IFC @ r222830

2 files changed, 37 insertions, 13 deletions

diff --git a/usr.bin/printf/printf.1 b/usr.bin/printf/printf.1
index 56c6855..792529a 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
@@ -172,7 +171,7 @@ A `\-' overrides a `0' if both are used;
 .It "Field Width:"
 An optional digit string specifying a
 .Em field width ;
-if the output string has fewer characters than the field width it will
+if the output string has fewer bytes than the field width it will
 be blank-padded on the left (or right, if the left-adjustment indicator
 has been given) to make up the field width (note that a leading zero
 is a flag, but an embedded zero is part of a field width);
@@ -186,7 +185,7 @@ for
 .Cm e
 and
 .Cm f
-formats, or the maximum number of characters to be printed
+formats, or the maximum number of bytes to be printed
 from a string; if the digit string is missing, the precision is treated
 as zero;
 .It Format:
@@ -272,15 +271,15 @@ and
 .Ql nan ,
 respectively.
 .It Cm c
-The first character of
+The first byte of
 .Ar argument
 is printed.
 .It Cm s
-Characters from the string
+Bytes from the string
 .Ar argument
-are printed until the end is reached or until the number of characters
+are printed until the end is reached or until the number of bytes
 indicated by the precision specification is reached; however if the
-precision is 0 or missing, all characters in the string are printed.
+precision is 0 or missing, the string is printed entirely.
 .It Cm b
 As for
 .Cm s ,
@@ -347,6 +346,17 @@ to interpret the dash as a program argument.
 .Nm --
 must be used before 
 .Ar format .
+.Pp
+If the locale contains multibyte characters
+(such as UTF-8),
+the
+.Cm c
+format and
+.Cm b
+and
+.Cm s
+formats with a precision
+may not operate as expected.
 .Sh BUGS
 Since the floating point numbers are translated from
 .Tn ASCII
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);
 }