add -E flag to compile regular expressions using the extended POSIX

syntax. The -E flag is compatible with the other BSDs and OSX. -r is
also provided as an alias for compatibility with GNU sed.

feedback from jmc@ and millert@
ok millert@ pyr@ henning@ marco@

4 files changed, 29 insertions, 16 deletions

diff --git a/usr.bin/sed/compile.c b/usr.bin/sed/compile.c
index bc40a514581..60c6cac9330 100644
--- a/usr.bin/sed/compile.c
+++ b/usr.bin/sed/compile.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: compile.c,v 1.28 2008/10/16 16:34:32 millert Exp $	*/
+/*	$OpenBSD: compile.c,v 1.29 2009/08/07 03:30:56 djm Exp $	*/
 
 /*-
  * Copyright (c) 1992 Diomidis Spinellis.
@@ -35,7 +35,7 @@
 
 #ifndef lint
 /* from: static char sccsid[] = "@(#)compile.c	8.2 (Berkeley) 4/28/95"; */
-static const char rcsid[] = "$OpenBSD: compile.c,v 1.28 2008/10/16 16:34:32 millert Exp $";
+static const char rcsid[] = "$OpenBSD: compile.c,v 1.29 2009/08/07 03:30:56 djm Exp $";
 #endif /* not lint */
 
 #include <sys/types.h>
@@ -439,7 +439,7 @@ compile_re(char *p, regex_t **repp)
 		return (p);
 	}
 	*repp = xmalloc(sizeof(regex_t));
-	if (p && (eval = regcomp(*repp, re, 0)) != 0)
+	if (p && (eval = regcomp(*repp, re, Eflag ? REG_EXTENDED : 0)) != 0)
 		err(COMPILE, "RE error: %s", strregerror(eval, *repp));
 	if (maxnsub < (*repp)->re_nsub)
 		maxnsub = (*repp)->re_nsub;
diff --git a/usr.bin/sed/extern.h b/usr.bin/sed/extern.h
index 80e359576f7..51fa89bb230 100644
--- a/usr.bin/sed/extern.h
+++ b/usr.bin/sed/extern.h
@@ -1,4 +1,4 @@
-/* *	$OpenBSD: extern.h,v 1.5 2008/10/08 17:26:47 millert Exp $*/
+/* *	$OpenBSD: extern.h,v 1.6 2009/08/07 03:30:56 djm Exp $*/
 /*-
  * Copyright (c) 1992 Diomidis Spinellis.
  * Copyright (c) 1992, 1993
@@ -41,7 +41,7 @@ extern size_t maxnsub;
 extern u_long linenum;
 extern int appendnum;
 extern int lastline;
-extern int aflag, eflag, nflag;
+extern int Eflag, aflag, eflag, nflag;
 extern char *fname;
 
 void	 cfclose(struct s_command *, struct s_command *);
diff --git a/usr.bin/sed/main.c b/usr.bin/sed/main.c
index fe2158ba4d1..ac151a90262 100644
--- a/usr.bin/sed/main.c
+++ b/usr.bin/sed/main.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: main.c,v 1.15 2008/10/16 16:34:32 millert Exp $	*/
+/*	$OpenBSD: main.c,v 1.16 2009/08/07 03:30:56 djm Exp $	*/
 
 /*-
  * Copyright (c) 1992 Diomidis Spinellis.
@@ -38,7 +38,7 @@ static const char copyright[] =
 "@(#) Copyright (c) 1992, 1993\n\
 	The Regents of the University of California.  All rights reserved.\n";
 /* from: static char sccsid[] = "@(#)main.c	8.2 (Berkeley) 1/3/94"; */
-static const char rcsid[] = "$OpenBSD: main.c,v 1.15 2008/10/16 16:34:32 millert Exp $";
+static const char rcsid[] = "$OpenBSD: main.c,v 1.16 2009/08/07 03:30:56 djm Exp $";
 #endif /* not lint */
 
 #include <sys/types.h>
@@ -86,7 +86,7 @@ struct s_flist {
  */
 static struct s_flist *files, **fl_nextp = &files;
 
-int aflag, eflag, nflag;
+int Eflag, aflag, eflag, nflag;
 
 /*
  * Current file and line number; line numbers restart across compilation
@@ -105,8 +105,12 @@ main(int argc, char *argv[])
 	int c, fflag;
 
 	fflag = 0;
-	while ((c = getopt(argc, argv, "ae:f:nu")) != -1)
+	while ((c = getopt(argc, argv, "Eae:f:nru")) != -1)
 		switch (c) {
+		case 'E':
+		case 'r':
+			Eflag = 1;
+			break;
 		case 'a':
 			aflag = 1;
 			break;
@@ -127,8 +131,8 @@ main(int argc, char *argv[])
 		default:
 		case '?':
 			(void)fprintf(stderr,
-			    "usage: sed [-anu] command [file ...]\n"
-			    "       sed [-anu] [-e command] [-f command_file] [file ...]\n");
+			    "usage: sed [-aEnru] command [file ...]\n"
+			    "       sed [-aEnru] [-e command] [-f command_file] [file ...]\n");
 			exit(1);
 		}
 	argc -= optind;
diff --git a/usr.bin/sed/sed.1 b/usr.bin/sed/sed.1
index 33270493dc1..d8812d4f145 100644
--- a/usr.bin/sed/sed.1
+++ b/usr.bin/sed/sed.1
@@ -1,4 +1,4 @@
-.\"	$OpenBSD: sed.1,v 1.32 2009/02/08 17:15:10 jmc Exp $
+.\"	$OpenBSD: sed.1,v 1.33 2009/08/07 03:30:56 djm Exp $
 .\"
 .\" Copyright (c) 1992, 1993
 .\"	The Regents of the University of California.  All rights reserved.
@@ -32,7 +32,7 @@
 .\"
 .\"	from: @(#)sed.1	8.2 (Berkeley) 12/30/93
 .\"
-.Dd $Mdocdate: February 8 2009 $
+.Dd $Mdocdate: August 7 2009 $
 .Dt SED 1
 .Os
 .Sh NAME
@@ -40,11 +40,11 @@
 .Nd stream editor
 .Sh SYNOPSIS
 .Nm sed
-.Op Fl anu
+.Op Fl Eanru
 .Ar command
 .Op Ar
 .Nm sed
-.Op Fl anu
+.Op Fl aEnru
 .Op Fl e Ar command
 .Op Fl f Ar command_file
 .Op Ar
@@ -69,6 +69,11 @@ regardless of their origin.
 .Pp
 The options are as follows:
 .Bl -tag -width Ds
+.It Fl E
+Interpret regular expressions using the POSIX extended regular expression
+syntax (documented in
+.Xr re_format 7 ).
+The default behaviour is to use the POSIX basic regular expression syntax.
 .It Fl a
 The files listed as parameters for the
 .Ql w
@@ -91,6 +96,10 @@ Append the editing commands found in the file
 .Ar command_file
 to the list of commands.
 The editing commands should each be listed on a separate line.
+.It Fl r
+is an alias for
+.Fl E
+(enable POSIX extended regular exressions) for compatibility with GNU sed.
 .It Fl n
 By default, each line of input is echoed to the standard output after
 all of the commands have been applied to it.
@@ -520,7 +529,7 @@ utility is compliant with the
 specification.
 .Pp
 The flags
-.Op Fl au
+.Op Fl aEru
 are extensions to that specification.
 .Pp
 The use of newlines to separate multiple commands on the command line