diff options
author | Nicolas LÅ“uillet <nicolas@loeuillet.org> | 2014-02-21 15:57:10 +0100 |
---|---|---|
committer | Nicolas LÅ“uillet <nicolas@loeuillet.org> | 2014-02-21 15:57:10 +0100 |
commit | 99679d06884120c57f43b44e55e03595f1f87bed (patch) | |
tree | a3f2a1aa1afdaeca1386d0c6e8a75344fd2241fb /inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI | |
parent | 655214ab30ee84884dc408488b85586f36263fcb (diff) | |
parent | d3b47e94705e17b3ba3529cbb1dc6efe69c5d2b7 (diff) | |
download | wallabag-99679d06884120c57f43b44e55e03595f1f87bed.tar.gz wallabag-99679d06884120c57f43b44e55e03595f1f87bed.tar.zst wallabag-99679d06884120c57f43b44e55e03595f1f87bed.zip |
Merge pull request #481 from wallabag/dev1.5.2
1.5.2
Diffstat (limited to 'inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI')
5 files changed, 311 insertions, 0 deletions
diff --git a/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Email.php b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Email.php new file mode 100644 index 00000000..846d3881 --- /dev/null +++ b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Email.php | |||
@@ -0,0 +1,20 @@ | |||
1 | <?php | ||
2 | |||
3 | abstract class HTMLPurifier_AttrDef_URI_Email extends HTMLPurifier_AttrDef | ||
4 | { | ||
5 | |||
6 | /** | ||
7 | * Unpacks a mailbox into its display-name and address | ||
8 | * @param string $string | ||
9 | * @return mixed | ||
10 | */ | ||
11 | public function unpack($string) | ||
12 | { | ||
13 | // needs to be implemented | ||
14 | } | ||
15 | |||
16 | } | ||
17 | |||
18 | // sub-implementations | ||
19 | |||
20 | // vim: et sw=4 sts=4 | ||
diff --git a/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php new file mode 100644 index 00000000..3b041ce8 --- /dev/null +++ b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Email/SimpleCheck.php | |||
@@ -0,0 +1,29 @@ | |||
1 | <?php | ||
2 | |||
3 | /** | ||
4 | * Primitive email validation class based on the regexp found at | ||
5 | * http://www.regular-expressions.info/email.html | ||
6 | */ | ||
7 | class HTMLPurifier_AttrDef_URI_Email_SimpleCheck extends HTMLPurifier_AttrDef_URI_Email | ||
8 | { | ||
9 | |||
10 | /** | ||
11 | * @param string $string | ||
12 | * @param HTMLPurifier_Config $config | ||
13 | * @param HTMLPurifier_Context $context | ||
14 | * @return bool|string | ||
15 | */ | ||
16 | public function validate($string, $config, $context) | ||
17 | { | ||
18 | // no support for named mailboxes i.e. "Bob <bob@example.com>" | ||
19 | // that needs more percent encoding to be done | ||
20 | if ($string == '') { | ||
21 | return false; | ||
22 | } | ||
23 | $string = trim($string); | ||
24 | $result = preg_match('/^[A-Z0-9._%-]+@[A-Z0-9.-]+\.[A-Z]{2,4}$/i', $string); | ||
25 | return $result ? $string : false; | ||
26 | } | ||
27 | } | ||
28 | |||
29 | // vim: et sw=4 sts=4 | ||
diff --git a/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Host.php b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Host.php new file mode 100644 index 00000000..01457785 --- /dev/null +++ b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/Host.php | |||
@@ -0,0 +1,128 @@ | |||
1 | <?php | ||
2 | |||
3 | /** | ||
4 | * Validates a host according to the IPv4, IPv6 and DNS (future) specifications. | ||
5 | */ | ||
6 | class HTMLPurifier_AttrDef_URI_Host extends HTMLPurifier_AttrDef | ||
7 | { | ||
8 | |||
9 | /** | ||
10 | * IPv4 sub-validator. | ||
11 | * @type HTMLPurifier_AttrDef_URI_IPv4 | ||
12 | */ | ||
13 | protected $ipv4; | ||
14 | |||
15 | /** | ||
16 | * IPv6 sub-validator. | ||
17 | * @type HTMLPurifier_AttrDef_URI_IPv6 | ||
18 | */ | ||
19 | protected $ipv6; | ||
20 | |||
21 | public function __construct() | ||
22 | { | ||
23 | $this->ipv4 = new HTMLPurifier_AttrDef_URI_IPv4(); | ||
24 | $this->ipv6 = new HTMLPurifier_AttrDef_URI_IPv6(); | ||
25 | } | ||
26 | |||
27 | /** | ||
28 | * @param string $string | ||
29 | * @param HTMLPurifier_Config $config | ||
30 | * @param HTMLPurifier_Context $context | ||
31 | * @return bool|string | ||
32 | */ | ||
33 | public function validate($string, $config, $context) | ||
34 | { | ||
35 | $length = strlen($string); | ||
36 | // empty hostname is OK; it's usually semantically equivalent: | ||
37 | // the default host as defined by a URI scheme is used: | ||
38 | // | ||
39 | // If the URI scheme defines a default for host, then that | ||
40 | // default applies when the host subcomponent is undefined | ||
41 | // or when the registered name is empty (zero length). | ||
42 | if ($string === '') { | ||
43 | return ''; | ||
44 | } | ||
45 | if ($length > 1 && $string[0] === '[' && $string[$length - 1] === ']') { | ||
46 | //IPv6 | ||
47 | $ip = substr($string, 1, $length - 2); | ||
48 | $valid = $this->ipv6->validate($ip, $config, $context); | ||
49 | if ($valid === false) { | ||
50 | return false; | ||
51 | } | ||
52 | return '[' . $valid . ']'; | ||
53 | } | ||
54 | |||
55 | // need to do checks on unusual encodings too | ||
56 | $ipv4 = $this->ipv4->validate($string, $config, $context); | ||
57 | if ($ipv4 !== false) { | ||
58 | return $ipv4; | ||
59 | } | ||
60 | |||
61 | // A regular domain name. | ||
62 | |||
63 | // This doesn't match I18N domain names, but we don't have proper IRI support, | ||
64 | // so force users to insert Punycode. | ||
65 | |||
66 | // There is not a good sense in which underscores should be | ||
67 | // allowed, since it's technically not! (And if you go as | ||
68 | // far to allow everything as specified by the DNS spec... | ||
69 | // well, that's literally everything, modulo some space limits | ||
70 | // for the components and the overall name (which, by the way, | ||
71 | // we are NOT checking!). So we (arbitrarily) decide this: | ||
72 | // let's allow underscores wherever we would have allowed | ||
73 | // hyphens, if they are enabled. This is a pretty good match | ||
74 | // for browser behavior, for example, a large number of browsers | ||
75 | // cannot handle foo_.example.com, but foo_bar.example.com is | ||
76 | // fairly well supported. | ||
77 | $underscore = $config->get('Core.AllowHostnameUnderscore') ? '_' : ''; | ||
78 | |||
79 | // The productions describing this are: | ||
80 | $a = '[a-z]'; // alpha | ||
81 | $an = '[a-z0-9]'; // alphanum | ||
82 | $and = "[a-z0-9-$underscore]"; // alphanum | "-" | ||
83 | // domainlabel = alphanum | alphanum *( alphanum | "-" ) alphanum | ||
84 | $domainlabel = "$an($and*$an)?"; | ||
85 | // toplabel = alpha | alpha *( alphanum | "-" ) alphanum | ||
86 | $toplabel = "$a($and*$an)?"; | ||
87 | // hostname = *( domainlabel "." ) toplabel [ "." ] | ||
88 | if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) { | ||
89 | return $string; | ||
90 | } | ||
91 | |||
92 | // If we have Net_IDNA2 support, we can support IRIs by | ||
93 | // punycoding them. (This is the most portable thing to do, | ||
94 | // since otherwise we have to assume browsers support | ||
95 | |||
96 | if ($config->get('Core.EnableIDNA')) { | ||
97 | $idna = new Net_IDNA2(array('encoding' => 'utf8', 'overlong' => false, 'strict' => true)); | ||
98 | // we need to encode each period separately | ||
99 | $parts = explode('.', $string); | ||
100 | try { | ||
101 | $new_parts = array(); | ||
102 | foreach ($parts as $part) { | ||
103 | $encodable = false; | ||
104 | for ($i = 0, $c = strlen($part); $i < $c; $i++) { | ||
105 | if (ord($part[$i]) > 0x7a) { | ||
106 | $encodable = true; | ||
107 | break; | ||
108 | } | ||
109 | } | ||
110 | if (!$encodable) { | ||
111 | $new_parts[] = $part; | ||
112 | } else { | ||
113 | $new_parts[] = $idna->encode($part); | ||
114 | } | ||
115 | } | ||
116 | $string = implode('.', $new_parts); | ||
117 | if (preg_match("/^($domainlabel\.)*$toplabel\.?$/i", $string)) { | ||
118 | return $string; | ||
119 | } | ||
120 | } catch (Exception $e) { | ||
121 | // XXX error reporting | ||
122 | } | ||
123 | } | ||
124 | return false; | ||
125 | } | ||
126 | } | ||
127 | |||
128 | // vim: et sw=4 sts=4 | ||
diff --git a/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv4.php b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv4.php new file mode 100644 index 00000000..bbc8a77e --- /dev/null +++ b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv4.php | |||
@@ -0,0 +1,45 @@ | |||
1 | <?php | ||
2 | |||
3 | /** | ||
4 | * Validates an IPv4 address | ||
5 | * @author Feyd @ forums.devnetwork.net (public domain) | ||
6 | */ | ||
7 | class HTMLPurifier_AttrDef_URI_IPv4 extends HTMLPurifier_AttrDef | ||
8 | { | ||
9 | |||
10 | /** | ||
11 | * IPv4 regex, protected so that IPv6 can reuse it. | ||
12 | * @type string | ||
13 | */ | ||
14 | protected $ip4; | ||
15 | |||
16 | /** | ||
17 | * @param string $aIP | ||
18 | * @param HTMLPurifier_Config $config | ||
19 | * @param HTMLPurifier_Context $context | ||
20 | * @return bool|string | ||
21 | */ | ||
22 | public function validate($aIP, $config, $context) | ||
23 | { | ||
24 | if (!$this->ip4) { | ||
25 | $this->_loadRegex(); | ||
26 | } | ||
27 | |||
28 | if (preg_match('#^' . $this->ip4 . '$#s', $aIP)) { | ||
29 | return $aIP; | ||
30 | } | ||
31 | return false; | ||
32 | } | ||
33 | |||
34 | /** | ||
35 | * Lazy load function to prevent regex from being stuffed in | ||
36 | * cache. | ||
37 | */ | ||
38 | protected function _loadRegex() | ||
39 | { | ||
40 | $oct = '(?:25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9][0-9]|[0-9])'; // 0-255 | ||
41 | $this->ip4 = "(?:{$oct}\\.{$oct}\\.{$oct}\\.{$oct})"; | ||
42 | } | ||
43 | } | ||
44 | |||
45 | // vim: et sw=4 sts=4 | ||
diff --git a/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv6.php b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv6.php new file mode 100644 index 00000000..67f148bd --- /dev/null +++ b/inc/3rdparty/htmlpurifier/HTMLPurifier/AttrDef/URI/IPv6.php | |||
@@ -0,0 +1,89 @@ | |||
1 | <?php | ||
2 | |||
3 | /** | ||
4 | * Validates an IPv6 address. | ||
5 | * @author Feyd @ forums.devnetwork.net (public domain) | ||
6 | * @note This function requires brackets to have been removed from address | ||
7 | * in URI. | ||
8 | */ | ||
9 | class HTMLPurifier_AttrDef_URI_IPv6 extends HTMLPurifier_AttrDef_URI_IPv4 | ||
10 | { | ||
11 | |||
12 | /** | ||
13 | * @param string $aIP | ||
14 | * @param HTMLPurifier_Config $config | ||
15 | * @param HTMLPurifier_Context $context | ||
16 | * @return bool|string | ||
17 | */ | ||
18 | public function validate($aIP, $config, $context) | ||
19 | { | ||
20 | if (!$this->ip4) { | ||
21 | $this->_loadRegex(); | ||
22 | } | ||
23 | |||
24 | $original = $aIP; | ||
25 | |||
26 | $hex = '[0-9a-fA-F]'; | ||
27 | $blk = '(?:' . $hex . '{1,4})'; | ||
28 | $pre = '(?:/(?:12[0-8]|1[0-1][0-9]|[1-9][0-9]|[0-9]))'; // /0 - /128 | ||
29 | |||
30 | // prefix check | ||
31 | if (strpos($aIP, '/') !== false) { | ||
32 | if (preg_match('#' . $pre . '$#s', $aIP, $find)) { | ||
33 | $aIP = substr($aIP, 0, 0 - strlen($find[0])); | ||
34 | unset($find); | ||
35 | } else { | ||
36 | return false; | ||
37 | } | ||
38 | } | ||
39 | |||
40 | // IPv4-compatiblity check | ||
41 | if (preg_match('#(?<=:' . ')' . $this->ip4 . '$#s', $aIP, $find)) { | ||
42 | $aIP = substr($aIP, 0, 0 - strlen($find[0])); | ||
43 | $ip = explode('.', $find[0]); | ||
44 | $ip = array_map('dechex', $ip); | ||
45 | $aIP .= $ip[0] . $ip[1] . ':' . $ip[2] . $ip[3]; | ||
46 | unset($find, $ip); | ||
47 | } | ||
48 | |||
49 | // compression check | ||
50 | $aIP = explode('::', $aIP); | ||
51 | $c = count($aIP); | ||
52 | if ($c > 2) { | ||
53 | return false; | ||
54 | } elseif ($c == 2) { | ||
55 | list($first, $second) = $aIP; | ||
56 | $first = explode(':', $first); | ||
57 | $second = explode(':', $second); | ||
58 | |||
59 | if (count($first) + count($second) > 8) { | ||
60 | return false; | ||
61 | } | ||
62 | |||
63 | while (count($first) < 8) { | ||
64 | array_push($first, '0'); | ||
65 | } | ||
66 | |||
67 | array_splice($first, 8 - count($second), 8, $second); | ||
68 | $aIP = $first; | ||
69 | unset($first, $second); | ||
70 | } else { | ||
71 | $aIP = explode(':', $aIP[0]); | ||
72 | } | ||
73 | $c = count($aIP); | ||
74 | |||
75 | if ($c != 8) { | ||
76 | return false; | ||
77 | } | ||
78 | |||
79 | // All the pieces should be 16-bit hex strings. Are they? | ||
80 | foreach ($aIP as $piece) { | ||
81 | if (!preg_match('#^[0-9a-fA-F]{4}$#s', sprintf('%04s', $piece))) { | ||
82 | return false; | ||
83 | } | ||
84 | } | ||
85 | return $original; | ||
86 | } | ||
87 | } | ||
88 | |||
89 | // vim: et sw=4 sts=4 | ||