Configuration

Configuration Overview

The Elasticsearch integration requires configuration across multiple layers: Elasticsearch server settings, database connections, WordPress integration, and application-specific parameters.

Elasticsearch Configuration

Server Configuration

File: inc/elasticsearch.php

class ProductElasticsearch {
    // Connection settings
    private $host = '91.99.113.45';
    private $port = 9200;
    private $index_name = 'products';
    private $cluster_name = 'balerina';

    // Timeout settings
    private $timeout = 30;
    private $connect_timeout = 10;

    // Retry settings
    private $max_retries = 3;
    private $retry_delay = 1; // seconds
}

Index Configuration

Index Settings:

{
  "settings": {
    "number_of_shards": 3,
    "number_of_replicas": 1,
    "refresh_interval": "30s",
    "max_result_window": 10000,
    "analysis": {
      "analyzer": {
        "lithuanian_analyzer": {
          "tokenizer": "standard",
          "filter": [
            "lowercase",
            "asciifolding",
            "lithuanian_snowball",
            "edge_ngram_filter"
          ]
        }
      },
      "filter": {
        "lithuanian_snowball": {
          "type": "snowball",
          "language": "Lithuanian"
        },
        "edge_ngram_filter": {
          "type": "edge_ngram",
          "min_gram": 2,
          "max_gram": 15
        }
      }
    }
  }
}

Mapping Configuration

Field Mappings:

{
  "mappings": {
    "properties": {
      "id": {
        "type": "integer"
      },
      "title": {
        "type": "text",
        "analyzer": "lithuanian_analyzer",
        "fields": {
          "keyword": {
            "type": "keyword"
          },
          "raw": {
            "type": "keyword"
          }
        }
      },
      "brand": {
        "type": "keyword",
        "fields": {
          "text": {
            "type": "text",
            "analyzer": "lithuanian_analyzer"
          }
        }
      },
      "description": {
        "type": "text",
        "analyzer": "lithuanian_analyzer"
      },
      "price": {
        "type": "float"
      },
      "list_price": {
        "type": "float"
      },
      "discount_percentage": {
        "type": "float"
      },
      "availability": {
        "type": "keyword"
      },
      "category": {
        "type": "keyword"
      },
      "category_path": {
        "type": "text",
        "fields": {
          "keyword": {
            "type": "keyword"
          }
        }
      },
      "sku": {
        "type": "keyword"
      },
      "ean": {
        "type": "keyword"
      },
      "image_url": {
        "type": "keyword",
        "index": false
      },
      "product_url": {
        "type": "keyword",
        "index": false
      },
      "specifications": {
        "type": "object",
        "enabled": false
      },
      "created_at": {
        "type": "date"
      },
      "updated_at": {
        "type": "date"
      }
    }
  }
}

Database Configuration

PostgreSQL Connection

File: scripts/elasticsearch-auto-sync.php

class ElasticsearchAutoSyncManager {
    // Database connection
    private $db_host = '162.55.174.116';
    private $db_port = 5432;
    private $db_name = 'categories_db';
    private $db_user = 'website';
    private $db_password = '***';

    private function getDatabaseConnection() {
        $conn_string = "host={$this->db_host} dbname={$this->db_name} user={$this->db_user} password={$this->db_password} port={$this->db_port}";

        $connection = pg_connect($conn_string);

        if (!$connection) {
            throw new Exception("Failed to connect to PostgreSQL database");
        }

        return $connection;
    }
}

Database Schema Requirements

-- Required column for sync tracking
ALTER TABLE product ADD COLUMN added_search BOOLEAN DEFAULT FALSE;

-- Performance indexes
CREATE INDEX idx_product_added_search ON product(added_search);
CREATE INDEX idx_product_composite ON product(added_search, id) WHERE title IS NOT NULL;
CREATE INDEX idx_product_updated ON product(updated_at DESC) WHERE added_search = FALSE;

-- Category indexes
CREATE INDEX idx_category_parent ON core_category(parent_id);
CREATE INDEX idx_category_path ON core_category(path);

Sync Configuration

Batch Processing Settings

File: scripts/elasticsearch-auto-sync.php

class ElasticsearchAutoSyncManager {
    // Batch processing configuration
    private $batch_size = 500;           // Products per batch
    private $max_time = 240;             // Max seconds per run (4 minutes)
    private $memory_limit = '256M';      // Memory limit
    private $cron_interval = 15;         // Minutes between runs

    // Error handling
    private $max_failures = 3;           // Max failures per batch
    private $consecutive_failure_limit = 5; // Max consecutive failures

    // Performance tuning
    private $gc_frequency = 10;          // Garbage collection every N batches
    private $log_level = 'INFO';         // Logging level
}

State Management Configuration

// State file configuration
private $state_file = 'elasticsearch-sync-state.json';
private $log_file = 'elasticsearch-auto-sync.log';
private $backup_state_file = 'elasticsearch-sync-state.backup.json';

// State persistence settings
private $state_backup_frequency = 10;    // Backup state every N batches
private $max_state_file_size = 1048576; // 1MB max state file size

WordPress Configuration

Admin Menu Configuration

File: functions.php

// Admin menu configuration
add_action('admin_menu', 'elasticsearch_admin_menu');

function elasticsearch_admin_menu() {
    add_management_page(
        'Elasticsearch Sync',           // Page title
        'Elasticsearch Sync',           // Menu title
        'manage_options',               // Capability
        'elasticsearch-sync',           // Menu slug
        'elasticsearch_sync_page'       // Callback
    );
}

AJAX Configuration

// AJAX endpoint configuration
add_action('wp_ajax_get_elasticsearch_stats', 'ajax_get_elasticsearch_stats');
add_action('wp_ajax_get_elasticsearch_log', 'ajax_get_elasticsearch_log');
add_action('wp_ajax_test_elasticsearch_connection', 'ajax_test_elasticsearch_connection');
add_action('wp_ajax_reset_elasticsearch_sync', 'ajax_reset_elasticsearch_sync');
add_action('wp_ajax_run_manual_elasticsearch_sync', 'ajax_run_manual_elasticsearch_sync');
add_action('wp_ajax_search_products', 'ajax_search_products');

// Public AJAX endpoints
add_action('wp_ajax_nopriv_search_products', 'ajax_search_products');
add_action('wp_ajax_nopriv_load_category_children', 'ajax_load_category_children');
add_action('wp_ajax_nopriv_search_categories', 'ajax_search_categories');

Template Configuration

// Template configuration
add_action('template_redirect', 'elasticsearch_template_redirect');

function elasticsearch_template_redirect() {
    if (is_page_template('page-search.php')) {
        // Search page specific configuration
        add_action('wp_enqueue_scripts', 'enqueue_search_scripts');
    } elseif (is_page_template('page-elasticsearch-console.php')) {
        // Console page specific configuration
        add_action('wp_enqueue_scripts', 'enqueue_console_scripts');
    }
}

Application Configuration

Search Configuration

File: inc/elasticsearch.php

class ProductElasticsearch {
    // Search configuration
    private $default_page_size = 20;
    private $max_page_size = 100;
    private $default_sort = ['_score' => 'desc'];

    // Search boosting
    private $field_weights = [
        'title' => 3,
        'brand' => 2,
        'description' => 1,
        'sku' => 1
    ];

    // Fuzzy search configuration
    private $fuzziness = 'AUTO';
    private $max_expansions = 50;

    // Highlighting configuration
    private $highlight_fragment_size = 150;
    private $highlight_number_of_fragments = 1;
}

Performance Configuration

// Performance settings
private $connection_pool_size = 10;
private $request_timeout = 30;
private $bulk_request_size = 1000;
private $scroll_timeout = '5m';

// Caching configuration
private $cache_ttl = 300; // 5 minutes
private $cache_prefix = 'elasticsearch_';
private $enable_query_cache = true;

Environment Configuration

Environment Variables

File: .env

# Elasticsearch Configuration
ELASTICSEARCH_HOST=91.99.113.45
ELASTICSEARCH_PORT=9200
ELASTICSEARCH_INDEX=products
ELASTICSEARCH_CLUSTER=balerina
ELASTICSEARCH_TIMEOUT=30

# Database Configuration
DB_HOST=162.55.174.116
DB_PORT=5432
DB_NAME=categories_db
DB_USER=website
DB_PASSWORD=your_secure_password

# Sync Configuration
SYNC_BATCH_SIZE=500
SYNC_MAX_TIME=240
SYNC_MEMORY_LIMIT=256M
SYNC_CRON_INTERVAL=15

# Logging Configuration
LOG_LEVEL=INFO
LOG_MAX_SIZE=10485760
LOG_MAX_FILES=5
LOG_ROTATE_DAILY=true

# Performance Configuration
CACHE_TTL=300
CACHE_ENABLED=true
QUERY_CACHE_ENABLED=true

Configuration Loading

// Load environment configuration
function load_elasticsearch_config() {
    $config = [];

    // Load from .env file
    if (file_exists('.env')) {
        $env_content = file_get_contents('.env');
        $lines = explode("\n", $env_content);

        foreach ($lines as $line) {
            $line = trim($line);
            if (empty($line) || strpos($line, '#') === 0) {
                continue;
            }

            list($key, $value) = explode('=', $line, 2);
            $config[trim($key)] = trim($value);
        }
    }

    // Override with WordPress constants
    if (defined('ELASTICSEARCH_HOST')) {
        $config['ELASTICSEARCH_HOST'] = ELASTICSEARCH_HOST;
    }

    return $config;
}

Cron Configuration

Crontab Setup

# Add to crontab
crontab -e

# Elasticsearch Auto-Sync (every 15 minutes)
*/15 * * * * /usr/bin/php /var/www/html/wp-content/themes/products/scripts/elasticsearch-auto-sync.php >> /var/log/dealai/elasticsearch-sync.log 2>&1

# Log rotation (daily at 5 AM)
0 5 * * * /usr/sbin/logrotate /etc/logrotate.d/dealai >> /var/log/dealai/logrotate.log 2>&1

# Database maintenance (weekly, Sunday 4 AM)
0 4 * * 0 /usr/bin/psql -h 162.55.174.116 -U website -d categories_db -c "VACUUM ANALYZE;" >> /var/log/dealai/db-maintenance.log 2>&1

Log Rotation Configuration

File: /etc/logrotate.d/dealai

/var/log/dealai/*.log {
    daily
    missingok
    rotate 14
    compress
    delaycompress
    notifempty
    create 0640 www-data www-data
    sharedscripts
    postrotate
        systemctl reload rsyslog > /dev/null 2>&1 || true
    endscript
}

Security Configuration

Access Control

// WordPress capability requirements
$required_capabilities = [
    'elasticsearch_console' => 'manage_options',
    'elasticsearch_stats' => 'manage_options',
    'elasticsearch_logs' => 'manage_options',
    'elasticsearch_reset' => 'manage_options',
    'search_products' => 'read' // Public access
];

// Check user capabilities
function check_elasticsearch_permissions($action) {
    global $required_capabilities;

    $capability = $required_capabilities[$action] ?? 'manage_options';

    if (!current_user_can($capability)) {
        wp_send_json_error('Insufficient permissions');
    }
}

Input Validation

// Input validation configuration
$validation_rules = [
    'query' => [
        'type' => 'string',
        'max_length' => 255,
        'sanitize' => 'sanitize_text_field'
    ],
    'category' => [
        'type' => 'integer',
        'min' => 1,
        'sanitize' => 'intval'
    ],
    'min_price' => [
        'type' => 'float',
        'min' => 0,
        'sanitize' => 'floatval'
    ],
    'max_price' => [
        'type' => 'float',
        'min' => 0,
        'sanitize' => 'floatval'
    ],
    'page' => [
        'type' => 'integer',
        'min' => 1,
        'max' => 1000,
        'sanitize' => 'intval'
    ],
    'per_page' => [
        'type' => 'integer',
        'min' => 1,
        'max' => 100,
        'sanitize' => 'intval'
    ]
];

Monitoring Configuration

Health Check Configuration

// Health check settings
$health_check_config = [
    'elasticsearch' => [
        'enabled' => true,
        'interval' => 300, // 5 minutes
        'timeout' => 10,
        'retries' => 3
    ],
    'database' => [
        'enabled' => true,
        'interval' => 600, // 10 minutes
        'timeout' => 5,
        'retries' => 2
    ],
    'sync_process' => [
        'enabled' => true,
        'interval' => 900, // 15 minutes
        'stuck_threshold' => 3600 // 1 hour
    ]
];

Alert Configuration

// Alert thresholds
$alert_thresholds = [
    'error_rate' => 0.1, // 10% error rate
    'consecutive_failures' => 3,
    'sync_stuck_hours' => 2,
    'memory_usage' => 0.8, // 80% memory usage
    'disk_usage' => 0.9 // 90% disk usage
];

// Alert recipients
$alert_recipients = [
    '[email protected]',
    '[email protected]'
];

Performance Configuration

Caching Configuration

// WordPress object cache configuration
$cache_config = [
    'enabled' => true,
    'ttl' => 300, // 5 minutes
    'prefix' => 'elasticsearch_',
    'groups' => [
        'search_results' => 300,
        'aggregations' => 600,
        'categories' => 1800,
        'stats' => 60
    ]
];

// Redis configuration (if available)
$redis_config = [
    'enabled' => true,
    'host' => '127.0.0.1',
    'port' => 6379,
    'database' => 0,
    'timeout' => 5
];

Query Optimization

// Query optimization settings
$query_optimization = [
    'use_filters' => true,
    'cache_queries' => true,
    'limit_aggregations' => 100,
    'max_result_window' => 10000,
    'preference' => '_local' // Prefer local shards
];

Next Steps

• Deployment - Installation and setup
• Troubleshooting - Common issues and solutions
• Performance Optimization - Performance tuning
• API Endpoints - API reference