PHP_Typography::process() - Code Metrics - Inspection of "Reduce coupling" - mundschenk-at/php-typography - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Pull Request — master (#44)

by Der Mundschenk

created 2017-12-16 21:24 UTC

PHP_Typography::process() A

↳ Parent: PHP_Typography

Complexity

Conditions	1
Paths	1

Size

Total Lines	5
Code Lines	4

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	5
rs	9.4285
c	0
b	0
f	0
cc	1
eloc	4
nc	1
nop	3

<?php
/**
 *  This file is part of PHP-Typography.
 *
 *  Copyright 2014-2017 Peter Putzer.
 *  Copyright 2009-2011 KINGdesk, LLC.
 *
 *  This program is free software; you can redistribute it and/or modify
 *  it under the terms of the GNU General Public License as published by
 *  the Free Software Foundation; either version 2 of the License, or
 *  (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *  GNU General Public License for more details.
 *
 *  You should have received a copy of the GNU General Public License along
 *  with this program; if not, write to the Free Software Foundation, Inc.,
 *  51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
 *
 *  ***
 *
 *  @package mundschenk-at/php-typography
 *  @license http://www.gnu.org/licenses/gpl-2.0.html
 */

namespace PHP_Typography;

use PHP_Typography\Fixes\Registry;
use PHP_Typography\Fixes\Default_Registry;

/**
 * Parses HTML5 (or plain text) and applies various typographic fixes to the text.
 *
 * If used with multibyte language, UTF-8 encoding is required.
 *
 * Portions of this code have been inspired by:
 *  - typogrify (https://code.google.com/p/typogrify/)
 *  - WordPress code for wptexturize (https://developer.wordpress.org/reference/functions/wptexturize/)
 *  - PHP SmartyPants Typographer (https://michelf.ca/projects/php-smartypants/typographer/)
 *
 *  @author Jeffrey D. King <[email protected]>
 *  @author Peter Putzer <[email protected]>
 */
class PHP_Typography {

	/**
	 * A DOM-based HTML5 parser.
	 *
	 * @var \Masterminds\HTML5
	 */
	private $html5_parser;

	/**
	 * The hyphenator cache.
	 *
	 * @var Hyphenator\Cache
	 */
	protected $hyphenator_cache;

	/**
	 * The node fixes registry.
	 *
	 * @var Registry|null;
	 */
	private $registry;

	/**
	 * Whether the Hyphenator\Cache of the $registry needs to be updated.
	 *
	 * @var bool
	 */
	private $update_registry_cache;

	/**
	 * Sets up a new PHP_Typography object.
	 *
	 * @param Registry|null $registry Optional. A fix registry instance. Default null,
	 *                                meaning the default fixes are used.
	 */
	public function __construct( Registry $registry = null ) {
		$this->registry              = $registry;
		$this->update_registry_cache = ! empty( $registry );
	}

	/**
	 * Modifies $html according to the defined settings.
	 *
	 * @param string   $html      A HTML fragment.
	 * @param Settings $settings  A settings object.
	 * @param bool     $is_title  Optional. If the HTML fragment is a title. Default false.
	 *
	 * @return string The processed $html.
	 */
	public function process( $html, Settings $settings, $is_title = false ) {
		return $this->process_textnodes( $html, function( $html, $settings, $is_title ) {
			return $this->get_registry()->apply_fixes( $html, $settings, $is_title, false );
		}, $settings, $is_title );
	}

	/**
	 * Modifies $html according to the defined settings, in a way that is appropriate for RSS feeds
	 * (i.e. excluding processes that may not display well with limited character set intelligence).
	 *
	 * @param string   $html     A HTML fragment.
	 * @param Settings $settings  A settings object.
	 * @param bool     $is_title Optional. If the HTML fragment is a title. Default false.
	 *
	 * @return string The processed $html.
	 */
	public function process_feed( $html, Settings $settings, $is_title = false ) {
		return $this->process_textnodes( $html, function( $html, $settings, $is_title ) {
			return $this->get_registry()->apply_fixes( $html, $settings, $is_title, true );
		}, $settings, $is_title );
	}

	/**
	 * Applies specific fixes to all textnodes of the HTML fragment.
	 *
	 * @param string   $html     A HTML fragment.
	 * @param callable $fixer    A callback that applies typography fixes to a single textnode.
	 * @param Settings $settings  A settings object.
	 * @param bool     $is_title Optional. If the HTML fragment is a title. Default false.
	 *
	 * @return string The processed $html.
	 */
	public function process_textnodes( $html, callable $fixer, Settings $settings, $is_title = false ) {
		if ( isset( $settings['ignoreTags'] ) && $is_title && ( in_array( 'h1', $settings['ignoreTags'], true ) || in_array( 'h2', $settings['ignoreTags'], true ) ) ) {
			return $html;
		}

		// Lazy-load our parser (the text parser is not needed for feeds).
		$html5_parser = $this->get_html5_parser();

		// Parse the HTML.
		$dom = $this->parse_html( $html5_parser, $html, $settings );

		// Abort if there were parsing errors.
		if ( empty( $dom ) ) {
			return $html;
		}

		// Query some nodes in the DOM.
		$xpath          = new \DOMXPath( $dom );
		$body_node      = $xpath->query( '/html/body' )->item( 0 );
		$all_textnodes  = $xpath->query( '//text()', $body_node );
		$tags_to_ignore = $this->query_tags_to_ignore( $xpath, $body_node, $settings );

		// Start processing.
		foreach ( $all_textnodes as $textnode ) {
			if ( self::arrays_intersect( DOM::get_ancestors( $textnode ), $tags_to_ignore ) ) {
				continue;
			}

			// We won't be doing anything with spaces, so we can jump ship if that is all we have.
			if ( $textnode->isWhitespaceInElementContent() ) {
				continue;
			}

			// Decode all characters except < > &.
			$textnode->data = htmlspecialchars( $textnode->data, ENT_NOQUOTES, 'UTF-8' ); // returns < > & to encoded HTML characters (&lt; &gt; and &amp; respectively).

			// Apply fixes.
			$fixer( $textnode, $settings, $is_title );

			// Until now, we've only been working on a textnode: HTMLify result.
			$this->replace_node_with_html( $textnode, $textnode->data );
		}

		return $html5_parser->saveHTML( $body_node->childNodes );
	}

	/**
	 * Determines whether two object arrays intersect. The second array is expected
	 * to use the spl_object_hash for its keys.
	 *
	 * @param array $array1 The keys are ignored.
	 * @param array $array2 This array has to be in the form ( $spl_object_hash => $object ).
	 *
	 * @return boolean
	 */
	protected static function arrays_intersect( array $array1, array $array2 ) {
		foreach ( $array1 as $value ) {
			if ( isset( $array2[ spl_object_hash( $value ) ] ) ) {
				return true;
			}
		}

		return false;
	}

	/**
	 * Parse HTML5 fragment while ignoring certain warnings for invalid HTML code (e.g. duplicate IDs).
	 *
	 * @param \Masterminds\HTML5 $parser   An intialized parser object.
	 * @param string             $html     The HTML fragment to parse (not a complete document).
	 * @param Settings           $settings The settings to apply.
	 *
	 * @return \DOMDocument|null The encoding has already been set to UTF-8. Returns null if there were parsing errors.
	 */
	public function parse_html( \Masterminds\HTML5 $parser, $html, Settings $settings ) {
		// Silence some parsing errors for invalid HTML.
		set_error_handler( [ $this, 'handle_parsing_errors' ] ); // @codingStandardsIgnoreLine
		$xml_error_handling = libxml_use_internal_errors( true );

		// Do the actual parsing.
		$dom           = $parser->loadHTML( '<!DOCTYPE html><html><body>' . $html . '</body></html>' );
		$dom->encoding = 'UTF-8';

		// Restore original error handling.
		libxml_clear_errors();
		libxml_use_internal_errors( $xml_error_handling );
		restore_error_handler();

		// Handle any parser errors.
		$errors = $parser->getErrors();
		if ( ! empty( $settings['parserErrorsHandler'] ) && ! empty( $errors ) ) {
			$errors = $settings['parserErrorsHandler']( $errors );
		}

		// Return null if there are still unhandled parsing errors.
		if ( ! empty( $errors ) && ! $settings['parserErrorsIgnore'] ) {
			$dom = null;
		}

		return $dom;
	}

	/**
	 * Silently handle certain HTML parsing errors.
	 *
	 * @param int    $errno      Error number.
	 * @param string $errstr     Error message.
	 * @param string $errfile    The file in which the error occurred.
	 * @param int    $errline    The line in which the error occurred.
	 * @param array  $errcontext Calling context.
	 *
	 * @return boolean Returns true if the error was handled, false otherwise.
	 */
	public function handle_parsing_errors( $errno, $errstr, $errfile, $errline, array $errcontext ) {

		if ( ! ( error_reporting() & $errno ) ) { // @codingStandardsIgnoreLine.
			return true; // not interesting.
		}

		// Ignore warnings from parser & let PHP handle the rest.
		return $errno & E_USER_WARNING && 0 === substr_compare( $errfile, 'DOMTreeBuilder.php', -18 );
	}

	/**
	 * Retrieves an array of nodes that should be skipped during processing.
	 *
	 * @param \DOMXPath $xpath        A valid XPath instance for the DOM to be queried.
	 * @param \DOMNode  $initial_node The starting node of the XPath query.
	 * @param Settings  $settings     The settings to apply.
	 *
	 * @return \DOMNode[] An array of \DOMNode (can be empty).
	 */
	public function query_tags_to_ignore( \DOMXPath $xpath, \DOMNode $initial_node, Settings $settings ) {
		$elements    = [];
		$query_parts = [];
		if ( ! empty( $settings['ignoreTags'] ) ) {
			$query_parts[] = '//' . implode( ' | //', $settings['ignoreTags'] );
		}
		if ( ! empty( $settings['ignoreClasses'] ) ) {
			$query_parts[] = "//*[contains(concat(' ', @class, ' '), ' " . implode( " ') or contains(concat(' ', @class, ' '), ' ", $settings['ignoreClasses'] ) . " ')]";
		}
		if ( ! empty( $settings['ignoreIDs'] ) ) {
			$query_parts[] = '//*[@id=\'' . implode( '\' or @id=\'', $settings['ignoreIDs'] ) . '\']';
		}

		if ( ! empty( $query_parts ) ) {
			$ignore_query = implode( ' | ', $query_parts );

			$nodelist = $xpath->query( $ignore_query, $initial_node );
			if ( false !== $nodelist ) {
				$elements = DOM::nodelist_to_array( $nodelist );
			}
		}

		return $elements;
	}

	/**
	 * Replaces the given node with HTML content. Uses the HTML5 parser.
	 *
	 * @param \DOMNode $node    The node to replace.
	 * @param string   $content The HTML fragment used to replace the node.
	 *
	 * @return \DOMNode|array An array of \DOMNode containing the new nodes or the old \DOMNode if the replacement failed.
	 */
	public function replace_node_with_html( \DOMNode $node, $content ) {
		$result = $node;

		$parent = $node->parentNode;
		if ( empty( $parent ) ) {
			return $node; // abort early to save cycles.
		}

		set_error_handler( [ $this, 'handle_parsing_errors' ] ); // @codingStandardsIgnoreLine.

		$html_fragment = $this->get_html5_parser()->loadHTMLFragment( $content );
		if ( ! empty( $html_fragment ) ) {
			$imported_fragment = $node->ownerDocument->importNode( $html_fragment, true );

			if ( ! empty( $imported_fragment ) ) {
				// Save the children of the imported DOMDocumentFragment before replacement.
				$children = DOM::nodelist_to_array( $imported_fragment->childNodes );

				if ( false !== $parent->replaceChild( $imported_fragment, $node ) ) {
					// Success! We return the saved array of DOMNodes as
					// $imported_fragment is just an empty DOMDocumentFragment now.
					$result = $children;
				}
			}
		}

		restore_error_handler();

		return $result;
	}

	/**
	 * Retrieves the fix registry.
	 *
	 * @return Registry
	 */
	public function get_registry() {
		if ( ! isset( $this->registry ) ) {
			$this->registry = new Default_Registry( $this->get_hyphenator_cache() );
		} elseif ( $this->update_registry_cache ) {
			$this->registry->update_hyphenator_cache( $this->get_hyphenator_cache() );
			$this->update_registry_cache = false;
		}

		return $this->registry;
	}

	/**
	 * Retrieves the HTML5 parser instance.
	 *
	 * @return \Masterminds\HTML5
	 */
	public function get_html5_parser() {
		// Lazy-load HTML5 parser.
		if ( ! isset( $this->html5_parser ) ) {
			$this->html5_parser = new \Masterminds\HTML5( [
				'disable_html_ns' => true,
			] );
		}

		return $this->html5_parser;
	}

	/**
	 * Retrieves the hyphenator cache.
	 *
	 * @return Hyphenator\Cache
	 */
	public function get_hyphenator_cache() {
		if ( ! isset( $this->hyphenator_cache ) ) {
			$this->hyphenator_cache = new Hyphenator\Cache();
		}

		return $this->hyphenator_cache;
	}

	/**
	 * Injects an existing Hyphenator\Cache (to facilitate persistent language caching).
	 *
	 * @param Hyphenator\Cache $cache A hyphenator cache instance.
	 */
	public function set_hyphenator_cache( Hyphenator\Cache $cache ) {
		$this->hyphenator_cache = $cache;

		// Change hyphenator cache for existing token fixes.
		if ( isset( $this->registry ) ) {
			$this->registry->update_hyphenator_cache( $cache );
		}
	}

	/**
	 * Retrieves the list of valid language plugins in the given directory.
	 *
	 * @param string $path The path in which to look for language plugin files.
	 *
	 * @return string[] An array in the form ( $language_code => $language_name ).
	 */
	private static function get_language_plugin_list( $path ) {
		$language_name_pattern = '/"language"\s*:\s*((".+")|(\'.+\'))\s*,/';
		$languages             = [];
		$handle                = opendir( $path );

		// Read all files in directory.
		$file = readdir( $handle );
		while ( $file ) {
			// We only want the JSON files.
			if ( '.json' === substr( $file, -5 ) ) {
				$file_content = file_get_contents( $path . $file );
				if ( preg_match( $language_name_pattern, $file_content, $matches ) ) {
					$language_name = substr( $matches[1], 1, -1 );
					$language_code = substr( $file, 0, -5 );

					$languages[ $language_code ] = $language_name;
				}
			}

			// Read next file.
			$file = readdir( $handle );
		}
		closedir( $handle );

		// Sort translated language names according to current locale.
		asort( $languages );

		return $languages;
	}

	/**
	 * Retrieves the list of valid hyphenation languages.
	 *
	 * Note that this method reads all the language files on disc, so you should
	 * cache the results if possible.
	 *
	 * @return string[] An array in the form of ( LANG_CODE => LANGUAGE ).
	 */
	public static function get_hyphenation_languages() {
		return self::get_language_plugin_list( __DIR__ . '/lang/' );
	}

	/**
	 * Retrieves the list of valid diacritic replacement languages.
	 *
	 * Note that this method reads all the language files on disc, so you should
	 * cache the results if possible.
	 *
	 * @return string[] An array in the form of ( LANG_CODE => LANGUAGE ).
	 */
	public static function get_diacritic_languages() {
		return self::get_language_plugin_list( __DIR__ . '/diacritics/' );
	}
}


Scrutinizer GitHub App not installed

GitHub Access Token became invalid

Pull Request — master (#44)

PHP_Typography::process() A

Complexity

Size

Duplication

Importance

1		<?php
2		/**
3		* This file is part of PHP-Typography.
4		*
5		* Copyright 2014-2017 Peter Putzer.
6		* Copyright 2009-2011 KINGdesk, LLC.
7		*
8		* This program is free software; you can redistribute it and/or modify
9		* it under the terms of the GNU General Public License as published by
10		* the Free Software Foundation; either version 2 of the License, or
11		* (at your option) any later version.
12		*
13		* This program is distributed in the hope that it will be useful,
14		* but WITHOUT ANY WARRANTY; without even the implied warranty of
15		* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
16		* GNU General Public License for more details.
17		*
18		* You should have received a copy of the GNU General Public License along
19		* with this program; if not, write to the Free Software Foundation, Inc.,
20		* 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
21		*
22		* ***
23		*
24		* @package mundschenk-at/php-typography
25		* @license http://www.gnu.org/licenses/gpl-2.0.html
26		*/
27
28		namespace PHP_Typography;
29
30		use PHP_Typography\Fixes\Registry;
31		use PHP_Typography\Fixes\Default_Registry;
32
33		/**
34		* Parses HTML5 (or plain text) and applies various typographic fixes to the text.
35		*
36		* If used with multibyte language, UTF-8 encoding is required.
37		*
38		* Portions of this code have been inspired by:
39		* - typogrify (https://code.google.com/p/typogrify/)
40		* - WordPress code for wptexturize (https://developer.wordpress.org/reference/functions/wptexturize/)
41		* - PHP SmartyPants Typographer (https://michelf.ca/projects/php-smartypants/typographer/)
42		*
43		* @author Jeffrey D. King <[email protected]>
44		* @author Peter Putzer <[email protected]>
45		*/
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		public function __construct( Registry $registry = null ) {
83		$this->registry = $registry;
84		$this->update_registry_cache = ! empty( $registry );
85		}
86
87		/**
88		* Modifies $html according to the defined settings.
89		*
90		* @param string $html A HTML fragment.
91		* @param Settings $settings A settings object.
92		* @param bool $is_title Optional. If the HTML fragment is a title. Default false.
93		*
94		* @return string The processed $html.
95		*/
96		public function process( $html, Settings $settings, $is_title = false ) {
97		return $this->process_textnodes( $html, function( $html, $settings, $is_title ) {
98		return $this->get_registry()->apply_fixes( $html, $settings, $is_title, false );
99		}, $settings, $is_title );
100		}
101
102		/**
103		* Modifies $html according to the defined settings, in a way that is appropriate for RSS feeds
104		* (i.e. excluding processes that may not display well with limited character set intelligence).
105		*
106		* @param string $html A HTML fragment.
107		* @param Settings $settings A settings object.
108		* @param bool $is_title Optional. If the HTML fragment is a title. Default false.
109		*
110		* @return string The processed $html.
111		*/
112		public function process_feed( $html, Settings $settings, $is_title = false ) {
113		return $this->process_textnodes( $html, function( $html, $settings, $is_title ) {
114		return $this->get_registry()->apply_fixes( $html, $settings, $is_title, true );
115		}, $settings, $is_title );
116		}
117
118		/**
119		* Applies specific fixes to all textnodes of the HTML fragment.
120		*
121		* @param string $html A HTML fragment.
122		* @param callable $fixer A callback that applies typography fixes to a single textnode.
123		* @param Settings $settings A settings object.
124		* @param bool $is_title Optional. If the HTML fragment is a title. Default false.
125		*
126		* @return string The processed $html.
127		*/
128		public function process_textnodes( $html, callable $fixer, Settings $settings, $is_title = false ) {
129		if ( isset( $settings['ignoreTags'] ) && $is_title && ( in_array( 'h1', $settings['ignoreTags'], true ) \|\| in_array( 'h2', $settings['ignoreTags'], true ) ) ) {
130		return $html;
131		}
132
133		// Lazy-load our parser (the text parser is not needed for feeds).
134		$html5_parser = $this->get_html5_parser();
135
136		// Parse the HTML.
137		$dom = $this->parse_html( $html5_parser, $html, $settings );
138
139		// Abort if there were parsing errors.
140		if ( empty( $dom ) ) {
141		return $html;
142		}
143
144		// Query some nodes in the DOM.
145		$xpath = new \DOMXPath( $dom );
146		$body_node = $xpath->query( '/html/body' )->item( 0 );
147		$all_textnodes = $xpath->query( '//text()', $body_node );
148		$tags_to_ignore = $this->query_tags_to_ignore( $xpath, $body_node, $settings );
149
150		// Start processing.
151		foreach ( $all_textnodes as $textnode ) {
152		if ( self::arrays_intersect( DOM::get_ancestors( $textnode ), $tags_to_ignore ) ) {
153		continue;
154		}
155
156		// We won't be doing anything with spaces, so we can jump ship if that is all we have.
157		if ( $textnode->isWhitespaceInElementContent() ) {
158		continue;
159		}
160
161		// Decode all characters except < > &.
162		$textnode->data = htmlspecialchars( $textnode->data, ENT_NOQUOTES, 'UTF-8' ); // returns < > & to encoded HTML characters (< > and & respectively).
163
164		// Apply fixes.
165		$fixer( $textnode, $settings, $is_title );
166
167		// Until now, we've only been working on a textnode: HTMLify result.
168		$this->replace_node_with_html( $textnode, $textnode->data );
169		}
170
171		return $html5_parser->saveHTML( $body_node->childNodes );
172		}
173
174		/**
175		* Determines whether two object arrays intersect. The second array is expected
176		* to use the spl_object_hash for its keys.
177		*
178		* @param array $array1 The keys are ignored.
179		* @param array $array2 This array has to be in the form ( $spl_object_hash => $object ).
180		*
181		* @return boolean
182		*/
183		protected static function arrays_intersect( array $array1, array $array2 ) {
184		foreach ( $array1 as $value ) {
185		if ( isset( $array2[ spl_object_hash( $value ) ] ) ) {
186		return true;
187		}
188		}
189
190		return false;
191		}
192
193		/**
194		* Parse HTML5 fragment while ignoring certain warnings for invalid HTML code (e.g. duplicate IDs).
195		*
196		* @param \Masterminds\HTML5 $parser An intialized parser object.
197		* @param string $html The HTML fragment to parse (not a complete document).
198		* @param Settings $settings The settings to apply.
199		*
200		* @return \DOMDocument\|null The encoding has already been set to UTF-8. Returns null if there were parsing errors.
201		*/
202		public function parse_html( \Masterminds\HTML5 $parser, $html, Settings $settings ) {
203		// Silence some parsing errors for invalid HTML.
204		set_error_handler( [ $this, 'handle_parsing_errors' ] ); // @codingStandardsIgnoreLine
205		$xml_error_handling = libxml_use_internal_errors( true );
206
207		// Do the actual parsing.
208		$dom = $parser->loadHTML( '<!DOCTYPE html><html><body>' . $html . '</body></html>' );
209		$dom->encoding = 'UTF-8';
210
211		// Restore original error handling.
212		libxml_clear_errors();
213		libxml_use_internal_errors( $xml_error_handling );
214		restore_error_handler();
215
216		// Handle any parser errors.
217		$errors = $parser->getErrors();
218		if ( ! empty( $settings['parserErrorsHandler'] ) && ! empty( $errors ) ) {
219		$errors = $settings['parserErrorsHandler']( $errors );
220		}
221
222		// Return null if there are still unhandled parsing errors.
223		if ( ! empty( $errors ) && ! $settings['parserErrorsIgnore'] ) {
224		$dom = null;
225		}
226
227		return $dom;
228		}
229
230		/**
231		* Silently handle certain HTML parsing errors.
232		*
233		* @param int $errno Error number.
234		* @param string $errstr Error message.
235		* @param string $errfile The file in which the error occurred.
236		* @param int $errline The line in which the error occurred.
237		* @param array $errcontext Calling context.
238		*
239		* @return boolean Returns true if the error was handled, false otherwise.
240		*/
241		public function handle_parsing_errors( $errno, $errstr, $errfile, $errline, array $errcontext ) {
		0 ignored issues – show Unused Code introduced 2017-08-07 06:10 UTC by Report Bug Copy Issue Report The parameter `$errline` is not used and could be removed. This check looks from parameters that have been defined for a function or method, but which are not used in the method body. Loading history... Unused Code introduced 2017-08-07 06:10 UTC by Report Bug Copy Issue Report The parameter `$errcontext` is not used and could be removed. This check looks from parameters that have been defined for a function or method, but which are not used in the method body. Loading history...
242		if ( ! ( error_reporting() & $errno ) ) { // @codingStandardsIgnoreLine.
243		return true; // not interesting.
244		}
245
246		// Ignore warnings from parser & let PHP handle the rest.
247		return $errno & E_USER_WARNING && 0 === substr_compare( $errfile, 'DOMTreeBuilder.php', -18 );
248		}
249
250		/**
251		* Retrieves an array of nodes that should be skipped during processing.
252		*
253		* @param \DOMXPath $xpath A valid XPath instance for the DOM to be queried.
254		* @param \DOMNode $initial_node The starting node of the XPath query.
255		* @param Settings $settings The settings to apply.
256		*
257		* @return \DOMNode[] An array of \DOMNode (can be empty).
258		*/
259		public function query_tags_to_ignore( \DOMXPath $xpath, \DOMNode $initial_node, Settings $settings ) {
260		$elements = [];
261		$query_parts = [];
262	View Code Duplication	if ( ! empty( $settings['ignoreTags'] ) ) {
263		$query_parts[] = '//' . implode( ' \| //', $settings['ignoreTags'] );
264		}
265	View Code Duplication	if ( ! empty( $settings['ignoreClasses'] ) ) {
266		$query_parts[] = "//*[contains(concat(' ', @class, ' '), ' " . implode( " ') or contains(concat(' ', @class, ' '), ' ", $settings['ignoreClasses'] ) . " ')]";
267		}
268	View Code Duplication	if ( ! empty( $settings['ignoreIDs'] ) ) {
269		$query_parts[] = '//*[@id=\'' . implode( '\' or @id=\'', $settings['ignoreIDs'] ) . '\']';
270		}
271
272	View Code Duplication	if ( ! empty( $query_parts ) ) {
273		$ignore_query = implode( ' \| ', $query_parts );
274
275		$nodelist = $xpath->query( $ignore_query, $initial_node );
276		if ( false !== $nodelist ) {
277		$elements = DOM::nodelist_to_array( $nodelist );
278		}
279		}
280
281		return $elements;
282		}
283
284		/**
285		* Replaces the given node with HTML content. Uses the HTML5 parser.
286		*
287		* @param \DOMNode $node The node to replace.
288		* @param string $content The HTML fragment used to replace the node.
289		*
290		* @return \DOMNode\|array An array of \DOMNode containing the new nodes or the old \DOMNode if the replacement failed.
291		*/
292		public function replace_node_with_html( \DOMNode $node, $content ) {
293		$result = $node;
294
295		$parent = $node->parentNode;
296		if ( empty( $parent ) ) {
297		return $node; // abort early to save cycles.
298		}
299
300		set_error_handler( [ $this, 'handle_parsing_errors' ] ); // @codingStandardsIgnoreLine.
301
302		$html_fragment = $this->get_html5_parser()->loadHTMLFragment( $content );
303		if ( ! empty( $html_fragment ) ) {
304		$imported_fragment = $node->ownerDocument->importNode( $html_fragment, true );
305
306	View Code Duplication	if ( ! empty( $imported_fragment ) ) {
307		// Save the children of the imported DOMDocumentFragment before replacement.
308		$children = DOM::nodelist_to_array( $imported_fragment->childNodes );
309
310		if ( false !== $parent->replaceChild( $imported_fragment, $node ) ) {
311		// Success! We return the saved array of DOMNodes as
312		// $imported_fragment is just an empty DOMDocumentFragment now.
313		$result = $children;
314		}
315		}
316		}
317
318		restore_error_handler();
319
320		return $result;
321		}
322
323		/**
324		* Retrieves the fix registry.
325		*
326		* @return Registry
327		*/
328		public function get_registry() {
329		if ( ! isset( $this->registry ) ) {
330		$this->registry = new Default_Registry( $this->get_hyphenator_cache() );
331		} elseif ( $this->update_registry_cache ) {
332		$this->registry->update_hyphenator_cache( $this->get_hyphenator_cache() );
333		$this->update_registry_cache = false;
334		}
335
336		return $this->registry;
337		}
338
339		/**
340		* Retrieves the HTML5 parser instance.
341		*
342		* @return \Masterminds\HTML5
343		*/
344		public function get_html5_parser() {
345		// Lazy-load HTML5 parser.
346		if ( ! isset( $this->html5_parser ) ) {
347		$this->html5_parser = new \Masterminds\HTML5( [
348		'disable_html_ns' => true,
349		] );
350		}
351
352		return $this->html5_parser;
353		}
354
355		/**
356		* Retrieves the hyphenator cache.
357		*
358		* @return Hyphenator\Cache
359		*/
360		public function get_hyphenator_cache() {
361		if ( ! isset( $this->hyphenator_cache ) ) {
362		$this->hyphenator_cache = new Hyphenator\Cache();
363		}
364
365		return $this->hyphenator_cache;
366		}
367
368		/**
369		* Injects an existing Hyphenator\Cache (to facilitate persistent language caching).
370		*
371		* @param Hyphenator\Cache $cache A hyphenator cache instance.
372		*/
373		public function set_hyphenator_cache( Hyphenator\Cache $cache ) {
374		$this->hyphenator_cache = $cache;
375
376		// Change hyphenator cache for existing token fixes.
377		if ( isset( $this->registry ) ) {
378		$this->registry->update_hyphenator_cache( $cache );
379		}
380		}
381
382		/**
383		* Retrieves the list of valid language plugins in the given directory.
384		*
385		* @param string $path The path in which to look for language plugin files.
386		*
387		* @return string[] An array in the form ( $language_code => $language_name ).
388		*/
389		private static function get_language_plugin_list( $path ) {
390		$language_name_pattern = '/"language"\s:\s((".+")\|(\'.+\'))\s*,/';
391		$languages = [];
392		$handle = opendir( $path );
393
394		// Read all files in directory.
395		$file = readdir( $handle );
396		while ( $file ) {
397		// We only want the JSON files.
398		if ( '.json' === substr( $file, -5 ) ) {
399		$file_content = file_get_contents( $path . $file );
400		if ( preg_match( $language_name_pattern, $file_content, $matches ) ) {
401		$language_name = substr( $matches[1], 1, -1 );
402		$language_code = substr( $file, 0, -5 );
403
404		$languages[ $language_code ] = $language_name;
405		}
406		}
407
408		// Read next file.
409		$file = readdir( $handle );
410		}
411		closedir( $handle );
412
413		// Sort translated language names according to current locale.
414		asort( $languages );
415
416		return $languages;
417		}
418
419		/**
420		* Retrieves the list of valid hyphenation languages.
421		*
422		* Note that this method reads all the language files on disc, so you should
423		* cache the results if possible.
424		*
425		* @return string[] An array in the form of ( LANG_CODE => LANGUAGE ).
426		*/
427		public static function get_hyphenation_languages() {
428		return self::get_language_plugin_list( __DIR__ . '/lang/' );
429		}
430
431		/**
432		* Retrieves the list of valid diacritic replacement languages.
433		*
434		* Note that this method reads all the language files on disc, so you should
435		* cache the results if possible.
436		*
437		* @return string[] An array in the form of ( LANG_CODE => LANGUAGE ).
438		*/
439		public static function get_diacritic_languages() {
440		return self::get_language_plugin_list( __DIR__ . '/diacritics/' );
441		}
442		}
443

mundschenk-at / php-typography

Scrutinizer GitHub App not installed

GitHub Access Token became invalid

Pull Request — master (#44)

PHP_Typography::process() A

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like