use strict;
my $str = '# The CMS, who maintain these codes, describe the format as:-
# "HCPCS Level II codes (also known as alpha-numeric codes) consist of a single alphabetical letter followed by 4 numeric digits."
# (https://www.cms.gov/medicare/coding-billing/healthcare-common-procedure-system)
# NOTE: This regex will not identify HCPCS Level I codes (AKA CPT codes)
# Also, some sources say the single letter ranges only from A-V (this regex follows A-Z)
# It\'s not clear if the first letter must be capitalized. This regex assumes not.
# This version of the regex matches optional modifiers (ie a hyphen then 2 characters after the code)
# (https://www.aapc.com/resources/what-are-medical-coding-modifiers)
# A separate regex has been created on regex101 that ignores modifiers
# Genuine code patterns
E8015
A6410
C5278
G2102
M1221
V2623
V2756
c5278
g2102
m1221
v2623
v2756
G2102-23
E8015-OK
V2756-L5
V2756-5Q
# Should fail
EE8015
6410
E641O
[6410
_6510
g212
C52789
G2101-
G2101-2
G2101-K
G2101-OKK
G2101-123
G2101-!!
G2101-!1
G2101-()';
my $regex = qr/^[a-zA-Z]\d{4}(-[a-zA-Z0-9]{2})?$/mp;
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