@raw_parsed = EXTRACT child_id int, ws_sold_date_sk string, ws_sold_time_sk string, ws_ship_date_sk string, ws_item_sk string, ws_bill_customer_sk string, ws_bill_cdemo_sk string, ws_bill_hdemo_sk string, ws_bill_addr_sk string, ws_ship_customer_sk string, ws_ship_cdemo_sk string, ws_ship_hdemo_sk string, ws_ship_addr_sk string, ws_web_page_sk string, ws_web_site_sk string, ws_ship_mode_sk string, ws_warehouse_sk string, ws_promo_sk string, ws_order_number string, ws_quantity string, ws_wholesale_cost string, ws_list_price string, ws_sales_price string, ws_ext_discount_amt string, ws_ext_sales_price string, ws_ext_wholesale_cost string, ws_ext_list_price string, ws_ext_tax string, ws_coupon_amt string, ws_ext_ship_cost string, ws_net_paid string, ws_net_paid_inc_tax string, ws_net_paid_inc_ship string, ws_net_paid_inc_ship_tax string, ws_net_profit string, empty string FROM "wasb://web-sales@/{*}_{child_id}_100.dat" USING Extractors.Text(delimiter: '|'); @date_dim = EXTRACT d_date_sk string, d_date_id string, d_date string, d_month_seq string, d_week_seq string, d_quarter_seq string, d_year int, d_dow string, d_moy string, d_dom string, d_qoy string, d_fy_year string, d_fy_quarter_seq string, d_fy_week_seq string, d_day_name string, d_quarter_name string, d_holiday string, d_weekend string, d_following_holiday string, d_first_dom string, d_last_dom string, d_same_day_ly string, d_same_day_lq string, d_current_day string, d_current_week string, d_current_month string, d_current_quarter string, d_current_year string, empty string FROM "wasb://date-dim@/date_dim_1_100.dat" USING Extractors.Text(delimiter: '|'); @filtered_results = SELECT ws_sold_date_sk, ws_sold_time_sk, ws_ship_date_sk, ws_item_sk, ws_bill_customer_sk, ws_bill_addr_sk, ws_ship_hdemo_sk, ws_ship_addr_sk, ws_web_page_sk, ws_web_site_sk, ws_ship_mode_sk, ws_warehouse_sk, ws_promo_sk, ws_order_number, ws_quantity, ws_wholesale_cost, ws_list_price, ws_sales_price, ws_ext_discount_amt, ws_ext_sales_price, ws_ext_wholesale_cost, ws_ext_list_price, ws_ext_ship_cost, ws_net_paid, ws_net_profit FROM @raw_parsed INNER JOIN (SELECT d_date_sk, d_year FROM @date_dim) AS dd ON ws_sold_date_sk == dd.d_date_sk WHERE dd.d_year == 2003; OUTPUT @filtered_results TO "/last_available_year/web_sales.csv" USING Outputters.Csv(outputHeader: true);