Created
December 15, 2021 22:05
-
-
Save michaelbutler/a3176c4d14a6ec357d9b1ce9ce8b8b92 to your computer and use it in GitHub Desktop.
Handle confusable strings in PHP
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?php | |
$confusables = [ | |
'a' => '(@|⍺|a|𝐚|𝑎|𝒂|𝒶|𝓪|𝔞|𝕒|𝖆|𝖺|𝗮|𝘢|𝙖|𝚊|ɑ|α|𝛂|𝛼|𝜶|𝝰|𝞪|а|A|𝐀|𝐴|𝑨|𝒜|𝓐|𝔄|𝔸|𝕬|𝖠|𝗔|𝘈|𝘼|𝙰|Α|𝚨|𝛢|𝜜|𝝖|𝞐|А|Ꭺ|ᗅ|ꓮ|𖽀|𐊠)', | |
'b' => '(𝐛|𝑏|𝒃|𝒷|𝓫|𝔟|𝕓|𝖇|𝖻|𝗯|𝘣|𝙗|𝚋|Ƅ|Ь|Ꮟ|ᑲ|ᖯ|B|ℬ|𝐁|𝐵|𝑩|𝓑|𝔅|𝔹|𝕭|𝖡|𝗕|𝘉|𝘽|𝙱|Ꞵ|Β|𝚩|𝛣|𝜝|𝝗|𝞑|В|Ᏼ|ᗷ|ꓐ|𐊂|𐊡|𐌁)', | |
'c' => '(c|ⅽ|𝐜|𝑐|𝒄|𝒸|𝓬|𝔠|𝕔|𝖈|𝖼|𝗰|𝘤|𝙘|𝚌|ᴄ|ϲ|ⲥ|с|ꮯ|𐐽|🝌|𑣲|𑣩|C|Ⅽ|ℂ|ℭ|𝐂|𝐶|𝑪|𝒞|𝓒|𝕮|𝖢|𝗖|𝘊|𝘾|𝙲|Ϲ|Ⲥ|С|Ꮯ|ꓚ|𐊢|𐌂|𐐕|𐔜)', | |
'd' => '(ⅾ|ⅆ|𝐝|𝑑|𝒅|𝒹|𝓭|𝔡|𝕕|𝖉|𝖽|𝗱|𝘥|𝙙|𝚍|ԁ|Ꮷ|ᑯ|ꓒ|Ⅾ|ⅅ|𝐃|𝐷|𝑫|𝒟|𝓓|𝔇|𝔻|𝕯|𝖣|𝗗|𝘋|𝘿|𝙳|Ꭰ|ᗞ|ᗪ|ꓓ)', | |
'e' => '(℮|e|ℯ|ⅇ|𝐞|𝑒|𝒆|𝓮|𝔢|𝕖|𝖊|𝖾|𝗲|𝘦|𝙚|𝚎|ꬲ|е|ҽ|⋿|E|ℰ|𝐄|𝐸|𝑬|𝓔|𝔈|𝔼|𝕰|𝖤|𝗘|𝘌|𝙀|𝙴|Ε|𝚬|𝛦|𝜠|𝝚|𝞔|Е|ⴹ|Ꭼ|ꓰ|𑢦|𑢮|𐊆)', | |
'f' => '(𝐟|𝑓|𝒇|𝒻|𝓯|𝔣|𝕗|𝖋|𝖿|𝗳|𝘧|𝙛|𝚏|ꬵ|ꞙ|ſ|ẝ|ք|𝈓|ℱ|𝐅|𝐹|𝑭|𝓕|𝔉|𝔽|𝕱|𝖥|𝗙|𝘍|𝙁|𝙵|Ꞙ|Ϝ|𝟊|ᖴ|ꓝ|𑣂|𑢢|𐊇|𐊥|𐔥)', | |
'g' => '(g|ℊ|𝐠|𝑔|𝒈|𝓰|𝔤|𝕘|𝖌|𝗀|𝗴|𝘨|𝙜|𝚐|ɡ|ᶃ|ƍ|ց|𝐆|𝐺|𝑮|𝒢|𝓖|𝔊|𝔾|𝕲|𝖦|𝗚|𝘎|𝙂|𝙶|Ԍ|Ꮐ|Ᏻ|ꓖ)', | |
'h' => '(h|ℎ|𝐡|𝒉|𝒽|𝓱|𝔥|𝕙|𝖍|𝗁|𝗵|𝘩|𝙝|𝚑|һ|հ|Ꮒ|H|ℋ|ℌ|ℍ|𝐇|𝐻|𝑯|𝓗|𝕳|𝖧|𝗛|𝘏|𝙃|𝙷|Η|𝚮|𝛨|𝜢|𝝜|𝞖|Ⲏ|Н|Ꮋ|ᕼ|ꓧ|𐋏)', | |
'i' => '(˛|⍳|i|ⅰ|ℹ|ⅈ|𝐢|𝑖|𝒊|𝒾|𝓲|𝔦|𝕚|𝖎|𝗂|𝗶|𝘪|𝙞|𝚒|𝚤|ɪ|ɩ|ι|ι|ͺ|𝛊|𝜄|𝜾|𝝸|𝞲|і|ꙇ|ӏ|ꭵ|Ꭵ|𑣃)', | |
'j' => '(j|ⅉ|𝐣|𝑗|𝒋|𝒿|𝓳|𝔧|𝕛|𝖏|𝗃|𝗷|𝘫|𝙟|𝚓|ϳ|ј|J|𝐉|𝐽|𝑱|𝒥|𝓙|𝔍|𝕁|𝕵|𝖩|𝗝|𝘑|𝙅|𝙹|Ʝ|Ϳ|Ј|Ꭻ|ᒍ|ꓙ)', | |
'k' => '(𝐤|𝑘|𝒌|𝓀|𝓴|𝔨|𝕜|𝖐|𝗄|𝗸|𝘬|𝙠|𝚔|K|K|𝐊|𝐾|𝑲|𝒦|𝓚|𝔎|𝕂|𝕶|𝖪|𝗞|𝘒|𝙆|𝙺|Κ|𝚱|𝛫|𝜥|𝝟|𝞙|Ⲕ|К|Ꮶ|ᛕ|ꓗ|𐔘)', | |
'l' => '(Ɩ|ǀ|Ι|І|Ӏ|׀|ו|ן|ا|١|۱|ߊ|ᛁ|ℐ|ℑ|ℓ|Ⅰ|ⅼ|∣|⏽|Ⲓ|ⵏ|ꓲ|𐊊|𐌉|𐌠|𖼨|𝐈|𝐥|𝐼|𝑙|𝑰|𝒍|𝓁|𝓘|𝓵|𝔩|𝕀|𝕝|𝕴|𝖑|𝖨|𝗅|𝗜|𝗹|𝘐|𝘭|𝙄|𝙡|𝙸|𝚕|𝚰|𝛪|𝜤|𝝞|𝞘|𝟏|𝟙|𝟣|𝟭|𝟷|𞣇|𞸀|𞺀|🯱|ﺍ|ﺎ|I|l|│)', | |
'm' => '(ⅿ|𑜀|𑣣|𝐦|𝑚|𝒎|𝓂|𝓶|𝔪|𝕞|𝖒|𝗆|𝗺|𝘮|𝙢|𝚖|Μ|Ϻ|М|Ꮇ|ᗰ|ᛖ|ℳ|Ⅿ|Ⲙ|ꓟ|𐊰|𐌑|𝐌|𝑀|𝑴|𝓜|𝔐|𝕄|𝕸|𝖬|𝗠|𝘔|𝙈|𝙼|𝚳|𝛭|𝜧|𝝡|𝞛|M)', | |
'n' => '(𝐧|𝑛|𝒏|𝓃|𝓷|𝔫|𝕟|𝖓|𝗇|𝗻|𝘯|𝙣|𝚗|ո|ռ|N|ℕ|𝐍|𝑁|𝑵|𝒩|𝓝|𝔑|𝕹|𝖭|𝗡|𝘕|𝙉|𝙽|Ν|𝚴|𝛮|𝜨|𝝢|𝞜|Ⲛ|ꓠ|𐔓)', | |
'o' => '(ం|ಂ|ം|ං|०|੦|૦|௦|౦|೦|൦|๐|໐|၀|٥|۵|o|ℴ|𝐨|𝑜|𝒐|𝓸|𝔬|𝕠|𝖔|𝗈|𝗼|𝘰|𝙤|𝚘|ᴏ|ᴑ|ꬽ|ο|𝛐|𝜊|𝝄|𝝾|𝞸|σ|𝛔|𝜎|𝝈|𝞂|𝞼|ⲟ|о|ჿ|օ|ס|ه|𞸤|𞹤|𞺄|ﻫ|ﻬ|ﻪ|ﻩ|ھ|ﮬ|ﮭ|ﮫ|ﮪ|ہ|ﮨ|ﮩ|ﮧ|ﮦ|ە|ഠ|ဝ|𐓪|𑣈|𑣗|𐐬|0|߀|০|୦|〇|𑓐|𑣠|𝟎|𝟘|𝟢|𝟬|𝟶|O|𝐎|𝑂|𝑶|𝒪|𝓞|𝔒|𝕆|𝕺|𝖮|𝗢|𝘖|𝙊|𝙾|Ο|𝚶|𝛰|𝜪|𝝤|𝞞|Ⲟ|О|Օ|ⵔ|ዐ|ଠ|𐓂|ꓳ|𑢵|𐊒|𐊫|𐐄|𐔖)', | |
'p' => '(⍴|p|𝐩|𝑝|𝒑|𝓅|𝓹|𝔭|𝕡|𝖕|𝗉|𝗽|𝘱|𝙥|𝚙|ρ|ϱ|𝛒|𝛠|𝜌|𝜚|𝝆|𝝔|𝞀|𝞎|𝞺|𝟈|ⲣ|р|P|ℙ|𝐏|𝑃|𝑷|𝒫|𝓟|𝔓|𝕻|𝖯|𝗣|𝘗|𝙋|𝙿|Ρ|𝚸|𝛲|𝜬|𝝦|𝞠|Ⲣ|Р|Ꮲ|ᑭ|ꓑ|𐊕)', | |
'q' => '(𝐪|𝑞|𝒒|𝓆|𝓺|𝔮|𝕢|𝖖|𝗊|𝗾|𝘲|𝙦|𝚚|ԛ|գ|զ|ℚ|𝐐|𝑄|𝑸|𝒬|𝓠|𝔔|𝕼|𝖰|𝗤|𝘘|𝙌|𝚀|ⵕ)', | |
'r' => '(𝐫|𝑟|𝒓|𝓇|𝓻|𝔯|𝕣|𝖗|𝗋|𝗿|𝘳|𝙧|𝚛|ꭇ|ꭈ|ᴦ|ⲅ|г|ꮁ|𝈖|ℛ|ℜ|ℝ|𝐑|𝑅|𝑹|𝓡|𝕽|𝖱|𝗥|𝘙|𝙍|𝚁|Ʀ|Ꭱ|Ꮢ|𐒴|ᖇ|ꓣ|𖼵)', | |
's' => '(s|𝐬|𝑠|𝒔|𝓈|𝓼|𝔰|𝕤|𝖘|𝗌|𝘀|𝘴|𝙨|𝚜|ꜱ|ƽ|ѕ|ꮪ|𑣁|𐑈|S|𝐒|𝑆|𝑺|𝒮|𝓢|𝔖|𝕊|𝕾|𝖲|𝗦|𝘚|𝙎|𝚂|Ѕ|Տ|Ꮥ|Ꮪ|ꓢ|𖼺|𐊖|𐐠)', | |
't' => '(𝐭|𝑡|𝒕|𝓉|𝓽|𝔱|𝕥|𝖙|𝗍|𝘁|𝘵|𝙩|𝚝|⊤|⟙|🝨|T|𝐓|𝑇|𝑻|𝒯|𝓣|𝔗|𝕋|𝕿|𝖳|𝗧|𝘛|𝙏|𝚃|Τ|𝚻|𝛵|𝜯|𝝩|𝞣|Ⲧ|Т|Ꭲ|ꓔ|𖼊|𑢼|𐊗|𐊱|𐌕)', | |
'u' => '(𝐮|𝑢|𝒖|𝓊|𝓾|𝔲|𝕦|𝖚|𝗎|𝘂|𝘶|𝙪|𝚞|ꞟ|ᴜ|ꭎ|ꭒ|ʋ|υ|𝛖|𝜐|𝝊|𝞄|𝞾|ս|𐓶|𑣘|∪|⋃|𝐔|𝑈|𝑼|𝒰|𝓤|𝔘|𝕌|𝖀|𝖴|𝗨|𝘜|𝙐|𝚄|Ս|ሀ|𐓎|ᑌ|ꓴ|𖽂|𑢸)', | |
'v' => '(∨|⋁|v|ⅴ|𝐯|𝑣|𝒗|𝓋|𝓿|𝔳|𝕧|𝖛|𝗏|𝘃|𝘷|𝙫|𝚟|ᴠ|ν|𝛎|𝜈|𝝂|𝝼|𝞶|ѵ|ט|𑜆|ꮩ|𑣀|𝈍|٧|۷|Ⅴ|𝐕|𝑉|𝑽|𝒱|𝓥|𝔙|𝕍|𝖁|𝖵|𝗩|𝘝|𝙑|𝚅|Ѵ|ⴸ|Ꮩ|ᐯ|ꛟ|ꓦ|𖼈|𑢠|𐔝)', | |
'w' => '(ɯ|ѡ|ԝ|ա|ᴡ|ꮃ|𑜊|𑜎|𑜏|𝐰|𝑤|𝒘|𝓌|𝔀|𝔴|𝕨|𝖜|𝗐|𝘄|𝘸|𝙬|𝚠|Ԝ|Ꮃ|Ꮤ|ꓪ|𑣦|𑣯|𝐖|𝑊|𝑾|𝒲|𝓦|𝔚|𝕎|𝖂|𝖶|𝗪|𝘞|𝙒|𝚆)', | |
'x' => '(᙮|×|⤫|⤬|⨯|x|ⅹ|𝐱|𝑥|𝒙|𝓍|𝔁|𝔵|𝕩|𝖝|𝗑|𝘅|𝘹|𝙭|𝚡|х|ᕁ|ᕽ|᙭|╳|𐌢|𑣬|X|Ⅹ|𝐗|𝑋|𝑿|𝒳|𝓧|𝔛|𝕏|𝖃|𝖷|𝗫|𝘟|𝙓|𝚇|Ꭓ|Χ|𝚾|𝛸|𝜲|𝝬|𝞦|Ⲭ|Х|ⵝ|ᚷ|ꓫ|𐊐|𐊴|𐌗|𐔧)', | |
'y' => '(ɣ|ᶌ|y|𝐲|𝑦|𝒚|𝓎|𝔂|𝔶|𝕪|𝖞|𝗒|𝘆|𝘺|𝙮|𝚢|ʏ|ỿ|ꭚ|γ|ℽ|𝛄|𝛾|𝜸|𝝲|𝞬|у|ү|ყ|𑣜|Y|𝐘|𝑌|𝒀|𝒴|𝓨|𝔜|𝕐|𝖄|𝖸|𝗬|𝘠|𝙔|𝚈|Υ|ϒ|𝚼|𝛶|𝜰|𝝪|𝞤|Ⲩ|У|Ү|Ꭹ|Ꮍ|ꓬ|𖽃|𑢤|𐊲)', | |
'z' => '(𝐳|𝑧|𝒛|𝓏|𝔃|𝔷|𝕫|𝖟|𝗓|𝘇|𝘻|𝙯|𝚣|ᴢ|ꮓ|𑣄|𐋵|𑣥|Z|ℤ|ℨ|𝐙|𝑍|𝒁|𝒵|𝓩|𝖅|𝖹|𝗭|𝘡|𝙕|𝚉|Ζ|𝚭|𝛧|𝜡|𝝛|𝞕|Ꮓ|ꓜ|𑢩)', | |
]; | |
// Input obfuscated string | |
$string = '𝒇ᴦ℮℮𝐩०𝙧𝕟'; | |
$string = mb_strtolower($string, 'UTF-8'); | |
// Fairly intensive technique to convert an obfuscated string back into plain ASCII | |
foreach ($confusables as $replacement => $regex) { | |
$string = preg_replace("~$regex~u", $replacement, $string); | |
} | |
echo $string . "\n"; // outputs "freeporn" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment