Issues in minify-html.php - New Issues - Inspection of "updated readme with 2.3.2 changelog" - futtta/autoptimize - Measure and Improve Code Quality continuously with Scrutinizer

Completed

Push — master ( 9a01d9...c990d6 )

by frank

created 2018-01-04 16:45 UTC

classes/external/php/minify-html.php (1 issue)

Labels

Severity

Minor 1

Upgrade to new PHP Analysis Engine

These results are based on our legacy PHP analysis, consider migrating to our new PHP analysis engine instead. Learn more

<?php
/**
 * Class Minify_HTML  
 * @package Minify
 */

/**
 * Compress HTML
 *
 * This is a heavy regex-based removal of whitespace, unnecessary comments and 
 * tokens. IE conditional comments are preserved. There are also options to have
 * STYLE and SCRIPT blocks compressed by callback functions. 
 * 
 * A test suite is available.
 * 
 * @package Minify
 * @author Stephen Clay <[email protected]>
 */
class Minify_HTML {

    /**
     * "Minify" an HTML page
     *
     * @param string $html
     *
     * @param array $options
     *
     * 'cssMinifier' : (optional) callback function to process content of STYLE
     * elements.
     * 
     * 'jsMinifier' : (optional) callback function to process content of SCRIPT
     * elements. Note: the type attribute is ignored.
     * 
     * 'xhtml' : (optional boolean) should content be treated as XHTML1.0? If
     * unset, minify will sniff for an XHTML doctype.
	 * 
     * 'keepComments' : (optional boolean) should the HTML comments be kept
     * in the HTML Code?
     * 
     * @return string
     */
    public static function minify($html, $options = array()) {
        $min = new Minify_HTML($html, $options);
        return $min->process();
    }
    
    
    /**
     * Create a minifier object
     *
     * @param string $html
     *
     * @param array $options
     *
     * 'cssMinifier' : (optional) callback function to process content of STYLE
     * elements.
     * 
     * 'jsMinifier' : (optional) callback function to process content of SCRIPT
     * elements. Note: the type attribute is ignored.
     * 
     * 'xhtml' : (optional boolean) should content be treated as XHTML1.0? If
     * unset, minify will sniff for an XHTML doctype.
	 * 
     * 'xhtml' : (optional boolean) should content be treated as XHTML1.0? If
     * unset, minify will sniff for an XHTML doctype.
     * 
     * @return null
     */
    public function __construct($html, $options = array())
    {
        $this->_html = str_replace("\r\n", "\n", trim($html));
        if (isset($options['xhtml'])) {
            $this->_isXhtml = (bool)$options['xhtml'];
        }
        if (isset($options['cssMinifier'])) {
            $this->_cssMinifier = $options['cssMinifier'];
        }
        if (isset($options['jsMinifier'])) {
            $this->_jsMinifier = $options['jsMinifier'];
        }
        if (isset($options['keepComments'])) {
            $this->_keepComments = $options['keepComments'];
        }
    }
    
    
    /**
     * Minify the markeup given in the constructor
     * 
     * @return string
     */
    public function process()
    {
        if ($this->_isXhtml === null) {
            $this->_isXhtml = (false !== strpos($this->_html, '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML'));
        }
        
        $this->_replacementHash = 'MINIFYHTML' . md5($_SERVER['REQUEST_TIME']);
        $this->_placeholders = array();
        
        // replace SCRIPTs (and minify) with placeholders
        $this->_html = preg_replace_callback(
            '/(\\s*)(<script\\b[^>]*?>)([\\s\\S]*?)<\\/script>(\\s*)/i'
            ,array($this, '_removeScriptCB')
            ,$this->_html);
        
        // replace STYLEs (and minify) with placeholders
        $this->_html = preg_replace_callback(
            '/\\s*(<style\\b[^>]*?>)([\\s\\S]*?)<\\/style>\\s*/i'
            ,array($this, '_removeStyleCB')
            ,$this->_html);
        
        // remove HTML comments (not containing IE conditional comments).
		if  ($this->_keepComments == false) {
			$this->_html = preg_replace_callback(
				'/<!--([\\s\\S]*?)-->/'
				,array($this, '_commentCB')
				,$this->_html);
        }
		
        // replace PREs with placeholders
        $this->_html = preg_replace_callback('/\\s*(<pre\\b[^>]*?>[\\s\\S]*?<\\/pre>)\\s*/i'
            ,array($this, '_removePreCB')
            ,$this->_html);
        
        // replace TEXTAREAs with placeholders
        $this->_html = preg_replace_callback(
            '/\\s*(<textarea\\b[^>]*?>[\\s\\S]*?<\\/textarea>)\\s*/i'
            ,array($this, '_removeTextareaCB')
            ,$this->_html);
			
		// replace data: URIs with placeholders
        $this->_html = preg_replace_callback(
            '/(=("|\')data:.*\\2)/Ui'
            ,array($this, '_removeDataURICB')
            ,$this->_html);
        
        // trim each line.
        // replace by space instead of '' to avoid newline after opening tag getting zapped
        $this->_html = preg_replace('/^\s+|\s+$/m', ' ', $this->_html);
        
        // remove ws around block/undisplayed elements
        $this->_html = preg_replace('/\\s+(<\\/?(?:area|article|aside|base(?:font)?|blockquote|body'
            .'|canvas|caption|center|col(?:group)?|dd|dir|div|dl|dt|fieldset|figcaption|figure|footer|form'
            .'|frame(?:set)?|h[1-6]|head|header|hgroup|hr|html|legend|li|link|main|map|menu|meta|nav'
            .'|ol|opt(?:group|ion)|output|p|param|section|t(?:able|body|head|d|h||r|foot|itle)'
            .'|ul|video)\\b[^>]*>)/i', '$1', $this->_html);
            
        // remove ws outside of all elements
        $this->_html = preg_replace_callback(
            '/>([^<]+)</'
            ,array($this, '_outsideTagCB')
            ,$this->_html);
        
        // use newlines before 1st attribute in open tags (to limit line lengths)
        //$this->_html = preg_replace('/(<[a-z\\-]+)\\s+([^>]+>)/i', "$1\n$2", $this->_html);

        
        // fill placeholders
        $this->_html = str_replace(
            array_keys($this->_placeholders)
            ,array_values($this->_placeholders)
            ,$this->_html
        );
        return $this->_html;
    }
    
    protected function _commentCB($m)
    {
        return (0 === strpos($m[1], '[') || false !== strpos($m[1], '<!['))
            ? $m[0]
            : '';
    }
    
    protected function _reservePlace($content)
    {
        $placeholder = '%' . $this->_replacementHash . count($this->_placeholders) . '%';
        $this->_placeholders[$placeholder] = $content;
        return $placeholder;
    }

    protected $_isXhtml = null;
    protected $_replacementHash = null;
    protected $_placeholders = array();
    protected $_cssMinifier = null;
    protected $_jsMinifier = null;
	protected $_keepComments = false;

    protected function _outsideTagCB($m)
    {
        return '>' . preg_replace('/^\\s+|\\s+$/', ' ', $m[1]) . '<';
    }
    
    protected function _removePreCB($m)
    {
        return $this->_reservePlace($m[1]);
    }
    
    protected function _removeTextareaCB($m)
    {
        return $this->_reservePlace($m[1]);
    }
	
	protected function _removeDataURICB($m)
    {
        return $this->_reservePlace($m[1]);
    }

    protected function _removeStyleCB($m)
    {
        $openStyle = $m[1];
        $css = $m[2];
        // remove HTML comments
        $css = preg_replace('/(?:^\\s*<!--|-->\\s*$)/', '', $css);
        
        // remove CDATA section markers
        $css = $this->_removeCdata($css);
        
        // minify
        $minifier = $this->_cssMinifier
            ? $this->_cssMinifier
            : 'trim';
        $css = call_user_func($minifier, $css);
        
        return $this->_reservePlace($this->_needsCdata($css)
            ? "{$openStyle}/*<![CDATA[*/{$css}/*]]>*/</style>"
            : "{$openStyle}{$css}</style>"
        );
    }

    protected function _removeScriptCB($m)
    {
        $openScript = $m[2];
        $js = $m[3];
        
        // whitespace surrounding? preserve at least one space
        $ws1 = ($m[1] === '') ? '' : ' ';
        $ws2 = ($m[4] === '') ? '' : ' ';
 
        // remove HTML comments (and ending "//" if present)
        $js = preg_replace('/(?:^\\s*<!--\\s*|\\s*(?:\\/\\/)?\\s*-->\\s*$)/', '', $js);
            
        // remove CDATA section markers
        $js = $this->_removeCdata($js);
        
        // minify
        $minifier = $this->_jsMinifier
            ? $this->_jsMinifier
            : 'trim'; 
        $js = call_user_func($minifier, $js);
        
        return $this->_reservePlace($this->_needsCdata($js)
            ? "{$ws1}{$openScript}/*<![CDATA[*/{$js}/*]]>*/</script>{$ws2}"
            : "{$ws1}{$openScript}{$js}</script>{$ws2}"
        );
    }

    protected function _removeCdata($str)
    {
        return (false !== strpos($str, '<![CDATA['))
            ? str_replace(array('/* <![CDATA[ */','/* ]]> */','/*<![CDATA[*/','/*]]>*/','<![CDATA[', ']]>'), '', $str)
            : $str;
    }
    
    protected function _needsCdata($str)
    {
        return ($this->_isXhtml && preg_match('/(?:[<&]|\\-\\-|\\]\\]>)/', $str));
    }
}


1		<?php
2		/**
3		* Class Minify_HTML
4		* @package Minify
5		*/
6
7		/**
8		* Compress HTML
9		*
10		* This is a heavy regex-based removal of whitespace, unnecessary comments and
11		* tokens. IE conditional comments are preserved. There are also options to have
12		* STYLE and SCRIPT blocks compressed by callback functions.
13		*
14		* A test suite is available.
15		*
16		* @package Minify
17		* @author Stephen Clay <[email protected]>
18		*/
19		class Minify_HTML {
20
21		/**
22		* "Minify" an HTML page
23		*
24		* @param string $html
25		*
26		* @param array $options
27		*
28		* 'cssMinifier' : (optional) callback function to process content of STYLE
29		* elements.
30		*
31		* 'jsMinifier' : (optional) callback function to process content of SCRIPT
32		* elements. Note: the type attribute is ignored.
33		*
34		* 'xhtml' : (optional boolean) should content be treated as XHTML1.0? If
35		* unset, minify will sniff for an XHTML doctype.
36		*
37		* 'keepComments' : (optional boolean) should the HTML comments be kept
38		* in the HTML Code?
39		*
40		* @return string
41		*/
42		public static function minify($html, $options = array()) {
43		$min = new Minify_HTML($html, $options);
44		return $min->process();
45		}
46
47
48		/**
49		* Create a minifier object
50		*
51		* @param string $html
52		*
53		* @param array $options
54		*
55		* 'cssMinifier' : (optional) callback function to process content of STYLE
56		* elements.
57		*
58		* 'jsMinifier' : (optional) callback function to process content of SCRIPT
59		* elements. Note: the type attribute is ignored.
60		*
61		* 'xhtml' : (optional boolean) should content be treated as XHTML1.0? If
62		* unset, minify will sniff for an XHTML doctype.
63		*
64		* 'xhtml' : (optional boolean) should content be treated as XHTML1.0? If
65		* unset, minify will sniff for an XHTML doctype.
66		*
67		* @return null
68		*/
69		public function __construct($html, $options = array())
70		{
71		$this->_html = str_replace("\r\n", "\n", trim($html));
72		if (isset($options['xhtml'])) {
73		$this->_isXhtml = (bool)$options['xhtml'];
74		}
75		if (isset($options['cssMinifier'])) {
76		$this->_cssMinifier = $options['cssMinifier'];
77		}
78		if (isset($options['jsMinifier'])) {
79		$this->_jsMinifier = $options['jsMinifier'];
80		}
81		if (isset($options['keepComments'])) {
82		$this->_keepComments = $options['keepComments'];
83		}
84		}
85
86
87		/**
88		* Minify the markeup given in the constructor
89		*
90		* @return string
91		*/
92		public function process()
93		{
94	View Code Duplication	if ($this->_isXhtml === null) {
95		$this->_isXhtml = (false !== strpos($this->_html, '<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML'));
96		}
97
98		$this->_replacementHash = 'MINIFYHTML' . md5($_SERVER['REQUEST_TIME']);
99		$this->_placeholders = array();
100
101		// replace SCRIPTs (and minify) with placeholders
102		$this->_html = preg_replace_callback(
103		'/(\\s)(<script\\b[^>]?>)([\\s\\S]?)<\\/script>(\\s)/i'
104		,array($this, '_removeScriptCB')
105		,$this->_html);
106
107		// replace STYLEs (and minify) with placeholders
108		$this->_html = preg_replace_callback(
109		'/\\s(<style\\b[^>]?>)([\\s\\S]?)<\\/style>\\s/i'
110		,array($this, '_removeStyleCB')
111		,$this->_html);
112
113		// remove HTML comments (not containing IE conditional comments).
114		if ($this->_keepComments == false) {
115		$this->_html = preg_replace_callback(
116		'/<!--([\\s\\S]*?)-->/'
117		,array($this, '_commentCB')
118		,$this->_html);
119		}
120
121		// replace PREs with placeholders
122		$this->_html = preg_replace_callback('/\\s(<pre\\b[^>]?>[\\s\\S]?<\\/pre>)\\s/i'
123		,array($this, '_removePreCB')
124		,$this->_html);
125
126		// replace TEXTAREAs with placeholders
127		$this->_html = preg_replace_callback(
128		'/\\s(<textarea\\b[^>]?>[\\s\\S]?<\\/textarea>)\\s/i'
129		,array($this, '_removeTextareaCB')
130		,$this->_html);
131
132		// replace data: URIs with placeholders
133		$this->_html = preg_replace_callback(
134		'/(=("\|\')data:.*\\2)/Ui'
135		,array($this, '_removeDataURICB')
136		,$this->_html);
137
138		// trim each line.
139		// replace by space instead of '' to avoid newline after opening tag getting zapped
140		$this->_html = preg_replace('/^\s+\|\s+$/m', ' ', $this->_html);
141
142		// remove ws around block/undisplayed elements
143		$this->_html = preg_replace('/\\s+(<\\/?(?:area\|article\|aside\|base(?:font)?\|blockquote\|body'
144		.'\|canvas\|caption\|center\|col(?:group)?\|dd\|dir\|div\|dl\|dt\|fieldset\|figcaption\|figure\|footer\|form'
145		.'\|frame(?:set)?\|h[1-6]\|head\|header\|hgroup\|hr\|html\|legend\|li\|link\|main\|map\|menu\|meta\|nav'
146		.'\|ol\|opt(?:group\|ion)\|output\|p\|param\|section\|t(?:able\|body\|head\|d\|h\|\|r\|foot\|itle)'
147		.'\|ul\|video)\\b[^>]*>)/i', '$1', $this->_html);
148
149		// remove ws outside of all elements
150		$this->_html = preg_replace_callback(
151		'/>([^<]+)</'
152		,array($this, '_outsideTagCB')
153		,$this->_html);
154
155		// use newlines before 1st attribute in open tags (to limit line lengths)
156		//$this->_html = preg_replace('/(<[a-z\\-]+)\\s+([^>]+>)/i', "$1\n$2", $this->_html);
		0 ignored issues – show Unused Code Comprehensibility introduced 2016-11-16 14:04 UTC by Report Bug Copy Issue Report Show Similar Issues like this `58%` of this comment could be valid code. Did you maybe forget this after debugging? Sometimes obsolete code just ends up commented out instead of removed. In this case it is better to remove the code once you have checked you do not need it. The code might also have been commented out for debugging purposes. In this case it is vital that someone uncomments it again or your project may behave in very unexpected ways in production. This check looks for comments that seem to be mostly valid code and reports them. Loading history...
157
158		// fill placeholders
159		$this->_html = str_replace(
160		array_keys($this->_placeholders)
161		,array_values($this->_placeholders)
162		,$this->_html
163		);
164		return $this->_html;
165		}
166
167		protected function _commentCB($m)
168		{
169		return (0 === strpos($m[1], '[') \|\| false !== strpos($m[1], '<!['))
170		? $m[0]
171		: '';
172		}
173
174		protected function _reservePlace($content)
175		{
176		$placeholder = '%' . $this->_replacementHash . count($this->_placeholders) . '%';
177		$this->_placeholders[$placeholder] = $content;
178		return $placeholder;
179		}
180
181		protected $_isXhtml = null;
182		protected $_replacementHash = null;
183		protected $_placeholders = array();
184		protected $_cssMinifier = null;
185		protected $_jsMinifier = null;
186		protected $_keepComments = false;
187
188		protected function _outsideTagCB($m)
189		{
190		return '>' . preg_replace('/^\\s+\|\\s+$/', ' ', $m[1]) . '<';
191		}
192
193		protected function _removePreCB($m)
194		{
195		return $this->_reservePlace($m[1]);
196		}
197
198		protected function _removeTextareaCB($m)
199		{
200		return $this->_reservePlace($m[1]);
201		}
202
203		protected function _removeDataURICB($m)
204		{
205		return $this->_reservePlace($m[1]);
206		}
207
208	View Code Duplication	protected function _removeStyleCB($m)
209		{
210		$openStyle = $m[1];
211		$css = $m[2];
212		// remove HTML comments
213		$css = preg_replace('/(?:^\\s<!--\|-->\\s$)/', '', $css);
214
215		// remove CDATA section markers
216		$css = $this->_removeCdata($css);
217
218		// minify
219		$minifier = $this->_cssMinifier
220		? $this->_cssMinifier
221		: 'trim';
222		$css = call_user_func($minifier, $css);
223
224		return $this->_reservePlace($this->_needsCdata($css)
225		? "{$openStyle}/<![CDATA[/{$css}/]]>/</style>"
226		: "{$openStyle}{$css}</style>"
227		);
228		}
229
230	View Code Duplication	protected function _removeScriptCB($m)
231		{
232		$openScript = $m[2];
233		$js = $m[3];
234
235		// whitespace surrounding? preserve at least one space
236		$ws1 = ($m[1] === '') ? '' : ' ';
237		$ws2 = ($m[4] === '') ? '' : ' ';
238
239		// remove HTML comments (and ending "//" if present)
240		$js = preg_replace('/(?:^\\s<!--\\s\|\\s(?:\\/\\/)?\\s-->\\s*$)/', '', $js);
241
242		// remove CDATA section markers
243		$js = $this->_removeCdata($js);
244
245		// minify
246		$minifier = $this->_jsMinifier
247		? $this->_jsMinifier
248		: 'trim';
249		$js = call_user_func($minifier, $js);
250
251		return $this->_reservePlace($this->_needsCdata($js)
252		? "{$ws1}{$openScript}/<![CDATA[/{$js}/]]>/</script>{$ws2}"
253		: "{$ws1}{$openScript}{$js}</script>{$ws2}"
254		);
255		}
256
257		protected function _removeCdata($str)
258		{
259		return (false !== strpos($str, '<![CDATA['))
260		? str_replace(array('/* <![CDATA[ /','/ ]]> /','/<![CDATA[/','/]]>*/','<![CDATA[', ']]>'), '', $str)
261		: $str;
262		}
263
264		protected function _needsCdata($str)
265		{
266		return ($this->_isXhtml && preg_match('/(?:[<&]\|\\-\\-\|\\]\\]>)/', $str));
267		}
268		}
269

futtta / autoptimize

Push — master ( 9a01d9...c990d6 )

classes/external/php/minify-html.php (1 issue)

Labels

Severity

Introduced By

Upgrade to new PHP Analysis Engine

Duplication Side-by-Side

Filter issues like