homepage

PEP 238 says:
"For complex numbers, // raises an exception, since
floor() of a complex number is not allowed."
But on 2.3 (and on CVS) complex floor division returns
divmod[0]
Is this a bug on complexobject.c or the PEP wasn't updated?
Regards,
-Hernan 

Logged In: YES 
user_id=112690
As suggested by Tim I'll upload here the patch and the test
for this bug.
The patch clears nb_true_divide entry and deletes the
complex_int_div function.

Logged In: YES 
user_id=6380
Hm. I believe that if divmod() returns something, // should
return the same thing (well, divmod()[0]). But what on earth
does divmod() do on two complex numbers??? Does it make
sense to have divmod() on complex at all? Assigned to Tim
for a ruling.

Logged In: YES 
user_id=31435
Heh. divmod(c1, c2)[0] for complexes returns
 floor((c1/c2).real)
according to the Reference Manual (5.6 Binary arithmetic 
operations), and it looks like the code implements that 
just so. The Library manual's "Builtin Functions" section 
only mentions ints, longs and floats, while the same 
manual's "2.2.4 Numeric Types" claims, in a footnote, 
that "Builtin Functions" told the full truth about divmod.
The primary lesson I take from this is that a .chm file is 
a truly wonderful way to search the docs <wink>.
I don't think divmod is useful for complexes, and would be 
happy to see it go away. But I guess that means taking the 
full-blown deprecation path.
I note that the original complexobject.c didn't implement 
divmod. The current divmod appears to derive from a patch 
contributed by Tim Hochberg, in rev 2.10 in 1996. You 
(Guido) added a question mark to the checkin comment, so I 
figure it never made much sense to you either.
I agree floor divsion and divmod(...)[0] should do the same 
thing, whatever that is.

Logged In: YES 
user_id=6380
OK, I'll add the deprecation warning.

Logged In: YES 
user_id=6380
Fred, can you fix the docs?

Logged In: YES 
user_id=6380
Note: complex % is also being deprecated.

Logged In: YES 
user_id=80475
Fred, here's a doc patch.
Okay to commit and close this bug?

Logged In: YES 
user_id=3066
The \deprecated markup should always be a separate paragraph
(or list item). Please revise the doc patch and re-submit
for review. (But thanks for working on this; the content is
good!)

Logged In: YES 
user_id=80475
Separated the \deprecated sections. Revised patch attached.

Logged In: YES 
user_id=3066
Thanks! Go ahead and check it in.

Logged In: YES 
user_id=80475
Committed as:
 libfuncs.tex 1.106
 libstdtypes.tex 1.94
 ref5.tex 1.62
Closing patch.