C2x scanf binary constant handling

C2x adds binary integer constants starting with 0b or 0B, and supports
those constants for the %i scanf format (in addition to the %b format,
which isn't yet implemented for scanf in glibc).  Implement that scanf
support for glibc.

As with the strtol support, this is incompatible with previous C
standard versions, in that such an input string starting with 0b or 0B
was previously required to be parsed as 0 (with the rest of the input
potentially matching subsequent parts of the scanf format string).
Thus this patch adds 12 new __isoc23_* functions per long double
format (12, 24 or 36 depending on how many long double formats the
glibc configuration supports), with appropriate header redirection
support (generally very closely following that for the __isoc99_*
scanf functions - note that __GLIBC_USE (DEPRECATED_SCANF) takes
precedence over __GLIBC_USE (C2X_STRTOL), so the case of GNU
extensions to C89 continues to get old-style GNU %a and does not get
this new feature).  The function names would remain as __isoc23_* even
if C2x ends up published in 2024 rather than 2023.

When scanf %b support is added, I think it will be appropriate for all
versions of scanf to follow C2x rules for inputs to the %b format
(given that there are no compatibility concerns for a new format).

Tested for x86_64 (full glibc testsuite).  The first version was also
tested for powerpc (32-bit) and powerpc64le (stdio-common/ and wcsmbs/
tests), and with build-many-glibcs.py.

1 files changed, 170 insertions, 0 deletions

diff --git a/sysdeps/ieee754/ldbl-opt/nldbl-compat.c b/sysdeps/ieee754/ldbl-opt/nldbl-compat.c
index c654ebe416..22112c54d4 100644
--- a/sysdeps/ieee754/ldbl-opt/nldbl-compat.c
+++ b/sysdeps/ieee754/ldbl-opt/nldbl-compat.c
@@ -45,6 +45,10 @@ libc_hidden_proto (__nldbl___isoc99_vsscanf)
 libc_hidden_proto (__nldbl___isoc99_vfscanf)
 libc_hidden_proto (__nldbl___isoc99_vswscanf)
 libc_hidden_proto (__nldbl___isoc99_vfwscanf)
+libc_hidden_proto (__nldbl___isoc23_vsscanf)
+libc_hidden_proto (__nldbl___isoc23_vfscanf)
+libc_hidden_proto (__nldbl___isoc23_vswscanf)
+libc_hidden_proto (__nldbl___isoc23_vfwscanf)
 
 /* Compatibility with IEEE double as long double.
    IEEE quad long double is used by default for most programs, so
@@ -992,6 +996,172 @@ __nldbl___isoc99_wscanf (const wchar_t *fmt, ...)
   return ret;
 }
 
+int
+attribute_compat_text_section
+__nldbl___isoc23_vfscanf (FILE *s, const char *fmt, va_list ap)
+{
+  return __vfscanf_internal (s, fmt, ap,
+			     SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			     | SCANF_ISOC23_BIN_CST);
+}
+libc_hidden_def (__nldbl___isoc23_vfscanf)
+
+int
+attribute_compat_text_section
+__nldbl___isoc23_sscanf (const char *s, const char *fmt, ...)
+{
+  _IO_strfile sf;
+  FILE *f = _IO_strfile_read (&sf, s);
+  va_list ap;
+  int ret;
+
+  va_start (ap, fmt);
+  ret = __vfscanf_internal (f, fmt, ap,
+			    SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			    | SCANF_ISOC23_BIN_CST);
+  va_end (ap);
+
+  return ret;
+}
+
+int
+attribute_compat_text_section
+__nldbl___isoc23_vsscanf (const char *s, const char *fmt, va_list ap)
+{
+  _IO_strfile sf;
+  FILE *f = _IO_strfile_read (&sf, s);
+
+  return __vfscanf_internal (f, fmt, ap,
+			     SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			     | SCANF_ISOC23_BIN_CST);
+}
+libc_hidden_def (__nldbl___isoc23_vsscanf)
+
+int
+attribute_compat_text_section
+__nldbl___isoc23_vscanf (const char *fmt, va_list ap)
+{
+  return __vfscanf_internal (stdin, fmt, ap,
+			     SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			     | SCANF_ISOC23_BIN_CST);
+}
+
+int
+attribute_compat_text_section
+__nldbl___isoc23_fscanf (FILE *s, const char *fmt, ...)
+{
+  va_list ap;
+  int ret;
+
+  va_start (ap, fmt);
+  ret = __vfscanf_internal (s, fmt, ap,
+			    SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			    | SCANF_ISOC23_BIN_CST);
+  va_end (ap);
+
+  return ret;
+}
+
+int
+attribute_compat_text_section
+__nldbl___isoc23_scanf (const char *fmt, ...)
+{
+  va_list ap;
+  int ret;
+
+  va_start (ap, fmt);
+  ret = __vfscanf_internal (stdin, fmt, ap,
+			    SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			    | SCANF_ISOC23_BIN_CST);
+  va_end (ap);
+
+  return ret;
+}
+
+int
+attribute_compat_text_section
+__nldbl___isoc23_vfwscanf (FILE *s, const wchar_t *fmt, va_list ap)
+{
+  return __vfwscanf_internal (s, fmt, ap,
+			      SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			      | SCANF_ISOC23_BIN_CST);
+}
+libc_hidden_def (__nldbl___isoc23_vfwscanf)
+
+int
+attribute_compat_text_section
+__nldbl___isoc23_swscanf (const wchar_t *s, const wchar_t *fmt, ...)
+{
+  _IO_strfile sf;
+  struct _IO_wide_data wd;
+  FILE *f = _IO_strfile_readw (&sf, &wd, s);
+  va_list ap;
+  int ret;
+
+  va_start (ap, fmt);
+  ret = __vfwscanf_internal (f, fmt, ap,
+			     SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			     | SCANF_ISOC23_BIN_CST);
+  va_end (ap);
+
+  return ret;
+}
+
+int
+attribute_compat_text_section
+__nldbl___isoc23_vswscanf (const wchar_t *s, const wchar_t *fmt, va_list ap)
+{
+  _IO_strfile sf;
+  struct _IO_wide_data wd;
+  FILE *f = _IO_strfile_readw (&sf, &wd, s);
+
+  return __vfwscanf_internal (f, fmt, ap,
+			      SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			      | SCANF_ISOC23_BIN_CST);
+}
+libc_hidden_def (__nldbl___isoc23_vswscanf)
+
+int
+attribute_compat_text_section
+__nldbl___isoc23_vwscanf (const wchar_t *fmt, va_list ap)
+{
+  return __vfwscanf_internal (stdin, fmt, ap,
+			      SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			      | SCANF_ISOC23_BIN_CST);
+}
+
+int
+attribute_compat_text_section
+__nldbl___isoc23_fwscanf (FILE *s, const wchar_t *fmt, ...)
+{
+  va_list ap;
+  int ret;
+
+  va_start (ap, fmt);
+  ret = __vfwscanf_internal (s, fmt, ap,
+			     SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			     | SCANF_ISOC23_BIN_CST);
+  va_end (ap);
+
+  return ret;
+}
+
+int
+attribute_compat_text_section
+__nldbl___isoc23_wscanf (const wchar_t *fmt, ...)
+{
+  va_list ap;
+  int ret;
+
+  va_start (ap, fmt);
+  ret = __vfwscanf_internal (stdin, fmt, ap,
+			     SCANF_LDBL_IS_DBL | SCANF_ISOC99_A
+			     | SCANF_ISOC23_BIN_CST);
+  va_end (ap);
+
+  return ret;
+}
+
 void
 __nldbl_argp_error (const struct argp_state *state, const char *fmt, ...)
 {