WordPressを読む 51-2 /blog/wp-includes/kses.php 2
2015/01/30
目次
/blog/wp-includes/kses.php 2
関数 wp_kses()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 | /** * Filters content and keeps only allowable HTML elements. * * This function makes sure that only the allowed HTML element names, attribute * names and attribute values plus only sane HTML entities will occur in * $string. You have to remove any slashes from PHP's magic quotes before you * call this function. * * The default allowed protocols are 'http', 'https', 'ftp', 'mailto', 'news', * 'irc', 'gopher', 'nntp', 'feed', 'telnet, 'mms', 'rtsp' and 'svn'. This * covers all common link protocols, except for 'javascript' which should not * be allowed for untrusted users. * * @since 1.0.0 * * @param string $string Content to filter through kses * @param array $allowed_html List of allowed HTML elements * @param array $allowed_protocols Optional. Allowed protocol in links. * @return string Filtered content with only allowed HTML elements */ function wp_kses( $string, $allowed_html, $allowed_protocols = array() ) { if ( empty( $allowed_protocols ) ) $allowed_protocols = wp_allowed_protocols(); $string = wp_kses_no_null($string); $string = wp_kses_js_entities($string); $string = wp_kses_normalize_entities($string); $string = wp_kses_hook($string, $allowed_html, $allowed_protocols); // WP changed the order of these funcs and added args to wp_kses_hook return wp_kses_split($string, $allowed_html, $allowed_protocols); } |
関数 wp_kses_allowed_html()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 | /** * Return a list of allowed tags and attributes for a given context. * * @since 3.5.0 * * @param string $context The context for which to retrieve tags. Allowed values are * post | strip | data | entities or the name of a field filter such as pre_user_description. * @return array List of allowed tags and their allowed attributes. */ function wp_kses_allowed_html( $context = '' ) { global $allowedposttags, $allowedtags, $allowedentitynames; if ( is_array( $context ) ) { /** * Filter HTML elements allowed for a given context. * * @since 3.5.0 * * @param string $tags Allowed tags, attributes, and/or entities. * @param string $context Context to judge allowed tags by. Allowed values are 'post', * 'data', 'strip', 'entities', 'explicit', or the name of a filter. */ return apply_filters( 'wp_kses_allowed_html', $context, 'explicit' ); } switch ( $context ) { case 'post': /** This filter is documented in wp-includes/kses.php */ return apply_filters( 'wp_kses_allowed_html', $allowedposttags, $context ); break; case 'user_description': case 'pre_user_description': $tags = $allowedtags; $tags['a']['rel'] = true; /** This filter is documented in wp-includes/kses.php */ return apply_filters( 'wp_kses_allowed_html', $tags, $context ); break; case 'strip': /** This filter is documented in wp-includes/kses.php */ return apply_filters( 'wp_kses_allowed_html', array(), $context ); break; case 'entities': /** This filter is documented in wp-includes/kses.php */ return apply_filters( 'wp_kses_allowed_html', $allowedentitynames, $context); break; case 'data': default: /** This filter is documented in wp-includes/kses.php */ return apply_filters( 'wp_kses_allowed_html', $allowedtags, $context ); } } |
関数 wp_kses_hook()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 | /** * You add any kses hooks here. * * There is currently only one kses WordPress hook and it is called here. All * parameters are passed to the hooks and expected to receive a string. * * @since 1.0.0 * * @param string $string Content to filter through kses * @param array $allowed_html List of allowed HTML elements * @param array $allowed_protocols Allowed protocol in links * @return string Filtered content through 'pre_kses' hook */ function wp_kses_hook( $string, $allowed_html, $allowed_protocols ) { /** * Filter content to be run through kses. * * @since 2.3.0 * * @param string $string Content to run through kses. * @param array $allowed_html Allowed HTML elements. * @param array $allowed_protocols Allowed protocol in links. */ $string = apply_filters( 'pre_kses', $string, $allowed_html, $allowed_protocols ); return $string; } |
関数 wp_kses_version()
1 2 3 4 5 6 7 8 9 10 | /** * This function returns kses' version number. * * @since 1.0.0 * * @return string KSES Version Number */ function wp_kses_version() { return '0.2.2'; } |
関数 wp_kses_split()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 | /** * Searches for HTML tags, no matter how malformed. * * It also matches stray ">" characters. * * @since 1.0.0 * * @param string $string Content to filter * @param array $allowed_html Allowed HTML elements * @param array $allowed_protocols Allowed protocols to keep * @return string Content with fixed HTML tags */ function wp_kses_split( $string, $allowed_html, $allowed_protocols ) { global $pass_allowed_html, $pass_allowed_protocols; $pass_allowed_html = $allowed_html; $pass_allowed_protocols = $allowed_protocols; return preg_replace_callback( '%(<!--.*?(-->|$))|(<[^>]*(>|$)|>)%', '_wp_kses_split_callback', $string ); } |
関数 _wp_kses_split_callback()
1 2 3 4 5 6 7 8 9 10 | /** * Callback for wp_kses_split. * * @since 3.1.0 * @access private */ function _wp_kses_split_callback( $match ) { global $pass_allowed_html, $pass_allowed_protocols; return wp_kses_split2( $match[0], $pass_allowed_html, $pass_allowed_protocols ); } |
関数 wp_kses_split2()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 | /** * Callback for wp_kses_split for fixing malformed HTML tags. * * This function does a lot of work. It rejects some very malformed things like * <:::>. It returns an empty string, if the element isn't allowed (look ma, no * strip_tags()!). Otherwise it splits the tag into an element and an attribute * list. * * After the tag is split into an element and an attribute list, it is run * through another filter which will remove illegal attributes and once that is * completed, will be returned. * * @access private * @since 1.0.0 * @uses wp_kses_attr() * * @param string $string Content to filter * @param array $allowed_html Allowed HTML elements * @param array $allowed_protocols Allowed protocols to keep * @return string Fixed HTML element */ function wp_kses_split2($string, $allowed_html, $allowed_protocols) { $string = wp_kses_stripslashes($string); if (substr($string, 0, 1) != '<') return '>'; # It matched a ">" character if ( '<!--' == substr( $string, 0, 4 ) ) { $string = str_replace( array('<!--', '-->'), '', $string ); while ( $string != ($newstring = wp_kses($string, $allowed_html, $allowed_protocols)) ) $string = $newstring; if ( $string == '' ) return ''; // prevent multiple dashes in comments $string = preg_replace('/--+/', '-', $string); // prevent three dashes closing a comment $string = preg_replace('/-$/', '', $string); return "<!--{$string}-->"; } # Allow HTML comments if (!preg_match('%^<\s*(/\s*)?([a-zA-Z0-9]+)([^>]*)>?$%', $string, $matches)) return ''; # It's seriously malformed $slash = trim($matches[1]); $elem = $matches[2]; $attrlist = $matches[3]; if ( ! is_array( $allowed_html ) ) $allowed_html = wp_kses_allowed_html( $allowed_html ); if ( ! isset($allowed_html[strtolower($elem)]) ) return ''; # They are using a not allowed HTML element if ($slash != '') return "</$elem>"; # No attributes are allowed for closing elements return wp_kses_attr( $elem, $attrlist, $allowed_html, $allowed_protocols ); } |
関数 wp_kses_attr()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 | /** * Removes all attributes, if none are allowed for this element. * * If some are allowed it calls wp_kses_hair() to split them further, and then * it builds up new HTML code from the data that kses_hair() returns. It also * removes "<" and ">" characters, if there are any left. One more thing it does * is to check if the tag has a closing XHTML slash, and if it does, it puts one * in the returned code as well. * * @since 1.0.0 * * @param string $element HTML element/tag * @param string $attr HTML attributes from HTML element to closing HTML element tag * @param array $allowed_html Allowed HTML elements * @param array $allowed_protocols Allowed protocols to keep * @return string Sanitized HTML element */ function wp_kses_attr($element, $attr, $allowed_html, $allowed_protocols) { # Is there a closing XHTML slash at the end of the attributes? if ( ! is_array( $allowed_html ) ) $allowed_html = wp_kses_allowed_html( $allowed_html ); $xhtml_slash = ''; if (preg_match('%\s*/\s*$%', $attr)) $xhtml_slash = ' /'; # Are any attributes allowed at all for this element? if ( ! isset($allowed_html[strtolower($element)]) || count($allowed_html[strtolower($element)]) == 0 ) return "<$element$xhtml_slash>"; # Split it $attrarr = wp_kses_hair($attr, $allowed_protocols); # Go through $attrarr, and save the allowed attributes for this element # in $attr2 $attr2 = ''; $allowed_attr = $allowed_html[strtolower($element)]; foreach ($attrarr as $arreach) { if ( ! isset( $allowed_attr[strtolower($arreach['name'])] ) ) continue; # the attribute is not allowed $current = $allowed_attr[strtolower($arreach['name'])]; if ( $current == '' ) continue; # the attribute is not allowed if ( strtolower( $arreach['name'] ) == 'style' ) { $orig_value = $arreach['value']; $value = safecss_filter_attr( $orig_value ); if ( empty( $value ) ) continue; $arreach['value'] = $value; $arreach['whole'] = str_replace( $orig_value, $value, $arreach['whole'] ); } if ( ! is_array($current) ) { $attr2 .= ' '.$arreach['whole']; # there are no checks } else { # there are some checks $ok = true; foreach ($current as $currkey => $currval) { if ( ! wp_kses_check_attr_val($arreach['value'], $arreach['vless'], $currkey, $currval) ) { $ok = false; break; } } if ( $ok ) $attr2 .= ' '.$arreach['whole']; # it passed them } # if !is_array($current) } # foreach # Remove any "<" or ">" characters $attr2 = preg_replace('/[<>]/', '', $attr2); return "<$element$attr2$xhtml_slash>"; } |
関数 wp_kses_hair()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 | /** * Builds an attribute list from string containing attributes. * * This function does a lot of work. It parses an attribute list into an array * with attribute data, and tries to do the right thing even if it gets weird * input. It will add quotes around attribute values that don't have any quotes * or apostrophes around them, to make it easier to produce HTML code that will * conform to W3C's HTML specification. It will also remove bad URL protocols * from attribute values. It also reduces duplicate attributes by using the * attribute defined first (foo='bar' foo='baz' will result in foo='bar'). * * @since 1.0.0 * * @param string $attr Attribute list from HTML element to closing HTML element tag * @param array $allowed_protocols Allowed protocols to keep * @return array List of attributes after parsing */ function wp_kses_hair($attr, $allowed_protocols) { $attrarr = array(); $mode = 0; $attrname = ''; $uris = array('xmlns', 'profile', 'href', 'src', 'cite', 'classid', 'codebase', 'data', 'usemap', 'longdesc', 'action'); # Loop through the whole attribute list while (strlen($attr) != 0) { $working = 0; # Was the last operation successful? switch ($mode) { case 0 : # attribute name, href for instance if ( preg_match('/^([-a-zA-Z:]+)/', $attr, $match ) ) { $attrname = $match[1]; $working = $mode = 1; $attr = preg_replace( '/^[-a-zA-Z:]+/', '', $attr ); } break; case 1 : # equals sign or valueless ("selected") if (preg_match('/^\s*=\s*/', $attr)) # equals sign { $working = 1; $mode = 2; $attr = preg_replace('/^\s*=\s*/', '', $attr); break; } if (preg_match('/^\s+/', $attr)) # valueless { $working = 1; $mode = 0; if(false === array_key_exists($attrname, $attrarr)) { $attrarr[$attrname] = array ('name' => $attrname, 'value' => '', 'whole' => $attrname, 'vless' => 'y'); } $attr = preg_replace('/^\s+/', '', $attr); } break; case 2 : # attribute value, a URL after href= for instance if (preg_match('%^"([^"]*)"(\s+|/?$)%', $attr, $match)) # "value" { $thisval = $match[1]; if ( in_array(strtolower($attrname), $uris) ) $thisval = wp_kses_bad_protocol($thisval, $allowed_protocols); if(false === array_key_exists($attrname, $attrarr)) { $attrarr[$attrname] = array ('name' => $attrname, 'value' => $thisval, 'whole' => "$attrname=\"$thisval\"", 'vless' => 'n'); } $working = 1; $mode = 0; $attr = preg_replace('/^"[^"]*"(\s+|$)/', '', $attr); break; } if (preg_match("%^'([^']*)'(\s+|/?$)%", $attr, $match)) # 'value' { $thisval = $match[1]; if ( in_array(strtolower($attrname), $uris) ) $thisval = wp_kses_bad_protocol($thisval, $allowed_protocols); if(false === array_key_exists($attrname, $attrarr)) { $attrarr[$attrname] = array ('name' => $attrname, 'value' => $thisval, 'whole' => "$attrname='$thisval'", 'vless' => 'n'); } $working = 1; $mode = 0; $attr = preg_replace("/^'[^']*'(\s+|$)/", '', $attr); break; } if (preg_match("%^([^\s\"']+)(\s+|/?$)%", $attr, $match)) # value { $thisval = $match[1]; if ( in_array(strtolower($attrname), $uris) ) $thisval = wp_kses_bad_protocol($thisval, $allowed_protocols); if(false === array_key_exists($attrname, $attrarr)) { $attrarr[$attrname] = array ('name' => $attrname, 'value' => $thisval, 'whole' => "$attrname=\"$thisval\"", 'vless' => 'n'); } # We add quotes to conform to W3C's HTML spec. $working = 1; $mode = 0; $attr = preg_replace("%^[^\s\"']+(\s+|$)%", '', $attr); } break; } # switch if ($working == 0) # not well formed, remove and try again { $attr = wp_kses_html_error($attr); $mode = 0; } } # while if ($mode == 1 && false === array_key_exists($attrname, $attrarr)) # special case, for when the attribute list ends with a valueless # attribute like "selected" $attrarr[$attrname] = array ('name' => $attrname, 'value' => '', 'whole' => $attrname, 'vless' => 'y'); return $attrarr; } |
関数 wp_kses_check_attr_val()
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 | /** * Performs different checks for attribute values. * * The currently implemented checks are "maxlen", "minlen", "maxval", "minval" * and "valueless". * * @since 1.0.0 * * @param string $value Attribute value * @param string $vless Whether the value is valueless. Use 'y' or 'n' * @param string $checkname What $checkvalue is checking for. * @param mixed $checkvalue What constraint the value should pass * @return bool Whether check passes */ function wp_kses_check_attr_val($value, $vless, $checkname, $checkvalue) { $ok = true; switch (strtolower($checkname)) { case 'maxlen' : # The maxlen check makes sure that the attribute value has a length not # greater than the given value. This can be used to avoid Buffer Overflows # in WWW clients and various Internet servers. if (strlen($value) > $checkvalue) $ok = false; break; case 'minlen' : # The minlen check makes sure that the attribute value has a length not # smaller than the given value. if (strlen($value) < $checkvalue) $ok = false; break; case 'maxval' : # The maxval check does two things: it checks that the attribute value is # an integer from 0 and up, without an excessive amount of zeroes or # whitespace (to avoid Buffer Overflows). It also checks that the attribute # value is not greater than the given value. # This check can be used to avoid Denial of Service attacks. if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value)) $ok = false; if ($value > $checkvalue) $ok = false; break; case 'minval' : # The minval check makes sure that the attribute value is a positive integer, # and that it is not smaller than the given value. if (!preg_match('/^\s{0,6}[0-9]{1,6}\s{0,6}$/', $value)) $ok = false; if ($value < $checkvalue) $ok = false; break; case 'valueless' : # The valueless check makes sure if the attribute has a value # (like <a href="blah">) or not (<option selected>). If the given value # is a "y" or a "Y", the attribute must not have a value. # If the given value is an "n" or an "N", the attribute must have one. if (strtolower($checkvalue) != $vless) $ok = false; break; } # switch return $ok; } |