Simple converter from markdown-style _annotations_ to Unicode combining characters.

formatunicode.pl

#!/usr/bin/perl -C63

# Converts
#    The -quick- _brown_ =fox= ^jumps^ +over+ ~the~ @lazy@ dog.
# into
#    The q̶u̶i̶c̶k̶ b̲r̲o̲w̲n̲ f̳o̳x̳ j̅u̅m̅p̅s̅ o̱v̱e̱ṟ t̴h̴e̴ l̿a̿z̿y̿ dog.
#
# Implemented by Vitaly "_Vi" Shukela in 2016. Public domain / CC-0.

use strict;
use warnings;
use utf8;

$_=' '.(join ' ',@ARGV).' ';

sub interleave($$) {
    my $t=shift;
    my $r=shift;
    $t =~ s@\X@$&$r@g;
    return $t;
}

s@(?<=\s) \- (?=\w)   (.*?)   (?<=\w) \- (?=\s|$)@  interleave($1,pack("U*",0x0336))   @gex; # strikethough
s@(?<=\s) \~ (?=\w)   (.*?)   (?<=\w) \~ (?=\s|$)@  interleave($1,pack("U*",0x0334))   @gex; # tildethough
s@(?<=\s) \_ (?=\w)   (.*?)   (?<=\w) \_ (?=\s|$)@  interleave($1,pack("U*",0x0332))   @gex; # underline
s@(?<=\s) \= (?=\w)   (.*?)   (?<=\w) \= (?=\s|$)@  interleave($1,pack("U*",0x0333))   @gex; # double underline
s@(?<=\s) \+ (?=\w)   (.*?)   (?<=\w) \+ (?=\s|$)@  interleave($1,pack("U*",0x0331))   @gex; # dashed underline
s@(?<=\s) \^ (?=\w)   (.*?)   (?<=\w) \^ (?=\s|$)@  interleave($1,pack("U*",0x0305))   @gex; # overline
s@(?<=\s) \@ (?=\w)   (.*?)   (?<=\w) \@ (?=\s|$)@  interleave($1,pack("U*",0x033f))   @gex; # double overline


substr($_,0,1)='';
substr($_,-1,1)='';

print $_, "\n";