Okay, this is silly and I probably could have found a better way to spend the last couple hours but I was curious and surprised by Text::Unidecode’s lack of efficacy here so… (has to be <pre/> instead of <code/> tags because of content.)
Posting it because I do these things so rarely I’ll lose the memory of how to do it if I don’t. :P
#!/usr/bin/env perl
use 5.14.0; # Not sure this is earliest/best.
use utf8;
use strictures;
use open ":std", ":encoding(utf8)";
use Unicode::UCD "charinfo";
use charnames ":full";
use YAML; # For introspection if you're curious.
my @sex_and_porn = <DATA>;
for my $sap ( @sex_and_porn )
{
chomp $sap;
my @string;
for my $chr ( split "", $sap )
{
next unless $chr =~ /\A[[:print:]]+\z/;
my $info = charinfo(ord($chr));
# print Dump($info);
my $name = $info->{name};
next if $name =~ /COMBINING/;
my $replacement;
if ( $name =~ /\b(SMALL|CAPITAL)?(?: LETTER)?(?: TURNED| SHARP)? ([A-Z])\b/ )
{
no warnings "uninitialized";
my $case = $1 eq "SMALL" ? "SMALL" : "CAPITAL";
$replacement = "LATIN $case LETTER $2";
}
my $final = charnames::string_vianame( $replacement || $name );
push @string, $final =~ /(?:\b[A-Z]\b| )/i ?
$final : "\x{0}";
}
s/\x{0}+/[?]/g for @string;
printf " %15s -> %s\n\n", $sap, join "", @string;
}
__DATA__
s3x & pr0n
s̸͚͍̺̺͇̝̥͎͕̃e̸̲͆̅̈́̈̈́̆͆̀͆͘͜x̶̧̟̭̘̿̂̈́͝ ̷̨͇͓͖̅̄͑̓̕͝a̵̰̜̣͎͔͛͗̆̋̓n̸͍̳͍̤̊́͌͌͗͂͘d̵͇̱̣̈́̀͒͆̐͠͝ ̷̡͓̥̙͕̦͙̬̠͒̐ͅp̶̡̖̫̱̞̙͔͑̊͛͌̈́͘ô̷̫̰̫̹̘̖̪͙͌͋͗̓̓̂̿r̴͎͇͖̲̦̤͕̉n̸̘̝͇͌̂͒̈́͝
รєא คภ๔ ק๏гภ
ˢᵉˣ ᵃⁿᵈ ᵖᵒʳⁿ
𝚜𝚎𝚡 𝚊𝚗𝚍 𝚙𝚘𝚛𝚗
uɹod puɐ xǝs
🅂🄴🅇 🄰🄽🄳 🄿🄾🅁🄽
🎀 𝓈𝑒𝓍 𝒶𝓃𝒹 𝓅🍑𝓇𝓃 🎀
𝘀𝗲𝘅 𝗮𝗻𝗱 𝗽𝗼𝗿𝗻
ßêx and pørñ
ẞӬ𐊜 AƝḊ ⓅỚℝꞐ
Output–
s3x & pr0n -> s[?]x [?] pr[?]n
s̸͚͍̺̺͇̝̥͎͕̃e̸̲͆̅̈́̈̈́̆͆̀͆͘͜x̶̧̟̭̘̿̂̈́͝ ̷̨͇͓͖̅̄͑̓̕͝a̵̰̜̣͎͔͛͗̆̋̓n̸͍̳͍̤̊́͌͌͗͂͘d̵͇̱̣̈́̀͒͆̐͠͝ ̷̡͓̥̙͕̦͙̬̠͒̐ͅp̶̡̖̫̱̞̙͔͑̊͛͌̈́͘ô̷̫̰̫̹̘̖̪͙͌͋͗̓̓̂̿r̴͎͇͖̲̦̤͕̉n̸̘̝͇͌̂͒̈́͝ -> sex and porn
รєא คภ๔ ק๏гภ -> [?][?][?] [?][?][?] [?][?][?][?]
ˢᵉˣ ᵃⁿᵈ ᵖᵒʳⁿ -> sex and porn
𝚜𝚎𝚡 𝚊𝚗𝚍 𝚙𝚘𝚛𝚗 -> sex and porn
uɹod puɐ xǝs -> urod pua xes
🅂🄴🅇 🄰🄽🄳 🄿🄾🅁🄽 -> SEX AND PORN
🎀 𝓈𝑒𝓍 𝒶𝓃𝒹 𝓅🍑𝓇𝓃 🎀 -> [?] sex and p[?]rn [?]
𝘀𝗲𝘅 𝗮𝗻𝗱 𝗽𝗼𝗿𝗻 -> sex and porn
ßêx and pørñ -> sex and porn
ẞӬ𐊜 AƝḊ ⓅỚℝꞐ -> SEX AND PORN
In reply to Re^3: Bad Language In Contact Messages
by Your Mother
in thread Bad Language In Contact Messages
by Milti
| For: | Use: | ||
| & | & | ||
| < | < | ||
| > | > | ||
| [ | [ | ||
| ] | ] |