From 0ba281cb4bf9f5f65529dfa4c8282abb734dd454 Mon Sep 17 00:00:00 2001
From: Robert Haas <rhaas@postgresql.org>
Date: Tue, 5 Oct 2021 11:50:21 -0400
Subject: Flexible options for BASE_BACKUP.

Previously, BASE_BACKUP used an entirely hard-coded syntax, but that's
hard to extend. Instead, adopt the same kind of syntax we've used for
SQL commands such as VACUUM, ANALYZE, COPY, and EXPLAIN, where it's
not necessary for all of the option names to be parser keywords.

In the new syntax, most of the options now take an optional Boolean
argument. To match our practice in other in places, the options which
the old syntax called NOWAIT and NOVERIFY_CHECKSUMS options are in the
new syntax called WAIT and VERIFY_CHECKUMS, and the default value is
false. In the new syntax, the FAST option has been replaced by a
CHECKSUM option whose value may be 'fast' or 'spread'.

This commit does not remove support for the old syntax. It just adds
the new one as an additional option, and makes pg_basebackup prefer
the new syntax when the server is new enough to support it.

Patch by me, reviewed and tested by Fabien Coelho, Sergei Kornilov,
Fujii Masao, and Tushar Ahuja.

Discussion: http://postgr.es/m/CA+TgmobAczXDRO_Gr2euo_TxgzaH1JxbNxvFx=HYvBinefNH8Q@mail.gmail.com
Discussion: http://postgr.es/m/CA+TgmoZGwR=ZVWFeecncubEyPdwghnvfkkdBe9BLccLSiqdf9Q@mail.gmail.com
---
 src/backend/replication/basebackup.c  | 51 +++++++++++-------
 src/backend/replication/repl_gram.y   | 97 ++++++++++++++++++++++++++++++-----
 src/bin/pg_basebackup/pg_basebackup.c | 71 ++++++++++++++++---------
 src/bin/pg_basebackup/streamutil.c    | 61 ++++++++++++++++++++++
 src/bin/pg_basebackup/streamutil.h    | 12 +++++
 5 files changed, 235 insertions(+), 57 deletions(-)

(limited to 'src')

diff --git a/src/backend/replication/basebackup.c b/src/backend/replication/basebackup.c
index e09108d0ece..4c97ab7b5a7 100644
--- a/src/backend/replication/basebackup.c
+++ b/src/backend/replication/basebackup.c
@@ -19,6 +19,7 @@
 #include "access/xlog_internal.h"	/* for pg_start/stop_backup */
 #include "catalog/pg_type.h"
 #include "common/file_perm.h"
+#include "commands/defrem.h"
 #include "commands/progress.h"
 #include "lib/stringinfo.h"
 #include "libpq/libpq.h"
@@ -764,7 +765,7 @@ parse_basebackup_options(List *options, basebackup_options *opt)
 	ListCell   *lopt;
 	bool		o_label = false;
 	bool		o_progress = false;
-	bool		o_fast = false;
+	bool		o_checkpoint = false;
 	bool		o_nowait = false;
 	bool		o_wal = false;
 	bool		o_maxrate = false;
@@ -787,7 +788,7 @@ parse_basebackup_options(List *options, basebackup_options *opt)
 				ereport(ERROR,
 						(errcode(ERRCODE_SYNTAX_ERROR),
 						 errmsg("duplicate option \"%s\"", defel->defname)));
-			opt->label = strVal(defel->arg);
+			opt->label = defGetString(defel);
 			o_label = true;
 		}
 		else if (strcmp(defel->defname, "progress") == 0)
@@ -796,25 +797,35 @@ parse_basebackup_options(List *options, basebackup_options *opt)
 				ereport(ERROR,
 						(errcode(ERRCODE_SYNTAX_ERROR),
 						 errmsg("duplicate option \"%s\"", defel->defname)));
-			opt->progress = true;
+			opt->progress = defGetBoolean(defel);
 			o_progress = true;
 		}
-		else if (strcmp(defel->defname, "fast") == 0)
+		else if (strcmp(defel->defname, "checkpoint") == 0)
 		{
-			if (o_fast)
+			char	   *optval = defGetString(defel);
+
+			if (o_checkpoint)
 				ereport(ERROR,
 						(errcode(ERRCODE_SYNTAX_ERROR),
 						 errmsg("duplicate option \"%s\"", defel->defname)));
-			opt->fastcheckpoint = true;
-			o_fast = true;
+			if (pg_strcasecmp(optval, "fast") == 0)
+				opt->fastcheckpoint = true;
+			else if (pg_strcasecmp(optval, "spread") == 0)
+				opt->fastcheckpoint = false;
+			else
+				ereport(ERROR,
+						(errcode(ERRCODE_SYNTAX_ERROR),
+						 errmsg("unrecognized checkpoint type: \"%s\"",
+								optval)));
+			o_checkpoint = true;
 		}
-		else if (strcmp(defel->defname, "nowait") == 0)
+		else if (strcmp(defel->defname, "wait") == 0)
 		{
 			if (o_nowait)
 				ereport(ERROR,
 						(errcode(ERRCODE_SYNTAX_ERROR),
 						 errmsg("duplicate option \"%s\"", defel->defname)));
-			opt->nowait = true;
+			opt->nowait = !defGetBoolean(defel);
 			o_nowait = true;
 		}
 		else if (strcmp(defel->defname, "wal") == 0)
@@ -823,19 +834,19 @@ parse_basebackup_options(List *options, basebackup_options *opt)
 				ereport(ERROR,
 						(errcode(ERRCODE_SYNTAX_ERROR),
 						 errmsg("duplicate option \"%s\"", defel->defname)));
-			opt->includewal = true;
+			opt->includewal = defGetBoolean(defel);
 			o_wal = true;
 		}
 		else if (strcmp(defel->defname, "max_rate") == 0)
 		{
-			long		maxrate;
+			int64		maxrate;
 
 			if (o_maxrate)
 				ereport(ERROR,
 						(errcode(ERRCODE_SYNTAX_ERROR),
 						 errmsg("duplicate option \"%s\"", defel->defname)));
 
-			maxrate = intVal(defel->arg);
+			maxrate = defGetInt64(defel);
 			if (maxrate < MAX_RATE_LOWER || maxrate > MAX_RATE_UPPER)
 				ereport(ERROR,
 						(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
@@ -851,21 +862,21 @@ parse_basebackup_options(List *options, basebackup_options *opt)
 				ereport(ERROR,
 						(errcode(ERRCODE_SYNTAX_ERROR),
 						 errmsg("duplicate option \"%s\"", defel->defname)));
-			opt->sendtblspcmapfile = true;
+			opt->sendtblspcmapfile = defGetBoolean(defel);
 			o_tablespace_map = true;
 		}
-		else if (strcmp(defel->defname, "noverify_checksums") == 0)
+		else if (strcmp(defel->defname, "verify_checksums") == 0)
 		{
 			if (o_noverify_checksums)
 				ereport(ERROR,
 						(errcode(ERRCODE_SYNTAX_ERROR),
 						 errmsg("duplicate option \"%s\"", defel->defname)));
-			noverify_checksums = true;
+			noverify_checksums = !defGetBoolean(defel);
 			o_noverify_checksums = true;
 		}
 		else if (strcmp(defel->defname, "manifest") == 0)
 		{
-			char	   *optval = strVal(defel->arg);
+			char	   *optval = defGetString(defel);
 			bool		manifest_bool;
 
 			if (o_manifest)
@@ -890,7 +901,7 @@ parse_basebackup_options(List *options, basebackup_options *opt)
 		}
 		else if (strcmp(defel->defname, "manifest_checksums") == 0)
 		{
-			char	   *optval = strVal(defel->arg);
+			char	   *optval = defGetString(defel);
 
 			if (o_manifest_checksums)
 				ereport(ERROR,
@@ -905,8 +916,10 @@ parse_basebackup_options(List *options, basebackup_options *opt)
 			o_manifest_checksums = true;
 		}
 		else
-			elog(ERROR, "option \"%s\" not recognized",
-				 defel->defname);
+			ereport(ERROR,
+					errcode(ERRCODE_SYNTAX_ERROR),
+					errmsg("option \"%s\" not recognized",
+						   defel->defname));
 	}
 	if (opt->label == NULL)
 		opt->label = "base backup";
diff --git a/src/backend/replication/repl_gram.y b/src/backend/replication/repl_gram.y
index e1e8ec29cc4..3b59d62ed86 100644
--- a/src/backend/replication/repl_gram.y
+++ b/src/backend/replication/repl_gram.y
@@ -95,13 +95,13 @@ static SQLCmd *make_sqlcmd(void);
 %type <node>	base_backup start_replication start_logical_replication
 				create_replication_slot drop_replication_slot identify_system
 				timeline_history show sql_cmd
-%type <list>	base_backup_opt_list
-%type <defelt>	base_backup_opt
+%type <list>	base_backup_legacy_opt_list generic_option_list
+%type <defelt>	base_backup_legacy_opt generic_option
 %type <uintval>	opt_timeline
 %type <list>	plugin_options plugin_opt_list
 %type <defelt>	plugin_opt_elem
 %type <node>	plugin_opt_arg
-%type <str>		opt_slot var_name
+%type <str>		opt_slot var_name ident_or_keyword
 %type <boolval>	opt_temporary
 %type <list>	create_slot_opt_list
 %type <defelt>	create_slot_opt
@@ -157,12 +157,24 @@ var_name:	IDENT	{ $$ = $1; }
 		;
 
 /*
+ * BASE_BACKUP ( option [ 'value' ] [, ...] )
+ *
+ * We also still support the legacy syntax:
+ *
  * BASE_BACKUP [LABEL '<label>'] [PROGRESS] [FAST] [WAL] [NOWAIT]
  * [MAX_RATE %d] [TABLESPACE_MAP] [NOVERIFY_CHECKSUMS]
  * [MANIFEST %s] [MANIFEST_CHECKSUMS %s]
+ *
+ * Future options should be supported only using the new syntax.
  */
 base_backup:
-			K_BASE_BACKUP base_backup_opt_list
+			K_BASE_BACKUP '(' generic_option_list ')'
+				{
+					BaseBackupCmd *cmd = makeNode(BaseBackupCmd);
+					cmd->options = $3;
+					$$ = (Node *) cmd;
+				}
+			| K_BASE_BACKUP base_backup_legacy_opt_list
 				{
 					BaseBackupCmd *cmd = makeNode(BaseBackupCmd);
 					cmd->options = $2;
@@ -170,14 +182,14 @@ base_backup:
 				}
 			;
 
-base_backup_opt_list:
-			base_backup_opt_list base_backup_opt
+base_backup_legacy_opt_list:
+			base_backup_legacy_opt_list base_backup_legacy_opt
 				{ $$ = lappend($1, $2); }
 			| /* EMPTY */
 				{ $$ = NIL; }
 			;
 
-base_backup_opt:
+base_backup_legacy_opt:
 			K_LABEL SCONST
 				{
 				  $$ = makeDefElem("label",
@@ -190,8 +202,8 @@ base_backup_opt:
 				}
 			| K_FAST
 				{
-				  $$ = makeDefElem("fast",
-								   (Node *)makeInteger(true), -1);
+				  $$ = makeDefElem("checkpoint",
+								   (Node *)makeString("fast"), -1);
 				}
 			| K_WAL
 				{
@@ -200,8 +212,8 @@ base_backup_opt:
 				}
 			| K_NOWAIT
 				{
-				  $$ = makeDefElem("nowait",
-								   (Node *)makeInteger(true), -1);
+				  $$ = makeDefElem("wait",
+								   (Node *)makeInteger(false), -1);
 				}
 			| K_MAX_RATE UCONST
 				{
@@ -215,8 +227,8 @@ base_backup_opt:
 				}
 			| K_NOVERIFY_CHECKSUMS
 				{
-				  $$ = makeDefElem("noverify_checksums",
-								   (Node *)makeInteger(true), -1);
+				  $$ = makeDefElem("verify_checksums",
+								   (Node *)makeInteger(false), -1);
 				}
 			| K_MANIFEST SCONST
 				{
@@ -422,6 +434,65 @@ plugin_opt_arg:
 sql_cmd:
 			IDENT							{ $$ = (Node *) make_sqlcmd(); }
 		;
+
+generic_option_list:
+			generic_option_list ',' generic_option
+				{ $$ = lappend($1, $3); }
+			| generic_option
+				{ $$ = list_make1($1); }
+			;
+
+generic_option:
+			ident_or_keyword
+				{
+					$$ = makeDefElem($1, NULL, -1);
+				}
+			| ident_or_keyword IDENT
+				{
+					$$ = makeDefElem($1, (Node *) makeString($2), -1);
+				}
+			| ident_or_keyword SCONST
+				{
+					$$ = makeDefElem($1, (Node *) makeString($2), -1);
+				}
+			| ident_or_keyword UCONST
+				{
+					$$ = makeDefElem($1, (Node *) makeInteger($2), -1);
+				}
+			;
+
+ident_or_keyword:
+			IDENT							{ $$ = $1; }
+			| K_BASE_BACKUP					{ $$ = "base_backup"; }
+			| K_IDENTIFY_SYSTEM				{ $$ = "identify_system"; }
+			| K_SHOW						{ $$ = "show"; }
+			| K_START_REPLICATION			{ $$ = "start_replication"; }
+			| K_CREATE_REPLICATION_SLOT	{ $$ = "create_replication_slot"; }
+			| K_DROP_REPLICATION_SLOT		{ $$ = "drop_replication_slot"; }
+			| K_TIMELINE_HISTORY			{ $$ = "timeline_history"; }
+			| K_LABEL						{ $$ = "label"; }
+			| K_PROGRESS					{ $$ = "progress"; }
+			| K_FAST						{ $$ = "fast"; }
+			| K_WAIT						{ $$ = "wait"; }
+			| K_NOWAIT						{ $$ = "nowait"; }
+			| K_MAX_RATE					{ $$ = "max_rate"; }
+			| K_WAL							{ $$ = "wal"; }
+			| K_TABLESPACE_MAP				{ $$ = "tablespace_map"; }
+			| K_NOVERIFY_CHECKSUMS			{ $$ = "noverify_checksums"; }
+			| K_TIMELINE					{ $$ = "timeline"; }
+			| K_PHYSICAL					{ $$ = "physical"; }
+			| K_LOGICAL						{ $$ = "logical"; }
+			| K_SLOT						{ $$ = "slot"; }
+			| K_RESERVE_WAL					{ $$ = "reserve_wal"; }
+			| K_TEMPORARY					{ $$ = "temporary"; }
+			| K_TWO_PHASE					{ $$ = "two_phase"; }
+			| K_EXPORT_SNAPSHOT				{ $$ = "export_snapshot"; }
+			| K_NOEXPORT_SNAPSHOT			{ $$ = "noexport_snapshot"; }
+			| K_USE_SNAPSHOT				{ $$ = "use_snapshot"; }
+			| K_MANIFEST					{ $$ = "manifest"; }
+			| K_MANIFEST_CHECKSUMS			{ $$ = "manifest_checksums"; }
+		;
+
 %%
 
 static SQLCmd *
diff --git a/src/bin/pg_basebackup/pg_basebackup.c b/src/bin/pg_basebackup/pg_basebackup.c
index 669aa207a3c..27ee6394cfa 100644
--- a/src/bin/pg_basebackup/pg_basebackup.c
+++ b/src/bin/pg_basebackup/pg_basebackup.c
@@ -1804,10 +1804,6 @@ BaseBackup(void)
 	TimeLineID	latesttli;
 	TimeLineID	starttli;
 	char	   *basebkp;
-	char		escaped_label[MAXPGPATH];
-	char	   *maxrate_clause = NULL;
-	char	   *manifest_clause = NULL;
-	char	   *manifest_checksums_clause = "";
 	int			i;
 	char		xlogstart[64];
 	char		xlogend[64];
@@ -1816,8 +1812,11 @@ BaseBackup(void)
 	int			serverVersion,
 				serverMajor;
 	int			writing_to_stdout;
+	bool		use_new_option_syntax = false;
+	PQExpBufferData buf;
 
 	Assert(conn != NULL);
+	initPQExpBuffer(&buf);
 
 	/*
 	 * Check server version. BASE_BACKUP command was introduced in 9.1, so we
@@ -1835,6 +1834,8 @@ BaseBackup(void)
 					 serverver ? serverver : "'unknown'");
 		exit(1);
 	}
+	if (serverMajor >= 1500)
+		use_new_option_syntax = true;
 
 	/*
 	 * If WAL streaming was requested, also check that the server is new
@@ -1865,20 +1866,48 @@ BaseBackup(void)
 	/*
 	 * Start the actual backup
 	 */
-	PQescapeStringConn(conn, escaped_label, label, sizeof(escaped_label), &i);
-
+	AppendStringCommandOption(&buf, use_new_option_syntax, "LABEL", label);
+	if (estimatesize)
+		AppendPlainCommandOption(&buf, use_new_option_syntax, "PROGRESS");
+	if (includewal == FETCH_WAL)
+		AppendPlainCommandOption(&buf, use_new_option_syntax, "WAL");
+	if (fastcheckpoint)
+	{
+		if (use_new_option_syntax)
+			AppendStringCommandOption(&buf, use_new_option_syntax,
+									  "CHECKPOINT", "fast");
+		else
+			AppendPlainCommandOption(&buf, use_new_option_syntax, "FAST");
+	}
+	if (includewal != NO_WAL)
+	{
+		if (use_new_option_syntax)
+			AppendIntegerCommandOption(&buf, use_new_option_syntax, "WAIT", 0);
+		else
+			AppendPlainCommandOption(&buf, use_new_option_syntax, "NOWAIT");
+	}
 	if (maxrate > 0)
-		maxrate_clause = psprintf("MAX_RATE %u", maxrate);
+		AppendIntegerCommandOption(&buf, use_new_option_syntax, "MAX_RATE",
+									  maxrate);
+	if (format == 't')
+		AppendPlainCommandOption(&buf, use_new_option_syntax, "TABLESPACE_MAP");
+	if (!verify_checksums)
+	{
+		if (use_new_option_syntax)
+			AppendIntegerCommandOption(&buf, use_new_option_syntax,
+										  "VERIFY_CHECKSUMS", 0);
+		else
+			AppendPlainCommandOption(&buf, use_new_option_syntax,
+										"NOVERIFY_CHECKSUMS");
+	}
 
 	if (manifest)
 	{
-		if (manifest_force_encode)
-			manifest_clause = "MANIFEST 'force-encode'";
-		else
-			manifest_clause = "MANIFEST 'yes'";
+		AppendStringCommandOption(&buf, use_new_option_syntax, "MANIFEST",
+									 manifest_force_encode ? "force-encode" : "yes");
 		if (manifest_checksums != NULL)
-			manifest_checksums_clause = psprintf("MANIFEST_CHECKSUMS '%s'",
-												 manifest_checksums);
+			AppendStringCommandOption(&buf, use_new_option_syntax,
+										 "MANIFEST_CHECKSUMS", manifest_checksums);
 	}
 
 	if (verbose)
@@ -1893,18 +1922,10 @@ BaseBackup(void)
 			fprintf(stderr, "\n");
 	}
 
-	basebkp =
-		psprintf("BASE_BACKUP LABEL '%s' %s %s %s %s %s %s %s %s %s",
-				 escaped_label,
-				 estimatesize ? "PROGRESS" : "",
-				 includewal == FETCH_WAL ? "WAL" : "",
-				 fastcheckpoint ? "FAST" : "",
-				 includewal == NO_WAL ? "" : "NOWAIT",
-				 maxrate_clause ? maxrate_clause : "",
-				 format == 't' ? "TABLESPACE_MAP" : "",
-				 verify_checksums ? "" : "NOVERIFY_CHECKSUMS",
-				 manifest_clause ? manifest_clause : "",
-				 manifest_checksums_clause);
+	if (use_new_option_syntax && buf.len > 0)
+		basebkp = psprintf("BASE_BACKUP (%s)", buf.data);
+	else
+		basebkp = psprintf("BASE_BACKUP %s", buf.data);
 
 	if (PQsendQuery(conn, basebkp) == 0)
 	{
diff --git a/src/bin/pg_basebackup/streamutil.c b/src/bin/pg_basebackup/streamutil.c
index f5b3b476e52..d782b81adc6 100644
--- a/src/bin/pg_basebackup/streamutil.c
+++ b/src/bin/pg_basebackup/streamutil.c
@@ -603,6 +603,67 @@ DropReplicationSlot(PGconn *conn, const char *slot_name)
 	return true;
 }
 
+/*
+ * Append a "plain" option - one with no value - to a server command that
+ * is being constructed.
+ *
+ * In the old syntax, all options were parser keywords, so you could just
+ * write things like SOME_COMMAND OPTION1 OPTION2 'opt2value' OPTION3 42. The
+ * new syntax uses a comma-separated list surrounded by parentheses, so the
+ * equivalent is SOME_COMMAND (OPTION1, OPTION2 'optvalue', OPTION3 42).
+ */
+void
+AppendPlainCommandOption(PQExpBuffer buf, bool use_new_option_syntax,
+						 char *option_name)
+{
+	if (buf->len > 0 && buf->data[buf->len - 1] != '(')
+	{
+		if (use_new_option_syntax)
+			appendPQExpBufferStr(buf, ", ");
+		else
+			appendPQExpBufferChar(buf, ' ');
+	}
+
+	appendPQExpBuffer(buf, " %s", option_name);
+}
+
+/*
+ * Append an option with an associated string value to a server command that
+ * is being constructed.
+ *
+ * See comments for AppendPlainCommandOption, above.
+ */
+void
+AppendStringCommandOption(PQExpBuffer buf, bool use_new_option_syntax,
+						  char *option_name, char *option_value)
+{
+	AppendPlainCommandOption(buf, use_new_option_syntax, option_name);
+
+	if (option_value != NULL)
+	{
+		size_t		length = strlen(option_value);
+		char	   *escaped_value = palloc(1 + 2 * length);
+
+		PQescapeStringConn(conn, escaped_value, option_value, length, NULL);
+		appendPQExpBuffer(buf, " '%s'", escaped_value);
+		pfree(escaped_value);
+	}
+}
+
+/*
+ * Append an option with an associated integer value to a server command
+ * is being constructed.
+ *
+ * See comments for AppendPlainCommandOption, above.
+ */
+void
+AppendIntegerCommandOption(PQExpBuffer buf, bool use_new_option_syntax,
+						   char *option_name, int32 option_value)
+{
+	AppendPlainCommandOption(buf, use_new_option_syntax, option_name);
+
+	appendPQExpBuffer(buf, " %d", option_value);
+}
 
 /*
  * Frontend version of GetCurrentTimestamp(), since we are not linked with
diff --git a/src/bin/pg_basebackup/streamutil.h b/src/bin/pg_basebackup/streamutil.h
index 504803b9763..65135c79e08 100644
--- a/src/bin/pg_basebackup/streamutil.h
+++ b/src/bin/pg_basebackup/streamutil.h
@@ -15,6 +15,7 @@
 #include "access/xlogdefs.h"
 #include "datatype/timestamp.h"
 #include "libpq-fe.h"
+#include "pqexpbuffer.h"
 
 extern const char *progname;
 extern char *connection_string;
@@ -40,6 +41,17 @@ extern bool RunIdentifySystem(PGconn *conn, char **sysid,
 							  TimeLineID *starttli,
 							  XLogRecPtr *startpos,
 							  char **db_name);
+
+extern void AppendPlainCommandOption(PQExpBuffer buf,
+									 bool use_new_option_syntax,
+									 char *option_value);
+extern void AppendStringCommandOption(PQExpBuffer buf,
+									  bool use_new_option_syntax,
+									  char *option_name, char *option_value);
+extern void AppendIntegerCommandOption(PQExpBuffer buf,
+									   bool use_new_option_syntax,
+									   char *option_name, int32 option_value);
+
 extern bool RetrieveWalSegSize(PGconn *conn);
 extern TimestampTz feGetCurrentTimestamp(void);
 extern void feTimestampDifference(TimestampTz start_time, TimestampTz stop_time,
-- 
cgit v1.2.3