', $fixed); return $fixed; } private function sanitize_seo_content($content) { // Define allowed HTML tags for SEO content $allowed_html = wp_kses_allowed_html('post'); // Add essential SEO tags that might be missing from default allowed tags $seo_tags = array( 'h1' => array( 'id' => array(), 'class' => array(), 'style' => array(), ), 'h2' => array( 'id' => array(), 'class' => array(), 'style' => array(), ), 'h3' => array( 'id' => array(), 'class' => array(), 'style' => array(), ), 'h4' => array( 'id' => array(), 'class' => array(), 'style' => array(), ), 'h5' => array( 'id' => array(), 'class' => array(), 'style' => array(), ), 'h6' => array( 'id' => array(), 'class' => array(), 'style' => array(), ), 'div' => array( 'id' => array(), 'class' => array(), 'style' => array(), ), 'span' => array( 'id' => array(), 'class' => array(), 'style' => array(), ), 'table' => array( 'id' => array(), 'class' => array(), 'style' => array(), 'border' => array(), 'cellpadding' => array(), 'cellspacing' => array(), ), 'thead' => array(), 'tbody' => array(), 'tr' => array( 'id' => array(), 'class' => array(), ), 'th' => array( 'id' => array(), 'class' => array(), 'scope' => array(), ), 'td' => array( 'id' => array(), 'class' => array(), 'colspan' => array(), 'rowspan' => array(), ), ); // Merge with existing allowed tags $allowed_html = array_merge($allowed_html, $seo_tags); // Apply sanitization with our enhanced allowed tags return wp_kses($content, $allowed_html); } /** * Calculate word count for content * Handles both Hebrew and English text properly */ public function calculate_word_count($content) { if (empty($content)) { return 0; } // Remove HTML tags and decode entities $text = wp_strip_all_tags($content); $text = html_entity_decode($text, ENT_QUOTES, 'UTF-8'); // Remove extra whitespace and normalize $text = preg_replace('/\s+/', ' ', trim($text)); if (empty($text)) { return 0; } // For Hebrew text, count words by spaces and punctuation // Hebrew doesn't use spaces between all words consistently if (preg_match('/[\x{0590}-\x{05FF}]/u', $text)) { // Hebrew text detected - use character-based estimation // Average Hebrew word is about 4-5 characters $char_count = mb_strlen($text, 'UTF-8'); $estimated_words = max(1, round($char_count / 4.5)); // Also count actual spaces for mixed content $space_count = substr_count($text, ' '); // Use the higher count for better accuracy return max($estimated_words, $space_count + 1); } // For English/Latin text, use standard word counting $words = str_word_count($text, 0, 'אבגדהוזחטיכלמנסעפצקרשתךםןףץ'); return max(1, $words); } }