| 1 | <?php |
| 2 | |
| 3 | namespace wcf\system\bbcode; |
| 4 | |
| 5 | use wcf\data\smiley\Smiley; |
| 6 | use wcf\data\smiley\SmileyCache; |
| 7 | use wcf\system\event\EventHandler; |
| 8 | use wcf\system\SingletonFactory; |
| 9 | use wcf\util\StringUtil; |
| 10 | |
| 11 | /** |
| 12 | * Parses urls and smilies in simple messages. |
| 13 | * |
| 14 | * @author Marcel Werk |
| 15 | * @copyright 2001-2019 WoltLab GmbH |
| 16 | * @license GNU Lesser General Public License <http://opensource.org/licenses/lgpl-license.php> |
| 17 | */ |
| 18 | class SimpleMessageParser extends SingletonFactory |
| 19 | { |
| 20 | /** |
| 21 | * forbidden characters |
| 22 | * @var string |
| 23 | */ |
| 24 | protected static $illegalChars = '[^\x0-\x2C\x2E\x2F\x3A-\x40\x5B-\x60\x7B-\x7F]+'; |
| 25 | |
| 26 | /** |
| 27 | * list of smilies |
| 28 | * @var Smiley[] |
| 29 | */ |
| 30 | protected $smilies = []; |
| 31 | |
| 32 | /** |
| 33 | * cached URLs |
| 34 | * @var string[] |
| 35 | */ |
| 36 | protected $cachedURLs = []; |
| 37 | |
| 38 | /** |
| 39 | * cached e-mails |
| 40 | * @var string[] |
| 41 | */ |
| 42 | protected $cachedEmails = []; |
| 43 | |
| 44 | /** |
| 45 | * currently parsed message |
| 46 | * @var string |
| 47 | */ |
| 48 | public $message = ''; |
| 49 | |
| 50 | /** |
| 51 | * @inheritDoc |
| 52 | */ |
| 53 | protected function init() |
| 54 | { |
| 55 | parent::init(); |
| 56 | |
| 57 | if (MODULE_SMILEY == 1) { |
| 58 | // get smilies |
| 59 | $smilies = SmileyCache::getInstance()->getSmilies(); |
| 60 | $categories = SmileyCache::getInstance()->getCategories(); |
| 61 | foreach ($smilies as $categoryID => $categorySmilies) { |
| 62 | if ($categories[$categoryID ?: null]->isDisabled) { |
| 63 | continue; |
| 64 | } |
| 65 | |
| 66 | /** @var Smiley $smiley */ |
| 67 | foreach ($categorySmilies as $smiley) { |
| 68 | foreach ($smiley->smileyCodes as $smileyCode) { |
| 69 | $this->smilies[$smileyCode] = $smiley->getHtml(); |
| 70 | } |
| 71 | } |
| 72 | } |
| 73 | \krsort($this->smilies); |
| 74 | } |
| 75 | } |
| 76 | |
| 77 | /** |
| 78 | * Parses the given message and returns the parsed message. |
| 79 | * |
| 80 | * @param string $message |
| 81 | * @param bool $parseURLs |
| 82 | * @param bool $parseSmilies |
| 83 | * @return string |
| 84 | */ |
| 85 | public function parse($message, $parseURLs = true, $parseSmilies = true) |
| 86 | { |
| 87 | $this->message = $message; |
| 88 | $this->cachedURLs = $this->cachedEmails = []; |
| 89 | |
| 90 | // call event |
| 91 | EventHandler::getInstance()->fireAction($this, 'beforeParsing'); |
| 92 | |
| 93 | // parse urls |
| 94 | if ($parseURLs) { |
| 95 | $this->message = $this->parseURLs($this->message); |
| 96 | } |
| 97 | |
| 98 | // encode html |
| 99 | $this->message = StringUtil::encodeHTML($this->message); |
| 100 | |
| 101 | // converts newlines to <br>'s |
| 102 | $this->message = \nl2br($this->message, false); |
| 103 | |
| 104 | // parse urls |
| 105 | if ($parseURLs) { |
| 106 | $this->message = $this->insertCachedURLs($this->message); |
| 107 | } |
| 108 | |
| 109 | // parse smilies |
| 110 | if ($parseSmilies) { |
| 111 | $this->message = $this->parseSmilies($this->message); |
| 112 | } |
| 113 | |
| 114 | // replace bad html tags (script etc.) |
| 115 | $badSearch = ['/(javascript):/i', '/(about):/i', '/(vbscript):/i']; |
| 116 | $badReplace = ['$1<b></b>:', '$1<b></b>:', '$1<b></b>:']; |
| 117 | $this->message = \preg_replace($badSearch, $badReplace, $this->message); |
| 118 | |
| 119 | // call event |
| 120 | EventHandler::getInstance()->fireAction($this, 'afterParsing'); |
| 121 | |
| 122 | return $this->message; |
| 123 | } |
| 124 | |
| 125 | /** |
| 126 | * Parses urls. |
| 127 | * |
| 128 | * @param string $text |
| 129 | * @return string text |
| 130 | */ |
| 131 | public function parseURLs($text) |
| 132 | { |
| 133 | // define pattern |
| 134 | $urlPattern = '~(?<!\B|"|\'|=|/|\]|,|\?) |
| 135 | (?: # hostname |
| 136 | (?:ftp|https?)://' . static::$illegalChars . '(?:\.' . static::$illegalChars . ')* |
| 137 | | |
| 138 | www\.(?:' . static::$illegalChars . '\.)+ |
| 139 | (?:[a-z]{2,63}(?=\b)) # tld |
| 140 | ) |
| 141 | |
| 142 | (?::\d+)? # port |
| 143 | |
| 144 | (?: |
| 145 | / |
| 146 | [^!.,?;"\'<>()\[\]{}\s]* |
| 147 | (?: |
| 148 | [!.,?;(){}]+ [^!.,?;"\'<>()\[\]{}\s]+ |
| 149 | )* |
| 150 | )? |
| 151 | ~ix'; |
| 152 | $emailPattern = '~(?<!\B|"|\'|=|/|\]|,|:) |
| 153 | (?:) |
| 154 | \w+(?:[\.\-]\w+)* |
| 155 | @ |
| 156 | (?:' . static::$illegalChars . '\.)+ # hostname |
| 157 | (?:[a-z]{2,4}(?=\b)) |
| 158 | (?!"|\'|\[|\-) |
| 159 | ~ix'; |
| 160 | |
| 161 | // parse urls |
| 162 | $text = \preg_replace_callback($urlPattern, [$this, 'cacheURLsCallback'], $text); |
| 163 | |
| 164 | // parse emails |
| 165 | if (\str_contains($text, '@')) { |
| 166 | $text = \preg_replace_callback($emailPattern, [$this, 'cacheEmailsCallback'], $text); |
| 167 | } |
| 168 | |
| 169 | return $text; |
| 170 | } |
| 171 | |
| 172 | /** |
| 173 | * Returns the hash for an matched URL in the message. |
| 174 | * |
| 175 | * @param array $matches |
| 176 | * @return string |
| 177 | */ |
| 178 | protected function cacheURLsCallback($matches) |
| 179 | { |
| 180 | $hash = '@@' . StringUtil::getRandomID() . '@@'; |
| 181 | $this->cachedURLs[$hash] = $matches[0]; |
| 182 | |
| 183 | return $hash; |
| 184 | } |
| 185 | |
| 186 | /** |
| 187 | * Returns the hash for an matched e-mail in the message. |
| 188 | * |
| 189 | * @param array $matches |
| 190 | * @return string |
| 191 | */ |
| 192 | protected function cacheEmailsCallback($matches) |
| 193 | { |
| 194 | $hash = '@@' . StringUtil::getRandomID() . '@@'; |
| 195 | $this->cachedEmails[$hash] = $matches[0]; |
| 196 | |
| 197 | return $hash; |
| 198 | } |
| 199 | |
| 200 | /** |
| 201 | * Reinserts cached URLs and e-mails. |
| 202 | * |
| 203 | * @param string $text |
| 204 | * @return string |
| 205 | */ |
| 206 | protected function insertCachedURLs($text) |
| 207 | { |
| 208 | foreach ($this->cachedURLs as $hash => $url) { |
| 209 | // add protocol if necessary |
| 210 | if (!\preg_match("/[a-z]:\\/\\//si", $url)) { |
| 211 | $url = 'http://' . $url; |
| 212 | } |
| 213 | |
| 214 | $text = \str_replace($hash, StringUtil::getAnchorTag($url, '', true, true), $text); |
| 215 | } |
| 216 | |
| 217 | foreach ($this->cachedEmails as $hash => $email) { |
| 218 | $email = StringUtil::encodeHTML($email); |
| 219 | |
| 220 | $text = \str_replace($hash, '<a href="mailto:' . $email . '">' . $email . '</a>', $text); |
| 221 | } |
| 222 | |
| 223 | return $text; |
| 224 | } |
| 225 | |
| 226 | /** |
| 227 | * Parses smiley codes. |
| 228 | * |
| 229 | * @param string $text |
| 230 | * @return string text |
| 231 | */ |
| 232 | public function parseSmilies($text) |
| 233 | { |
| 234 | $smileyCount = 0; |
| 235 | foreach ($this->smilies as $code => $html) { |
| 236 | $text = \preg_replace_callback('~(?<=^|\s)' . \preg_quote( |
| 237 | StringUtil::encodeHTML($code), |
| 238 | '~' |
| 239 | ) . '(?=$|\s|<br />|<br>)~', static function () use ($code, $html, &$smileyCount) { |
| 240 | if ($smileyCount === 50) { |
| 241 | return $code; |
| 242 | } |
| 243 | |
| 244 | $smileyCount++; |
| 245 | |
| 246 | return $html; |
| 247 | }, $text); |
| 248 | } |
| 249 | |
| 250 | return $text; |
| 251 | } |
| 252 | } |