use strict;
my $str = '{1: Initial address, regex should say valid/match}
2001:0db8:0000:0000:0000:ff00:0042:8329
{2: After removing all leading zeroes, regex should say valid/match}
2001:db8:0:0:0:ff00:42:8329
{3: After omitting consecutive sections of zeroes, regex should say valid/match}
2001:db8::ff00:42:8329
{4: The loopback address, regex should say valid/match}
0000:0000:0000:0000:0000:0000:0000:0001
{5: The loopback address be abbreviated to ::1 by using both rules, regex should say valid/match}
::1
{6: This should be valid, regex should say valid/match}
ABCD:ABCD:ABCD:ABCD:ABCD:ABCD:192.168.158.190
{7: This should NOT be valid/match}
::
{These two formats allows IPv6 applications to communicate directly with IPv4 applications, regex should say valid/match}
{8}
0:0:0:0:0:ffff:192.1.56.10
{9}
::ffff:192.1.56.10/96
{These next two formats are used for tunneling. It allows IPv6 nodes to communicate across an IPv4 infrastructure, regex should say valid/match}
{10}
0:0:0:0:0:0:192.1.56.10
{11}
::192.1.56.10/96
{These 4 should be valid/match}
{12}
::FFFF:129.144.52.38
{13}
::129.144.52.38
{14}
::FFFF:d
{15}
1080:0:0:0:8:800:200C:417A
{These 4 should NOT be valid/match}
{16}
::FFFF:d.d.d
{17}
::FFFF:d.d
{18}
::d.d.d
{19}
::d.d';
my $regex = qr/(?:^|\s)(([0-9a-fA-F]{1,4}:){7}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,7}:|([0-9a-fA-F]{1,4}:){1,6}[0-9a-fA-F]{1,4}|([0-9a-fA-F]{1,4}:){1,5}(:[0-9a-fA-F]{1,4}){1,2}|([0-9a-fA-F]{1,4}:){1,4}(:[0-9a-fA-F]{1,4}){1,3}|([0-9a-fA-F]{1,4}:){1,3}(:[0-9a-fA-F]{1,4}){1,4}|([0-9a-fA-F]{1,4}:){1,2}(:[0-9a-fA-F]{1,4}){1,5}|[0-9a-fA-F]{1,4}:((:[0-9a-fA-F]{1,4}){1,6})|:((:[0-9a-fA-F]{1,4}){1,7}|:)|fe80:(:[0-9a-fA-F]{0,4}){0,4}%[0-9a-zA-Z]+|::(ffff(:0{1,4})?:)?((25[0-5]|2[0-4]\d|1\d{0,2}|[1-9]?\d)\.){3}(25[0-5]|2[0-4]\d|1\d{0,2}|[1-9]?\d)|([0-9a-fA-F]{1,4}:){1,4}:((25[0-5]|2[0-4]\d|1\d{0,2}|[1-9]?\d)\.){3}(25[0-5]|2[0-4]\d|1\d{0,2}|[1-9]?\d))(?=\s|$)
/imp;
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