use strict;
my $str = 'EVENLY BALANCED curly braces
{{{}}}
{ test1 { test2 { test3 { test4 } } } }
UNEVENLY BALANCED curly braces
{{{{}}}
{ 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 the opening and closing elements before the recursion occurs
(?(DEFINE)
(?<open_curly>\{)
(?<close_curly>\})
(?<open_square>\[)
(?<close_square>\])
(?P<open_pascal>(?i:\bbegin\b))
(?P<close_pascal>(?i:\bend\b))
(?P<open_lua>--\[)
(?P<close_lua>--\])
(?<open>\g'open_curly'|\g'open_square'|\g'open_pascal'|\g'open_lua')
(?<close>\g'close_curly'|\g'close_square'|\g'close_pascal'|\g'close_lua')
)
# Match the opening element
(\g'open'
(?>
# For recursion, don't match either the opening
# or closing element
(?!\g'open'|\g'close')(.)
|
# Recurse this captured pattern
(?-1)
)*
# Match the closing element
\g'close')
/xp;
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