6496588bbc
X bills a post containing a URL at a much higher rate than a plain post, and its algorithm demotes link posts. The X version of a post now rewrites every URL non-clickable (https://example.com/post becomes example(.)com/post): scheme and www. dropped, every dot of the host replaced with (.). Leaving a single dot intact would still leave a resolvable domain for X to detect, so all of them are broken. A scheme or www. proves a token is a URL on its own; a bare host only counts when its last label is a delegated TLD, which is the one thing telling acme.com apart from Node.js. That check runs against App\Support\LinkTlds, generated from the whole IANA root zone in every form a TLD can appear in a post -- ASCII, punycode and the Unicode it decodes to -- because whatever X links is what X bills, so a hand-picked subset would leave us paying for its gaps. If the regex engine bails out on pathological input the original content is returned instead of crashing the publisher. The transform lives in the Platform::X arm of ContentSanitizer, so it reaches publishing and the app/API/MCP previews from one place and cannot touch any other network. Off by default; opt in with X_DEFUSE_LINKS. The editor counts characters and renders its preview client-side and cannot ask the server on every keystroke, so the rewrite is mirrored in TypeScript. PHP stays the source of truth: a parity test fails if the two TLD sets drift, and a browser test drives the real editor so the mirror is covered rather than assumed. Without it the composer promised text the network never receives. Character limits now measure the text a reader will see: sanitized, then with markup resolved away. Measuring the raw draft blocked saving posts that publish fine and let through posts the network rejects, and counted the editor's HTML toward the limit. Measuring the sanitized form alone would have counted Telegram's escaped entities, rejecting messages Telegram accepts. Empty content is handled once inside the sanitizer instead of by a guard repeated at every call site.
211 lines
18 KiB
PHP
211 lines
18 KiB
PHP
<?php
|
||
|
||
declare(strict_types=1);
|
||
|
||
namespace App\Support;
|
||
|
||
use App\Services\Social\ContentSanitizer;
|
||
|
||
/**
|
||
* Every top-level domain delegated in the root zone, in each form it can appear in
|
||
* a post: ASCII, punycode (`xn--p1ai`) and the Unicode it decodes to (`рф`). This
|
||
* mirrors the list X's own link detection uses, and that parity is the point — a
|
||
* post X turns into a link is exactly a post X bills at the link rate, so a
|
||
* hand-picked subset would leave {@see ContentSanitizer}
|
||
* paying for its own gaps.
|
||
*
|
||
* Regenerate when TLDs are added or retired. Source of truth:
|
||
* https://data.iana.org/TLD/tlds-alpha-by-domain.txt — lowercase every entry and,
|
||
* for each `xn--` one, add `idn_to_utf8()` of it alongside.
|
||
*
|
||
* Snapshot: Version 2026082900, Last Updated Sat Aug 29 07:07:01 2026 UTC
|
||
*
|
||
* @var array<int, string>
|
||
*/
|
||
class LinkTlds
|
||
{
|
||
/** @var array<int, string> */
|
||
private const TLDS = [
|
||
'aaa', 'aarp', 'abb', 'abbott', 'abbvie', 'abc', 'able', 'abogado', 'abudhabi', 'ac', 'academy',
|
||
'accenture', 'accountant', 'accountants', 'aco', 'actor', 'ad', 'ads', 'adult', 'ae', 'aeg', 'aero',
|
||
'aetna', 'af', 'afl', 'africa', 'ag', 'agakhan', 'agency', 'ai', 'aig', 'airbus', 'airforce',
|
||
'airtel', 'akdn', 'al', 'alibaba', 'alipay', 'allfinanz', 'allstate', 'ally', 'alsace', 'alstom',
|
||
'am', 'amazon', 'americanexpress', 'americanfamily', 'amex', 'amfam', 'amica', 'amsterdam',
|
||
'analytics', 'android', 'anquan', 'anz', 'ao', 'aol', 'apartments', 'app', 'apple', 'aq',
|
||
'aquarelle', 'ar', 'arab', 'aramco', 'archi', 'army', 'arpa', 'art', 'arte', 'as', 'asda', 'asia',
|
||
'associates', 'at', 'athleta', 'attorney', 'au', 'auction', 'audi', 'audible', 'audio', 'auspost',
|
||
'author', 'auto', 'autos', 'aw', 'aws', 'ax', 'axa', 'az', 'azure', 'ba', 'baby', 'baidu',
|
||
'banamex', 'band', 'bank', 'bar', 'barcelona', 'barclaycard', 'barclays', 'barefoot', 'bargains',
|
||
'baseball', 'basketball', 'bauhaus', 'bayern', 'bb', 'bbc', 'bbt', 'bbva', 'bcg', 'bcn', 'bd', 'be',
|
||
'beats', 'beauty', 'beer', 'berlin', 'best', 'bestbuy', 'bet', 'bf', 'bg', 'bh', 'bharti', 'bi',
|
||
'bible', 'bid', 'bike', 'bing', 'bingo', 'bio', 'biz', 'bj', 'black', 'blackfriday', 'blockbuster',
|
||
'blog', 'bloomberg', 'blue', 'bm', 'bms', 'bmw', 'bn', 'bnpparibas', 'bo', 'boats', 'boehringer',
|
||
'bofa', 'bom', 'bond', 'boo', 'book', 'booking', 'bosch', 'bostik', 'boston', 'bot', 'boutique',
|
||
'box', 'br', 'bradesco', 'bridgestone', 'broadway', 'broker', 'brother', 'brussels', 'bs', 'bt',
|
||
'build', 'builders', 'business', 'buy', 'buzz', 'bv', 'bw', 'by', 'bz', 'bzh', 'ca', 'cab', 'cafe',
|
||
'cal', 'call', 'calvinklein', 'cam', 'camera', 'camp', 'canon', 'capetown', 'capital', 'capitalone',
|
||
'car', 'caravan', 'cards', 'care', 'career', 'careers', 'cars', 'casa', 'case', 'cash', 'casino',
|
||
'cat', 'catering', 'catholic', 'cba', 'cbn', 'cbre', 'cc', 'cd', 'center', 'ceo', 'cern', 'cf',
|
||
'cfa', 'cfd', 'cg', 'ch', 'chanel', 'channel', 'charity', 'chase', 'chat', 'cheap', 'chintai',
|
||
'christmas', 'chrome', 'church', 'ci', 'cipriani', 'circle', 'cisco', 'citadel', 'citi', 'citic',
|
||
'city', 'ck', 'cl', 'claims', 'cleaning', 'click', 'clinic', 'clinique', 'clothing', 'cloud',
|
||
'club', 'clubmed', 'cm', 'cn', 'co', 'coach', 'codes', 'coffee', 'college', 'cologne', 'com',
|
||
'commbank', 'community', 'company', 'compare', 'computer', 'comsec', 'condos', 'construction',
|
||
'consulting', 'contact', 'contractors', 'cooking', 'cool', 'coop', 'corsica', 'country', 'coupon',
|
||
'coupons', 'courses', 'cpa', 'cr', 'credit', 'creditcard', 'creditunion', 'cricket', 'crown', 'crs',
|
||
'cruise', 'cruises', 'cu', 'cuisinella', 'cv', 'cw', 'cx', 'cy', 'cymru', 'cyou', 'cz', 'dad',
|
||
'dance', 'data', 'date', 'dating', 'datsun', 'day', 'dclk', 'dds', 'de', 'deal', 'dealer', 'deals',
|
||
'degree', 'delivery', 'dell', 'deloitte', 'delta', 'democrat', 'dental', 'dentist', 'desi',
|
||
'design', 'dev', 'dhl', 'diamonds', 'diet', 'digital', 'direct', 'directory', 'discount',
|
||
'discover', 'dish', 'diy', 'dj', 'dk', 'dm', 'dnp', 'do', 'docs', 'doctor', 'dog', 'domains', 'dot',
|
||
'download', 'drive', 'dtv', 'dubai', 'dupont', 'durban', 'dvag', 'dvr', 'dz', 'earth', 'eat', 'ec',
|
||
'eco', 'edeka', 'edu', 'education', 'ee', 'eg', 'email', 'emerck', 'energy', 'engineer',
|
||
'engineering', 'enterprises', 'epson', 'equipment', 'er', 'ericsson', 'erni', 'es', 'esq', 'estate',
|
||
'et', 'eu', 'eurovision', 'eus', 'events', 'exchange', 'expert', 'exposed', 'express', 'extraspace',
|
||
'fage', 'fail', 'fairwinds', 'faith', 'family', 'fan', 'fans', 'farm', 'farmers', 'fashion', 'fast',
|
||
'fedex', 'feedback', 'ferrari', 'ferrero', 'fi', 'fidelity', 'fido', 'film', 'final', 'finance',
|
||
'financial', 'fire', 'firestone', 'firmdale', 'fish', 'fishing', 'fit', 'fitness', 'fj', 'fk',
|
||
'flickr', 'flights', 'flir', 'florist', 'flowers', 'fly', 'fm', 'fo', 'foo', 'food', 'football',
|
||
'ford', 'forex', 'forsale', 'forum', 'foundation', 'fox', 'fr', 'free', 'fresenius', 'frl',
|
||
'frogans', 'frontier', 'ftr', 'fujitsu', 'fun', 'fund', 'furniture', 'futbol', 'fyi', 'ga', 'gal',
|
||
'gallery', 'gallo', 'gallup', 'game', 'games', 'gap', 'garden', 'gay', 'gb', 'gbiz', 'gd', 'gdn',
|
||
'ge', 'gea', 'gent', 'genting', 'george', 'gf', 'gg', 'ggee', 'gh', 'gi', 'gift', 'gifts', 'gives',
|
||
'giving', 'gl', 'glass', 'gle', 'global', 'globo', 'gm', 'gmail', 'gmbh', 'gmo', 'gmx', 'gn',
|
||
'godaddy', 'gold', 'goldpoint', 'golf', 'goodyear', 'goog', 'google', 'gop', 'got', 'gov', 'gp',
|
||
'gq', 'gr', 'grainger', 'graphics', 'gratis', 'green', 'gripe', 'grocery', 'group', 'gs', 'gt',
|
||
'gu', 'gucci', 'guge', 'guide', 'guitars', 'guru', 'gw', 'gy', 'hair', 'hamburg', 'hangout', 'haus',
|
||
'hbo', 'hdfc', 'hdfcbank', 'health', 'healthcare', 'help', 'helsinki', 'here', 'hermes', 'hiphop',
|
||
'hisamitsu', 'hitachi', 'hiv', 'hk', 'hkt', 'hm', 'hn', 'hockey', 'holdings', 'holiday',
|
||
'homedepot', 'homegoods', 'homes', 'homesense', 'honda', 'horse', 'hospital', 'host', 'hosting',
|
||
'hot', 'hotels', 'hotmail', 'house', 'how', 'hr', 'hsbc', 'ht', 'hu', 'hughes', 'hyatt', 'hyundai',
|
||
'ibm', 'icbc', 'ice', 'icu', 'id', 'ie', 'ieee', 'ifm', 'ikano', 'il', 'im', 'imamat', 'imdb',
|
||
'immo', 'immobilien', 'in', 'inc', 'industries', 'infiniti', 'info', 'ing', 'ink', 'institute',
|
||
'insurance', 'insure', 'int', 'international', 'intuit', 'investments', 'io', 'ipiranga', 'iq',
|
||
'ir', 'irish', 'is', 'ismaili', 'ist', 'istanbul', 'it', 'itau', 'itv', 'jaguar', 'java', 'jcb',
|
||
'je', 'jeep', 'jetzt', 'jewelry', 'jio', 'jll', 'jm', 'jmp', 'jnj', 'jo', 'jobs', 'joburg', 'jot',
|
||
'joy', 'jp', 'jpmorgan', 'jprs', 'juegos', 'juniper', 'kaufen', 'kddi', 'ke', 'kerryhotels',
|
||
'kerryproperties', 'kfh', 'kg', 'kh', 'ki', 'kia', 'kids', 'kim', 'kindle', 'kitchen', 'kiwi', 'km',
|
||
'kn', 'koeln', 'komatsu', 'kosher', 'kp', 'kpmg', 'kpn', 'kr', 'krd', 'kred', 'kuokgroup', 'kw',
|
||
'ky', 'kyoto', 'kz', 'la', 'lacaixa', 'lamborghini', 'lamer', 'land', 'landrover', 'lanxess',
|
||
'lasalle', 'lat', 'latino', 'latrobe', 'law', 'lawyer', 'lb', 'lc', 'lds', 'lease', 'leclerc',
|
||
'lefrak', 'legal', 'lego', 'lexus', 'lgbt', 'li', 'lidl', 'life', 'lifeinsurance', 'lifestyle',
|
||
'lighting', 'like', 'lilly', 'limited', 'limo', 'lincoln', 'link', 'live', 'living', 'lk', 'llc',
|
||
'llp', 'loan', 'loans', 'locker', 'locus', 'lol', 'london', 'lotte', 'lotto', 'love', 'lpl',
|
||
'lplfinancial', 'lr', 'ls', 'lt', 'ltd', 'ltda', 'lu', 'lundbeck', 'luxe', 'luxury', 'lv', 'ly',
|
||
'ma', 'madrid', 'maif', 'maison', 'makeup', 'man', 'management', 'mango', 'map', 'market',
|
||
'marketing', 'markets', 'marriott', 'marshalls', 'mattel', 'mba', 'mc', 'mckinsey', 'md', 'me',
|
||
'med', 'media', 'meet', 'melbourne', 'meme', 'memorial', 'men', 'menu', 'merck', 'merckmsd', 'mg',
|
||
'mh', 'miami', 'microsoft', 'mil', 'mini', 'mint', 'mit', 'mitsubishi', 'mk', 'ml', 'mlb', 'mls',
|
||
'mm', 'mma', 'mn', 'mo', 'mobi', 'mobile', 'moda', 'moe', 'moi', 'mom', 'monash', 'money',
|
||
'monster', 'mormon', 'mortgage', 'moscow', 'moto', 'motorcycles', 'mov', 'movie', 'mp', 'mq', 'mr',
|
||
'ms', 'msd', 'mt', 'mtn', 'mtr', 'mu', 'museum', 'music', 'mv', 'mw', 'mx', 'my', 'mz', 'na', 'nab',
|
||
'nagoya', 'name', 'navy', 'nba', 'nc', 'ne', 'nec', 'net', 'netbank', 'netflix', 'network',
|
||
'neustar', 'new', 'news', 'next', 'nextdirect', 'nexus', 'nf', 'nfl', 'ng', 'ngo', 'nhk', 'ni',
|
||
'nico', 'nike', 'nikon', 'ninja', 'nissan', 'nissay', 'nl', 'no', 'nokia', 'norton', 'now',
|
||
'nowruz', 'nowtv', 'np', 'nr', 'nra', 'nrw', 'ntt', 'nu', 'nyc', 'nz', 'obi', 'observer', 'office',
|
||
'okinawa', 'olayan', 'olayangroup', 'ollo', 'om', 'omega', 'one', 'ong', 'onl', 'online', 'ooo',
|
||
'open', 'oracle', 'orange', 'org', 'organic', 'origins', 'osaka', 'otsuka', 'ott', 'ovh', 'pa',
|
||
'page', 'panasonic', 'paris', 'pars', 'partners', 'parts', 'party', 'pay', 'pccw', 'pe', 'pet',
|
||
'pf', 'pfizer', 'pg', 'ph', 'pharmacy', 'phd', 'philips', 'phone', 'photo', 'photography', 'photos',
|
||
'physio', 'pics', 'pictet', 'pictures', 'pid', 'pin', 'ping', 'pink', 'pioneer', 'pizza', 'pk',
|
||
'pl', 'place', 'play', 'playstation', 'plumbing', 'plus', 'pm', 'pn', 'pnc', 'pohl', 'poker',
|
||
'politie', 'porn', 'post', 'pr', 'praxi', 'press', 'prime', 'pro', 'prod', 'productions', 'prof',
|
||
'progressive', 'promo', 'properties', 'property', 'protection', 'pru', 'prudential', 'ps', 'pt',
|
||
'pub', 'pw', 'pwc', 'py', 'qa', 'qpon', 'quebec', 'quest', 'racing', 'radio', 're', 'read',
|
||
'realestate', 'realtor', 'realty', 'recipes', 'red', 'redumbrella', 'rehab', 'reise', 'reisen',
|
||
'reit', 'reliance', 'ren', 'rent', 'rentals', 'repair', 'report', 'republican', 'rest',
|
||
'restaurant', 'review', 'reviews', 'rexroth', 'rich', 'richardli', 'ricoh', 'ril', 'rio', 'rip',
|
||
'ro', 'rocks', 'rodeo', 'rogers', 'room', 'rs', 'rsvp', 'ru', 'rugby', 'ruhr', 'run', 'rw', 'rwe',
|
||
'ryukyu', 'sa', 'saarland', 'safe', 'safety', 'sakura', 'sale', 'salon', 'samsclub', 'samsung',
|
||
'sandvik', 'sandvikcoromant', 'sanofi', 'sap', 'sarl', 'sas', 'save', 'saxo', 'sb', 'sbi', 'sbs',
|
||
'sc', 'scb', 'schaeffler', 'schmidt', 'scholarships', 'school', 'schule', 'schwarz', 'science',
|
||
'scot', 'sd', 'se', 'search', 'seat', 'secure', 'security', 'seek', 'select', 'sener', 'services',
|
||
'seven', 'sew', 'sex', 'sexy', 'sfr', 'sg', 'sh', 'shangrila', 'sharp', 'shell', 'shia', 'shiksha',
|
||
'shoes', 'shop', 'shopping', 'shouji', 'show', 'si', 'silk', 'sina', 'singles', 'site', 'sj', 'sk',
|
||
'ski', 'skin', 'sky', 'skype', 'sl', 'sling', 'sm', 'smart', 'smile', 'sn', 'sncf', 'so', 'soccer',
|
||
'social', 'softbank', 'software', 'sohu', 'solar', 'solutions', 'song', 'sony', 'soy', 'spa',
|
||
'space', 'sport', 'spot', 'sr', 'srl', 'ss', 'st', 'stada', 'staples', 'star', 'statebank',
|
||
'statefarm', 'stc', 'stcgroup', 'stockholm', 'storage', 'store', 'stream', 'studio', 'study',
|
||
'style', 'su', 'sucks', 'supplies', 'supply', 'support', 'surf', 'surgery', 'suzuki', 'sv',
|
||
'swatch', 'swiss', 'sx', 'sy', 'sydney', 'systems', 'sz', 'tab', 'taipei', 'talk', 'taobao',
|
||
'target', 'tatamotors', 'tatar', 'tattoo', 'tax', 'taxi', 'tc', 'tci', 'td', 'tdk', 'team', 'tech',
|
||
'technology', 'tel', 'temasek', 'tennis', 'teva', 'tf', 'tg', 'th', 'thd', 'theater', 'theatre',
|
||
'tiaa', 'tickets', 'tienda', 'tips', 'tires', 'tirol', 'tj', 'tjmaxx', 'tjx', 'tk', 'tkmaxx', 'tl',
|
||
'tm', 'tmall', 'tn', 'to', 'today', 'tokyo', 'tools', 'top', 'toray', 'toshiba', 'total', 'tours',
|
||
'town', 'toyota', 'toys', 'tr', 'trade', 'trading', 'training', 'travel', 'travelers',
|
||
'travelersinsurance', 'trust', 'trv', 'tt', 'tube', 'tui', 'tunes', 'tushu', 'tv', 'tvs', 'tw',
|
||
'tz', 'ua', 'ubank', 'ubs', 'ug', 'uk', 'unicom', 'university', 'uno', 'uol', 'ups', 'us', 'uy',
|
||
'uz', 'va', 'vacations', 'vana', 'vanguard', 'vc', 've', 'vegas', 'ventures', 'verisign',
|
||
'vermögensberater', 'vermögensberatung', 'versicherung', 'vet', 'vg', 'vi', 'viajes', 'video',
|
||
'vig', 'viking', 'villas', 'vin', 'vip', 'virgin', 'visa', 'vision', 'viva', 'vivo', 'vlaanderen',
|
||
'vn', 'vodka', 'volvo', 'vote', 'voting', 'voto', 'voyage', 'vu', 'wales', 'walmart', 'walter',
|
||
'wang', 'wanggou', 'watch', 'watches', 'weather', 'weatherchannel', 'web', 'webcam', 'weber',
|
||
'website', 'wed', 'wedding', 'weibo', 'weir', 'wf', 'whoswho', 'wien', 'wiki', 'williamhill', 'win',
|
||
'windows', 'wine', 'winners', 'wme', 'woodside', 'work', 'works', 'world', 'wow', 'ws', 'wtc',
|
||
'wtf', 'xbox', 'xerox', 'xihuan', 'xin', 'xn--11b4c3d', 'xn--1ck2e1b', 'xn--1qqw23a', 'xn--2scrj9c',
|
||
'xn--30rr7y', 'xn--3bst00m', 'xn--3ds443g', 'xn--3e0b707e', 'xn--3hcrj9c', 'xn--3pxu8k',
|
||
'xn--42c2d9a', 'xn--45br5cyl', 'xn--45brj9c', 'xn--45q11c', 'xn--4dbrk0ce', 'xn--4gbrim',
|
||
'xn--54b7fta0cc', 'xn--55qw42g', 'xn--55qx5d', 'xn--5su34j936bgsg', 'xn--5tzm5g', 'xn--6frz82g',
|
||
'xn--6qq986b3xl', 'xn--80adxhks', 'xn--80ao21a', 'xn--80aqecdr1a', 'xn--80asehdb', 'xn--80aswg',
|
||
'xn--8y0a063a', 'xn--90a3ac', 'xn--90ae', 'xn--90ais', 'xn--9dbq2a', 'xn--9et52u', 'xn--9krt00a',
|
||
'xn--b4w605ferd', 'xn--bck1b9a5dre4c', 'xn--c1avg', 'xn--c2br7g', 'xn--cck2b3b', 'xn--cckwcxetd',
|
||
'xn--cg4bki', 'xn--clchc0ea0b2g2a9gcd', 'xn--czr694b', 'xn--czrs0t', 'xn--czru2d', 'xn--d1acj3b',
|
||
'xn--d1alf', 'xn--e1a4c', 'xn--eckvdtc9d', 'xn--efvy88h', 'xn--fct429k', 'xn--fhbei',
|
||
'xn--fiq228c5hs', 'xn--fiq64b', 'xn--fiqs8s', 'xn--fiqz9s', 'xn--fjq720a', 'xn--flw351e',
|
||
'xn--fpcrj9c3d', 'xn--fzc2c9e2c', 'xn--fzys8d69uvgm', 'xn--g2xx48c', 'xn--gckr3f0f', 'xn--gecrj9c',
|
||
'xn--gk3at1e', 'xn--h2breg3eve', 'xn--h2brj9c', 'xn--h2brj9c8c', 'xn--hxt814e', 'xn--i1b6b1a6a2e',
|
||
'xn--imr513n', 'xn--io0a7i', 'xn--j1aef', 'xn--j1amh', 'xn--j6w193g', 'xn--jlq480n2rg',
|
||
'xn--jvr189m', 'xn--kcrx77d1x4a', 'xn--kprw13d', 'xn--kpry57d', 'xn--kput3i', 'xn--l1acc',
|
||
'xn--lgbbat1ad8j', 'xn--mgb9awbf', 'xn--mgba3a3ejt', 'xn--mgba3a4f16a', 'xn--mgba7c0bbn0a',
|
||
'xn--mgbaam7a8h', 'xn--mgbab2bd', 'xn--mgbah1a3hjkrd', 'xn--mgbai9azgqp6j', 'xn--mgbayh7gpa',
|
||
'xn--mgbbh1a', 'xn--mgbbh1a71e', 'xn--mgbc0a9azcg', 'xn--mgbca7dzdo', 'xn--mgbcpq6gpa1a',
|
||
'xn--mgberp4a5d4ar', 'xn--mgbgu82a', 'xn--mgbi4ecexp', 'xn--mgbpl2fh', 'xn--mgbt3dhd',
|
||
'xn--mgbtx2b', 'xn--mgbx4cd0ab', 'xn--mix891f', 'xn--mk1bu44c', 'xn--mxtq1m', 'xn--ngbc5azd',
|
||
'xn--ngbe9e0a', 'xn--ngbrx', 'xn--node', 'xn--nqv7f', 'xn--nqv7fs00ema', 'xn--nyqy26a',
|
||
'xn--o3cw4h', 'xn--ogbpf8fl', 'xn--otu796d', 'xn--p1acf', 'xn--p1ai', 'xn--pgbs0dh', 'xn--pssy2u',
|
||
'xn--q7ce6a', 'xn--q9jyb4c', 'xn--qcka1pmc', 'xn--qxa6a', 'xn--qxam', 'xn--rhqv96g', 'xn--rovu88b',
|
||
'xn--rvc1e0am3e', 'xn--s9brj9c', 'xn--ses554g', 'xn--t60b56a', 'xn--tckwe', 'xn--tiq49xqyj',
|
||
'xn--unup4y', 'xn--vermgensberater-ctb', 'xn--vermgensberatung-pwb', 'xn--vhquv', 'xn--vuq861b',
|
||
'xn--w4r85el8fhu5dnra', 'xn--w4rs40l', 'xn--wgbh1c', 'xn--wgbl6a', 'xn--xhq521b',
|
||
'xn--xkc2al3hye2a', 'xn--xkc2dl3a5ee0h', 'xn--y9a3aq', 'xn--yfro4i67o', 'xn--ygbi2ammx',
|
||
'xn--zfr164b', 'xxx', 'xyz', 'yachts', 'yahoo', 'yamaxun', 'yandex', 'ye', 'yodobashi', 'yoga',
|
||
'yokohama', 'you', 'youtube', 'yt', 'yun', 'za', 'zappos', 'zara', 'zero', 'zip', 'zm', 'zone',
|
||
'zuerich', 'zw', 'ελ', 'ευ', 'бг', 'бел', 'дети', 'ею', 'католик', 'ком', 'мкд', 'мон', 'москва',
|
||
'онлайн', 'орг', 'рус', 'рф', 'сайт', 'срб', 'укр', 'қаз', 'հայ', 'ישראל', 'קום', 'ابوظبي',
|
||
'ارامكو', 'الاردن', 'البحرين', 'الجزائر', 'السعودية', 'العليان', 'المغرب', 'امارات', 'ایران',
|
||
'بارت', 'بازار', 'بيتك', 'بھارت', 'تونس', 'سودان', 'سورية', 'شبكة', 'عراق', 'عرب', 'عمان', 'فلسطين',
|
||
'قطر', 'كاثوليك', 'كوم', 'مصر', 'مليسيا', 'موريتانيا', 'موقع', 'همراه', 'پاکستان', 'ڀارت', 'कॉम',
|
||
'नेट', 'भारत', 'भारतम्', 'भारोत', 'संगठन', 'বাংলা', 'ভারত', 'ভাৰত', 'ਭਾਰਤ', 'ભારત', 'ଭାରତ',
|
||
'இந்தியா', 'இலங்கை', 'சிங்கப்பூர்', 'భారత్', 'ಭಾರತ', 'ഭാരതം', 'ලංකා', 'คอม', 'ไทย', 'ລາວ', 'გე',
|
||
'みんな', 'アマゾン', 'クラウド', 'グーグル', 'コム', 'ストア', 'セール', 'ファッション', 'ポイント', '世界', '中信', '中国', '中國', '中文网',
|
||
'亚马逊', '企业', '佛山', '信息', '健康', '八卦', '公司', '公益', '台湾', '台灣', '商城', '商店', '商标', '嘉里', '嘉里大酒店', '在线',
|
||
'大拿', '天主教', '娱乐', '家電', '广东', '微博', '慈善', '我爱你', '手机', '招聘', '政务', '政府', '新加坡', '新闻', '时尚', '書籍',
|
||
'机构', '淡马锡', '游戏', '澳門', '点看', '移动', '组织机构', '网址', '网店', '网站', '网络', '联通', '谷歌', '购物', '通販', '集团',
|
||
'電訊盈科', '飞利浦', '食品', '餐厅', '香格里拉', '香港', '닷넷', '닷컴', '삼성', '한국',
|
||
];
|
||
|
||
/**
|
||
* The whole set, for handing to a client that has to recognise links itself —
|
||
* the post editor counts characters and previews without a round trip. Shipping
|
||
* it from here keeps this class the only place the list is declared.
|
||
*
|
||
* @return array<int, string>
|
||
*/
|
||
public static function all(): array
|
||
{
|
||
return self::TLDS;
|
||
}
|
||
|
||
/**
|
||
* Whether the given label is a delegated top-level domain. Backed by a flipped
|
||
* lookup built once per process, so this stays O(1) across a whole post.
|
||
*/
|
||
public static function has(string $tld): bool
|
||
{
|
||
static $lookup = null;
|
||
|
||
$lookup ??= array_flip(self::TLDS);
|
||
|
||
return isset($lookup[mb_strtolower($tld)]);
|
||
}
|
||
}
|