Filter::isUtf8() - Code Metrics - gplcart/xss - Measure and Improve Code Quality continuously with Scrutinizer

Filter::isUtf8() A
last analyzed 2018-03-10 14:53 UTC

↳ Parent: Filter

Complexity

Conditions	2
Paths	2

Size

Total Lines	8
Code Lines	4

Duplication

Lines	0
Ratio	0 %

Importance

Changes

Metric	Value
dl	0
loc	8
rs	9.4285
c	0
b	0
f	0
cc	2
eloc	4
nc	2
nop	1

<?php

/**
 * @package XSS filter
 * @author Iurii Makukh <[email protected]>
 * @copyright Copyright (c) 2018, Iurii Makukh
 * @license https://www.gnu.org/licenses/gpl.html GNU/GPLv3
 */

namespace gplcart\modules\xss\helpers;

/**
 * XSS filter. Based on Drupal's XSS filter
 */
class Filter
{

    /**
     * An array of allowed protocols
     * @var array
     */
    protected $protocols;

    /**
     * An array of allowed tags
     * @var array
     */
    protected $tags;

    /**
     * Constructor
     */
    public function __construct()
    {
        $this->tags = array();
        $this->protocols = array();
    }

    /**
     * Set allowed protocols
     * @param array $protocols
     * @return $this
     */
    public function setProtocols(array $protocols)
    {
        $this->protocols = $protocols;
        return $this;
    }

    /**
     * Set allowed tags
     * @param array $tags
     * @return $this
     */
    public function setTags(array $tags)
    {
        $this->tags = $tags;
        return $this;
    }

    /**
     * Filter a string
     * @param string $string
     * @return string
     */
    public function filter($string)
    {
        // Only operate on valid UTF-8 strings. This is necessary to prevent cross
        // site scripting issues on Internet Explorer 6.
        if (!$this->isUtf8($string)) {
            return '';
        }

        // Remove NULL characters (ignored by some browsers).
        $string = str_replace(chr(0), '', $string);

        // Remove Netscape 4 JS entities.
        $string = preg_replace('%&\s*\{[^}]*(\}\s*;?|$)%', '', $string);

        // Defuse all HTML entities.
        $string = str_replace('&', '&amp;', $string);

        // Change back only well-formed entities in our whitelist:
        // Decimal numeric entities.
        $string = preg_replace('/&amp;#([0-9]+;)/', '&#\1', $string);

        // Hexadecimal numeric entities.
        $string = preg_replace('/&amp;#[Xx]0*((?:[0-9A-Fa-f]{2})+;)/', '&#x\1', $string);

        // Named entities.
        $string = preg_replace('/&amp;([A-Za-z][A-Za-z0-9]*;)/', '&\1', $string);

        return (string) preg_replace_callback('%
            (
            <(?=[^a-zA-Z!/])  # a lone <
            |                 # or
            <!--.*?-->        # a comment
            |                 # or
            <[^>]*(>|$)       # a string that starts with a <, up until the > or the end of the string
            |                 # or
            >                 # just a >
            )%x', array($this, 'build'), $string);
    }

    /**
     * Whether a string is valid UTF-8
     * @param string $string
     * @return boolean
     */
    protected function isUtf8($string)
    {
        if (strlen($string) == 0) {
            return true;
        }

        return preg_match('/^./us', $string) === 1;
    }

    /**
     * Build a filtered tag
     * @param array $m
     * @return string
     */
    protected function build($m)
    {
        $string = $m[1];

        if (substr($string, 0, 1) != '<') {
            // We matched a lone ">" character.
            return '&gt;';
        } elseif (strlen($string) == 1) {
            // We matched a lone "<" character.
            return '&lt;';
        }

        if (!preg_match('%^<\s*(/\s*)?([a-zA-Z0-9\-]+)([^>]*)>?|(<!--.*?-->)$%', $string, $matches)) {
            // Seriously malformed.
            return '';
        }

        $slash = trim($matches[1]);
        $elem = &$matches[2];
        $attrlist = &$matches[3];
        $comment = &$matches[4];

        if ($comment) {
            $elem = '!--';
        }

        if (!in_array(strtolower($elem), $this->tags, true)) {
            return ''; // Disallowed HTML element.
        }

        if ($comment) {
            return $comment;
        }

        if ($slash != '') {
            return "</$elem>";
        }

        // Is there a closing XHTML slash at the end of the attributes?
        $attrlist = preg_replace('%(\s?)/\s*$%', '\1', $attrlist, -1, $count);
        $xhtml_slash = $count ? ' /' : '';

        // Clean up attributes.
        $attr2 = implode(' ', $this->explodeAttributes($attrlist));
        $attr2 = preg_replace('/[<>]/', '', $attr2);
        $attr2 = strlen($attr2) ? ' ' . $attr2 : '';

        return "<$elem$attr2$xhtml_slash>";
    }

    /**
     * Returns an array of filtered attributes
     * @param string $attr
     * @return array
     */
    protected function explodeAttributes($attr)
    {
        $attrarr = array();
        $mode = 0;
        $attrname = '';
        $skip = false;

        while (strlen($attr) != 0) {

            $working = 0;

            switch ($mode) {
                case 0:
                    // Attribute name, href for instance.
                    if (preg_match('/^([-a-zA-Z]+)/', $attr, $match)) {
                        $attrname = strtolower($match[1]);
                        $skip = ($attrname == 'style' || substr($attrname, 0, 2) == 'on');
                        $working = $mode = 1;
                        $attr = preg_replace('/^[-a-zA-Z]+/', '', $attr);
                    }
                    break;
                case 1:
                    // Equals sign or valueless ("selected").
                    if (preg_match('/^\s*=\s*/', $attr)) {
                        $working = 1;
                        $mode = 2;
                        $attr = preg_replace('/^\s*=\s*/', '', $attr);
                        break;
                    }

                    if (preg_match('/^\s+/', $attr)) {
                        $working = 1;
                        $mode = 0;

                        if (!$skip) {
                            $attrarr[] = $attrname;
                        }

                        $attr = preg_replace('/^\s+/', '', $attr);
                    }
                    break;
                case 2:
                    // Attribute value, a URL after href= for instance.
                    if (preg_match('/^"([^"]*)"(\s+|$)/', $attr, $match)) {
                        $thisval = $this->badProtocol($match[1]);

                        if (!$skip) {
                            $attrarr[] = "$attrname=\"$thisval\"";
                        }

                        $working = 1;
                        $mode = 0;
                        $attr = preg_replace('/^"[^"]*"(\s+|$)/', '', $attr);
                        break;
                    }

                    if (preg_match("/^'([^']*)'(\s+|$)/", $attr, $match)) {

                        $thisval = $this->badProtocol($match[1]);

                        if (!$skip) {
                            $attrarr[] = "$attrname='$thisval'";
                        }

                        $working = 1;
                        $mode = 0;
                        $attr = preg_replace("/^'[^']*'(\s+|$)/", '', $attr);
                        break;
                    }

                    if (preg_match("%^([^\s\"']+)(\s+|$)%", $attr, $match)) {
                        $thisval = $this->badProtocol($match[1]);

                        if (!$skip) {
                            $attrarr[] = "$attrname=\"$thisval\"";
                        }

                        $working = 1;
                        $mode = 0;
                        $attr = preg_replace("%^[^\s\"']+(\s+|$)%", '', $attr);
                    }
                    break;
            }

            if ($working == 0) {
                // Not well formed; remove and try again.
                $attr = preg_replace('/
                ^
                (
                "[^"]*("|$)     # - a string that starts with a double quote, up until the next double quote or the end of the string
                |               # or
                \'[^\']*(\'|$)| # - a string that starts with a quote, up until the next quote or the end of the string
                |               # or
                \S              # - a non-whitespace character
                )*              # any number of the above three
                \s*             # any number of whitespaces
                /x', '', $attr);

                $mode = 0;
            }
        }

        // The attribute list ends with a valueless attribute like "selected".
        if ($mode == 1 && !$skip) {
            $attrarr[] = $attrname;
        }

        return $attrarr;
    }

    /**
     * @param string $string
     * @return string
     */
    protected function badProtocol($string)
    {
        $decoded = html_entity_decode($string, ENT_QUOTES, 'UTF-8');
        return htmlspecialchars($this->stripDangerousProtocols($decoded), ENT_QUOTES, 'UTF-8');
    }

    /**
     * @param string $uri
     * @return string
     */
    protected function stripDangerousProtocols($uri)
    {
        // Iteratively remove any invalid protocol found.
        do {
            $before = $uri;
            $colonpos = strpos($uri, ':');

            if ($colonpos > 0) {
                // We found a colon, possibly a protocol. Verify.
                $protocol = substr($uri, 0, $colonpos);

                // If a colon is preceded by a slash, question mark or hash, it cannot
                // possibly be part of the URL scheme. This must be a relative URL, which
                // inherits the (safe) protocol of the base document.
                if (preg_match('![/?#]!', $protocol)) {
                    break;
                }

                // Check if this is a disallowed protocol. Per RFC2616, section 3.2.3
                // (URI Comparison) scheme comparison must be case-insensitive.
                if (!in_array(strtolower($protocol), $this->protocols, true)) {
                    $uri = substr($uri, $colonpos + 1);
                }
            }
        } while ($before != $uri);

        return $uri;
    }

}


1			<?php
2
3			/**
4			* @package XSS filter
5			* @author Iurii Makukh <[email protected]>
6			* @copyright Copyright (c) 2018, Iurii Makukh
7			* @license https://www.gnu.org/licenses/gpl.html GNU/GPLv3
8			*/
9
10			namespace gplcart\modules\xss\helpers;
11
12			/**
13			* XSS filter. Based on Drupal's XSS filter
14			*/
15			class Filter
16			{
17
18			/**
19			* An array of allowed protocols
20			* @var array
21			*/
22			protected $protocols;
23
24			/**
25			* An array of allowed tags
26			* @var array
27			*/
28			protected $tags;
29
30			/**
31			* Constructor
32			*/
33			public function __construct()
34			{
35			$this->tags = array();
36			$this->protocols = array();
37			}
38
39			/**
40			* Set allowed protocols
41			* @param array $protocols
42			* @return $this
43			*/
44			public function setProtocols(array $protocols)
45			{
46			$this->protocols = $protocols;
47			return $this;
48			}
49
50			/**
51			* Set allowed tags
52			* @param array $tags
53			* @return $this
54			*/
55			public function setTags(array $tags)
56			{
57			$this->tags = $tags;
58			return $this;
59			}
60
61			/**
62			* Filter a string
63			* @param string $string
64			* @return string
65			*/
66			public function filter($string)
67			{
68			// Only operate on valid UTF-8 strings. This is necessary to prevent cross
69			// site scripting issues on Internet Explorer 6.
70			if (!$this->isUtf8($string)) {
71			return '';
72			}
73
74			// Remove NULL characters (ignored by some browsers).
75			$string = str_replace(chr(0), '', $string);
76
77			// Remove Netscape 4 JS entities.
78			$string = preg_replace('%&\s\{[^}](\}\s*;?\|$)%', '', $string);
79
80			// Defuse all HTML entities.
81			$string = str_replace('&', '&', $string);
82
83			// Change back only well-formed entities in our whitelist:
84			// Decimal numeric entities.
85			$string = preg_replace('/&#([0-9]+;)/', '&#\1', $string);
86
87			// Hexadecimal numeric entities.
88			$string = preg_replace('/&#[Xx]0*((?:[0-9A-Fa-f]{2})+;)/', '&#x\1', $string);
89
90			// Named entities.
91			$string = preg_replace('/&([A-Za-z][A-Za-z0-9]*;)/', '&\1', $string);
92
93			return (string) preg_replace_callback('%
94			(
95			<(?=[^a-zA-Z!/]) # a lone <
96			\| # or
97			<!--.*?--> # a comment
98			\| # or
99			<[^>]*(>\|$) # a string that starts with a <, up until the > or the end of the string
100			\| # or
101			> # just a >
102			)%x', array($this, 'build'), $string);
103			}
104
105			/**
106			* Whether a string is valid UTF-8
107			* @param string $string
108			* @return boolean
109			*/
110			protected function isUtf8($string)
111			{
112			if (strlen($string) == 0) {
113			return true;
114			}
115
116			return preg_match('/^./us', $string) === 1;
117			}
118
119			/**
120			* Build a filtered tag
121			* @param array $m
122			* @return string
123			*/
124			protected function build($m)
125			{
126			$string = $m[1];
127
128			if (substr($string, 0, 1) != '<') {
129			// We matched a lone ">" character.
130			return '>';
131			} elseif (strlen($string) == 1) {
132			// We matched a lone "<" character.
133			return '<';
134			}
135
136			if (!preg_match('%^<\s(/\s)?([a-zA-Z0-9\-]+)([^>])>?\|(<!--.?-->)$%', $string, $matches)) {
137			// Seriously malformed.
138			return '';
139			}
140
141			$slash = trim($matches[1]);
142			$elem = &$matches[2];
143			$attrlist = &$matches[3];
144			$comment = &$matches[4];
145
146			if ($comment) {
147			$elem = '!--';
148			}
149
150			if (!in_array(strtolower($elem), $this->tags, true)) {
151			return ''; // Disallowed HTML element.
152			}
153
154			if ($comment) {
155			return $comment;
156			}
157
158			if ($slash != '') {
159			return "</$elem>";
160			}
161
162			// Is there a closing XHTML slash at the end of the attributes?
163			$attrlist = preg_replace('%(\s?)/\s*$%', '\1', $attrlist, -1, $count);
164			$xhtml_slash = $count ? ' /' : '';
165
166			// Clean up attributes.
167			$attr2 = implode(' ', $this->explodeAttributes($attrlist));
168			$attr2 = preg_replace('/[<>]/', '', $attr2);
169			$attr2 = strlen($attr2) ? ' ' . $attr2 : '';
170
171			return "<$elem$attr2$xhtml_slash>";
172			}
173
174			/**
175			* Returns an array of filtered attributes
176			* @param string $attr
177			* @return array
178			*/
179			protected function explodeAttributes($attr)
180			{
181			$attrarr = array();
182			$mode = 0;
183			$attrname = '';
184			$skip = false;
185
186			while (strlen($attr) != 0) {
187
188			$working = 0;
189
190			switch ($mode) {
191			case 0:
192			// Attribute name, href for instance.
193			if (preg_match('/^([-a-zA-Z]+)/', $attr, $match)) {
194			$attrname = strtolower($match[1]);
195			$skip = ($attrname == 'style' \|\| substr($attrname, 0, 2) == 'on');
196			$working = $mode = 1;
197			$attr = preg_replace('/^[-a-zA-Z]+/', '', $attr);
198			}
199			break;
200			case 1:
201			// Equals sign or valueless ("selected").
202			if (preg_match('/^\s=\s/', $attr)) {
203			$working = 1;
204			$mode = 2;
205			$attr = preg_replace('/^\s=\s/', '', $attr);
206			break;
207			}
208
209			if (preg_match('/^\s+/', $attr)) {
210			$working = 1;
211			$mode = 0;
212
213			if (!$skip) {
214			$attrarr[] = $attrname;
215			}
216
217			$attr = preg_replace('/^\s+/', '', $attr);
218			}
219			break;
220			case 2:
221			// Attribute value, a URL after href= for instance.
222			if (preg_match('/^"([^"]*)"(\s+\|$)/', $attr, $match)) {
223			$thisval = $this->badProtocol($match[1]);
224
225			if (!$skip) {
226			$attrarr[] = "$attrname=\"$thisval\"";
227			}
228
229			$working = 1;
230			$mode = 0;
231			$attr = preg_replace('/^"[^"]*"(\s+\|$)/', '', $attr);
232			break;
233			}
234
235			if (preg_match("/^'([^']*)'(\s+\|$)/", $attr, $match)) {
236
237			$thisval = $this->badProtocol($match[1]);
238
239			if (!$skip) {
240			$attrarr[] = "$attrname='$thisval'";
241			}
242
243			$working = 1;
244			$mode = 0;
245			$attr = preg_replace("/^'[^']*'(\s+\|$)/", '', $attr);
246			break;
247			}
248
249			if (preg_match("%^([^\s\"']+)(\s+\|$)%", $attr, $match)) {
250			$thisval = $this->badProtocol($match[1]);
251
252			if (!$skip) {
253			$attrarr[] = "$attrname=\"$thisval\"";
254			}
255
256			$working = 1;
257			$mode = 0;
258			$attr = preg_replace("%^[^\s\"']+(\s+\|$)%", '', $attr);
259			}
260			break;
261			}
262
263			if ($working == 0) {
264			// Not well formed; remove and try again.
265			$attr = preg_replace('/
266			^
267			(
268			"[^"]*("\|$) # - a string that starts with a double quote, up until the next double quote or the end of the string
269			\| # or
270			\'[^\']*(\'\|$)\| # - a string that starts with a quote, up until the next quote or the end of the string
271			\| # or
272			\S # - a non-whitespace character
273			)* # any number of the above three
274			\s* # any number of whitespaces
275			/x', '', $attr);
276
277			$mode = 0;
278			}
279			}
280
281			// The attribute list ends with a valueless attribute like "selected".
282			if ($mode == 1 && !$skip) {
283			$attrarr[] = $attrname;
284			}
285
286			return $attrarr;
287			}
288
289			/**
290			* @param string $string
291			* @return string
292			*/
293			protected function badProtocol($string)
294			{
295			$decoded = html_entity_decode($string, ENT_QUOTES, 'UTF-8');
296			return htmlspecialchars($this->stripDangerousProtocols($decoded), ENT_QUOTES, 'UTF-8');
297			}
298
299			/**
300			* @param string $uri
301			* @return string
302			*/
303			protected function stripDangerousProtocols($uri)
304			{
305			// Iteratively remove any invalid protocol found.
306			do {
307			$before = $uri;
308			$colonpos = strpos($uri, ':');
309
310			if ($colonpos > 0) {
311			// We found a colon, possibly a protocol. Verify.
312			$protocol = substr($uri, 0, $colonpos);
313
314			// If a colon is preceded by a slash, question mark or hash, it cannot
315			// possibly be part of the URL scheme. This must be a relative URL, which
316			// inherits the (safe) protocol of the base document.
317			if (preg_match('![/?#]!', $protocol)) {
318			break;
319			}
320
321			// Check if this is a disallowed protocol. Per RFC2616, section 3.2.3
322			// (URI Comparison) scheme comparison must be case-insensitive.
323			if (!in_array(strtolower($protocol), $this->protocols, true)) {
324			$uri = substr($uri, $colonpos + 1);
325			}
326			}
327			} while ($before != $uri);
328
329			return $uri;
330			}
331
332			}
333

gplcart / xss

Filter::isUtf8() A last analyzed 2018-03-10 14:53 UTC

Complexity

Size

Duplication

Importance

Duplication Side-by-Side

Filter issues like

Filter::isUtf8() A
last analyzed 2018-03-10 14:53 UTC