Prevent duplicate escape-string warnings when using pg_stat_statements.

tglsfdc · tglsfdc · commit eb213acfe2a5 · 2015-01-22T18:11:00.000-05:00
contrib/pg_stat_statements will sometimes run the core lexer a second time
on submitted statements.  Formerly, if you had standard_conforming_strings
turned off, this led to sometimes getting two copies of any warnings
enabled by escape_string_warning.  While this is probably no longer a big
deal in the field, it's a pain for regression testing.

To fix, change the lexer so it doesn't consult the escape_string_warning
GUC variable directly, but looks at a copy in the core_yy_extra_type state
struct.  Then, pg_stat_statements can change that copy to disable warnings
while it's redoing the lexing.

It seemed like a good idea to make this happen for all three of the GUCs
consulted by the lexer, not just escape_string_warning.  There's not an
immediate use-case for callers to adjust the other two AFAIK, but making
it possible is easy enough and seems like good future-proofing.

Arguably this is a bug fix, but there doesn't seem to be enough interest to
justify a back-patch.  We'd not be able to back-patch exactly as-is anyway,
for fear of breaking ABI compatibility of the struct.  (We could perhaps
back-patch the addition of only escape_string_warning by adding it at the
end of the struct, where there's currently alignment padding space.)
diff --git a/contrib/pg_stat_statements/pg_stat_statements.c b/contrib/pg_stat_statements/pg_stat_statements.c
@@ -2816,6 +2816,9 @@ fill_in_constant_lengths(pgssJumbleState *jstate, const char *query)
 							 ScanKeywords,
 							 NumScanKeywords);
 
+	/* we don't want to re-emit any escape string warnings */
+	yyextra.escape_string_warning = false;
+
 	/* Search for each constant, in sequence */
 	for (i = 0; i < jstate->clocations_count; i++)
 	{
diff --git a/src/backend/parser/scan.l b/src/backend/parser/scan.l
@@ -505,7 +505,7 @@ other			.
 					yyextra->warn_on_first_escape = true;
 					yyextra->saw_non_ascii = false;
 					SET_YYLLOC();
-					if (standard_conforming_strings)
+					if (yyextra->standard_conforming_strings)
 						BEGIN(xq);
 					else
 						BEGIN(xe);
@@ -520,7 +520,7 @@ other			.
 				}
 {xusstart}		{
 					SET_YYLLOC();
-					if (!standard_conforming_strings)
+					if (!yyextra->standard_conforming_strings)
 						ereport(ERROR,
 								(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
 								 errmsg("unsafe use of string constant with Unicode escapes"),
@@ -622,8 +622,8 @@ other			.
 <xe>{xeescape}  {
 					if (yytext[1] == '\'')
 					{
-						if (backslash_quote == BACKSLASH_QUOTE_OFF ||
-							(backslash_quote == BACKSLASH_QUOTE_SAFE_ENCODING &&
+						if (yyextra->backslash_quote == BACKSLASH_QUOTE_OFF ||
+							(yyextra->backslash_quote == BACKSLASH_QUOTE_SAFE_ENCODING &&
 							 PG_ENCODING_IS_CLIENT_ONLY(pg_get_client_encoding())))
 							ereport(ERROR,
 									(errcode(ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER),
@@ -1074,6 +1074,10 @@ scanner_init(const char *str,
 	yyext->keywords = keywords;
 	yyext->num_keywords = num_keywords;
 
+	yyext->backslash_quote = backslash_quote;
+	yyext->escape_string_warning = escape_string_warning;
+	yyext->standard_conforming_strings = standard_conforming_strings;
+
 	/*
 	 * Make a scan buffer with special termination needed by flex.
 	 */
@@ -1433,7 +1437,7 @@ check_string_escape_warning(unsigned char ychar, core_yyscan_t yyscanner)
 {
 	if (ychar == '\'')
 	{
-		if (yyextra->warn_on_first_escape && escape_string_warning)
+		if (yyextra->warn_on_first_escape && yyextra->escape_string_warning)
 			ereport(WARNING,
 					(errcode(ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER),
 					 errmsg("nonstandard use of \\' in a string literal"),
@@ -1443,7 +1447,7 @@ check_string_escape_warning(unsigned char ychar, core_yyscan_t yyscanner)
 	}
 	else if (ychar == '\\')
 	{
-		if (yyextra->warn_on_first_escape && escape_string_warning)
+		if (yyextra->warn_on_first_escape && yyextra->escape_string_warning)
 			ereport(WARNING,
 					(errcode(ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER),
 					 errmsg("nonstandard use of \\\\ in a string literal"),
@@ -1458,7 +1462,7 @@ check_string_escape_warning(unsigned char ychar, core_yyscan_t yyscanner)
 static void
 check_escape_warning(core_yyscan_t yyscanner)
 {
-	if (yyextra->warn_on_first_escape && escape_string_warning)
+	if (yyextra->warn_on_first_escape && yyextra->escape_string_warning)
 		ereport(WARNING,
 				(errcode(ERRCODE_NONSTANDARD_USE_OF_ESCAPE_CHARACTER),
 				 errmsg("nonstandard use of escape in a string literal"),
diff --git a/src/include/parser/scanner.h b/src/include/parser/scanner.h
@@ -77,6 +77,16 @@ typedef struct core_yy_extra_type
 	const ScanKeyword *keywords;
 	int			num_keywords;
 
+	/*
+	 * Scanner settings to use.  These are initialized from the corresponding
+	 * GUC variables by scanner_init().  Callers can modify them after
+	 * scanner_init() if they don't want the scanner's behavior to follow the
+	 * prevailing GUC settings.
+	 */
+	int			backslash_quote;
+	bool		escape_string_warning;
+	bool		standard_conforming_strings;
+
 	/*
 	 * literalbuf is used to accumulate literal values when multiple rules are
 	 * needed to parse a single literal.  Call startlit() to reset buffer to

Original file line number	Diff line number	Diff line change
`@@ -2816,6 +2816,9 @@ fill_in_constant_lengths(pgssJumbleState jstate, const char query)`
`2816`	`2816`	`ScanKeywords,`
`2817`	`2817`	`NumScanKeywords);`
`2818`	`2818`
	`2819`	`+ /* we don't want to re-emit any escape string warnings */`
	`2820`	`+ yyextra.escape_string_warning = false;`
	`2821`	`+`
`2819`	`2822`	`/* Search for each constant, in sequence */`
`2820`	`2823`	`for (i = 0; i < jstate->clocations_count; i++)`
`2821`	`2824`	`{`