#!/usr/bin/perl
use strict;
use warnings;
use Data::Dumper;
$|=1;

# Don't read in another line if we are still working
# on a START line. This is caused by the
# X START Y syntax in conjunction with the idea
# of END absent a START in this example file format.

# As a thought redefining the input separtator to
# be 'START' could possibly be productive if the format
# is not exactly like this?,

# This format has some of the nastiest things to deal
# with. They normally do not occur all at once!


my @record=();
my $line_in ='';

while ( $line_in =~ /START/ or $line_in =<DATA>)
{      
    $line_in =  construct_record($line_in) if $line_in =~ /START/;
}


sub construct_record
{
    my $line = shift;
    
    if ( (my $x) = $line =~ /START\s+(\w+)\s*$/)
    {
       push @record, $x;
    }

    while (defined ($line = <DATA>) and ($line !~ /(START|END)/) )
    {
        $line =~ s/^\s*|\s*$//g;
        push @record, $line;
    }
    
    $line //= '';  #could be an EOF
  
    if (my ($b4end) = $line =~ /^ (?: (.+) \s+ )? END $/x)
    {
        push @record, $b4end if $b4end;
        output_record();
        return '';  # no continuation of this record
    } 
    if ( my ($x,$y) = $line =~ /^ (?: (.+) \s+ )? START (?: \s+ (.+) )? $/x )
    {
        if ($x)
        {
           push @record, $x; 
           output_record();  
        }
        if ($y)
        {
            output_record();  # might be: "^START 77"?
            return "START $y";
        }
     }   
     return '';
}

sub output_record  # or process it somehow...
{
    print "Record: @record\n" if (@record >1);
    @record=();
}

=Prints
Record: a b
Record: c d e f g
Record: h i
Record: j k
=cut


__DATA__
START
a
b
START c
d
e
f
g END
ignoreme
START h
i START j
k
END