LinkTrait::parseLink() - Code Metrics - Inspection of "copied table tests from GFM to markdown extra" - cebe/markdown - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 9ffe58...cd3227 )

by Carsten

created 2018-03-14 09:37 UTC

LinkTrait::parseLink() B

↳ Parent: LinkTrait

Complexity

Conditions	5
Paths	3

Size

Total Lines	26
Code Lines	18

Duplication

Lines	10
Ratio	38.46 %

Code Coverage

Tests	15
CRAP Score	5.1158

Importance

Changes

Metric	Value
dl	10
loc	26
ccs	15
cts	18
cp	0.8333
rs	8.439
c	0
b	0
f	0
cc	5
eloc	18
nc	3
nop	1
crap	5.1158

<?php
/**
 * @copyright Copyright (c) 2014 Carsten Brandt
 * @license https://github.com/cebe/markdown/blob/master/LICENSE
 * @link https://github.com/cebe/markdown#readme
 */

namespace cebe\markdown\inline;

// work around https://github.com/facebook/hhvm/issues/1120
defined('ENT_HTML401') || define('ENT_HTML401', 0);

/**
 * Addes links and images as well as url markers.
 *
 * This trait conflicts with the HtmlTrait. If both are used together,
 * you have to define a resolution, by defining the HtmlTrait::parseInlineHtml
 * as private so it is not used directly:
 *
 * ```php
 * use block\HtmlTrait {
 *     parseInlineHtml as private parseInlineHtml;
 * }
 * ```
 *
 * If the method exists it is called internally by this trait.
 *
 * Also make sure to reset references on prepare():
 *
 * ```php
 * protected function prepare()
 * {
 *     // reset references
 *     $this->references = [];
 * }
 * ```
 */
trait LinkTrait
{
	/**
	 * @var array a list of defined references in this document.
	 */
	protected $references = [];

	/**
	 * Remove backslash from escaped characters
	 * @param $text
	 * @return string
	 */
	protected function replaceEscape($text)
	{
		$strtr = [];
		foreach($this->escapeCharacters as $char) {
			$strtr["\\$char"] = $char;
		}
		return strtr($text, $strtr);
	}

	/**
	 * Parses a link indicated by `[`.
	 * @marker [
	 */
	protected function parseLink($markdown)
	{
		if (!in_array('parseLink', array_slice($this->context, 1)) && ($parts = $this->parseLinkOrImage($markdown)) !== false) {
			list($text, $url, $title, $offset, $key) = $parts;
			return [
				[
					'link',
					'text' => $this->parseInline($text),
					'url' => $url,
					'title' => $title,
					'refkey' => $key,
					'orig' => substr($markdown, 0, $offset),
				],
				$offset
			];
		} else {
			// remove all starting [ markers to avoid next one to be parsed as link
			$result = '[';
			$i = 1;
			while (isset($markdown[$i]) && $markdown[$i] == '[') {
				$result .= '[';
				$i++;
			}
			return [['text', $result], $i];
		}
	}

	/**
	 * Parses an image indicated by `![`.
	 * @marker ![
	 */
	protected function parseImage($markdown)
	{
		if (($parts = $this->parseLinkOrImage(substr($markdown, 1))) !== false) {
			list($text, $url, $title, $offset, $key) = $parts;

			return [
				[
					'image',
					'text' => $text,
					'url' => $url,
					'title' => $title,
					'refkey' => $key,
					'orig' => substr($markdown, 0, $offset + 1),
				],
				$offset + 1
			];
		} else {
			// remove all starting [ markers to avoid next one to be parsed as link
			$result = '!';
			$i = 1;
			while (isset($markdown[$i]) && $markdown[$i] == '[') {
				$result .= '[';
				$i++;
			}
			return [['text', $result], $i];
		}
	}

	protected function parseLinkOrImage($markdown)
	{
		if (strpos($markdown, ']') !== false && preg_match('/\[((?>[^\]\[]+|(?R))*)\]/', $markdown, $textMatches)) { // TODO improve bracket regex
			$text = $textMatches[1];
			$offset = strlen($textMatches[0]);
			$markdown = substr($markdown, $offset);

			$pattern = <<<REGEXP
				/(?(R) # in case of recursion match parentheses
					 \(((?>[^\s()]+)|(?R))*\)
				|      # else match a link with title
					^\(\s*(((?>[^\s()]+)|(?R))*)(\s+"(.*?)")?\s*\)
				)/x
REGEXP;
			if (preg_match($pattern, $markdown, $refMatches)) {
				// inline link
				return [
					$text,
					isset($refMatches[2]) ? $this->replaceEscape($refMatches[2]) : '', // url
					empty($refMatches[5]) ? null: $refMatches[5], // title
					$offset + strlen($refMatches[0]), // offset
					null, // reference key
				];
			} elseif (preg_match('/^([ \n]?\[(.*?)\])?/s', $markdown, $refMatches)) {
				// reference style link
				if (empty($refMatches[2])) {
					$key = strtolower($text);
				} else {
					$key = strtolower($refMatches[2]);
				}
				return [
					$text,
					null, // url
					null, // title
					$offset + strlen($refMatches[0]), // offset
					$key,
				];
			}
		}
		return false;
	}

	/**
	 * Parses inline HTML.
	 * @marker <
	 */
	protected function parseLt($text)
	{
		if (strpos($text, '>') !== false) {
			if (!in_array('parseLink', $this->context)) { // do not allow links in links
				if (preg_match('/^<([^\s]*?@[^\s]*?\.\w+?)>/', $text, $matches)) {
					// email address
					return [
						['email', $this->replaceEscape($matches[1])],
						strlen($matches[0])
					];
				} elseif (preg_match('/^<([a-z]{3,}:\/\/[^\s]+?)>/', $text, $matches)) {
					// URL
					return [
						['url', $this->replaceEscape($matches[1])],
						strlen($matches[0])
					];
				}
			}
			// try inline HTML if it was neither a URL nor email if HtmlTrait is included.
			if (method_exists($this, 'parseInlineHtml')) {
				return $this->parseInlineHtml($text);
			}
		}
		return [['text', '&lt;'], 1];
	}

	protected function renderEmail($block)
	{
		$email = htmlspecialchars($block[1], ENT_NOQUOTES | ENT_SUBSTITUTE, 'UTF-8');
		return "<a href=\"mailto:$email\">$email</a>";
	}

	protected function renderUrl($block)

	{
		$url = htmlspecialchars($block[1], ENT_COMPAT | ENT_HTML401, 'UTF-8');
		$decodedUrl = urldecode($block[1]);
		$secureUrlText = preg_match('//u', $decodedUrl) ? $decodedUrl : $block[1];
		$text = htmlspecialchars($secureUrlText, ENT_NOQUOTES | ENT_SUBSTITUTE, 'UTF-8');
		return "<a href=\"$url\">$text</a>";
	}

	protected function lookupReference($key)
	{
		$normalizedKey = preg_replace('/\s+/', ' ', $key);
		if (isset($this->references[$key]) || isset($this->references[$key = $normalizedKey])) {
			return $this->references[$key];
		}
		return false;
	}

	protected function renderLink($block)
	{
		if (isset($block['refkey'])) {
			if (($ref = $this->lookupReference($block['refkey'])) !== false) {
				$block = array_merge($block, $ref);
			} else {
				return $block['orig'];
			}
		}
		return '<a href="' . htmlspecialchars($block['url'], ENT_COMPAT | ENT_HTML401, 'UTF-8') . '"'
			. (empty($block['title']) ? '' : ' title="' . htmlspecialchars($block['title'], ENT_COMPAT | ENT_HTML401 | ENT_SUBSTITUTE, 'UTF-8') . '"')
			. '>' . $this->renderAbsy($block['text']) . '</a>';
	}

	protected function renderImage($block)
	{
		if (isset($block['refkey'])) {
			if (($ref = $this->lookupReference($block['refkey'])) !== false) {
				$block = array_merge($block, $ref);
			} else {
				return $block['orig'];
			}
		}
		return '<img src="' . htmlspecialchars($block['url'], ENT_COMPAT | ENT_HTML401, 'UTF-8') . '"'
			. ' alt="' . htmlspecialchars($block['text'], ENT_COMPAT | ENT_HTML401 | ENT_SUBSTITUTE, 'UTF-8') . '"'
			. (empty($block['title']) ? '' : ' title="' . htmlspecialchars($block['title'], ENT_COMPAT | ENT_HTML401 | ENT_SUBSTITUTE, 'UTF-8') . '"')
			. ($this->html5 ? '>' : ' />');
	}

	// references

	protected function identifyReference($line)
	{
		return ($line[0] === ' ' || $line[0] === '[') && preg_match('/^ {0,3}\[(.+?)\]:\s*([^\s]+?)(?:\s+[\'"](.+?)[\'"])?\s*$/', $line);
	}

	/**
	 * Consume link references
	 */
	protected function consumeReference($lines, $current)
	{
		while (isset($lines[$current]) && preg_match('/^ {0,3}\[(.+?)\]:\s*(.+?)(?:\s+[\(\'"](.+?)[\)\'"])?\s*$/', $lines[$current], $matches)) {
			$label = strtolower($matches[1]);

			$this->references[$label] = [
				'url' => $this->replaceEscape($matches[2]),
			];
			if (isset($matches[3])) {
				$this->references[$label]['title'] = $matches[3];
			} else {
				// title may be on the next line
				if (isset($lines[$current + 1]) && preg_match('/^\s+[\(\'"](.+?)[\)\'"]\s*$/', $lines[$current + 1], $matches)) {
					$this->references[$label]['title'] = $matches[1];
					$current++;
				}
			}
			$current++;
		}
		return [false, --$current];
	}
}


1			<?php
2			/**
3			* @copyright Copyright (c) 2014 Carsten Brandt
4			* @license https://github.com/cebe/markdown/blob/master/LICENSE
5			* @link https://github.com/cebe/markdown#readme
6			*/
7
8			namespace cebe\markdown\inline;
9
10			// work around https://github.com/facebook/hhvm/issues/1120
11	1		defined('ENT_HTML401') \|\| define('ENT_HTML401', 0);
12
13			/**
14			* Addes links and images as well as url markers.
15			*
16			* This trait conflicts with the HtmlTrait. If both are used together,
17			* you have to define a resolution, by defining the HtmlTrait::parseInlineHtml
18			* as private so it is not used directly:
19			*
20			* ```php
21			* use block\HtmlTrait {
22			* parseInlineHtml as private parseInlineHtml;
23			* }
24			* ```
25			*
26			* If the method exists it is called internally by this trait.
27			*
28			* Also make sure to reset references on prepare():
29			*
30			* ```php
31			* protected function prepare()
32			* {
33			* // reset references
34			* $this->references = [];
35			* }
36			* ```
37			*/
38			trait LinkTrait
39			{
40			/**
41			* @var array a list of defined references in this document.
42			*/
43			protected $references = [];
44
45			/**
46			* Remove backslash from escaped characters
47			* @param $text
48			* @return string
49			*/
50	52		protected function replaceEscape($text)
51			{
52	52		$strtr = [];
53	52		foreach($this->escapeCharacters as $char) {
54	52		$strtr["\\$char"] = $char;
55	52		}
56	52		return strtr($text, $strtr);
57			}
58
59			/**
60			* Parses a link indicated by `[`.
61			* @marker [
62			*/
63	50		protected function parseLink($markdown)
64			{
65	50		if (!in_array('parseLink', array_slice($this->context, 1)) && ($parts = $this->parseLinkOrImage($markdown)) !== false) {
66	50		list($text, $url, $title, $offset, $key) = $parts;
67			return [
68			[
69	50		'link',
70	50		'text' => $this->parseInline($text),
71	50		'url' => $url,
72	50		'title' => $title,
73	50		'refkey' => $key,
74	50		'orig' => substr($markdown, 0, $offset),
75	50		],
76			$offset
77	50		];
78		View Code Duplication	} else {
79			// remove all starting [ markers to avoid next one to be parsed as link
80	11		$result = '[';
81	11		$i = 1;
82	11		while (isset($markdown[$i]) && $markdown[$i] == '[') {
83			$result .= '[';
84			$i++;
85			}
86	11		return [['text', $result], $i];
87			}
88			}
89
90			/**
91			* Parses an image indicated by `![`.
92			* @marker ![
93			*/
94	7		protected function parseImage($markdown)
95			{
96	7		if (($parts = $this->parseLinkOrImage(substr($markdown, 1))) !== false) {
97	7		list($text, $url, $title, $offset, $key) = $parts;
98
99			return [
100			[
101	7		'image',
102	7		'text' => $text,
103	7		'url' => $url,
104	7		'title' => $title,
105	7		'refkey' => $key,
106	7		'orig' => substr($markdown, 0, $offset + 1),
107	7		],
108			$offset + 1
109	7		];
110		View Code Duplication	} else {
111			// remove all starting [ markers to avoid next one to be parsed as link
112	3		$result = '!';
113	3		$i = 1;
114	3		while (isset($markdown[$i]) && $markdown[$i] == '[') {
115	3		$result .= '[';
116	3		$i++;
117	3		}
118	3		return [['text', $result], $i];
119			}
120			}
121
122	50		protected function parseLinkOrImage($markdown)
123			{
124	50		if (strpos($markdown, ']') !== false && preg_match('/\[((?>[^\]\[]+\|(?R))*)\]/', $markdown, $textMatches)) { // TODO improve bracket regex
125	50		$text = $textMatches[1];
126	50		$offset = strlen($textMatches[0]);
127	50		$markdown = substr($markdown, $offset);
128
129			$pattern = <<<REGEXP
130			/(?(R) # in case of recursion match parentheses
131			\(((?>[^\s()]+)\|(?R))*\)
132			\| # else match a link with title
133			^\(\s(((?>[^\s()]+)\|(?R)))(\s+"(.?)")?\s\)
134			)/x
135	50		REGEXP;
136	50		if (preg_match($pattern, $markdown, $refMatches)) {
137			// inline link
138			return [
139	33		$text,
140	33		isset($refMatches[2]) ? $this->replaceEscape($refMatches[2]) : '', // url
141	33		empty($refMatches[5]) ? null: $refMatches[5], // title
142	33		$offset + strlen($refMatches[0]), // offset
143	33		null, // reference key
144	33		];
145	40		} elseif (preg_match('/^([ \n]?\[(.*?)\])?/s', $markdown, $refMatches)) {
146			// reference style link
147	40		if (empty($refMatches[2])) {
148	33		$key = strtolower($text);
149	33		} else {
150	17		$key = strtolower($refMatches[2]);
151			}
152			return [
153	40		$text,
154	40		null, // url
155	40		null, // title
156	40		$offset + strlen($refMatches[0]), // offset
157	40		$key,
158	40		];
159			}
160			}
161	3		return false;
162			}
163
164			/**
165			* Parses inline HTML.
166			* @marker <
167			*/
168	30		protected function parseLt($text)
169			{
170	30		if (strpos($text, '>') !== false) {
171	26		if (!in_array('parseLink', $this->context)) { // do not allow links in links
172	26	View Code Duplication	if (preg_match('/^<([^\s]?@[^\s]?\.\w+?)>/', $text, $matches)) {
173			// email address
174			return [
175	3		['email', $this->replaceEscape($matches[1])],
176	3		strlen($matches[0])
177	3		];
178	26		} elseif (preg_match('/^<([a-z]{3,}:\/\/[^\s]+?)>/', $text, $matches)) {
179			// URL
180			return [
181	10		['url', $this->replaceEscape($matches[1])],
182	10		strlen($matches[0])
183	10		];
184			}
185	16		}
186			// try inline HTML if it was neither a URL nor email if HtmlTrait is included.
187	16		if (method_exists($this, 'parseInlineHtml')) {
188	16		return $this->parseInlineHtml($text);
189			}
190			}
191	11		return [['text', '<'], 1];
192			}
193
194	3		protected function renderEmail($block)
195			{
196	3		$email = htmlspecialchars($block[1], ENT_NOQUOTES \| ENT_SUBSTITUTE, 'UTF-8');
197	3		return "<a href=\"mailto:$email\">$email</a>";
198			}
199
200	10	View Code Duplication	protected function renderUrl($block)
			0 ignored issues – show Duplication introduced 2017-08-22 10:15 UTC by Report Bug Copy Issue Report This method seems to be duplicated in your project. Duplicated code is one of the most pungent code smells. If you need to duplicate the same code in three or more different places, we strongly encourage you to look into extracting the code into a single class or operation. You can also find more detailed suggestions in the “Code” section of your repository. Loading history...
201			{
202	10		$url = htmlspecialchars($block[1], ENT_COMPAT \| ENT_HTML401, 'UTF-8');
203	10		$decodedUrl = urldecode($block[1]);
204	10		$secureUrlText = preg_match('//u', $decodedUrl) ? $decodedUrl : $block[1];
205	10		$text = htmlspecialchars($secureUrlText, ENT_NOQUOTES \| ENT_SUBSTITUTE, 'UTF-8');
206	10		return "<a href=\"$url\">$text</a>";
207			}
208
209	40		protected function lookupReference($key)
210			{
211	40		$normalizedKey = preg_replace('/\s+/', ' ', $key);
212	40		if (isset($this->references[$key]) \|\| isset($this->references[$key = $normalizedKey])) {
213	29		return $this->references[$key];
214			}
215	20		return false;
216			}
217
218	33		protected function renderLink($block)
219			{
220	33	View Code Duplication	if (isset($block['refkey'])) {
221	24		if (($ref = $this->lookupReference($block['refkey'])) !== false) {
222	19		$block = array_merge($block, $ref);
223	19		} else {
224	11		return $block['orig'];
225			}
226	19		}
227	32		return '<a href="' . htmlspecialchars($block['url'], ENT_COMPAT \| ENT_HTML401, 'UTF-8') . '"'
228	32		. (empty($block['title']) ? '' : ' title="' . htmlspecialchars($block['title'], ENT_COMPAT \| ENT_HTML401 \| ENT_SUBSTITUTE, 'UTF-8') . '"')
229	32		. '>' . $this->renderAbsy($block['text']) . '</a>';
230			}
231
232	4		protected function renderImage($block)
233			{
234	4	View Code Duplication	if (isset($block['refkey'])) {
235	2		if (($ref = $this->lookupReference($block['refkey'])) !== false) {
236			$block = array_merge($block, $ref);
237			} else {
238	2		return $block['orig'];
239			}
240			}
241	4		return '<img src="' . htmlspecialchars($block['url'], ENT_COMPAT \| ENT_HTML401, 'UTF-8') . '"'
242	4		. ' alt="' . htmlspecialchars($block['text'], ENT_COMPAT \| ENT_HTML401 \| ENT_SUBSTITUTE, 'UTF-8') . '"'
243	4		. (empty($block['title']) ? '' : ' title="' . htmlspecialchars($block['title'], ENT_COMPAT \| ENT_HTML401 \| ENT_SUBSTITUTE, 'UTF-8') . '"')
244	4		. ($this->html5 ? '>' : ' />');
245			}
246
247			// references
248
249	141		protected function identifyReference($line)
250			{
251	141		return ($line[0] === ' ' \|\| $line[0] === '[') && preg_match('/^ {0,3}\[(.+?)\]:\s([^\s]+?)(?:\s+[\'"](.+?)[\'"])?\s$/', $line);
252			}
253
254			/**
255			* Consume link references
256			*/
257	19		protected function consumeReference($lines, $current)
258			{
259	19		while (isset($lines[$current]) && preg_match('/^ {0,3}\[(.+?)\]:\s(.+?)(?:\s+[\(\'"](.+?)[\)\'"])?\s$/', $lines[$current], $matches)) {
260	19		$label = strtolower($matches[1]);
261
262	19		$this->references[$label] = [
263	19		'url' => $this->replaceEscape($matches[2]),
264			];
265	19	View Code Duplication	if (isset($matches[3])) {
266	9		$this->references[$label]['title'] = $matches[3];
267	9		} else {
268			// title may be on the next line
269	16		if (isset($lines[$current + 1]) && preg_match('/^\s+[\(\'"](.+?)[\)\'"]\s*$/', $lines[$current + 1], $matches)) {
270	2		$this->references[$label]['title'] = $matches[1];
271	2		$current++;
272	2		}
273			}
274	19		$current++;
275	19		}
276	19		return [false, --$current];
277			}
278			}
279

cebe / markdown

Push — master ( 9ffe58...cd3227 )

LinkTrait::parseLink() B

Complexity

Size

Duplication

Code Coverage

Importance

Duplication Side-by-Side

Filter issues like