Parser::isImage() - Code Metrics - Inspection of "fix(encoding): convert HTML entities to UTF-8" - hypeJunction/http-parser - Measure and Improve Code Quality continuously with Scrutinizer

Passed

Push — master ( e50892...2ef246 )

by Ismayil

created 2016-10-14 18:08 UTC

Parser::isImage() A

↳ Parent: Parser

Complexity

Conditions	2
Paths	2

Size

Total Lines	9
Code Lines	6

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	6
CRAP Score	2

Importance

Changes

Metric	Value
dl	0
loc	9
ccs	6
cts	6
cp	1
rs	9.6666
c	0
b	0
f	0
cc	2
eloc	6
nc	2
nop	1
crap	2

<?php

namespace hypeJunction;

use DOMDocument;
use Exception;
use GuzzleHttp\ClientInterface;
use GuzzleHttp\Psr7\Response;

/**
 * Parses HTTP resource into a serialable array of metatags
 */
class Parser {

	/**
	 * @var ClientInterface
	 */
	private $client;

	/**
	 * @var array
	 */
	private static $cache;

	/**
	 * Constructor
	 * @param ClientInterface $client HTTP Client
	 */
	public function __construct(ClientInterface $client) {
		$this->client = $client;
	}

	/**
	 * Parses a URL into a an array of metatags
	 *
	 * @param string $url URL to parse
	 * @return array
	 */
	public function parse($url = '') {

		$data = $this->getImageData($url);
		if (!$data) {
			$data = $this->getOEmbedData($url);
		}
		if (!$data) {
			$data = $this->getDOMData($url);
			if (is_array($data) && !empty($data['oembed_url'])) {
				foreach ($data['oembed_url'] as $oembed_url) {
					$oembed_data = $this->parse($oembed_url);
					if (!empty($oembed_data) && is_array($oembed_data)) {
						$oembed_data['oembed_url'] = $oembed_data['url'];
						unset($oembed_data['url']);
						$data = array_merge($data, $oembed_data);
					}
				}
			}
		}
	
		if (!is_array($data)) {
			$data = array();
		}

		if (empty($data['thumbnail_url']) && !empty($data['thumbnails'])) {
			$data['thumbnail_url'] = $data['thumbnails'][0];
		}

		return $data;
	}

	/**
	 * Parses image metatags
	 *
	 * @param string $url URL of the image
	 * @return array|false
	 */
	public function getImageData($url = '') {
		if (!$this->isImage($url)) {
			return false;
		}

		return array(
			'type' => 'photo',
			'url' => $url,
			'thumbnails' => array($url),
		);
	}

	/**
	 * Parses OEmbed data
	 *
	 * @param  string $url URL of the image
	 * @return array|false
	 */
	public function getOEmbedData($url = '') {

		if (!$this->isJSON($url) && !$this->isXML($url)) {
			return false;
		}

		$meta = array(
			'url' => $url,
		);

		$content = $this->read($url);
		if (!$content) {
			return $meta;
		}

		$data = new \stdClass();
		if ($this->isJSON($url)) {
			$data = json_decode($content);
		} else if ($this->isXML($url)) {
			$data = simplexml_load_string($content);
		}

		$props = array(
			'type',
			'version',
			'title',
			'author_name',
			'author_url',
			'provider_name',
			'provider_url',
			'cache_age',
			'thumbnail_url',
			'thumbnail_width',
			'thumbnail_height',
			'width',
			'height',
			'html',
		);
		foreach ($props as $key) {
			if (!empty($data->$key)) {
				$meta[$key] = (string) $data->$key;
			}
		}
		return $meta;
	}

	/**
	 * Parses metatags from DOM
	 *
	 * @param  string $url URL
	 * @return array|false
	 */
	public function getDOMData($url = '') {

		if (!$this->isHTML($url)) {
			return false;
		}

		$doc = $this->getDOM($url);
		if (!$doc) {
			return false;
		}
		
		$defaults = array(
			'url' => $url,
		);

		$link_tags = $this->parseLinkTags($doc);
		$meta_tags = $this->parseMetaTags($doc);
		$img_tags = $this->parseImgTags($doc);

		$meta = array_merge_recursive($defaults, $link_tags, $meta_tags, $img_tags);
		
		if (empty($meta['title'])) {
			$meta['title'] = $this->parseTitle($doc);
		}


		return $meta;
	}

	/**
	 * Check if URL exists and is reachable by making an HTTP request to retrieve header information
	 *
	 * @param string $url URL of the resource
	 * @return boolean
	 */
	public function exists($url = '') {
		$response = $this->request($url);
		if ($response instanceof Response) {
			return $response->getStatusCode() == 200;
		}
		return false;
	}

	/**
	 * Returns head of the resource
	 *
	 * @param string $url URL of the resource
	 * @return Response|false
	 */
	public function request($url = '') {
		if (!filter_var($url, FILTER_VALIDATE_URL)) {
			return false;
		}
		if (!isset(self::$cache[$url])) {
			try {
				$response = $this->client->request('GET', $url);
			} catch (Exception $e) {
				$response = false;
				error_log("Parser Error for HEAD request ($url): {$e->getMessage()}");
			}
			self::$cache[$url] = $response;
		}

		return self::$cache[$url];
	}

	/**
	 * Get contents of the page
	 *
	 * @param string $url URL of the resource
	 * @return string
	 */
	public function read($url = '') {
		$body = '';
		if (!$this->exists($url)) {
			return $body;
		}

		$response = $this->request($url);
		$body = (string) $response->getBody();
		return $body;
	}

	/**
	 * Checks if resource is an html page
	 *
	 * @param string $url URL of the resource
	 * @return boolean
	 */
	public function isHTML($url = '') {
		$mime = $this->getContentType($url);
		return strpos($mime, 'text/html') !== false;
	}

	/**
	 * Checks if resource is JSON
	 *
	 * @param string $url URL of the resource
	 * @return boolean
	 */
	public function isJSON($url = '') {
		$mime = $this->getContentType($url);
		return strpos($mime, 'json') !== false;
	}

	/**
	 * Checks if resource is XML
	 *
	 * @param string $url URL of the resource
	 * @return boolean
	 */
	public function isXML($url = '') {
		$mime = $this->getContentType($url);
		return strpos($mime, 'xml') !== false;
	}

	/**
	 * Checks if resource is an image
	 *
	 * @param string $url URL of the resource
	 * @return boolean
	 */
	public function isImage($url = '') {
		$mime = $this->getContentType($url);
		if ($mime) {
			list($simple,) = explode('/', $mime);
			return ($simple == 'image');
		}

		return false;
	}

	/**
	 * Get mime type of the URL content
	 *
	 * @param string $url URL of the resource
	 * @return string
	 */
	public function getContentType($url = '') {
		$response = $this->request($url);
		if ($response instanceof Response) {
			$header = $response->getHeader('Content-Type');
			if (is_array($header) && !empty($header)) {
				$parts = explode(';', $header[0]);
				return trim($parts[0]);
			}
		}
		return '';
	}

	/**
	 * Returns HTML contents of the page
	 *
	 * @param string $url URL of the resource
	 * @return string
	 */
	public function getHTML($url = '') {
		if (!$this->isHTML($url)) {
			return '';
		}
		return $this->read($url);
	}

	/**
	 * Returns HTML contents of the page as a DOMDocument
	 *
	 * @param string $url URL of the resource
	 * @return DOMDocument|false
	 */
	public function getDOM($url = '') {
		$html = $this->getHTML($url);
		if (empty($html)) {
			return false;
		}
		$doc = new DOMDocument();
		if (is_callable('mb_convert_encoding')) {
			$doc->loadHTML(mb_convert_encoding($html, 'HTML-ENTITIES', 'UTF-8'));
		} else {
			$doc->loadHTML($html);
		}
		if (!$doc->documentURI) {
			$doc->documentURI = $url;
		}
		return $doc;
	}

	/**
	 * Parses document title
	 *
	 * @param DOMDocument $doc Document
	 * @return string
	 */
	public function parseTitle(DOMDocument $doc) {
		$node = $doc->getElementsByTagName('title');
		$title = $node->item(0)->nodeValue;
		return ($title) ?: '';
	}

	/**
	 * Parses <link> tags
	 *
	 * @param DOMDocument $doc Document
	 * @return array
	 */
	public function parseLinkTags(DOMDocument $doc) {

		$meta = array();

		$nodes = $doc->getElementsByTagName('link');
		foreach ($nodes as $node) {
			$rel = $node->getAttribute('rel');
			$href = $node->getAttribute('href');

			switch ($rel) {

				case 'icon' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
					$meta['icons'][] = $this->getAbsoluteURL($doc, $href);
					break;

				case 'canonical' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
					$meta['canonical'] = $this->getAbsoluteURL($doc, $href);
					break;

				case 'alternate' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
					$type = $node->getAttribute('type');
					if (in_array($type, array(
								'application/json+oembed',
								'text/json+oembed',
								'application/xml+oembed',
								'text/xml+oembed'
							))) {
						$meta['oembed_url'][] = $this->getAbsoluteURL($doc, $href);
					}
					break;
			}
		}

		return $meta;
	}

	/**
	 * Parses <meta> tags
	 *
	 * @param DOMDocument $doc Document
	 * @return array
	 */
	public function parseMetaTags(DOMDocument $doc) {

		$meta = array();

		$nodes = $doc->getElementsByTagName('meta');
		if (!empty($nodes)) {
			foreach ($nodes as $node) {
				$name = $node->getAttribute('name');
				if (!$name) {
					$name = $node->getAttribute('property');
				}
				if (!$name) {
					continue;
				}

				$name = strtolower($name);

				$content = $node->getAttribute('content');
				if (isset($meta['metatags'][$name])) {
					if (!is_array($meta['metatags'][$name])) {
						$meta['metatags'][$name] = array($meta['metatags'][$name]);
					}
					$meta['metatags'][$name][] = $content;
				} else {
					$meta['metatags'][$name] = $content;
				}

				switch ($name) {

					case 'title' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
					case 'og:title' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
					case 'twitter:title' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
						if (empty($meta['title'])) {
							$meta['title'] = $content;
						}
						break;

					case 'og:type' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
						if (empty($meta['type'])) {
							$meta['type'] = $content;
						}
						break;

					case 'description' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
					case 'og:description' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
					case 'twitter:description' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
						if (empty($meta['description'])) {
							$meta['description'] = $content;
						}
						break;

					case 'keywords' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
						if (is_string($content)) {
							$content = explode(',', $content);
							$content = array_map('trim', $content);
						}
						$meta['tags'] = $content;
						break;

					case 'og:site_name' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
					case 'twitter:site' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
						if (empty($meta['provider_name'])) {
							$meta['provider_name'] = $content;
						}
						break;

					case 'og:image' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
					case 'twitter:image' :
switch ($selector) {
    case "A": //right
        doSomething();
        break;
    case "B" : //wrong
        doSomethingElse();
        break;
}
						$meta['thumbnails'][] = $this->getAbsoluteURL($doc, $content);
						break;
				}
			}
		}

		return $meta;
	}

	/**
	 * Parses <img> tags
	 *
	 * @param DOMDocument $doc Document
	 * @return array
	 */
	public function parseImgTags(DOMDocument $doc) {

		$meta = array();

		$nodes = $doc->getElementsByTagName('img');
		foreach ($nodes as $node) {
			$src = $node->getAttribute('src');
			$meta['thumbnails'][] = $this->getAbsoluteURL($doc, $src);
		}

		return $meta;
	}

	/**
	 * Normalizes relative URLs
	 *
	 * @param DOMDocument $doc  Document
	 * @param string      $href URL to normalize
	 * @return string
	 */
	public function getAbsoluteURL(DOMDocument $doc, $href = '') {

		// Check if $url is absolute
		if (parse_url($href, PHP_URL_HOST)) {
			return $href;
		}

		$uri = trim($doc->documentURI ?: '', '/');

		// Check if $url is relative to root
		if (substr($href, 0, 1) === "/") {
			$scheme = parse_url($uri, PHP_URL_SCHEME);
			$host = parse_url($uri, PHP_URL_HOST);
			return "$scheme://$host$href";
		}

		// $url is relative to page
		return "$uri/$href";
	}

}


1		<?php
2
3		namespace hypeJunction;
4
5		use DOMDocument;
6		use Exception;
7		use GuzzleHttp\ClientInterface;
8		use GuzzleHttp\Psr7\Response;
9
10		/**
11		* Parses HTTP resource into a serialable array of metatags
12		*/
13		class Parser {
14
15		/**
16		* @var ClientInterface
17		*/
18		private $client;
19
20		/**
21		* @var array
22		*/
23		private static $cache;
24
25		/**
26		* Constructor
27		* @param ClientInterface $client HTTP Client
28		*/
29		public function __construct(ClientInterface $client) {
30		$this->client = $client;
31		}
32
33		/**
34		* Parses a URL into a an array of metatags
35		*
36		* @param string $url URL to parse
37		* @return array
38		*/
39	1	public function parse($url = '') {
40
41	1	$data = $this->getImageData($url);
42	1	if (!$data) {
43	1	$data = $this->getOEmbedData($url);
44	1	}
45	1	if (!$data) {
46	1	$data = $this->getDOMData($url);
47	1	if (is_array($data) && !empty($data['oembed_url'])) {
48	1	foreach ($data['oembed_url'] as $oembed_url) {
49	1	$oembed_data = $this->parse($oembed_url);
50	1	if (!empty($oembed_data) && is_array($oembed_data)) {
51		$oembed_data['oembed_url'] = $oembed_data['url'];
52		unset($oembed_data['url']);
53		$data = array_merge($data, $oembed_data);
54		}
55	1	}
56	1	}
57	1	}
58
59	1	if (!is_array($data)) {
60	1	$data = array();
61	1	}
62
63	1	if (empty($data['thumbnail_url']) && !empty($data['thumbnails'])) {
64	1	$data['thumbnail_url'] = $data['thumbnails'][0];
65	1	}
66
67	1	return $data;
68		}
69
70		/**
71		* Parses image metatags
72		*
73		* @param string $url URL of the image
74		* @return array\|false
75		*/
76	1	public function getImageData($url = '') {
77	1	if (!$this->isImage($url)) {
78	1	return false;
79		}
80
81		return array(
82	1	'type' => 'photo',
83	1	'url' => $url,
84	1	'thumbnails' => array($url),
85	1	);
86		}
87
88		/**
89		* Parses OEmbed data
90		*
91		* @param string $url URL of the image
92		* @return array\|false
93		*/
94	2	public function getOEmbedData($url = '') {
95
96	2	if (!$this->isJSON($url) && !$this->isXML($url)) {
97	1	return false;
98		}
99
100		$meta = array(
101	2	'url' => $url,
102	2	);
103
104	2	$content = $this->read($url);
105	2	if (!$content) {
106		return $meta;
107		}
108
109	2	$data = new \stdClass();
110	2	if ($this->isJSON($url)) {
111	1	$data = json_decode($content);
112	2	} else if ($this->isXML($url)) {
113	1	$data = simplexml_load_string($content);
114	1	}
115
116		$props = array(
117	2	'type',
118	2	'version',
119	2	'title',
120	2	'author_name',
121	2	'author_url',
122	2	'provider_name',
123	2	'provider_url',
124	2	'cache_age',
125	2	'thumbnail_url',
126	2	'thumbnail_width',
127	2	'thumbnail_height',
128	2	'width',
129	2	'height',
130	2	'html',
131	2	);
132	2	foreach ($props as $key) {
133	2	if (!empty($data->$key)) {
134	2	$meta[$key] = (string) $data->$key;
135	2	}
136	2	}
137	2	return $meta;
138		}
139
140		/**
141		* Parses metatags from DOM
142		*
143		* @param string $url URL
144		* @return array\|false
145		*/
146	1	public function getDOMData($url = '') {
147
148	1	if (!$this->isHTML($url)) {
149	1	return false;
150		}
151
152	1	$doc = $this->getDOM($url);
153	1	if (!$doc) {
154		return false;
155		}
156
157		$defaults = array(
158	1	'url' => $url,
159	1	);
160
161	1	$link_tags = $this->parseLinkTags($doc);
162	1	$meta_tags = $this->parseMetaTags($doc);
163	1	$img_tags = $this->parseImgTags($doc);
164
165	1	$meta = array_merge_recursive($defaults, $link_tags, $meta_tags, $img_tags);
166
167	1	if (empty($meta['title'])) {
168		$meta['title'] = $this->parseTitle($doc);
169		}
170
171
172	1	return $meta;
173		}
174
175		/**
176		* Check if URL exists and is reachable by making an HTTP request to retrieve header information
177		*
178		* @param string $url URL of the resource
179		* @return boolean
180		*/
181	1	public function exists($url = '') {
182	1	$response = $this->request($url);
183	1	if ($response instanceof Response) {
184	1	return $response->getStatusCode() == 200;
185		}
186		return false;
187		}
188
189		/**
190		* Returns head of the resource
191		*
192		* @param string $url URL of the resource
193		* @return Response\|false
194		*/
195	1	public function request($url = '') {
196	1	if (!filter_var($url, FILTER_VALIDATE_URL)) {
197		return false;
198		}
199	1	if (!isset(self::$cache[$url])) {
200		try {
201	1	$response = $this->client->request('GET', $url);
202	1	} catch (Exception $e) {
203		$response = false;
204		error_log("Parser Error for HEAD request ($url): {$e->getMessage()}");
205		}
206	1	self::$cache[$url] = $response;
207	1	}
208
209	1	return self::$cache[$url];
210		}
211
212		/**
213		* Get contents of the page
214		*
215		* @param string $url URL of the resource
216		* @return string
217		*/
218	1	public function read($url = '') {
219	1	$body = '';
220	1	if (!$this->exists($url)) {
221	1	return $body;
222		}
223
224	1	$response = $this->request($url);
225	1	$body = (string) $response->getBody();
226	1	return $body;
227		}
228
229		/**
230		* Checks if resource is an html page
231		*
232		* @param string $url URL of the resource
233		* @return boolean
234		*/
235	1	public function isHTML($url = '') {
236	1	$mime = $this->getContentType($url);
237	1	return strpos($mime, 'text/html') !== false;
238		}
239
240		/**
241		* Checks if resource is JSON
242		*
243		* @param string $url URL of the resource
244		* @return boolean
245		*/
246	1	public function isJSON($url = '') {
247	1	$mime = $this->getContentType($url);
248	1	return strpos($mime, 'json') !== false;
249		}
250
251		/**
252		* Checks if resource is XML
253		*
254		* @param string $url URL of the resource
255		* @return boolean
256		*/
257	1	public function isXML($url = '') {
258	1	$mime = $this->getContentType($url);
259	1	return strpos($mime, 'xml') !== false;
260		}
261
262		/**
263		* Checks if resource is an image
264		*
265		* @param string $url URL of the resource
266		* @return boolean
267		*/
268	1	public function isImage($url = '') {
269	1	$mime = $this->getContentType($url);
270	1	if ($mime) {
271	1	list($simple,) = explode('/', $mime);
272	1	return ($simple == 'image');
273		}
274
275	1	return false;
276		}
277
278		/**
279		* Get mime type of the URL content
280		*
281		* @param string $url URL of the resource
282		* @return string
283		*/
284	1	public function getContentType($url = '') {
285	1	$response = $this->request($url);
286	1	if ($response instanceof Response) {
287	1	$header = $response->getHeader('Content-Type');
288	1	if (is_array($header) && !empty($header)) {
289	1	$parts = explode(';', $header[0]);
290	1	return trim($parts[0]);
291		}
292	1	}
293	1	return '';
294		}
295
296		/**
297		* Returns HTML contents of the page
298		*
299		* @param string $url URL of the resource
300		* @return string
301		*/
302	1	public function getHTML($url = '') {
303	1	if (!$this->isHTML($url)) {
304	1	return '';
305		}
306	1	return $this->read($url);
307		}
308
309		/**
310		* Returns HTML contents of the page as a DOMDocument
311		*
312		* @param string $url URL of the resource
313		* @return DOMDocument\|false
314		*/
315	1	public function getDOM($url = '') {
316	1	$html = $this->getHTML($url);
317	1	if (empty($html)) {
318	1	return false;
319		}
320	1	$doc = new DOMDocument();
321	1	if (is_callable('mb_convert_encoding')) {
322	1	$doc->loadHTML(mb_convert_encoding($html, 'HTML-ENTITIES', 'UTF-8'));
323	1	} else {
324		$doc->loadHTML($html);
325		}
326	1	if (!$doc->documentURI) {
327	1	$doc->documentURI = $url;
328	1	}
329	1	return $doc;
330		}
331
332		/**
333		* Parses document title
334		*
335		* @param DOMDocument $doc Document
336		* @return string
337		*/
338	1	public function parseTitle(DOMDocument $doc) {
339	1	$node = $doc->getElementsByTagName('title');
340	1	$title = $node->item(0)->nodeValue;
341	1	return ($title) ?: '';
342		}
343
344		/**
345		* Parses <link> tags
346		*
347		* @param DOMDocument $doc Document
348		* @return array
349		*/
350	1	public function parseLinkTags(DOMDocument $doc) {
351
352	1	$meta = array();
353
354	1	$nodes = $doc->getElementsByTagName('link');
355	1	foreach ($nodes as $node) {
356	1	$rel = $node->getAttribute('rel');
357	1	$href = $node->getAttribute('href');
358
359		switch ($rel) {
360
361	1	case 'icon' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
362	1	$meta['icons'][] = $this->getAbsoluteURL($doc, $href);
363	1	break;
364
365	1	case 'canonical' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
366	1	$meta['canonical'] = $this->getAbsoluteURL($doc, $href);
367	1	break;
368
369	1	case 'alternate' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
370	1	$type = $node->getAttribute('type');
371	1	if (in_array($type, array(
372	1	'application/json+oembed',
373	1	'text/json+oembed',
374	1	'application/xml+oembed',
375		'text/xml+oembed'
376	1	))) {
377	1	$meta['oembed_url'][] = $this->getAbsoluteURL($doc, $href);
378	1	}
379	1	break;
380		}
381	1	}
382
383	1	return $meta;
384		}
385
386		/**
387		* Parses <meta> tags
388		*
389		* @param DOMDocument $doc Document
390		* @return array
391		*/
392	1	public function parseMetaTags(DOMDocument $doc) {
393
394	1	$meta = array();
395
396	1	$nodes = $doc->getElementsByTagName('meta');
397	1	if (!empty($nodes)) {
398	1	foreach ($nodes as $node) {
399	1	$name = $node->getAttribute('name');
400	1	if (!$name) {
401	1	$name = $node->getAttribute('property');
402	1	}
403	1	if (!$name) {
404	1	continue;
405		}
406
407	1	$name = strtolower($name);
408
409	1	$content = $node->getAttribute('content');
410	1	if (isset($meta['metatags'][$name])) {
411	1	if (!is_array($meta['metatags'][$name])) {
412	1	$meta['metatags'][$name] = array($meta['metatags'][$name]);
413	1	}
414	1	$meta['metatags'][$name][] = $content;
415	1	} else {
416	1	$meta['metatags'][$name] = $content;
417		}
418
419		switch ($name) {
420
421	1	case 'title' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
422	1	case 'og:title' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
423	1	case 'twitter:title' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
424	1	if (empty($meta['title'])) {
425	1	$meta['title'] = $content;
426	1	}
427	1	break;
428
429	1	case 'og:type' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
430	1	if (empty($meta['type'])) {
431	1	$meta['type'] = $content;
432	1	}
433	1	break;
434
435	1	case 'description' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
436	1	case 'og:description' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
437	1	case 'twitter:description' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
438	1	if (empty($meta['description'])) {
439	1	$meta['description'] = $content;
440	1	}
441	1	break;
442
443	1	case 'keywords' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
444	1	if (is_string($content)) {
445	1	$content = explode(',', $content);
446	1	$content = array_map('trim', $content);
447	1	}
448	1	$meta['tags'] = $content;
449	1	break;
450
451	1	case 'og:site_name' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
452	1	case 'twitter:site' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
453	1	if (empty($meta['provider_name'])) {
454	1	$meta['provider_name'] = $content;
455	1	}
456	1	break;
457
458	1	case 'og:image' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
459	1	case 'twitter:image' :
		0 ignored issues – show Coding Style introduced 2016-02-07 16:27 UTC by Report Bug Copy Issue Report There must be no space before the colon in a CASE statement As per the PSR-2 coding standard, there must not be a space in front of the colon in case statements. switch ($selector) { case "A": //right doSomething(); break; case "B" : //wrong doSomethingElse(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
460	1	$meta['thumbnails'][] = $this->getAbsoluteURL($doc, $content);
461	1	break;
462		}
463	1	}
464	1	}
465
466	1	return $meta;
467		}
468
469		/**
470		* Parses <img> tags
471		*
472		* @param DOMDocument $doc Document
473		* @return array
474		*/
475	1	public function parseImgTags(DOMDocument $doc) {
476
477	1	$meta = array();
478
479	1	$nodes = $doc->getElementsByTagName('img');
480	1	foreach ($nodes as $node) {
481	1	$src = $node->getAttribute('src');
482	1	$meta['thumbnails'][] = $this->getAbsoluteURL($doc, $src);
483	1	}
484
485	1	return $meta;
486		}
487
488		/**
489		* Normalizes relative URLs
490		*
491		* @param DOMDocument $doc Document
492		* @param string $href URL to normalize
493		* @return string
494		*/
495	1	public function getAbsoluteURL(DOMDocument $doc, $href = '') {
496
497		// Check if $url is absolute
498	1	if (parse_url($href, PHP_URL_HOST)) {
499	1	return $href;
500		}
501
502	1	$uri = trim($doc->documentURI ?: '', '/');
503
504		// Check if $url is relative to root
505	1	if (substr($href, 0, 1) === "/") {
506	1	$scheme = parse_url($uri, PHP_URL_SCHEME);
507	1	$host = parse_url($uri, PHP_URL_HOST);
508	1	return "$scheme://$host$href";
509		}
510
511		// $url is relative to page
512	1	return "$uri/$href";
513		}
514
515		}
516

hypeJunction / http-parser

Push — master ( e50892...2ef246 )

Parser::isImage() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like