Update libpg_query to 17-6.2.2 (#143)

Author: lfittl

CHANGELOG.md

@@ -2,7 +2,35 @@
 
 ## Unreleased
 
-* ...
+* Upgrade to libpg_query 17-6.2.2
+  - Add pg_query_is_utility_stmt function to determine if query text contains utility statements [#313](https://github.com/pganalyze/libpg_query/pull/313)
+    - This is a fast check for callers that don't actually need the parse tree itself
+  - Add fast summary information function (pg_query_summary)
+    - This allows gathering certain information, for example which tables are referenced in a
+      statement, without requiring a Protobuf serialization step in a higher level library
+    - Additionally this can also be used to perform "smart truncation" of a query by
+      omitting deeply nested information (e.g. a CTE definition, or a target list) whilst
+        preserving more essential parts like the FROM clause
+  - pg_query_normalize: Fix handling of special strings in DefElem
+    - This avoids a crash when running the normalize function on certain utility statements
+  - Deparser:
+    - Introduce pretty printing / formatting
+      - Introduces a new optional pretty print mode that emits a human readable
+        output. A detailed explanation of the mechanism can be found at the start
+        of the deparser file.
+    - Rework handling of expressions inside typecasts
+      - Prefer (..)::type syntax, unless we are already in a function call.
+    - Use lowercase keywords in xmlroot functions
+      - This matches other XML functions as well as the Postgres documentation,
+        since these are closer to function argument names than regular keywords.
+    - Fix deparse of ALTER TABLE a ALTER b SET STATISTICS DEFAULT
+    - Fix the null pointer dereference when handling identity columns
+  - Allow alternate definitions of NAMEDATALEN identifier limit
+    - This allows building libpg_query with an override of the built-time limit of
+      Postgres identifiers (typically 63 characters)
+  - Normalization: Add support for CALL statements
+  - Bump Postgres to 17.7 and switch back to release tarballs
+
 
 ## 6.1.0     2025-02-24
 

Makefile

@@ -16,7 +16,7 @@ benchmark:
 
 # --- Below only needed for releasing new versions
 
-LIB_PG_QUERY_TAG = 17-6.1.0
+LIB_PG_QUERY_TAG = 17-6.2.2
 
 root_dir := $(shell dirname $(realpath $(lastword $(MAKEFILE_LIST))))
 LIB_TMPDIR = $(root_dir)/tmp
@@ -40,7 +40,7 @@ update_source: clean $(LIBDIR)
 	rm parser/pg_query_outfuncs_protobuf_cpp.cc
 	mv parser/postgres/* parser/
 	rmdir parser/postgres
-	cp -a $(LIBDIR)/pg_query.h parser/include
+	cp -a $(LIBDIR)/{pg_query.h,postgres_deparse.h} parser/include
 	# Protobuf definitions
 	mkdir -p $(PWD)/bin
 	GOBIN=$(PWD)/bin go install google.golang.org/protobuf/cmd/protoc-gen-go

parse_test.go

@@ -0,0 +1,23 @@
+PostgreSQL Database Management System
+(also known as Postgres, formerly known as Postgres95)
+
+Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
+
+Portions Copyright (c) 1994, The Regents of the University of California
+
+Permission to use, copy, modify, and distribute this software and its
+documentation for any purpose, without fee, and without a written agreement
+is hereby granted, provided that the above copyright notice and this
+paragraph and the following two paragraphs appear in all copies.
+
+IN NO EVENT SHALL THE UNIVERSITY OF CALIFORNIA BE LIABLE TO ANY PARTY FOR
+DIRECT, INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING
+LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS
+DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED OF THE
+POSSIBILITY OF SUCH DAMAGE.
+
+THE UNIVERSITY OF CALIFORNIA SPECIFICALLY DISCLAIMS ANY WARRANTIES,
+INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
+AND FITNESS FOR A PARTICULAR PURPOSE.  THE SOFTWARE PROVIDED HEREUNDER IS
+ON AN "AS IS" BASIS, AND THE UNIVERSITY OF CALIFORNIA HAS NO OBLIGATIONS TO
+PROVIDE MAINTENANCE, SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS.

parser/COPYRIGHT

@@ -34,11 +34,11 @@ import (
 	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/port"
 	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/port/atomics"
 	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/port/win32"
+	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/port/win32_msvc"
+	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/port/win32_msvc/sys"
 	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/port/win32/arpa"
 	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/port/win32/netinet"
 	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/port/win32/sys"
-	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/port/win32_msvc"
-	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/port/win32_msvc/sys"
 	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/portability"
 	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/postmaster"
 	_ "github.com/pganalyze/pg_query_go/v6/parser/include/postgres/regex"

parser/build_cgo.go

@@ -1,9 +1,12 @@
 #ifndef PG_QUERY_H
 #define PG_QUERY_H
 
+#include <stdbool.h>
 #include <stdint.h>
 #include <sys/types.h>
 
+#include "postgres_deparse.h"
+
 typedef struct {
 	char* message; // exception message
 	char* funcname; // source function of exception (e.g. SearchSysCache)
@@ -13,6 +16,12 @@ typedef struct {
 	char* context; // additional context (optional, can be NULL)
 } PgQueryError;
 
+typedef struct {
+	int length;
+	bool *items;
+	PgQueryError* error;
+} PgQueryIsUtilityResult;
+
 typedef struct {
   size_t len;
   char* data;
@@ -53,6 +62,12 @@ typedef struct {
   PgQueryError* error;
 } PgQueryDeparseResult;
 
+typedef struct {
+  PostgresDeparseComment **comments;
+  size_t comment_count;
+  PgQueryError* error;
+} PgQueryDeparseCommentsResult;
+
 typedef struct {
   char* plpgsql_funcs;
   PgQueryError* error;
@@ -70,6 +85,12 @@ typedef struct {
   PgQueryError* error;
 } PgQueryNormalizeResult;
 
+typedef struct {
+	PgQueryProtobuf summary;
+	char* stderr_buffer;
+	PgQueryError* error;
+} PgQuerySummaryParseResult;
+
 // Postgres parser options (parse mode and GUCs that affect parsing)
 
 typedef enum
@@ -118,23 +139,32 @@ PgQuerySplitResult pg_query_split_with_scanner(const char *input);
 PgQuerySplitResult pg_query_split_with_parser(const char *input);
 
 PgQueryDeparseResult pg_query_deparse_protobuf(PgQueryProtobuf parse_tree);
+PgQueryDeparseResult pg_query_deparse_protobuf_opts(PgQueryProtobuf parse_tree, struct PostgresDeparseOpts opts);
+PgQueryDeparseCommentsResult pg_query_deparse_comments_for_query(const char *query);
+
+PgQueryIsUtilityResult pg_query_is_utility_stmt(const char *query);
+
+PgQuerySummaryParseResult pg_query_summary(const char* input, int parser_options, int truncate_limit);
 
 void pg_query_free_normalize_result(PgQueryNormalizeResult result);
 void pg_query_free_scan_result(PgQueryScanResult result);
 void pg_query_free_parse_result(PgQueryParseResult result);
 void pg_query_free_split_result(PgQuerySplitResult result);
 void pg_query_free_deparse_result(PgQueryDeparseResult result);
+void pg_query_free_deparse_comments_result(PgQueryDeparseCommentsResult result);
 void pg_query_free_protobuf_parse_result(PgQueryProtobufParseResult result);
 void pg_query_free_plpgsql_parse_result(PgQueryPlpgsqlParseResult result);
 void pg_query_free_fingerprint_result(PgQueryFingerprintResult result);
+void pg_query_free_is_utility_result(PgQueryIsUtilityResult result);
+void pg_query_free_summary_parse_result(PgQuerySummaryParseResult result);
 
 // Optional, cleans up the top-level memory context (automatically done for threads that exit)
 void pg_query_exit(void);
 
 // Postgres version information
 #define PG_MAJORVERSION "17"
-#define PG_VERSION "17.4"
-#define PG_VERSION_NUM 170004
+#define PG_VERSION "17.7"
+#define PG_VERSION_NUM 170007
 
 // Deprecated APIs below
 

parser/include/pg_query.h

@@ -271,7 +271,7 @@ typedef struct IndexAmRoutine
 	ambuild_function ambuild;
 	ambuildempty_function ambuildempty;
 	aminsert_function aminsert;
-	aminsertcleanup_function aminsertcleanup;
+	aminsertcleanup_function aminsertcleanup;	/* can be NULL */
 	ambulkdelete_function ambulkdelete;
 	amvacuumcleanup_function amvacuumcleanup;
 	amcanreturn_function amcanreturn;	/* can be NULL */

parser/include/postgres/access/amapi.h

@@ -55,7 +55,7 @@ typedef enum
 /*
  * Shared-memory state
  *
- * ControlLock is used to protect access to the other fields, except
+ * SLRU bank locks are used to protect access to the other fields, except
  * latest_page_number, which uses atomics; see comment in slru.c.
  */
 typedef struct SlruSharedData

parser/include/postgres/access/slru.h

@@ -129,7 +129,9 @@ typedef enum TU_UpdateIndexes
 /*
  * When table_tuple_update, table_tuple_delete, or table_tuple_lock fail
  * because the target tuple is already outdated, they fill in this struct to
- * provide information to the caller about what happened.
+ * provide information to the caller about what happened. When those functions
+ * succeed, the contents of this struct should not be relied upon, except for
+ * `traversed`, which may be set in both success and failure cases.
  *
  * ctid is the target's ctid link: it is the same as the target's TID if the
  * target was deleted, or the location of the replacement tuple if the target
@@ -145,6 +147,9 @@ typedef enum TU_UpdateIndexes
  * tuple); otherwise cmax is zero.  (We make this restriction because
  * HeapTupleHeaderGetCmax doesn't work for tuples outdated in other
  * transactions.)
+ *
+ * traversed indicates if an update chain was followed in order to try to lock
+ * the target tuple.  (This may be set in both success and failure cases.)
  */
 typedef struct TM_FailureData
 {
@@ -1549,7 +1554,7 @@ table_tuple_update(Relation rel, ItemPointer otid, TupleTableSlot *slot,
  *
  * Input parameters:
  *	relation: relation containing tuple (caller must hold suitable lock)
- *	tid: TID of tuple to lock
+ *	tid: TID of tuple to lock (updated if an update chain was followed)
  *	snapshot: snapshot to use for visibility determinations
  *	cid: current command ID (used for visibility test, and stored into
  *		tuple's cmax if lock is successful)
@@ -1574,8 +1579,10 @@ table_tuple_update(Relation rel, ItemPointer otid, TupleTableSlot *slot,
  *	TM_WouldBlock: lock couldn't be acquired and wait_policy is skip
  *
  * In the failure cases other than TM_Invisible and TM_Deleted, the routine
- * fills *tmfd with the tuple's t_ctid, t_xmax, and, if possible, t_cmax.  See
- * comments for struct TM_FailureData for additional info.
+ * fills *tmfd with the tuple's t_ctid, t_xmax, and, if possible, t_cmax.
+ * Additionally, in both success and failure cases, tmfd->traversed is set if
+ * an update chain was followed.  See comments for struct TM_FailureData for
+ * additional info.
  */
 static inline TM_Result
 table_tuple_lock(Relation rel, ItemPointer tid, Snapshot snapshot,

parser/include/postgres/access/tableam.h

@@ -265,6 +265,7 @@ extern void SwitchIntoArchiveRecovery(XLogRecPtr EndRecPtr, TimeLineID replayTLI
 extern void ReachedEndOfBackup(XLogRecPtr EndRecPtr, TimeLineID tli);
 extern void SetInstallXLogFileSegmentActive(void);
 extern bool IsInstallXLogFileSegmentActive(void);
+extern void ResetInstallXLogFileSegmentActive(void);
 extern void XLogShutdownWalRcv(void);
 
 /*