in reply to Re: date format string -> Reg Ex solution
in thread date format string -> Reg Ex solution

Incredible.

This is exactly the kind of thing I was looking for. It doesn't handle AM/PM, which important in my case. Below is my hacked version that supports AM/PM by using "pp" to designate this. This creates an exceptional case in the script, because before only numbers were accepted, so instead of just \d, I'm now matching against \dPpAaMm 

# test like this: perl this_script.pl '02/04/2003 06:30 PM'
use strict;
sub prepareFormat {
    my $format = shift;

    # TODO: check that only valid characters appear in the format
    # The logic should be: for any character A-Z in the format string,
    #   die if it's not one of: Y M D h m s p  

    my ($i, @order) = 0;
    my $num_chars  = 'YMDhms';
    $format =~ s/([$num_chars]+)(\?)?/ $order[$i++] = substr($1,0,1); 
+'('.('\d' x length($1))."$2)"/ge;

    # use "p" for AM/PM
    $format =~ s/pp/ $order[$i++] = substr('p',0,1); "(AM|PM)"/e;


    $format = qr/^(?:$format)$/;
    return [$format, \@order];
}

sub parseDate {
    my ($format, $date) = @_;
    my @data = ($date =~ $format->[0])
        or return;
    my %result;
    for(my $i = 0; $i <= $#data; $i++) {
        $result{$format->[1]->[$i]} ||= $data[$i];
    }

    $result{h} += 12 if ($result{p} eq 'PM' and $result{h} != 12);
    $result{h} = 0   if ($result{p} eq 'AM' and $result{h} == 12);


    return map $result{$_}, qw(Y M D h m s);
}

#my $format = prepareFormat ('YYYY/MM/DD');
#my $format = prepareFormat ('YYYY-DD-MM|YYYY-DD-M|YYYY-D-MM|YYYY-D-M'
+);
#my $format = prepareFormat ('YYYY-DD?-MM?');
#my $format = prepareFormat ('YYYY-DD?-MM? hh?:mm?');
#my $format = prepareFormat ('YYYY-DD?-MM? hh?:mm?(?::ss?)?');
#my $format = prepareFormat ('YYYY-DD?-MM?(?: hh?:mm?(?::ss?)?)?');
my $format = prepareFormat ('MM/DD/YYYY hh:mm pp');

    my ($year, $month, $day, $hour, $min, $sec) = parseDate($format, $
+ARGV[0])
        or print "\tNot in the right format!\n" and exit;
    print "Year: $year, Month: $month, Day: $day, Hour: $hour, Min: $m
+in, Sec: $sec\n";

[download]

-mark

Replies are listed 'Best First'.
Re: Re: Re: date format string -> Reg Ex solution
by Jenda (Abbot) on Apr 23, 2003 at 20:44 UTC

    First a tiny nit. substr('p',0,1); is better written as 'p' ;-)

    Next there is a potential problem. Your code works correctly only if the AM/PM is the last thing in the string. This may seem to be an unimportant restriction, but imagine the format was 'YYYY/MM/DD hh:mm pp|DD.MM.YYYY hh:mm pp'. In this case the indexes in @order will be incorrect!

    The solution is to process the 'pp' at the same time as the other characters: 

    use strict;
sub prepareFormat {
    my $format = shift;

    # TODO: check that only valid characters appear in the format
    # The logic should be: for any character A-Z in the format string,
    #   die if it's not one of: Y M D h m s p

    my ($i, @order) = 0;
    my $num_chars  = 'YMDhms';
    $format =~ s{([$num_chars]+|pp)(\?)?}{
        $order[$i++] = substr($1,0,1);
        if ($1 eq 'pp') {
            "(AM|PM|am|pm)"
        } else {
            '('.('\d' x length($1))."$2)"
        }
    }ge;

    $format = qr/^(?:$format)$/;
    return [$format, \@order];
}

sub parseDate {
    my ($format, $date) = @_;
    my @data = ($date =~ $format->[0])
        or return;
    my %result;
    for(my $i = 0; $i <= $#data; $i++) {
        $result{$format->[1]->[$i]} ||= $data[$i];
    }

    $result{h} += 12 if (uc($result{p}) eq 'PM' and $result{h} != 12);
    $result{h} = 0   if (uc($result{p}) eq 'AM' and $result{h} == 12);


    return map $result{$_}, qw(Y M D h m s);
}
...

    [download]

    Jenda
    Always code as if the guy who ends up maintaining your code will be a violent psychopath who knows where you live.
       -- Rick Osborne

    Edit by castaway: Closed small tag in signature

[reply]
[d/l]
[select]

In Section Seekers of Perl Wisdom