Re: How to strip comments and whitespace from a regex defined with /x? (ppix_regexp_strip_comments)

[Anonymous Monk]

As a followup to Re^3: How to strip comments and whitespace from a regex defined with /x?

#!/usr/bin/perl --
use strict;
use warnings;
use PPIx::Regexp;
use Data::Dump;
my $r = PPIx::Regexp->new(q{
s{
(?# probulary )
\d+ # digits
[ ] # space
\s+ # spaces
\w+ # words 
(?# probulary )}{}gx
});
print "\n\n", $r->content, "\n";
dd( $r );
delete_commentsss( $r );
print "\n\n";
dd($r);
print "\n\n", $r->content, "\n";
sub delete_commentsss {
    my( $n ) = @_;
    for my $child ( eval { $n->children } ){        
        if( eval{ $child->children } ){ #$haskids 
            delete_commentsss( $child );
        } else {
            for my $il ( qw{ start children finish } ){
                if( $n->{$il} ){
                    @{ $n->{$il}  } = grep {
                        not(
                            $_->isa(  "PPIx::Regexp::Token::Whitespace
+" )
                            or
                            $_->isa(  "PPIx::Regexp::Token::Comment" )
                        )
                    } @{ $n->{$il}  };
                }
            }
        }
    }
    return $n;
}

__END__



s{
(?# probulary )
\d+ # digits
[ ] # space
\s+ # spaces
\w+ # words 
(?# probulary )}{}gx

bless({
  children => [
    bless({ content => "\n", perl_version_introduced => "5.000" }, "PP
+Ix::Regexp::Token::Whitespace"),
    bless({ content => "s" }, "PPIx::Regexp::Token::Structure"),
    bless({
      children => [
        bless({ content => "\\d" }, "PPIx::Regexp::Token::CharClass::S
+imple"),
        bless({ content => "+" }, "PPIx::Regexp::Token::Quantifier"),
        bless({ content => " ", perl_version_introduced => "5.000" }, 
+"PPIx::Regexp::Token::Whitespace"),
        bless({ content => "# digits\n" }, "PPIx::Regexp::Token::Comme
+nt"),
        bless({
          children => [bless({ content => " " }, "PPIx::Regexp::Token:
+:Literal")],
          finish   => [bless({ content => "]" }, "PPIx::Regexp::Token:
+:Structure")],
          start    => [bless({ content => "[" }, "PPIx::Regexp::Token:
+:Structure")],
          type     => [],
        }, "PPIx::Regexp::Structure::CharClass"),
        bless({ content => " ", perl_version_introduced => "5.000" }, 
+"PPIx::Regexp::Token::Whitespace"),
        bless({ content => "# space\n" }, "PPIx::Regexp::Token::Commen
+t"),
        bless({ content => "\\s" }, "PPIx::Regexp::Token::CharClass::S
+imple"),
        bless({ content => "+" }, "PPIx::Regexp::Token::Quantifier"),
        bless({ content => " ", perl_version_introduced => "5.000" }, 
+"PPIx::Regexp::Token::Whitespace"),
        bless({ content => "# spaces\n" }, "PPIx::Regexp::Token::Comme
+nt"),
        bless({ content => "\\w" }, "PPIx::Regexp::Token::CharClass::S
+imple"),
        bless({ content => "+" }, "PPIx::Regexp::Token::Quantifier"),
        bless({ content => " ", perl_version_introduced => "5.000" }, 
+"PPIx::Regexp::Token::Whitespace"),
        bless({ content => "# words \n" }, "PPIx::Regexp::Token::Comme
+nt"),
        bless({ content => "(?# probulary )" }, "PPIx::Regexp::Token::
+Comment"),
      ],
      finish => [bless({ content => "}" }, "PPIx::Regexp::Token::Delim
+iter")],
      max_capture_number => 0,
      start => [
        bless({ content => "{" }, "PPIx::Regexp::Token::Delimiter"),
        bless({ content => "\n", perl_version_introduced => "5.000" },
+ "PPIx::Regexp::Token::Whitespace"),
        bless({ content => "(?# probulary )" }, "PPIx::Regexp::Token::
+Comment"),
        bless({ content => "\n", perl_version_introduced => "5.000" },
+ "PPIx::Regexp::Token::Whitespace"),
      ],
      type => [],
    }, "PPIx::Regexp::Structure::Regexp"),
    bless({ content => "{" }, "PPIx::Regexp::Token::Delimiter"),
    bless({ content => "}" }, "PPIx::Regexp::Token::Delimiter"),
    bless({ content => "gx", modifiers => { g => 1, x => 1 } }, "PPIx:
+:Regexp::Token::Modifier"),
    bless({ content => "\n", perl_version_introduced => "5.000" }, "PP
+Ix::Regexp::Token::Whitespace"),
  ],
  effective_modifiers => { g => 1, x => 1 },
  failures => 0,
  source => "\ns{\n(?# probulary )\n\\d+ # digits\n[ ] # space\n\\s+ #
+ spaces\n\\w+ # words \n(?# probulary )}{}gx\n",
}, "PPIx::Regexp")


bless({
  children => [
    bless({ content => "s" }, "PPIx::Regexp::Token::Structure"),
    bless({
      children => [
        bless({ content => "\\d" }, "PPIx::Regexp::Token::CharClass::S
+imple"),
        bless({ content => "+" }, "PPIx::Regexp::Token::Quantifier"),
        bless({
          children => [bless({ content => " " }, "PPIx::Regexp::Token:
+:Literal")],
          finish   => [bless({ content => "]" }, "PPIx::Regexp::Token:
+:Structure")],
          start    => [bless({ content => "[" }, "PPIx::Regexp::Token:
+:Structure")],
          type     => [],
        }, "PPIx::Regexp::Structure::CharClass"),
        bless({ content => "\\s" }, "PPIx::Regexp::Token::CharClass::S
+imple"),
        bless({ content => "+" }, "PPIx::Regexp::Token::Quantifier"),
        bless({ content => "\\w" }, "PPIx::Regexp::Token::CharClass::S
+imple"),
        bless({ content => "+" }, "PPIx::Regexp::Token::Quantifier"),
      ],
      finish => [bless({ content => "}" }, "PPIx::Regexp::Token::Delim
+iter")],
      max_capture_number => 0,
      start => [bless({ content => "{" }, "PPIx::Regexp::Token::Delimi
+ter")],
      type => [],
    }, "PPIx::Regexp::Structure::Regexp"),
    bless({ content => "{" }, "PPIx::Regexp::Token::Delimiter"),
    bless({ content => "}" }, "PPIx::Regexp::Token::Delimiter"),
    bless({ content => "gx", modifiers => { g => 1, x => 1 } }, "PPIx:
+:Regexp::Token::Modifier"),
  ],
  effective_modifiers => { g => 1, x => 1 },
  failures => 0,
  source => "\ns{\n(?# probulary )\n\\d+ # digits\n[ ] # space\n\\s+ #
+ spaces\n\\w+ # words \n(?# probulary )}{}gx\n",
}, "PPIx::Regexp")


s{\d+[ ]\s+\w+}{}gx