printf: Allow multibyte characters for '<char> form, avoid negative codes.

Examples:
  LC_ALL=en_US.UTF-8 printf '%d\n' $(printf \'\\303\\244)
  LC_ALL=en_US.ISO8859-1 printf '%d\n' $(printf \'\\344)
Both of these should print 228.

Like some other shells, incomplete or invalid multibyte characters yield the
value of the first byte without a warning.

Note that there is no general way to go back from the character code to the
character.

2 files changed, 20 insertions, 7 deletions

diff --git a/usr.bin/printf/printf.1 b/usr.bin/printf/printf.1
index 56c6855..2afb9d3 100644
--- a/usr.bin/printf/printf.1
+++ b/usr.bin/printf/printf.1
@@ -31,7 +31,7 @@
 .\"	@(#)printf.1	8.1 (Berkeley) 6/6/93
 .\" $FreeBSD$
 .\"
-.Dd April 25, 2011
+.Dd May 28, 2011
 .Dt PRINTF 1
 .Os
 .Sh NAME
@@ -68,8 +68,7 @@ otherwise it is evaluated as a C constant, with the following extensions:
 A leading plus or minus sign is allowed.
 .It
 If the leading character is a single or double quote, the value is the
-.Tn ASCII
-code of the next character.
+character code of the next character.
 .El
 .Pp
 The format string is reused as often as necessary to satisfy the
diff --git a/usr.bin/printf/printf.c b/usr.bin/printf/printf.c
index 56c1caf..eace370 100644
--- a/usr.bin/printf/printf.c
+++ b/usr.bin/printf/printf.c
@@ -58,6 +58,7 @@ static const char rcsid[] =
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
+#include <wchar.h>
 
 #ifdef SHELL
 #define main printfcmd
@@ -537,10 +538,23 @@ static int
 asciicode(void)
 {
 	int ch;
-
-	ch = **gargv;
-	if (ch == '\'' || ch == '"')
-		ch = (*gargv)[1];
+	wchar_t wch;
+	mbstate_t mbs;
+
+	ch = (unsigned char)**gargv;
+	if (ch == '\'' || ch == '"') {
+		memset(&mbs, 0, sizeof(mbs));
+		switch (mbrtowc(&wch, *gargv + 1, MB_LEN_MAX, &mbs)) {
+		case (size_t)-2:
+		case (size_t)-1:
+			wch = (unsigned char)gargv[0][1];
+			break;
+		case 0:
+			wch = 0;
+			break;
+		}
+		ch = wch;
+	}
 	++gargv;
 	return (ch);
 }