Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <eea930bc948c6f70a75d10ddc1b53730d4496f0b.1681516116.git.gabravier@gmail.com>
Date: Sat, 15 Apr 2023 14:28:28 +0200
From: Gabriel Ravier <gabravier@...il.com>
To: musl@...ts.openwall.com
Cc: Gabriel Ravier <gabravier@...il.com>
Subject: [PATCH v2 1/1] vfprintf: support C2x %b and %B conversion specifiers

These specifiers allow for formatted input/output of binary integers,
and have been added to C2x with N2630. The uppercase B specifier is
not formally required by C2x, as only lowercase specifiers were
reserved by C, and thus an implementation could have been using
uppercase B for an extension of their own, but C2x still has a note
saying that it is recommended practice to implement it as the logical
counterpart to b.
---
 src/stdio/vfprintf.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/src/stdio/vfprintf.c b/src/stdio/vfprintf.c
index a712d80f..3d7e0aeb 100644
--- a/src/stdio/vfprintf.c
+++ b/src/stdio/vfprintf.c
@@ -49,7 +49,7 @@ enum {
 static const unsigned char states[]['z'-'A'+1] = {
 	{ /* 0: bare types */
 		S('d') = INT, S('i') = INT,
-		S('o') = UINT, S('u') = UINT, S('x') = UINT, S('X') = UINT,
+		S('o') = UINT, S('u') = UINT, S('x') = UINT, S('X') = UINT, S('b') = UINT, S('B') = UINT,
 		S('e') = DBL, S('f') = DBL, S('g') = DBL, S('a') = DBL,
 		S('E') = DBL, S('F') = DBL, S('G') = DBL, S('A') = DBL,
 		S('c') = CHAR, S('C') = INT,
@@ -59,7 +59,7 @@ static const unsigned char states[]['z'-'A'+1] = {
 		S('z') = ZTPRE, S('j') = JPRE, S('t') = ZTPRE,
 	}, { /* 1: l-prefixed */
 		S('d') = LONG, S('i') = LONG,
-		S('o') = ULONG, S('u') = ULONG, S('x') = ULONG, S('X') = ULONG,
+		S('o') = ULONG, S('u') = ULONG, S('x') = ULONG, S('X') = ULONG, S('b') = ULONG, S('B') = ULONG,
 		S('e') = DBL, S('f') = DBL, S('g') = DBL, S('a') = DBL,
 		S('E') = DBL, S('F') = DBL, S('G') = DBL, S('A') = DBL,
 		S('c') = INT, S('s') = PTR, S('n') = PTR,
@@ -68,17 +68,20 @@ static const unsigned char states[]['z'-'A'+1] = {
 		S('d') = LLONG, S('i') = LLONG,
 		S('o') = ULLONG, S('u') = ULLONG,
 		S('x') = ULLONG, S('X') = ULLONG,
+		S('b') = ULLONG, S('B') = ULLONG,
 		S('n') = PTR,
 	}, { /* 3: h-prefixed */
 		S('d') = SHORT, S('i') = SHORT,
 		S('o') = USHORT, S('u') = USHORT,
 		S('x') = USHORT, S('X') = USHORT,
+		S('b') = USHORT, S('B') = USHORT,
 		S('n') = PTR,
 		S('h') = HHPRE,
 	}, { /* 4: hh-prefixed */
 		S('d') = CHAR, S('i') = CHAR,
 		S('o') = UCHAR, S('u') = UCHAR,
 		S('x') = UCHAR, S('X') = UCHAR,
+		S('b') = UCHAR, S('B') = UCHAR,
 		S('n') = PTR,
 	}, { /* 5: L-prefixed */
 		S('e') = LDBL, S('f') = LDBL, S('g') = LDBL, S('a') = LDBL,
@@ -88,11 +91,13 @@ static const unsigned char states[]['z'-'A'+1] = {
 		S('d') = PDIFF, S('i') = PDIFF,
 		S('o') = SIZET, S('u') = SIZET,
 		S('x') = SIZET, S('X') = SIZET,
+		S('b') = SIZET, S('B') = SIZET,
 		S('n') = PTR,
 	}, { /* 7: j-prefixed */
 		S('d') = IMAX, S('i') = IMAX,
 		S('o') = UMAX, S('u') = UMAX,
 		S('x') = UMAX, S('X') = UMAX,
+		S('b') = UMAX, S('B') = UMAX,
 		S('n') = PTR,
 	}
 };
@@ -162,6 +167,12 @@ static char *fmt_o(uintmax_t x, char *s)
 	return s;
 }
 
+static char *fmt_b(uintmax_t x, char *s)
+{
+	for (; x; x>>=1) *--s = '0' + (x&1);
+	return s;
+}
+
 static char *fmt_u(uintmax_t x, char *s)
 {
 	unsigned long y;
@@ -437,7 +448,12 @@ static int printf_core(FILE *f, const char *fmt, va_list *ap, union arg *nl_arg,
 	unsigned st, ps;
 	int cnt=0, l=0;
 	size_t i;
-	char buf[sizeof(uintmax_t)*3+3+LDBL_MANT_DIG/4];
+	/* This buffer is used for integer conversions. As such, it needs
+	 * to be able to contain the full representation of a number in base 2,
+	 * 8, 10 or 16, with base 2 having the largest possible requirement of
+	 * as many characters as the amount of bits in the largest possible
+	 * integer type */
+	char buf[sizeof(uintmax_t)*CHAR_BIT];
 	const char *prefix;
 	int t, pl;
 	wchar_t wc[2], *ws;
@@ -534,7 +550,7 @@ static int printf_core(FILE *f, const char *fmt, va_list *ap, union arg *nl_arg,
 		if (ferror(f)) return -1;
 
 		z = buf + sizeof(buf);
-		prefix = "-+   0X0x";
+		prefix = "-+   0X0x0B0b";
 		pl = 0;
 		t = s[-1];
 
@@ -564,6 +580,10 @@ static int printf_core(FILE *f, const char *fmt, va_list *ap, union arg *nl_arg,
 			a = fmt_x(arg.i, z, t&32);
 			if (arg.i && (fl & ALT_FORM)) prefix+=(t>>4), pl=2;
 			if (0) {
+		case 'b': case 'B':
+			a = fmt_b(arg.i, z);
+			if (arg.i && (fl & ALT_FORM)) prefix+=9+((t=='b')<<1), pl=2;
+			} if (0) {
 		case 'o':
 			a = fmt_o(arg.i, z);
 			if ((fl&ALT_FORM) && p<z-a+1) p=z-a+1;
-- 
2.39.2

Powered by blists - more mailing lists

Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.