function rs_wpss_anchortxt_blacklist_chk($haystack = NULL, $get_list_arr = FALSE, $haystack_type = 'author', $url = NULL)
{
/***
* Author Keyword Blacklist Check
* Use for testing Comment Author, New User Registrations, and anywhere else you need to test an author name.
* This list assembled based on statistical analysis of common anchor text spam keyphrases.
* Script creates all the necessary alphanumeric and linguistic variations to effectively test.
* $haystack_type can be 'author' (default) or 'content'
***/
global $wpss_cl_active;
if (empty($wpss_cl_active)) {
$wpss_cl_active = rs_wpss_is_plugin_active('commentluv/commentluv.php');
/* Check if active for compatibility with CommentLuv */
}
global $spamshield_options;
if (empty($spamshield_options)) {
$spamshield_options = get_option('spamshield_options');
}
if (!empty($spamshield_options['allow_comment_author_keywords'])) {
$wpss_cak_active = 1;
} else {
$wpss_cak_active = 0;
}
/* Check if Comment Author Name Keywords are allowed - equivalent to CommentLuve being active */
$blacklisted_keyphrases = rs_wpss_rbkmd(rs_wpss_get_anchortxt_blacklist(), 'de', TRUE);
$blacklisted_keyphrases_lite = rs_wpss_rbkmd(rs_wpss_get_anchortxt_blacklist_lite(), 'de', TRUE);
if ($haystack_type === 'author' && (!empty($wpss_cl_active) || !empty($wpss_cak_active) || empty($url))) {
$blacklisted_keyphrases = $blacklisted_keyphrases_lite;
}
if (!empty($get_list_arr)) {
if ($haystack_type === 'content') {
return $blacklisted_keyphrases_lite;
} else {
return $blacklisted_keyphrases;
}
}
/* Goes after array */
$blacklist_status = FALSE;
if (empty($haystack)) {
return FALSE;
}
if ($haystack_type === 'author') {
/* Check 1: Testing for URLs and author domain in author name */
if (preg_match("~^https?~i", $haystack)) {
return TRUE;
}
if (!empty($url)) {
$author_email_domain = rs_wpss_get_domain($url, TRUE);
$author_email_domain_rgx = rs_wpss_get_regex_phrase($author_email_domain, '', 'N');
if (preg_match($author_email_domain_rgx, $haystack)) {
return TRUE;
}
}
/* Check 2: Testing for max # words in author name, more than 7 is fail */
$author_words = rs_wpss_count_words($haystack);
$word_max = 7;
/* Default */
if (!empty($wpss_cl_active) || !empty($wpss_cak_active)) {
$word_max = 10;
}
/* CL or CAK active */
if ($author_words > $word_max) {
return TRUE;
}
/* Check 3: Testing for Odd Characters in author name */
$odd_char_regex = "~[\\@\\*]+~";
/* Default */
if (!empty($wpss_cl_active) || !empty($wpss_cak_active)) {
$odd_char_regex = "~(\\@{2,}|\\*)+~";
}
/* CL or CAK active */
if (preg_match($odd_char_regex, $haystack)) {
return TRUE;
}
/***
* Check 4: Testing for *author name* surrounded by asterisks
* Check 5: Testing for numbers and cash references ('1000','$5000', etc) in author name
***/
if (empty($wpss_cl_active) && empty($wpss_cak_active) && preg_match("~(^|[\\s\\.])(\$([0-9]+)([0-9,\\.]+)?|([0-9]+)([0-9,\\.]{3,})|([0-9]{3,}))(\$|[\\s])~", $haystack)) {
return TRUE;
}
/* Final Check: The Blacklist */
foreach ($blacklisted_keyphrases as $i => $blacklisted_keyphrase) {
$blacklisted_keyphrase_rgx = rs_wpss_regexify($blacklisted_keyphrase);
$regex_check_phrase = rs_wpss_get_regex_phrase($blacklisted_keyphrase_rgx, '', 'authorkw');
if (preg_match($regex_check_phrase, $haystack)) {
return TRUE;
}
}
} elseif ($haystack_type === 'content') {
/***
* Parse content for links with Anchor Text
* Test 1: Coming Soon
* For possible use later - from old filter: ((payday|students?|title|onli?ne|short([\s\.\-_]*)term)([\s\.\-_]*)loan|cash([\s\.\-_]*)advance)
* Final Check: The Blacklist
***/
$anchor_text_phrases = rs_wpss_parse_links($haystack, 'anchor_text');
foreach ($anchor_text_phrases as $a => $anchor_text_phrase) {
foreach ($blacklisted_keyphrases_lite as $i => $blacklisted_keyphrase) {
$blacklisted_keyphrase_rgx = rs_wpss_regexify($blacklisted_keyphrase);
$regex_check_phrase = rs_wpss_get_regex_phrase($blacklisted_keyphrase_rgx, '', 'authorkw');
if (preg_match($regex_check_phrase, $anchor_text_phrase)) {
return TRUE;
}
}
}
}
return $blacklist_status;
}
function rs_wpss_magic_parser($keyphrase_needles = array(), $haystack = NULL)
{
/**
* The Magic Parser
* Magically parse a large string of text for a number of keyphrases
* The "magic" is that this will check for all kinds of text variations, accents, plurals, 1337 (LEET), etc.
* Extremely accurate...same mechanism used in the rs_wpss_anchortxt_blacklist_chk() function
* @since 1.9.7.8
* @param array $keyphrase_needles The array containing keyphrases to search haystack for
* @param string $haystack The string of text to search. This works well for large chunks of text such as contact form submissions.
* @return bool TRUE if haystack contains any of the keyphrase needles, FALSE if it does not
*/
if (empty($keyphrase_needles) || empty($haystack) || !is_array($keyphrase_needles) || !is_string($haystack)) {
return FALSE;
}
foreach ($keyphrase_needles as $i => $keyphrase_needle) {
$keyphrase_needle_rgx = rs_wpss_regexify($keyphrase_needle);
$regex_check_phrase = rs_wpss_get_regex_phrase($keyphrase_needle_rgx, '', 'authorkw');
if (preg_match($regex_check_phrase, $haystack)) {
return TRUE;
}
}
return FALSE;
}
