Re^4: Reliably parsing an integer (updated)

in reply to Re^3: Reliably parsing an integer
in thread Reliably parsing an integer

It's quite often possible to construct a regex to discriminate a number range, but this is usually more of an academic exercise than a practical solution.

Turns out to not be too difficult if you cheat a little with some embedded code ;-) (of course hippo's suggestion is a lot more elegant Update: if that's the limit one wants to implement)

use Config;
use Math::BigInt;

my $regex = do {
    my $max = eval $Config{nv_overflows_integers_at} or die;
    my $len1 = length($max) - 1;
    my $range = substr $max, 0, 1;
    $range = $range eq "1" ? "1" : "1-$range";
    qr{ \A (?: (?!0) [0-9]{1,$len1}
        | ( [$range] [0-9]{$len1} )
            (?(?{ Math::BigInt->new($^N)->bgt($max) })(*F))
    ) \z }x };
[download]

One difference to my first version is that this regex doesn't allow zero (0).

Update: Updated benchmark and faster version of the code here.

Tests

use warnings;
use strict;

use Config;
use Math::BigInt;

my $regex = do {
    my $max = eval $Config{nv_overflows_integers_at} or die;
    my $len1 = length($max) - 1;
    my $range = substr $max, 0, 1;
    $range = $range eq "1" ? "1" : "1-$range";
    qr{ \A (?: (?!0) [0-9]{1,$len1}
        | ( [$range] [0-9]{$len1} )
            (?(?{ Math::BigInt->new($^N)->bgt($max) })(*F))
    ) \z }x }; 

use Test::More;

diag explain $regex;

unlike 0, $regex;
  like 1, $regex;
  like 3, $regex;
unlike "", $regex;
unlike "x", $regex;
unlike "123y", $regex;
unlike -1, $regex;
unlike "-9999999999999999999999999999999", $regex;

my $x = eval($Config{nv_overflows_integers_at})-1;
like "$x", $regex, "max-1 ($x)";
$x++;
like "$x", $regex, "max works ($x)";
$x++;
unlike "$x", $regex, "max+1 fails ($x)";
$x+=1_000;
unlike "$x", $regex;

unlike "999999999999999999999999999999999999", $regex;

done_testing;
[download]

Benchmark (vs. my first version):

#!/usr/bin/env perl
use warnings;
use strict;
use Benchmark qw/cmpthese/;

use feature 'state';
use Carp;
use Math::BigInt;
use Config;
use Regexp::Common qw/number/;

sub validate_int {
    my $str = shift;
    state $max = Math::BigInt->new(
        eval $Config{nv_overflows_integers_at} );
    croak "not an integer"
        unless defined $str && $str=~/\A$RE{num}{int}\z/;
    my $num = Math::BigInt->new($str);
    croak "integer to small" if $num < 0;
    croak "integer too big" if $num > $max;
    return $num->numify;
}

sub validate_int2 {
    my $str = shift;
    state $regex = do {
        my $max = eval $Config{nv_overflows_integers_at} or die;
        my $len1 = length($max) - 1;
        my $range = substr $max, 0, 1;
        $range = $range eq "1" ? "1" : "1-$range";
        qr{ \A (?: (?!0) [0-9]{1,$len1}
            | ( [$range] [0-9]{$len1} )
                (?(?{ Math::BigInt->new($^N)->bgt($max) })(*F))
        ) \z }x };
    croak "bad integer" unless $str =~ $regex;
    return 0+$str;
}

my $max = eval($Config{nv_overflows_integers_at});

cmpthese(-1, {
    first => sub {
        validate_int(1)==1 or die;
        validate_int(999)==999 or die;
        validate_int($max-1)==$max-1 or die;
        validate_int($max)==$max or die;
        defined eval { validate_int($max+1) } and die;
    },
    second => sub {
        validate_int2(1)==1 or die;
        validate_int2(999)==999 or die;
        validate_int2($max-1)==$max-1 or die;
        validate_int2($max)==$max or die;
        defined eval { validate_int2($max+1) } and die;
    },
});

__END__

          Rate  first second
first   4403/s     --   -70%
second 14902/s   238%     --
[download]

Comment on Re^4: Reliably parsing an integer (updated) Select or Download Code

In Section Seekers of Perl Wisdom