http://www.perlmonks.org?node_id=982969


in reply to regex extraction for variable number of args

hi,

I think you're looking for the balance parenthesis regex of Jeffery Friedl. After tweeking for quoted strings it looks something like ...

 my ($np);
 # The initial balance parentheses expression with an embedded set is:
 # $np=qr/\( ([^()] | (??{$np})) *\)/x;
 # And quoted strings are "(?:[^"]|\")*" and '(?:[^']|\')*' or ('|")(?
+:[^\1]|\\1)*\1 so
 $np=qr/
          \(                           # The opening "("
              ((                       # We'll want this hence the cap
+turing ()
                  '(?:[^']|\')*?'      #' a single quote string
                  | "(?:[^"]|\")*?"    #" a double quote string
                  | [^()]              # not a parentheses
                  | (??{$np})
              )*)
          \)                           # and the closing ")"
      /x;

[download]

Replies are listed 'Best First'.
Re^2: regex extraction for variable number of args
by clueless newbie (Curate) on Jul 22, 2012 at 14:33 UTC

    Hi, NetWallah,

    The OP is indeed interesting and goads me into this.

    Thanks!

    #!/usr/bin/perl

use strict;
use warnings;
use Smart::Comments;

    print "\n" x5;
    my ($np_1,$np_2);
    # The initial balance parentheses expression with an embedded set 
+is:
    # $np=qr/\( ([^()] | (??{$np})) *\)/x;
    # And quoted strings are "(?:[^"]|\")*" and '(?:[^']|\')*' or ('|"
+)(?:[^\1]|\\1)*\1 so
    $np_1=qr/
             \(                            # The opening "("
                 ((?:                      # We'll want this hence the
+ capturing ()
                     | [^'"()]             #' not a ' " ( or )
                     | (?:'(?:[^']|\')*?') #' a single quote string
                     | (?:"(?:[^"]|\")*?") #" a double quote string
                     | (??{$np_1})         # parenthesized expression
                 )*)
             \)                            # and the closing ")"
         /x;
    # Deal with the argument list
    $np_2=qr/
             (                             # We'll want this hence the
+ capturing ()
                 (?:                       #
                     [^'"(),]              #' not a ' " (  ) or ,
                     | (?:'(?:[^']|\')*?') #' a single quote string
                     | (?:"(?:[^"]|\")*?") #" a double quote string
                     | $np_1               # parenthesized expression 
+see above
                 )*
             )(,|\z)                       # termining , or \z
         /x;
  my $string=q{other stuff &COMPAREEQUAL(First-param.one,'(,',Third-pa
+ram); more stuff other stuff &COMPAREEQUAL(one(foo('bar'))+two(foobar
+),'(,',Third-param); more stuff dude() };
  ### $string
  while ($string =~ m/\b(\w+)\s*$np_1/g) {
        my ($subroutine_name,$argument_list)=($1,$2);
        ### $subroutine_name
        ### $argument_list
        while ($argument_list =~ m/$np_2/g and $1) {
            ### argument: $1
             };
         };
__END__

    [download]
    ### $string: 'other stuff &COMPAREEQUAL(First-param.one,\'(,\',Third-p
+aram); more stuff other stuff &COMPAREEQUAL(one(foo(\'bar\'))+two(foo
+bar),\'(,\',Third-param); more stuff dude() '

### $subroutine_name: 'COMPAREEQUAL'
### $argument_list: 'First-param.one,\'(,\',Third-param'

### argument: 'First-param.one'

### argument: '\'(,\''

### argument: 'Third-param'

### $subroutine_name: 'COMPAREEQUAL'
### $argument_list: 'one(foo(\'bar\'))+two(foobar),\'(,\',Third-param'

### argument: 'one(foo(\'bar\'))+two(foobar)'

### argument: '\'(,\''

### argument: 'Third-param'

### $subroutine_name: 'dude'
### $argument_list: ''

    [download]
[reply]
[d/l]
[select]

In Section Seekers of Perl Wisdom