comment on

One often works with IP addresses in packed form which allows for a very efficient regex match:

sub is_private {
    my ($packed_ip) = @_;
    return $packed_ip =~ m{
        ^
        (?: \x0A             # 10.0.0.0/8
        |   \xAC[\x10-\x1F]  # 172.16.0.0/12
        |   \xC0\xA8         # 192.168.0.0/16
        )
    }x;
}
[download]

Test:

use strict;
use warnings;

use Socket qw( inet_aton );

sub is_private {
    my ($packed_ip) = @_;
    return $packed_ip =~ m{
        ^
        (?: \x0A             # 10.0.0.0/8
        |   \xAC[\x10-\x1F]  # 172.16.0.0/12
        |   \xC0\xA8         # 192.168.0.0/16
        )
    }x;
}

my $result = '';
for (qw(
    9.255.255.255    10.0.0.0     10.255.255.255   11.0.0.0
    172.15.255.255   172.16.0.0   172.31.255.255   172.32.0.0
    192.167.255.255  192.168.0.0  192.168.255.255  192.169.0.0
)) {
    my $packed_ip = inet_aton($_);
    $result .= is_private($packed_ip) ? 1 : 0;
}

print("got:    $result\n");
print("expect: ", "0110"x3, "\n");
[download]

got:    011001100110
expect: 011001100110
[download]

Update: Alternatives:

sub is_private {
    my ($packed_ip) = @_;
    return ($packed_ip & "\xFF\x00\x00\x00") eq "\x0A\x00\x00\x00"
        || ($packed_ip & "\xFF\xF0\x00\x00") eq "\xAC\x10\x00\x00"
        || ($packed_ip & "\xFF\xFF\x00\x00") eq "\xC0\xA8\x00\x00";
}
[download]

sub is_private {
    my $nummy_ip = unpack('N', shift);
    return ($nummy_ip & 0xFF000000) == 0x0A000000   # 10.0.0.0/8
        || ($nummy_ip & 0xFFF00000) == 0xAC100000   # 172.16.0.0/12
        || ($nummy_ip & 0xFFFF0000) == 0xC0A80000;  # 192.168.0.0/16
}
[download]

use Inline CPP => <<'__EOI__';

    // Assumes the arg had UTF8=0

    IV is_private(const char* packed_ip) {
        // XXX Alignment issues
        const U16& hi = *(const U16*)packed_ip;

        // The irrelevant branch will be optimised away.
        if (*(const U16*)("\x12\x34") == 0x1234) {
            // Little endian
            if (  hi == 0xC0A8
               || (hi & 0xFFF0) == 0xAC10
               || (hi & 0xFF00) == 0x0A00
            )
                return 1;
        } else {
            // Little endian
            if (  hi == 0xA8C0
               || (hi & 0xF0FF) == 0x10AC
               || (hi & 0x00FF) == 0x000A
            )
                return 1;
        }

        return 0;
    }

__EOI__
[download]

In reply to Re: Regexp: Private IP Addresses by ikegami
in thread Regexp: Private IP Addresses by Anonymous Monk

Are you posting in the right place? Check out Where do I post X? to know for sure.
Posts may use any of the Perl Monks Approved HTML tags. Currently these include the following:
<code> <a> <b> <big> <blockquote> <br /> <dd> <dl> <dt> <em> <font> <h1> <h2> <h3> <h4> <h5> <h6> <hr /> <i> <li> <nbsp> <ol> <p> <small> <strike> <strong> <sub> <sup> <table> <td> <th> <tr> <tt> <u> <ul>
Snippets of code should be wrapped in <code> tags not <pre> tags. In fact, <pre> tags should generally be avoided. If they must be used, extreme care should be taken to ensure that their contents do not have long lines (<70 chars), in order to prevent horizontal scrolling (and possible janitor intervention).
Want more info? How to link or How to display code and escape characters are good places to start.


The stupid question is the question not asked
	PerlMonks