mundschenk-at /
php-typography
We could not synchronize checks via GitHub's checks API since Scrutinizer's GitHub App is not installed for this repository.
| Total Complexity | 54 |
| Total Lines | 444 |
| Duplicated Lines | 0 % |
| Coverage | 99.24% |
| Changes | 8 | ||
| Bugs | 0 | Features | 0 |
Complex classes like PHP_Typography often do a lot of different things. To break such a class down, we need to identify a cohesive component within that class. A common approach to find such a component is to look for fields/methods that share the same prefixes, or suffixes.
Once you have determined the fields that belong together, you can apply the Extract Class refactoring. If the component makes sense as a sub-class, Extract Subclass is also a candidate, and is often faster.
While breaking up the class, it is a good idea to analyze how other classes use PHP_Typography, and based on these observations, apply Extract Interface, too.
| 1 | <?php |
||
| 46 | class PHP_Typography { |
||
| 47 | |||
| 48 | /** |
||
| 49 | * A DOM-based HTML5 parser. |
||
| 50 | * |
||
| 51 | * @var \Masterminds\HTML5 |
||
| 52 | */ |
||
| 53 | private $html5_parser; |
||
| 54 | |||
| 55 | /** |
||
| 56 | * The hyphenator cache. |
||
| 57 | * |
||
| 58 | * @var Hyphenator\Cache |
||
| 59 | */ |
||
| 60 | protected $hyphenator_cache; |
||
| 61 | |||
| 62 | /** |
||
| 63 | * The node fixes registry. |
||
| 64 | * |
||
| 65 | * @var Registry|null; |
||
| 66 | */ |
||
| 67 | private $registry; |
||
| 68 | |||
| 69 | /** |
||
| 70 | * Whether the Hyphenator\Cache of the $registry needs to be updated. |
||
| 71 | * |
||
| 72 | * @var bool |
||
| 73 | */ |
||
| 74 | private $update_registry_cache; |
||
| 75 | |||
| 76 | /** |
||
| 77 | * Sets up a new PHP_Typography object. |
||
| 78 | * |
||
| 79 | * @param Registry|null $registry Optional. A fix registry instance. Default null, |
||
| 80 | * meaning the default fixes are used. |
||
| 81 | */ |
||
| 82 | 1 | public function __construct( Registry $registry = null ) { |
|
| 85 | 1 | } |
|
| 86 | |||
| 87 | /** |
||
| 88 | * Modifies $html according to the defined settings. |
||
| 89 | * |
||
| 90 | * @since 6.0.0 Parameter $body_classes added. |
||
| 91 | * |
||
| 92 | * @param string $html A HTML fragment. |
||
| 93 | * @param Settings $settings A settings object. |
||
| 94 | * @param bool $is_title Optional. If the HTML fragment is a title. Default false. |
||
| 95 | * @param string[] $body_classes Optional. CSS classes added to the virtual |
||
| 96 | * <body> element used for processing. Default []. |
||
| 97 | * |
||
| 98 | * @return string The processed $html. |
||
| 99 | */ |
||
| 100 | 44 | public function process( $html, Settings $settings, $is_title = false, array $body_classes = [] ) { |
|
| 109 | ); |
||
| 110 | } |
||
| 111 | |||
| 112 | /** |
||
| 113 | * Modifies $html according to the defined settings, in a way that is appropriate for RSS feeds |
||
| 114 | * (i.e. excluding processes that may not display well with limited character set intelligence). |
||
| 115 | * |
||
| 116 | * @since 6.0.0 Parameter $body_classes added. |
||
| 117 | * |
||
| 118 | * @param string $html A HTML fragment. |
||
| 119 | * @param Settings $settings A settings object. |
||
| 120 | * @param bool $is_title Optional. If the HTML fragment is a title. Default false. |
||
| 121 | * @param string[] $body_classes Optional. CSS classes added to the virtual |
||
| 122 | * <body> element used for processing. Default []. |
||
| 123 | * |
||
| 124 | * @return string The processed $html. |
||
| 125 | */ |
||
| 126 | 44 | public function process_feed( $html, Settings $settings, $is_title = false, array $body_classes = [] ) { |
|
| 135 | ); |
||
| 136 | } |
||
| 137 | |||
| 138 | /** |
||
| 139 | * Applies specific fixes to all textnodes of the HTML fragment. |
||
| 140 | * |
||
| 141 | * @since 6.0.0 Parameter $body_classes added. |
||
| 142 | * |
||
| 143 | * @param string $html A HTML fragment. |
||
| 144 | * @param callable $fixer A callback that applies typography fixes to a single textnode. |
||
| 145 | * @param Settings $settings A settings object. |
||
| 146 | * @param bool $is_title Optional. If the HTML fragment is a title. Default false. |
||
| 147 | * @param string[] $body_classes Optional. CSS classes added to the virtual |
||
| 148 | * <body> element used for processing. Default []. |
||
| 149 | * |
||
| 150 | * @return string The processed $html. |
||
| 151 | */ |
||
| 152 | 87 | public function process_textnodes( $html, callable $fixer, Settings $settings, $is_title = false, array $body_classes = [] ) { |
|
| 153 | 87 | if ( isset( $settings['ignoreTags'] ) && $is_title && ( \in_array( 'h1', /** Array. @scrutinizer ignore-type */ $settings['ignoreTags'], true ) || \in_array( 'h2', /** Array. @scrutinizer ignore-type */ $settings['ignoreTags'], true ) ) ) { |
|
| 154 | 42 | return $html; |
|
| 155 | } |
||
| 156 | |||
| 157 | // Lazy-load our parser (the text parser is not needed for feeds). |
||
| 158 | 45 | $html5_parser = $this->get_html5_parser(); |
|
| 159 | |||
| 160 | // Parse the HTML. |
||
| 161 | 45 | $dom = $this->parse_html( $html5_parser, $html, $settings, $body_classes ); |
|
| 162 | |||
| 163 | // Abort if there were parsing errors. |
||
| 164 | 45 | if ( ! $dom instanceof \DOMDocument || ! $dom->hasChildNodes() ) { |
|
| 165 | 2 | return $html; |
|
| 166 | } |
||
| 167 | |||
| 168 | // Query some nodes in the DOM. |
||
| 169 | 43 | $xpath = new \DOMXPath( $dom ); |
|
| 170 | 43 | $body_node = $xpath->query( '/html/body' )->item( 0 ); |
|
| 171 | |||
| 172 | // Abort if we could not retrieve the body node. |
||
| 173 | // This should be refactored to use exceptions in a future version. |
||
| 174 | 43 | if ( ! $body_node instanceof \DOMNode ) { |
|
| 175 | return $html; |
||
| 176 | } |
||
| 177 | |||
| 178 | // Get the list of tags that should be ignored. |
||
| 179 | 43 | $tags_to_ignore = $this->query_tags_to_ignore( $xpath, $body_node, $settings ); |
|
| 180 | |||
| 181 | // Start processing. |
||
| 182 | 43 | foreach ( $xpath->query( '//text()', $body_node ) as $textnode ) { |
|
| 183 | if ( |
||
| 184 | // One of the ancestors should be ignored. |
||
| 185 | 40 | self::arrays_intersect( DOM::get_ancestors( $textnode ), $tags_to_ignore ) || |
|
| 186 | // The node contains only whitespace. |
||
| 187 | 40 | $textnode->isWhitespaceInElementContent() |
|
| 188 | ) { |
||
| 189 | 3 | continue; |
|
| 190 | } |
||
| 191 | |||
| 192 | // Store original content. |
||
| 193 | 37 | $original = $textnode->data; |
|
| 194 | |||
| 195 | // Apply fixes. |
||
| 196 | 37 | $fixer( $textnode, $settings, $is_title ); |
|
| 197 | |||
| 198 | // Until now, we've only been working on a textnode: HTMLify result. |
||
| 199 | 37 | $new = $textnode->data; |
|
| 200 | |||
| 201 | // Replace original node (if anthing was changed). |
||
| 202 | 37 | if ( $new !== $original ) { |
|
| 203 | 1 | $this->replace_node_with_html( $textnode, $settings->apply_character_mapping( $new ) ); |
|
| 204 | } |
||
| 205 | } |
||
| 206 | |||
| 207 | 43 | return $html5_parser->saveHTML( $body_node->childNodes ); |
|
| 208 | } |
||
| 209 | |||
| 210 | /** |
||
| 211 | * Determines whether two object arrays intersect. The second array is expected |
||
| 212 | * to use the spl_object_hash for its keys. |
||
| 213 | * |
||
| 214 | * @param array $array1 The keys are ignored. |
||
| 215 | * @param array $array2 This array has to be in the form ( $spl_object_hash => $object ). |
||
| 216 | * |
||
| 217 | * @return boolean |
||
| 218 | */ |
||
| 219 | 4 | protected static function arrays_intersect( array $array1, array $array2 ) { |
|
| 220 | 4 | foreach ( $array1 as $value ) { |
|
| 221 | 2 | if ( isset( $array2[ \spl_object_hash( $value ) ] ) ) { |
|
| 222 | 1 | return true; |
|
| 223 | } |
||
| 224 | } |
||
| 225 | |||
| 226 | 3 | return false; |
|
| 227 | } |
||
| 228 | |||
| 229 | /** |
||
| 230 | * Parse HTML5 fragment while ignoring certain warnings for invalid HTML code (e.g. duplicate IDs). |
||
| 231 | * |
||
| 232 | * @since 6.0.0 Parameter $body_classes added. |
||
| 233 | * |
||
| 234 | * @param \Masterminds\HTML5 $parser An intialized parser object. |
||
| 235 | * @param string $html The HTML fragment to parse (not a complete document). |
||
| 236 | * @param Settings $settings The settings to apply. |
||
| 237 | * @param string[] $body_classes Optional. CSS classes added to the virtual |
||
| 238 | * <body> element used for processing. Default []. |
||
| 239 | * |
||
| 240 | * @return \DOMDocument|null The encoding has already been set to UTF-8. Returns null if there were parsing errors. |
||
| 241 | */ |
||
| 242 | 87 | public function parse_html( \Masterminds\HTML5 $parser, $html, Settings $settings, array $body_classes = [] ) { |
|
| 243 | // Silence some parsing errors for invalid HTML. |
||
| 244 | 87 | \set_error_handler( [ $this, 'handle_parsing_errors' ] ); // phpcs:ignore WordPress.PHP.DevelopmentFunctions.error_log_set_error_handler |
|
| 245 | 87 | $xml_error_handling = \libxml_use_internal_errors( true ); |
|
| 246 | |||
| 247 | // Inject <body> classes. |
||
| 248 | 87 | $body = empty( $body_classes ) ? 'body' : 'body class="' . \implode( ' ', $body_classes ) . '"'; |
|
| 249 | |||
| 250 | // Do the actual parsing. |
||
| 251 | 87 | $dom = $parser->loadHTML( "<!DOCTYPE html><html><{$body}>{$html}</body></html>" ); |
|
| 252 | 87 | $dom->encoding = 'UTF-8'; |
|
| 253 | |||
| 254 | // Restore original error handling. |
||
| 255 | 87 | \libxml_clear_errors(); |
|
| 256 | 87 | \libxml_use_internal_errors( $xml_error_handling ); |
|
| 257 | 87 | \restore_error_handler(); |
|
| 258 | |||
| 259 | // Handle any parser errors. |
||
| 260 | 87 | $errors = $parser->getErrors(); |
|
| 261 | 87 | if ( ! empty( $settings[ Settings::PARSER_ERRORS_HANDLER ] ) && ! empty( $errors ) ) { |
|
| 262 | 2 | $errors = $settings[ Settings::PARSER_ERRORS_HANDLER ]( $errors ); |
|
| 263 | } |
||
| 264 | |||
| 265 | // Return null if there are still unhandled parsing errors. |
||
| 266 | 87 | if ( ! empty( $errors ) && ! $settings[ Settings::PARSER_ERRORS_IGNORE ] ) { |
|
| 267 | 2 | $dom = null; |
|
| 268 | } |
||
| 269 | |||
| 270 | 87 | return $dom; |
|
| 271 | } |
||
| 272 | |||
| 273 | /** |
||
| 274 | * Silently handle certain HTML parsing errors. |
||
| 275 | * |
||
| 276 | * @since 6.0.0 Unused parameters $errline and $errcontext removed. |
||
| 277 | * |
||
| 278 | * @param int $errno Error number. |
||
| 279 | * @param string $errstr Error message. |
||
| 280 | * @param string $errfile The file in which the error occurred. |
||
| 281 | * |
||
| 282 | * @return boolean Returns true if the error was handled, false otherwise. |
||
| 283 | */ |
||
| 284 | 4 | public function handle_parsing_errors( $errno, $errstr, $errfile ) { |
|
| 285 | 4 | if ( ! ( \error_reporting() & $errno ) ) { // phpcs:ignore WordPress.PHP.DiscouragedPHPFunctions.runtime_configuration_error_reporting,WordPress.PHP.DevelopmentFunctions.prevent_path_disclosure_error_reporting |
|
| 286 | 4 | return true; // not interesting. |
|
| 287 | } |
||
| 288 | |||
| 289 | // Ignore warnings from parser & let PHP handle the rest. |
||
| 290 | 4 | return $errno & E_USER_WARNING && 0 === \substr_compare( $errfile, 'DOMTreeBuilder.php', -18 ); |
|
| 291 | } |
||
| 292 | |||
| 293 | /** |
||
| 294 | * Retrieves an array of nodes that should be skipped during processing. |
||
| 295 | * |
||
| 296 | * @param \DOMXPath $xpath A valid XPath instance for the DOM to be queried. |
||
| 297 | * @param \DOMNode $initial_node The starting node of the XPath query. |
||
| 298 | * @param Settings $settings The settings to apply. |
||
| 299 | * |
||
| 300 | * @return \DOMNode[] An array of \DOMNode (can be empty). |
||
| 301 | */ |
||
| 302 | 1 | public function query_tags_to_ignore( \DOMXPath $xpath, \DOMNode $initial_node, Settings $settings ) { |
|
| 303 | 1 | $elements = []; |
|
| 304 | 1 | $query_parts = []; |
|
| 305 | 1 | if ( ! empty( $settings['ignoreTags'] ) ) { |
|
| 306 | 1 | $query_parts[] = '//' . \implode( ' | //', /** Array. @scrutinizer ignore-type */ $settings['ignoreTags'] ); |
|
| 307 | } |
||
| 308 | 1 | if ( ! empty( $settings['ignoreClasses'] ) ) { |
|
| 309 | 1 | $query_parts[] = "//*[contains(concat(' ', @class, ' '), ' " . \implode( " ') or contains(concat(' ', @class, ' '), ' ", /** Array. @scrutinizer ignore-type */ $settings['ignoreClasses'] ) . " ')]"; |
|
| 310 | } |
||
| 311 | 1 | if ( ! empty( $settings['ignoreIDs'] ) ) { |
|
| 312 | 1 | $query_parts[] = '//*[@id=\'' . \implode( '\' or @id=\'', /** Array. @scrutinizer ignore-type */ $settings['ignoreIDs'] ) . '\']'; |
|
| 313 | } |
||
| 314 | |||
| 315 | 1 | if ( ! empty( $query_parts ) ) { |
|
| 316 | 1 | $ignore_query = \implode( ' | ', $query_parts ); |
|
| 317 | |||
| 318 | 1 | $nodelist = $xpath->query( $ignore_query, $initial_node ); |
|
| 319 | 1 | if ( false !== $nodelist ) { |
|
| 320 | 1 | $elements = DOM::nodelist_to_array( $nodelist ); |
|
| 321 | } |
||
| 322 | } |
||
| 323 | |||
| 324 | 1 | return $elements; |
|
| 325 | } |
||
| 326 | |||
| 327 | /** |
||
| 328 | * Replaces the given node with HTML content. Uses the HTML5 parser. |
||
| 329 | * |
||
| 330 | * @param \DOMNode $node The node to replace. |
||
| 331 | * @param string $content The HTML fragment used to replace the node. |
||
| 332 | * |
||
| 333 | * @return \DOMNode|array An array of \DOMNode containing the new nodes or the old \DOMNode if the replacement failed. |
||
| 334 | */ |
||
| 335 | 2 | public function replace_node_with_html( \DOMNode $node, $content ) { |
|
| 367 | } |
||
| 368 | |||
| 369 | /** |
||
| 370 | * Retrieves the fix registry. |
||
| 371 | * |
||
| 372 | * @return Registry |
||
| 373 | */ |
||
| 374 | 2 | public function get_registry() { |
|
| 375 | 2 | if ( ! isset( $this->registry ) ) { |
|
| 376 | 1 | $this->registry = new Default_Registry( $this->get_hyphenator_cache() ); |
|
| 377 | 1 | } elseif ( $this->update_registry_cache ) { |
|
| 378 | 1 | $this->registry->update_hyphenator_cache( $this->get_hyphenator_cache() ); |
|
|
|
|||
| 379 | 1 | $this->update_registry_cache = false; |
|
| 380 | } |
||
| 381 | |||
| 382 | 2 | return $this->registry; |
|
| 383 | } |
||
| 384 | |||
| 385 | /** |
||
| 386 | * Retrieves the HTML5 parser instance. |
||
| 387 | * |
||
| 388 | * @return \Masterminds\HTML5 |
||
| 389 | */ |
||
| 390 | 1 | public function get_html5_parser() { |
|
| 391 | // Lazy-load HTML5 parser. |
||
| 392 | 1 | if ( ! isset( $this->html5_parser ) ) { |
|
| 393 | 1 | $this->html5_parser = new \Masterminds\HTML5( [ 'disable_html_ns' => true ] ); |
|
| 394 | } |
||
| 395 | |||
| 396 | 1 | return $this->html5_parser; |
|
| 397 | } |
||
| 398 | |||
| 399 | /** |
||
| 400 | * Retrieves the hyphenator cache. |
||
| 401 | * |
||
| 402 | * @return Hyphenator\Cache |
||
| 403 | */ |
||
| 404 | 1 | public function get_hyphenator_cache() { |
|
| 405 | 1 | if ( ! isset( $this->hyphenator_cache ) ) { |
|
| 406 | 1 | $this->hyphenator_cache = new Hyphenator\Cache(); |
|
| 407 | } |
||
| 408 | |||
| 409 | 1 | return $this->hyphenator_cache; |
|
| 410 | } |
||
| 411 | |||
| 412 | /** |
||
| 413 | * Injects an existing Hyphenator\Cache (to facilitate persistent language caching). |
||
| 414 | * |
||
| 415 | * @param Hyphenator\Cache $cache A hyphenator cache instance. |
||
| 416 | */ |
||
| 417 | 2 | public function set_hyphenator_cache( Hyphenator\Cache $cache ) { |
|
| 418 | 2 | $this->hyphenator_cache = $cache; |
|
| 419 | |||
| 420 | // Change hyphenator cache for existing token fixes. |
||
| 421 | 2 | if ( isset( $this->registry ) ) { |
|
| 422 | 1 | $this->registry->update_hyphenator_cache( $cache ); |
|
| 423 | } |
||
| 424 | 2 | } |
|
| 425 | |||
| 426 | /** |
||
| 427 | * Retrieves the list of valid language plugins in the given directory. |
||
| 428 | * |
||
| 429 | * @param string $path The path in which to look for language plugin files. |
||
| 430 | * |
||
| 431 | * @return string[] An array in the form ( $language_code => $language_name ). |
||
| 432 | */ |
||
| 433 | 3 | private static function get_language_plugin_list( $path ) { |
|
| 466 | } |
||
| 467 | |||
| 468 | /** |
||
| 469 | * Retrieves the list of valid hyphenation languages. |
||
| 470 | * |
||
| 471 | * Note that this method reads all the language files on disc, so you should |
||
| 472 | * cache the results if possible. |
||
| 473 | * |
||
| 474 | * @return string[] An array in the form of ( LANG_CODE => LANGUAGE ). |
||
| 475 | */ |
||
| 476 | 1 | public static function get_hyphenation_languages() { |
|
| 478 | } |
||
| 479 | |||
| 480 | /** |
||
| 481 | * Retrieves the list of valid diacritic replacement languages. |
||
| 482 | * |
||
| 483 | * Note that this method reads all the language files on disc, so you should |
||
| 484 | * cache the results if possible. |
||
| 485 | * |
||
| 486 | * @return string[] An array in the form of ( LANG_CODE => LANGUAGE ). |
||
| 487 | */ |
||
| 488 | 1 | public static function get_diacritic_languages() { |
|
| 492 |
This check looks for calls to methods that do not seem to exist on a given type. It looks for the method on the type itself as well as in inherited classes or implemented interfaces.
This is most likely a typographical error or the method has been renamed.