agora inbox for [email protected]  

help / color / mirror / Atom feed

[PATCH v20 1/8] Row pattern recognition patch for raw parser.
244+ messages / 2 participants
[nested] [flat]

* [PATCH v20 1/8] Row pattern recognition patch for raw parser.
@ 2024-05-24 02:26 Tatsuo Ishii <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Tatsuo Ishii @ 2024-05-24 02:26 UTC (permalink / raw)

---
 src/backend/parser/gram.y       | 222 ++++++++++++++++++++++++++++++--
 src/include/nodes/parsenodes.h  |  67 ++++++++++
 src/include/parser/kwlist.h     |   9 ++
 src/include/parser/parse_node.h |   1 +
 4 files changed, 288 insertions(+), 11 deletions(-)

diff --git a/src/backend/parser/gram.y b/src/backend/parser/gram.y
index 4d582950b7..ef6f25b2f8 100644
--- a/src/backend/parser/gram.y
+++ b/src/backend/parser/gram.y
@@ -679,6 +679,21 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 				json_object_constructor_null_clause_opt
 				json_array_constructor_null_clause_opt
 
+%type <target>	row_pattern_measure_item
+				row_pattern_definition
+%type <node>	opt_row_pattern_common_syntax
+				opt_row_pattern_skip_to
+				row_pattern_subset_item
+				row_pattern_term
+%type <list>	opt_row_pattern_measures
+				row_pattern_measure_list
+				row_pattern_definition_list
+				opt_row_pattern_subset_clause
+				row_pattern_subset_list
+				row_pattern_subset_rhs
+				row_pattern
+%type <boolean>	opt_row_pattern_initial_or_seek
+				first_or_last
 
 /*
  * Non-keyword token types.  These are hard-wired into the "flex" lexer.
@@ -722,7 +737,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	CURRENT_TIME CURRENT_TIMESTAMP CURRENT_USER CURSOR CYCLE
 
 	DATA_P DATABASE DAY_P DEALLOCATE DEC DECIMAL_P DECLARE DEFAULT DEFAULTS
-	DEFERRABLE DEFERRED DEFINER DELETE_P DELIMITER DELIMITERS DEPENDS DEPTH DESC
+	DEFERRABLE DEFERRED DEFINE DEFINER DELETE_P DELIMITER DELIMITERS DEPENDS DEPTH DESC
 	DETACH DICTIONARY DISABLE_P DISCARD DISTINCT DO DOCUMENT_P DOMAIN_P
 	DOUBLE_P DROP
 
@@ -738,7 +753,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	HANDLER HAVING HEADER_P HOLD HOUR_P
 
 	IDENTITY_P IF_P ILIKE IMMEDIATE IMMUTABLE IMPLICIT_P IMPORT_P IN_P INCLUDE
-	INCLUDING INCREMENT INDENT INDEX INDEXES INHERIT INHERITS INITIALLY INLINE_P
+	INCLUDING INCREMENT INDENT INDEX INDEXES INHERIT INHERITS INITIAL INITIALLY INLINE_P
 	INNER_P INOUT INPUT_P INSENSITIVE INSERT INSTEAD INT_P INTEGER
 	INTERSECT INTERVAL INTO INVOKER IS ISNULL ISOLATION
 
@@ -751,7 +766,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	LEADING LEAKPROOF LEAST LEFT LEVEL LIKE LIMIT LISTEN LOAD LOCAL
 	LOCALTIME LOCALTIMESTAMP LOCATION LOCK_P LOCKED LOGGED
 
-	MAPPING MATCH MATCHED MATERIALIZED MAXVALUE MERGE MERGE_ACTION METHOD
+	MAPPING MATCH MATCHED MATERIALIZED MAXVALUE MEASURES MERGE MERGE_ACTION METHOD
 	MINUTE_P MINVALUE MODE MONTH_P MOVE
 
 	NAME_P NAMES NATIONAL NATURAL NCHAR NESTED NEW NEXT NFC NFD NFKC NFKD NO
@@ -763,8 +778,8 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	ORDER ORDINALITY OTHERS OUT_P OUTER_P
 	OVER OVERLAPS OVERLAY OVERRIDING OWNED OWNER
 
-	PARALLEL PARAMETER PARSER PARTIAL PARTITION PARTITIONS PASSING PASSWORD PATH
-	PLACING PLAN PLANS POLICY
+	PARALLEL PARAMETER PARSER PARTIAL PARTITION PARTITIONS PASSING PASSWORD PAST
+	PATH PATTERN_P PERIOD PERMUTE PLACING PLAN PLANS POLICY
 	POSITION PRECEDING PRECISION PRESERVE PREPARE PREPARED PRIMARY
 	PRIOR PRIVILEGES PROCEDURAL PROCEDURE PROCEDURES PROGRAM PUBLICATION
 
@@ -775,12 +790,13 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 	RESET RESTART RESTRICT RETURN RETURNING RETURNS REVOKE RIGHT ROLE ROLLBACK ROLLUP
 	ROUTINE ROUTINES ROW ROWS RULE
 
-	SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SELECT
+	SAVEPOINT SCALAR SCHEMA SCHEMAS SCROLL SEARCH SECOND_P SECURITY SEEK SELECT
 	SEQUENCE SEQUENCES
+
 	SERIALIZABLE SERVER SESSION SESSION_USER SET SETS SETOF SHARE SHOW
 	SIMILAR SIMPLE SKIP SMALLINT SNAPSHOT SOME SPLIT SOURCE SQL_P STABLE STANDALONE_P
 	START STATEMENT STATISTICS STDIN STDOUT STORAGE STORED STRICT_P STRING_P STRIP_P
-	SUBSCRIPTION SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER
+	SUBSCRIPTION SUBSET SUBSTRING SUPPORT SYMMETRIC SYSID SYSTEM_P SYSTEM_USER
 
 	TABLE TABLES TABLESAMPLE TABLESPACE TARGET TEMP TEMPLATE TEMPORARY TEXT_P THEN
 	TIES TIME TIMESTAMP TO TRAILING TRANSACTION TRANSFORM
@@ -889,6 +905,7 @@ static Node *makeRecursiveViewSelect(char *relname, List *aliases, Node *query);
 %nonassoc	UNBOUNDED NESTED /* ideally would have same precedence as IDENT */
 %nonassoc	IDENT PARTITION RANGE ROWS GROUPS PRECEDING FOLLOWING CUBE ROLLUP
 			SET KEYS OBJECT_P SCALAR VALUE_P WITH WITHOUT PATH
+			MEASURES AFTER INITIAL SEEK PATTERN_P
 %left		Op OPERATOR		/* multi-character ops and user-defined operators */
 %left		'+' '-'
 %left		'*' '/' '%'
@@ -16287,7 +16304,8 @@ over_clause: OVER window_specification
 		;
 
 window_specification: '(' opt_existing_window_name opt_partition_clause
-						opt_sort_clause opt_frame_clause ')'
+						opt_sort_clause opt_row_pattern_measures opt_frame_clause
+						opt_row_pattern_common_syntax ')'
 				{
 					WindowDef  *n = makeNode(WindowDef);
 
@@ -16295,10 +16313,12 @@ window_specification: '(' opt_existing_window_name opt_partition_clause
 					n->refname = $2;
 					n->partitionClause = $3;
 					n->orderClause = $4;
+					n->rowPatternMeasures = $5;
 					/* copy relevant fields of opt_frame_clause */
-					n->frameOptions = $5->frameOptions;
-					n->startOffset = $5->startOffset;
-					n->endOffset = $5->endOffset;
+					n->frameOptions = $6->frameOptions;
+					n->startOffset = $6->startOffset;
+					n->endOffset = $6->endOffset;
+					n->rpCommonSyntax = (RPCommonSyntax *)$7;
 					n->location = @1;
 					$$ = n;
 				}
@@ -16322,6 +16342,31 @@ opt_partition_clause: PARTITION BY expr_list		{ $$ = $3; }
 			| /*EMPTY*/								{ $$ = NIL; }
 		;
 
+/*
+ * ROW PATTERN_P MEASURES
+ */
+opt_row_pattern_measures: MEASURES row_pattern_measure_list	{ $$ = $2; }
+			| /*EMPTY*/								{ $$ = NIL; }
+		;
+
+row_pattern_measure_list:
+			row_pattern_measure_item
+					{ $$ = list_make1($1); }
+			| row_pattern_measure_list ',' row_pattern_measure_item
+					{ $$ = lappend($1, $3); }
+		;
+
+row_pattern_measure_item:
+			a_expr AS ColLabel
+				{
+					$$ = makeNode(ResTarget);
+					$$->name = $3;
+					$$->indirection = NIL;
+					$$->val = (Node *) $1;
+					$$->location = @1;
+				}
+		;
+
 /*
  * For frame clauses, we return a WindowDef, but only some fields are used:
  * frameOptions, startOffset, and endOffset.
@@ -16481,6 +16526,143 @@ opt_window_exclusion_clause:
 			| /*EMPTY*/				{ $$ = 0; }
 		;
 
+opt_row_pattern_common_syntax:
+opt_row_pattern_skip_to opt_row_pattern_initial_or_seek
+				PATTERN_P '(' row_pattern ')'
+				opt_row_pattern_subset_clause
+				DEFINE row_pattern_definition_list
+			{
+				RPCommonSyntax *n = makeNode(RPCommonSyntax);
+				n->rpSkipTo = ((RPCommonSyntax *)$1)->rpSkipTo;
+				n->rpSkipVariable = ((RPCommonSyntax *)$1)->rpSkipVariable;
+				n->initial = $2;
+				n->rpPatterns = $5;
+				n->rpSubsetClause = $7;
+				n->rpDefs = $9;
+				$$ = (Node *) n;
+			}
+			| /*EMPTY*/		{ $$ = NULL; }
+	;
+
+opt_row_pattern_skip_to:
+			AFTER MATCH SKIP TO NEXT ROW
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_NEXT_ROW;
+					n->rpSkipVariable = NULL;
+					$$ = (Node *) n;
+			}
+			| AFTER MATCH SKIP PAST LAST_P ROW
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_PAST_LAST_ROW;
+					n->rpSkipVariable = NULL;
+					$$ = (Node *) n;
+				}
+			| AFTER MATCH SKIP TO first_or_last ColId
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = $5? ST_FIRST_VARIABLE : ST_LAST_VARIABLE;
+					n->rpSkipVariable = $6;
+					$$ = (Node *) n;
+				}
+/*
+			| AFTER MATCH SKIP TO LAST_P ColId		%prec LAST_P
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_LAST_VARIABLE;
+					n->rpSkipVariable = $6;
+					$$ = n;
+				}
+			| AFTER MATCH SKIP TO ColId
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					n->rpSkipTo = ST_VARIABLE;
+					n->rpSkipVariable = $5;
+					$$ = n;
+				}
+*/
+			| /*EMPTY*/
+				{
+					RPCommonSyntax *n = makeNode(RPCommonSyntax);
+					/* temporary set default to ST_NEXT_ROW */
+					n->rpSkipTo = ST_PAST_LAST_ROW;
+					n->rpSkipVariable = NULL;
+					$$ = (Node *) n;
+				}
+	;
+
+first_or_last:
+			FIRST_P		{ $$ = true; }
+			| LAST_P	{ $$ = false; }
+	;
+
+opt_row_pattern_initial_or_seek:
+			INITIAL			{ $$ = true; }
+			| SEEK
+				{
+					ereport(ERROR,
+							(errcode(ERRCODE_SYNTAX_ERROR),
+							 errmsg("SEEK is not supported"),
+							 errhint("Use INITIAL."),
+							 parser_errposition(@1)));
+				}
+			| /*EMPTY*/		{ $$ = true; }
+		;
+
+row_pattern:
+			row_pattern_term							{ $$ = list_make1($1); }
+			| row_pattern row_pattern_term				{ $$ = lappend($1, $2); }
+		;
+
+row_pattern_term:
+			ColId	{ $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "", (Node *)makeString($1), NULL, @1); }
+			| ColId '*'	{ $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "*", (Node *)makeString($1), NULL, @1); }
+			| ColId '+'	{ $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "+", (Node *)makeString($1), NULL, @1); }
+			| ColId '?'	{ $$ = (Node *) makeSimpleA_Expr(AEXPR_OP, "?", (Node *)makeString($1), NULL, @1); }
+		;
+
+opt_row_pattern_subset_clause:
+			SUBSET row_pattern_subset_list	{ $$ = $2; }
+			| /*EMPTY*/												{ $$ = NIL; }
+		;
+
+row_pattern_subset_list:
+			row_pattern_subset_item									{ $$ = list_make1($1); }
+			| row_pattern_subset_list ',' row_pattern_subset_item	{ $$ = lappend($1, $3); }
+			| /*EMPTY*/												{ $$ = NIL; }
+		;
+
+row_pattern_subset_item: ColId '=' '(' row_pattern_subset_rhs ')'
+			{
+				RPSubsetItem *n = makeNode(RPSubsetItem);
+				n->name = $1;
+				n->rhsVariable = $4;
+				$$ = (Node *) n;
+			}
+		;
+
+row_pattern_subset_rhs:
+			ColId								{ $$ = list_make1(makeStringConst($1, @1)); }
+			| row_pattern_subset_rhs ',' ColId	{ $$ = lappend($1, makeStringConst($3, @1)); }
+			| /*EMPTY*/							{ $$ = NIL; }
+		;
+
+row_pattern_definition_list:
+			row_pattern_definition										{ $$ = list_make1($1); }
+			| row_pattern_definition_list ',' row_pattern_definition	{ $$ = lappend($1, $3); }
+		;
+
+row_pattern_definition:
+			ColId AS a_expr
+				{
+					$$ = makeNode(ResTarget);
+					$$->name = $1;
+					$$->indirection = NIL;
+					$$->val = (Node *) $3;
+					$$->location = @1;
+				}
+		;
 
 /*
  * Supporting nonterminals for expressions.
@@ -17691,6 +17873,7 @@ unreserved_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INLINE_P
 			| INPUT_P
 			| INSENSITIVE
@@ -17719,6 +17902,7 @@ unreserved_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| METHOD
 			| MINUTE_P
@@ -17764,7 +17948,11 @@ unreserved_keyword:
 			| PARTITIONS
 			| PASSING
 			| PASSWORD
+			| PAST
 			| PATH
+			| PATTERN_P
+			| PERIOD
+			| PERMUTE
 			| PLAN
 			| PLANS
 			| POLICY
@@ -17817,6 +18005,7 @@ unreserved_keyword:
 			| SEARCH
 			| SECOND_P
 			| SECURITY
+			| SEEK
 			| SEQUENCE
 			| SEQUENCES
 			| SERIALIZABLE
@@ -17845,6 +18034,7 @@ unreserved_keyword:
 			| STRING_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUPPORT
 			| SYSID
 			| SYSTEM_P
@@ -18039,6 +18229,7 @@ reserved_keyword:
 			| CURRENT_USER
 			| DEFAULT
 			| DEFERRABLE
+			| DEFINE
 			| DESC
 			| DISTINCT
 			| DO
@@ -18202,6 +18393,7 @@ bare_label_keyword:
 			| DEFAULTS
 			| DEFERRABLE
 			| DEFERRED
+			| DEFINE
 			| DEFINER
 			| DELETE_P
 			| DELIMITER
@@ -18279,6 +18471,7 @@ bare_label_keyword:
 			| INDEXES
 			| INHERIT
 			| INHERITS
+			| INITIAL
 			| INITIALLY
 			| INLINE_P
 			| INNER_P
@@ -18333,6 +18526,7 @@ bare_label_keyword:
 			| MATCHED
 			| MATERIALIZED
 			| MAXVALUE
+			| MEASURES
 			| MERGE
 			| MERGE_ACTION
 			| METHOD
@@ -18390,7 +18584,11 @@ bare_label_keyword:
 			| PARTITIONS
 			| PASSING
 			| PASSWORD
+			| PAST
 			| PATH
+			| PATTERN_P
+			| PERIOD
+			| PERMUTE
 			| PLACING
 			| PLAN
 			| PLANS
@@ -18449,6 +18647,7 @@ bare_label_keyword:
 			| SCROLL
 			| SEARCH
 			| SECURITY
+			| SEEK
 			| SELECT
 			| SEQUENCE
 			| SEQUENCES
@@ -18483,6 +18682,7 @@ bare_label_keyword:
 			| STRING_P
 			| STRIP_P
 			| SUBSCRIPTION
+			| SUBSET
 			| SUBSTRING
 			| SUPPORT
 			| SYMMETRIC
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index ddfed02db2..c8a2eed08f 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -550,6 +550,48 @@ typedef struct SortBy
 	ParseLoc	location;		/* operator location, or -1 if none/unknown */
 } SortBy;
 
+/*
+ * AFTER MATCH row pattern skip to types in row pattern common syntax
+ */
+typedef enum RPSkipTo
+{
+	ST_NONE,					/* AFTER MATCH omitted */
+	ST_NEXT_ROW,				/* SKIP TO NEXT ROW */
+	ST_PAST_LAST_ROW,			/* SKIP TO PAST LAST ROW */
+	ST_FIRST_VARIABLE,			/* SKIP TO FIRST variable name */
+	ST_LAST_VARIABLE,			/* SKIP TO LAST variable name */
+	ST_VARIABLE					/* SKIP TO variable name */
+}			RPSkipTo;
+
+/*
+ * Row Pattern SUBSET clause item
+ */
+typedef struct RPSubsetItem
+{
+	NodeTag		type;
+	char	   *name;			/* Row Pattern SUBSET clause variable name */
+	List	   *rhsVariable;	/* Row Pattern SUBSET rhs variables (list of
+								 * char *string) */
+}			RPSubsetItem;
+
+/*
+ * RowPatternCommonSyntax - raw representation of row pattern common syntax
+ *
+ */
+typedef struct RPCommonSyntax
+{
+	NodeTag		type;
+	RPSkipTo	rpSkipTo;		/* Row Pattern AFTER MATCH SKIP type */
+	char	   *rpSkipVariable; /* Row Pattern Skip To variable name, if any */
+	bool		initial;		/* true if <row pattern initial or seek> is
+								 * initial */
+	List	   *rpPatterns;		/* PATTERN variables (list of A_Expr) */
+	List	   *rpSubsetClause; /* row pattern subset clause (list of
+								 * RPSubsetItem), if any */
+	List	   *rpDefs;			/* row pattern definitions clause (list of
+								 * ResTarget) */
+}			RPCommonSyntax;
+
 /*
  * WindowDef - raw representation of WINDOW and OVER clauses
  *
@@ -565,6 +607,9 @@ typedef struct WindowDef
 	char	   *refname;		/* referenced window name, if any */
 	List	   *partitionClause;	/* PARTITION BY expression list */
 	List	   *orderClause;	/* ORDER BY (list of SortBy) */
+	List	   *rowPatternMeasures; /* row pattern measures (list of
+									 * ResTarget) */
+	RPCommonSyntax *rpCommonSyntax; /* row pattern common syntax */
 	int			frameOptions;	/* frame_clause options, see below */
 	Node	   *startOffset;	/* expression for starting bound, if any */
 	Node	   *endOffset;		/* expression for ending bound, if any */
@@ -1533,6 +1578,11 @@ typedef struct GroupingSet
  * the orderClause might or might not be copied (see copiedOrder); the framing
  * options are never copied, per spec.
  *
+ * "defineClause" is Row Pattern Recognition DEFINE clause (list of
+ * TargetEntry). TargetEntry.resname represents row pattern definition
+ * variable name. "patternVariable" and "patternRegexp" represents PATTERN
+ * clause.
+ *
  * The information relevant for the query jumbling is the partition clause
  * type and its bounds.
  */
@@ -1562,6 +1612,23 @@ typedef struct WindowClause
 	Index		winref;			/* ID referenced by window functions */
 	/* did we copy orderClause from refname? */
 	bool		copiedOrder pg_node_attr(query_jumble_ignore);
+	/* Row Pattern AFTER MACH SKIP clause */
+	RPSkipTo	rpSkipTo;		/* Row Pattern Skip To type */
+	char	   *rpSkipVariable; /* Row Pattern Skip To variable */
+	bool		initial;		/* true if <row pattern initial or seek> is
+								 * initial */
+	/* Row Pattern DEFINE clause (list of TargetEntry) */
+	List	   *defineClause;
+	/* Row Pattern DEFINE variable initial names (list of String) */
+	List	   *defineInitial;
+	/* Row Pattern PATTERN variable name (list of String) */
+	List	   *patternVariable;
+
+	/*
+	 * Row Pattern PATTERN regular expression quantifier ('+' or ''. list of
+	 * String)
+	 */
+	List	   *patternRegexp;
 } WindowClause;
 
 /*
diff --git a/src/include/parser/kwlist.h b/src/include/parser/kwlist.h
index f7fe834cf4..df49492629 100644
--- a/src/include/parser/kwlist.h
+++ b/src/include/parser/kwlist.h
@@ -129,6 +129,7 @@ PG_KEYWORD("default", DEFAULT, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("defaults", DEFAULTS, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("deferrable", DEFERRABLE, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("deferred", DEFERRED, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("define", DEFINE, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("definer", DEFINER, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("delete", DELETE_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("delimiter", DELIMITER, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -215,6 +216,7 @@ PG_KEYWORD("index", INDEX, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("indexes", INDEXES, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inherit", INHERIT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inherits", INHERITS, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("initial", INITIAL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("initially", INITIALLY, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inline", INLINE_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("inner", INNER_P, TYPE_FUNC_NAME_KEYWORD, BARE_LABEL)
@@ -273,6 +275,7 @@ PG_KEYWORD("match", MATCH, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("matched", MATCHED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("materialized", MATERIALIZED, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("maxvalue", MAXVALUE, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("measures", MEASURES, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("merge", MERGE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("merge_action", MERGE_ACTION, COL_NAME_KEYWORD, BARE_LABEL)
 PG_KEYWORD("method", METHOD, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -338,7 +341,11 @@ PG_KEYWORD("partition", PARTITION, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("partitions", PARTITIONS, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("passing", PASSING, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("password", PASSWORD, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("past", PAST, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("path", PATH, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("pattern", PATTERN_P, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("period", PERIOD, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("permute", PERMUTE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("placing", PLACING, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("plan", PLAN, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("plans", PLANS, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -400,6 +407,7 @@ PG_KEYWORD("scroll", SCROLL, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("search", SEARCH, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("second", SECOND_P, UNRESERVED_KEYWORD, AS_LABEL)
 PG_KEYWORD("security", SECURITY, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("seek", SEEK, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("select", SELECT, RESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("sequence", SEQUENCE, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("sequences", SEQUENCES, UNRESERVED_KEYWORD, BARE_LABEL)
@@ -434,6 +442,7 @@ PG_KEYWORD("strict", STRICT_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("string", STRING_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("strip", STRIP_P, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("subscription", SUBSCRIPTION, UNRESERVED_KEYWORD, BARE_LABEL)
+PG_KEYWORD("subset", SUBSET, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("substring", SUBSTRING, COL_NAME_KEYWORD, BARE_LABEL)
 PG_KEYWORD("support", SUPPORT, UNRESERVED_KEYWORD, BARE_LABEL)
 PG_KEYWORD("symmetric", SYMMETRIC, RESERVED_KEYWORD, BARE_LABEL)
diff --git a/src/include/parser/parse_node.h b/src/include/parser/parse_node.h
index 5b781d87a9..66935afff8 100644
--- a/src/include/parser/parse_node.h
+++ b/src/include/parser/parse_node.h
@@ -51,6 +51,7 @@ typedef enum ParseExprKind
 	EXPR_KIND_WINDOW_FRAME_RANGE,	/* window frame clause with RANGE */
 	EXPR_KIND_WINDOW_FRAME_ROWS,	/* window frame clause with ROWS */
 	EXPR_KIND_WINDOW_FRAME_GROUPS,	/* window frame clause with GROUPS */
+	EXPR_KIND_RPR_DEFINE,		/* DEFINE */
 	EXPR_KIND_SELECT_TARGET,	/* SELECT target list item */
 	EXPR_KIND_INSERT_TARGET,	/* INSERT target list item */
 	EXPR_KIND_UPDATE_SOURCE,	/* UPDATE assignment source item */
-- 
2.25.1


----Next_Part(Fri_May_24_11_39_19_2024_763)--
Content-Type: Text/X-Patch; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline;
 filename="v20-0002-Row-pattern-recognition-patch-parse-analysis.patch"



^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl |  8 ++--
 src/backend/commands/prepare.c             | 43 +++++++++++++++++++--
 src/test/regress/expected/prepare.out      | 44 +++++++++++++---------
 src/test/regress/sql/prepare.sql           |  2 +-
 4 files changed, 72 insertions(+), 25 deletions(-)

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 6af5ac1da18..535c4770095 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 34b6410d6a2..11b330ab73d 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--biRhQYMBrGQlqcCN--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl |  8 ++--
 src/backend/commands/prepare.c             | 43 +++++++++++++++++++--
 src/test/regress/expected/prepare.out      | 44 +++++++++++++---------
 src/test/regress/sql/prepare.sql           |  2 +-
 4 files changed, 72 insertions(+), 25 deletions(-)

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 6af5ac1da18..535c4770095 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 34b6410d6a2..11b330ab73d 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--biRhQYMBrGQlqcCN--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl |  8 ++--
 src/backend/commands/prepare.c             | 43 +++++++++++++++++++--
 src/test/regress/expected/prepare.out      | 44 +++++++++++++---------
 src/test/regress/sql/prepare.sql           |  2 +-
 4 files changed, 72 insertions(+), 25 deletions(-)

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 6af5ac1da18..535c4770095 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 34b6410d6a2..11b330ab73d 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--biRhQYMBrGQlqcCN--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl |  8 ++--
 src/backend/commands/prepare.c             | 43 +++++++++++++++++++--
 src/test/regress/expected/prepare.out      | 44 +++++++++++++---------
 src/test/regress/sql/prepare.sql           |  2 +-
 4 files changed, 72 insertions(+), 25 deletions(-)

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 6af5ac1da18..535c4770095 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 34b6410d6a2..11b330ab73d 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--biRhQYMBrGQlqcCN--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl |  8 ++--
 src/backend/commands/prepare.c             | 43 +++++++++++++++++++--
 src/test/regress/expected/prepare.out      | 44 +++++++++++++---------
 src/test/regress/sql/prepare.sql           |  2 +-
 4 files changed, 72 insertions(+), 25 deletions(-)

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 6af5ac1da18..535c4770095 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 34b6410d6a2..11b330ab73d 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--biRhQYMBrGQlqcCN--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl |  8 ++--
 src/backend/commands/prepare.c             | 43 +++++++++++++++++++--
 src/test/regress/expected/prepare.out      | 44 +++++++++++++---------
 src/test/regress/sql/prepare.sql           |  2 +-
 4 files changed, 72 insertions(+), 25 deletions(-)

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 6af5ac1da18..535c4770095 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 34b6410d6a2..11b330ab73d 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--biRhQYMBrGQlqcCN--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl |  8 ++--
 src/backend/commands/prepare.c             | 43 +++++++++++++++++++--
 src/test/regress/expected/prepare.out      | 44 +++++++++++++---------
 src/test/regress/sql/prepare.sql           |  2 +-
 4 files changed, 72 insertions(+), 25 deletions(-)

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 6af5ac1da18..535c4770095 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 34b6410d6a2..11b330ab73d 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--biRhQYMBrGQlqcCN--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl |  8 ++--
 src/backend/commands/prepare.c             | 43 +++++++++++++++++++--
 src/test/regress/expected/prepare.out      | 44 +++++++++++++---------
 src/test/regress/sql/prepare.sql           |  2 +-
 4 files changed, 72 insertions(+), 25 deletions(-)

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 6af5ac1da18..535c4770095 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 34b6410d6a2..11b330ab73d 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--biRhQYMBrGQlqcCN--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl |  8 ++--
 src/backend/commands/prepare.c             | 43 +++++++++++++++++++--
 src/test/regress/expected/prepare.out      | 44 +++++++++++++---------
 src/test/regress/sql/prepare.sql           |  2 +-
 4 files changed, 72 insertions(+), 25 deletions(-)

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 6af5ac1da18..535c4770095 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 34b6410d6a2..11b330ab73d 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--biRhQYMBrGQlqcCN--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  1 +
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 26 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index c27e9529bb6..ac967687796 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -36,6 +36,7 @@ REGRESS = \
 	parallel \
 	plancache \
 	squashing \
+	prepare \
 	cleanup \
 	oldextversions
 
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 9d78cb88b7d..c9e1d446d39 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -58,6 +58,7 @@ tests += {
       'parallel',
       'plancache',
       'squashing',
+      'prepare',
       'cleanup',
       'oldextversions',
     ],
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--xBRJzsblsXcilRYX--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <[email protected]>
  0 siblings, 0 replies; 244+ messages in thread

From: Julien Rouhaud @ 2025-12-24 14:31 UTC (permalink / raw)

When a multi statements query string contains one PREPARE statement (or
multiple), the whole query string was saved in the cached plan.  This is
wasteful as that string can be artitrarily big, but it can also confusing as
some other parts like pg_prepared_statements will output the saved query string
as-is.

This commit changes this behavior and only stores the part of the query string
that correspond to any given PREPARED statement, similarly to how it's already
done in pg_stat_statements.
---
 contrib/auto_explain/t/001_auto_explain.pl    |  8 +--
 contrib/pg_stat_statements/Makefile           |  2 +-
 .../pg_stat_statements/expected/prepare.out   | 53 +++++++++++++++++++
 contrib/pg_stat_statements/meson.build        |  1 +
 contrib/pg_stat_statements/sql/prepare.sql    | 15 ++++++
 src/backend/commands/prepare.c                | 45 ++++++++++++++--
 src/test/regress/expected/prepare.out         | 44 +++++++++------
 src/test/regress/sql/prepare.sql              |  2 +-
 8 files changed, 143 insertions(+), 27 deletions(-)
 create mode 100644 contrib/pg_stat_statements/expected/prepare.out
 create mode 100644 contrib/pg_stat_statements/sql/prepare.sql

diff --git a/contrib/auto_explain/t/001_auto_explain.pl b/contrib/auto_explain/t/001_auto_explain.pl
index 5f673bd14c1..f2d8625f8bb 100644
--- a/contrib/auto_explain/t/001_auto_explain.pl
+++ b/contrib/auto_explain/t/001_auto_explain.pl
@@ -60,7 +60,7 @@ $log_contents = query_log($node,
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1;/,
+	qr/Query Text: PREPARE get_proc\(name\) AS SELECT \* FROM pg_proc WHERE proname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -82,7 +82,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 like(
@@ -98,7 +98,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1;/,
+	qr/Query Text: PREPARE get_type\(name\) AS SELECT \* FROM pg_type WHERE typname = \$1/,
 	"prepared query text logged, text mode");
 
 unlike(
@@ -164,7 +164,7 @@ $log_contents = query_log(
 
 like(
 	$log_contents,
-	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1;"/,
+	qr/"Query Text": "PREPARE get_class\(name\) AS SELECT \* FROM pg_class WHERE relname = \$1"/,
 	"prepared query text logged, json mode");
 
 like(
diff --git a/contrib/pg_stat_statements/Makefile b/contrib/pg_stat_statements/Makefile
index fe0478ac552..9a6bda90070 100644
--- a/contrib/pg_stat_statements/Makefile
+++ b/contrib/pg_stat_statements/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_SL += $(filter -lm, $(LIBS))
 REGRESS_OPTS = --temp-config $(top_srcdir)/contrib/pg_stat_statements/pg_stat_statements.conf
 REGRESS = select dml cursors utility level_tracking planning \
 	user_activity wal entry_timestamp privileges extended \
-	parallel plancache cleanup oldextversions squashing
+	parallel plancache cleanup oldextversions squashing prepare
 # Disabled because these tests require "shared_preload_libraries=pg_stat_statements",
 # which typical installcheck users do not have (e.g. buildfarm clients).
 NO_INSTALLCHECK = 1
diff --git a/contrib/pg_stat_statements/expected/prepare.out b/contrib/pg_stat_statements/expected/prepare.out
new file mode 100644
index 00000000000..010e289c1b0
--- /dev/null
+++ b/contrib/pg_stat_statements/expected/prepare.out
@@ -0,0 +1,53 @@
+-- Tests for PREPARE
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+ ?column? 
+----------
+        1
+(1 row)
+
+ ?column? | ?column? 
+----------+----------
+        1 |        1
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | SELECT $1
+     1 |    1 | SELECT $1, $2
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+ t 
+---
+ t
+(1 row)
+
+EXECUTE p1;
+ ?column? 
+----------
+        1
+(1 row)
+
+EXECUTE p2(0);
+ ?column? 
+----------
+        0
+(1 row)
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+ calls | rows |                       query                        
+-------+------+----------------------------------------------------
+     1 |    1 | PREPARE p1 AS SELECT 1
+     1 |    1 | PREPARE p2(int) AS SELECT 2 * $1
+     1 |    1 | SELECT pg_stat_statements_reset() IS NOT NULL AS t
+(3 rows)
+
diff --git a/contrib/pg_stat_statements/meson.build b/contrib/pg_stat_statements/meson.build
index 079a8eb5afc..65258651bd2 100644
--- a/contrib/pg_stat_statements/meson.build
+++ b/contrib/pg_stat_statements/meson.build
@@ -59,6 +59,7 @@ tests += {
       'cleanup',
       'oldextversions',
       'squashing',
+      'prepare',
     ],
     'regress_args': ['--temp-config', files('pg_stat_statements.conf')],
     # Disabled because these tests require
diff --git a/contrib/pg_stat_statements/sql/prepare.sql b/contrib/pg_stat_statements/sql/prepare.sql
new file mode 100644
index 00000000000..a6bc5de4430
--- /dev/null
+++ b/contrib/pg_stat_statements/sql/prepare.sql
@@ -0,0 +1,15 @@
+-- Tests for PREPARE
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+-- Test that prepared statements in a multi-query string behaves as expected
+SELECT 1\;PREPARE p1 AS SELECT 1\; PREPARE p2(int) AS SELECT 2 * $1\; SELECT 1, 1;
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
+
+SELECT pg_stat_statements_reset() IS NOT NULL AS t;
+
+EXECUTE p1;
+EXECUTE p2(0);
+
+SELECT calls, rows, query FROM pg_stat_statements ORDER BY query COLLATE "C";
diff --git a/src/backend/commands/prepare.c b/src/backend/commands/prepare.c
index 5b86a727587..b8fe3dd5302 100644
--- a/src/backend/commands/prepare.c
+++ b/src/backend/commands/prepare.c
@@ -27,6 +27,7 @@
 #include "commands/prepare.h"
 #include "funcapi.h"
 #include "nodes/nodeFuncs.h"
+#include "nodes/queryjumble.h"
 #include "parser/parse_coerce.h"
 #include "parser/parse_collate.h"
 #include "parser/parse_expr.h"
@@ -64,6 +65,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	Oid		   *argtypes = NULL;
 	int			nargs;
 	List	   *query_list;
+	const char *new_query;
 
 	/*
 	 * Disallow empty-string statement name (conflicts with protocol-level
@@ -80,14 +82,49 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 */
 	rawstmt = makeNode(RawStmt);
 	rawstmt->stmt = stmt->query;
-	rawstmt->stmt_location = stmt_location;
-	rawstmt->stmt_len = stmt_len;
+
+	/*
+	 * Extract the query text if possible.
+	 *
+	 * If we have a statement location, we can extract the relevant part of the
+	 * possibly multi-statement query string.  If not just use what we were
+	 * given.
+	 */
+	if (stmt_location < 0)
+	{
+		rawstmt->stmt_location = stmt_location;
+		rawstmt->stmt_len = stmt_len;
+		new_query = pstate->p_sourcetext;
+	}
+	else
+	{
+		const char *cleaned;
+		char	   *tmp;
+
+		rawstmt->stmt_len = stmt_len;
+		cleaned = CleanQuerytext(pstate->p_sourcetext, &stmt_location,
+								 &rawstmt->stmt_len);
+
+		if (rawstmt->stmt_len == 0)
+			rawstmt->stmt_len = strlen(cleaned);
+
+		/*
+		 * CleanQuerytext() removes any leading whitespace and returns a
+		 * pointer to the first actual character, so the cleaned query string
+		 * is guaranteed to start at offset 0.
+		 */
+		rawstmt->stmt_location = 0;
+		tmp = palloc(rawstmt->stmt_len + 1);
+		strlcpy(tmp, cleaned, rawstmt->stmt_len + 1);
+
+		new_query = tmp;
+	}
 
 	/*
 	 * Create the CachedPlanSource before we do parse analysis, since it needs
 	 * to see the unmodified raw parse tree.
 	 */
-	plansource = CreateCachedPlan(rawstmt, pstate->p_sourcetext,
+	plansource = CreateCachedPlan(rawstmt, new_query,
 								  CreateCommandTag(stmt->query));
 
 	/* Transform list of TypeNames to array of type OIDs */
@@ -116,7 +153,7 @@ PrepareQuery(ParseState *pstate, PrepareStmt *stmt,
 	 * information about unknown parameters to be deduced from context.
 	 * Rewrite the query. The result could be 0, 1, or many queries.
 	 */
-	query_list = pg_analyze_and_rewrite_varparams(rawstmt, pstate->p_sourcetext,
+	query_list = pg_analyze_and_rewrite_varparams(rawstmt, new_query,
 												  &argtypes, &nargs, NULL);
 
 	/* Finish filling in the CachedPlanSource */
diff --git a/src/test/regress/expected/prepare.out b/src/test/regress/expected/prepare.out
index 5815e17b39c..c645a4e5d0e 100644
--- a/src/test/regress/expected/prepare.out
+++ b/src/test/regress/expected/prepare.out
@@ -6,7 +6,17 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+-----------+-----------------+--------------
 (0 rows)
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
+ ?column? 
+----------
+ bingo
+(1 row)
+
+ ?column? 
+----------
+       42
+(1 row)
+
 EXECUTE q1;
  a 
 ---
@@ -14,9 +24,9 @@ EXECUTE q1;
 (1 row)
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 1 AS a; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 1 AS a | {}              | {integer}
 (1 row)
 
 -- should fail
@@ -33,18 +43,18 @@ EXECUTE q1;
 
 PREPARE q2 AS SELECT 2 AS b;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q1   | PREPARE q1 AS SELECT 2;      | {}              | {integer}
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q1   | PREPARE q1 AS SELECT 2      | {}              | {integer}
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (2 rows)
 
 -- sql92 syntax
 DEALLOCATE PREPARE q1;
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
- name |          statement           | parameter_types | result_types 
-------+------------------------------+-----------------+--------------
- q2   | PREPARE q2 AS SELECT 2 AS b; | {}              | {integer}
+ name |          statement          | parameter_types | result_types 
+------+-----------------------------+-----------------+--------------
+ q2   | PREPARE q2 AS SELECT 2 AS b | {}              | {integer}
 (1 row)
 
 DEALLOCATE PREPARE q2;
@@ -168,20 +178,20 @@ SELECT name, statement, parameter_types, result_types FROM pg_prepared_statement
 ------+------------------------------------------------------------------+----------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------
  q2   | PREPARE q2(text) AS                                             +| {text}                                             | {name,boolean,boolean}
       |         SELECT datname, datistemplate, datallowconn             +|                                                    | 
-      |         FROM pg_database WHERE datname = $1;                     |                                                    | 
+      |         FROM pg_database WHERE datname = $1                      |                                                    | 
  q3   | PREPARE q3(text, int, float, boolean, smallint) AS              +| {text,integer,"double precision",boolean,smallint} | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE string4 = $1 AND (four = $2 OR+|                                                    | 
       |         ten = $3::bigint OR true = $4 OR odd = $5::int)         +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q5   | PREPARE q5(int, text) AS                                        +| {integer,text}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
       |         SELECT * FROM tenk1 WHERE unique1 = $1 OR stringu1 = $2 +|                                                    | 
-      |         ORDER BY unique1;                                        |                                                    | 
+      |         ORDER BY unique1                                         |                                                    | 
  q6   | PREPARE q6 AS                                                   +| {integer,name}                                     | {integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,integer,name,name,name}
-      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2;    |                                                    | 
+      |     SELECT * FROM tenk1 WHERE unique1 = $1 AND stringu1 = $2     |                                                    | 
  q7   | PREPARE q7(unknown) AS                                          +| {path}                                             | {text,path}
-      |     SELECT * FROM road WHERE thepath = $1;                       |                                                    | 
+      |     SELECT * FROM road WHERE thepath = $1                        |                                                    | 
  q8   | PREPARE q8 AS                                                   +| {integer,name}                                     | 
-      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1;           |                                                    | 
+      |     UPDATE tenk1 SET stringu1 = $2 WHERE unique1 = $1            |                                                    | 
 (6 rows)
 
 -- test DEALLOCATE ALL;
diff --git a/src/test/regress/sql/prepare.sql b/src/test/regress/sql/prepare.sql
index c6098dc95ce..0e7fe44725e 100644
--- a/src/test/regress/sql/prepare.sql
+++ b/src/test/regress/sql/prepare.sql
@@ -4,7 +4,7 @@
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
 
-PREPARE q1 AS SELECT 1 AS a;
+SELECT 'bingo'\;  PREPARE q1 AS SELECT 1 AS a \; SELECT 42;
 EXECUTE q1;
 
 SELECT name, statement, parameter_types, result_types FROM pg_prepared_statements;
-- 
2.52.0


--soawQPnav6xcFtRL--





^ permalink  raw  reply  [nested|flat] 244+ messages in thread