htmlparser::scan() - Code Metrics - Ariadne-CMS/ariadne - Measure and Improve Code Quality continuously with Scrutinizer

htmlparser::scan() F
last analyzed 2018-12-19 18:24 UTC

↳ Parent: htmlparser

Complexity

Conditions	60
Paths	36

Size

Total Lines

145

Duplication

Lines	29
Ratio	20 %

Code Coverage

Tests	70
CRAP Score	519.5163

Importance

Changes

Metric	Value
cc	60
nc	36
nop	2
dl	29
loc	145
rs	3.3333
c	0
b	0
f	0
ccs	70
cts	141
cp	0.4965
crap	519.5163

How to fix Long Method Complexity

<?php
	define('AR_HTMLPARSER_T_OPEN_TAG', 252);
	define('AR_HTMLPARSER_T_CLOSE_TAG', 251);
	define('AR_HTMLPARSER_T_TAG_END', 250);
	define('AR_HTMLPARSER_T_ASSIGN', 248);
	define('AR_HTMLPARSER_T_IDENT', 247);
	define('AR_HTMLPARSER_T_STRING', 246);
	define('AR_HTMLPARSER_T_ATTRIB', 245);
	define('AR_HTMLPARSER_T_NUMBER', 244);
	define('AR_HTMLPARSER_T_ATTRIB_VAL', 243);
	define('AR_HTMLPARSER_T_DOCTYPE', 242);

	define('AR_HTMLPARSER_T_EOF', 0);
	define('AR_HTMLPARSER_T_TEXT', -1);
	define('AR_HTMLPARSER_T_ERROR', -2);

	define('AR_HTMLPARSER_STATE_TEXT', 1);
	define('AR_HTMLPARSER_STATE_OPEN_TAG', 2);
	define('AR_HTMLPARSER_STATE_CLOSE_TAG', 3);
	define('AR_HTMLPARSER_STATE_ATTRIB', 4);
	define('AR_HTMLPARSER_STATE_COMMENT', 5);
	define('AR_HTMLPARSER_STATE_SCRIPT', 6);
	define('AR_HTMLPARSER_STATE_DOCTYPE', 7);

	define('CONTEXT_NORMAL', 1);
	define('CONTEXT_SCRIPT', 2);

	class htmlparser {

		protected static function scanner($buffer) {
			$scanner = array();
			$scanner['YYBUFFER'] = $buffer."\000";
			$scanner['YYCURSOR'] = 0;
			$scanner['YYSTATE'] = AR_HTMLPARSER_STATE_TEXT;
			$scanner['YYCONTEXT'] = CONTEXT_NORMAL;

			$class_ident_start = array();
			$start = ord('a');
			$end   = ord('z');
			for ($i = $start; $i <= $end; $i++) {
				$class_ident_start[chr($i)] = chr($i);
				$class_ident_start[strtoupper(chr($i))] = strtoupper(chr($i));
			}
			$scanner['class_ident_start'] = $class_ident_start;

			$class_attrib_start = $class_ident_start;
			$scanner['class_attrib_start'] = $class_attrib_start;


			$class_ident_next = $class_ident_start;
			$class_number = array();
			$start = ord('0');
			$end   = ord('9');
			for ($i = $start; $i <= $end; $i++) {
				$class_ident_next[chr($i)] = chr($i);
				$class_number[chr($i)] = chr($i);
			}
			$scanner['class_ident_next'] = $class_ident_next;
			$scanner['class_number'] = $class_number;

			// List of allowed characters for attribute names;
			$class_attrib_next = $class_ident_next;
			$class_attrib_next[':'] = ':';
			$class_attrib_next['-'] = '-';
			$class_attrib_next['_'] = '_';
			$class_attrib_next['.'] = '.';

			$scanner['class_attrib_next'] = $class_attrib_next;


			$class_whitespace = array(" " => " ", "\t" => "\t", "\r" => "\r", "\n" => "\n");
			$scanner['class_whitespace'] = $class_whitespace;

			return $scanner;
		}

		protected static function scan(&$scanner, &$value) {
			$YYCURSOR = &$scanner["YYCURSOR"];
			$YYBUFFER = &$scanner["YYBUFFER"];
			$yych = $YYBUFFER[$YYCURSOR];
			$YYSTATE = &$scanner["YYSTATE"];
			$YYCONTEXT = &$scanner["YYCONTEXT"];

			do {
				switch (true) {
					case $yych === $scanner['class_attrib_start'][$yych] && ($YYSTATE == AR_HTMLPARSER_STATE_DOCTYPE):
						$value = $yych;
						while ($scanner['class_attrib_next'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych) {
							$value .= $yych;
						}
						return AR_HTMLPARSER_T_ATTRIB_VAL;
					break;
					case $yych === '"' && ($YYSTATE == AR_HTMLPARSER_STATE_DOCTYPE):
						$yych = $yych = $YYBUFFER[++$YYCURSOR];
						while ($yych !== "\000" && $yych !== '"') {
							$value .= $yych;
							$yych = $yych = $YYBUFFER[++$YYCURSOR];
						}
						$value = '"'.$value.'"';
						$yych = $YYBUFFER[++$YYCURSOR];
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}
						return AR_HTMLPARSER_T_ATTRIB_VAL;
					break;
					case $yych === '"' && ($YYSTATE == AR_HTMLPARSER_STATE_ATTRIB):
					case $yych === "'" && ($YYSTATE == AR_HTMLPARSER_STATE_ATTRIB):
						$YYSTATE = AR_HTMLPARSER_STATE_OPEN_TAG;

						$quote = $yych;
						$yych = $yych = $YYBUFFER[++$YYCURSOR];
						while ($yych !== "\000" && $yych !== $quote) {
							$value .= $yych;
							$yych = $yych = $YYBUFFER[++$YYCURSOR];
						}
						$yych = $YYBUFFER[++$YYCURSOR];
$myVar = 'Value';
$higher = false;

if (rand(1, 6) > 3) {
    $higher = true;
} else {
    $higher = false;
}
						return AR_HTMLPARSER_T_ATTRIB_VAL;
					break;
					case $yych === '=' && ($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG):
						while ($scanner['class_whitespace'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych);
						$YYSTATE = AR_HTMLPARSER_STATE_ATTRIB;
						contine;
					break;
					case $yych === $scanner['class_whitespace'][$yych] && (($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG) || ($YYSTATE == AR_HTMLPARSER_STATE_CLOSE_TAG) || ($YYSTATE == AR_HTMLPARSER_STATE_DOCTYPE)):
						$yych = $YYBUFFER[++$YYCURSOR]; continue;
					break;
					case $yych === '-' && ($YYSTATE == AR_HTMLPARSER_STATE_COMMENT):
						if (substr($YYBUFFER, $YYCURSOR, 3) == '-->') {
							$YYSTATE = AR_HTMLPARSER_STATE_TEXT;
							$value = "-->"; $YYCURSOR+=3;
							return AR_HTMLPARSER_T_TEXT;
						}
						$value = '-';
						$YYBUFFER[++$YYCURSOR];
						return AR_HTMLPARSER_T_TEXT;
					break;
					case ($YYSTATE == AR_HTMLPARSER_STATE_TEXT) && (substr_compare($YYBUFFER, '<!--', $YYCURSOR, 4) == 0 ):
							$value		= "<!--"; $YYCURSOR+=4;
							$YYSTATE	= AR_HTMLPARSER_STATE_COMMENT;
							return AR_HTMLPARSER_T_TEXT;
					break;
					case ($YYSTATE == AR_HTMLPARSER_STATE_SCRIPT) && ( substr_compare($YYBUFFER, '</script>', $YYCURSOR, 9, true) == 0 ):
						$YYCONTEXT = CONTEXT_NORMAL;
						// fallthrough
					case ($YYSTATE == AR_HTMLPARSER_STATE_TEXT) && substr($YYBUFFER, $YYCURSOR, 2) == '</':
						$YYSTATE	= AR_HTMLPARSER_STATE_CLOSE_TAG;
						$YYCURSOR	+= 1;
						$value		= "";
						while ($scanner['class_ident_next'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych) {
							$value .= $yych;
						}
						return AR_HTMLPARSER_T_CLOSE_TAG;
					break;
					case ($YYSTATE == AR_HTMLPARSER_STATE_TEXT) && ( substr_compare($YYBUFFER, '<!doctype', $YYCURSOR, 9 , true) == 0 ):
						$YYSTATE	= AR_HTMLPARSER_STATE_DOCTYPE;
						$value		= substr($YYBUFFER, $YYCURSOR, 9/* strlen('<!doctype')*/);
						$YYCURSOR	+= 9 /*strlen('<!doctype')*/;
						return AR_HTMLPARSER_T_DOCTYPE;
					break;
					case $yych == '<' && ($YYSTATE == AR_HTMLPARSER_STATE_TEXT):
						$YYSTATE	= AR_HTMLPARSER_STATE_OPEN_TAG;
						$value		= "";
						while ($scanner['class_ident_next'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych) {
							$value .= $yych;
						}
						if (strtolower($value) == 'script') {
							$YYCONTEXT = CONTEXT_SCRIPT;
						}
						return AR_HTMLPARSER_T_OPEN_TAG;
					break;
					case $yych === $scanner['class_attrib_start'][$yych] && ($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG):
						$value = $yych;
						while ($scanner['class_attrib_next'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych) {
							$value .= $yych;
						}
						return AR_HTMLPARSER_T_ATTRIB;
					break;
					case $yych === $scanner['class_number'][$yych] && ($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG):
						$value = $yych;
						while ($scanner['class_number'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych) {
							$value .= $yych;
						}
						return AR_HTMLPARSER_T_NUMBER;
					break;
					case $yych === '>' && (($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG) || ($YYSTATE == AR_HTMLPARSER_STATE_CLOSE_TAG) || ($YYSTATE == AR_HTMLPARSER_STATE_DOCTYPE)):
						if ($YYCONTEXT == CONTEXT_SCRIPT) {
							$YYSTATE = AR_HTMLPARSER_STATE_SCRIPT;
						} else {
							$YYSTATE = AR_HTMLPARSER_STATE_TEXT;
						}
						$yych = $YYBUFFER[++$YYCURSOR]; continue;
					break;
					case ord($yych) === 0:
						$value = $yych;
						return AR_HTMLPARSER_T_EOF;
					break;
					case $yych === $yych && ($YYSTATE == AR_HTMLPARSER_STATE_ATTRIB):
						$YYSTATE = AR_HTMLPARSER_STATE_OPEN_TAG;
						$value = "";
						while ($scanner['class_whitespace'][$yych] !== $yych && ($yych != "\000" && $yych != ">")) {
							$value .= $yych;
							$yych = $YYBUFFER[++$YYCURSOR];
						}
						return AR_HTMLPARSER_T_ATTRIB_VAL;
					break;
					case $yych === $yych && ($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG):
						$yych = $YYBUFFER[++$YYCURSOR]; continue;
					break;
					case ($YYSTATE == AR_HTMLPARSER_STATE_TEXT):
						$value = "";
						while ( $yych != '<'  && $yych != "\000" ) {
							$value .= $yych;
							$yych = $YYBUFFER[++$YYCURSOR];
						}
						return AR_HTMLPARSER_T_TEXT;
					break;
					default:
						$value = $yych;
						$YYCURSOR++;
						return AR_HTMLPARSER_T_TEXT;
				}
			} while (1);

		}

		protected static function nextToken(&$parser) {
			$scanner = &$parser['scanner'];

			$new_token = static::scan($scanner, $new_value);

			if (isset($parser["token_ahead"])) {
				$parser["token"] = $parser["token_ahead"];
				$parser["token_value"] = $parser["token_ahead_value"];
			}
			$parser["token_ahead"] = $new_token;
			$parser["token_ahead_value"] = $new_value;
		}


		protected static function parse_Text(&$parser) {
			$result = "";
			while ($parser["token_ahead"] == AR_HTMLPARSER_T_TEXT) {
				static::nextToken($parser);
				$result .= $parser["token_value"];
			}
			return $result;
		}

		protected static function parse_Tag_Open(&$parser) {
			$singles = array(
				'br', 'img', 'area', 'link', 'param', 'hr', 'base', 'meta',
				'input', 'col'
			);

			$result = array('type' => 'tag');
			$tagName = $parser["token_ahead_value"];
			if (in_array(strtolower($tagName), $singles)) {
				$result['type'] = 'tagSingle';
			}
			$result['tagName'] = $tagName;
			static::nextToken($parser);
			while ($parser["token_ahead"] == AR_HTMLPARSER_T_ATTRIB) {
				static::nextToken($parser);
				$attrib = $parser["token_value"];
				$attrib_value = false;
				if ($parser["token_ahead"] == AR_HTMLPARSER_T_ATTRIB_VAL) {
					static::nextToken($parser);
					$attrib_value = $parser["token_value"];
				}
				$result['attribs'][$attrib] = $attrib_value;
			}

			return $result;
		}

		protected static function parse_Node(&$parser, &$stack) {
			$siblings = array('table', 'tr', 'td', 'li', 'ul');

			if (count($stack)) {
				$parentNode	= &$stack[count($stack)-1];
				$tagName	= strtolower($parentNode['tagName']);
			}
			$result = array();
			while ($parser["token_ahead"] != AR_HTMLPARSER_T_EOF) {
				switch ($parser["token_ahead"]) {
					case AR_HTMLPARSER_T_TEXT:
						$node = array('type' => 'text');
						$node['html'] = static::parse_Text($parser);
						$result[] = $node;
					break;
					case AR_HTMLPARSER_T_DOCTYPE:
						$node = array('type' => 'doctype');
						static::nextToken($parser);
						while ($parser["token_ahead"] == AR_HTMLPARSER_T_ATTRIB_VAL) {
							static::nextToken($parser);
							$attrib_value = $parser["token_value"];
							$node['attribs'][] = $attrib_value;
						}
						$result[] = $node;
					break;
					case AR_HTMLPARSER_T_OPEN_TAG:
						$nextTag = strtolower($parser["token_ahead_value"]);
						if ($nextTag == $tagName && in_array($tagName, $siblings)) {
function myFunction($a) {
    switch ($a) {
        case 'foo':
            $x = 1;
            break;

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

    // $x is potentially undefined here.
    echo $x;
}
							if ($parser['options']['noTagResolving']) {
								$parentNode['htmlTagClose'] = "";
function myFunction($a) {
    switch ($a) {
        case 'foo':
            $x = 1;
            break;

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

    // $x is potentially undefined here.
    echo $x;
}
							}
							return $result;
						}

						$node = static::parse_Tag_Open($parser);
						if ($node) {

							if ($node['type'] !== 'tagSingle') {
								$stack[] = &$node;
								$node['children'] = static::parse_Node($parser, $stack);
								array_pop($stack);
								end($stack);
							}
							$result[] = $node;
						}
					break;
					case AR_HTMLPARSER_T_CLOSE_TAG:
						$closeTag = $parser["token_ahead_value"];
						if ($tagName != strtolower($closeTag)) {
							// continue parsing because closing tag does not match current tag
							// FIXME: create a better check
							static::nextToken($parser);

							// if we do not resolve tags, we have to add this one as text
							if ($parser['options']['noTagResolving']) {
								$node = array('type' => 'text');
								$node['html'] = "</".$parser["token_value"].">";
								$result[] = $node;
							}
							continue;
						}

						// if we do not resolve tags, we have to add this one as text
						if ($parser['options']['noTagResolving']) {
							$parentNode['htmlTagClose'] = "</".$parser['token_ahead_value'].">";
						}

						static::nextToken($parser);
						return $result;
					default:
						static::nextToken($parser);
				}
			}
			if ($parser['options']['noTagResolving']) {
				$parentNode['htmlTagClose'] = "";
			}
			return $result;
		}

		protected static function compile_Attribs(&$node) {
			$result = "";
			if (is_array($node['attribs'])) {
				foreach ($node['attribs'] as $key => $value) {
					$result .= " $key";
					if ($value !== false) {
						$result .= "=\"".str_replace('"', '\"', $value)."\"";
					}
				}
			}
			return $result;
		}

		public static function compile($node) {
			$result = "";
			switch ($node['type']) {
				case 'tag':
				case 'tagSingle':
					if ($node['tagName']) {
						$result .= "<".$node['tagName'];
						$result .= static::compile_Attribs($node);
						$result .= ">";
					}
				case 'root':
					if (is_array($node['children'])) {
						foreach ($node['children'] as $child) {
							$result .= static::compile($child);
						}
					}
					if ($node['type'] == 'tag') {
						if (isset($node['htmlTagClose'])) {
							$result .= $node['htmlTagClose'];
						} else {
							$result .= "</".$node['tagName'].">";
						}
					}
				break;
				case 'doctype':
					$result .= "<!DOCTYPE";
					foreach ($node['attribs'] as $attrib) {
						$result .= " $attrib";
					}
					$result .= ">";
				break;
				default:
					$result .= $node['html'];
				break;
			}
			return $result;
		}

		public static function parse($document, $options = false) {
			if (!$options) {
				$options = array();
			}
			$parser = array('options' => $options);
			$scanner = static::scanner($document);
			$parser['scanner'] = &$scanner;
			$stack = array();
			static::nextToken($parser);
			$result = array(
				'type' => 'root',
				'children' => static::parse_Node($parser, $stack)
			);
			return $result;
		}
	}


htmlparser::scan() F
last analyzed 2018-12-19 18:24 UTC

Complexity

Size

Duplication

Code Coverage

Importance

How to fix Long Method Complexity

Long Method

Available Fixes

Available Fixes

1			<?php
2			define('AR_HTMLPARSER_T_OPEN_TAG', 252);
3			define('AR_HTMLPARSER_T_CLOSE_TAG', 251);
4			define('AR_HTMLPARSER_T_TAG_END', 250);
5			define('AR_HTMLPARSER_T_ASSIGN', 248);
6			define('AR_HTMLPARSER_T_IDENT', 247);
7			define('AR_HTMLPARSER_T_STRING', 246);
8			define('AR_HTMLPARSER_T_ATTRIB', 245);
9			define('AR_HTMLPARSER_T_NUMBER', 244);
10			define('AR_HTMLPARSER_T_ATTRIB_VAL', 243);
11			define('AR_HTMLPARSER_T_DOCTYPE', 242);
12
13			define('AR_HTMLPARSER_T_EOF', 0);
14			define('AR_HTMLPARSER_T_TEXT', -1);
15			define('AR_HTMLPARSER_T_ERROR', -2);
16
17			define('AR_HTMLPARSER_STATE_TEXT', 1);
18			define('AR_HTMLPARSER_STATE_OPEN_TAG', 2);
19			define('AR_HTMLPARSER_STATE_CLOSE_TAG', 3);
20			define('AR_HTMLPARSER_STATE_ATTRIB', 4);
21			define('AR_HTMLPARSER_STATE_COMMENT', 5);
22			define('AR_HTMLPARSER_STATE_SCRIPT', 6);
23			define('AR_HTMLPARSER_STATE_DOCTYPE', 7);
24
25			define('CONTEXT_NORMAL', 1);
26			define('CONTEXT_SCRIPT', 2);
27
28			class htmlparser {
29
30	16		protected static function scanner($buffer) {
31	16		$scanner = array();
32	16		$scanner['YYBUFFER'] = $buffer."\000";
33	16		$scanner['YYCURSOR'] = 0;
34	16		$scanner['YYSTATE'] = AR_HTMLPARSER_STATE_TEXT;
35	16		$scanner['YYCONTEXT'] = CONTEXT_NORMAL;
36
37	16		$class_ident_start = array();
38	16		$start = ord('a');
39	16		$end = ord('z');
40	16		for ($i = $start; $i <= $end; $i++) {
41	16		$class_ident_start[chr($i)] = chr($i);
42	16		$class_ident_start[strtoupper(chr($i))] = strtoupper(chr($i));
43	16		}
44	16		$scanner['class_ident_start'] = $class_ident_start;
45
46	16		$class_attrib_start = $class_ident_start;
47	16		$scanner['class_attrib_start'] = $class_attrib_start;
48
49
50	16		$class_ident_next = $class_ident_start;
51	16		$class_number = array();
52	16		$start = ord('0');
53	16		$end = ord('9');
54	16	View Code Duplication	for ($i = $start; $i <= $end; $i++) {
55	16		$class_ident_next[chr($i)] = chr($i);
56	16		$class_number[chr($i)] = chr($i);
57	16		}
58	16		$scanner['class_ident_next'] = $class_ident_next;
59	16		$scanner['class_number'] = $class_number;
60
61			// List of allowed characters for attribute names;
62	16		$class_attrib_next = $class_ident_next;
63	16		$class_attrib_next[':'] = ':';
64	16		$class_attrib_next['-'] = '-';
65	16		$class_attrib_next['_'] = '_';
66	16		$class_attrib_next['.'] = '.';
67
68	16		$scanner['class_attrib_next'] = $class_attrib_next;
69
70
71	16		$class_whitespace = array(" " => " ", "\t" => "\t", "\r" => "\r", "\n" => "\n");
72	16		$scanner['class_whitespace'] = $class_whitespace;
73
74	16		return $scanner;
75			}
76
77	16		protected static function scan(&$scanner, &$value) {
78	16		$YYCURSOR = &$scanner["YYCURSOR"];
79	16		$YYBUFFER = &$scanner["YYBUFFER"];
80	16		$yych = $YYBUFFER[$YYCURSOR];
81	16		$YYSTATE = &$scanner["YYSTATE"];
82	16		$YYCONTEXT = &$scanner["YYCONTEXT"];
83
84			do {
85			switch (true) {
86	16	View Code Duplication	case $yych === $scanner['class_attrib_start'][$yych] && ($YYSTATE == AR_HTMLPARSER_STATE_DOCTYPE):
87			$value = $yych;
88			while ($scanner['class_attrib_next'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych) {
89			$value .= $yych;
90			}
91			return AR_HTMLPARSER_T_ATTRIB_VAL;
92			break;
93	16		case $yych === '"' && ($YYSTATE == AR_HTMLPARSER_STATE_DOCTYPE):
94			$yych = $yych = $YYBUFFER[++$YYCURSOR];
95		View Code Duplication	while ($yych !== "\000" && $yych !== '"') {
96			$value .= $yych;
97			$yych = $yych = $YYBUFFER[++$YYCURSOR];
98			}
99			$value = '"'.$value.'"';
100			$yych = $YYBUFFER[++$YYCURSOR];
			0 ignored issues – show Unused Code introduced 2015-11-26 08:52 UTC by Report Bug Copy Issue Report `$yych` 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...
101			return AR_HTMLPARSER_T_ATTRIB_VAL;
102			break;
103	16		case $yych === '"' && ($YYSTATE == AR_HTMLPARSER_STATE_ATTRIB):
104	16		case $yych === "'" && ($YYSTATE == AR_HTMLPARSER_STATE_ATTRIB):
105	3		$YYSTATE = AR_HTMLPARSER_STATE_OPEN_TAG;
106
107	3		$quote = $yych;
108	3		$yych = $yych = $YYBUFFER[++$YYCURSOR];
109	3	View Code Duplication	while ($yych !== "\000" && $yych !== $quote) {
110	3		$value .= $yych;
111	3		$yych = $yych = $YYBUFFER[++$YYCURSOR];
112	3		}
113	3		$yych = $YYBUFFER[++$YYCURSOR];
			0 ignored issues – show Unused Code introduced 2015-11-26 08:52 UTC by Report Bug Copy Issue Report `$yych` 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...
114	3		return AR_HTMLPARSER_T_ATTRIB_VAL;
115			break;
116	16		case $yych === '=' && ($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG):
117	3		while ($scanner['class_whitespace'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych);
118	3		$YYSTATE = AR_HTMLPARSER_STATE_ATTRIB;
119	3		contine;
120	3		break;
121	16		case $yych === $scanner['class_whitespace'][$yych] && (($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG) \|\| ($YYSTATE == AR_HTMLPARSER_STATE_CLOSE_TAG) \|\| ($YYSTATE == AR_HTMLPARSER_STATE_DOCTYPE)):
122	3		$yych = $YYBUFFER[++$YYCURSOR]; continue;
123			break;
124	16		case $yych === '-' && ($YYSTATE == AR_HTMLPARSER_STATE_COMMENT):
125			if (substr($YYBUFFER, $YYCURSOR, 3) == '-->') {
126			$YYSTATE = AR_HTMLPARSER_STATE_TEXT;
127			$value = "-->"; $YYCURSOR+=3;
128			return AR_HTMLPARSER_T_TEXT;
129			}
130			$value = '-';
131			$YYBUFFER[++$YYCURSOR];
132			return AR_HTMLPARSER_T_TEXT;
133			break;
134	16		case ($YYSTATE == AR_HTMLPARSER_STATE_TEXT) && (substr_compare($YYBUFFER, '<!--', $YYCURSOR, 4) == 0 ):
135			$value = "<!--"; $YYCURSOR+=4;
136			$YYSTATE = AR_HTMLPARSER_STATE_COMMENT;
137			return AR_HTMLPARSER_T_TEXT;
138			break;
139	16		case ($YYSTATE == AR_HTMLPARSER_STATE_SCRIPT) && ( substr_compare($YYBUFFER, '</script>', $YYCURSOR, 9, true) == 0 ):
140			$YYCONTEXT = CONTEXT_NORMAL;
141			// fallthrough
142	16		case ($YYSTATE == AR_HTMLPARSER_STATE_TEXT) && substr($YYBUFFER, $YYCURSOR, 2) == '</':
143	4		$YYSTATE = AR_HTMLPARSER_STATE_CLOSE_TAG;
144	4		$YYCURSOR += 1;
145	4		$value = "";
146	4		while ($scanner['class_ident_next'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych) {
147	4		$value .= $yych;
148	4		}
149	4		return AR_HTMLPARSER_T_CLOSE_TAG;
150			break;
151	16		case ($YYSTATE == AR_HTMLPARSER_STATE_TEXT) && ( substr_compare($YYBUFFER, '<!doctype', $YYCURSOR, 9 , true) == 0 ):
152			$YYSTATE = AR_HTMLPARSER_STATE_DOCTYPE;
153			$value = substr($YYBUFFER, $YYCURSOR, 9/* strlen('<!doctype')*/);
154			$YYCURSOR += 9 /strlen('<!doctype')/;
155			return AR_HTMLPARSER_T_DOCTYPE;
156			break;
157	16		case $yych == '<' && ($YYSTATE == AR_HTMLPARSER_STATE_TEXT):
158	4		$YYSTATE = AR_HTMLPARSER_STATE_OPEN_TAG;
159	4		$value = "";
160	4		while ($scanner['class_ident_next'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych) {
161	4		$value .= $yych;
162	4		}
163	4		if (strtolower($value) == 'script') {
164			$YYCONTEXT = CONTEXT_SCRIPT;
165			}
166	4		return AR_HTMLPARSER_T_OPEN_TAG;
167			break;
168	16	View Code Duplication	case $yych === $scanner['class_attrib_start'][$yych] && ($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG):
169	3		$value = $yych;
170	3		while ($scanner['class_attrib_next'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych) {
171	3		$value .= $yych;
172	3		}
173	3		return AR_HTMLPARSER_T_ATTRIB;
174			break;
175	16	View Code Duplication	case $yych === $scanner['class_number'][$yych] && ($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG):
176			$value = $yych;
177			while ($scanner['class_number'][$yych = $YYBUFFER[++$YYCURSOR]] == $yych) {
178			$value .= $yych;
179			}
180			return AR_HTMLPARSER_T_NUMBER;
181			break;
182	16		case $yych === '>' && (($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG) \|\| ($YYSTATE == AR_HTMLPARSER_STATE_CLOSE_TAG) \|\| ($YYSTATE == AR_HTMLPARSER_STATE_DOCTYPE)):
183	4		if ($YYCONTEXT == CONTEXT_SCRIPT) {
184			$YYSTATE = AR_HTMLPARSER_STATE_SCRIPT;
185			} else {
186	4		$YYSTATE = AR_HTMLPARSER_STATE_TEXT;
187			}
188	4		$yych = $YYBUFFER[++$YYCURSOR]; continue;
189			break;
190	16		case ord($yych) === 0:
191	16		$value = $yych;
192	16		return AR_HTMLPARSER_T_EOF;
193			break;
194	4		case $yych === $yych && ($YYSTATE == AR_HTMLPARSER_STATE_ATTRIB):
195			$YYSTATE = AR_HTMLPARSER_STATE_OPEN_TAG;
196			$value = "";
197			while ($scanner['class_whitespace'][$yych] !== $yych && ($yych != "\000" && $yych != ">")) {
198			$value .= $yych;
199			$yych = $YYBUFFER[++$YYCURSOR];
200			}
201			return AR_HTMLPARSER_T_ATTRIB_VAL;
202			break;
203	4		case $yych === $yych && ($YYSTATE == AR_HTMLPARSER_STATE_OPEN_TAG):
204			$yych = $YYBUFFER[++$YYCURSOR]; continue;
205			break;
206	4		case ($YYSTATE == AR_HTMLPARSER_STATE_TEXT):
207	4		$value = "";
208	4		while ( $yych != '<' && $yych != "\000" ) {
209	4		$value .= $yych;
210	4		$yych = $YYBUFFER[++$YYCURSOR];
211	4		}
212	4		return AR_HTMLPARSER_T_TEXT;
213			break;
214			default:
215			$value = $yych;
216			$YYCURSOR++;
217			return AR_HTMLPARSER_T_TEXT;
218			}
219	4		} while (1);
220
221			}
222
223	16		protected static function nextToken(&$parser) {
224	16		$scanner = &$parser['scanner'];
225
226	16		$new_token = static::scan($scanner, $new_value);
227
228	16		if (isset($parser["token_ahead"])) {
229	4		$parser["token"] = $parser["token_ahead"];
230	4		$parser["token_value"] = $parser["token_ahead_value"];
231	4		}
232	16		$parser["token_ahead"] = $new_token;
233	16		$parser["token_ahead_value"] = $new_value;
234	16		}
235
236
237	4		protected static function parse_Text(&$parser) {
238	4		$result = "";
239	4		while ($parser["token_ahead"] == AR_HTMLPARSER_T_TEXT) {
240	4		static::nextToken($parser);
241	4		$result .= $parser["token_value"];
242	4		}
243	4		return $result;
244			}
245
246	4		protected static function parse_Tag_Open(&$parser) {
247			$singles = array(
248	4		'br', 'img', 'area', 'link', 'param', 'hr', 'base', 'meta',
249	4		'input', 'col'
250	4		);
251
252	4		$result = array('type' => 'tag');
253	4		$tagName = $parser["token_ahead_value"];
254	4		if (in_array(strtolower($tagName), $singles)) {
255			$result['type'] = 'tagSingle';
256			}
257	4		$result['tagName'] = $tagName;
258	4		static::nextToken($parser);
259	4		while ($parser["token_ahead"] == AR_HTMLPARSER_T_ATTRIB) {
260	3		static::nextToken($parser);
261	3		$attrib = $parser["token_value"];
262	3		$attrib_value = false;
263	3		if ($parser["token_ahead"] == AR_HTMLPARSER_T_ATTRIB_VAL) {
264	3		static::nextToken($parser);
265	3		$attrib_value = $parser["token_value"];
266	3		}
267	3		$result['attribs'][$attrib] = $attrib_value;
268	3		}
269
270	4		return $result;
271			}
272
273	16		protected static function parse_Node(&$parser, &$stack) {
274	16		$siblings = array('table', 'tr', 'td', 'li', 'ul');
275
276	16		if (count($stack)) {
277	4		$parentNode = &$stack[count($stack)-1];
278	4		$tagName = strtolower($parentNode['tagName']);
279	4		}
280	16		$result = array();
281	16		while ($parser["token_ahead"] != AR_HTMLPARSER_T_EOF) {
282	4		switch ($parser["token_ahead"]) {
283	4		case AR_HTMLPARSER_T_TEXT:
284	4		$node = array('type' => 'text');
285	4		$node['html'] = static::parse_Text($parser);
286	4		$result[] = $node;
287	4		break;
288	4		case AR_HTMLPARSER_T_DOCTYPE:
289			$node = array('type' => 'doctype');
290			static::nextToken($parser);
291			while ($parser["token_ahead"] == AR_HTMLPARSER_T_ATTRIB_VAL) {
292			static::nextToken($parser);
293			$attrib_value = $parser["token_value"];
294			$node['attribs'][] = $attrib_value;
295			}
296			$result[] = $node;
297			break;
298	4		case AR_HTMLPARSER_T_OPEN_TAG:
299	4		$nextTag = strtolower($parser["token_ahead_value"]);
300	4		if ($nextTag == $tagName && in_array($tagName, $siblings)) {
			0 ignored issues – show Bug introduced 2015-11-26 08:52 UTC by Report Bug Copy Issue Report The variable `$tagName` 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 $x; } Loading history...
301			if ($parser['options']['noTagResolving']) {
302			$parentNode['htmlTagClose'] = "";
			0 ignored issues – show Bug introduced 2015-11-26 08:52 UTC by Report Bug Copy Issue Report The variable `$parentNode` 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...
303			}
304			return $result;
305			}
306
307	4		$node = static::parse_Tag_Open($parser);
308	4		if ($node) {
			0 ignored issues – show Bug Best Practice introduced 2015-11-26 08:52 UTC by Report Bug Copy Issue Report The expression `$node` of type `array` is implicitly converted to a boolean; are you sure this is intended? If so, consider using `! empty($expr)` instead to make it clear that you intend to check for an array without elements. This check marks implicit conversions of arrays to boolean values in a comparison. While in PHP an empty array is considered to be equal (but not identical) to false, this is not always apparent. Consider making the comparison explicit by using `empty(..)` or `! empty(...)` instead. Loading history...
309	4		if ($node['type'] !== 'tagSingle') {
310	4		$stack[] = &$node;
311	4		$node['children'] = static::parse_Node($parser, $stack);
312	4		array_pop($stack);
313	4		end($stack);
314	4		}
315	4		$result[] = $node;
316	4		}
317	4		break;
318	4		case AR_HTMLPARSER_T_CLOSE_TAG:
319	4		$closeTag = $parser["token_ahead_value"];
320	4		if ($tagName != strtolower($closeTag)) {
321			// continue parsing because closing tag does not match current tag
322			// FIXME: create a better check
323			static::nextToken($parser);
324
325			// if we do not resolve tags, we have to add this one as text
326			if ($parser['options']['noTagResolving']) {
327			$node = array('type' => 'text');
328			$node['html'] = "</".$parser["token_value"].">";
329			$result[] = $node;
330			}
331			continue;
332			}
333
334			// if we do not resolve tags, we have to add this one as text
335	4		if ($parser['options']['noTagResolving']) {
336			$parentNode['htmlTagClose'] = "</".$parser['token_ahead_value'].">";
337			}
338
339	4		static::nextToken($parser);
340	4		return $result;
341			default:
342			static::nextToken($parser);
343	4		}
344	4		}
345	16		if ($parser['options']['noTagResolving']) {
346	12		$parentNode['htmlTagClose'] = "";
347	12		}
348	16		return $result;
349			}
350
351	4		protected static function compile_Attribs(&$node) {
352	4		$result = "";
353	4		if (is_array($node['attribs'])) {
354	3		foreach ($node['attribs'] as $key => $value) {
355	3		$result .= " $key";
356	3		if ($value !== false) {
357	3		$result .= "=\"".str_replace('"', '\"', $value)."\"";
358	3		}
359	3		}
360	3		}
361	4		return $result;
362			}
363
364	4		public static function compile($node) {
365	4		$result = "";
366	4		switch ($node['type']) {
367	4		case 'tag':
368	4		case 'tagSingle':
369	4		if ($node['tagName']) {
370	4		$result .= "<".$node['tagName'];
371	4		$result .= static::compile_Attribs($node);
372	4		$result .= ">";
373	4		}
374	4		case 'root':
375	4		if (is_array($node['children'])) {
376	4		foreach ($node['children'] as $child) {
377	4		$result .= static::compile($child);
378	4		}
379	4		}
380	4		if ($node['type'] == 'tag') {
381	4		if (isset($node['htmlTagClose'])) {
382			$result .= $node['htmlTagClose'];
383			} else {
384	4		$result .= "</".$node['tagName'].">";
385			}
386	4		}
387	4		break;
388	4		case 'doctype':
389			$result .= "<!DOCTYPE";
390			foreach ($node['attribs'] as $attrib) {
391			$result .= " $attrib";
392			}
393			$result .= ">";
394			break;
395	4		default:
396	4		$result .= $node['html'];
397	4		break;
398	4		}
399	4		return $result;
400			}
401
402	16		public static function parse($document, $options = false) {
403	16		if (!$options) {
404	4		$options = array();
405	4		}
406	16		$parser = array('options' => $options);
407	16		$scanner = static::scanner($document);
408	16		$parser['scanner'] = &$scanner;
409	16		$stack = array();
410	16		static::nextToken($parser);
411			$result = array(
412	16		'type' => 'root',
413	16		'children' => static::parse_Node($parser, $stack)
414	16		);
415	16		return $result;
416			}
417			}
418

Ariadne-CMS / ariadne

htmlparser::scan() F last analyzed 2018-12-19 18:24 UTC

Complexity

Size

Duplication

Code Coverage

Importance

How to fix Long Method Complexity

Long Method

Available Fixes

Available Fixes

Duplication Side-by-Side

Filter issues like

htmlparser::scan() F
last analyzed 2018-12-19 18:24 UTC