Routines are one of the means Raku has to reuse code. They come in several forms, most notably methods, which belong in classes and roles and are associated with an object; and functions (also called subroutines or subs, for short), which can be called independently of objects.

Subroutines default to lexical (my) scoping, and calls to them are generally resolved at compile time.

Subroutines can have a signature, also called parameter list, which specifies which, if any, arguments the signature expects. It can specify (or leave open) both the number and types of arguments, and the return value.

Introspection on subroutines is provided via Routine.

Using functions §

Subroutines §

The basic way to create a subroutine is to use the sub declarator followed by an optional identifier:

sub my-func { say "Look ma, no args!" }
my-func;

The sub declarator returns a value of type Sub that can be stored in any container:

my &c = sub { say "Look ma, no name!" }
c;     # OUTPUT: «Look ma, no name!␤» 
 
my Any:D $f = sub { say 'Still nameless...' }
$f();  # OUTPUT: «Still nameless...␤» 
 
my Code \a = sub { say ‚raw containers don't implement postcircumfix:<( )>‘ };
a.();  # OUTPUT: «raw containers don't implement postcircumfix:<( )>␤»

The declarator sub will declare a new name in the current scope at compile time. As such, any indirection has to be resolved at compile time:

constant aname = 'foo';
sub ::(aname) { say 'oi‽' };
foo;

This will become more useful once macros are added to Raku.

To have the subroutine take arguments, a signature goes between the subroutine's name and its body, in parentheses:

sub exclaim ($phrase) {
    say $phrase ~ "!!!!"
}
exclaim "Howdy, World";

By default, subroutines are lexically scoped. That is, sub foo {...} is the same as my sub foo {...} and is only defined within the current scope.

sub escape($str) {
    # Puts a slash before non-alphanumeric characters 
    S:g[<-alpha -digit>] = "\\$/" given $str
}
 
say escape 'foo#bar?'; # OUTPUT: «foo\#bar\?␤» 
 
{
    sub escape($str) {
        # Writes each non-alphanumeric character in its hexadecimal escape 
        S:g[<-alpha -digit>] = "\\x[{ $/.ord.base(16) }]" given $str
    }
 
    say escape 'foo#bar?' # OUTPUT: «foo\x[23]bar\x[3F]␤» 
}
 
# Back to original escape function 
say escape 'foo#bar?'; # OUTPUT: «foo\#bar\?␤»

Subroutines don't have to be named. If unnamed, they're called anonymous subroutines.

say sub ($a, $b) { $a ** 2 + $b ** 2 }(3, 4) # OUTPUT: «25␤»

But in this case, it's often desirable to use the more succinct block syntax. Subroutines and blocks can be called in place, as in the example above.

say -> $a, $b { $a ** 2 + $b ** 2 }(3, 4)    # OUTPUT: «25␤»

Or even

say { $^a ** 2 + $^b ** 2 }(3, 4)            # OUTPUT: «25␤»

Blocks and lambdas §

Whenever you see something like { $_ + 42 }, -> $a, $b { $a ** $b }, or { $^text.indent($:spaces) }, that's Block syntax; the -> is considered also part of the block. Statements such as if, for, while are followed by these kind of blocks.

for 1, 2, 3, 4 -> $a, $b {
    say $a ~ $b;
}
# OUTPUT: «12␤34␤»

They can also be used on their own as anonymous blocks of code.

say { $^a ** 2 + $^b ** 2}(3, 4) # OUTPUT: «25␤»

Please note that this implies that, despite the fact that statements such as if do not define a topic variable, they actually can:

my $foo = 33;
if $foo ** 33 -> $a {
    say "$a is not null"; # 
} # OUTPUT: «129110040087761027839616029934664535539337183380513 is not null␤»

For block syntax details, see the documentation for the Block type.

Signatures §

The parameters that a function accepts are described in its signature.

sub format(Str $s) { ... }
-> $a, $b { ... }

Details about the syntax and use of signatures can be found in the documentation on the Signature class.

Automatic signatures §

If no signature is provided but either of the two automatic variables @_ or %_ are used in the function body, a signature with *@_ or *%_ will be generated. Both automatic variables can be used at the same time.

sub s { say @_, %_ };
say &s.signature # OUTPUT: «(*@_, *%_)␤»

Arguments §

Arguments are supplied as a comma separated list. To disambiguate nested calls, use parentheses:

sub f(&c){ c() * 2 }; # call the function reference c with empty parameter list 
sub g($p){ $p - 2 };
say(g(42), 45);       # pass only 42 to g()

When calling a function, positional arguments should be supplied in the same order as the function's signature. Named arguments may be supplied in any order, but it's considered good form to place named arguments after positional arguments. Inside the argument list of a function call, some special syntax is supported:

sub f(|c){};
f :named(35);     # A named argument (in "adverb" form) 
f named => 35;    # Also a named argument 
f :35named;       # A named argument using abbreviated adverb form 
f 'named' => 35;  # Not a named argument, a Pair in a positional argument 
f 'hi', :1x, :2y; # Positional and named arguments 
my \c = <a b c>.Capture;
f |c;             # Merge the contents of Capture $c as if they were supplied

Arguments passed to a function are conceptually first collected in a Capture container. Details about the syntax and use of these containers can be found in the documentation on the Capture class.

When using named arguments, note that normal list "pair-chaining" allows one to skip commas between named arguments.

sub f(|c){};
f :dest</tmp/foo> :src</tmp/bar> :lines(512);
f :32x :50y :110z;   # This flavor of "adverb" works, too 
f :a:b:c;            # The spaces are also optional.

If positional arguments are also passed, then either they must be passed within parentheses placed immediately after the function's name or the comma after the last positional argument must be kept when chaining named arguments in abbreviated adverb form. The spaces between chained named arguments and the list of positional arguments is optional.

sub p($x, $y, :$translate, :$rotate) {};
p(1, 1, :translate, :rotate); # normal way 
p 1, 1, :translate, :rotate;  # also normal way 
 
p(1, 1) :translate  :rotate;  # parentheses + chained named arguments 
p(1, 1) :translate:rotate;
p(1, 1):translate:rotate;
 
p 1, 1, :translate  :rotate;  # dangling comma + chained named arguments 
p 1, 1, :translate:rotate;
p 1, 1,:translate:rotate;

Return values §

Any Block or Routine will provide the value of its last expression as a return value to the caller. If either return or return-rw is called, then its parameter, if any, will become the return value. The default return value is Nil.

sub a { 42 };
sub b { say a };
sub c { };
b;     # OUTPUT: «42␤» 
say c; # OUTPUT: «Nil␤»

Multiple return values are returned as a list or by creating a Capture. Destructuring can be used to untangle multiple return values.

sub a { 42, 'answer' };
put a.raku;
# OUTPUT: «(42, "answer")␤» 
 
my ($n, $s) = a;
put [$s, $n];
# OUTPUT: «answer 42␤» 
 
sub b { <a b c>.Capture };
put b.raku;
# OUTPUT: «\("a", "b", "c")␤»

Return type constraints §

Raku has many ways to specify a function's return type:

sub foo(--> Int)      {}; say &foo.returns; # OUTPUT: «(Int)␤»

sub foo() returns Int {}; say &foo.returns; # OUTPUT: «(Int)␤»

sub foo() of Int      {}; say &foo.returns; # OUTPUT: «(Int)␤»

my Int sub foo()      {}; say &foo.returns; # OUTPUT: «(Int)␤»

Attempting to return values of another type will cause a compilation error.

sub foo() returns Int { "a"; }; foo; # Type check fails

returns and of are equivalent, and both take only a Type since they are declaring a trait of the Callable. The last declaration is, in fact, a type declaration, which obviously can take only a type. In the other hand, --> can take either undefined or definite values.

Note that Nil and Failure are exempt from return type constraints and can be returned from any routine, regardless of its constraint:

sub foo() returns Int { fail   }; foo; # Failure returned 
sub bar() returns Int { return }; bar; # Nil returned

Multi-dispatch §

Raku allows for writing several routines with the same name but different signatures. When the routine is called by name, the runtime environment determines the proper candidate and invokes it.

Each candidate is declared with the multi keyword. Dispatch happens depending on the parameter arity (number), type and name; and under some circumstances the order of the multi declarations. Consider the following example:

# version 1 
multi happy-birthday( $name ) {
    say "Happy Birthday $name !";
}
 
# version 2 
multi happy-birthday( $name, $age ) {
    say "Happy {$age}th Birthday $name !";
}
 
# version 3 
multi happy-birthday( :$name, :$age, :$title  = 'Mr' ) {
    say "Happy {$age}th Birthday $title $name !";
}
 
 
# calls version 1 (arity) 
happy-birthday 'Larry';                        # OUTPUT: «Happy Birthday Larry !␤» 
# calls version 2 (arity) 
happy-birthday 'Luca', 40;                     # OUTPUT: «Happy 40th Birthday Luca !␤» 
# calls version 3 
# (named arguments win against arity) 
happy-birthday( age => '50', name => 'John' ); # OUTPUT: «Happy 50th Birthday Mr John !␤» 
# calls version 2 (arity) 
happy-birthday( 'Jack', 25 );                  # OUTPUT: «Happy 25th Birthday Jack !␤»

The first two versions of the happy-birthday sub differs only in the arity (number of arguments), while the third version uses named arguments and is chosen only when named arguments are used, even if the arity is the same of another multi candidate.

When two sub have the same arity, the type of the arguments drive the dispatch; when there are named arguments they drive the dispatch even when their type is the same as another candidate:

multi happy-birthday( Str $name, Int $age ) {
    say "Happy {$age}th Birthday $name !";
}
 
multi happy-birthday( Str $name, Str $title ) {
    say "Happy Birthday $title $name !";
}
 
multi happy-birthday( Str :$name, Int :$age ) {
    say "Happy Birthday $name, you turned $age !";
}
 
happy-birthday 'Luca', 40;                 # OUTPUT: «Happy 40th Birthday Luca !␤» 
happy-birthday 'Luca', 'Mr';               # OUTPUT: «Happy Birthday Mr Luca !␤» 
happy-birthday age => 40, name => 'Luca';  # OUTPUT: «Happy Birthday Luca, you turned 40 !␤»

Named parameters participate in the dispatch even if they are not provided in the call. Therefore a multi candidate with named parameters will be given precedence.

For more information about type constraints see the documentation for the Signature class.

multi as-json(Bool $d) { $d ?? 'true' !! 'false'; }
multi as-json(Real $d) { ~$d }
multi as-json(@d)      { sprintf '[%s]', @d.map(&as-json).join(', ') }
 
say as-json( True );                        # OUTPUT: «true␤» 
say as-json( 10.3 );                        # OUTPUT: «10.3␤» 
say as-json( [ True, 10.3, False, 24 ] );   # OUTPUT: «[true, 10.3, false, 24]␤»

For some signature differences (notably when using a where clause or a subset) the order of definition of the multi methods or subs is used, evaluating each possibility in turn. See multi resolution by order of definition below for examples.

multi without any specific routine type always defaults to a sub, but you can use it on methods as well. The candidates are all the multi methods of the object:

class Congrats {
    multi method congratulate($reason, $name) {
        say "Hooray for your $reason, $name";
    }
}
 
role BirthdayCongrats {
    multi method congratulate('birthday', $name) {
        say "Happy birthday, $name";
    }
    multi method congratulate('birthday', $name, $age) {
        say "Happy {$age}th birthday, $name";
    }
}
 
my $congrats = Congrats.new does BirthdayCongrats;
 
$congrats.congratulate('promotion','Cindy'); # OUTPUT: «Hooray for your promotion, Cindy␤» 
$congrats.congratulate('birthday','Bob');    # OUTPUT: «Happy birthday, Bob␤»

Unlike sub, if you use named parameters with multi methods, the parameters must be required parameters to behave as expected.

Please note that a non-multi sub or operator will hide multi candidates of the same name in any parent scope or child scope. The same is true for imported non-multi candidates.

Multi-dispatch can also work on parameter traits, with routines with is rw parameters having a higher priority than those that do not:

proto þoo (|) {*}
multi sub þoo( $ðar is rw ) { $ðar = 42 }
multi sub þoo( $ðar ) { $ðar + 42 }
my $bar = 7;
say þoo($bar); # OUTPUT: «42»

proto §

proto is a way to formally declare commonalities between multi candidates. It acts as a wrapper that can validate but not modify arguments. Consider this basic example:

proto congratulate(Str $reason, Str $name, |) {*}
multi congratulate($reason, $name) {
   say "Hooray for your $reason, $name";
}
multi congratulate($reason, $name, Int $rank) {
   say "Hooray for your $reason, $name -- got rank $rank!";
}
 
congratulate('being a cool number', 'Fred');     # OK 
congratulate('being a cool number', 'Fred', 42); # OK

congratulate('being a cool number', 42);         # Proto match error

The proto insists that all multi congratulate subs conform to the basic signature of two strings, optionally followed by further parameters. The | is an un-named Capture parameter, and allows a multi to take additional arguments. The first two calls succeed, but the third fails (at compile time) because 42 doesn't match Str.

say &congratulate.signature # OUTPUT: «(Str $reason, Str $name, | is raw)␤»

You can give the proto a function body, and place the {*} (note there is no whitespace inside the curly braces) where you want the dispatch to be done. This can be useful when you have a "hole" in your routine that gives it different behavior depending on the arguments given:

# attempts to notify someone -- False if unsuccessful 
proto notify(Str $user, Str $msg) {
   my \hour = DateTime.now.hour;
   if 8 < hour < 22 {
      return {*};
   } else {
      # we can't notify someone when they might be sleeping 
      return False;
   }
}

Since proto is a wrapper for multi candidates, the signatures of the routine's multi candidates do not necessarily have to match that of the proto; arguments of multi candidates may have subtypes of those of the proto, and the return types of the multi candidates may be entirely different from that of the proto. Using differing types like this is especially useful when giving proto a function body:

enum DebugType <LOG WARNING ERROR>;
 
#|[ Prints a message to stderr with a color-coded key. ] 
proto debug(DebugType:D $type, Str:D $message --> Bool:_) {
    note sprintf qb/\e[1;%dm[%s]\e[0m %s/, {*}, $type.key, $message
}
multi debug(LOG;; Str:D --> 32)     { }
multi debug(WARNING;; Str:D --> 33) { }
multi debug(ERROR;; Str:D --> 31)   { }

{*} always dispatches to candidates with the parameters it's called with. Parameter defaults and type coercions will work but are not passed on.

proto mistake-proto(Str() $str, Int $number = 42) {*}
multi mistake-proto($str, $number) { say $str.^name }
mistake-proto(7, 42);  # OUTPUT: «Int␤» -- not passed on

mistake-proto('test'); # fails -- not passed on

A longer example using proto for methods shows how to extract common functionality into a proto method.

class NewClass {
    has $.debug is rw = False;
    has $.value is rw = 'Initial value';
    proto method handle( | ) {
        note "before value is ｢$.value｣" if $.debug;
        {*}
        note "after value is ｢$.value｣" if $.debug;
    }
    multi method handle(Str $s) {
        $.value = $s;
        say 'in string'
    }
    multi method handle(Positional $s) {
        $.value = $s[0];
        say 'in positional'
    }
    multi method handle( $a, $b ) {
        $.value = "$a is looking askance at $b";
        say 'with more than one value'
    }
}
my NewClass $x .= new;
$x.handle('hello world');
$x.handle(<hello world>);
$x.debug = True;
$x.handle('hello world');
$x.handle(<hello world>);
$x.handle('Claire', 'John');
# OUTPUT: 
# in string 
# in positional 
# before value is ｢hello｣ 
# in string 
# after value is ｢hello world｣ 
# before value is ｢hello world｣ 
# in positional 
# after value is ｢hello｣ 
# before value is ｢hello｣ 
# with more than one value 
# after value is ｢Claire is looking askance at John｣

only §

The only keyword preceding sub or method indicates that it will be the only function with that name that inhabits a given namespace.

only sub you () {"Can make all the world seem right"};

This will make other declarations in the same namespace, such as

sub you ( $can ) { "Make the darkness bright" }

fail with an exception of type X::Redeclaration. only is the default value for all subs; in the case above, not declaring the first subroutine as only will yield exactly the same error; however, nothing prevents future developers from declaring a proto and preceding the names with multi. Using only before a routine is a defensive programming feature that declares the intention of not having routines with the same name declared in the same namespace in the future.

(exit code 1)
===SORRY!=== Error while compiling /tmp/only-redeclaration.p6
Redeclaration of routine 'you' (did you mean to declare a multi-sub?)
at /tmp/only-redeclaration.p6:3
------> <BOL>⏏<EOL>

Anonymous subs cannot be declared only. only sub {} will throw an error of type, surprisingly, X::Anon::Multi.

multi resolution by order of definition §

When the breakdown by parameter type is not enough to find an unambiguous match, there are some different tie breakers that may be evaluated in order of declaration of the methods or subs: these include where clauses and subsets, named parameters, and signature unpacks.

In this code example, two multi subs are distinguished only by where clauses where there's one ambiguous case that might pass either of them, the value 4. In this case, which ever multi sub is defined first wins:

{
  multi sub check_range ( Int $n where {$_ > 3} ) {
      return "over 3";
  };
  multi sub check_range ( Int $n where {$_ < 5} ) {
      return "under 5";
  };
  say check_range(4);  # OUTPUT: over 3 
}
{
  multi sub check_range ( Int $n where {$_ < 5} ) {
      return "under 5";
  };
  multi sub check_range ( Int $n where {$_ > 3} ) {
      return "over 3";
  };
  say check_range(4);  # OUTPUT: under 5 
}

In the following example, three subsets are used to restrict strings to certain allowed values, where there are overlaps between all three:

subset Monster  of Str where { $_ eq any( <godzilla gammera ghidora> ) };
subset Hero     of Str where { $_ eq any( <godzilla ultraman inframan> ) };
subset Knockoff of Str where { $_ eq any( <gammera inframan thorndike> ) };
 
{
    multi sub speak (Monster $name) {
        say "The monster, $name roars!";
    }
    multi sub speak (Hero $name) {
        say "The hero, $name shouts!";
    }
    multi sub speak (Knockoff $name) {
        say "The knockoff, $name, slinks away...";
    }
    speak('godzilla');     # OUTPUT: The monster, godzilla roars! 
    speak('gammera');      # OUTPUT: The monster, gammera roars! 
    speak('inframan');     # OUTPUT: The hero, inframan shouts! 
}

Note that here 'godzilla' is treated as Monster, not as Hero, because the Monster multi comes first; and neither 'gammera' or 'inframan' are treated as Knockoff, because that multi comes last.

It should be noted that the order of definition is the order in which Raku sees them, which might not be easy to discern if, for example, the multi subs were imported from different modules. As the organization of a code base becomes more complex, object classes may scale better than using subsets as types, as in this example.

Conventions and idioms §

While the dispatch system described above provides a lot of flexibility, there are some conventions that most internal functions, and those in many modules, will follow.

Slurpy conventions §

Perhaps the most important one of these conventions is the way slurpy list arguments are handled. Most of the time, functions will not automatically flatten slurpy lists. The rare exceptions are those functions that don't have a reasonable behavior on lists of lists (e.g., chrs) or where there is a conflict with an established idiom (e.g., pop being the inverse of push).

If you wish to match this look and feel, any Iterable argument must be broken out element-by-element using a **@ slurpy, with two nuances:

An Iterable inside a Scalar container doesn't count.
Lists created with a , at the top level only count as one Iterable.

This can be achieved by using a slurpy with a + or +@ instead of **@:

sub grab(+@a) { "grab $_".say for @a }

which is shorthand for something very close to:

multi sub grab(**@a) { "grab $_".say for @a }
multi sub grab(\a) {
    a ~~ Iterable and a.VAR !~~ Scalar ?? nextwith(|a) !! nextwith(a,)
}

This results in the following behavior, which is known as the "single argument rule" and is important to understand when invoking slurpy functions:

grab(1, 2);      # OUTPUT: «grab 1␤grab 2␤» 
grab((1, 2));    # OUTPUT: «grab 1␤grab 2␤» 
grab($(1, 2));   # OUTPUT: «grab 1 2␤» 
grab((1, 2), 3); # OUTPUT: «grab 1 2␤grab 3␤»

This also makes user-requested flattening feel consistent whether there is one sublist, or many:

grab(flat (1, 2), (3, 4));   # OUTPUT: «grab 1␤grab 2␤grab 3␤grab 4␤» 
grab(flat $(1, 2), $(3, 4)); # OUTPUT: «grab 1 2␤grab 3 4␤» 
grab(flat (1, 2));           # OUTPUT: «grab 1␤grab 2␤» 
grab(flat $(1, 2));          # OUTPUT: «grab 1␤grab 2␤»

It's worth noting that mixing binding and sigilless variables in these cases requires a bit of finesse, because there is no Scalar intermediary used during binding.

my $a = (1, 2);  # Normal assignment, equivalent to $(1, 2) 
grab($a);        # OUTPUT: «grab 1 2␤» 
my $b := (1, 2); # Binding, $b links directly to a bare (1, 2) 
grab($b);        # OUTPUT: «grab 1␤grab 2␤» 
my \c = (1, 2);  # Sigilless variables always bind, even with '=' 
grab(c);         # OUTPUT: «grab 1␤grab 2␤»

See the documentation of the list subroutine for more examples of how to use a routine that adheres to the single argument rule.

Functions are first-class objects §

Functions and other code objects can be passed around as values, just like any other object.

There are several ways to get hold of a code object. You can assign it to a variable at the point of declaration:

my $square = sub (Numeric $x) { $x * $x }
# and then use it: 
say $square(6);    # OUTPUT: «36␤»

Or you can reference an existing named function by using the &-sigil in front of it.

sub square($x) { $x * $x };
 
# get hold of a reference to the function: 
my $func = &square

This is very useful for higher order functions, that is, functions that take other functions as input. A simple one is map, which applies a function to each input element:

sub square($x) { $x * $x };
my @squared = map &square,  1..5;
say join ', ', @squared;        # OUTPUT: «1, 4, 9, 16, 25␤»

You can use the same for operators, except that in that case the name with which they have been declared, using infix:, must be used:

my $exp := &infix:<**>; say $exp(7,3); # OUTPUT: «343»

This can be done even in cases where operators have been auto-generated, for instance in this case where XX is the metaoperator X applied to the X operator.

my $XX := &infix:<XX>; say $XX( [1,(2,3)] , [(4,5),6]  );
# OUTPUT: «(((1 (4 5))) ((1 6)) (((2 3) (4 5))) (((2 3) 6)))»

Baseline is that, in case of operators, you don't really need to worry about the actual way they were defined, just use the &infix< > to grab a pointer to them.

Infix form §

To call a subroutine with 2 arguments like an infix operator, use a subroutine reference surrounded by [ and ].

sub plus { $^a + $^b };
say 21 [&plus] 21;
# OUTPUT: «42␤»

Closures §

All code objects in Raku are closures, which means they can reference lexical variables from an outer scope.

sub generate-sub($x) {
    my $y = 2 * $x;
    return sub { say $y };
    #      ^^^^^^^^^^^^^^  inner sub, uses $y 
}
my $generated = generate-sub(21);
$generated(); # OUTPUT: «42␤»

Here, $y is a lexical variable inside generate-sub, and the inner subroutine that is returned uses it. By the time that inner sub is called, generate-sub has already exited. Yet the inner sub can still use $y, because it closed over the variable.

Another closure example is the use of map to multiply a list of numbers:

my $multiply-by = 5;
say join ', ', map { $_ * $multiply-by }, 1..5;     # OUTPUT: «5, 10, 15, 20, 25␤»

Here, the block passed to map references the variable $multiply-by from the outer scope, making the block a closure.

Languages without closures cannot easily provide higher-order functions that are as easy to use and powerful as map.

Routines §

Routines are code objects that conform to type Routine, most notably Sub, Method, Regex and Submethod.

They carry extra functionality in addition to what a Block supplies: they can come as multis, you can wrap them, and exit early with return:

my $keywords = set <if for unless while>;
 
sub has-keyword(*@words) {
    for @words -> $word {
        return True if $word (elem) $keywords;
    }
    False;
}
 
say has-keyword 'not', 'one', 'here';       # OUTPUT: «False␤» 
say has-keyword 'but', 'here', 'for';       # OUTPUT: «True␤»

Here, return doesn't just leave the block inside which it was called, but the whole routine. In general, blocks are transparent to return, they attach to the outermost routine.

Routines can be inlined and as such provide an obstacle for wrapping. Use the pragma use soft; to prevent inlining to allow wrapping at runtime.

sub testee(Int $i, Str $s){
    rand.Rat * $i ~ $s;
}
 
sub wrap-to-debug(&c){
    say "wrapping {&c.name} with arguments {&c.signature.raku}";
    &c.wrap: sub (|args){
        note "calling {&c.name} with {args.gist}";
        my \ret-val := callwith(|args);
        note "returned from {&c.name} with return value {ret-val.raku}";
        ret-val
    }
}
 
my $testee-handler = wrap-to-debug(&testee);
# OUTPUT: «wrapping testee with arguments :(Int $i, Str $s)» 
 
say testee(10, "ten");
# OUTPUT: «calling testee with \(10, "ten")␤returned from testee with return value "6.151190ten"␤6.151190ten» 
&testee.unwrap($testee-handler);
say testee(10, "ten");
# OUTPUT: «6.151190ten␤»

Defining operators §

Operators are just subroutines with funny names. The funny names are composed of the category name (infix, prefix, postfix, circumfix, postcircumfix), followed by a colon, and a list of the operator name or names (two components in the case of circumfix and postcircumfix). A expanded explanation of all these operators and what they mean is included in this table.

This works both for adding multi candidates to existing operators and for defining new ones. In the latter case, the definition of the new subroutine automatically installs the new operator into the grammar, but only in the current lexical scope. Importing an operator via use or import also makes it available.

# adding a multi candidate to an existing operator: 
multi infix:<+>(Int $x, "same") { 2 * $x };
say 21 + "same";            # OUTPUT: «42␤» 
 
# defining a new operator 
sub postfix:<!>(Int $x where { $x >= 0 }) { [*] 1..$x };
say 6!;                     # OUTPUT: «720␤»

The operator declaration becomes available as soon as possible, so you can recurse into a just-defined operator:

sub postfix:<!>(Int $x where { $x >= 0 }) {
    $x == 0 ?? 1 !! $x * ($x - 1)!
}
say 6!;                     # OUTPUT: «720␤»

Circumfix and postcircumfix operators are made of two delimiters, one opening and one closing.

sub circumfix:<START END>(*@elems) {
    "start", @elems, "end"
}
 
say START 'a', 'b', 'c' END;        # OUTPUT: «(start [a b c] end)␤»

Postcircumfixes also receive the term after which they are parsed as an argument:

sub postcircumfix:<!! !!>($left, $inside) {
    "$left -> ( $inside )"
}
say 42!! 1 !!;      # OUTPUT: «42 -> ( 1 )␤»

Blocks can be assigned directly to operator names. Use a variable declarator and prefix the operator name with a &-sigil.

my &infix:<ieq> = -> |l { [eq] l>>.fc };
say "abc" ieq "Abc";
# OUTPUT: «True␤»

Precedence §

Operator precedence in Raku is specified relative to existing operators. The traits is tighter, is equiv and is looser can be provided with an operator to indicate how the precedence of the new operator is related to other, existing ones. More than one trait can be applied.

For example, infix:<*> has a tighter precedence than infix:<+>, and squeezing one in between works like this:

sub infix:<!!>($a, $b) is tighter(&infix:<+>) {
    2 * ($a + $b)
}
 
say 1 + 2 * 3 !! 4;     # OUTPUT: «21␤»

Here, the 1 + 2 * 3 !! 4 is parsed as 1 + ((2 * 3) !! 4), because the precedence of the new !! operator is between that of + and *.

The same effect could have been achieved with:

sub infix:<!!>($a, $b) is looser(&infix:<*>) { ... }

To put a new operator on the same precedence level as an existing operator, use is equiv(&other-operator) instead.

Associativity §

When the same operator appears several times in a row, there are multiple possible interpretations. For example:

1 + 2 + 3

could be parsed as

(1 + 2) + 3         # left associative

or as

1 + (2 + 3)         # right associative

For addition of real numbers, the distinction is somewhat moot, because + is mathematically associative.

But for other operators it matters a great deal. For example, for the exponentiation/power operator, infix:<**>:

say 2 ** (2 ** 3);      # OUTPUT: «256␤» 
say (2 ** 2) ** 3;      # OUTPUT: «64␤»

Raku has the following possible associativity configurations:

Associativity	Meaning of $a ! $b ! $c
left	($a ! $b) ! $c
right	$a ! ($b ! $c)
non	ILLEGAL
chain	($a ! $b) and ($b ! $c)
list	infix:<!>($a; $b; $c)

The Operator docs contain additional details about operator associativity.

You can specify the associativity of an infix operator with the is assoc trait, where left is the default associativity. Specifying the associativity of non-infix operators is planed but not yet implemented.

sub infix:<§>(*@a) is assoc<list> {
    '(' ~ @a.join('|') ~ ')';
}
 
say 1 § 2 § 3;      # OUTPUT: «(1|2|3)␤»

Traits §

Traits are subroutines that run at compile time and modify the behavior of a type, variable, routine, attribute, or other language object.

Examples of traits are:

class ChildClass is ParentClass { ... }
#                ^^ trait, with argument ParentClass
has $.attrib is rw;
#            ^^^^^  trait with name 'rw'
class SomeClass does AnotherRole { ... }
#               ^^^^ trait
has $!another-attribute handles <close>;
#                       ^^^^^^^ trait

... and also is tighter, is looser, is equiv and is assoc from the previous section.

Traits are subs declared in the form trait_mod<VERB>, where VERB stands for the name like is, does or handles. It receives the modified thing as argument, and the name as a named argument. See Sub for details.

multi sub trait_mod:<is>(Routine $r, :$doubles!) {
    $r.wrap({
        2 * callsame;
    });
}
 
sub square($x) is doubles {
    $x * $x;
}
 
say square 3;       # OUTPUT: «18␤»

See type Routine for the documentation of built-in routine traits.

Re-dispatching §

There are cases in which a routine might want to call the next method from a chain. This chain could be a list of parent classes in a class hierarchy, or it could be less specific multi candidates from a multi dispatch, or it could be the inner routine from a wrap.

Fortunately, we have a series of re-dispatching tools that help us to make it easy.

sub callsame §

callsame calls the next matching candidate with the same arguments that were used for the current candidate and returns that candidate's return value.

proto a(|) {*}
 
multi a(Any $x) {
    say "Any $x";
    return 5;
}
 
multi a(Int $x) {
    say "Int $x";
    my $res = callsame;
    say "Back in Int with $res";
}
 
a 1;        # OUTPUT: «Int 1␤Any 1␤Back in Int with 5␤»

sub callwith §

callwith calls the next candidate matching the original signature, that is, the next function that could possibly be used with the arguments provided by users and returns that candidate's return value.

proto a(|) {*}
 
multi a(Any $x) {
    say "Any $x";
    return 5;
}
multi a(Int $x) {
    say "Int $x";
    my $res = callwith($x + 1);
    say "Back in Int with $res";
}
 
a 1;        # OUTPUT: «Int 1␤Any 2␤Back in Int with 5␤»

Here, a 1 calls the most specific Int candidate first, and callwith re-dispatches to the less specific Any candidate. Note that although our parameter $x + 1 is an Int, still we call the next candidate in the chain.

In this case, for example:

proto how-many(|) {*}
 
multi how-many( Associative $a ) {
    say "Associative $a ";
    my $calling = callwith( 1 => $a );
    return $calling;
}
 
multi how-many( Pair $a ) {
    say "Pair $a ";
    return "There is $a "
 
}
 
multi how-many( Hash $a ) {
    say "Hash $a";
    return "Hashing $a";
}
 
my $little-piggy = little => 'piggy';
say $little-piggy.^name;        # OUTPUT: «Pair␤» 
say &how-many.cando( \( $little-piggy ));
# OUTPUT: «(sub how-many (Pair $a) { #`(Sub|68970512) ... } sub how-many (Associative $a) { #`(Sub|68970664) ... })␤» 
say how-many( $little-piggy  ); # OUTPUT: «Pair little     piggy␤There is little piggy␤»

the only candidates that take the Pair argument supplied by the user are the two functions defined first. Although a Pair can be easily coerced to a Hash, here is how signatures match:

say :( Pair ) ~~ :( Associative ); # OUTPUT: «True␤» 
say :( Pair ) ~~ :( Hash );        # OUTPUT: «False␤»

The arguments provided by us are a Pair. It does not match a Hash, so the corresponding function is thus not included in the list of candidates, as can be seen by the output of &how-many.cando( \( $little-piggy ));.

sub nextsame §

nextsame calls the next matching candidate with the same arguments that were used for the current candidate and never returns.

proto a(|) {*}
 
multi a(Any $x) {
    say "Any $x";
    return 5;
}
multi a(Int $x) {
    say "Int $x";
    nextsame;
    say "never executed because nextsame doesn't return";
}
 
a 1;        # OUTPUT: «Int 1␤Any 1␤»

sub nextwith §

nextwith calls the next matching candidate with arguments provided by users and never returns.

proto a(|) {*}
 
multi a(Any $x) {
    say "Any $x";
    return 5;
}
multi a(Int $x) {
    say "Int $x";
    nextwith($x + 1);
    say "never executed because nextwith doesn't return";
}
 
a 1;        # OUTPUT: «Int 1␤Any 2␤»

sub samewith §

samewith calls the multi again with arguments provided at the call site and returns the value provided by the call. This can be used for self-recursion.

proto factorial(|) {*}
 
multi factorial(Int $x where * ≤ 1) { 1 }
multi factorial(Int $x) {
    $x * samewith($x-1);
}
 
say (factorial 10); # OUTPUT: «36288000␤»

sub nextcallee §

Redispatch may be required to call a block that is not the current scope what provides nextsame and friends with the problem to referring to the wrong scope. Use nextcallee to capture the right candidate and call it at the desired time.

proto pick-winner(|) {*}
 
multi pick-winner (Int \s) {
    my &nextone = nextcallee;
    Promise.in(π²).then: { nextone s }
}
multi pick-winner { say "Woot! $^w won" }
 
with pick-winner ^5 .pick -> \result {
    say "And the winner is...";
    await result;
}
 
# OUTPUT: 
# And the winner is... 
# Woot! 3 won

The Int candidate takes the nextcallee and then fires up a Promise to be executed in parallel, after some timeout, and then returns. We can't use nextsame here, because it'd be trying to nextsame the Promise's block instead of our original routine.

Wrapped routines §

Besides those already mentioned above, re-dispatch is helpful in many more situations. For instance, for dispatching to wrapped routines:

# enable wrapping: 
use soft;
 
# function to be wrapped: 
sub square-root($x) { $x.sqrt }
 
&square-root.wrap(sub ($num) {
   nextsame if $num >= 0;
   1i * callwith(abs($num));
});
 
say square-root(4);     # OUTPUT: «2␤» 
say square-root(-4);    # OUTPUT: «0+2i␤»

Routines of parent class §

Another use case is to re-dispatch to methods from parent classes.

say Version.new('1.0.2') # OUTPUT: v1.0.2

class LoggedVersion is Version {
    method new(|c) {
        note "New version object created with arguments " ~ c.raku;
        nextsame;
    }
}
 
say LoggedVersion.new('1.0.2');
 
# OUTPUT: 
# New version object created with arguments \("1.0.2") 
# v1.0.2

Coercion types §

Coercion types force a specific type for routine arguments while allowing the routine itself to accept a wider input. When invoked, the arguments are narrowed automatically to the stricter type, and therefore within the routine the arguments have always the desired type.

In the case the arguments cannot be converted to the stricter type, a Type Check error is thrown.

sub double(Int(Cool) $x) {
    2 * $x
}
 
say double '21';# OUTPUT: «42␤» 
say double  21; # OUTPUT: «42␤» 
say double Any; # Type check failed in binding $x; expected 'Cool' but got 'Any'

In the above example, the Int is the target type to which the argument $x will be coerced, and Cool is the type that the routine accepts as wider input.

If the accepted wider input type is Any, it is possible to abbreviate the coercion Int(Any) by omitting the Any type, thus resulting in Int().

The coercion works by looking for a method with the same name as the target type: if such method is found on the argument, it is invoked to convert the latter to the expected narrow type. From the above, it is clear that it is possible to provide coercion among user types just providing the required methods:

class Bar {
   has $.msg;
}
 
class Foo {
   has $.msg = "I'm a foo!";
 
   # allows coercion from Foo to Bar 
   method Bar {
       Bar.new(:msg($.msg ~ ' But I am now Bar.'));
   }
}
 
# wants a Bar, but accepts Any 
sub print-bar(Bar() $bar) {
   say $bar.^name; # OUTPUT: «Bar␤» 
   say $bar.msg;   # OUTPUT: «I'm a foo! But I am now Bar.␤» 
}
 
print-bar Foo.new;

In the above code, once a Foo instance is passed as argument to print-bar, the Foo.Bar method is called and the result is placed into $bar.

Coercion types are supposed to work wherever types work, but Rakudo currently (2018.05) only implements them in signatures, for both parameters and return types.

Coercion also works with return types:

sub are-equal (Int $x, Int $y --> Bool(Int) ) { $x - $y };
 
for (2,4) X (1,2) -> ($a,$b) {
    say "Are $a and $b equal? ", are-equal($a, $b);
} #  OUTPUT: «Are 2 and 1 equal? True␤Are 2 and 2 equal? False␤Are 4 and 1 equal? True␤Are 4 and 2 equal? True␤»

In this case, we are coercing an Int to a Bool, which is then printed (put into a string context) in the for loop that calls the function.

sub MAIN §

Declaring a sub MAIN is not compulsory in Raku scripts, but you can provide one to create a command line interface for your script.