agora inbox for pgsql-hackers@postgresql.org  

help / color / mirror / Atom feed

[PATCH v29 07/11] Add DISTINCT support for IVM
916+ messages / 2 participants
[nested] [flat]

* [PATCH v29 07/11] Add DISTINCT support for IVM
@ 2023-05-31 10:08 Yugo Nagata <nagata@sraoss.co.jp>
  0 siblings, 0 replies; 916+ messages in thread

From: Yugo Nagata @ 2023-05-31 10:08 UTC (permalink / raw)

When IMMV is created with DISTINCT, multiplicity of tuples is
counted and stored in  "__ivm_count__" column, which is a hidden
column of IMMV.  The value in __ivm_count__ is updated when IMMV
is maintained incrementally. A tuple in IMMV can be removed if
and only if the count becomes zero.
---
 src/backend/commands/createas.c     | 141 ++++++++++++++++++++------
 src/backend/commands/indexcmds.c    |  40 ++++++++
 src/backend/commands/matview.c      | 148 ++++++++++++++++++++++++++--
 src/backend/commands/tablecmds.c    |   9 ++
 src/backend/parser/parse_relation.c |  18 +++-
 src/backend/rewrite/rewriteDefine.c |   3 +-
 src/include/commands/createas.h     |   2 +
 src/include/nodes/parsenodes.h      |   1 +
 8 files changed, 317 insertions(+), 45 deletions(-)

diff --git a/src/backend/commands/createas.c b/src/backend/commands/createas.c
index 415f110516..076f35ee6b 100644
--- a/src/backend/commands/createas.c
+++ b/src/backend/commands/createas.c
@@ -53,6 +53,7 @@
 #include "parser/parser.h"
 #include "parser/parsetree.h"
 #include "parser/parse_clause.h"
+#include "parser/parse_func.h"
 #include "rewrite/rewriteHandler.h"
 #include "storage/smgr.h"
 #include "tcop/tcopprot.h"
@@ -309,6 +310,9 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 					 errhint("functions must be marked IMMUTABLE")));
 
 		check_ivm_restriction((Node *) query);
+
+		/* For IMMV, we need to rewrite matview query */
+		query = rewriteQueryForIMMV(query, into->colNames);
 	}
 
 	if (into->skipData)
@@ -413,6 +417,49 @@ ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *stmt,
 	return address;
 }
 
+/*
+ * rewriteQueryForIMMV -- rewrite view definition query for IMMV
+ *
+ * count(*) is added for counting distinct tuples in views.
+ */
+Query *
+rewriteQueryForIMMV(Query *query, List *colNames)
+{
+	Query *rewritten;
+
+	Node *node;
+	ParseState *pstate = make_parsestate(NULL);
+	FuncCall *fn;
+
+	rewritten = copyObject(query);
+	pstate->p_expr_kind = EXPR_KIND_SELECT_TARGET;
+
+	/*
+	 * Convert DISTINCT to GROUP BY and add count(*) for counting distinct
+	 * tuples in views.
+	 */
+	if (rewritten->distinctClause)
+	{
+		TargetEntry *tle;
+
+		rewritten->groupClause = transformDistinctClause(NULL, &rewritten->targetList, rewritten->sortClause, false);
+
+		fn = makeFuncCall(SystemFuncName("count"), NIL, COERCE_EXPLICIT_CALL, -1);
+		fn->agg_star = true;
+
+		node = ParseFuncOrColumn(pstate, fn->funcname, NIL, NULL, fn, false, -1);
+
+		tle = makeTargetEntry((Expr *) node,
+								list_length(rewritten->targetList) + 1,
+								pstrdup("__ivm_count__"),
+								false);
+		rewritten->targetList = lappend(rewritten->targetList, tle);
+		rewritten->hasAggs = true;
+	}
+
+	return rewritten;
+}
+
 /*
  * GetIntoRelEFlags --- compute executor flags needed for CREATE TABLE AS
  *
@@ -536,7 +583,8 @@ intorel_startup(DestReceiver *self, int operation, TupleDesc typeinfo)
 		ColumnDef  *col;
 		char	   *colname;
 
-		if (lc)
+		/* Don't override hidden columns added for IVM */
+		if (lc && !isIvmName(NameStr(attribute->attname)))
 		{
 			colname = strVal(lfirst(lc));
 			lc = lnext(into->colNames, lc);
@@ -940,10 +988,6 @@ check_ivm_restriction_walker(Node *node, void *context)
 					ereport(ERROR,
 							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 							 errmsg("LIMIT/OFFSET clause is not supported on incrementally maintainable materialized view")));
-				if (qry->distinctClause)
-					ereport(ERROR,
-							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
-							 errmsg("DISTINCT is not supported on incrementally maintainable materialized view")));
 				if (qry->hasDistinctOn)
 					ereport(ERROR,
 							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
@@ -1090,12 +1134,18 @@ CreateIndexOnIMMV(Query *query, Relation matviewRel)
 	char		idxname[NAMEDATALEN];
 	List	   *indexoidlist = RelationGetIndexList(matviewRel);
 	ListCell   *indexoidscan;
-	Bitmapset *key_attnos;
 
 	snprintf(idxname, sizeof(idxname), "%s_index", RelationGetRelationName(matviewRel));
 
 	index = makeNode(IndexStmt);
 
+	/*
+	 * We consider null values not distinct to make sure that views with DISTINCT
+	 * or GROUP BY don't contain multiple NULL rows when NULL is inserted to
+	 * a base table concurrently.
+	 */
+	index->nulls_not_distinct = true;
+
 	index->unique = true;
 	index->primary = false;
 	index->isconstraint = false;
@@ -1122,41 +1172,68 @@ CreateIndexOnIMMV(Query *query, Relation matviewRel)
 	index->concurrent = false;
 	index->if_not_exists = false;
 
-	/* create index on the base tables' primary key columns */
-	key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
-	if (key_attnos)
+	if (query->distinctClause)
 	{
+		/* create unique constraint on all columns */
 		foreach(lc, query->targetList)
 		{
 			TargetEntry *tle = (TargetEntry *) lfirst(lc);
 			Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
-
-			if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
-			{
-				IndexElem  *iparam;
-
-				iparam = makeNode(IndexElem);
-				iparam->name = pstrdup(NameStr(attr->attname));
-				iparam->expr = NULL;
-				iparam->indexcolname = NULL;
-				iparam->collation = NIL;
-				iparam->opclass = NIL;
-				iparam->opclassopts = NIL;
-				iparam->ordering = SORTBY_DEFAULT;
-				iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
-				index->indexParams = lappend(index->indexParams, iparam);
-			}
+			IndexElem  *iparam;
+
+			iparam = makeNode(IndexElem);
+			iparam->name = pstrdup(NameStr(attr->attname));
+			iparam->expr = NULL;
+			iparam->indexcolname = NULL;
+			iparam->collation = NIL;
+			iparam->opclass = NIL;
+			iparam->opclassopts = NIL;
+			iparam->ordering = SORTBY_DEFAULT;
+			iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+			index->indexParams = lappend(index->indexParams, iparam);
 		}
 	}
 	else
 	{
-		/* create no index, just notice that an appropriate index is necessary for efficient IVM */
-		ereport(NOTICE,
-				(errmsg("could not create an index on materialized view \"%s\" automatically",
-						RelationGetRelationName(matviewRel)),
-				 errdetail("This target list does not have all the primary key columns. "),
-				 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
-		return;
+		Bitmapset *key_attnos;
+
+		/* create index on the base tables' primary key columns */
+		key_attnos = get_primary_key_attnos_from_query(query, &constraintList);
+		if (key_attnos)
+		{
+			foreach(lc, query->targetList)
+			{
+				TargetEntry *tle = (TargetEntry *) lfirst(lc);
+				Form_pg_attribute attr = TupleDescAttr(matviewRel->rd_att, tle->resno - 1);
+
+				if (bms_is_member(tle->resno - FirstLowInvalidHeapAttributeNumber, key_attnos))
+				{
+					IndexElem  *iparam;
+
+					iparam = makeNode(IndexElem);
+					iparam->name = pstrdup(NameStr(attr->attname));
+					iparam->expr = NULL;
+					iparam->indexcolname = NULL;
+					iparam->collation = NIL;
+					iparam->opclass = NIL;
+					iparam->opclassopts = NIL;
+					iparam->ordering = SORTBY_DEFAULT;
+					iparam->nulls_ordering = SORTBY_NULLS_DEFAULT;
+					index->indexParams = lappend(index->indexParams, iparam);
+				}
+			}
+		}
+		else
+		{
+			/* create no index, just notice that an appropriate index is necessary for efficient IVM */
+			ereport(NOTICE,
+					(errmsg("could not create an index on materialized view \"%s\" automatically",
+							RelationGetRelationName(matviewRel)),
+					 errdetail("This target list does not have all the primary key columns, "
+							   "or this view does not contain DISTINCT clause."),
+					 errhint("Create an index on the materialized view for efficient incremental maintenance.")));
+			return;
+		}
 	}
 
 	/* If we have a compatible index, we don't need to create another. */
diff --git a/src/backend/commands/indexcmds.c b/src/backend/commands/indexcmds.c
index ab8b81b302..4811a1c8df 100644
--- a/src/backend/commands/indexcmds.c
+++ b/src/backend/commands/indexcmds.c
@@ -38,6 +38,7 @@
 #include "commands/dbcommands.h"
 #include "commands/defrem.h"
 #include "commands/event_trigger.h"
+#include "commands/matview.h"
 #include "commands/progress.h"
 #include "commands/tablecmds.h"
 #include "commands/tablespace.h"
@@ -1104,6 +1105,45 @@ DefineIndex(Oid tableId,
 	safe_index = indexInfo->ii_Expressions == NIL &&
 		indexInfo->ii_Predicate == NIL;
 
+	/*
+	 * We disallow unique indexes on IVM columns of IMMVs.
+	 */
+	if (RelationIsIVM(rel) && stmt->unique)
+	{
+		for (int i = 0; i < indexInfo->ii_NumIndexKeyAttrs; i++)
+		{
+			AttrNumber	attno = indexInfo->ii_IndexAttrNumbers[i];
+			if (attno > 0)
+			{
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+		}
+
+		if (indexInfo->ii_Expressions)
+		{
+			Bitmapset  *indexattrs = NULL;
+			int			varno = -1;
+
+			pull_varattnos((Node *) indexInfo->ii_Expressions, 1, &indexattrs);
+
+			while ((varno = bms_next_member(indexattrs, varno)) >= 0)
+			{
+				int attno = varno + FirstLowInvalidHeapAttributeNumber;
+				char *name = NameStr(TupleDescAttr(rel->rd_att, attno - 1)->attname);
+				if (name && isIvmName(name))
+					ereport(ERROR,
+							(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+							 errmsg("unique index creation on IVM columns is not supported")));
+			}
+
+		}
+	}
+
+
 	/*
 	 * Report index creation if appropriate (delay this till after most of the
 	 * error checks)
diff --git a/src/backend/commands/matview.c b/src/backend/commands/matview.c
index 39305f3c49..aa518f20ef 100644
--- a/src/backend/commands/matview.c
+++ b/src/backend/commands/matview.c
@@ -152,11 +152,15 @@ static Query *rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *
 
 static void apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
 			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
-			Query *query);
+			Query *query, bool use_count, char *count_colname);
 static void apply_old_delta(const char *matviewname, const char *deltaname_old,
 				List *keys);
+static void apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname);
 static void apply_new_delta(const char *matviewname, const char *deltaname_new,
 				StringInfo target_list);
+static void apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname);
 static char *get_matching_condition_string(List *keys);
 static void generate_equal(StringInfo querybuf, Oid opttype,
 			   const char *leftop, const char *rightop);
@@ -271,6 +275,7 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 	Oid			matviewOid;
 	Relation	matviewRel;
 	Query	   *dataQuery;
+	Query	   *viewQuery;
 	Oid			tableSpace;
 	Oid			relowner;
 	Oid			OIDNewHeap;
@@ -330,8 +335,13 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 						"CONCURRENTLY", "WITH NO DATA")));
 
 
-	dataQuery = get_matview_query(matviewRel);
+	viewQuery = get_matview_query(matviewRel);
 
+	/* For IMMV, we need to rewrite matview query */
+	if (!stmt->skipData && RelationIsIVM(matviewRel))
+		dataQuery = rewriteQueryForIMMV(viewQuery,NIL);
+	else
+		dataQuery = viewQuery;
 
 	/*
 	 * Check that there is a unique index with no WHERE clause on one or more
@@ -511,8 +521,8 @@ ExecRefreshMatView(RefreshMatViewStmt *stmt, const char *queryString,
 
 	if (!stmt->skipData && RelationIsIVM(matviewRel) && !oldPopulated)
 	{
-		CreateIndexOnIMMV(dataQuery, matviewRel);
-		CreateIvmTriggersOnBaseTables(dataQuery, matviewOid);
+		CreateIndexOnIMMV(viewQuery, matviewRel);
+		CreateIvmTriggersOnBaseTables(viewQuery, matviewOid);
 	}
 
 	table_close(matviewRel, NoLock);
@@ -1512,6 +1522,13 @@ IVM_immediate_maintenance(PG_FUNCTION_ARGS)
 			int	rte_index = lfirst_int(lc2);
 			TupleDesc		tupdesc_old;
 			TupleDesc		tupdesc_new;
+			bool	use_count = false;
+			char   *count_colname = NULL;
+
+			count_colname = pstrdup("__ivm_count__");
+
+			if (query->distinctClause)
+				use_count = true;
 
 			/* calculate delta tables */
 			calc_delta(table, rte_index, rewritten, dest_old, dest_new,
@@ -1524,7 +1541,8 @@ IVM_immediate_maintenance(PG_FUNCTION_ARGS)
 			{
 				/* apply the delta tables to the materialized view */
 				apply_delta(matviewOid, old_tuplestore, new_tuplestore,
-							tupdesc_old, tupdesc_new, query);
+							tupdesc_old, tupdesc_new, query, use_count,
+							count_colname);
 			}
 			PG_CATCH();
 			{
@@ -1997,7 +2015,7 @@ rewrite_query_for_postupdate_state(Query *query, MV_TriggerTable *table, int rte
 static void
 apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *new_tuplestores,
 			TupleDesc tupdesc_old, TupleDesc tupdesc_new,
-			Query *query)
+			Query *query, bool use_count, char *count_colname)
 {
 	StringInfoData querybuf;
 	StringInfoData target_list_buf;
@@ -2073,7 +2091,12 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 		if (rc != SPI_OK_REL_REGISTER)
 			elog(ERROR, "SPI_register failed");
 
-		apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
+		if (use_count)
+			/* apply old delta and get rows to be recalculated */
+			apply_old_delta_with_count(matviewname, OLD_DELTA_ENRNAME,
+									   keys, count_colname);
+		else
+			apply_old_delta(matviewname, OLD_DELTA_ENRNAME, keys);
 
 	}
 	/* For tuple insertion */
@@ -2095,7 +2118,11 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 			elog(ERROR, "SPI_register failed");
 
 		/* apply new delta */
-		apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
+		if (use_count)
+			apply_new_delta_with_count(matviewname, NEW_DELTA_ENRNAME,
+								keys, &target_list_buf, count_colname);
+		else
+			apply_new_delta(matviewname, NEW_DELTA_ENRNAME, &target_list_buf);
 	}
 
 	/* We're done maintaining the materialized view. */
@@ -2108,6 +2135,51 @@ apply_delta(Oid matviewOid, Tuplestorestate *old_tuplestores, Tuplestorestate *n
 		elog(ERROR, "SPI_finish failed");
 }
 
+/*
+ * apply_old_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_old
+ * which contains tuples to be deleted from to a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct.
+ */
+static void
+apply_old_delta_with_count(const char *matviewname, const char *deltaname_old,
+				List *keys, const char *count_colname)
+{
+	StringInfoData	querybuf;
+	char   *match_cond;
+
+	/* build WHERE condition for searching tuples to be deleted */
+	match_cond = get_matching_condition_string(keys);
+
+	/* Search for matching tuples from the view and update or delete if found. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH t AS ("			/* collecting tid of target tuples in the view */
+						"SELECT diff.%s, "			/* count column */
+								"(diff.%s OPERATOR(pg_catalog.=) mv.%s) AS for_dlt, "
+								"mv.ctid "
+						"FROM %s AS mv, %s AS diff "
+						"WHERE %s"					/* tuple matching condition */
+					"), updt AS ("			/* update a tuple if this is not to be deleted */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.-) t.%s "
+						"FROM t WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND NOT for_dlt "
+					")"
+					/* delete a tuple if this is to be deleted */
+					"DELETE FROM %s AS mv USING t "
+					"WHERE mv.ctid OPERATOR(pg_catalog.=) t.ctid AND for_dlt",
+					count_colname,
+					count_colname, count_colname,
+					matviewname, deltaname_old,
+					match_cond,
+					matviewname, count_colname, count_colname, count_colname,
+					matviewname);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_DELETE)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
 /*
  * apply_old_delta
  *
@@ -2157,6 +2229,66 @@ apply_old_delta(const char *matviewname, const char *deltaname_old,
 		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
 }
 
+/*
+ * apply_new_delta_with_count
+ *
+ * Execute a query for applying a delta table given by deltname_new
+ * which contains tuples to be inserted into a materialized view given by
+ * matviewname.  This is used when counting is required, that is, the view
+ * has aggregate or distinct. Also, when a table in EXISTS sub queries
+ * is modified.
+ */
+static void
+apply_new_delta_with_count(const char *matviewname, const char* deltaname_new,
+				List *keys, StringInfo target_list, const char* count_colname)
+{
+	StringInfoData	querybuf;
+	StringInfoData	returning_keys;
+	ListCell	*lc;
+	char	*match_cond = "";
+
+	/* build WHERE condition for searching tuples to be updated */
+	match_cond = get_matching_condition_string(keys);
+
+	/* build string of keys list */
+	initStringInfo(&returning_keys);
+	if (keys)
+	{
+		foreach (lc, keys)
+		{
+			Form_pg_attribute attr = (Form_pg_attribute) lfirst(lc);
+			char   *resname = NameStr(attr->attname);
+			appendStringInfo(&returning_keys, "%s", quote_qualified_identifier("mv", resname));
+			if (lnext(keys, lc))
+				appendStringInfo(&returning_keys, ", ");
+		}
+	}
+	else
+		appendStringInfo(&returning_keys, "NULL");
+
+	/* Search for matching tuples from the view and update if found or insert if not. */
+	initStringInfo(&querybuf);
+	appendStringInfo(&querybuf,
+					"WITH updt AS ("		/* update a tuple if this exists in the view */
+						"UPDATE %s AS mv SET %s = mv.%s OPERATOR(pg_catalog.+) diff.%s "
+						"FROM %s AS diff "
+						"WHERE %s "					/* tuple matching condition */
+						"RETURNING %s"				/* returning keys of updated tuples */
+					") INSERT INTO %s (%s) "	/* insert a new tuple if this doesn't exist */
+						"SELECT %s FROM %s AS diff "
+						"WHERE NOT EXISTS (SELECT 1 FROM updt AS mv WHERE %s);",
+					matviewname, count_colname, count_colname, count_colname,
+					deltaname_new,
+					match_cond,
+					returning_keys.data,
+					matviewname, target_list->data,
+					target_list->data, deltaname_new,
+					match_cond);
+
+	if (SPI_exec(querybuf.data, 0) != SPI_OK_INSERT)
+		elog(ERROR, "SPI_exec failed: %s", querybuf.data);
+}
+
 /*
  * apply_new_delta
  *
diff --git a/src/backend/commands/tablecmds.c b/src/backend/commands/tablecmds.c
index 47c900445c..adbd768e0d 100644
--- a/src/backend/commands/tablecmds.c
+++ b/src/backend/commands/tablecmds.c
@@ -53,6 +53,7 @@
 #include "commands/cluster.h"
 #include "commands/comment.h"
 #include "commands/defrem.h"
+#include "commands/matview.h"
 #include "commands/event_trigger.h"
 #include "commands/policy.h"
 #include "commands/sequence.h"
@@ -3673,6 +3674,14 @@ renameatt_internal(Oid myrelid,
 	targetrelation = relation_open(myrelid, AccessExclusiveLock);
 	renameatt_check(myrelid, RelationGetForm(targetrelation), recursing);
 
+	/*
+	 * Don't rename IVM columns.
+	 */
+	if (RelationIsIVM(targetrelation) && isIvmName(oldattname))
+		ereport(ERROR,
+				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
+				 errmsg("IVM column can not be renamed")));
+
 	/*
 	 * if the 'recurse' flag is set then we are supposed to rename this
 	 * attribute in all classes that inherit from 'relname' (as well as in
diff --git a/src/backend/parser/parse_relation.c b/src/backend/parser/parse_relation.c
index 864ea9b0d5..c257440414 100644
--- a/src/backend/parser/parse_relation.c
+++ b/src/backend/parser/parse_relation.c
@@ -36,6 +36,7 @@
 #include "utils/rel.h"
 #include "utils/syscache.h"
 #include "utils/varlena.h"
+#include "commands/matview.h"
 
 
 /*
@@ -97,7 +98,7 @@ static void expandTupleDesc(TupleDesc tupdesc, Alias *eref,
 							int count, int offset,
 							int rtindex, int sublevels_up,
 							int location, bool include_dropped,
-							List **colnames, List **colvars);
+							List **colnames, List **colvars, bool is_ivm);
 static int	specialAttNum(const char *attname);
 static bool rte_visible_if_lateral(ParseState *pstate, RangeTblEntry *rte);
 static bool rte_visible_if_qualified(ParseState *pstate, RangeTblEntry *rte);
@@ -1502,6 +1503,7 @@ addRangeTableEntry(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -1587,6 +1589,7 @@ addRangeTableEntryForRelation(ParseState *pstate,
 	rte->relid = RelationGetRelid(rel);
 	rte->relkind = rel->rd_rel->relkind;
 	rte->rellockmode = lockmode;
+	rte->relisivm = rel->rd_rel->relisivm;
 
 	/*
 	 * Build the list of effective column names using user-supplied aliases
@@ -2758,7 +2761,7 @@ expandRTE(RangeTblEntry *rte, int rtindex, int sublevels_up,
 						expandTupleDesc(tupdesc, rte->eref,
 										rtfunc->funccolcount, atts_done,
 										rtindex, sublevels_up, location,
-										include_dropped, colnames, colvars);
+										include_dropped, colnames, colvars, false);
 					}
 					else if (functypclass == TYPEFUNC_SCALAR)
 					{
@@ -3026,7 +3029,7 @@ expandRelation(Oid relid, Alias *eref, int rtindex, int sublevels_up,
 	expandTupleDesc(rel->rd_att, eref, rel->rd_att->natts, 0,
 					rtindex, sublevels_up,
 					location, include_dropped,
-					colnames, colvars);
+					colnames, colvars, RelationIsIVM(rel));
 	relation_close(rel, AccessShareLock);
 }
 
@@ -3043,7 +3046,7 @@ static void
 expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 				int rtindex, int sublevels_up,
 				int location, bool include_dropped,
-				List **colnames, List **colvars)
+				List **colnames, List **colvars, bool is_ivm)
 {
 	ListCell   *aliascell;
 	int			varattno;
@@ -3056,6 +3059,9 @@ expandTupleDesc(TupleDesc tupdesc, Alias *eref, int count, int offset,
 	{
 		Form_pg_attribute attr = TupleDescAttr(tupdesc, varattno);
 
+		if (is_ivm && isIvmName(NameStr(attr->attname)) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		if (attr->attisdropped)
 		{
 			if (include_dropped)
@@ -3218,6 +3224,10 @@ expandNSItemAttrs(ParseState *pstate, ParseNamespaceItem *nsitem,
 		Var		   *varnode = (Var *) lfirst(var);
 		TargetEntry *te;
 
+		/* if transform * into columnlist with IMMV, remove IVM columns */
+		if (rte->relisivm && isIvmName(label) && !MatViewIncrementalMaintenanceIsEnabled())
+			continue;
+
 		te = makeTargetEntry((Expr *) varnode,
 							 (AttrNumber) pstate->p_next_resno++,
 							 label,
diff --git a/src/backend/rewrite/rewriteDefine.c b/src/backend/rewrite/rewriteDefine.c
index e36fc72e1e..f6dc7ba202 100644
--- a/src/backend/rewrite/rewriteDefine.c
+++ b/src/backend/rewrite/rewriteDefine.c
@@ -621,7 +621,8 @@ checkRuleResultList(List *targetList, TupleDesc resultDesc, bool isSelect,
 														attr->atttypmod))));
 	}
 
-	if (i != resultDesc->natts)
+	/* No check for materialized views since this could have special columns for IVM */
+	if ((!isSelect || requireColumnNameMatch) && i != resultDesc->natts)
 		ereport(ERROR,
 				(errcode(ERRCODE_INVALID_OBJECT_DEFINITION),
 				 isSelect ?
diff --git a/src/include/commands/createas.h b/src/include/commands/createas.h
index 09a64fa2e5..76a7873ebf 100644
--- a/src/include/commands/createas.h
+++ b/src/include/commands/createas.h
@@ -29,6 +29,8 @@ extern ObjectAddress ExecCreateTableAs(ParseState *pstate, CreateTableAsStmt *st
 extern void CreateIvmTriggersOnBaseTables(Query *qry, Oid matviewOid);
 extern void CreateIndexOnIMMV(Query *query, Relation matviewRel);
 
+extern Query *rewriteQueryForIMMV(Query *query, List *colNames);
+
 extern int	GetIntoRelEFlags(IntoClause *intoClause);
 
 extern DestReceiver *CreateIntoRelDestReceiver(IntoClause *intoClause);
diff --git a/src/include/nodes/parsenodes.h b/src/include/nodes/parsenodes.h
index fef4c714b8..1a2b8fa09e 100644
--- a/src/include/nodes/parsenodes.h
+++ b/src/include/nodes/parsenodes.h
@@ -1073,6 +1073,7 @@ typedef struct RangeTblEntry
 	int			rellockmode;	/* lock level that query requires on the rel */
 	struct TableSampleClause *tablesample;	/* sampling info, or NULL */
 	Index		perminfoindex;
+	bool		relisivm;
 
 	/*
 	 * Fields valid for a subquery RTE (else NULL):
-- 
2.25.1


--Multipart=_Mon__28_Aug_2023_16_05_30_+0900_b1OvQD_3A3ZMTGvj
Content-Type: text/x-diff;
 name="v29-0008-Add-aggregates-support-in-IVM.patch"
Content-Disposition: attachment;
 filename="v29-0008-Add-aggregates-support-in-IVM.patch"
Content-Transfer-Encoding: quoted-printable



^ permalink  raw  reply  [nested|flat] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v2] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v3] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread

* [PATCH v1] Cleanup explicit PREPARE query strings
@ 2025-12-24 14:31 Julien Rouhaud <julien.rouhaud@free.fr>
  0 siblings, 0 replies; 916+ 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] 916+ messages in thread