Drop add_headers - headers can now be added to meta[] to be applied for any action. Consilidate Tagging in a service

lib/tasks/duckdb.rake

@@ -0,0 +1,127 @@
+# frozen_string_literal: true
+
+namespace :duckdb do
+  desc "Rebuild DuckDB analytics database from scratch"
+  task rebuild: :environment do
+    puts "=" * 80
+    puts "DuckDB Rebuild"
+    puts "=" * 80
+    puts
+
+    duckdb_path = Rails.root.join("storage", "analytics.duckdb")
+
+    # Step 1: Check if DuckDB exists
+    if File.exist?(duckdb_path)
+      puts "🗑️  Deleting existing DuckDB database..."
+      File.delete(duckdb_path)
+      puts "   ✅ Deleted: #{duckdb_path}"
+      puts
+    else
+      puts "ℹ️  No existing DuckDB database found"
+      puts
+    end
+
+    # Step 2: Rebuild from PostgreSQL
+    puts "🔨 Rebuilding DuckDB from PostgreSQL events..."
+    puts
+
+    start_time = Time.current
+    begin
+      SyncEventsToDuckdbJob.perform_now
+      duration = Time.current - start_time
+
+      # Step 3: Verify the rebuild
+      event_count = AnalyticsDuckdbService.instance.event_count
+      bot_count = AnalyticsDuckdbService.instance.with_connection do |conn|
+        result = conn.query("SELECT COUNT(*) FROM events WHERE is_bot = true")
+        result.first&.first || 0
+      end
+
+      puts "=" * 80
+      puts "✅ DuckDB Rebuild Complete!"
+      puts "=" * 80
+      puts "  Duration: #{duration.round(2)}s"
+      puts "  Total events synced: #{event_count}"
+      puts "  Bot events: #{bot_count} (#{(bot_count.to_f / event_count * 100).round(1)}%)" if event_count > 0
+      puts "  Human events: #{event_count - bot_count} (#{((event_count - bot_count).to_f / event_count * 100).round(1)}%)" if event_count > 0
+      puts
+      puts "📂 Database location: #{duckdb_path}"
+      puts "📊 Database size: #{File.size(duckdb_path) / 1024.0 / 1024.0}MB"
+      puts
+    rescue => e
+      puts "❌ Error rebuilding DuckDB: #{e.message}"
+      puts e.backtrace.first(5).join("\n")
+      exit 1
+    end
+  end
+
+  desc "Show DuckDB statistics"
+  task stats: :environment do
+    duckdb_path = Rails.root.join("storage", "analytics.duckdb")
+
+    unless File.exist?(duckdb_path)
+      puts "❌ DuckDB database not found at: #{duckdb_path}"
+      exit 1
+    end
+
+    puts "=" * 80
+    puts "DuckDB Statistics"
+    puts "=" * 80
+    puts
+
+    total = AnalyticsDuckdbService.instance.event_count
+
+    AnalyticsDuckdbService.instance.with_connection do |conn|
+      # Bot breakdown
+      result = conn.query(<<~SQL)
+        SELECT
+          is_bot,
+          COUNT(*) as event_count,
+          COUNT(DISTINCT ip_address) as unique_ips
+        FROM events
+        GROUP BY is_bot
+      SQL
+
+      puts "📊 Bot Traffic Breakdown:"
+      result.each do |row|
+        type = row[0] ? "🤖 Bots" : "👤 Humans"
+        count = row[1]
+        ips = row[2]
+        percentage = (count.to_f / total * 100).round(1)
+        puts "  #{type}: #{count} events (#{percentage}%) from #{ips} unique IPs"
+      end
+      puts
+
+      # Date range
+      range_result = conn.query("SELECT MIN(timestamp), MAX(timestamp) FROM events")
+      min_ts, max_ts = range_result.first
+      puts "📅 Date Range:"
+      puts "  Oldest event: #{min_ts}"
+      puts "  Newest event: #{max_ts}"
+      puts
+
+      # Database info
+      puts "💾 Database Info:"
+      puts "  Location: #{duckdb_path}"
+      puts "  Size: #{(File.size(duckdb_path) / 1024.0 / 1024.0).round(2)}MB"
+      puts "  Total events: #{total}"
+      puts
+    end
+  end
+
+  desc "Sync new events from PostgreSQL to DuckDB"
+  task sync: :environment do
+    puts "🔄 Syncing events from PostgreSQL to DuckDB..."
+    start_time = Time.current
+
+    begin
+      SyncEventsToDuckdbJob.perform_now
+      duration = Time.current - start_time
+
+      puts "✅ Sync complete in #{duration.round(2)}s"
+    rescue => e
+      puts "❌ Error syncing: #{e.message}"
+      exit 1
+    end
+  end
+end