use strict;
my $str = 'EVENLY BALANCED curly braces
{{{}}}
{ test1 { test2 { test3 { test4 } } } }
UNEVENLY BALANCED curly braces
{{{{}}} end <-- this is needed, otherwise this line balances with the line below :)
{ test1 { test2 { test3 { test4 } } } } }
MULTI-LINE EVENLY BALANCED curly braces
{
}
MULTI-LINE UNEVENLY BALANCED curly braces
{{
}
EVENLY BALANCED square braces
[ test1 [ test2 [ test3 [ test4 ] ] ] ]
EVENLY BALANCED square and curly braces
{ test1 [ test2 { test3 [ test4 ] } ] }
UNEVENLY BALANCED square and curly braces
{ test1 [ test2 { test3 [ test4 ] } } ]
';
my $regex = qr/(?(DEFINE)
(?<curly> \{ \g<content>*? \} )
(?<square> \[ \g<content>*? \] )
(?<pascal> \bbegin\b \g<content>*? \bend\b )
(?<lua> --\[ \g<content>*? --\] )
(?<nested> \g<curly> | \g<square> | \g<pascal> | \g<lua> )
(?<content>
# Math non-recursive content (atomically)
(?: (?! [{}\[\]] | \bbegin\b | \bend\b | --[\[\]] ) .)++
# Or recurse
| \g<nested>
)
)
\g<nested>/sxp;
if ( $str =~ /$regex/g ) {
print "Whole match is ${^MATCH} and its start/end positions can be obtained via \$-[0] and \$+[0]\n";
# print "Capture Group 1 is $1 and its start/end positions can be obtained via \$-[1] and \$+[1]\n";
# print "Capture Group 2 is $2 ... and so on\n";
}
# ${^POSTMATCH} and ${^PREMATCH} are also available with the use of '/p'
# Named capture groups can be called via $+{name}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Perl, please visit: http://perldoc.perl.org/perlre.html