X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2Foverload.pm;h=21a4b671ffc1cefbc0a29b182acf7e6a55b2dca0;hb=36902e12d2b30e9370acddd3ddab927d842061cf;hp=cce5df7852dc1ae1c2232f4e04725e2d2d5fcfad;hpb=6b82e2f59e3c46c3c35c70f18f42e8c715a2cb5e;p=p5sagit%2Fp5-mst-13.2.git diff --git a/lib/overload.pm b/lib/overload.pm index cce5df7..21a4b67 100644 --- a/lib/overload.pm +++ b/lib/overload.pm @@ -1,5 +1,7 @@ package overload; +our $VERSION = '1.00'; + $overload::hint_bits = 0x20000; sub nil {} @@ -106,7 +108,7 @@ sub mycan { # Real can would leave stubs. } %constants = ( - 'integer' => 0x1000, + 'integer' => 0x1000, 'float' => 0x2000, 'binary' => 0x4000, 'q' => 0x8000, @@ -121,7 +123,7 @@ sub mycan { # Real can would leave stubs. binary => "& | ^", unary => "neg ! ~", mutators => '++ --', - func => "atan2 cos sin exp abs log sqrt", + func => "atan2 cos sin exp abs log sqrt int", conversion => 'bool "" 0+', iterators => '<>', dereferencing => '${} @{} %{} &{} *{}', @@ -132,25 +134,18 @@ sub constant { # Arguments: what, sub while (@_) { if (@_ == 1) { - if (warnings::enabled) { - require Carp; - Carp::carp ("Odd number of arguments for overload::constant"); - } + warnings::warnif ("Odd number of arguments for overload::constant"); last; } elsif (!exists $constants {$_ [0]}) { - if (warnings::enabled) { - require Carp; - Carp::carp ("`$_[0]' is not an overloadable type"); - } + warnings::warnif ("`$_[0]' is not an overloadable type"); } elsif (!ref $_ [1] || "$_[1]" !~ /CODE\(0x[\da-f]+\)$/) { # Can't use C above as code references can be # blessed, and C would return the package the ref is blessed into. if (warnings::enabled) { - require Carp; $_ [1] = "undef" unless defined $_ [1]; - Carp::carp ("`$_[1]' is not a code reference"); + warnings::warn ("`$_[1]' is not a code reference"); } } else { @@ -174,7 +169,7 @@ sub remove_constant { __END__ -=head1 NAME +=head1 NAME overload - Package for overloading perl operations @@ -182,7 +177,7 @@ overload - Package for overloading perl operations package SomeThing; - use overload + use overload '+' => \&myadd, '-' => \&mysub; # etc @@ -204,12 +199,12 @@ The compilation directive package Number; use overload - "+" => \&add, + "+" => \&add, "*=" => "muas"; declares function Number::add() for addition, and method muas() in the "class" C (or one of its base classes) -for the assignment form C<*=> of multiplication. +for the assignment form C<*=> of multiplication. Arguments of this directive come in (key, value) pairs. Legal values are values legal inside a C<&{ ... }> call, so the name of a @@ -304,20 +299,20 @@ if C<+=> is not overloaded. =back B Due to the presense of assignment versions of operations, -routines which may be called in assignment context may create -self-referential structures. Currently Perl will not free self-referential +routines which may be called in assignment context may create +self-referential structures. Currently Perl will not free self-referential structures until cycles are C broken. You may get problems when traversing your structures too. -Say, +Say, use overload '+' => sub { bless [ \$_[0], \$_[1] ] }; is asking for trouble, since for code C<$obj += $foo> the subroutine -is called as C<$obj = add($obj, $foo, undef)>, or C<$obj = [\$obj, +is called as C<$obj = add($obj, $foo, undef)>, or C<$obj = [\$obj, \$foo]>. If using such a subroutine is an important optimization, one can overload C<+=> explicitly by a non-"optimized" version, or switch -to non-optimized version if C (see +to non-optimized version if C (see L). Even if no I assignment-variants of operators are present in @@ -375,11 +370,16 @@ postfix form. =item * I - "atan2", "cos", "sin", "exp", "abs", "log", "sqrt", + "atan2", "cos", "sin", "exp", "abs", "log", "sqrt", "int" If C is unavailable, it can be autogenerated using methods for "E" or "E=E" combined with either unary minus or subtraction. +Note that traditionally the Perl function L rounds to 0, thus for +floating-point-like types one should follow the same semantic. If +C is unavailable, it can be autogenerated using the overloading of +C<0+>. + =item * I "bool", "\"\"", "0+", @@ -390,6 +390,11 @@ be used instead. C is used in the flow control operators return any arbitrary Perl value. If the corresponding operation for this value is overloaded too, that operation will be called again with this value. +As a special case if the overload returns the object itself then it will +be used directly. An overloaded conversion returning the object is +probably a bug, because you're likely to get something that looks like +C. + =item * I "<>" @@ -407,6 +412,12 @@ If not overloaded, the argument will be dereferenced I, thus should be of correct type. These functions should return a reference of correct type, or another object with overloaded dereferencing. +As a special case if the overload returns the object itself then it +will be used directly (provided it is the correct type). + +The dereference operators must be specified explicitly they will not be passed to +"nomethod". + =item * I "nomethod", "fallback", "=", @@ -489,11 +500,16 @@ the last one is used. Say, C<1-$a> can be equivalent to if the pair C<"nomethod" =E "nomethodMethod"> was specified in the C directive. +The C<"nomethod"> mechanism is I used for the dereference operators +( ${} @{} %{} &{} *{} ). + + If some operation cannot be resolved, and there is no function assigned to C<"nomethod">, then an exception will be raised via die()-- unless C<"fallback"> was specified as a key in C directive. -=head2 Fallback + +=head2 Fallback The key C<"fallback"> governs what to do if a method for a particular operation is not found. Three different cases are possible depending on @@ -517,7 +533,7 @@ present. =item * defined, but FALSE No autogeneration is tried. Perl tries to call -C<"nomethod"> value, and if this is missing, raises an exception. +C<"nomethod"> value, and if this is missing, raises an exception. =back @@ -535,7 +551,7 @@ This operation is called in the situations when a mutator is applied to a reference that shares its object with some other reference, such as - $a=$b; + $a=$b; ++$a; To make this change $a and not change $b, a copy of C<$$a> is made, @@ -546,7 +562,7 @@ done if C<++> is expressed via a method for C<'++'> or C<'+='> (or C). Note that if this operation is expressed via C<'+'> a nonmutator, i.e., as in - $a=$b; + $a=$b; $a=$a+1; then C<$a> does not reference a new copy of C<$$a>, since $$a does not @@ -560,15 +576,15 @@ string copy if the object is a plain scalar. =item B -The actually executed code for +The actually executed code for - $a=$b; + $a=$b; Something else which does not modify $a or $b.... ++$a; may be - $a=$b; + $a=$b; Something else which does not modify $a or $b.... $a = $a->clone(undef,""); $a->incr(undef,""); @@ -595,7 +611,7 @@ substitutions are possible for the following operations: C<$a+=$b> can use the method for C<"+"> if the method for C<"+="> is not defined. -=item I +=item I String, numeric, and boolean conversion are calculated in terms of one another if not all of them are defined. @@ -622,7 +638,7 @@ string or numerical conversion. can be expressed in terms of string conversion. -=item I +=item I can be expressed in terms of its "spaceship" counterpart: either C=E> or C: @@ -730,20 +746,20 @@ to overload constant pieces of regular expressions. The corresponding values are references to functions which take three arguments: the first one is the I string form of the constant, the second one -is how Perl interprets this constant, the third one is how the constant is used. +is how Perl interprets this constant, the third one is how the constant is used. Note that the initial string form does not -contain string delimiters, and has backslashes in backslash-delimiter +contain string delimiters, and has backslashes in backslash-delimiter combinations stripped (thus the value of delimiter is not relevant for -processing of this string). The return value of this function is how this +processing of this string). The return value of this function is how this constant is going to be interpreted by Perl. The third argument is undefined unless for overloaded C- and C- constants, it is C in single-quote context (comes from strings, regular expressions, and single-quote HERE -documents), it is C for arguments of C/C operators, +documents), it is C for arguments of C/C operators, it is C for right-hand side of C-operator, and it is C otherwise. Since an expression C<"ab$cd,,"> is just a shortcut for C<'ab' . $cd . ',,'>, it is expected that overloaded constant strings are equipped with reasonable -overloaded catenation operator, otherwise absurd results will result. +overloaded catenation operator, otherwise absurd results will result. Similarly, negative numbers are considered as negations of positive constants. Note that it is probably meaningless to call the functions overload::constant() @@ -757,7 +773,7 @@ From these methods they may be called as overload::constant integer => sub {Math::BigInt->new(shift)}; } -B Currently overloaded-ness of constants does not propagate +B Currently overloaded-ness of constants does not propagate into C. =head1 IMPLEMENTATION @@ -799,7 +815,7 @@ packages acquire a magic during the next Cing into the package. This magic is three-words-long for packages without overloading, and carries the cache table if the package is overloaded. -Copying (C<$a=$b>) is shallow; however, a one-level-deep copying is +Copying (C<$a=$b>) is shallow; however, a one-level-deep copying is carried out before any operation that can imply an assignment to the object $a (or $b) refers to, like C<$a++>. You can override this behavior by defining your own copy constructor (see L<"Copy Constructor">). @@ -810,8 +826,8 @@ to be changed are constant (but this is not enforced). =head1 Metaphor clash One may wonder why the semantic of overloaded C<=> is so counter intuitive. -If it I counter intuitive to you, you are subject to a metaphor -clash. +If it I counter intuitive to you, you are subject to a metaphor +clash. Here is a Perl object metaphor: @@ -830,10 +846,10 @@ that $a and $b are separate entities. The difference is not relevant in the absence of mutators. After a Perl-way assignment an operation which mutates the data referenced by $a -would change the data referenced by $b too. Effectively, after +would change the data referenced by $b too. Effectively, after C<$a = $b> values of $a and $b become I. -On the other hand, anyone who has used algebraic notation knows the +On the other hand, anyone who has used algebraic notation knows the expressive power of the arithmetic metaphor. Overloading works hard to enable this metaphor while preserving the Perlian way as far as possible. Since it is not not possible to freely mix two contradicting @@ -842,7 +858,7 @@ far as all the mutators are called via overloaded access only>. The way it is done is described in L. If some mutator methods are directly applied to the overloaded values, -one may need to I other values which references the +one may need to I other values which references the same value: $a = new Data 23; @@ -866,7 +882,7 @@ However, it would not make preserve "objectness" of $a. But Perl I a way to make assignments to an object do whatever you want. It is just not the overload, but tie()ing interface (see L). Adding a FETCH() method -which returns the object itself, and STORE() method which changes the +which returns the object itself, and STORE() method which changes the value of the object, one can reproduce the arithmetic metaphor in its completeness, at least for variables which were tie()d from the start. @@ -910,8 +926,8 @@ allowing index 0 to be treated as a normal element. package two_refs; use overload '%{}' => \&gethash, '@{}' => sub { $ {shift()} }; - sub new { - my $p = shift; + sub new { + my $p = shift; bless \ [@_], $p; } sub gethash { @@ -925,13 +941,13 @@ allowing index 0 to be treated as a normal element. my %fields; my $i = 0; $fields{$_} = $i++ foreach qw{zero one two three}; - sub STORE { + sub STORE { my $self = ${shift()}; my $key = $fields{shift()}; defined $key or die "Out of band access"; $$self->[$key] = shift; } - sub FETCH { + sub FETCH { my $self = ${shift()}; my $key = $fields{shift()}; defined $key or die "Out of band access"; @@ -958,26 +974,26 @@ would would lead to a memory leak. Both these problems can be cured. Say, if we want to overload hash dereference on a reference to an object which is I as a hash itself, the only problem one has to circumvent is how to access -this I hash (as opposed to the I exhibited by +this I hash (as opposed to the I hash exhibited by the overloaded dereference operator). Here is one possible fetching routine: sub access_hash { my ($self, $key) = (shift, shift); my $class = ref $self; - bless $self, 'overload::dummy'; # Disable overloading of %{} + bless $self, 'overload::dummy'; # Disable overloading of %{} my $out = $self->{$key}; bless $self, $class; # Restore overloading $out; } -To move creation of the tied hash on each access, one may an extra +To remove creation of the tied hash on each access, one may an extra level of indirection which allows a non-circular structure of references: package two_refs1; use overload '%{}' => sub { ${shift()}->[1] }, '@{}' => sub { ${shift()}->[0] }; - sub new { - my $p = shift; + sub new { + my $p = shift; my $a = [@_]; my %h; tie %h, $p, $a; @@ -994,23 +1010,23 @@ level of indirection which allows a non-circular structure of references: my %fields; my $i = 0; $fields{$_} = $i++ foreach qw{zero one two three}; - sub STORE { + sub STORE { my $a = ${shift()}; my $key = $fields{shift()}; defined $key or die "Out of band access"; $a->[$key] = shift; } - sub FETCH { + sub FETCH { my $a = ${shift()}; my $key = $fields{shift()}; defined $key or die "Out of band access"; $a->[$key]; } -Now if $baz is overloaded like this, then C<$bar> is a reference to a +Now if $baz is overloaded like this, then C<$baz> is a reference to a reference to the intermediate array, which keeps a reference to an actual array, and the access hash. The tie()ing object for the access -hash is also a reference to a reference to the actual array, so +hash is a reference to a reference to the actual array, so =over @@ -1085,7 +1101,7 @@ Add a pretty-printer method to the module F: $a = $a->pretty if ref $a; $b = $b->pretty if ref $b; "[$meth $a $b]"; - } + } Now one can finish the script by @@ -1097,7 +1113,7 @@ inside such a method it is not necessary to pretty-print the I $a and $b of an object. In the above subroutine C<"[$meth $a $b]"> is a catenation of some strings and components $a and $b. If these components use overloading, the catenation operator -will look for an overloaded operator C<.>, if not present, it will +will look for an overloaded operator C<.>; if not present, it will look for an overloaded operator C<"">. Thus it is enough to use use overload nomethod => \&wrap, '""' => \&str; @@ -1106,7 +1122,7 @@ look for an overloaded operator C<"">. Thus it is enough to use $a = 'u' unless defined $a; $b = 'u' unless defined $b; "[$meth $a $b]"; - } + } Now one can change the last line of the script to @@ -1117,7 +1133,7 @@ which outputs side = [/ [- [sqrt [+ 1 [** [n 1 u] 2]] u] 1] [n 1 u]] and one can inspect the value in debugger using all the possible -methods. +methods. Something is is still amiss: consider the loop variable $cnt of the script. It was a number, not an object. We cannot make this value of @@ -1151,9 +1167,9 @@ slightly modified str()): } else { "[$meth $a]"; } - } - my %subr = ( n => sub {$_[0]}, - sqrt => sub {sqrt $_[0]}, + } + my %subr = ( n => sub {$_[0]}, + sqrt => sub {sqrt $_[0]}, '-' => sub {shift() - shift()}, '+' => sub {shift() + shift()}, '/' => sub {shift() / shift()}, @@ -1162,7 +1178,7 @@ slightly modified str()): ); sub num { my ($meth, $a, $b) = @{+shift}; - my $subr = $subr{$meth} + my $subr = $subr{$meth} or die "Do not know how to ($meth) in symbolic"; $a = $a->num if ref $a eq __PACKAGE__; $b = $b->num if ref $b eq __PACKAGE__; @@ -1200,7 +1216,7 @@ mutator methods (C<++>, C<-=> and so on), does not do deep copying (not required without mutators!), and implements only those arithmetic operations which are used in the example. -To implement most arithmetic operations is easy, one should just use +To implement most arithmetic operations is easy; one should just use the tables of operations, and change the code which fills %subr to my %subr = ( 'n' => sub {$_[0]} ); @@ -1222,7 +1238,7 @@ special to make C<+=> and friends work, except filling C<+=> entry of way to know that the implementation of C<'+='> does not mutate the argument, compare L). -To implement a copy constructor, add C<'=' => \&cpy> to C +To implement a copy constructor, add C<< '=' => \&cpy >> to C line, and code (this code assumes that mutators change things one level deep only, so recursive copying is not needed): @@ -1231,7 +1247,7 @@ deep only, so recursive copying is not needed): bless [@$self], ref $self; } -To make C<++> and C<--> work, we need to implement actual mutators, +To make C<++> and C<--> work, we need to implement actual mutators, either directly, or in C. We continue to do things inside C, thus add @@ -1240,7 +1256,7 @@ C, thus add return $obj; } -after the first line of wrap(). This is not a most effective +after the first line of wrap(). This is not a most effective implementation, one may consider sub inc { $_[0] = bless ['++', shift, 1]; } @@ -1263,8 +1279,8 @@ As a final remark, note that one can fill %subr by $subr{'++'} = $subr{'+'}; $subr{'--'} = $subr{'-'}; -This finishes implementation of a primitive symbolic calculator in -50 lines of Perl code. Since the numeric values of subexpressions +This finishes implementation of a primitive symbolic calculator in +50 lines of Perl code. Since the numeric values of subexpressions are not cached, the calculator is very slow. Here is the answer for the exercise: In the case of str(), we need no @@ -1290,9 +1306,9 @@ until the value is I. To see it in action, add a method - sub STORE { - my $obj = shift; - $#$obj = 1; + sub STORE { + my $obj = shift; + $#$obj = 1; @$obj->[0,1] = ('=', shift); } @@ -1361,7 +1377,7 @@ key (in fact a presence of this method shows that this package has overloading enabled, and it is what is used by the C function of module C). -The module might issues the following warnings: +The module might issue the following warnings: =over 4 @@ -1393,12 +1409,12 @@ C is present (possibly undefined). This may create interesting effects if some package is not overloaded, but inherits from two overloaded packages. -Relation between overloading and tie()ing is broken. Overloading is +Relation between overloading and tie()ing is broken. Overloading is triggered or not basing on the I class of tie()d value. -This happens because the presence of overloading is checked too early, +This happens because the presence of overloading is checked too early, before any tie()d access is attempted. If the FETCH()ed class of the -tie()d value does not change, a simple workaround is to access the value +tie()d value does not change, a simple workaround is to access the value immediately after tie()ing, so that after this call the I class coincides with the current one.