use strict;
my $str = 'GENESIS 1:1 In the beginning God created the heavens ... the ground. 2:7 And the LORD ... I buried Leah. 49:32 The purchase of the field and of the cave ... and he was put in a coffin in Egypt. EXODUS 1:1 Now these are the names ...';
my $regex = qr/\b(?:([A-Z]{2,})(?= \d+:\d)|\G(?!^))(?:(\d+):(\d+))?\s*((?:[^\dA-Z]+|\d++(?!:\d)|[A-Z](?![A-Z]+ \d+:\d))*)/mp;
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