Converts from an English-like UTF-8 to ASCII

asciify.pl

#!/usr/bin/perl

use strict;
use warnings;

use Unicode::Normalize;

use open ":encoding(utf8)";
binmode STDIN, ":encoding(utf8)";
binmode STDOUT, ":encoding(ascii)";
binmode STDERR, ":encoding(utf8)";

while (<>) {
    # Smart quotes etc.
    s/\x{2013}/--/g;
    s/\x{2014}/--/g;
    s/\x{2018}/`/g;
    s/\x{2019}/'/g;
    s/\x{201c}/``/g;
    s/\x{201d}/''/g;
    # Unicode normalization.
    $_ = NFKD($_);
    # Removes diacritics so decomposed.
    s/\p{NonspacingMark}//g;
    # Ignores normalization problems.
    next if (/[^[:ascii:]]/);
    # Penn Treebank-ify the quotation characters.
    s/^\"/``/;
    s/([ (\[{<])"/$1``/g;
    s/"/''/g;
    print;
}