} or warn "Could not include count for html entities: $@";
eval {
+ my $agemap = do 'unicode-age.inc.pl'
+ or warn "Could not include unicode version data: $!";
+
use Unicode::UCD 'charinfo';
for my $code (0 .. 256**2*2) {
my $charinfo = charinfo($code) or next;
next if $charinfo->{category} =~ /^[MC]/; # ignore Marks and "other" Control chars
push @{ $charlist{$_}->{ $charinfo->{$_} } }, chr $code
for qw( script category block );
+ push @{ $charlist{version}->{$_} }, (chr $code) x ($agemap->{$code} <= $_)
+ for 11, 30, 63;
}
1;
} or warn "Could not include unicode groups: $@";
say "# automatically generated by $0";
say 'use utf8;';
say '+', pp(\%charlist) =~ s{
- ( \[ \s* \d [^]]* ) ,\s* # arrays of numbers, excluding trailing comma
+ ( \[ \s* \d [^]]* ) ,\s* (?= \] ) # arrays of numbers, excluding trailing comma
}{ $1 =~ s/\s+//gr }msxgre; # strip whitespace
__END__