<?php
/**
 * Content Analyzer class
 *
 * @package     AIContentGuide
 * @subpackage  AIContentGuide/includes
 */

// If this file is called directly, abort.
if (!defined('ABSPATH')) {
    exit;
}

/**
 * Class for analyzing site content.
 */
class FULGID_AICOGU_Content_Analyzer {

    /**
     * Settings array.
     *
     * @var array
     */
    private $settings;

    /**
     * SEO integrator instance.
     *
     * @var FULGID_AICOGU_SEO_Integrator
     */
    private $seo_integrator;

    /**
     * Constructor.
     */
    public function __construct() {
        $this->settings = get_option('fulgid_aicogu_settings', array());
        $this->seo_integrator = new FULGID_AICOGU_SEO_Integrator();
    }

    /**
     * Analyze site content and return structured data for llms.txt.
     *
     * @return string The formatted content for llms.txt.
     */
    public function analyze_site_content() {
        // Initialize content with enhanced header
        $content = $this->get_enhanced_site_header();
        
        // Add site metadata section
        $content .= $this->get_site_metadata();
        
        // Add navigation structure
        $content .= $this->get_navigation_structure();
        
        // Get main content sections with enhanced formatting
        $content .= $this->get_enhanced_main_content();
        
        // Get taxonomies if enabled
        if (!empty($this->settings['include_taxonomies'])) {
            $content .= $this->get_enhanced_taxonomies();
        }
        
        // Add popular content section
        $content .= $this->get_popular_content();
        
        // Add recent content section
        $content .= $this->get_recent_content();
        
        // Add contact and social information
        $content .= $this->get_contact_information();
        
        // Get custom content if set
        if (!empty($this->settings['custom_content'])) {
            $content .= "\n\n## Custom Information\n\n" . $this->settings['custom_content'];
        }
        
        // Add footer information
        $content .= $this->get_site_footer();
        
        return $content;
    }

    /**
     * Get enhanced site header with title, description, and metadata.
     *
     * @return string
     */
    private function get_enhanced_site_header() {
        $site_name = get_bloginfo('name');
        $site_description = get_bloginfo('description');
        $site_url = home_url();
        
        $content = "# {$site_name}\n\n";
        $content .= "> **{$site_description}**\n\n";
        $content .= "🌐 **Website:** [{$site_url}]({$site_url})\n\n";
        
        // Add generation timestamp
        $content .= "📅 **Generated:** " . date('Y-m-d H:i:s T') . "\n\n";
        
        // Add site introduction if set
        if (!empty($this->settings['site_introduction'])) {
            $content .= "## About This Site\n\n";
            $content .= $this->settings['site_introduction'] . "\n\n";
        }
        
        $content .= "---\n\n";
        
        return $content;
    }

    /**
     * Get site metadata section.
     *
     * @return string
     */
    private function get_site_metadata() {
        $content = "## 📊 Site Information\n\n";
        
        // WordPress info
        $wp_version = get_bloginfo('version');
        $admin_email = get_bloginfo('admin_email');
        $language = get_bloginfo('language');
        $charset = get_bloginfo('charset');
        
        $content .= "- **Content Management System:** WordPress {$wp_version}\n";
        $content .= "- **Language:** {$language}\n";
        $content .= "- **Character Encoding:** {$charset}\n";
        
        // Site statistics
        $post_count = wp_count_posts('post')->publish;
        $page_count = wp_count_posts('page')->publish;
        $user_count = count_users()['total_users'];
        
        $content .= "- **Published Posts:** {$post_count}\n";
        $content .= "- **Published Pages:** {$page_count}\n";
        $content .= "- **Total Users:** {$user_count}\n";
        
        // Theme info
        $theme = wp_get_theme();
        $content .= "- **Active Theme:** {$theme->get('Name')} v{$theme->get('Version')}\n";
        
        $content .= "\n";
        
        return $content;
    }
    
    /**
     * Get navigation structure.
     *
     * @return string
     */
    private function get_navigation_structure() {
        $content = "## 🧭 Site Navigation\n\n";
        
        // Get primary menu if exists
        $locations = get_nav_menu_locations();
        if (!empty($locations['primary'])) {
            $menu = wp_get_nav_menu_object($locations['primary']);
            if ($menu) {
                $menu_items = wp_get_nav_menu_items($menu->term_id);
                if ($menu_items) {
                    $content .= "### Primary Menu\n\n";
                    foreach ($menu_items as $item) {
                        if ($item->menu_item_parent == 0) { // Top level items only
                            $content .= "- [{$item->title}]({$item->url})\n";
                        }
                    }
                    $content .= "\n";
                }
            }
        }
        
        return $content;
    }

    /**
     * Get enhanced main content for llms.txt file.
     *
     * @return string
     */
    private function get_enhanced_main_content() {
        $content = "## 📚 Content Sections\n\n";
        $post_types = $this->get_included_post_types();
        
        foreach ($post_types as $post_type) {
            $post_type_obj = get_post_type_object($post_type);
            if (!$post_type_obj) {
                continue;
            }
            
            // Get post count for this type
            $post_count = wp_count_posts($post_type)->publish;
            
            // Add enhanced section heading for post type
            $content .= "### " . $post_type_obj->labels->name . " ({$post_count} items)\n\n";
            
            // Get posts for this post type
            $posts = $this->get_posts_for_post_type($post_type);
            
            if (empty($posts)) {
                $content .= "_No content available in this section._\n\n";
                continue;
            }
            
            foreach ($posts as $post) {
                // Skip if this post is excluded
                if ($this->is_post_excluded($post->ID)) {
                    continue;
                }
                
                // Get post title, URL, and description
                $title = $post->post_title;
                $url = get_permalink($post->ID);
                $description = $this->get_post_description($post);
                $date = get_the_date('Y-m-d', $post->ID);
                $author = get_the_author_meta('display_name', $post->post_author);
                
                // Get post tags/categories for context
                $tags = get_the_tags($post->ID);
                $categories = get_the_category($post->ID);
                $meta_info = [];
                
                if (!empty($categories)) {
                    $cat_names = array_map(function($cat) { return $cat->name; }, $categories);
                    $meta_info[] = 'Categories: ' . implode(', ', $cat_names);
                }
                
                if (!empty($tags)) {
                    $tag_names = array_map(function($tag) { return $tag->name; }, $tags);
                    $meta_info[] = 'Tags: ' . implode(', ', $tag_names);
                }
                
                // Enhanced content format
                $content .= "**[{$title}]({$url})**\n";
                $content .= "_{$description}_\n";
                $content .= "📅 Published: {$date} | ✍️ Author: {$author}\n";
                
                if (!empty($meta_info)) {
                    $content .= "🏷️ " . implode(' | ', $meta_info) . "\n";
                }
                
                $content .= "\n";
            }
            
            $content .= "---\n\n";
        }
        
        return $content;
    }

    /**
     * Get enhanced taxonomies content.
     *
     * @return string
     */
    private function get_enhanced_taxonomies() {
        $content = "## 🏷️ Content Categories & Tags\n\n";
        $taxonomies = !empty($this->settings['taxonomies']) ? $this->settings['taxonomies'] : array('category', 'post_tag');
        
        foreach ($taxonomies as $taxonomy) {
            $tax_obj = get_taxonomy($taxonomy);
            if (!$tax_obj) {
                continue;
            }
            
            // Get terms for this taxonomy
            $terms = get_terms(array(
                'taxonomy' => $taxonomy,
                'hide_empty' => true,
                'orderby' => 'count',
                'order' => 'DESC',
            ));
            
            if (empty($terms) || is_wp_error($terms)) {
                continue;
            }
            
            // Add section heading for taxonomy
            $content .= "### " . $tax_obj->labels->name . " (" . count($terms) . " terms)\n\n";
            
            foreach ($terms as $term) {
                $name = $term->name;
                $url = get_term_link($term);
                $description = !empty($term->description) ? wp_strip_all_tags($term->description) : "Content related to {$name}";
                $post_count = $term->count;
                
                // Enhanced format with post count and better styling
                $content .= "**[{$name}]({$url})** ({$post_count} posts)\n";
                $content .= "_{$description}_\n\n";
            }
            
            $content .= "---\n\n";
        }
        
        return $content;
    }

    /**
     * Get included post types from settings.
     *
     * @return array
     */
    private function get_included_post_types() {
        $default_post_types = array('page', 'post');
        return !empty($this->settings['post_types']) ? $this->settings['post_types'] : $default_post_types;
    }

    /**
     * Get posts for a specific post type.
     *
     * @param string $post_type The post type.
     * @return array
     */
    private function get_posts_for_post_type($post_type) {
        $max_posts = !empty($this->settings['max_posts_per_type']) ? intval($this->settings['max_posts_per_type']) : 20;
        
        $args = array(
            'post_type' => $post_type,
            'post_status' => 'publish',
            'posts_per_page' => $max_posts,
            'orderby' => 'date',
            'order' => 'DESC',
        );
        
        // Apply SEO filtering if integrated
        $args = $this->seo_integrator->filter_query_args($args);
        
        return get_posts($args);
    }

    /**
     * Check if a post is excluded from llms.txt.
     *
     * @param int $post_id The post ID.
     * @return bool
     */
    private function is_post_excluded($post_id) {
        // Check if post is in excluded list
        $excluded_posts = !empty($this->settings['excluded_posts']) ? $this->settings['excluded_posts'] : array();
        if (in_array($post_id, $excluded_posts)) {
            return true;
        }
        
        // Check if post has noindex from SEO plugins
        if ($this->seo_integrator->is_post_noindex($post_id)) {
            return true;
        }
        
        return false;
    }

    /**
     * Get description for a post.
     *
     * @param WP_Post $post The post object.
     * @return string
     */
    private function get_post_description($post) {
        // Check for SEO description first
        $seo_description = $this->seo_integrator->get_meta_description($post->ID);
        if (!empty($seo_description)) {
            // Use wp_strip_all_tags to remove any HTML
            $description = wp_strip_all_tags($seo_description);
        }
        // Fall back to excerpt if available
        else if (!empty($post->post_excerpt)) {
            $description = wp_strip_all_tags($post->post_excerpt);
        }
        // Generate description from content
        else {
            $content = wp_strip_all_tags($post->post_content);
            
            // Clean up any extra whitespace or line breaks
            $content = preg_replace('/\s+/', ' ', $content);
            $content = trim($content);
            
            $max_length = !empty($this->settings['description_length']) ? intval($this->settings['description_length']) : 150;
            
            if (strlen($content) > $max_length) {
                $description = substr($content, 0, $max_length) . '...';
            } else {
                $description = $content;
            }
        }
        
        // Ensure the description is properly sanitized before returning
        return sanitize_text_field($description);
    }
    
    /**
     * Get popular content section.
     *
     * @return string
     */
    private function get_popular_content() {
        $content = "## 🔥 Popular Content\n\n";
        
        // Get most commented posts
        $popular_posts = get_posts(array(
            'post_type' => 'post',
            'post_status' => 'publish',
            'posts_per_page' => 5,
            'orderby' => 'comment_count',
            'order' => 'DESC',
            'meta_query' => array(
                array(
                    'key' => '_wp_old_slug',
                    'compare' => 'NOT EXISTS'
                )
            )
        ));
        
        if (!empty($popular_posts)) {
            $content .= "### Most Discussed Posts\n\n";
            foreach ($popular_posts as $post) {
                if ($this->is_post_excluded($post->ID)) {
                    continue;
                }
                
                $title = $post->post_title;
                $url = get_permalink($post->ID);
                $comment_count = $post->comment_count;
                
                $content .= "- **[{$title}]({$url})** ({$comment_count} comments)\n";
            }
            $content .= "\n";
        }
        
        return $content;
    }
    
    /**
     * Get recent content section.
     *
     * @return string
     */
    private function get_recent_content() {
        $content = "## 🆕 Recent Updates\n\n";
        
        // Get recently updated posts
        $recent_posts = get_posts(array(
            'post_type' => array('post', 'page'),
            'post_status' => 'publish',
            'posts_per_page' => 5,
            'orderby' => 'modified',
            'order' => 'DESC',
        ));
        
        if (!empty($recent_posts)) {
            foreach ($recent_posts as $post) {
                if ($this->is_post_excluded($post->ID)) {
                    continue;
                }
                
                $title = $post->post_title;
                $url = get_permalink($post->ID);
                $modified_date = get_the_modified_date('Y-m-d', $post->ID);
                $post_type = get_post_type_object($post->post_type)->labels->singular_name;
                
                $content .= "- **[{$title}]({$url})** ({$post_type}) - Updated: {$modified_date}\n";
            }
            $content .= "\n";
        }
        
        return $content;
    }
    
    /**
     * Get contact and social information.
     *
     * @return string
     */
    private function get_contact_information() {
        $content = "## 📞 Contact & Social\n\n";
        
        // Get admin email
        $admin_email = get_bloginfo('admin_email');
        if ($admin_email && !empty($admin_email)) {
            $content .= "**Contact Email:** {$admin_email}\n\n";
        }
        
        // Check for common social media and contact options
        $social_options = array(
            'facebook' => 'Facebook',
            'twitter' => 'Twitter',
            'instagram' => 'Instagram',
            'linkedin' => 'LinkedIn',
            'youtube' => 'YouTube'
        );
        
        $found_social = false;
        foreach ($social_options as $platform => $label) {
            $option_value = get_option($platform . '_url', '');
            if (!empty($option_value)) {
                if (!$found_social) {
                    $content .= "**Social Media:**\n";
                    $found_social = true;
                }
                $content .= "- [{$label}]({$option_value})\n";
            }
        }
        
        if ($found_social) {
            $content .= "\n";
        }
        
        return $content;
    }
    
    /**
     * Get site footer information.
     *
     * @return string
     */
    private function get_site_footer() {
        $content = "---\n\n";
        $content .= "## ℹ️ About This File\n\n";
        $content .= "This llms.txt file was automatically generated by the LLMs Text Generator plugin.\n";
        $content .= "It follows the [llms.txt specification](https://llmstxt.org/) to help AI systems better understand this website's content.\n\n";
        $content .= "**Last Updated:** " . date('Y-m-d H:i:s T') . "\n";
        $content .= "**Generator:** LLMs Text Generator for WordPress\n";
        $content .= "**Enhanced by:** [llmstxt.in](https://llmstxt.in/?utm_source=plugin&utm_medium=footer)\n";
        $content .= "**Made with ❤️ by:** [Fulgid](https://fulgid.in)\n\n";
        $content .= "_This file is automatically updated when content changes._\n";
        
        return $content;
    }
}