#!/usr/bin/perl -w 
use strict;
use warnings;
#Convert annoying, worthless 'fullwidth' Latin-1 characters
#to their semi-sane normal ASCII counterparts

my(%codes,$wide,$ascii,$x);
#this is the land where the fullwidth latin-1 characters reside
for($x=65281;$x<65374;$x++){
    ($wide,$ascii) = make_codes($x);
    $codes{$wide} = $ascii;
}

while(<>){
    chomp;
    foreach my $utf(keys %codes){
        s/$utf/$codes{$utf}/g;
    }
    print $_."\n";
}


sub make_codes{
    my $ud = $_[0];
    my $from = ud_to_utf8hex($ud);
    #subtract 65248 to get the ASCII value
    my $to = ud_to_utf8hex($ud-65248); 
    return($from, $to);
}

sub ud_to_utf8hex{
    my $ud = $_[0];
    my ($b1,$b2,$b3);
    if($ud >= 0 && $ud <= 127){ #basic ASCII values don't need to be a
+ltered
        return(sprintf("%c",$ud));
    }elsif($ud >= 2048 && $ud <= 65535){ #valid for 2048 <= $ud <= 655
+35
        $b1 = 224 + sprintf("%d", ($ud/4096));
        $b2 = 128 + (($ud/64) % 64);
        $b3 = 128 + ($ud % 64);
    }

    return(sprintf("\\x\{%X\}\\x\{%X\}\\x\{%X\}",$b1,$b2,$b3));
}
[download]