use .csv.gz

.github/workflows/openairframes-daily-release.yaml

@@ -227,7 +227,7 @@ jobs:
         uses: actions/upload-artifact@v4
         with:
           name: adsb-release
-          path: data/openairframes/openairframes_adsb_*.csv
+          path: data/openairframes/openairframes_adsb_*.csv.gz
           retention-days: 1
 
   build-community:
@@ -388,7 +388,7 @@ jobs:
           
           # Find files from artifacts using find (handles nested structures)
           CSV_FILE_FAA=$(find artifacts/faa -name "openairframes_faa_*.csv" -type f 2>/dev/null | head -1)
-          CSV_FILE_ADSB=$(find artifacts/adsb -name "openairframes_adsb_*.csv" -type f 2>/dev/null | head -1)
+          CSV_FILE_ADSB=$(find artifacts/adsb -name "openairframes_adsb_*.csv.gz" -type f 2>/dev/null | head -1)
           CSV_FILE_COMMUNITY=$(find artifacts/community -name "openairframes_community_*.csv" -type f 2>/dev/null | head -1)
           ZIP_FILE=$(find artifacts/faa -name "ReleasableAircraft_*.zip" -type f 2>/dev/null | head -1)
           JSON_FILE_ADSBX=$(find artifacts/adsbexchange -name "basic-ac-db_*.json.gz" -type f 2>/dev/null | head -1)

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}")

src/create_daily_adsb_release.py

@@ -77,7 +77,7 @@ if __name__ == '__main__':
     OUT_ROOT = Path("data/openairframes")
     OUT_ROOT.mkdir(parents=True, exist_ok=True)
 
-    output_file = OUT_ROOT / f"openairframes_adsb_{start_date_str}_{date_str}.csv"
+    output_file = OUT_ROOT / f"openairframes_adsb_{start_date_str}_{date_str}.csv.gz"
     df_combined.write_csv(output_file)
 
     print(f"Saved: {output_file}")

src/get_latest_release.py

@@ -165,7 +165,7 @@ def download_latest_aircraft_adsb_csv(
         Path to the downloaded file
     """
     assets = get_latest_release_assets(repo, github_token=github_token)
-    asset = pick_asset(assets, name_regex=r"^openairframes_adsb_.*\.csv$")
+    asset = pick_asset(assets, name_regex=r"^openairframes_adsb_.*\.csv(\.gz)?$")
     saved_to = download_asset(asset, output_dir / asset.name, github_token=github_token)
     print(f"Downloaded: {asset.name} ({asset.size} bytes) -> {saved_to}")
     return saved_to
@@ -176,7 +176,7 @@ def get_latest_aircraft_adsb_csv_df():
     import pandas as pd
     df = pd.read_csv(csv_path)
     df = df.fillna("")
-    # 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}")