Fix pg_restore's processing of old-style BLOB COMMENTS data.

tglsfdc · tglsfdc · commit ce7fc4fbbca7 · 2014-06-12T20:14:46.000-04:00
Prior to 9.0, pg_dump handled comments on large objects by dumping a bunch
of COMMENT commands into a single BLOB COMMENTS archive object.  With
sufficiently many such comments, some of the commands would likely get
split across bufferloads when restoring, causing failures in
direct-to-database restores (though no problem would be evident in text
output).  This is the same type of issue we have with table data dumped as
INSERT commands, and it can be fixed in the same way, by using a mini SQL
lexer to figure out where the command boundaries are.  Fortunately, the
COMMENT commands are no more complex to lex than INSERTs, so we can just
re-use the existing lexer for INSERTs.

Per bug #10611 from Jacek Zalewski.  Back-patch to all active branches.
diff --git a/src/bin/pg_dump/pg_backup_archiver.c b/src/bin/pg_dump/pg_backup_archiver.c
@@ -672,7 +672,13 @@ restore_toc_entry(ArchiveHandle *AH, TocEntry *te,
 
 					_selectOutputSchema(AH, "pg_catalog");
 
+					/* Send BLOB COMMENTS data to ExecuteSimpleCommands() */
+					if (strcmp(te->desc, "BLOB COMMENTS") == 0)
+						AH->outputKind = OUTPUT_OTHERDATA;
+
 					(*AH->PrintTocDataPtr) (AH, te, ropt);
+
+					AH->outputKind = OUTPUT_SQLCMDS;
 				}
 				else
 				{
diff --git a/src/bin/pg_dump/pg_backup_db.c b/src/bin/pg_dump/pg_backup_db.c
@@ -425,9 +425,14 @@ ExecuteSqlCommand(ArchiveHandle *AH, const char *qry, const char *desc)
  * identifiers, so that we can recognize statement-terminating semicolons.
  * We assume that INSERT data will not contain SQL comments, E'' literals,
  * or dollar-quoted strings, so this is much simpler than a full SQL lexer.
+ *
+ * Note: when restoring from a pre-9.0 dump file, this code is also used to
+ * process BLOB COMMENTS data, which has the same problem of containing
+ * multiple SQL commands that might be split across bufferloads.  Fortunately,
+ * that data won't contain anything complicated to lex either.
  */
 static void
-ExecuteInsertCommands(ArchiveHandle *AH, const char *buf, size_t bufLen)
+ExecuteSimpleCommands(ArchiveHandle *AH, const char *buf, size_t bufLen)
 {
 	const char *qry = buf;
 	const char *eos = buf + bufLen;
@@ -511,9 +516,10 @@ ExecuteSqlCommandBuf(ArchiveHandle *AH, const char *buf, size_t bufLen)
 	else if (AH->outputKind == OUTPUT_OTHERDATA)
 	{
 		/*
-		 * Table data expressed as INSERT commands.
+		 * Table data expressed as INSERT commands; or, in old dump files,
+		 * BLOB COMMENTS data (which is expressed as COMMENT ON commands).
 		 */
-		ExecuteInsertCommands(AH, buf, bufLen);
+		ExecuteSimpleCommands(AH, buf, bufLen);
 	}
 	else
 	{
diff --git a/src/bin/pg_dump/pg_dump.c b/src/bin/pg_dump/pg_dump.c
@@ -1415,7 +1415,7 @@ dumpTableData_copy(Archive *fout, void *dcontext)
  *
  * Caution: when we restore from an archive file direct to database, the
  * INSERT commands emitted by this function have to be parsed by
- * pg_backup_db.c's ExecuteInsertCommands(), which will not handle comments,
+ * pg_backup_db.c's ExecuteSimpleCommands(), which will not handle comments,
  * E'' strings, or dollar-quoted strings.  So don't emit anything like that.
  */
 static int

Original file line number	Diff line number	Diff line change
`@@ -672,7 +672,13 @@ restore_toc_entry(ArchiveHandle AH, TocEntry te,`
`672`	`672`
`673`	`673`	`_selectOutputSchema(AH, "pg_catalog");`
`674`	`674`
	`675`	`+ /* Send BLOB COMMENTS data to ExecuteSimpleCommands() */`
	`676`	`+ if (strcmp(te->desc, "BLOB COMMENTS") == 0)`
	`677`	`+ AH->outputKind = OUTPUT_OTHERDATA;`
	`678`	`+`
`675`	`679`	`(*AH->PrintTocDataPtr) (AH, te, ropt);`
	`680`	`+`
	`681`	`+ AH->outputKind = OUTPUT_SQLCMDS;`
`676`	`682`	`}`
`677`	`683`	`else`
`678`	`684`	`{`
Original file line number	Diff line number	Diff line change
`@@ -1415,7 +1415,7 @@ dumpTableData_copy(Archive fout, void dcontext)`
`1415`	`1415`	`*`
`1416`	`1416`	`* Caution: when we restore from an archive file direct to database, the`
`1417`	`1417`	`* INSERT commands emitted by this function have to be parsed by`
`1418`		`- * pg_backup_db.c's ExecuteInsertCommands(), which will not handle comments,`
	`1418`	`+ * pg_backup_db.c's ExecuteSimpleCommands(), which will not handle comments,`
`1419`	`1419`	`* E'' strings, or dollar-quoted strings. So don't emit anything like that.`
`1420`	`1420`	`*/`
`1421`	`1421`	`static int`