svn commit: r322211 - in head: contrib/netbsd-tests/lib/libc/regex/data lib/libc/regex

[Kyle Evans]

Author: kevans
Date: Tue Aug  8 04:10:46 2017
New Revision: 322211
URL: https://svnweb.freebsd.org/changeset/base/322211

Log:
  regex(3): Handle invalid {} constructs consistently and adjust tests
  
  Currently, regex(3) exhibits the following wrong behavior as demonstrated
  with sed:
  
   - echo "a{1,2,3}b" | sed -r "s/{/_/"     (1)
   - echo "a{1,2,3}b" | sed "s/\}/_/"       (2)
   - echo "a{1,2,3}b" | sed -r "s/{}/_/"    (3)
  
  Cases (1) and (3) should throw errors but they actually succeed, and (2)
  throws an error when it should match the literal '}'. The correct behavior
  was decided by comparing to the behavior with the equivalent BRE (1)(3) or
  ERE (2) and consulting POSIX, along with some reasonable evaluation.
  
  Tests were also adjusted/added accordingly.
  
  PR:		166861
  Reviewed by:	emaste, ngie, pfg
  Approved by:	emaste (mentor)
  MFC after:	never
  Differential Revision:	https://reviews.freebsd.org/D10315

Modified:
  head/contrib/netbsd-tests/lib/libc/regex/data/repet_bounded.in
  head/contrib/netbsd-tests/lib/libc/regex/data/repet_multi.in
  head/lib/libc/regex/regcomp.c

Modified: head/contrib/netbsd-tests/lib/libc/regex/data/repet_bounded.in
==============================================================================
--- head/contrib/netbsd-tests/lib/libc/regex/data/repet_bounded.in	Tue Aug  8 00:31:10 2017	(r322210)
+++ head/contrib/netbsd-tests/lib/libc/regex/data/repet_bounded.in	Tue Aug  8 04:10:46 2017	(r322211)
@@ -1,9 +1,24 @@
 # the dreaded bounded repetitions
-{		&	{	{
-{abc		&	{abc	{abc
+# Begin FreeBSD
+{		C	BADRPT
+{		b	{	{
+\{		-	{	{
+\{		bC	BADRPT
+{}		C	BADRPT
+{}		b	{}	{}
+\{\}		-	{}	{}
+\{\}		bC	BADRPT
+}		&	}	}
+\}		&	}	}
+{abc		b	{abc	{abc
+{abc		C	BADRPT
+# End FreeBSD
 {1		C	BADRPT
 {1}		C	BADRPT
-a{b		&	a{b	a{b
+# Begin FreeBSD
+a{b		b	a{b	a{b
+a{b		C	BADRPT
+# End FreeBSD
 a{1}b		-	ab	ab
 a\{1\}b		b	ab	ab
 a{1,}b		-	ab	ab
@@ -16,9 +31,15 @@ a{1a		C	EBRACE
 a\{1a		bC	EBRACE
 a{1a}		C	BADBR
 a\{1a\}		bC	BADBR
-a{,2}		-	a{,2}	a{,2}
+# Begin FreeBSD
+a{,2}		b	a{,2}	a{,2}
+a{,2}		C	BADBR
+# End FreeBSD
 a\{,2\}		bC	BADBR
-a{,}		-	a{,}	a{,}
+# Begin FreeBSD
+a{,}		b	a{,}	a{,}
+a{,}		C	BADBR
+# End FreeBSD
 a\{,\}		bC	BADBR
 a{1,x}		C	BADBR
 a\{1,x\}	bC	BADBR

Modified: head/contrib/netbsd-tests/lib/libc/regex/data/repet_multi.in
==============================================================================
--- head/contrib/netbsd-tests/lib/libc/regex/data/repet_multi.in	Tue Aug  8 00:31:10 2017	(r322210)
+++ head/contrib/netbsd-tests/lib/libc/regex/data/repet_multi.in	Tue Aug  8 04:10:46 2017	(r322211)
@@ -15,7 +15,10 @@ a?{1}		C	BADRPT
 a{1}*		C	BADRPT
 a{1}+		C	BADRPT
 a{1}?		C	BADRPT
-a*{b}		-	a{b}	a{b}
+# Begin FreeBSD
+a*{b}		b	a{b}	a{b}
+a*{b}		C	BADRPT
+# End FreeBSD
 a\{1\}\{1\}	bC	BADRPT
 a*\{1\}		bC	BADRPT
 a\{1\}*		bC	BADRPT

Modified: head/lib/libc/regex/regcomp.c
==============================================================================
--- head/lib/libc/regex/regcomp.c	Tue Aug  8 00:31:10 2017	(r322210)
+++ head/lib/libc/regex/regcomp.c	Tue Aug  8 04:10:46 2017	(r322211)
@@ -412,6 +412,7 @@ p_ere_exp(struct parse *p, struct branchc *bc)
 	case '*':
 	case '+':
 	case '?':
+	case '{':
 		SETERROR(REG_BADRPT);
 		break;
 	case '.':
@@ -438,9 +439,6 @@ p_ere_exp(struct parse *p, struct branchc *bc)
 			break;
 		}
 		break;
-	case '{':		/* okay as ordinary except if digit follows */
-		(void)REQUIRE(!MORE() || !isdigit((uch)PEEK()), REG_BADRPT);
-		/* FALLTHROUGH */
 	default:
 		if (p->error != 0)
 			return (false);
@@ -454,9 +452,11 @@ p_ere_exp(struct parse *p, struct branchc *bc)
 		return (false);
 	c = PEEK();
 	/* we call { a repetition if followed by a digit */
-	if (!( c == '*' || c == '+' || c == '?' ||
-				(c == '{' && MORE2() && isdigit((uch)PEEK2())) ))
+	if (!( c == '*' || c == '+' || c == '?' || c == '{'))
 		return (false);		/* no repetition, we're done */
+	else if (c == '{')
+		(void)REQUIRE(MORE2() && \
+		    (isdigit((uch)PEEK2()) || PEEK2() == ','), REG_BADRPT);
 	NEXT();
 
 	(void)REQUIRE(!wascaret, REG_BADRPT);
@@ -757,7 +757,6 @@ p_simp_re(struct parse *p, struct branchc *bc)
 		(void)REQUIRE(EATTWO('\\', ')'), REG_EPAREN);
 		break;
 	case BACKSL|')':	/* should not get here -- must be user */
-	case BACKSL|'}':
 		SETERROR(REG_EPAREN);
 		break;
 	case BACKSL|'1':