Hi Ken!

Here's my latest try. It may be of interest to you. This is full-on 5.10+ as I wanted to get away from the  (??{ ... }) construct with its scary warnings and experiment some more with the  (?PARNO) construct, and also with  (DEFINE), which I still don't fully understand. As you see, the  (DEFINE) version requires an extra grep step; I couldn't figure out how to avoid it. Also, definition of empty squares or curlies expanded to include unlimited whitespace. Tested under Strawberries 5.10.1.5 and 5.14.4.1. 

use 5.010;  # ++ possessive, (?PARNO), (DEFINE)
use strict;
use warnings;

use Test::More
  # tests => ?? + 1  # Test::NoWarnings adds 1 test
    'no_plan'
    ;
use Test::NoWarnings;


my $empty_curly  = qr{  { \s*  } }xms;
my $empty_square = qr{ \[ \s* \] }xms;
my $not_empty = qr{ (?! $empty_curly | $empty_square) }xms;

my $curly  = qr{ $not_empty  { (?: [^{}]  ++ | $empty_curly  | (?R) )+
+  } }xms;
my $square = qr{ $not_empty \[ (?: [^\[\]]++ | $empty_square | (?R) )+
+ \] }xms;

my $re1 = qr{ $curly | $square }xms;

my $re2 = qr{
    ( (?&SQUARE) | (?&CURLY) )           # works
  # (?<X>(?&SQUARE)) | (?<Y>(?&CURLY))   # works
  #      (?&SQUARE)  |      (?&CURLY)    # no
  #  (?: (?&SQUARE)  |      (?&CURLY) )  # no
    (?(DEFINE)
        (?<EMPTY_SQUARE> \[ \s* \] )
        (?<EMPTY_CURLY>   { \s*  } )
        (?<NOT_EMPTY> (?! (?&EMPTY_SQUARE) | (?&EMPTY_CURLY)))
        (?<SQUARE> (?&NOT_EMPTY) \[ (?: [^\[\]]++ | (?&EMPTY_SQUARE) |
+ (?R) )+ \] )
        (?<CURLY>  (?&NOT_EMPTY)  { (?: [^{}]  ++ | (?&EMPTY_CURLY)  |
+ (?R) )+  } )
        )
    }xms;


VECTOR:
for my $ar_vector (
    [ '...?[](...$[] = [ USER_ENTITY_NAME ], text${} = { this is a tes
+t })...',
      '[ USER_ENTITY_NAME ]', '{ this is a test }',
      ],
    [ 'a[] = a[ ] = a[  ] = [ this is a [ test ] { test2 } ]',
      '[ this is a [ test ] { test2 } ]',
      ],
    [ 'a{} = a{ } = a{  } = { this is a { test } [ test2 ] }',
      '{ this is a { test } [ test2 ] }',
      ],
    [ '{ a { b [ {}c{} ] d } e } = [ f [ g { []h[] } i ] j ]',
      '{ a { b [ {}c{} ] d } e }', '[ f [ g { []h[] } i ] j ]',
      ],
    [ '{}[]{ {}[] { } [ ] }[ ]{ } - [  ]{  }[ []{} [ ] { } ]{}[]',
      '{ {}[] { } [ ] }', '[ []{} [ ] { } ]',
      ],
    ) {

    my ($string, @expected) = @$ar_vector;

    is_deeply [ $string =~ m{ $re1 }xmsg ], \@expected,
      # qq{}
        ;

    is_deeply [ grep defined, $string =~ m{ $re2 }xmsg ],
              \@expected,
      # qq{}
        ;

    }  # end for VECTOR

[download]

In reply to Re^4: Regular expressions: Extracting certain text from a line by AnomalousMonk
in thread Regular expressions: Extracting certain text from a line by Wcool

Title:
Use:  <p> text here (a paragraph) </p>
and:  <code> code here </code>
to format your post, it's "PerlMonks-approved HTML":


  • Posts are HTML formatted. Put <p> </p> tags around your paragraphs. Put <code> </code> tags around your code and data!
  • Titles consisting of a single word are discouraged, and in most cases are disallowed outright.
  • Read Where should I post X? if you're not absolutely sure you're posting in the right place.
  • Please read these before you post! —
  • Posts may use any of the Perl Monks Approved HTML tags:
    a, abbr, b, big, blockquote, br, caption, center, col, colgroup, dd, del, details, div, dl, dt, em, font, h1, h2, h3, h4, h5, h6, hr, i, ins, li, ol, p, pre, readmore, small, span, spoiler, strike, strong, sub, summary, sup, table, tbody, td, tfoot, th, thead, tr, tt, u, ul, wbr
  • You may need to use entities for some characters, as follows. (Exception: Within code tags, you can put the characters literally.)
            For:     Use:
    & &amp;
    < &lt;
    > &gt;
    [ &#91;
    ] &#93;
  • Link using PerlMonks shortcuts! What shortcuts can I use for linking?
  • See Writeup Formatting Tips and other pages linked from there for more info.