use strict;
my $str = '1.0.0
1.0.0-alpha
1.0.0-alpha.1
1.0.0-0.3.7
1.0.0-x.7.z.92
1.0.0-alpha+001
1.0.0+20130313144700
1.0.0-beta+exp.sha.5114f85';
my $regex = qr/^ # Start of version string
\s* # Ignore leading whitespace
(?:v\.?)? # Optional "v" or "v." before the version
(?<major>\d+) \. (?<minor>\d+) \. (?<patch>\d+) # MAJOR.MINOR.PATCH
(?:- # Pre-release versions start with '-'
(?<pre> # Capture the pre-release identifier(s)
(?: # The PR rules are annoyingly tight
[0-9A-Za-z-] # No leading `0`, but a `0` on its own is fine
| # More than one character...
[1-9A-Za-z-][0-9A-Za-z-]* # ...means no leading zero
) # That's the FIRST pre-release identifier
(?: # Multiple are allowed...
\. # ...dot-separated...
(?: # ...with the same rules as above
[0-9A-Za-z-]
|
[1-9A-Za-z-][0-9A-Za-z-]*
)
)* # Of course, you can also have just the one
) # End name-cap group `pre`
)? # End non-cap group encompassing the leading `-` and the identifiers
(?: # Built metadata is SIMILAR, but with two differences:
\+ # Difference one: starts with `+`
(?<meta>
[0-9A-Za-z-]+ # Difference two: leading `0` is allowed, so the match rule is simpler
(?:\.[0-9A-Za-z-]+)* # Same dot-delim repetition
) # End name-cap group `meta`
)? # End non-cap group encompassing leading `+` and identifiers
\s* # Ignore trailing whitespace
$ # End version string/mixp;
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