use strict;
my $str = ' NATIONAL VOTERS\' REGISTER
ELECTORAL COMMISSION ACT, CAP(140)
NVR TEXT REGISTER FOR GENERAL ELECTIONS 2015/2016
DISTRICT : 12 JOI
CONSTITUENCY : 035 GRGR RT
SUB-COUNTY : 11 GHT
PARISH : 01 ATZ
POLLING STATION : 01 OT
TOTAL: 398
NO OF PAGES : 9
THE REPUBLIC
NATIONAL VOTERS\' REGISTER
ELECTORAL COMMISSION ACT, CAP(140)
NVR TEXT REGISTER FOR GENERAL ELECTIONS 2015/2016
DISTRICT : 12 JOI PARISH : 01 ATZ
CONSTITUENCY : 035 GRGR RT POLLING STATION : 01 OT
SUB-COUNTY : 11 GHT
VOTER NO SURNAME OTHERNAMES DOB SEX APPID/RECEIPT NO VILLAGE
57534676 AAA BBB 01-01-1965 M 0323830000V0C/CM5607 ABC
53276273 CCC DDD 28-07-1981 M 1074620203FUX/CM9007 TTR RR
TOTAL: 398 PAGE : 1 OF 9
THE REPUBLIC
NATIONAL VOTERS\' REGISTER
ELECTORAL COMMISSION ACT, CAP(140)
NVR TEXT REGISTER FOR GENERAL ELECTIONS 2015/2016
DISTRICT : 12 JOI PARISH : 01 ATZ
CONSTITUENCY : 035 GRGR RT POLLING STATION : 01 OT
SUB-COUNTY : 11 GHT
VOTER NO SURNAME OTHERNAMES DOB SEX APPID/RECEIPT NO VILLAGE
53390750 EEE FFF 18-04-1978 F 13238200006Z6/CF8507 TTR
60977834 GGG HHH 25-05-1979 F 1176520002RK4/CF1907 BREH';
my $regex = qr~^ \h*+
(?<VOTERNO> [0-9]+ ) \h+
(?<SURNAME> \S+ (?>\h\S+)*? ) \h{2,}
(?<OTHERNAMES> \S+ (?>\h\S+)*? ) \h{2,}
(?<DOB> [0-9]{2}-[0-9]{2}-[0-9]{4} ) \h+
(?<SEX> [FM] ) \h+
(?<APPID_RECNO> [0-9A-Z/]+ ) \h+
(?<VILLAGE> \S+ (?>\h\S+)* )
\h* $~mxp;
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