0A ٠
# common formatting control
-ZS # ZWSP; capitals like other Cc
-ZN # ZWNJ; less obvious alt: 'Z
-ZW # ZWJ; ZJ somewhy used for tsadi; less obvious alt: "Z
-LR # LRM
-RL # RLM; keep rl for ɼ
+ZS \8203 # ZWSP; capitals like other Cc
+ZN \8204 # ZWNJ; less obvious alt: 'Z
+ZW \8205 # ZWJ; ZJ somewhy used for tsadi; less obvious alt: "Z
+LR \8206 # LRM
+RL \8207 # RLM; keep rl for ɼ
###
# under development or temporary
use warnings;
use open IN => ':utf8', ':std';
-our $VERSION = '1.01';
+our $VERSION = '1.02';
my $di = do "data/digraphs-rfc.inc.pl"
or warn "official digraphs not included for comparison: ", $@ // $!;
say "# automatically generated by $0";
say '+{';
for (readline) {
- my ($mnem, $chr) = m{^([!"%'-Z_a-z]{2}) (.)} or next;
+ my ($mnem, $cp, $chr) = m{^([!"%'-Z_a-z]{2}) (?:(\\\d+)|(.))} or next;
warn("$mnem already defined"), next if defined $di->{$mnem};
- my $chrstr = sprintf '"\x{%x}"', ord $chr;
+ my $chrstr = sprintf '"\x{%x}"', $cp // ord $chr;
say "q{$mnem} => $chrstr,";
}
say '}';