Re: Adaptive parser for tab delimited text file

[roboticus]

reaper9187:

If you don't mind storing your data in a hash, it doesn't have to be adaptive. Instead you can parse the line pairs as hash keys & values respectively. Something like this:

$ cat t.pl
#!/usr/bin/perl
use strict;
use warnings;
use Data::Dumper;

my %CELLS;
my $tmp;
my $curCELL;
my $curCELLR;
while (<DATA>) {
    # skip blank lines
    next if /^\s*$/;

    # Line isn't empty, so current line is a list of field names
    # and the next line is a list of the values
    my @names = split /\s+/, $_;
    my @values = split /\s+/, <DATA>;

    $curCELL  = $values[0] if $names[0] eq 'CELL';
    $curCELLR = $values[0] if $names[0] eq 'CELLR';

    # Store the name/value pairs (if we have both keys)
    next unless defined $curCELL and defined $curCELLR;

    @{$CELLS{$curCELL}{$curCELLR}}{@names} = @values;
}

print Dumper(\%CELLS);

__DATA__
NEIGHBOUR RELATION DATA

CELL
LUC325C

CELLR     DIR     CAND   CS
LUC325B   MUTUAL  BOTH   NO

KHYST   KOFFSETP  KOFFSETN   LHYST   LOFFSETP  LOFFSETN
 3       0                    3       0

TRHYST  TROFFSETP  TROFFSETN  AWOFFSET  BQOFFSET
 2       0                     5         3

HIHYST  LOHYST  OFFSETP  OFFSETN  BQOFFSETAFR
 5       3       0                 3

CELLR     DIR     CAND   CS
LUC116A   MUTUAL  BOTH   NO

KHYST   KOFFSETP  KOFFSETN   LHYST   LOFFSETP  LOFFSETN
 3       0                    3       0

TRHYST  TROFFSETP  TROFFSETN  AWOFFSET  BQOFFSET
 2       0                     5         3

HIHYST  LOHYST  OFFSETP  OFFSETN  BQOFFSETAFR
 5       3       0                 3

CELLR     DIR     CAND   CS
LUC204A   MUTUAL  BOTH   NO

KHYST   KOFFSETP  KOFFSETN   LHYST   LOFFSETP  LOFFSETN
 3       0                    3       0

TRHYST  TROFFSETP  TROFFSETN  AWOFFSET  BQOFFSET
 2       0                     5         3

HIHYST  LOHYST  OFFSETP  OFFSETN  BQOFFSETAFR
 5       3       0                 3

CELL
LUC082B

When I run it, I get the following:

$ perl t.pl
$VAR1 = {
          'LUC325C' => {
                         'LUC204A' => {
                                        'KHYST' => '',
                                        'OFFSETN' => '0',
                                        'TROFFSETN' => '0',
                                        'OFFSETP' => '3',
                                        'LOFFSETN' => undef,
                                        'DIR' => 'MUTUAL',
                                        'LOHYST' => '5',
                                        'LHYST' => '3',
                                        'CAND' => 'BOTH',
                                        'BQOFFSET' => '3',
                                        'LOFFSETP' => '0',
                                        'CELLR' => 'LUC204A',
                                        'KOFFSETN' => '0',
                                        'KOFFSETP' => '3',
                                        'TRHYST' => '',
                                        'HIHYST' => '',
                                        'CS' => 'NO',
                                        'AWOFFSET' => '5',
                                        'BQOFFSETAFR' => '3',
                                        'TROFFSETP' => '2'
                                      },
                         'LUC116A' => {
                                        'KHYST' => '',
                                        'OFFSETN' => '0',
                                        'TROFFSETN' => '0',
                                        'OFFSETP' => '3',
                                        'LOFFSETN' => undef,
                                        'DIR' => 'MUTUAL',
                                        'LOHYST' => '5',
                                        'LHYST' => '3',
                                        'CAND' => 'BOTH',
                                        'BQOFFSET' => '3',
                                        'LOFFSETP' => '0',
                                        'CELLR' => 'LUC116A',
                                        'KOFFSETN' => '0',
                                        'KOFFSETP' => '3',
                                        'TRHYST' => '',
                                        'HIHYST' => '',
                                        'CS' => 'NO',
                                        'AWOFFSET' => '5',
                                        'BQOFFSETAFR' => '3',
                                        'TROFFSETP' => '2'
                                      },
                         'LUC325B' => {
                                        'KHYST' => '',
                                        'OFFSETN' => '0',
                                        'TROFFSETN' => '0',
                                        'OFFSETP' => '3',
                                        'LOFFSETN' => undef,
                                        'DIR' => 'MUTUAL',
                                        'LOHYST' => '5',
                                        'LHYST' => '3',
                                        'CAND' => 'BOTH',
                                        'BQOFFSET' => '3',
                                        'LOFFSETP' => '0',
                                        'CELLR' => 'LUC325B',
                                        'KOFFSETN' => '0',
                                        'KOFFSETP' => '3',
                                        'TRHYST' => '',
                                        'HIHYST' => '',
                                        'CS' => 'NO',
                                        'AWOFFSET' => '5',
                                        'BQOFFSETAFR' => '3',
                                        'TROFFSETP' => '2'
                                      }
                       },
          'LUC082B' => {
                         'LUC204A' => {
                                        'CELL' => 'LUC082B'
                                      }
                       }
        };

$

...roboticus

When your only tool is a hammer, all problems look like your thumb.