Move pg_stat_statements query jumbling to core.

Add compute_query_id GUC to control whether a query identifier should be
computed by the core (off by default).  It's thefore now possible to
disable core queryid computation and use pg_stat_statements with a
different algorithm to compute the query identifier by using a
third-party module.

To ensure that a single source of query identifier can be used and is
well defined, modules that calculate a query identifier should throw an
error if compute_query_id specified to compute a query id and if a query
idenfitier was already calculated.

Discussion: https://postgr.es/m/20210407125726.tkvjdbw76hxnpwfi@nol

Author: Julien Rouhaud

Reviewed-by: Alvaro Herrera, Nitin Jadhav, Zhihong Yu

2 files changed, 59 insertions, 0 deletions

diff --git a/src/include/utils/guc.h b/src/include/utils/guc.h
index 5004ee41779..9b6552b25b2 100644
--- a/src/include/utils/guc.h
+++ b/src/include/utils/guc.h
@@ -248,6 +248,7 @@ extern bool log_btree_build_stats;
 extern PGDLLIMPORT bool check_function_bodies;
 extern bool session_auth_is_superuser;
 
+extern bool compute_query_id;
 extern bool log_duration;
 extern int	log_parameter_max_length;
 extern int	log_parameter_max_length_on_error;
diff --git a/src/include/utils/queryjumble.h b/src/include/utils/queryjumble.h
new file mode 100644
index 00000000000..83ba7339fae
--- /dev/null
+++ b/src/include/utils/queryjumble.h
@@ -0,0 +1,58 @@
+/*-------------------------------------------------------------------------
+ *
+ * queryjumble.h
+ *	  Query normalization and fingerprinting.
+ *
+ * Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group
+ * Portions Copyright (c) 1994, Regents of the University of California
+ *
+ * IDENTIFICATION
+ *	  src/include/utils/queryjumble.h
+ *
+ *-------------------------------------------------------------------------
+ */
+#ifndef QUERYJUBLE_H
+#define QUERYJUBLE_H
+
+#include "nodes/parsenodes.h"
+
+#define JUMBLE_SIZE				1024	/* query serialization buffer size */
+
+/*
+ * Struct for tracking locations/lengths of constants during normalization
+ */
+typedef struct LocationLen
+{
+	int			location;		/* start offset in query text */
+	int			length;			/* length in bytes, or -1 to ignore */
+} LocationLen;
+
+/*
+ * Working state for computing a query jumble and producing a normalized
+ * query string
+ */
+typedef struct JumbleState
+{
+	/* Jumble of current query tree */
+	unsigned char *jumble;
+
+	/* Number of bytes used in jumble[] */
+	Size		jumble_len;
+
+	/* Array of locations of constants that should be removed */
+	LocationLen *clocations;
+
+	/* Allocated length of clocations array */
+	int			clocations_buf_size;
+
+	/* Current number of valid entries in clocations array */
+	int			clocations_count;
+
+	/* highest Param id we've seen, in order to start normalization correctly */
+	int			highest_extern_param_id;
+} JumbleState;
+
+const char *CleanQuerytext(const char *query, int *location, int *len);
+JumbleState *JumbleQuery(Query *query, const char *querytext);
+
+#endif							/* QUERYJUMBLE_H */