Parser::parse() - Code Metrics - Inspection of "MediaEmbed: reorganized some code. No functional c..." - s9e/TextFormatter - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 0e549e...7e9c0f )

by Josh

created 2016-09-30 17:25 UTC

Parser::parse() A

↳ Parent: Parser

Complexity

Conditions	2
Paths	2

Size

Total Lines	13
Code Lines	7

Duplication

Lines	0
Ratio	0 %

Code Coverage

Tests	9
CRAP Score	2

Importance

Changes

Metric	Value
cc	2
eloc	7
nc	2
nop	2
dl	0
loc	13
ccs	9
cts	9
cp	1
crap	2
rs	9.4285
c	0
b	0
f	0

<?php

/**
* @package   s9e\TextFormatter
* @copyright Copyright (c) 2010-2016 The s9e Authors
* @license   http://www.opensource.org/licenses/mit-license.php The MIT License
*/
namespace s9e\TextFormatter\Plugins\MediaEmbed;

use s9e\TextFormatter\Utils\Http;
use s9e\TextFormatter\Parser as TagStack;
use s9e\TextFormatter\Parser\Tag;
use s9e\TextFormatter\Plugins\ParserBase;

class Parser extends ParserBase
{
	/**
	* @var \s9e\TextFormatter\Utils\Http\Client Client used to perform HTTP request
	*/
	protected static $client;

	/**
	* {@inheritdoc}
	*/
	public function parse($text, array $matches)
	{
		foreach ($matches as $m)
		{
			$url = $m[0][0];
			$pos = $m[0][1];
			$len = strlen($url);

			// Give that tag priority over other tags such as Autolink's
			$tag = $this->parser->addSelfClosingTag('MEDIA', $pos, $len, -10);
			$tag->setAttribute('url', $url);
		}
	}

	/**
	* Filter a MEDIA tag
	*
	* This will always invalidate the original tag, and possibly replace it with the tag that
	* corresponds to the media site
	*
	* @param  Tag      $tag      The original tag
	* @param  TagStack $tagStack Parser instance, so that we can add the new tag to the stack
	* @param  array    $sites    Map of [host => siteId]
	* @return bool               Unconditionally FALSE
	*/
	public static function filterTag(Tag $tag, TagStack $tagStack, array $sites)
	{
		if ($tag->hasAttribute('media'))
		{
			self::addTagFromMediaId($tag, $tagStack, $sites);
		}
		elseif ($tag->hasAttribute('url'))
		{
			self::addTagFromMediaUrl($tag, $tagStack, $sites);
		}

		return false;
	}

	/**
	* Test whether a given tag has at least one non-default attribute
	*
	* @param  Tag  $tag The original tag
	* @return bool      Whether the tag contains an attribute not named "url"
	*/
	public static function hasNonDefaultAttribute(Tag $tag)
	{
		foreach ($tag->getAttributes() as $attrName => $void)
		{
			if ($attrName !== 'url')
			{
				return true;
			}
		}

		return false;
	}

	/**
	* Scrape the content of an URL to extract some data
	*
	* @param  Tag    $tag          Source tag
	* @param  array  $scrapeConfig Array of scrape directives
	* @param  string $cacheDir     Path to the cache directory
	* @return bool                 Unconditionally TRUE
	*/
	public static function scrape(Tag $tag, array $scrapeConfig, $cacheDir = null)
	{
		if ($tag->hasAttribute('url'))
		{
			// Ensure that the URL actually looks like a URL if we want to use it to scrape
			$url = $tag->getAttribute('url');
			if (preg_match('#^https?://[^<>"\'\\s]+$#D', $url))
			{
				foreach ($scrapeConfig as $scrape)
				{
					self::scrapeEntry($url, $tag, $scrape, $cacheDir);
				}
			}
		}

		return true;
	}

	//==============================================================================================
	// Internals
	//==============================================================================================

	/**
	* Add a site tag
	*
	* @param  Tag      $tag      The original tag
	* @param  TagStack $tagStack Parser instance, so that we can add the new tag to the stack
	* @param  string   $siteId   Site ID
	* @return void
	*/
	protected static function addSiteTag(Tag $tag, TagStack $tagStack, $siteId)
	{
		$endTag = $tag->getEndTag() ?: $tag;

		// Compute the boundaries of our new tag
		$lpos = $tag->getPos();
		$rpos = $endTag->getPos() + $endTag->getLen();

		// Create a new tag and copy this tag's attributes and priority
		$tagStack->addTagPair(strtoupper($siteId), $lpos, 0, $rpos, 0, $tag->getSortPriority())->setAttributes($tag->getAttributes());
	}

	/**
	* Add a media site tag based on the attributes of a MEDIA tag
	*
	* @param  Tag      $tag      The original tag
	* @param  TagStack $tagStack Parser instance
	* @param  array    $sites    Map of [host => siteId]
	* @return void
	*/
	protected static function addTagFromMediaId(Tag $tag, TagStack $tagStack, array $sites)
	{
		$siteId = strtolower($tag->getAttribute('media'));
		if (in_array($siteId, $sites, true))
		{
			self::addSiteTag($tag, $tagStack, $siteId);
		}
	}

	/**
	* Add a media site tag based on the url attribute of a MEDIA tag
	*
	* @param  Tag      $tag      The original tag
	* @param  TagStack $tagStack Parser instance
	* @param  array    $sites    Map of [host => siteId]
	* @return void
	*/
	protected static function addTagFromMediaUrl(Tag $tag, TagStack $tagStack, array $sites)
	{
		// Capture the scheme and (if applicable) host of the URL
		$p = parse_url($tag->getAttribute('url'));
		if (isset($p['scheme']) && isset($sites[$p['scheme'] . ':']))
		{
			$siteId = $sites[$p['scheme'] . ':'];
		}
		elseif (isset($p['host']))
		{
			$siteId = self::findSiteIdByHost($p['host'], $sites);
		}

		if (!empty($siteId))
		{
			self::addSiteTag($tag, $tagStack, $siteId);
		}
	}

	/**
	* Match a given host to a site ID
	*
	* @param  string      $host  Host
	* @param  array       $sites Map of [host => siteId]
	* @return string|bool        Site ID or FALSE
	*/
	protected static function findSiteIdByHost($host, array $sites)
	{
		// Start with the full host then pop domain labels off the start until we get a match
		do
		{
			if (isset($sites[$host]))
			{
				return $sites[$host];
			}

			$pos = strpos($host, '.');
			if ($pos === false)
			{
				break;
			}

			$host = substr($host, 1 + $pos);
		}
		while ($host > '');

		return false;
	}

	/**
	* Return a cached instance of the HTTP client
	*
	* @return \s9e\TextFormatter\Utils\Http\Client
	*/
	protected static function getHttpClient()
	{
		if (!isset(self::$client))
		{
			self::$client = Http::getClient();
		}
		self::$client->timeout = 10;

		return self::$client;
	}

	/**
	* Replace {@var} tokens in given URL
	*
	* @param  string   $url  Original URL
	* @param  string[] $vars Replacements
	* @return string         Modified URL
	*/
	protected static function replaceTokens($url, array $vars)
	{
		return preg_replace_callback(
			'#\\{@(\\w+)\\}#',
			function ($m) use ($vars)
			{
				return (isset($vars[$m[1]])) ? $vars[$m[1]] : '';
			},
			$url
		);
	}

	/**
	* Scrape the content of an URL to extract some data
	*
	* @param  string $url      Original URL
	* @param  Tag    $tag      Source tag
	* @param  array  $scrape   Array of scrape directives
	* @param  string $cacheDir Path to the cache directory
	* @return void
	*/
	protected static function scrapeEntry($url, Tag $tag, array $scrape, $cacheDir)
	{
		list($matchRegexps, $extractRegexps, $attrNames) = $scrape;

		if (!self::tagIsMissingAnyAttribute($tag, $attrNames))
		{
			return;
		}

		// Test whether this URL matches any regexp
		$vars    = [];
		$matched = false;
		foreach ((array) $matchRegexps as $matchRegexp)
		{
			if (preg_match($matchRegexp, $url, $m))
			{
				$vars   += $m;
				$matched = true;
			}
		}
		if (!$matched)
		{
			return;
		}

		// Add the tag's attributes to the named captures from the "match" regexp
		$vars += $tag->getAttributes();

		$scrapeUrl = (isset($scrape[3])) ? self::replaceTokens($scrape[3], $vars) : $url;
		self::scrapeUrl($scrapeUrl, $tag, (array) $extractRegexps, $cacheDir);
	}

	/**
	* Scrape a URL to help fill a tag's attributes
	*
	* @param  string      $url      URL to scrape
	* @param  Tag         $tag      Tag to fill
	* @param  string[]    $regexps  Regexps used to extract content from the page
	* @param  string|null $cacheDir Path to the cache directory
	* @return void
	*/
	protected static function scrapeUrl($url, Tag $tag, array $regexps, $cacheDir)
	{
		$content = self::wget($url, $cacheDir);

		// Execute the extract regexps and fill any missing attribute
		foreach ($regexps as $regexp)
		{
			if (preg_match($regexp, $content, $m))
			{
				foreach ($m as $k => $v)
				{
					if (!is_numeric($k) && !$tag->hasAttribute($k))
					{
						$tag->setAttribute($k, $v);
					}
				}
			}
		}
	}

	/**
	* Test whether a tag is missing any of given attributes
	*
	* @param  Tag      $tag
	* @param  string[] $attrNames
	* @return bool
	*/
	protected static function tagIsMissingAnyAttribute(Tag $tag, array $attrNames)
	{
		foreach ($attrNames as $attrName)
		{
			if (!$tag->hasAttribute($attrName))
			{
				return true;
			}
		}

		return false;
	}

	/**
	* Retrieve external content (possibly from the cache)
	*
	* If the cache directory exists, the external content will be saved into it. Cached content is
	* never pruned
	*
	* @param  string $url      URL
	* @param  string $cacheDir Path to the cache directory
	* @return string           External content
	*/
	protected static function wget($url, $cacheDir = null)
	{
		$prefix = '';
		$url    = preg_replace('(#.*)s', '', $url);

		// Return the content from the cache if applicable
		if (isset($cacheDir) && file_exists($cacheDir))
		{
			$cacheFile = $cacheDir . '/http.' . crc32($url);
			if (extension_loaded('zlib'))
			{
				$prefix     = 'compress.zlib://';
				$cacheFile .= '.gz';
			}
			if (file_exists($cacheFile))
			{
				return file_get_contents($prefix . $cacheFile);
			}
		}

		// Retrieve the external content from the source
		$content = @self::getHttpClient()->get($url, ['User-Agent: PHP (not Mozilla)']);

		// Save to the cache if applicable
		if (isset($cacheFile) && !empty($content))
		{
			file_put_contents($prefix . $cacheFile, $content);
		}

		return $content;
	}
}

1		<?php
2
3		/**
4		* @package s9e\TextFormatter
5		* @copyright Copyright (c) 2010-2016 The s9e Authors
6		* @license http://www.opensource.org/licenses/mit-license.php The MIT License
7		*/
8		namespace s9e\TextFormatter\Plugins\MediaEmbed;
9
10		use s9e\TextFormatter\Utils\Http;
11		use s9e\TextFormatter\Parser as TagStack;
12		use s9e\TextFormatter\Parser\Tag;
13		use s9e\TextFormatter\Plugins\ParserBase;
14
15		class Parser extends ParserBase
16		{
17		/**
18		* @var \s9e\TextFormatter\Utils\Http\Client Client used to perform HTTP request
19		*/
20		protected static $client;
21
22		/**
23		* {@inheritdoc}
24		*/
25	355	public function parse($text, array $matches)
26		{
27	355	foreach ($matches as $m)
28		{
29	355	$url = $m[0][0];
30	355	$pos = $m[0][1];
31	355	$len = strlen($url);
32
33		// Give that tag priority over other tags such as Autolink's
34	355	$tag = $this->parser->addSelfClosingTag('MEDIA', $pos, $len, -10);
35	355	$tag->setAttribute('url', $url);
36	355	}
37	355	}
38
39		/**
40		* Filter a MEDIA tag
41		*
42		* This will always invalidate the original tag, and possibly replace it with the tag that
43		* corresponds to the media site
44		*
45		* @param Tag $tag The original tag
46		* @param TagStack $tagStack Parser instance, so that we can add the new tag to the stack
47		* @param array $sites Map of [host => siteId]
48		* @return bool Unconditionally FALSE
49		*/
50	357	public static function filterTag(Tag $tag, TagStack $tagStack, array $sites)
51		{
52	357	if ($tag->hasAttribute('media'))
53	357	{
54	6	self::addTagFromMediaId($tag, $tagStack, $sites);
55	6	}
56	352	elseif ($tag->hasAttribute('url'))
57		{
58	352	self::addTagFromMediaUrl($tag, $tagStack, $sites);
59	352	}
60
61	357	return false;
62		}
63
64		/**
65		* Test whether a given tag has at least one non-default attribute
66		*
67		* @param Tag $tag The original tag
68		* @return bool Whether the tag contains an attribute not named "url"
69		*/
70	54	public static function hasNonDefaultAttribute(Tag $tag)
71		{
72	54	foreach ($tag->getAttributes() as $attrName => $void)
73		{
74	54	if ($attrName !== 'url')
75	54	{
76	50	return true;
77		}
78	50	}
79
80	5	return false;
81		}
82
83		/**
84		* Scrape the content of an URL to extract some data
85		*
86		* @param Tag $tag Source tag
87		* @param array $scrapeConfig Array of scrape directives
88		* @param string $cacheDir Path to the cache directory
89		* @return bool Unconditionally TRUE
90		*/
91	120	public static function scrape(Tag $tag, array $scrapeConfig, $cacheDir = null)
92		{
93	120	if ($tag->hasAttribute('url'))
94	120	{
95		// Ensure that the URL actually looks like a URL if we want to use it to scrape
96	119	$url = $tag->getAttribute('url');
97	119	if (preg_match('#^https?://[^<>"\'\\s]+$#D', $url))
98	119	{
99	116	foreach ($scrapeConfig as $scrape)
100		{
101	116	self::scrapeEntry($url, $tag, $scrape, $cacheDir);
102	116	}
103	116	}
104	119	}
105
106	120	return true;
107		}
108
109		//==============================================================================================
110		// Internals
111		//==============================================================================================
112
113		/**
114		* Add a site tag
115		*
116		* @param Tag $tag The original tag
117		* @param TagStack $tagStack Parser instance, so that we can add the new tag to the stack
118		* @param string $siteId Site ID
119		* @return void
120		*/
121	355	protected static function addSiteTag(Tag $tag, TagStack $tagStack, $siteId)
122		{
123	355	$endTag = $tag->getEndTag() ?: $tag;
124
125		// Compute the boundaries of our new tag
126	355	$lpos = $tag->getPos();
127	355	$rpos = $endTag->getPos() + $endTag->getLen();
128
129		// Create a new tag and copy this tag's attributes and priority
130	355	$tagStack->addTagPair(strtoupper($siteId), $lpos, 0, $rpos, 0, $tag->getSortPriority())->setAttributes($tag->getAttributes());
131	355	}
132
133		/**
134		* Add a media site tag based on the attributes of a MEDIA tag
135		*
136		* @param Tag $tag The original tag
137		* @param TagStack $tagStack Parser instance
138		* @param array $sites Map of [host => siteId]
139		* @return void
140		*/
141	6	protected static function addTagFromMediaId(Tag $tag, TagStack $tagStack, array $sites)
142		{
143	6	$siteId = strtolower($tag->getAttribute('media'));
144	6	if (in_array($siteId, $sites, true))
145	6	{
146	5	self::addSiteTag($tag, $tagStack, $siteId);
147	5	}
148	6	}
149
150		/**
151		* Add a media site tag based on the url attribute of a MEDIA tag
152		*
153		* @param Tag $tag The original tag
154		* @param TagStack $tagStack Parser instance
155		* @param array $sites Map of [host => siteId]
156		* @return void
157		*/
158	352	protected static function addTagFromMediaUrl(Tag $tag, TagStack $tagStack, array $sites)
159		{
160		// Capture the scheme and (if applicable) host of the URL
161	352	$p = parse_url($tag->getAttribute('url'));
162	352	if (isset($p['scheme']) && isset($sites[$p['scheme'] . ':']))
163	352	{
164	4	$siteId = $sites[$p['scheme'] . ':'];
165	4	}
166	348	elseif (isset($p['host']))
167		{
168	348	$siteId = self::findSiteIdByHost($p['host'], $sites);
169	348	}
170
171	352	if (!empty($siteId))
172	352	{
173	350	self::addSiteTag($tag, $tagStack, $siteId);
174	350	}
175	352	}
176
177		/**
178		* Match a given host to a site ID
179		*
180		* @param string $host Host
181		* @param array $sites Map of [host => siteId]
182		* @return string\|bool Site ID or FALSE
183		*/
184	348	protected static function findSiteIdByHost($host, array $sites)
185		{
186		// Start with the full host then pop domain labels off the start until we get a match
187		do
188		{
189	348	if (isset($sites[$host]))
190	348	{
191	346	return $sites[$host];
192		}
193
194	228	$pos = strpos($host, '.');
195	228	if ($pos === false)
196	228	{
197	4	break;
198		}
199
200	228	$host = substr($host, 1 + $pos);
201		}
202	228	while ($host > '');
203
204	4	return false;
205		}
206
207		/**
208		* Return a cached instance of the HTTP client
209		*
210		* @return \s9e\TextFormatter\Utils\Http\Client
211		*/
212	1	protected static function getHttpClient()
213		{
214	1	if (!isset(self::$client))
215	1	{
216	1	self::$client = Http::getClient();
217	1	}
218	1	self::$client->timeout = 10;
219
220	1	return self::$client;
221		}
222
223		/**
224		* Replace {@var} tokens in given URL
225		*
226		* @param string $url Original URL
227		* @param string[] $vars Replacements
228		* @return string Modified URL
229		*/
230	17	protected static function replaceTokens($url, array $vars)
231		{
232	17	return preg_replace_callback(
233	17	'#\\{@(\\w+)\\}#',
234	17	function ($m) use ($vars)
235		{
236	17	return (isset($vars[$m[1]])) ? $vars[$m[1]] : '';
237	17	},
238		$url
239	17	);
240		}
241
242		/**
243		* Scrape the content of an URL to extract some data
244		*
245		* @param string $url Original URL
246		* @param Tag $tag Source tag
247		* @param array $scrape Array of scrape directives
248		* @param string $cacheDir Path to the cache directory
249		* @return void
250		*/
251	116	protected static function scrapeEntry($url, Tag $tag, array $scrape, $cacheDir)
252		{
253	116	list($matchRegexps, $extractRegexps, $attrNames) = $scrape;
254
255	116	if (!self::tagIsMissingAnyAttribute($tag, $attrNames))
256	116	{
257	32	return;
258		}
259
260		// Test whether this URL matches any regexp
261	91	$vars = [];
262	91	$matched = false;
263	91	foreach ((array) $matchRegexps as $matchRegexp)
264		{
265	91	if (preg_match($matchRegexp, $url, $m))
266	91	{
267	67	$vars += $m;
268	67	$matched = true;
269	67	}
270	91	}
271	91	if (!$matched)
272	91	{
273	31	return;
274		}
275
276		// Add the tag's attributes to the named captures from the "match" regexp
277	67	$vars += $tag->getAttributes();
278
279	67	$scrapeUrl = (isset($scrape[3])) ? self::replaceTokens($scrape[3], $vars) : $url;
280	67	self::scrapeUrl($scrapeUrl, $tag, (array) $extractRegexps, $cacheDir);
281	67	}
282
283		/**
284		* Scrape a URL to help fill a tag's attributes
285		*
286		* @param string $url URL to scrape
287		* @param Tag $tag Tag to fill
288		* @param string[] $regexps Regexps used to extract content from the page
289		* @param string\|null $cacheDir Path to the cache directory
290		* @return void
291		*/
292	67	protected static function scrapeUrl($url, Tag $tag, array $regexps, $cacheDir)
293		{
294	67	$content = self::wget($url, $cacheDir);
295
296		// Execute the extract regexps and fill any missing attribute
297	67	foreach ($regexps as $regexp)
298		{
299	67	if (preg_match($regexp, $content, $m))
300	67	{
301	65	foreach ($m as $k => $v)
302		{
303	65	if (!is_numeric($k) && !$tag->hasAttribute($k))
304	65	{
305	65	$tag->setAttribute($k, $v);
306	65	}
307	65	}
308	65	}
309	67	}
310	67	}
311
312		/**
313		* Test whether a tag is missing any of given attributes
314		*
315		* @param Tag $tag
316		* @param string[] $attrNames
317		* @return bool
318		*/
319	116	protected static function tagIsMissingAnyAttribute(Tag $tag, array $attrNames)
320		{
321	116	foreach ($attrNames as $attrName)
322		{
323	116	if (!$tag->hasAttribute($attrName))
324	116	{
325	91	return true;
326		}
327	34	}
328
329	32	return false;
330		}
331
332		/**
333		* Retrieve external content (possibly from the cache)
334		*
335		* If the cache directory exists, the external content will be saved into it. Cached content is
336		* never pruned
337		*
338		* @param string $url URL
339		* @param string $cacheDir Path to the cache directory
340		* @return string External content
341		*/
342	67	protected static function wget($url, $cacheDir = null)
343		{
344	67	$prefix = '';
345	67	$url = preg_replace('(#.*)s', '', $url);
346
347		// Return the content from the cache if applicable
348	67	if (isset($cacheDir) && file_exists($cacheDir))
349	67	{
350	67	$cacheFile = $cacheDir . '/http.' . crc32($url);
351	67	if (extension_loaded('zlib'))
352	67	{
353	67	$prefix = 'compress.zlib://';
354	67	$cacheFile .= '.gz';
355	67	}
356	67	if (file_exists($cacheFile))
357	67	{
358	66	return file_get_contents($prefix . $cacheFile);
359		}
360	1	}
361
362		// Retrieve the external content from the source
363	1	$content = @self::getHttpClient()->get($url, ['User-Agent: PHP (not Mozilla)']);
364
365		// Save to the cache if applicable
366	1	if (isset($cacheFile) && !empty($content))
367	1	{
368	1	file_put_contents($prefix . $cacheFile, $content);
369	1	}
370
371	1	return $content;
372		}
373		}

s9e / TextFormatter

Push — master ( 0e549e...7e9c0f )

Parser::parse() A

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like