[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <ab2c18fd4289930804af370f8dd79fdb0f9864c2.1724800256.git.gabravier@gmail.com>
Date: Wed, 28 Aug 2024 01:12:11 +0200
From: Gabriel Ravier <gabravier@...il.com>
To: musl@...ts.openwall.com
Cc: Gabriel Ravier <gabravier@...il.com>
Subject: [PATCH v3 1/1] vfprintf: support C23 b and B conversion specifiers
These specifiers allow for formatted output of binary integers, and
have been added to C23 through N2630. The uppoercase B specifier is
not made entirely mandatory by C23, as only lowercase specifiers are
reserved for the standard, and thus an implementation could have been
using uppercase B for an unrelated extension, but C23 still has a note
stating it is recommended practice to implement it as the uppercase
counterpart of the b specifier.
I have tested this on:
- glibc's tests for %b and %B
- The libc testsuite I'm developing over at https://github.com/GabrielRavier/yalibct
- musl's libc-test
- musl's libc-testsuite
And observed no regressions.
---
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 360d723a..ec51aa3c 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') = INT, S('C') = UINT,
@@ -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') = UINT, 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,
}
};
@@ -150,6 +155,12 @@ static const char xdigits[16] = {
"0123456789ABCDEF"
};
+static char *fmt_b(uintmax_t x, char *s)
+{
+ for (; x; x>>=1) *--s = '0' + (x&1);
+ return s;
+}
+
static char *fmt_x(uintmax_t x, char *s, int lower)
{
for (; x; x>>=4) *--s = xdigits[(x&15)]|lower;
@@ -431,7 +442,12 @@ 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];
+ /* This buffer is used for integer conversions. As such, it needs
+ * to be able to contain the full representation of a number (without a
+ * prefix/padding or null terminator) 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;
@@ -528,7 +544,7 @@ 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];
@@ -558,6 +574,10 @@ 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;
--
2.46.0
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.
