{"attributes": [6], "dependency": 6, "degree": 0.292508},
+         {"attributes": [-2], "dependency": -1, "degree": 0.113999},
+         {"attributes": [6, -2], "dependency": -1, "degree": 0.348479},
+         {"attributes": [-1, -2], "dependency": 6, "degree": 0.839691}]'::pg_dependencies;
+
 -- Tidy up
 DROP TABLE sb_1, sb_2 CASCADE;
 DROP FUNCTION extstat_small(x numeric);
-- 
2.51.1