HTMLParser::parse() - Code Metrics - Icybee/Patron - Measure and Improve Code Quality continuously with Scrutinizer

HTMLParser::parse() A
last analyzed 2016-07-08 22:28 UTC

↳ Parent: HTMLParser

Complexity

Conditions	2
Paths	2

Size

Total Lines	48
Code Lines	10

Duplication

Lines	0
Ratio	0 %

Importance

Changes	2
Bugs	0	Features	0

Metric	Value
c	2
b	0
f	0
dl	0
loc	48
rs	9.125
cc	2
eloc	10
nc	2
nop	3

<?php

/*
 * This file is part of the Patron package.
 *
 * (c) Olivier Laviale <[email protected]>
 *
 * For the full copyright and license information, please view the LICENSE
 * file that was distributed with this source code.
 */

namespace Patron;

class HTMLParser
{
	const T_ERROR_HANDLER = 'error-handler';

	private $encoding;
	private $matches;
	private $escaped;
	private $opened = [];

	protected $error_handler;
	protected $namespace;

	public function __construct(array $tags=[])
	{
		$tags += [

			self::T_ERROR_HANDLER => function($str, $args) {

				trigger_error(\ICanBoogie\format($str, $args));

			}

		];

		$this->error_handler = $tags[self::T_ERROR_HANDLER];
	}

	public function parse($html, $namespace=null, $encoding='utf-8')
	{
		$this->encoding = $encoding;
		$this->namespace = $namespace;

		#
		# we take care of escaping comments and processing options. they will not be parsed
		# and will end as text nodes
		#

		$html = $this->escapeSpecials($html);

		#
		# in order to create a tree, we first need to split the HTML using the markups,
		# creating a nice flat array of texts and opening and closing markups.
		#
		# the array can be read as follows :
		#
		# i+0 => some text
		# i+1 => '/' for closing markups, nothing otherwise
		# i+2 => the markup it self, without the '<' '>'
		#
		# note that i+2 might end with a '/' indicating an auto-closing markup
		#

		$this->matches = preg_split
		(
			'#<(/?)' . $namespace . '([^>]*)>#', $html, -1, PREG_SPLIT_DELIM_CAPTURE
		);

		#
		# the flat representation is now ready, we can create our tree
		#

		$tree = $this->buildTree();

		#
		# if comments or processing options where escaped, we can
		# safely unescape them now
		#

		if ($this->escaped)
		{
			$tree = $this->unescapeSpecials($tree);
		}

		return $tree;
	}

	protected function escapeSpecials($html)
	{
		#
		# here we escape comments
		#

		$html = preg_replace_callback('#<\!--.+-->#sU', [ $this, 'escapeSpecials_callback' ], $html);

		#
		# and processing options
		#

		$html = preg_replace_callback('#<\?.+\?>#sU', [ $this, 'escapeSpecials_callback' ], $html);

		return $html;
	}

	protected function escapeSpecials_callback($m)
	{
		$this->escaped = true;

		$text = $m[0];

		$text = str_replace
		(
			[ '<', '>' ],
			[ "\x01", "\x02" ],
			$text
		);

		return $text;
	}

	protected function unescapeSpecials($tree)
	{
		return is_array($tree) ? array_map([ $this, 'unescapeSpecials' ], $tree) : str_replace
		(
			[ "\x01", "\x02" ],
			[ '<', '>' ],
			$tree
		);
	}

	protected function buildTree()
	{
		$nodes = [];

		$i = 0;
		$text = null;
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}

		while (($value = array_shift($this->matches)) !== null)
		{
			switch ($i++ % 3)
			{
				case 0:
switch ($expr) {
    case "A": { //wrong
        doSomething();
        break;
    }
    case "B": //right
        doSomething();
        break;
}
				{
					#
					# if the trimed value is not empty we preserve the value,
					# otherwise we discard it.
					#

					if (trim($value))
					{
						$nodes[] = $value;
					}
				}
				break;

				case 1:
switch ($expr) {
    case "A": { //wrong
        doSomething();
        break;
    }
    case "B": //right
        doSomething();
        break;
}
				{
					$closing = ($value == '/');
				}
				break;

				case 2:
switch ($expr) {
    case "A": { //wrong
        doSomething();
        break;
    }
    case "B": //right
        doSomething();
        break;
}
				{
					if (substr($value, -1, 1) == '/')
					{
						#
						# auto closing
						#

						$nodes[] = $this->parseMarkup(substr($value, 0, -1));
					}
					else if ($closing)
function myFunction($a) {
    switch ($a) {
        case 'foo':
            $x = 1;
            break;

        case 'bar':
            $x = 2;
            break;
    }

    // $x is potentially undefined here.
    echo $x;
}
					{
						#
						# closing markup
						#

						$open = array_pop($this->opened);

						if ($value != $open)
						{
							$this->error($value, $open);
						}

						return $nodes;
					}
					else
					{
						#
						# this is an open markup with possible children
						#

						$node = $this->parseMarkup($value);

						#
						# push the markup name into the opened markups
						#

						$this->opened[] = $node['name'];

						#
						# create the node and parse its children
						#

						$node['children'] = $this->buildTree($this->matches);


						$nodes[] = $node;
					}
				}
			}
		}

		return $nodes;
	}

	protected function parseMarkup($markup)
	{
		#
		# get markup's name
		#

		preg_match('#^[^\s]+#', $markup, $matches);

		$name = $matches[0];

		#
		# get markup's arguments
		#

		preg_match_all('#\s+([^=]+)\s*=\s*"([^"]+)"#', $markup, $matches, PREG_SET_ORDER);

		#
		# transform the matches into a nice key/value array
		#

		$args = [];

		foreach ($matches as $m)
$collection = json_decode($data, true);
if ( ! is_array($collection)) {
    throw new \RuntimeException('$collection must be an array.');
}

foreach ($collection as $item) { /** ... */ }
		{
			#
			# we unescape the html entities of the argument's value
			#

			$args[$m[1]] = html_entity_decode($m[2], ENT_QUOTES, $this->encoding);
		}

		return [ 'name' => $name, 'args' => $args ];
	}

	protected function error($markup, $expected)
	{
		$this->malformed = true;
class MyClass { }

$x = new MyClass();
$x->foo = true;

		call_user_func
		(
			$this->error_handler, $expected
			? 'unexpected closing markup %markup, should be %expected'
			: 'unexpected closing markup %markup, when none was opened', [

				'%markup' => $this->namespace . $markup, '%expected' => $expected

			]
		);
	}

	static public function collectMarkup($nodes, $markup)
	{
		$collected = [];

		foreach ($nodes as $node)
		{
			if (!is_array($node))
			{
				continue;
			}

			if ($node['name'] == $markup)
			{
				$collected[] = $node;
			}

			if (isset($node['children']))
			{
				$collected = array_merge($collected, self::collectMarkup($node['children'], $markup));
			}
		}

		return $collected;
	}
}


1			<?php
2
3			/*
4			* This file is part of the Patron package.
5			*
6			* (c) Olivier Laviale <[email protected]>
7			*
8			* For the full copyright and license information, please view the LICENSE
9			* file that was distributed with this source code.
10			*/
11
12			namespace Patron;
13
14			class HTMLParser
15			{
16			const T_ERROR_HANDLER = 'error-handler';
17
18			private $encoding;
19			private $matches;
20			private $escaped;
21			private $opened = [];
22
23			protected $error_handler;
24			protected $namespace;
25
26			public function __construct(array $tags=[])
27			{
28			$tags += [
29
30			self::T_ERROR_HANDLER => function($str, $args) {
31
32			trigger_error(\ICanBoogie\format($str, $args));
33
34			}
35
36			];
37
38			$this->error_handler = $tags[self::T_ERROR_HANDLER];
39			}
40
41			public function parse($html, $namespace=null, $encoding='utf-8')
42			{
43			$this->encoding = $encoding;
44			$this->namespace = $namespace;
45
46			#
47			# we take care of escaping comments and processing options. they will not be parsed
48			# and will end as text nodes
49			#
50
51			$html = $this->escapeSpecials($html);
52
53			#
54			# in order to create a tree, we first need to split the HTML using the markups,
55			# creating a nice flat array of texts and opening and closing markups.
56			#
57			# the array can be read as follows :
58			#
59			# i+0 => some text
60			# i+1 => '/' for closing markups, nothing otherwise
61			# i+2 => the markup it self, without the '<' '>'
62			#
63			# note that i+2 might end with a '/' indicating an auto-closing markup
64			#
65
66			$this->matches = preg_split
67			(
68			'#<(/?)' . $namespace . '([^>]*)>#', $html, -1, PREG_SPLIT_DELIM_CAPTURE
69			);
70
71			#
72			# the flat representation is now ready, we can create our tree
73			#
74
75			$tree = $this->buildTree();
76
77			#
78			# if comments or processing options where escaped, we can
79			# safely unescape them now
80			#
81
82			if ($this->escaped)
83			{
84			$tree = $this->unescapeSpecials($tree);
85			}
86
87			return $tree;
88			}
89
90			protected function escapeSpecials($html)
91			{
92			#
93			# here we escape comments
94			#
95
96			$html = preg_replace_callback('#<\!--.+-->#sU', [ $this, 'escapeSpecials_callback' ], $html);
97
98			#
99			# and processing options
100			#
101
102			$html = preg_replace_callback('#<\?.+\?>#sU', [ $this, 'escapeSpecials_callback' ], $html);
103
104			return $html;
105			}
106
107			protected function escapeSpecials_callback($m)
108			{
109			$this->escaped = true;
110
111			$text = $m[0];
112
113			$text = str_replace
114			(
115			[ '<', '>' ],
116			[ "\x01", "\x02" ],
117			$text
118			);
119
120			return $text;
121			}
122
123			protected function unescapeSpecials($tree)
124			{
125			return is_array($tree) ? array_map([ $this, 'unescapeSpecials' ], $tree) : str_replace
126			(
127			[ "\x01", "\x02" ],
128			[ '<', '>' ],
129			$tree
130			);
131			}
132
133			protected function buildTree()
134			{
135			$nodes = [];
136
137			$i = 0;
138			$text = null;
			0 ignored issues – show Unused Code introduced 2016-01-23 20:34 UTC by Report Bug Copy Issue Report `$text` is not used, you could remove the assignment. This check looks for variable assignements that are either overwritten by other assignments or where the variable is not used subsequently. $myVar = 'Value'; $higher = false; if (rand(1, 6) > 3) { $higher = true; } else { $higher = false; } Both the `$myVar` assignment in line 1 and the `$higher` assignment in line 2 are dead. The first because `$myVar` is never used and the second because `$higher` is always overwritten for every possible time line. Loading history...
139
140			while (($value = array_shift($this->matches)) !== null)
141			{
142			switch ($i++ % 3)
143			{
144			case 0:
			0 ignored issues – show Coding Style introduced 2016-07-08 22:28 UTC by Report Bug Copy Issue Report CASE statements must be defined using a colon As per the PSR-2 coding standard, case statements should not be wrapped in curly braces. There is no need for braces, since each case is terminated by the next `break`. switch ($expr) { case "A": { //wrong doSomething(); break; } case "B": //right doSomething(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
145			{
146			#
147			# if the trimed value is not empty we preserve the value,
148			# otherwise we discard it.
149			#
150
151			if (trim($value))
152			{
153			$nodes[] = $value;
154			}
155			}
156			break;
157
158			case 1:
			0 ignored issues – show Coding Style introduced 2016-07-08 22:28 UTC by Report Bug Copy Issue Report CASE statements must be defined using a colon As per the PSR-2 coding standard, case statements should not be wrapped in curly braces. There is no need for braces, since each case is terminated by the next `break`. switch ($expr) { case "A": { //wrong doSomething(); break; } case "B": //right doSomething(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
159			{
160			$closing = ($value == '/');
161			}
162			break;
163
164			case 2:
			0 ignored issues – show Coding Style introduced 2016-07-08 22:28 UTC by Report Bug Copy Issue Report CASE statements must be defined using a colon As per the PSR-2 coding standard, case statements should not be wrapped in curly braces. There is no need for braces, since each case is terminated by the next `break`. switch ($expr) { case "A": { //wrong doSomething(); break; } case "B": //right doSomething(); break; } To learn more about the PSR-2 coding standard, please refer to the PHP-Fig. Loading history...
165			{
166			if (substr($value, -1, 1) == '/')
167			{
168			#
169			# auto closing
170			#
171
172			$nodes[] = $this->parseMarkup(substr($value, 0, -1));
173			}
174			else if ($closing)
			0 ignored issues – show Bug introduced 2016-01-23 20:34 UTC by Report Bug Copy Issue Report The variable `$closing` does not seem to be defined for all execution paths leading up to this point. If you define a variable conditionally, it can happen that it is not defined for all execution paths. Let’s take a look at an example: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } // $x is potentially undefined here. echo $x; } In the above example, the variable `$x` is defined if you pass “foo” or “bar” as argument for `$a`. However, since the `switch` statement has no default case statement, if you pass any other value, the variable `$x` would be undefined. Available Fixes Check for existence of the variable explicitly: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } if (isset($x)) { // Make sure it's always set. echo $x; } } Define a default value for the variable: function myFunction($a) { $x = ''; // Set a default which gets overridden for certain paths. switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; } echo $x; } Add a value for the missing path: function myFunction($a) { switch ($a) { case 'foo': $x = 1; break; case 'bar': $x = 2; break; // We add support for the missing case. default: $x = ''; break; } echo $x; } Loading history...
175			{
176			#
177			# closing markup
178			#
179
180			$open = array_pop($this->opened);
181
182			if ($value != $open)
183			{
184			$this->error($value, $open);
185			}
186
187			return $nodes;
188			}
189			else
190			{
191			#
192			# this is an open markup with possible children
193			#
194
195			$node = $this->parseMarkup($value);
196
197			#
198			# push the markup name into the opened markups
199			#
200
201			$this->opened[] = $node['name'];
202
203			#
204			# create the node and parse its children
205			#
206
207			$node['children'] = $this->buildTree($this->matches);
			0 ignored issues – show Unused Code introduced 2016-01-23 20:34 UTC by Report Bug Copy Issue Report The call to `HTMLParser::buildTree()` has too many arguments starting with `$this->matches`. This check compares calls to functions or methods with their respective definitions. If the call has more arguments than are defined, it raises an issue. If a function is defined several times with a different number of parameters, the check may pick up the wrong definition and report false positives. One codebase where this has been known to happen is Wordpress. In this case you can add the `@ignore` PhpDoc annotation to the duplicate definition and it will be ignored. Loading history...
208
209			$nodes[] = $node;
210			}
211			}
212			}
213			}
214
215			return $nodes;
216			}
217
218			protected function parseMarkup($markup)
219			{
220			#
221			# get markup's name
222			#
223
224			preg_match('#^[^\s]+#', $markup, $matches);
225
226			$name = $matches[0];
227
228			#
229			# get markup's arguments
230			#
231
232			preg_match_all('#\s+([^=]+)\s=\s"([^"]+)"#', $markup, $matches, PREG_SET_ORDER);
233
234			#
235			# transform the matches into a nice key/value array
236			#
237
238			$args = [];
239
240			foreach ($matches as $m)
			0 ignored issues – show Bug introduced 2016-01-23 20:34 UTC by Report Bug Copy Issue Report The expression `$matches` of type `null\|array<integer,array<integer,string>>` is not guaranteed to be traversable. How about adding an additional type check? There are different options of fixing this problem. If you want to be on the safe side, you can add an additional type-check: $collection = json_decode($data, true); if ( ! is_array($collection)) { throw new \RuntimeException('$collection must be an array.'); } foreach ($collection as $item) { /** ... / } If you are sure that the expression is traversable, you might want to add a doc comment cast* to improve IDE auto-completion and static analysis: /** @var array $collection / $collection = json_decode($data, true); foreach ($collection as $item) { /* .. / } Mark the issue as a false-positive*: Just hover the remove button, in the top-right corner of this issue for more options. Loading history...
241			{
242			#
243			# we unescape the html entities of the argument's value
244			#
245
246			$args[$m[1]] = html_entity_decode($m[2], ENT_QUOTES, $this->encoding);
247			}
248
249			return [ 'name' => $name, 'args' => $args ];
250			}
251
252			protected function error($markup, $expected)
253			{
254			$this->malformed = true;
			0 ignored issues – show Bug introduced 2016-01-23 20:34 UTC by Report Bug Copy Issue Report The property `malformed` does not exist. Did you maybe forget to declare it? In PHP it is possible to write to properties without declaring them. For example, the following is perfectly valid PHP code: class MyClass { } $x = new MyClass(); $x->foo = true; Generally, it is a good practice to explictly declare properties to avoid accidental typos and provide IDE auto-completion: class MyClass { public $foo; } $x = new MyClass(); $x->foo = true; Loading history...
255
256			call_user_func
257			(
258			$this->error_handler, $expected
259			? 'unexpected closing markup %markup, should be %expected'
260			: 'unexpected closing markup %markup, when none was opened', [
261
262			'%markup' => $this->namespace . $markup, '%expected' => $expected
263
264			]
265			);
266			}
267
268			static public function collectMarkup($nodes, $markup)
269			{
270			$collected = [];
271
272			foreach ($nodes as $node)
273			{
274			if (!is_array($node))
275			{
276			continue;
277			}
278
279			if ($node['name'] == $markup)
280			{
281			$collected[] = $node;
282			}
283
284			if (isset($node['children']))
285			{
286			$collected = array_merge($collected, self::collectMarkup($node['children'], $markup));
287			}
288			}
289
290			return $collected;
291			}
292			}
293

Icybee / Patron

HTMLParser::parse() A last analyzed 2016-07-08 22:28 UTC

Complexity

Size

Duplication

Importance

Available Fixes

Duplication Side-by-Side

Filter issues like

HTMLParser::parse() A
last analyzed 2016-07-08 22:28 UTC