Commit | Line | Data |
4633a7c4 |
1 | package overload; |
2 | |
0e06870b |
3 | our $VERSION = '1.00'; |
4 | |
d5448623 |
5 | $overload::hint_bits = 0x20000; |
6 | |
a6006777 |
7 | sub nil {} |
8 | |
4633a7c4 |
9 | sub OVERLOAD { |
10 | $package = shift; |
11 | my %arg = @_; |
a6006777 |
12 | my ($sub, $fb); |
13 | $ {$package . "::OVERLOAD"}{dummy}++; # Register with magic by touching. |
14 | *{$package . "::()"} = \&nil; # Make it findable via fetchmethod. |
4633a7c4 |
15 | for (keys %arg) { |
a6006777 |
16 | if ($_ eq 'fallback') { |
17 | $fb = $arg{$_}; |
18 | } else { |
19 | $sub = $arg{$_}; |
20 | if (not ref $sub and $sub !~ /::/) { |
44a8e56a |
21 | $ {$package . "::(" . $_} = $sub; |
22 | $sub = \&nil; |
a6006777 |
23 | } |
24 | #print STDERR "Setting `$ {'package'}::\cO$_' to \\&`$sub'.\n"; |
25 | *{$package . "::(" . $_} = \&{ $sub }; |
26 | } |
4633a7c4 |
27 | } |
a6006777 |
28 | ${$package . "::()"} = $fb; # Make it findable too (fallback only). |
4633a7c4 |
29 | } |
30 | |
31 | sub import { |
32 | $package = (caller())[0]; |
33 | # *{$package . "::OVERLOAD"} = \&OVERLOAD; |
34 | shift; |
35 | $package->overload::OVERLOAD(@_); |
36 | } |
37 | |
38 | sub unimport { |
39 | $package = (caller())[0]; |
a6006777 |
40 | ${$package . "::OVERLOAD"}{dummy}++; # Upgrade the table |
4633a7c4 |
41 | shift; |
42 | for (@_) { |
a6006777 |
43 | if ($_ eq 'fallback') { |
44 | undef $ {$package . "::()"}; |
45 | } else { |
46 | delete $ {$package . "::"}{"(" . $_}; |
47 | } |
4633a7c4 |
48 | } |
49 | } |
50 | |
51 | sub Overloaded { |
a6006777 |
52 | my $package = shift; |
53 | $package = ref $package if ref $package; |
54 | $package->can('()'); |
4633a7c4 |
55 | } |
56 | |
44a8e56a |
57 | sub ov_method { |
58 | my $globref = shift; |
59 | return undef unless $globref; |
60 | my $sub = \&{*$globref}; |
61 | return $sub if $sub ne \&nil; |
62 | return shift->can($ {*$globref}); |
63 | } |
64 | |
4633a7c4 |
65 | sub OverloadedStringify { |
a6006777 |
66 | my $package = shift; |
67 | $package = ref $package if ref $package; |
44a8e56a |
68 | #$package->can('(""') |
ee239bfe |
69 | ov_method mycan($package, '(""'), $package |
70 | or ov_method mycan($package, '(0+'), $package |
71 | or ov_method mycan($package, '(bool'), $package |
72 | or ov_method mycan($package, '(nomethod'), $package; |
4633a7c4 |
73 | } |
74 | |
75 | sub Method { |
a6006777 |
76 | my $package = shift; |
77 | $package = ref $package if ref $package; |
44a8e56a |
78 | #my $meth = $package->can('(' . shift); |
79 | ov_method mycan($package, '(' . shift), $package; |
80 | #return $meth if $meth ne \&nil; |
81 | #return $ {*{$meth}}; |
4633a7c4 |
82 | } |
83 | |
84 | sub AddrRef { |
a6006777 |
85 | my $package = ref $_[0]; |
86 | return "$_[0]" unless $package; |
87 | bless $_[0], overload::Fake; # Non-overloaded package |
4633a7c4 |
88 | my $str = "$_[0]"; |
89 | bless $_[0], $package; # Back |
a6006777 |
90 | $package . substr $str, index $str, '='; |
4633a7c4 |
91 | } |
92 | |
93 | sub StrVal { |
f6b3007c |
94 | (OverloadedStringify($_[0]) or ref($_[0]) eq 'Regexp') ? |
a6006777 |
95 | (AddrRef(shift)) : |
4633a7c4 |
96 | "$_[0]"; |
97 | } |
98 | |
44a8e56a |
99 | sub mycan { # Real can would leave stubs. |
100 | my ($package, $meth) = @_; |
101 | return \*{$package . "::$meth"} if defined &{$package . "::$meth"}; |
102 | my $p; |
103 | foreach $p (@{$package . "::ISA"}) { |
104 | my $out = mycan($p, $meth); |
105 | return $out if $out; |
106 | } |
107 | return undef; |
108 | } |
109 | |
b3ac6de7 |
110 | %constants = ( |
22d4bb9c |
111 | 'integer' => 0x1000, |
b3ac6de7 |
112 | 'float' => 0x2000, |
113 | 'binary' => 0x4000, |
114 | 'q' => 0x8000, |
115 | 'qr' => 0x10000, |
116 | ); |
117 | |
ee239bfe |
118 | %ops = ( with_assign => "+ - * / % ** << >> x .", |
119 | assign => "+= -= *= /= %= **= <<= >>= x= .=", |
2877bd81 |
120 | num_comparison => "< <= > >= == !=", |
ee239bfe |
121 | '3way_comparison'=> "<=> cmp", |
2877bd81 |
122 | str_comparison => "lt le gt ge eq ne", |
ee239bfe |
123 | binary => "& | ^", |
124 | unary => "neg ! ~", |
125 | mutators => '++ --', |
126 | func => "atan2 cos sin exp abs log sqrt", |
127 | conversion => 'bool "" 0+', |
f5284f61 |
128 | iterators => '<>', |
129 | dereferencing => '${} @{} %{} &{} *{}', |
ee239bfe |
130 | special => 'nomethod fallback ='); |
131 | |
22d4bb9c |
132 | use warnings::register; |
b3ac6de7 |
133 | sub constant { |
134 | # Arguments: what, sub |
135 | while (@_) { |
22d4bb9c |
136 | if (@_ == 1) { |
137 | warnings::warnif ("Odd number of arguments for overload::constant"); |
138 | last; |
139 | } |
140 | elsif (!exists $constants {$_ [0]}) { |
141 | warnings::warnif ("`$_[0]' is not an overloadable type"); |
142 | } |
143 | elsif (!ref $_ [1] || "$_[1]" !~ /CODE\(0x[\da-f]+\)$/) { |
144 | # Can't use C<ref $_[1] eq "CODE"> above as code references can be |
145 | # blessed, and C<ref> would return the package the ref is blessed into. |
146 | if (warnings::enabled) { |
147 | $_ [1] = "undef" unless defined $_ [1]; |
148 | warnings::warn ("`$_[1]' is not a code reference"); |
149 | } |
150 | } |
151 | else { |
152 | $^H{$_[0]} = $_[1]; |
153 | $^H |= $constants{$_[0]} | $overload::hint_bits; |
154 | } |
b3ac6de7 |
155 | shift, shift; |
156 | } |
157 | } |
158 | |
159 | sub remove_constant { |
160 | # Arguments: what, sub |
161 | while (@_) { |
162 | delete $^H{$_[0]}; |
163 | $^H &= ~ $constants{$_[0]}; |
164 | shift, shift; |
165 | } |
166 | } |
167 | |
4633a7c4 |
168 | 1; |
169 | |
170 | __END__ |
171 | |
22d4bb9c |
172 | =head1 NAME |
4633a7c4 |
173 | |
cb1a09d0 |
174 | overload - Package for overloading perl operations |
4633a7c4 |
175 | |
176 | =head1 SYNOPSIS |
177 | |
178 | package SomeThing; |
179 | |
22d4bb9c |
180 | use overload |
4633a7c4 |
181 | '+' => \&myadd, |
182 | '-' => \&mysub; |
183 | # etc |
184 | ... |
185 | |
186 | package main; |
187 | $a = new SomeThing 57; |
188 | $b=5+$a; |
189 | ... |
190 | if (overload::Overloaded $b) {...} |
191 | ... |
192 | $strval = overload::StrVal $b; |
193 | |
4633a7c4 |
194 | =head1 DESCRIPTION |
195 | |
196 | =head2 Declaration of overloaded functions |
197 | |
198 | The compilation directive |
199 | |
200 | package Number; |
201 | use overload |
22d4bb9c |
202 | "+" => \&add, |
4633a7c4 |
203 | "*=" => "muas"; |
204 | |
205 | declares function Number::add() for addition, and method muas() in |
206 | the "class" C<Number> (or one of its base classes) |
22d4bb9c |
207 | for the assignment form C<*=> of multiplication. |
4633a7c4 |
208 | |
209 | Arguments of this directive come in (key, value) pairs. Legal values |
e7ea3e70 |
210 | are values legal inside a C<&{ ... }> call, so the name of a |
211 | subroutine, a reference to a subroutine, or an anonymous subroutine |
212 | will all work. Note that values specified as strings are |
213 | interpreted as methods, not subroutines. Legal keys are listed below. |
4633a7c4 |
214 | |
215 | The subroutine C<add> will be called to execute C<$a+$b> if $a |
216 | is a reference to an object blessed into the package C<Number>, or if $a is |
217 | not an object from a package with defined mathemagic addition, but $b is a |
218 | reference to a C<Number>. It can also be called in other situations, like |
219 | C<$a+=7>, or C<$a++>. See L<MAGIC AUTOGENERATION>. (Mathemagical |
220 | methods refer to methods triggered by an overloaded mathematical |
221 | operator.) |
222 | |
774d564b |
223 | Since overloading respects inheritance via the @ISA hierarchy, the |
224 | above declaration would also trigger overloading of C<+> and C<*=> in |
225 | all the packages which inherit from C<Number>. |
e7ea3e70 |
226 | |
4633a7c4 |
227 | =head2 Calling Conventions for Binary Operations |
228 | |
229 | The functions specified in the C<use overload ...> directive are called |
230 | with three (in one particular case with four, see L<Last Resort>) |
231 | arguments. If the corresponding operation is binary, then the first |
232 | two arguments are the two arguments of the operation. However, due to |
233 | general object calling conventions, the first argument should always be |
234 | an object in the package, so in the situation of C<7+$a>, the |
235 | order of the arguments is interchanged. It probably does not matter |
236 | when implementing the addition method, but whether the arguments |
237 | are reversed is vital to the subtraction method. The method can |
238 | query this information by examining the third argument, which can take |
239 | three different values: |
240 | |
241 | =over 7 |
242 | |
243 | =item FALSE |
244 | |
245 | the order of arguments is as in the current operation. |
246 | |
247 | =item TRUE |
248 | |
249 | the arguments are reversed. |
250 | |
251 | =item C<undef> |
252 | |
253 | the current operation is an assignment variant (as in |
254 | C<$a+=7>), but the usual function is called instead. This additional |
ee239bfe |
255 | information can be used to generate some optimizations. Compare |
256 | L<Calling Conventions for Mutators>. |
4633a7c4 |
257 | |
258 | =back |
259 | |
260 | =head2 Calling Conventions for Unary Operations |
261 | |
262 | Unary operation are considered binary operations with the second |
263 | argument being C<undef>. Thus the functions that overloads C<{"++"}> |
264 | is called with arguments C<($a,undef,'')> when $a++ is executed. |
265 | |
ee239bfe |
266 | =head2 Calling Conventions for Mutators |
267 | |
268 | Two types of mutators have different calling conventions: |
269 | |
270 | =over |
271 | |
272 | =item C<++> and C<--> |
273 | |
274 | The routines which implement these operators are expected to actually |
275 | I<mutate> their arguments. So, assuming that $obj is a reference to a |
276 | number, |
277 | |
278 | sub incr { my $n = $ {$_[0]}; ++$n; $_[0] = bless \$n} |
279 | |
280 | is an appropriate implementation of overloaded C<++>. Note that |
281 | |
282 | sub incr { ++$ {$_[0]} ; shift } |
283 | |
284 | is OK if used with preincrement and with postincrement. (In the case |
285 | of postincrement a copying will be performed, see L<Copy Constructor>.) |
286 | |
287 | =item C<x=> and other assignment versions |
288 | |
289 | There is nothing special about these methods. They may change the |
290 | value of their arguments, and may leave it as is. The result is going |
291 | to be assigned to the value in the left-hand-side if different from |
292 | this value. |
293 | |
f610777f |
294 | This allows for the same method to be used as overloaded C<+=> and |
ee239bfe |
295 | C<+>. Note that this is I<allowed>, but not recommended, since by the |
296 | semantic of L<"Fallback"> Perl will call the method for C<+> anyway, |
297 | if C<+=> is not overloaded. |
298 | |
299 | =back |
300 | |
301 | B<Warning.> Due to the presense of assignment versions of operations, |
22d4bb9c |
302 | routines which may be called in assignment context may create |
303 | self-referential structures. Currently Perl will not free self-referential |
ee239bfe |
304 | structures until cycles are C<explicitly> broken. You may get problems |
305 | when traversing your structures too. |
306 | |
22d4bb9c |
307 | Say, |
ee239bfe |
308 | |
309 | use overload '+' => sub { bless [ \$_[0], \$_[1] ] }; |
310 | |
311 | is asking for trouble, since for code C<$obj += $foo> the subroutine |
22d4bb9c |
312 | is called as C<$obj = add($obj, $foo, undef)>, or C<$obj = [\$obj, |
ee239bfe |
313 | \$foo]>. If using such a subroutine is an important optimization, one |
314 | can overload C<+=> explicitly by a non-"optimized" version, or switch |
22d4bb9c |
315 | to non-optimized version if C<not defined $_[2]> (see |
ee239bfe |
316 | L<Calling Conventions for Binary Operations>). |
317 | |
318 | Even if no I<explicit> assignment-variants of operators are present in |
319 | the script, they may be generated by the optimizer. Say, C<",$obj,"> or |
320 | C<',' . $obj . ','> may be both optimized to |
321 | |
322 | my $tmp = ',' . $obj; $tmp .= ','; |
323 | |
4633a7c4 |
324 | =head2 Overloadable Operations |
325 | |
ee239bfe |
326 | The following symbols can be specified in C<use overload> directive: |
4633a7c4 |
327 | |
328 | =over 5 |
329 | |
330 | =item * I<Arithmetic operations> |
331 | |
332 | "+", "+=", "-", "-=", "*", "*=", "/", "/=", "%", "%=", |
333 | "**", "**=", "<<", "<<=", ">>", ">>=", "x", "x=", ".", ".=", |
334 | |
335 | For these operations a substituted non-assignment variant can be called if |
336 | the assignment variant is not available. Methods for operations "C<+>", |
337 | "C<->", "C<+=>", and "C<-=>" can be called to automatically generate |
338 | increment and decrement methods. The operation "C<->" can be used to |
339 | autogenerate missing methods for unary minus or C<abs>. |
340 | |
ee239bfe |
341 | See L<"MAGIC AUTOGENERATION">, L<"Calling Conventions for Mutators"> and |
342 | L<"Calling Conventions for Binary Operations">) for details of these |
343 | substitutions. |
344 | |
4633a7c4 |
345 | =item * I<Comparison operations> |
346 | |
347 | "<", "<=", ">", ">=", "==", "!=", "<=>", |
348 | "lt", "le", "gt", "ge", "eq", "ne", "cmp", |
349 | |
350 | If the corresponding "spaceship" variant is available, it can be |
351 | used to substitute for the missing operation. During C<sort>ing |
352 | arrays, C<cmp> is used to compare values subject to C<use overload>. |
353 | |
354 | =item * I<Bit operations> |
355 | |
356 | "&", "^", "|", "neg", "!", "~", |
357 | |
358 | "C<neg>" stands for unary minus. If the method for C<neg> is not |
3bc6ec80 |
359 | specified, it can be autogenerated using the method for |
360 | subtraction. If the method for "C<!>" is not specified, it can be |
361 | autogenerated using the methods for "C<bool>", or "C<\"\">", or "C<0+>". |
4633a7c4 |
362 | |
363 | =item * I<Increment and decrement> |
364 | |
365 | "++", "--", |
366 | |
367 | If undefined, addition and subtraction methods can be |
368 | used instead. These operations are called both in prefix and |
369 | postfix form. |
370 | |
371 | =item * I<Transcendental functions> |
372 | |
373 | "atan2", "cos", "sin", "exp", "abs", "log", "sqrt", |
374 | |
375 | If C<abs> is unavailable, it can be autogenerated using methods |
1fef88e7 |
376 | for "E<lt>" or "E<lt>=E<gt>" combined with either unary minus or subtraction. |
4633a7c4 |
377 | |
378 | =item * I<Boolean, string and numeric conversion> |
379 | |
380 | "bool", "\"\"", "0+", |
381 | |
f5284f61 |
382 | If one or two of these operations are not overloaded, the remaining ones can |
4633a7c4 |
383 | be used instead. C<bool> is used in the flow control operators |
384 | (like C<while>) and for the ternary "C<?:>" operation. These functions can |
385 | return any arbitrary Perl value. If the corresponding operation for this value |
386 | is overloaded too, that operation will be called again with this value. |
387 | |
22d4bb9c |
388 | As a special case if the overload returns the object itself then it will |
389 | be used directly. An overloaded conversion returning the object is |
390 | probably a bug, because you're likely to get something that looks like |
391 | C<YourPackage=HASH(0x8172b34)>. |
392 | |
f5284f61 |
393 | =item * I<Iteration> |
394 | |
395 | "<>" |
396 | |
397 | If not overloaded, the argument will be converted to a filehandle or |
398 | glob (which may require a stringification). The same overloading |
399 | happens both for the I<read-filehandle> syntax C<E<lt>$varE<gt>> and |
400 | I<globbing> syntax C<E<lt>${var}E<gt>>. |
401 | |
402 | =item * I<Dereferencing> |
403 | |
404 | '${}', '@{}', '%{}', '&{}', '*{}'. |
405 | |
406 | If not overloaded, the argument will be dereferenced I<as is>, thus |
407 | should be of correct type. These functions should return a reference |
408 | of correct type, or another object with overloaded dereferencing. |
409 | |
22d4bb9c |
410 | As a special case if the overload returns the object itself then it |
411 | will be used directly (provided it is the correct type). |
412 | |
413 | The dereference operators must be specified explicitly they will not be passed to |
414 | "nomethod". |
415 | |
4633a7c4 |
416 | =item * I<Special> |
417 | |
418 | "nomethod", "fallback", "=", |
419 | |
420 | see L<SPECIAL SYMBOLS FOR C<use overload>>. |
421 | |
422 | =back |
423 | |
ee239bfe |
424 | See L<"Fallback"> for an explanation of when a missing method can be |
425 | autogenerated. |
426 | |
427 | A computer-readable form of the above table is available in the hash |
428 | %overload::ops, with values being space-separated lists of names: |
429 | |
430 | with_assign => '+ - * / % ** << >> x .', |
431 | assign => '+= -= *= /= %= **= <<= >>= x= .=', |
2877bd81 |
432 | num_comparison => '< <= > >= == !=', |
ee239bfe |
433 | '3way_comparison'=> '<=> cmp', |
2877bd81 |
434 | str_comparison => 'lt le gt ge eq ne', |
ee239bfe |
435 | binary => '& | ^', |
436 | unary => 'neg ! ~', |
437 | mutators => '++ --', |
438 | func => 'atan2 cos sin exp abs log sqrt', |
439 | conversion => 'bool "" 0+', |
f5284f61 |
440 | iterators => '<>', |
441 | dereferencing => '${} @{} %{} &{} *{}', |
ee239bfe |
442 | special => 'nomethod fallback =' |
4633a7c4 |
443 | |
e7ea3e70 |
444 | =head2 Inheritance and overloading |
445 | |
774d564b |
446 | Inheritance interacts with overloading in two ways. |
e7ea3e70 |
447 | |
448 | =over |
449 | |
450 | =item Strings as values of C<use overload> directive |
451 | |
774d564b |
452 | If C<value> in |
e7ea3e70 |
453 | |
454 | use overload key => value; |
455 | |
774d564b |
456 | is a string, it is interpreted as a method name. |
e7ea3e70 |
457 | |
458 | =item Overloading of an operation is inherited by derived classes |
459 | |
774d564b |
460 | Any class derived from an overloaded class is also overloaded. The |
461 | set of overloaded methods is the union of overloaded methods of all |
462 | the ancestors. If some method is overloaded in several ancestor, then |
e7ea3e70 |
463 | which description will be used is decided by the usual inheritance |
774d564b |
464 | rules: |
e7ea3e70 |
465 | |
774d564b |
466 | If C<A> inherits from C<B> and C<C> (in this order), C<B> overloads |
467 | C<+> with C<\&D::plus_sub>, and C<C> overloads C<+> by C<"plus_meth">, |
468 | then the subroutine C<D::plus_sub> will be called to implement |
469 | operation C<+> for an object in package C<A>. |
e7ea3e70 |
470 | |
471 | =back |
472 | |
774d564b |
473 | Note that since the value of the C<fallback> key is not a subroutine, |
474 | its inheritance is not governed by the above rules. In the current |
475 | implementation, the value of C<fallback> in the first overloaded |
476 | ancestor is used, but this is accidental and subject to change. |
e7ea3e70 |
477 | |
4633a7c4 |
478 | =head1 SPECIAL SYMBOLS FOR C<use overload> |
479 | |
480 | Three keys are recognized by Perl that are not covered by the above |
481 | description. |
482 | |
774d564b |
483 | =head2 Last Resort |
4633a7c4 |
484 | |
485 | C<"nomethod"> should be followed by a reference to a function of four |
486 | parameters. If defined, it is called when the overloading mechanism |
487 | cannot find a method for some operation. The first three arguments of |
488 | this function coincide with the arguments for the corresponding method if |
489 | it were found, the fourth argument is the symbol |
490 | corresponding to the missing method. If several methods are tried, |
491 | the last one is used. Say, C<1-$a> can be equivalent to |
492 | |
493 | &nomethodMethod($a,1,1,"-") |
494 | |
495 | if the pair C<"nomethod" =E<gt> "nomethodMethod"> was specified in the |
496 | C<use overload> directive. |
497 | |
22d4bb9c |
498 | The C<"nomethod"> mechanism is I<not> used for the dereference operators |
499 | ( ${} @{} %{} &{} *{} ). |
500 | |
501 | |
4633a7c4 |
502 | If some operation cannot be resolved, and there is no function |
503 | assigned to C<"nomethod">, then an exception will be raised via die()-- |
504 | unless C<"fallback"> was specified as a key in C<use overload> directive. |
505 | |
22d4bb9c |
506 | |
507 | =head2 Fallback |
4633a7c4 |
508 | |
509 | The key C<"fallback"> governs what to do if a method for a particular |
510 | operation is not found. Three different cases are possible depending on |
511 | the value of C<"fallback">: |
512 | |
513 | =over 16 |
514 | |
515 | =item * C<undef> |
516 | |
517 | Perl tries to use a |
518 | substituted method (see L<MAGIC AUTOGENERATION>). If this fails, it |
519 | then tries to calls C<"nomethod"> value; if missing, an exception |
520 | will be raised. |
521 | |
522 | =item * TRUE |
523 | |
524 | The same as for the C<undef> value, but no exception is raised. Instead, |
525 | it silently reverts to what it would have done were there no C<use overload> |
526 | present. |
527 | |
528 | =item * defined, but FALSE |
529 | |
530 | No autogeneration is tried. Perl tries to call |
22d4bb9c |
531 | C<"nomethod"> value, and if this is missing, raises an exception. |
4633a7c4 |
532 | |
533 | =back |
534 | |
e7ea3e70 |
535 | B<Note.> C<"fallback"> inheritance via @ISA is not carved in stone |
536 | yet, see L<"Inheritance and overloading">. |
537 | |
4633a7c4 |
538 | =head2 Copy Constructor |
539 | |
540 | The value for C<"="> is a reference to a function with three |
541 | arguments, i.e., it looks like the other values in C<use |
542 | overload>. However, it does not overload the Perl assignment |
543 | operator. This would go against Camel hair. |
544 | |
545 | This operation is called in the situations when a mutator is applied |
546 | to a reference that shares its object with some other reference, such |
547 | as |
548 | |
22d4bb9c |
549 | $a=$b; |
ee239bfe |
550 | ++$a; |
4633a7c4 |
551 | |
552 | To make this change $a and not change $b, a copy of C<$$a> is made, |
553 | and $a is assigned a reference to this new object. This operation is |
ee239bfe |
554 | done during execution of the C<++$a>, and not during the assignment, |
4633a7c4 |
555 | (so before the increment C<$$a> coincides with C<$$b>). This is only |
ee239bfe |
556 | done if C<++> is expressed via a method for C<'++'> or C<'+='> (or |
557 | C<nomethod>). Note that if this operation is expressed via C<'+'> |
558 | a nonmutator, i.e., as in |
4633a7c4 |
559 | |
22d4bb9c |
560 | $a=$b; |
4633a7c4 |
561 | $a=$a+1; |
562 | |
563 | then C<$a> does not reference a new copy of C<$$a>, since $$a does not |
564 | appear as lvalue when the above code is executed. |
565 | |
566 | If the copy constructor is required during the execution of some mutator, |
567 | but a method for C<'='> was not specified, it can be autogenerated as a |
568 | string copy if the object is a plain scalar. |
569 | |
570 | =over 5 |
571 | |
572 | =item B<Example> |
573 | |
22d4bb9c |
574 | The actually executed code for |
4633a7c4 |
575 | |
22d4bb9c |
576 | $a=$b; |
4633a7c4 |
577 | Something else which does not modify $a or $b.... |
578 | ++$a; |
579 | |
580 | may be |
581 | |
22d4bb9c |
582 | $a=$b; |
4633a7c4 |
583 | Something else which does not modify $a or $b.... |
584 | $a = $a->clone(undef,""); |
585 | $a->incr(undef,""); |
586 | |
587 | if $b was mathemagical, and C<'++'> was overloaded with C<\&incr>, |
588 | C<'='> was overloaded with C<\&clone>. |
589 | |
590 | =back |
591 | |
f610777f |
592 | Same behaviour is triggered by C<$b = $a++>, which is consider a synonym for |
ee239bfe |
593 | C<$b = $a; ++$a>. |
594 | |
4633a7c4 |
595 | =head1 MAGIC AUTOGENERATION |
596 | |
597 | If a method for an operation is not found, and the value for C<"fallback"> is |
598 | TRUE or undefined, Perl tries to autogenerate a substitute method for |
599 | the missing operation based on the defined operations. Autogenerated method |
600 | substitutions are possible for the following operations: |
601 | |
602 | =over 16 |
603 | |
604 | =item I<Assignment forms of arithmetic operations> |
605 | |
606 | C<$a+=$b> can use the method for C<"+"> if the method for C<"+="> |
607 | is not defined. |
608 | |
22d4bb9c |
609 | =item I<Conversion operations> |
4633a7c4 |
610 | |
611 | String, numeric, and boolean conversion are calculated in terms of one |
612 | another if not all of them are defined. |
613 | |
614 | =item I<Increment and decrement> |
615 | |
616 | The C<++$a> operation can be expressed in terms of C<$a+=1> or C<$a+1>, |
617 | and C<$a--> in terms of C<$a-=1> and C<$a-1>. |
618 | |
619 | =item C<abs($a)> |
620 | |
621 | can be expressed in terms of C<$aE<lt>0> and C<-$a> (or C<0-$a>). |
622 | |
623 | =item I<Unary minus> |
624 | |
625 | can be expressed in terms of subtraction. |
626 | |
3bc6ec80 |
627 | =item I<Negation> |
628 | |
629 | C<!> and C<not> can be expressed in terms of boolean conversion, or |
630 | string or numerical conversion. |
631 | |
4633a7c4 |
632 | =item I<Concatenation> |
633 | |
634 | can be expressed in terms of string conversion. |
635 | |
22d4bb9c |
636 | =item I<Comparison operations> |
4633a7c4 |
637 | |
638 | can be expressed in terms of its "spaceship" counterpart: either |
639 | C<E<lt>=E<gt>> or C<cmp>: |
1fef88e7 |
640 | |
4633a7c4 |
641 | <, >, <=, >=, ==, != in terms of <=> |
642 | lt, gt, le, ge, eq, ne in terms of cmp |
643 | |
f5284f61 |
644 | =item I<Iterator> |
645 | |
646 | <> in terms of builtin operations |
647 | |
648 | =item I<Dereferencing> |
649 | |
650 | ${} @{} %{} &{} *{} in terms of builtin operations |
651 | |
4633a7c4 |
652 | =item I<Copy operator> |
653 | |
654 | can be expressed in terms of an assignment to the dereferenced value, if this |
655 | value is a scalar and not a reference. |
656 | |
657 | =back |
658 | |
ee239bfe |
659 | =head1 Losing overloading |
4633a7c4 |
660 | |
661 | The restriction for the comparison operation is that even if, for example, |
662 | `C<cmp>' should return a blessed reference, the autogenerated `C<lt>' |
663 | function will produce only a standard logical value based on the |
664 | numerical value of the result of `C<cmp>'. In particular, a working |
665 | numeric conversion is needed in this case (possibly expressed in terms of |
666 | other conversions). |
667 | |
668 | Similarly, C<.=> and C<x=> operators lose their mathemagical properties |
669 | if the string conversion substitution is applied. |
670 | |
671 | When you chop() a mathemagical object it is promoted to a string and its |
672 | mathemagical properties are lost. The same can happen with other |
673 | operations as well. |
674 | |
675 | =head1 Run-time Overloading |
676 | |
677 | Since all C<use> directives are executed at compile-time, the only way to |
678 | change overloading during run-time is to |
679 | |
680 | eval 'use overload "+" => \&addmethod'; |
681 | |
682 | You can also use |
683 | |
684 | eval 'no overload "+", "--", "<="'; |
685 | |
686 | though the use of these constructs during run-time is questionable. |
687 | |
688 | =head1 Public functions |
689 | |
690 | Package C<overload.pm> provides the following public functions: |
691 | |
692 | =over 5 |
693 | |
694 | =item overload::StrVal(arg) |
695 | |
696 | Gives string value of C<arg> as in absence of stringify overloading. |
697 | |
698 | =item overload::Overloaded(arg) |
699 | |
700 | Returns true if C<arg> is subject to overloading of some operations. |
701 | |
702 | =item overload::Method(obj,op) |
703 | |
704 | Returns C<undef> or a reference to the method that implements C<op>. |
705 | |
706 | =back |
707 | |
b3ac6de7 |
708 | =head1 Overloading constants |
709 | |
710 | For some application Perl parser mangles constants too much. It is possible |
711 | to hook into this process via overload::constant() and overload::remove_constant() |
712 | functions. |
713 | |
714 | These functions take a hash as an argument. The recognized keys of this hash |
715 | are |
716 | |
717 | =over 8 |
718 | |
719 | =item integer |
720 | |
721 | to overload integer constants, |
722 | |
723 | =item float |
724 | |
725 | to overload floating point constants, |
726 | |
727 | =item binary |
728 | |
729 | to overload octal and hexadecimal constants, |
730 | |
731 | =item q |
732 | |
733 | to overload C<q>-quoted strings, constant pieces of C<qq>- and C<qx>-quoted |
734 | strings and here-documents, |
735 | |
736 | =item qr |
737 | |
738 | to overload constant pieces of regular expressions. |
739 | |
740 | =back |
741 | |
742 | The corresponding values are references to functions which take three arguments: |
743 | the first one is the I<initial> string form of the constant, the second one |
22d4bb9c |
744 | is how Perl interprets this constant, the third one is how the constant is used. |
b3ac6de7 |
745 | Note that the initial string form does not |
22d4bb9c |
746 | contain string delimiters, and has backslashes in backslash-delimiter |
b3ac6de7 |
747 | combinations stripped (thus the value of delimiter is not relevant for |
22d4bb9c |
748 | processing of this string). The return value of this function is how this |
b3ac6de7 |
749 | constant is going to be interpreted by Perl. The third argument is undefined |
750 | unless for overloaded C<q>- and C<qr>- constants, it is C<q> in single-quote |
751 | context (comes from strings, regular expressions, and single-quote HERE |
22d4bb9c |
752 | documents), it is C<tr> for arguments of C<tr>/C<y> operators, |
b3ac6de7 |
753 | it is C<s> for right-hand side of C<s>-operator, and it is C<qq> otherwise. |
754 | |
755 | Since an expression C<"ab$cd,,"> is just a shortcut for C<'ab' . $cd . ',,'>, |
756 | it is expected that overloaded constant strings are equipped with reasonable |
22d4bb9c |
757 | overloaded catenation operator, otherwise absurd results will result. |
b3ac6de7 |
758 | Similarly, negative numbers are considered as negations of positive constants. |
759 | |
760 | Note that it is probably meaningless to call the functions overload::constant() |
761 | and overload::remove_constant() from anywhere but import() and unimport() methods. |
762 | From these methods they may be called as |
763 | |
764 | sub import { |
765 | shift; |
766 | return unless @_; |
767 | die "unknown import: @_" unless @_ == 1 and $_[0] eq ':constant'; |
768 | overload::constant integer => sub {Math::BigInt->new(shift)}; |
769 | } |
770 | |
22d4bb9c |
771 | B<BUGS> Currently overloaded-ness of constants does not propagate |
b3ac6de7 |
772 | into C<eval '...'>. |
773 | |
4633a7c4 |
774 | =head1 IMPLEMENTATION |
775 | |
776 | What follows is subject to change RSN. |
777 | |
e7ea3e70 |
778 | The table of methods for all operations is cached in magic for the |
779 | symbol table hash for the package. The cache is invalidated during |
780 | processing of C<use overload>, C<no overload>, new function |
781 | definitions, and changes in @ISA. However, this invalidation remains |
782 | unprocessed until the next C<bless>ing into the package. Hence if you |
783 | want to change overloading structure dynamically, you'll need an |
784 | additional (fake) C<bless>ing to update the table. |
785 | |
786 | (Every SVish thing has a magic queue, and magic is an entry in that |
787 | queue. This is how a single variable may participate in multiple |
788 | forms of magic simultaneously. For instance, environment variables |
789 | regularly have two forms at once: their %ENV magic and their taint |
790 | magic. However, the magic which implements overloading is applied to |
791 | the stashes, which are rarely used directly, thus should not slow down |
792 | Perl.) |
4633a7c4 |
793 | |
794 | If an object belongs to a package using overload, it carries a special |
795 | flag. Thus the only speed penalty during arithmetic operations without |
796 | overloading is the checking of this flag. |
797 | |
774d564b |
798 | In fact, if C<use overload> is not present, there is almost no overhead |
799 | for overloadable operations, so most programs should not suffer |
800 | measurable performance penalties. A considerable effort was made to |
801 | minimize the overhead when overload is used in some package, but the |
802 | arguments in question do not belong to packages using overload. When |
803 | in doubt, test your speed with C<use overload> and without it. So far |
804 | there have been no reports of substantial speed degradation if Perl is |
805 | compiled with optimization turned on. |
4633a7c4 |
806 | |
e7ea3e70 |
807 | There is no size penalty for data if overload is not used. The only |
808 | size penalty if overload is used in some package is that I<all> the |
809 | packages acquire a magic during the next C<bless>ing into the |
810 | package. This magic is three-words-long for packages without |
f610777f |
811 | overloading, and carries the cache table if the package is overloaded. |
4633a7c4 |
812 | |
22d4bb9c |
813 | Copying (C<$a=$b>) is shallow; however, a one-level-deep copying is |
4633a7c4 |
814 | carried out before any operation that can imply an assignment to the |
815 | object $a (or $b) refers to, like C<$a++>. You can override this |
816 | behavior by defining your own copy constructor (see L<"Copy Constructor">). |
817 | |
818 | It is expected that arguments to methods that are not explicitly supposed |
819 | to be changed are constant (but this is not enforced). |
820 | |
ee239bfe |
821 | =head1 Metaphor clash |
822 | |
f610777f |
823 | One may wonder why the semantic of overloaded C<=> is so counter intuitive. |
22d4bb9c |
824 | If it I<looks> counter intuitive to you, you are subject to a metaphor |
825 | clash. |
ee239bfe |
826 | |
827 | Here is a Perl object metaphor: |
828 | |
829 | I< object is a reference to blessed data> |
830 | |
831 | and an arithmetic metaphor: |
832 | |
833 | I< object is a thing by itself>. |
834 | |
835 | The I<main> problem of overloading C<=> is the fact that these metaphors |
836 | imply different actions on the assignment C<$a = $b> if $a and $b are |
837 | objects. Perl-think implies that $a becomes a reference to whatever |
838 | $b was referencing. Arithmetic-think implies that the value of "object" |
839 | $a is changed to become the value of the object $b, preserving the fact |
840 | that $a and $b are separate entities. |
841 | |
842 | The difference is not relevant in the absence of mutators. After |
843 | a Perl-way assignment an operation which mutates the data referenced by $a |
22d4bb9c |
844 | would change the data referenced by $b too. Effectively, after |
ee239bfe |
845 | C<$a = $b> values of $a and $b become I<indistinguishable>. |
846 | |
22d4bb9c |
847 | On the other hand, anyone who has used algebraic notation knows the |
ee239bfe |
848 | expressive power of the arithmetic metaphor. Overloading works hard |
849 | to enable this metaphor while preserving the Perlian way as far as |
850 | possible. Since it is not not possible to freely mix two contradicting |
851 | metaphors, overloading allows the arithmetic way to write things I<as |
852 | far as all the mutators are called via overloaded access only>. The |
853 | way it is done is described in L<Copy Constructor>. |
854 | |
855 | If some mutator methods are directly applied to the overloaded values, |
22d4bb9c |
856 | one may need to I<explicitly unlink> other values which references the |
ee239bfe |
857 | same value: |
858 | |
859 | $a = new Data 23; |
860 | ... |
861 | $b = $a; # $b is "linked" to $a |
862 | ... |
863 | $a = $a->clone; # Unlink $b from $a |
864 | $a->increment_by(4); |
865 | |
866 | Note that overloaded access makes this transparent: |
867 | |
868 | $a = new Data 23; |
869 | $b = $a; # $b is "linked" to $a |
870 | $a += 4; # would unlink $b automagically |
871 | |
872 | However, it would not make |
873 | |
874 | $a = new Data 23; |
875 | $a = 4; # Now $a is a plain 4, not 'Data' |
876 | |
877 | preserve "objectness" of $a. But Perl I<has> a way to make assignments |
878 | to an object do whatever you want. It is just not the overload, but |
879 | tie()ing interface (see L<perlfunc/tie>). Adding a FETCH() method |
22d4bb9c |
880 | which returns the object itself, and STORE() method which changes the |
ee239bfe |
881 | value of the object, one can reproduce the arithmetic metaphor in its |
882 | completeness, at least for variables which were tie()d from the start. |
883 | |
884 | (Note that a workaround for a bug may be needed, see L<"BUGS">.) |
885 | |
886 | =head1 Cookbook |
887 | |
888 | Please add examples to what follows! |
889 | |
890 | =head2 Two-face scalars |
891 | |
892 | Put this in F<two_face.pm> in your Perl library directory: |
893 | |
894 | package two_face; # Scalars with separate string and |
895 | # numeric values. |
896 | sub new { my $p = shift; bless [@_], $p } |
897 | use overload '""' => \&str, '0+' => \&num, fallback => 1; |
898 | sub num {shift->[1]} |
899 | sub str {shift->[0]} |
900 | |
901 | Use it as follows: |
902 | |
903 | require two_face; |
904 | my $seven = new two_face ("vii", 7); |
905 | printf "seven=$seven, seven=%d, eight=%d\n", $seven, $seven+1; |
906 | print "seven contains `i'\n" if $seven =~ /i/; |
907 | |
908 | (The second line creates a scalar which has both a string value, and a |
909 | numeric value.) This prints: |
910 | |
911 | seven=vii, seven=7, eight=8 |
912 | seven contains `i' |
913 | |
f5284f61 |
914 | =head2 Two-face references |
915 | |
916 | Suppose you want to create an object which is accessible as both an |
22d4bb9c |
917 | array reference and a hash reference, similar to the |
918 | L<pseudo-hash|perlref/"Pseudo-hashes: Using an array as a hash"> |
919 | builtin Perl type. Let's make it better than a pseudo-hash by |
920 | allowing index 0 to be treated as a normal element. |
f5284f61 |
921 | |
922 | package two_refs; |
923 | use overload '%{}' => \&gethash, '@{}' => sub { $ {shift()} }; |
22d4bb9c |
924 | sub new { |
925 | my $p = shift; |
f5284f61 |
926 | bless \ [@_], $p; |
927 | } |
928 | sub gethash { |
929 | my %h; |
930 | my $self = shift; |
931 | tie %h, ref $self, $self; |
932 | \%h; |
933 | } |
934 | |
935 | sub TIEHASH { my $p = shift; bless \ shift, $p } |
936 | my %fields; |
937 | my $i = 0; |
938 | $fields{$_} = $i++ foreach qw{zero one two three}; |
22d4bb9c |
939 | sub STORE { |
f5284f61 |
940 | my $self = ${shift()}; |
941 | my $key = $fields{shift()}; |
942 | defined $key or die "Out of band access"; |
943 | $$self->[$key] = shift; |
944 | } |
22d4bb9c |
945 | sub FETCH { |
f5284f61 |
946 | my $self = ${shift()}; |
947 | my $key = $fields{shift()}; |
948 | defined $key or die "Out of band access"; |
949 | $$self->[$key]; |
950 | } |
951 | |
952 | Now one can access an object using both the array and hash syntax: |
953 | |
954 | my $bar = new two_refs 3,4,5,6; |
955 | $bar->[2] = 11; |
956 | $bar->{two} == 11 or die 'bad hash fetch'; |
957 | |
958 | Note several important features of this example. First of all, the |
959 | I<actual> type of $bar is a scalar reference, and we do not overload |
960 | the scalar dereference. Thus we can get the I<actual> non-overloaded |
961 | contents of $bar by just using C<$$bar> (what we do in functions which |
962 | overload dereference). Similarly, the object returned by the |
963 | TIEHASH() method is a scalar reference. |
964 | |
965 | Second, we create a new tied hash each time the hash syntax is used. |
966 | This allows us not to worry about a possibility of a reference loop, |
967 | would would lead to a memory leak. |
968 | |
969 | Both these problems can be cured. Say, if we want to overload hash |
970 | dereference on a reference to an object which is I<implemented> as a |
971 | hash itself, the only problem one has to circumvent is how to access |
972 | this I<actual> hash (as opposed to the I<virtual> exhibited by |
973 | overloaded dereference operator). Here is one possible fetching routine: |
974 | |
975 | sub access_hash { |
976 | my ($self, $key) = (shift, shift); |
977 | my $class = ref $self; |
22d4bb9c |
978 | bless $self, 'overload::dummy'; # Disable overloading of %{} |
f5284f61 |
979 | my $out = $self->{$key}; |
980 | bless $self, $class; # Restore overloading |
981 | $out; |
982 | } |
983 | |
984 | To move creation of the tied hash on each access, one may an extra |
985 | level of indirection which allows a non-circular structure of references: |
986 | |
987 | package two_refs1; |
988 | use overload '%{}' => sub { ${shift()}->[1] }, |
989 | '@{}' => sub { ${shift()}->[0] }; |
22d4bb9c |
990 | sub new { |
991 | my $p = shift; |
f5284f61 |
992 | my $a = [@_]; |
993 | my %h; |
994 | tie %h, $p, $a; |
995 | bless \ [$a, \%h], $p; |
996 | } |
997 | sub gethash { |
998 | my %h; |
999 | my $self = shift; |
1000 | tie %h, ref $self, $self; |
1001 | \%h; |
1002 | } |
1003 | |
1004 | sub TIEHASH { my $p = shift; bless \ shift, $p } |
1005 | my %fields; |
1006 | my $i = 0; |
1007 | $fields{$_} = $i++ foreach qw{zero one two three}; |
22d4bb9c |
1008 | sub STORE { |
f5284f61 |
1009 | my $a = ${shift()}; |
1010 | my $key = $fields{shift()}; |
1011 | defined $key or die "Out of band access"; |
1012 | $a->[$key] = shift; |
1013 | } |
22d4bb9c |
1014 | sub FETCH { |
f5284f61 |
1015 | my $a = ${shift()}; |
1016 | my $key = $fields{shift()}; |
1017 | defined $key or die "Out of band access"; |
1018 | $a->[$key]; |
1019 | } |
1020 | |
1021 | Now if $baz is overloaded like this, then C<$bar> is a reference to a |
1022 | reference to the intermediate array, which keeps a reference to an |
1023 | actual array, and the access hash. The tie()ing object for the access |
22d4bb9c |
1024 | hash is also a reference to a reference to the actual array, so |
f5284f61 |
1025 | |
1026 | =over |
1027 | |
1028 | =item * |
1029 | |
1030 | There are no loops of references. |
1031 | |
1032 | =item * |
1033 | |
1034 | Both "objects" which are blessed into the class C<two_refs1> are |
1035 | references to a reference to an array, thus references to a I<scalar>. |
1036 | Thus the accessor expression C<$$foo-E<gt>[$ind]> involves no |
1037 | overloaded operations. |
1038 | |
1039 | =back |
1040 | |
ee239bfe |
1041 | =head2 Symbolic calculator |
1042 | |
1043 | Put this in F<symbolic.pm> in your Perl library directory: |
1044 | |
1045 | package symbolic; # Primitive symbolic calculator |
1046 | use overload nomethod => \&wrap; |
1047 | |
1048 | sub new { shift; bless ['n', @_] } |
1049 | sub wrap { |
1050 | my ($obj, $other, $inv, $meth) = @_; |
1051 | ($obj, $other) = ($other, $obj) if $inv; |
1052 | bless [$meth, $obj, $other]; |
1053 | } |
1054 | |
1055 | This module is very unusual as overloaded modules go: it does not |
1056 | provide any usual overloaded operators, instead it provides the L<Last |
1057 | Resort> operator C<nomethod>. In this example the corresponding |
f610777f |
1058 | subroutine returns an object which encapsulates operations done over |
ee239bfe |
1059 | the objects: C<new symbolic 3> contains C<['n', 3]>, C<2 + new |
1060 | symbolic 3> contains C<['+', 2, ['n', 3]]>. |
1061 | |
1062 | Here is an example of the script which "calculates" the side of |
1063 | circumscribed octagon using the above package: |
1064 | |
1065 | require symbolic; |
1066 | my $iter = 1; # 2**($iter+2) = 8 |
1067 | my $side = new symbolic 1; |
1068 | my $cnt = $iter; |
3cb6de81 |
1069 | |
ee239bfe |
1070 | while ($cnt--) { |
1071 | $side = (sqrt(1 + $side**2) - 1)/$side; |
1072 | } |
1073 | print "OK\n"; |
1074 | |
1075 | The value of $side is |
1076 | |
1077 | ['/', ['-', ['sqrt', ['+', 1, ['**', ['n', 1], 2]], |
1078 | undef], 1], ['n', 1]] |
1079 | |
1080 | Note that while we obtained this value using a nice little script, |
1081 | there is no simple way to I<use> this value. In fact this value may |
1082 | be inspected in debugger (see L<perldebug>), but ony if |
1083 | C<bareStringify> B<O>ption is set, and not via C<p> command. |
1084 | |
1085 | If one attempts to print this value, then the overloaded operator |
1086 | C<""> will be called, which will call C<nomethod> operator. The |
1087 | result of this operator will be stringified again, but this result is |
1088 | again of type C<symbolic>, which will lead to an infinite loop. |
1089 | |
1090 | Add a pretty-printer method to the module F<symbolic.pm>: |
1091 | |
1092 | sub pretty { |
1093 | my ($meth, $a, $b) = @{+shift}; |
1094 | $a = 'u' unless defined $a; |
1095 | $b = 'u' unless defined $b; |
1096 | $a = $a->pretty if ref $a; |
1097 | $b = $b->pretty if ref $b; |
1098 | "[$meth $a $b]"; |
22d4bb9c |
1099 | } |
ee239bfe |
1100 | |
1101 | Now one can finish the script by |
1102 | |
1103 | print "side = ", $side->pretty, "\n"; |
1104 | |
1105 | The method C<pretty> is doing object-to-string conversion, so it |
1106 | is natural to overload the operator C<""> using this method. However, |
1107 | inside such a method it is not necessary to pretty-print the |
1108 | I<components> $a and $b of an object. In the above subroutine |
1109 | C<"[$meth $a $b]"> is a catenation of some strings and components $a |
1110 | and $b. If these components use overloading, the catenation operator |
1111 | will look for an overloaded operator C<.>, if not present, it will |
1112 | look for an overloaded operator C<"">. Thus it is enough to use |
1113 | |
1114 | use overload nomethod => \&wrap, '""' => \&str; |
1115 | sub str { |
1116 | my ($meth, $a, $b) = @{+shift}; |
1117 | $a = 'u' unless defined $a; |
1118 | $b = 'u' unless defined $b; |
1119 | "[$meth $a $b]"; |
22d4bb9c |
1120 | } |
ee239bfe |
1121 | |
1122 | Now one can change the last line of the script to |
1123 | |
1124 | print "side = $side\n"; |
1125 | |
1126 | which outputs |
1127 | |
1128 | side = [/ [- [sqrt [+ 1 [** [n 1 u] 2]] u] 1] [n 1 u]] |
1129 | |
1130 | and one can inspect the value in debugger using all the possible |
22d4bb9c |
1131 | methods. |
ee239bfe |
1132 | |
1133 | Something is is still amiss: consider the loop variable $cnt of the |
1134 | script. It was a number, not an object. We cannot make this value of |
1135 | type C<symbolic>, since then the loop will not terminate. |
1136 | |
1137 | Indeed, to terminate the cycle, the $cnt should become false. |
1138 | However, the operator C<bool> for checking falsity is overloaded (this |
1139 | time via overloaded C<"">), and returns a long string, thus any object |
1140 | of type C<symbolic> is true. To overcome this, we need a way to |
1141 | compare an object to 0. In fact, it is easier to write a numeric |
1142 | conversion routine. |
1143 | |
1144 | Here is the text of F<symbolic.pm> with such a routine added (and |
f610777f |
1145 | slightly modified str()): |
ee239bfe |
1146 | |
1147 | package symbolic; # Primitive symbolic calculator |
1148 | use overload |
1149 | nomethod => \&wrap, '""' => \&str, '0+' => \# |
1150 | |
1151 | sub new { shift; bless ['n', @_] } |
1152 | sub wrap { |
1153 | my ($obj, $other, $inv, $meth) = @_; |
1154 | ($obj, $other) = ($other, $obj) if $inv; |
1155 | bless [$meth, $obj, $other]; |
1156 | } |
1157 | sub str { |
1158 | my ($meth, $a, $b) = @{+shift}; |
1159 | $a = 'u' unless defined $a; |
1160 | if (defined $b) { |
1161 | "[$meth $a $b]"; |
1162 | } else { |
1163 | "[$meth $a]"; |
1164 | } |
22d4bb9c |
1165 | } |
1166 | my %subr = ( n => sub {$_[0]}, |
1167 | sqrt => sub {sqrt $_[0]}, |
ee239bfe |
1168 | '-' => sub {shift() - shift()}, |
1169 | '+' => sub {shift() + shift()}, |
1170 | '/' => sub {shift() / shift()}, |
1171 | '*' => sub {shift() * shift()}, |
1172 | '**' => sub {shift() ** shift()}, |
1173 | ); |
1174 | sub num { |
1175 | my ($meth, $a, $b) = @{+shift}; |
22d4bb9c |
1176 | my $subr = $subr{$meth} |
ee239bfe |
1177 | or die "Do not know how to ($meth) in symbolic"; |
1178 | $a = $a->num if ref $a eq __PACKAGE__; |
1179 | $b = $b->num if ref $b eq __PACKAGE__; |
1180 | $subr->($a,$b); |
1181 | } |
1182 | |
1183 | All the work of numeric conversion is done in %subr and num(). Of |
f610777f |
1184 | course, %subr is not complete, it contains only operators used in the |
ee239bfe |
1185 | example below. Here is the extra-credit question: why do we need an |
1186 | explicit recursion in num()? (Answer is at the end of this section.) |
1187 | |
1188 | Use this module like this: |
1189 | |
1190 | require symbolic; |
1191 | my $iter = new symbolic 2; # 16-gon |
1192 | my $side = new symbolic 1; |
1193 | my $cnt = $iter; |
3cb6de81 |
1194 | |
ee239bfe |
1195 | while ($cnt) { |
1196 | $cnt = $cnt - 1; # Mutator `--' not implemented |
1197 | $side = (sqrt(1 + $side**2) - 1)/$side; |
1198 | } |
1199 | printf "%s=%f\n", $side, $side; |
1200 | printf "pi=%f\n", $side*(2**($iter+2)); |
1201 | |
1202 | It prints (without so many line breaks) |
1203 | |
1204 | [/ [- [sqrt [+ 1 [** [/ [- [sqrt [+ 1 [** [n 1] 2]]] 1] |
1205 | [n 1]] 2]]] 1] |
1206 | [/ [- [sqrt [+ 1 [** [n 1] 2]]] 1] [n 1]]]=0.198912 |
1207 | pi=3.182598 |
1208 | |
1209 | The above module is very primitive. It does not implement |
1210 | mutator methods (C<++>, C<-=> and so on), does not do deep copying |
1211 | (not required without mutators!), and implements only those arithmetic |
1212 | operations which are used in the example. |
1213 | |
f610777f |
1214 | To implement most arithmetic operations is easy, one should just use |
ee239bfe |
1215 | the tables of operations, and change the code which fills %subr to |
1216 | |
1217 | my %subr = ( 'n' => sub {$_[0]} ); |
1218 | foreach my $op (split " ", $overload::ops{with_assign}) { |
1219 | $subr{$op} = $subr{"$op="} = eval "sub {shift() $op shift()}"; |
1220 | } |
1221 | my @bins = qw(binary 3way_comparison num_comparison str_comparison); |
1222 | foreach my $op (split " ", "@overload::ops{ @bins }") { |
1223 | $subr{$op} = eval "sub {shift() $op shift()}"; |
1224 | } |
1225 | foreach my $op (split " ", "@overload::ops{qw(unary func)}") { |
1226 | print "defining `$op'\n"; |
1227 | $subr{$op} = eval "sub {$op shift()}"; |
1228 | } |
1229 | |
1230 | Due to L<Calling Conventions for Mutators>, we do not need anything |
1231 | special to make C<+=> and friends work, except filling C<+=> entry of |
1232 | %subr, and defining a copy constructor (needed since Perl has no |
1233 | way to know that the implementation of C<'+='> does not mutate |
1234 | the argument, compare L<Copy Constructor>). |
1235 | |
1236 | To implement a copy constructor, add C<'=' => \&cpy> to C<use overload> |
1237 | line, and code (this code assumes that mutators change things one level |
1238 | deep only, so recursive copying is not needed): |
1239 | |
1240 | sub cpy { |
1241 | my $self = shift; |
1242 | bless [@$self], ref $self; |
1243 | } |
1244 | |
22d4bb9c |
1245 | To make C<++> and C<--> work, we need to implement actual mutators, |
ee239bfe |
1246 | either directly, or in C<nomethod>. We continue to do things inside |
1247 | C<nomethod>, thus add |
1248 | |
1249 | if ($meth eq '++' or $meth eq '--') { |
1250 | @$obj = ($meth, (bless [@$obj]), 1); # Avoid circular reference |
1251 | return $obj; |
1252 | } |
1253 | |
22d4bb9c |
1254 | after the first line of wrap(). This is not a most effective |
ee239bfe |
1255 | implementation, one may consider |
1256 | |
1257 | sub inc { $_[0] = bless ['++', shift, 1]; } |
1258 | |
1259 | instead. |
1260 | |
1261 | As a final remark, note that one can fill %subr by |
1262 | |
1263 | my %subr = ( 'n' => sub {$_[0]} ); |
1264 | foreach my $op (split " ", $overload::ops{with_assign}) { |
1265 | $subr{$op} = $subr{"$op="} = eval "sub {shift() $op shift()}"; |
1266 | } |
1267 | my @bins = qw(binary 3way_comparison num_comparison str_comparison); |
1268 | foreach my $op (split " ", "@overload::ops{ @bins }") { |
1269 | $subr{$op} = eval "sub {shift() $op shift()}"; |
1270 | } |
1271 | foreach my $op (split " ", "@overload::ops{qw(unary func)}") { |
1272 | $subr{$op} = eval "sub {$op shift()}"; |
1273 | } |
1274 | $subr{'++'} = $subr{'+'}; |
1275 | $subr{'--'} = $subr{'-'}; |
1276 | |
22d4bb9c |
1277 | This finishes implementation of a primitive symbolic calculator in |
1278 | 50 lines of Perl code. Since the numeric values of subexpressions |
ee239bfe |
1279 | are not cached, the calculator is very slow. |
1280 | |
1281 | Here is the answer for the exercise: In the case of str(), we need no |
1282 | explicit recursion since the overloaded C<.>-operator will fall back |
1283 | to an existing overloaded operator C<"">. Overloaded arithmetic |
1284 | operators I<do not> fall back to numeric conversion if C<fallback> is |
1285 | not explicitly requested. Thus without an explicit recursion num() |
1286 | would convert C<['+', $a, $b]> to C<$a + $b>, which would just rebuild |
1287 | the argument of num(). |
1288 | |
1289 | If you wonder why defaults for conversion are different for str() and |
1290 | num(), note how easy it was to write the symbolic calculator. This |
1291 | simplicity is due to an appropriate choice of defaults. One extra |
f610777f |
1292 | note: due to the explicit recursion num() is more fragile than sym(): |
1293 | we need to explicitly check for the type of $a and $b. If components |
ee239bfe |
1294 | $a and $b happen to be of some related type, this may lead to problems. |
1295 | |
1296 | =head2 I<Really> symbolic calculator |
1297 | |
1298 | One may wonder why we call the above calculator symbolic. The reason |
1299 | is that the actual calculation of the value of expression is postponed |
1300 | until the value is I<used>. |
1301 | |
1302 | To see it in action, add a method |
1303 | |
22d4bb9c |
1304 | sub STORE { |
1305 | my $obj = shift; |
1306 | $#$obj = 1; |
ee239bfe |
1307 | @$obj->[0,1] = ('=', shift); |
1308 | } |
1309 | |
1310 | to the package C<symbolic>. After this change one can do |
1311 | |
1312 | my $a = new symbolic 3; |
1313 | my $b = new symbolic 4; |
1314 | my $c = sqrt($a**2 + $b**2); |
1315 | |
1316 | and the numeric value of $c becomes 5. However, after calling |
1317 | |
1318 | $a->STORE(12); $b->STORE(5); |
1319 | |
1320 | the numeric value of $c becomes 13. There is no doubt now that the module |
1321 | symbolic provides a I<symbolic> calculator indeed. |
1322 | |
1323 | To hide the rough edges under the hood, provide a tie()d interface to the |
1324 | package C<symbolic> (compare with L<Metaphor clash>). Add methods |
1325 | |
1326 | sub TIESCALAR { my $pack = shift; $pack->new(@_) } |
1327 | sub FETCH { shift } |
1328 | sub nop { } # Around a bug |
1329 | |
1330 | (the bug is described in L<"BUGS">). One can use this new interface as |
1331 | |
1332 | tie $a, 'symbolic', 3; |
1333 | tie $b, 'symbolic', 4; |
1334 | $a->nop; $b->nop; # Around a bug |
1335 | |
1336 | my $c = sqrt($a**2 + $b**2); |
1337 | |
1338 | Now numeric value of $c is 5. After C<$a = 12; $b = 5> the numeric value |
1339 | of $c becomes 13. To insulate the user of the module add a method |
1340 | |
1341 | sub vars { my $p = shift; tie($_, $p), $_->nop foreach @_; } |
1342 | |
1343 | Now |
1344 | |
1345 | my ($a, $b); |
1346 | symbolic->vars($a, $b); |
1347 | my $c = sqrt($a**2 + $b**2); |
1348 | |
1349 | $a = 3; $b = 4; |
1350 | printf "c5 %s=%f\n", $c, $c; |
1351 | |
1352 | $a = 12; $b = 5; |
1353 | printf "c13 %s=%f\n", $c, $c; |
1354 | |
1355 | shows that the numeric value of $c follows changes to the values of $a |
1356 | and $b. |
1357 | |
4633a7c4 |
1358 | =head1 AUTHOR |
1359 | |
1fef88e7 |
1360 | Ilya Zakharevich E<lt>F<ilya@math.mps.ohio-state.edu>E<gt>. |
4633a7c4 |
1361 | |
1362 | =head1 DIAGNOSTICS |
1363 | |
1364 | When Perl is run with the B<-Do> switch or its equivalent, overloading |
1365 | induces diagnostic messages. |
1366 | |
e7ea3e70 |
1367 | Using the C<m> command of Perl debugger (see L<perldebug>) one can |
1368 | deduce which operations are overloaded (and which ancestor triggers |
1369 | this overloading). Say, if C<eq> is overloaded, then the method C<(eq> |
1370 | is shown by debugger. The method C<()> corresponds to the C<fallback> |
1371 | key (in fact a presence of this method shows that this package has |
1372 | overloading enabled, and it is what is used by the C<Overloaded> |
ee239bfe |
1373 | function of module C<overload>). |
e7ea3e70 |
1374 | |
22d4bb9c |
1375 | The module might issue the following warnings: |
1376 | |
1377 | =over 4 |
1378 | |
1379 | =item Odd number of arguments for overload::constant |
1380 | |
1381 | (W) The call to overload::constant contained an odd number of arguments. |
1382 | The arguments should come in pairs. |
1383 | |
1384 | =item `%s' is not an overloadable type |
1385 | |
1386 | (W) You tried to overload a constant type the overload package is unaware of. |
1387 | |
1388 | =item `%s' is not a code reference |
1389 | |
1390 | (W) The second (fourth, sixth, ...) argument of overload::constant needs |
1391 | to be a code reference. Either an anonymous subroutine, or a reference |
1392 | to a subroutine. |
1393 | |
1394 | =back |
1395 | |
4633a7c4 |
1396 | =head1 BUGS |
1397 | |
aa689395 |
1398 | Because it is used for overloading, the per-package hash %OVERLOAD now |
1399 | has a special meaning in Perl. The symbol table is filled with names |
1400 | looking like line-noise. |
4633a7c4 |
1401 | |
a6006777 |
1402 | For the purpose of inheritance every overloaded package behaves as if |
1403 | C<fallback> is present (possibly undefined). This may create |
1404 | interesting effects if some package is not overloaded, but inherits |
1405 | from two overloaded packages. |
4633a7c4 |
1406 | |
22d4bb9c |
1407 | Relation between overloading and tie()ing is broken. Overloading is |
ee239bfe |
1408 | triggered or not basing on the I<previous> class of tie()d value. |
1409 | |
22d4bb9c |
1410 | This happens because the presence of overloading is checked too early, |
ee239bfe |
1411 | before any tie()d access is attempted. If the FETCH()ed class of the |
22d4bb9c |
1412 | tie()d value does not change, a simple workaround is to access the value |
ee239bfe |
1413 | immediately after tie()ing, so that after this call the I<previous> class |
1414 | coincides with the current one. |
1415 | |
1416 | B<Needed:> a way to fix this without a speed penalty. |
1417 | |
b3ac6de7 |
1418 | Barewords are not covered by overloaded string constants. |
1419 | |
ee239bfe |
1420 | This document is confusing. There are grammos and misleading language |
1421 | used in places. It would seem a total rewrite is needed. |
4633a7c4 |
1422 | |
1423 | =cut |
1424 | |