%o and %x can now format signed integers

Optionally treat integers as signed numbers with %o
and %x format specifiers, instead of treating them as
a machine-dependent two’s complement representation.
This option is more machine-independent, allows formats
like "#x%x" to be useful for reading later, and is
better-insulated for future changes involving bignums.
Setting the new variable ‘binary-as-unsigned’ to nil
enables the new behavior (Bug#32252).
This is a simplified version of the change proposed in:
https://lists.gnu.org/r/emacs-devel/2018-07/msg00763.html
I simplified that proposal by omitting bitwidth modifiers, as
I could not find an any example uses in the Emacs source code
that needed them and doing them correctly would have been
quite a bit more work for apparently little benefit.
* doc/lispref/strings.texi (Formatting Strings):
Document that %x and %o format negative integers in a
platform-dependent way.  Also, document how to format
numbers so that the same values can be read back in.
* etc/NEWS: Document the change.
* src/editfns.c (styled_format): Treat integers as signed
numbers even with %o and %x, if binary-as-unsigned is nil.
Support the + and space flags with %o and %x, since they’re
about signs.
(syms_of_editfns): New variable binary-as-unsigned.
* test/src/editfns-tests.el (read-large-integer):
Test that maximal integers can be read after printing
with all integer formats, if binary-as-unsigned is nil.

1 files changed, 38 insertions, 5 deletions

diff --git a/src/editfns.c b/src/editfns.c
index 1d6040da3f7..df257219e8f 100644
--- a/src/editfns.c
+++ b/src/editfns.c
@@ -4196,8 +4196,8 @@ contain either numbered or unnumbered %-sequences but not both, except
 that %% can be mixed with numbered %-sequences.
 
 The + flag character inserts a + before any nonnegative number, while a
-space inserts a space before any nonnegative number; these flags only
-affect %d, %e, %f, and %g sequences, and the + flag takes precedence.
+space inserts a space before any nonnegative number; these flags
+affect only numeric %-sequences, and the + flag takes precedence.
 The - and 0 flags affect the width specifier, as described below.
 
 The # flag means to use an alternate display form for %o, %x, %X, %e,
@@ -4736,10 +4736,22 @@ styled_format (ptrdiff_t nargs, Lisp_Object *args, bool message)
                 }
               else
                 {
-                  /* Don't sign-extend for octal or hex printing.  */
                   uprintmax_t x;
+                  bool negative;
                   if (INTEGERP (arg))
-                    x = XUINT (arg);
+                    {
+                      if (binary_as_unsigned)
+                        {
+                          x = XUINT (arg);
+                          negative = false;
+                        }
+                      else
+                        {
+                          EMACS_INT i = XINT (arg);
+                          negative = i < 0;
+                          x = negative ? -i : i;
+                        }
+                    }
                   else
                     {
                       double d = XFLOAT_DATA (arg);
@@ -4747,8 +4759,13 @@ styled_format (ptrdiff_t nargs, Lisp_Object *args, bool message)
                       if (! (0 <= d && d < uprintmax + 1))
                         xsignal1 (Qoverflow_error, arg);
                       x = d;
+                      negative = false;
                     }
-                  sprintf_bytes = sprintf (sprintf_buf, convspec, prec, x);
+                  sprintf_buf[0] = negative ? '-' : plus_flag ? '+' : ' ';
+                  bool signedp = negative | plus_flag | space_flag;
+                  sprintf_bytes = sprintf (sprintf_buf + signedp,
+                                           convspec, prec, x);
+                  sprintf_bytes += signedp;
                 }
 
               /* Now the length of the formatted item is known, except it omits
@@ -5558,6 +5575,22 @@ functions if all the text being accessed has this property.  */);
   DEFVAR_LISP ("operating-system-release", Voperating_system_release,
                doc: /* The release of the operating system Emacs is running on.  */);
 
+  DEFVAR_BOOL ("binary-as-unsigned",
+               binary_as_unsigned,
+               doc: /* Non-nil means `format' %x and %o treat integers as unsigned.
+This has machine-dependent results.  Nil means to treat integers as
+signed, which is portable; for example, if N is a negative integer,
+(read (format "#x%x") N) returns N only when this variable is nil.
+
+This variable is experimental; email 32252@debbugs.gnu.org if you need
+it to be non-nil.  */);
+  /* For now, default to true if bignums exist, false in traditional Emacs.  */
+#ifdef lisp_h_FIXNUMP
+  binary_as_unsigned = true;
+#else
+  binary_as_unsigned = false;
+#endif
+
   defsubr (&Spropertize);
   defsubr (&Schar_equal);
   defsubr (&Sgoto_char);