sed: process \r, \n, and \t

This is both reasonable and a common GNUism that a lot of ported software
expects.

Universally process \r, \n, and \t into carriage return, newline, and tab
respectively. Newline still doesn't function in contexts where it can't
(e.g. BRE), but we process it anyways rather than passing
UB \n (escaped ordinary) through to the underlying regex engine.

Adding a --posix flag to disable these was considered, but sed.1 already
declares this version of sed a super-set of POSIX specification and this
behavior is the most likely expected when one attempts to use one of these
escape sequences in pattern space.

This differs from pre-r197362 behavior in that we now honor the three
arguably most common escape sequences used with sed(1) and we do so outside
of character classes, too.

Other escape sequences, like \s and \S, will come later when GNU extensions
are added to libregex; sed will likely link against libregex by default,
since the GNU extensions tend to be fairly un-intrusive.

PR:		229925
Reviewed by:	bapt, emaste, pfg
Differential Revision:	https://reviews.freebsd.org/D22750

3 files changed, 69 insertions, 8 deletions

diff --git a/usr.bin/sed/compile.c b/usr.bin/sed/compile.c
index 4427faeff4a2..e03103420559 100644
--- a/usr.bin/sed/compile.c
+++ b/usr.bin/sed/compile.c
@@ -395,10 +395,21 @@ compile_delimited(char *p, char *d, int is_tr)
 			continue;
 		} else if (*p == '\\' && p[1] == '[') {
 			*d++ = *p++;
-		} else if (*p == '\\' && p[1] == c)
+		} else if (*p == '\\' && p[1] == c) {
 			p++;
-		else if (*p == '\\' && p[1] == 'n') {
-			*d++ = '\n';
+		} else if (*p == '\\' &&
+		    (p[1] == 'n' || p[1] == 'r' || p[1] == 't')) {
+			switch (p[1]) {
+			case 'n':
+				*d++ = '\n';
+				break;
+			case 'r':
+				*d++ = '\r';
+				break;
+			case 't':
+				*d++ = '\t';
+				break;
+			}
 			p += 2;
 			continue;
 		} else if (*p == '\\' && p[1] == '\\') {
@@ -428,13 +439,29 @@ compile_ccl(char **sp, char *t)
 		*t++ = *s++;
 	if (*s == ']')
 		*t++ = *s++;
-	for (; *s && (*t = *s) != ']'; s++, t++)
+	for (; *s && (*t = *s) != ']'; s++, t++) {
 		if (*s == '[' && ((d = *(s+1)) == '.' || d == ':' || d == '=')) {
 			*++t = *++s, t++, s++;
 			for (c = *s; (*t = *s) != ']' || c != d; s++, t++)
 				if ((c = *s) == '\0')
 					return NULL;
+		} else if (*s == '\\') {
+			switch (s[1]) {
+			case 'n':
+				*t = '\n';
+				s++;
+				break;
+			case 'r':
+				*t = '\r';
+				s++;
+				break;
+			case 't':
+				*t = '\t';
+				s++;
+				break;
+			}
 		}
+	}
 	return (*s == ']') ? *sp = ++s, ++t : NULL;
 }
 
@@ -521,8 +548,23 @@ compile_subst(char *p, struct s_subst *s)
 								linenum, fname, *p);
 					if (s->maxbref < ref)
 						s->maxbref = ref;
-				} else if (*p == '&' || *p == '\\')
-					*sp++ = '\\';
+				} else {
+					switch (*p) {
+					case '&':
+					case '\\':
+						*sp++ = '\\';
+						break;
+					case 'n':
+						*p = '\n';
+						break;
+					case 'r':
+						*p = '\r';
+						break;
+					case 't':
+						*p = '\t';
+						break;
+					}
+				}
 			} else if (*p == c) {
 				if (*++p == '\0' && more) {
 					if (cu_fgets(lbuf, sizeof(lbuf), &more))
diff --git a/usr.bin/sed/tests/regress.multitest.out/8.22 b/usr.bin/sed/tests/regress.multitest.out/8.22
index 1191247b6d9a..c66dd65b0993 100644
--- a/usr.bin/sed/tests/regress.multitest.out/8.22
+++ b/usr.bin/sed/tests/regress.multitest.out/8.22
@@ -1,2 +1 @@
-1
-2
+1X2
diff --git a/usr.bin/sed/tests/sed2_test.sh b/usr.bin/sed/tests/sed2_test.sh
index 9acd628a8f1e..48e1c2b216f6 100755
--- a/usr.bin/sed/tests/sed2_test.sh
+++ b/usr.bin/sed/tests/sed2_test.sh
@@ -69,9 +69,29 @@ inplace_command_q_body()
 	atf_check -s not-exit:0 stat -q '.!'*
 }
 
+atf_test_case escape_subst
+escape_subst_head()
+{
+	atf_set "descr" "Verify functional escaping of \\n, \\r, and \\t"
+}
+escape_subst_body()
+{
+	printf "a\nt\\\t\n\tb\n\t\tc\r\n" > a
+	tr -d '\r' < a > b
+	printf "a\tb c\rx\n" > c
+
+	atf_check -o 'inline:a\nt\\t\n' sed '/\t/d' a
+	atf_check -o 'inline:a\nt\\t\n    b\n        c\r\n' sed 's/\t/    /g' a
+	atf_check -o 'inline:a\nt\\t\n\t\tb\n\t\t\t\tc\r\n' sed 's/\t/\t\t/g' a
+	atf_check -o 'inline:a\nt\n\tb\n\t\tc\r\n' sed 's/\\t//g' a
+	atf_check -o file:b sed 's/\r//' a
+	atf_check -o 'inline:abcx\n' sed 's/[ \r\t]//g' c
+}
+
 atf_init_test_cases()
 {
 	atf_add_test_case inplace_command_q
 	atf_add_test_case inplace_hardlink_src
 	atf_add_test_case inplace_symlink_src
+	atf_add_test_case escape_subst
 }