#!/usr/bin/perl
# -*- cperl -*-

use utf8;
require "./db.pl";

my ($pack) = findrecord('pack', 'packname', 'gjiten');
die "You must create the gjiten pack first (and make sure its language is set correctly).\n" if not ref $pack;

my $packid = $$pack{id};
my $langid = $$pack{language};
my $userid = $$pack{user} || 1; # We guess that the first user is probably the sysadmin.

my ($category) = findrecord('category', 'name', 'word');
die "How can there be no word category?\n" if not ref $category;

my $catid = $$category{id};

my $dicfile = '/usr/share/gjiten/dics/edict';
open DIC,
  #'<:encoding(UTF-8)',
  '<',
  $dicfile or die "Cannot open dictionary: $dicfile";

my ($total, $skipped, $japanese, $already, $inserted);
while (<DIC>) {
  my $line = $_;
  my ($firstchar) = $line =~ /^(.)/;
  ++$total;
  if ($firstchar le '~') {
    ++$skipped;
    print "Skipping (starts with low character '$firstchar'): $line";
  } else {
    ++$japanese;
    die if $japanese > 50 or $total > 100;
    my ($word, @def) = split m{/}, $line;
    my ($spelling, $reading) = $word =~ /([^[ ]+) ?\s*(?:[[](.*?)[]])?/;
    my ($chars, @char) = $spelling;
    #while ($chars) {
    #  my ($c) = $chars =~ m/^(.)/;
    #  $chars =~ s/^(.)//;
    #  push @char, $c;
    #}
    #my @char = $spelling =~ m/(\X)/g;
    my @char = $spelling =~ m/(\P{M}\p{M}*)/g;
    use Data::Dumper;
    print Dumper(+{
                   word => $word,
                   spelling => $spelling,
                   reading  => $reading,
                   defs => \@def,
                   char => \@char,
                  });
  }
}

print "Of $total lines, skipped $skipped.\nFound $japanese Japanese words.
$already already had cards.\n$inserted new cards would be created.\n";