use strict;
use warnings;


my $text=  <<TEXT;
    Those APCs are APC 282, 376, 377 and 398.
The APC assignments are also shown in attachment K1.
In the Final Rule, we indicated that clinical characteristics and
expected resource use.  Procedures are sufficiently similar to those
other procedures assigned to APC 282, 376, 377, and 398, and that
we believe those APC assignments were appropriate.
Specifically APCs 662 and APC 282. As shown in attachment K3 under
option number 1, to be placed in APC 662. Our data analysis shows
that combining services currently assigned to APC 662 would result
in an APC median cost of about 302. The 6 CPT-Codes that would go
into APC
662 are: CPT-Codes 0145T through 0150T. The two other cardiac CT
codes, specifically 0144T and 0151T would be assigned to APC 282.
The inclusion of the two codes into APC 282 would result in...
and also APC 101,102or103, and not 666.
But APC 6666 is not really an APC!
How about APC 6666, 777?  (Neither is parsed.)
How about APCs 777, 6666?  (Gets 777, ignores 6666; is this OK?)
TEXT


# define regex components

# an APC number
my $number = qr( \d{3} (?! \d ) )x;  # 3 digits, not followed by a digit

# required preamble to an APC number
my $preamble = do {
    my $leadin    = qr( APC s? )x;
    my $separator = qr( \s+ )x;
    qr( $leadin $separator )x;
    };

# additional APC numbers may follow after properly introduced number
my $continuation = do {
    my $comma  = qr( , )x;
    my $clause = qr( $comma? \s* (?: and | or ) )x;
    # \G means continue from point previous match ended
    qr( \G \s* (?: $comma | $clause ) \s* )x;
    };

# end regex component definitions


# do test extraction

my @extracts = 
    $text =~ m{ (?: $preamble | $continuation) ($number) }xg;

print "Extract $_ = $extracts[$_] \n" for 0 .. $#extracts;