use strict;
my $str = '2^10^ is 1024.
Space is not allowed:
P^a cat^
But it\'s ok if it is escaped
P^a\\ cat^
Line break is a no-no, even escaped
P^a\\
cat^
Hmm <sup>This is a Microsoft superscript!</sup>
H^2^0
text^a\\ superscript^
';
my $regex = qr/(?<sup_all>
(?:
(?<!\\)\^
(?<sup_text>
(?>\\[\^[:blank:]\h]|[^\^[:blank:]\h\v])*+
)
(?<!\\)\^
)
|
(?: # or the Microsoft way. Beurk
\<sup\>
(?<sup_text>
((?!\v).)+
)
\<\/sup\>
)
)/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