Fix ancient bug in parsing of BRE-mode regular expressions.

tglsfdc · tglsfdc · commit afcc8772edce · 2021-01-08T12:16:00.000-05:00
brenext(), when parsing a '*' quantifier, forgot to return any "value" for the token; per the equivalent case in next(), it should return value 1 to indicate that greedy rather than non-greedy behavior is wanted. The result is that the compiled regexp could behave like 'x*?' rather than the intended 'x*', if we were unlucky enough to have a zero in v->nextvalue at this point. That seems to happen with some reliability if we have '.*' at the beginning of a BRE-mode regexp, although that depends on the initial contents of a stack-allocated struct, so it's not guaranteed to fail. Found by Alexander Lakhin using valgrind testing. This bug seems to be aboriginal in Spencer's code, so back-patch all the way. Discussion: https://postgr.es/m/16814-6c5e3edd2bdf0d50@postgresql.org
diff --git a/src/backend/regex/regc_lex.c b/src/backend/regex/regc_lex.c
@@ -994,7 +994,7 @@ brenext(struct vars *v,
 		case CHR('*'):
 			if (LASTTYPE(EMPTY) || LASTTYPE('(') || LASTTYPE('^'))
 				RETV(PLAIN, c);
-			RET('*');
+			RETV('*', 1);
 			break;
 		case CHR('['):
 			if (HAVE(6) && *(v->now + 0) == CHR('[') &&
diff --git a/src/test/modules/test_regex/expected/test_regex.out b/src/test/modules/test_regex/expected/test_regex.out
@@ -614,6 +614,14 @@ ERROR:  invalid regular expression: quantifier operand invalid
 -- expectError	7.15 -		a*+	BADRPT
 select * from test_regex('a*+', '', '-');
 ERROR:  invalid regular expression: quantifier operand invalid
+-- test for ancient brenext() bug; not currently in Tcl
+select * from test_regex('.*b', 'aaabbb', 'b');
+ test_regex 
+------------
+ {0}
+ {aaabbb}
+(2 rows)
+
 -- doing 8 "braces"
 -- expectMatch	8.1  NQ		"a{0,1}"	""	""
 select * from test_regex('a{0,1}', '', 'NQ');
diff --git a/src/test/modules/test_regex/sql/test_regex.sql b/src/test/modules/test_regex/sql/test_regex.sql
@@ -214,6 +214,8 @@ select * from test_regex('a?*', '', '-');
 select * from test_regex('a+*', '', '-');
 -- expectError	7.15 -		a*+	BADRPT
 select * from test_regex('a*+', '', '-');
+-- test for ancient brenext() bug; not currently in Tcl
+select * from test_regex('.*b', 'aaabbb', 'b');
 
 -- doing 8 "braces"
 
