10 use B qw/class ppname svref_2object OPf_KIDS/;
14 Sub::Nary - Try to count how many elements a subroutine can return in list context.
31 my $sn = Sub::Nary->new();
32 my $r = $sn->nary(\&hlagh);
36 This module uses the L<B> framework to walk into subroutines and try to guess how many scalars are likely to be returned in list context. It's not always possible to give a definitive answer to this question at compile time, so the results are given in terms of "probability of return" (to be understood in a sense described below).
42 The usual constructor. Currently takes no argument.
44 =head2 C<nary $coderef>
46 Takes a code reference to a named or anonymous subroutine, and returns a hash reference whose keys are the possible numbers of returning scalars, and the corresponding values the "probability" to get them. A few special keys are also used :
52 C<'list'> is used to denote a possibly infinite number of returned arguments ;
56 C<'exit'> gives the probability for C<exit> to be called somewhere in the code.
60 The return value hence would look at
62 { 1 => 0.2, 2 => 0.4, 4 => 0.25, list => 0.1, exit => 0.05 }
64 that is, we should get C<1> scalar C<1> time over C<5> and so on. The sum of all values is C<1>. The returned result, and all the results obtained from intermediate subs, are cached into the object.
68 Flushes the L<Sub::Nary> object cache. Returns the object itself.
70 =head1 PROBABILITY OF RETURN
72 The probability is computed as such :
78 When branching, each branch is considered equally possible.
80 For example, the subroutine
90 is seen returning one or two arguments each with probability C<1/2>.
102 it is considered to return C<3> scalars with probability C<1/2>, C<2> with probability C<1/2 * 1/2 = 1/4> and C<1> (when the two tests fail, the last computed value is returned, which here is C<< $x > 0.9 >> evaluated in the scalar context of the test) with remaining probability C<1/4>.
106 The total probability law for a given returning point is the convolution product of the probabilities of its list elements.
111 return 1, simple(), 2
114 returns C<3> or C<4> arguments with probability C<1/2> ; and
117 return simple(), simple()
120 never returns C<1> argument but returns C<2> with probability C<1/2 * 1/2 = 1/4>, C<3> with probability C<1/2 * 1/2 + 1/2 * 1/2 = 1/2> and C<4> with probability C<1/4> too.
124 If a core function may return different numbers of scalars, each kind is considered equally possible.
126 For example, C<stat> returns C<13> elements on success and C<0> on error. The according probability will then be C<< { 0 => 0.5, 13 => 0.5 } >>.
130 The C<list> and C<exit> states are absorbing in regard of all the other ones.
132 This is just a pedantic way to say that C<list + fixed length = list>, C<exit + fixed length = exit>, but note also that C<exit + list = exit>.
136 return 1, simple(), @_
139 is considered as always returning an unbounded list.
141 Also, the convolution law does not behave the same when C<list> or C<exit> elements are involved : in the following example,
152 return oneorlist(), oneorlist()
155 C<composed> returns C<2> scalars with probability C<1/2 * 1/2 = 1/4> and a C<list> with probability C<3/4>.
163 XSLoader::load(__PACKAGE__, $VERSION);
167 croak 'First argument isn\'t a valid ' . __PACKAGE__ . ' object'
168 unless ref $_[0] and $_[0]->isa(__PACKAGE__);
173 $class = ref($class) || $class || __PACKAGE__;
174 bless { cache => { } }, $class;
180 $self->{cache} = { };
189 return ($self->enter(svref_2object($sub)))[1];
193 local $SIG{__DIE__} = \&Carp::confess;
195 $n eq 'null' ? substr(ppname($_[0]->targ), 3) : $n
199 my ($p, $n, $c) = @_;
200 return unless defined $p;
201 return { 0 => $c } unless $n;
203 my $z = delete $p->{0};
204 return { 'list' => $c } unless $z;
205 return { 0 => $c } if $z == 1;
206 return { 0 => $c * $z, list => $c * (1 - $z) };
208 my $r = combine map { { %$p } } 1 .. $n;
209 $r->{$_} *= $c for keys %$r;
215 $ops{$_} = 1 for scalops;
216 $ops{$_} = 0 for qw/stub nextstate iter unstack/;
217 $ops{$_} = 1 for qw/padsv/;
218 $ops{$_} = 'list' for qw/padav/;
219 $ops{$_} = 'list' for qw/padhv rv2hv/;
220 $ops{$_} = 'list' for qw/padany/;
221 $ops{$_} = 'list' for qw/match entereval readline/;
223 $ops{each} = { 0 => 0.5, 2 => 0.5 };
224 $ops{stat} = { 0 => 0.5, 13 => 0.5 };
226 $ops{caller} = sub { my @a = caller 0; scalar @a }->();
227 $ops{localtime} = do { my @a = localtime; scalar @a };
228 $ops{gmtime} = do { my @a = gmtime; scalar @a };
230 $ops{$_} = { 0 => 0.5, 10 => 0.5 } for map "gpw$_", qw/nam uid ent/;
231 $ops{$_} = { 0 => 0.5, 4 => 0.5 } for map "ggr$_", qw/nam gid ent/;
232 $ops{$_} = 'list' for qw/ghbyname ghbyaddr ghostent/;
233 $ops{$_} = { 0 => 0.5, 4 => 0.5 } for qw/gnbyname gnbyaddr gnetent/;
234 $ops{$_} = { 0 => 0.5, 3 => 0.5 } for qw/gpbyname gpbynumber gprotoent/;
235 $ops{$_} = { 0 => 0.5, 4 => 0.5 } for qw/gsbyname gsbyport gservent/;
237 # Stolen from B::Deparse
239 sub padval { $_[0]->{cv}->[0]->PADLIST->ARRAYelt(1)->ARRAYelt($_[1]) }
242 my ($self, $op) = @_;
243 if (class($op) eq 'PADOP') {
244 return $self->padval($op->padix)
245 } else { # class($op) eq "SVOP"
251 my ($self, $op) = @_;
253 # the constant could be in the pad (under useithreads)
254 $sv = $self->padval($op->targ) unless $$sv;
259 my ($self, $cv) = @_;
261 return undef, 'list' if class($cv) ne 'CV';
263 return undef, 'list' if null $op;
266 return undef, { %{$self->{cache}->{$tag}} } if exists $self->{cache}->{$tag};
268 # Anything can happen with recursion
269 for (@{$self->{cv}}) {
270 return undef, 'list' if $tag == tag($_->ROOT);
273 unshift @{$self->{cv}}, $cv;
274 my $r = add $self->inspect($op->first);
275 shift @{$self->{cv}};
277 $self->{cache}->{$tag} = { %$r };
285 my ($self, $op) = @_;
288 my $meth = $self->can('pp_' . $n);
289 return $self->$meth($op) if $meth;
292 if (exists $ops{$n}) {
294 $l = { %$l } if ref $l;
298 $meth = $self->can('OPc_' . $c);
300 my ($r, $lc) = $self->$meth($op);
301 $lc = $l if defined $l;
305 return undef, (defined $l) ? $l : 0;
310 sub OPc_UNOP { $_[0]->inspect($_[1]->first); }
315 my ($self, $op) = @_;
317 my ($r, $l1) = $self->inspect($op->first);
318 return $r, $l1 unless defined $l1;
320 my ($r2, $l2) = $self->inspect($op->last);
321 my $c = 1 - count $r;
322 $r = add $r, scale $c, $r2 if defined $r2;
324 my $l = scale +(1 - count $r), normalize combine $l1, $l2;
332 my ($self, $op) = @_;
336 return undef, 0 if null $op;
338 my ($r1, $l1) = $self->inspect($op);
339 return $r1, $l1 if defined $r1 and zero $l1;
343 my ($r2, $l2) = $self->inspect($op);
348 # If the logop has no else branch, it can also return the *scalar* result of
352 ($r3, $l3) = $self->inspect($op);
355 my $r = add $r1, scale $c / 2, add $r2, $r3;
356 my $l = scale $c / 2, add $l2, $l3;
359 return $self->OPc_LISTOP($op);
365 my ($self, $op) = @_;
368 return undef, 0 if null $op;
369 if (name($op) eq 'pushmark') {
371 return undef, 0 if null $op;
376 for (; not null $op; $op = $op->sibling) {
378 if ($n eq 'nextstate') {
382 if ($n eq 'lineseq') {
387 my ($rc, $lc) = $self->inspect($op);
389 $r = add $r, scale $c, $rc if defined $rc;
390 if (not defined $lc) {
394 push @l, scale $c, $lc;
397 my $l = scale +(1 - count $r), normalize combine @l;
402 sub pp_return { add($_[0]->OPc_LISTOP($_[1])), undef }
405 my ($self, $op) = @_;
407 $op = $op->first while $op->flags & OPf_KIDS;
408 # First must be a pushmark
410 # Next must be non null - at worse it's the rv2cv
414 for (; not null $op->sibling; $op = $op->sibling) {
415 my ($rc, $lc) = $self->inspect($op);
416 return $rc, $lc if defined $rc and not defined $lc;
417 $r = add $r, scale $c, $rc;
421 if (name($op) eq 'rv2cv') {
425 my $next = $op->sibling;
426 while (not null $next) {
428 $next = $next->sibling;
431 } while $op->flags & OPf_KIDS and ($n eq 'null' or $n eq 'leave');
432 return 'list', undef unless $n eq 'gv' or $n eq 'refgen';
433 local $self->{sub} = 1;
434 my ($rc, $lc) = $self->inspect($op);
435 return $r, scale $c, $lc;
438 return $r, { 'list' => $c };
443 my ($self, $op) = @_;
445 return $self->{sub} ? $self->enter($self->gv_or_padgv($op)->CV) : (undef, 1)
449 my ($self, $op) = @_;
451 return $self->{sub} ? $self->enter($self->const_sv($op)) : (undef, 1)
455 my ($self, $op) = @_;
458 if ($op->flags & OPf_KIDS) {
459 ($r, my $l) = $self->inspect($op->first);
460 return $r, $l if defined $r and zero $l;
461 $r->{exit} = 1 - count $r;
463 $r = { 'exit' => 1 };
470 my ($self, $op) = @_;
472 my ($r, undef) = $self->OPc_LISTOP($op);
474 my $c = 1 - count $r;
475 $r->{die} = $c if $c;
484 my ($self, $op) = @_;
487 while ($op->flags & OPf_KIDS) {
488 my $nop = $op->first;
490 if ($nn eq 'pushmark') {
491 $nop = $nop->sibling;
494 if ($n eq 'rv2cv' and $nn eq 'gv') {
495 return $self->enter($self->gv_or_padgv($nop)->CV);
501 return undef, 'list';
505 my ($self, $op) = @_;
507 return undef, 0 unless $op->isa('B::SVOP');
509 my $sv = $self->const_sv($op);
514 } elsif ($c eq 'HV') {
521 sub pp_aslice { $_[0]->inspect($_[1]->first->sibling) }
524 *pp_hslice = *pp_aslice{CODE};
526 sub pp_lslice { $_[0]->inspect($_[1]->first) }
529 my ($self, $op) = @_;
532 if (name($op) eq 'gv') {
533 return undef, { list => 1 };
540 my ($self, $op) = @_;
542 my $r = ($self->inspect($op->first))[0];
544 my $c = 1 - count $r;
545 return $r, $c ? { 1 => $c } : undef
551 my ($self, $op) = @_;
555 # Can't assign to return
556 my $l = ($self->inspect($op->sibling))[1];
557 return undef, $l if not exists $l->{list};
565 my ($self, $op) = @_;
567 my ($r, $l) = $self->OPc_LISTOP($op);
569 my $d = delete $r->{die};
570 return $r, $l if not defined $d;
572 my $z = delete $l->{0};
573 $l = { %$l, 0 => $z };
584 my ($self, $op) = @_;
589 if (name($op) eq 'enteriter') { # for loop ?
591 ($r1, $l1) = $self->inspect($op);
592 return $r1, $l1 if defined $r1 and zero $l1;
597 if (name($op->first) eq 'and') {
598 ($r2, $l2) = $self->inspect($op->first->first);
599 return $r2, $l2 if defined $r2 and zero $l2;
601 return { list => 1 }, undef if !$for and defined $r2;
602 my ($r3, $l3) = $self->inspect($op->first->first->sibling);
603 return { list => 1 }, undef if defined $r3 and defined $l3;
604 $r2 = add $r2, scale $c, $r3;
606 ($r2, $l2) = $self->inspect($op);
607 return { list => 1 }, undef if defined $r2 and defined $l2;
610 my $r = (defined $r1) ? add $r1, scale +(1 - count $r1), $r2
612 my $c = 1 - count $r;
613 return $r, $c ? { 0 => $c } : undef;
617 my ($self, $op) = @_;
620 return $self->inspect($op) if name($op) ne 'range';
623 my $begin = $op->first;
624 if (name($begin) eq 'const') {
625 my $end = $begin->sibling;
626 if (name($end) eq 'const') {
627 $begin = $self->const_sv($begin);
628 $end = $self->const_sv($end);
630 no warnings 'numeric';
631 $begin = int ${$begin->object_2svref};
632 $end = int ${$end->object_2svref};
634 return undef, $end - $begin + 1;
636 ($r, $l) = $self->inspect($end);
639 ($r, $l) = $self->inspect($begin);
642 my $c = 1 - count $r;
643 return $r, $c ? { 'list' => $c } : undef
647 my ($self, $op) = @_;
650 return $self->inspect($op) if name($op) ne 'grepstart';
651 $op = $op->first->sibling;
653 my ($r2, $l2) = $self->inspect($op->sibling);
654 return $r2, $l2 if defined $r2 and zero $l2;
655 my $c2 = count $l2; # First one to happen
657 my ($r1, $l1) = $self->inspect($op);
658 return (add $r2, scale $c2, $r1), undef if defined $r1 and zero $l1
662 $l2 = { $l2 => 1 } unless ref $l2;
665 add map { scale $l2->{$_}, cumulate $r1, $_, $c1 } keys %$l2;
666 my $c = 1 - count $r;
667 return $r, $c ? { ((zero $l2) ? 0 : 'list') => $c } : undef;
671 my ($self, $op) = @_;
674 return $self->inspect($op) if name($op) ne 'mapstart';
675 $op = $op->first->sibling;
677 my ($r2, $l2) = $self->inspect($op->sibling);
678 return $r2, $l2 if defined $r2 and zero $l2;
679 my $c2 = count $l2; # First one to happen
681 my ($r1, $l1) = $self->inspect($op);
682 return (add $r2, scale $c2, $r1), undef if defined $r1 and zero $l1
686 $l2 = { $l2 => 1 } unless ref $l2;
689 add map { scale $l2->{$_}, cumulate $r1, $_, $c1 } keys %$l2;
690 my $c = 1 - count $r;
691 my $l = scale $c, normalize add map { power $l1, $_, $l2->{$_} } keys %$l2;
697 An object-oriented module shouldn't export any function, and so does this one.
701 The algorithm may be pessimistic (things seen as C<list> while they are of fixed length) but not optimistic (the opposite, duh).
703 C<wantarray> isn't specialized when encountered in the optree.
709 L<Carp> (standard since perl 5), L<B> (since perl 5.005) and L<XSLoader> (since perl 5.006).
713 Vincent Pit, C<< <perl at profvince.com> >>, L<http://www.profvince.com>.
715 You can contact me by mail or on C<irc.perl.org> (vincent).
719 Please report any bugs or feature requests to C<bug-sub-nary at rt.cpan.org>, or through the web interface at L<http://rt.cpan.org/NoAuth/ReportBug.html?Queue=Sub-Nary>. I will be notified, and then you'll automatically be notified of progress on your bug as I make changes.
723 You can find documentation for this module with the perldoc command.
727 Tests code coverage report is available at L<http://www.profvince.com/perl/cover/Sub-Nary>.
729 =head1 ACKNOWLEDGEMENTS
731 Thanks to Sebastien Aperghis-Tramoni for helping to name this module.
733 =head1 COPYRIGHT & LICENSE
735 Copyright 2008 Vincent Pit, all rights reserved.
737 This program is free software; you can redistribute it and/or modify it under the same terms as Perl itself.
741 1; # End of Sub::Nary