use .csv.gz

src/adsb/combine_chunks_to_csv.py

@@ -176,7 +176,7 @@ def main():
     if args.start_date and args.end_date:
         # Historical mode
         output_id = f"{args.start_date}_{args.end_date}"
-        output_filename = f"openairframes_adsb_{args.start_date}_{args.end_date}.csv"
+        output_filename = f"openairframes_adsb_{args.start_date}_{args.end_date}.csv.gz"
         print(f"Combining chunks for date range: {args.start_date} to {args.end_date}")
     else:
         # Daily mode - use same date for start and end
@@ -187,7 +187,7 @@ def main():
         
         date_str = target_day.strftime("%Y-%m-%d")
         output_id = date_str
-        output_filename = f"openairframes_adsb_{date_str}_{date_str}.csv"
+        output_filename = f"openairframes_adsb_{date_str}_{date_str}.csv.gz"
         print(f"Combining chunks for {date_str}")
     
     chunks_dir = args.chunks_dir

src/adsb/compress_adsb_to_aircraft_data.py

@@ -264,7 +264,7 @@ def get_latest_aircraft_adsb_csv_df():
         if df[col].dtype == pl.Utf8:
             df = df.with_columns(pl.col(col).fill_null(""))
     
-    # Extract start date from filename pattern: openairframes_adsb_{start_date}_{end_date}.csv
+    # Extract start date from filename pattern: openairframes_adsb_{start_date}_{end_date}.csv[.gz]
     match = re.search(r"openairframes_adsb_(\d{4}-\d{2}-\d{2})_", str(csv_path))
     if not match:
         raise ValueError(f"Could not extract date from filename: {csv_path.name}")