[Chugalug] gedit vs geany

[Dan Lyke]

So there are things about this file that I'm not understanding, I
thought that the '.bla' starting a line was an ID, and the following
script shows a lot of duplicates of those, but a start on parsing this
might look like:

#!/usr/bin/perl -w
use warnings;
use strict;

open my $fh, '<', 'gnotes'
    || die "Unable to open gnotes";

my $generation;
my $generationDates;
my $people = {};

while (my $line = <$fh>)
{
    chomp $line;
    my $lineNumber = $.;

    if ($line =~ /^\s*\;.*?\s+GENERATION\s+(\d+)?/)
    {
        $generation = $1;
        $generationDates = undef;

        if ($line =~ /(\d{4})\-(\d{4})/)
        {
            $generationDates = [$1,$2];
        }
    }
    elsif ($line =~ /^\s*\;/)
    {
         # unrecognized comment line
    }
    elsif ($line =~ /^\.(\S*)\s+(.*?)?\s*\;\;/)
    {
         my ($id1, $lineageNotSure) = ($1,$2);
    my ($stuff, $name, $dates) = split /\;\;/, $line;
    my ($familyName, $maidenName);
    $familyName = $1 if ($name =~ /\/(\w+)\//);
    $maidenName = $1 if ($name =~ /\((\w+)\)/);

    if ($people->{$id1})
    {
            print "Duplicate ID at line $lineNumber: $line\n   was $people->{$i\
d1}->{line}\n";
    }
        else
    {
            $people->{$id1} =
            {
             line => $line,
             name => $name,
             dates => $dates,
             lineage => $lineageNotSure,
            };
    }
    }
    elsif ($line =~ /^\.(\S*)\s+(\(+.*?\))\s*(.*)/)
    {
        my ($id1, $lineageNotSure,$nameAndStuff) = ($1,$2,$3);

        if ($people->{$id1})
        {
            print "Duplicate ID at line $lineNumber: $line\n   was $people->{$i\
d1}->{line}\n";
        }
        else
        {
            $people->{$id1} =
            {
             line => $line,
             name => $nameAndStuff,
             lineage => $lineageNotSure,
            };
        }
    }
    elsif ($line !~ /^\s*$/)
    {
        print "Unrecognized line: $line\n";
    }
}