fix None value comparision

This reverts commit ccf55b2308.

.github/workflows/historical-adsb.yaml

@@ -95,20 +95,27 @@ jobs:
             # Verify tar integrity
             tar -tf extracted_data.tar > /dev/null && echo "Tar integrity check passed" || { echo "Tar integrity check FAILED"; exit 1; }
             
-            # Create checksum of the FULL tar before splitting (for verification after reassembly)
-            echo "=== Creating checksum of full tar ==="
-            sha256sum extracted_data.tar > full_tar.sha256
-            cat full_tar.sha256
+            # Record tar size and checksum for verification after reassembly
+            echo "=== Recording tar metadata ==="
+            ORIGINAL_SIZE=$(stat --format=%s extracted_data.tar)
+            ORIGINAL_SHA=$(sha256sum extracted_data.tar | awk '{print $1}')
+            echo "Size: $ORIGINAL_SIZE"
+            echo "SHA256: $ORIGINAL_SHA"
             
             # Split into 500MB chunks to avoid artifact upload issues
             echo "=== Splitting tar into 500MB chunks ==="
             mkdir -p tar_chunks
             split -b 500M extracted_data.tar tar_chunks/extracted_data.tar.part_
             rm extracted_data.tar
-            mv full_tar.sha256 tar_chunks/
+            
+            # Write metadata file (plain text so artifact upload won't skip it)
+            echo "$ORIGINAL_SHA  extracted_data.tar" > tar_chunks/checksum.txt
+            echo "$ORIGINAL_SIZE" >> tar_chunks/checksum.txt
             
             echo "=== Chunks created ==="
             ls -lah tar_chunks/
+            echo "=== Checksum file ==="
+            cat tar_chunks/checksum.txt
           else
             echo "ERROR: No extracted directories found, cannot create tar"
             exit 1
@@ -179,19 +186,30 @@ jobs:
             echo "=== Reassembled tar file info ==="
             ls -lah extracted_data.tar
             
-            # Verify checksum of reassembled tar matches original
-            echo "=== Verifying reassembled tar checksum ==="
-            echo "Original checksum:"
-            cat tar_chunks/full_tar.sha256
-            echo "Reassembled checksum:"
-            sha256sum extracted_data.tar
-            sha256sum -c tar_chunks/full_tar.sha256 || { echo "ERROR: Reassembled tar checksum mismatch - data corrupted during transfer"; exit 1; }
-            echo "Checksum verified - data integrity confirmed"
+            # Verify integrity
+            echo "=== Verifying reassembled tar ==="
+            if [ -f tar_chunks/checksum.txt ]; then
+              EXPECTED_SHA=$(head -1 tar_chunks/checksum.txt | awk '{print $1}')
+              EXPECTED_SIZE=$(sed -n '2p' tar_chunks/checksum.txt)
+              ACTUAL_SHA=$(sha256sum extracted_data.tar | awk '{print $1}')
+              ACTUAL_SIZE=$(stat --format=%s extracted_data.tar)
+              echo "Expected: SHA=$EXPECTED_SHA Size=$EXPECTED_SIZE"
+              echo "Actual:   SHA=$ACTUAL_SHA Size=$ACTUAL_SIZE"
+              if [ "$EXPECTED_SHA" != "$ACTUAL_SHA" ] || [ "$EXPECTED_SIZE" != "$ACTUAL_SIZE" ]; then
+                echo "ERROR: Reassembled tar does not match original - data corrupted during transfer"
+                exit 1
+              fi
+              echo "Checksum and size verified"
+            else
+              echo "WARNING: No checksum file found, falling back to tar integrity check"
+              tar -tf extracted_data.tar > /dev/null || { echo "ERROR: Tar file is corrupted"; exit 1; }
+              echo "Tar integrity check passed"
+            fi
             
             rm -rf tar_chunks
             
             echo "=== Extracting ==="
-            tar -xvf extracted_data.tar
+            tar -xf extracted_data.tar
             rm extracted_data.tar
             echo "has_data=true" >> "$GITHUB_OUTPUT"
             echo "=== Contents of data/output ==="

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

@@ -302,6 +302,7 @@ jobs:
           python-version: "3.14"
 
       - name: Run Mictronics DB release script
+        continue-on-error: true
         run: |
           python -m src.contributions.create_daily_microtonics_release ${{ inputs.date && format('--date {0}', inputs.date) || '' }}
           ls -lah data/openairframes
@@ -312,11 +313,12 @@ jobs:
           name: mictronics-db
           path: data/openairframes/mictronics-db_*.zip
           retention-days: 1
+          if-no-files-found: ignore
 
   create-release:
     runs-on: ubuntu-latest
-    needs: [build-faa, adsb-reduce, build-community]
-    if: github.event_name != 'schedule'
+    needs: [build-faa, adsb-reduce, build-community, build-adsbexchange-json, build-mictronics-db]
+    if: github.event_name != 'schedule' && !failure() && !cancelled()
     steps:
       - name: Checkout for gh CLI
         uses: actions/checkout@v4
@@ -351,6 +353,7 @@ jobs:
 
       - name: Download Mictronics DB artifact
         uses: actions/download-artifact@v4
+        continue-on-error: true
         with:
           name: mictronics-db
           path: artifacts/mictronics
@@ -405,8 +408,12 @@ jobs:
           if [ -z "$JSON_FILE_ADSBX" ] || [ ! -f "$JSON_FILE_ADSBX" ]; then
             MISSING_FILES="$MISSING_FILES ADSBX_JSON"
           fi
+          
+          # Optional files - warn but don't fail
+          OPTIONAL_MISSING=""
           if [ -z "$ZIP_FILE_MICTRONICS" ] || [ ! -f "$ZIP_FILE_MICTRONICS" ]; then
-            MISSING_FILES="$MISSING_FILES MICTRONICS_ZIP"
+            OPTIONAL_MISSING="$OPTIONAL_MISSING MICTRONICS_ZIP"
+            ZIP_FILE_MICTRONICS=""
           fi
           
           if [ -n "$MISSING_FILES" ]; then
@@ -425,7 +432,14 @@ jobs:
           CSV_BASENAME_COMMUNITY=$(basename "$CSV_FILE_COMMUNITY" 2>/dev/null || echo "")
           ZIP_BASENAME=$(basename "$ZIP_FILE")
           JSON_BASENAME_ADSBX=$(basename "$JSON_FILE_ADSBX")
-          ZIP_BASENAME_MICTRONICS=$(basename "$ZIP_FILE_MICTRONICS")
+          ZIP_BASENAME_MICTRONICS=""
+          if [ -n "$ZIP_FILE_MICTRONICS" ]; then
+            ZIP_BASENAME_MICTRONICS=$(basename "$ZIP_FILE_MICTRONICS")
+          fi
+          
+          if [ -n "$OPTIONAL_MISSING" ]; then
+            echo "WARNING: Optional files missing:$OPTIONAL_MISSING (will continue without them)"
+          fi
           
           echo "date=$DATE" >> "$GITHUB_OUTPUT"
           echo "tag=$TAG" >> "$GITHUB_OUTPUT"
@@ -463,7 +477,7 @@ jobs:
         with:
           tag_name: ${{ steps.meta.outputs.tag }}
           name: ${{ steps.meta.outputs.name }}
-          fail_on_unmatched_files: true
+          fail_on_unmatched_files: false
           body: |
             Automated daily snapshot generated at 06:00 UTC for ${{ steps.meta.outputs.date }}.
 
@@ -473,7 +487,7 @@ jobs:
             - ${{ steps.meta.outputs.csv_basename_community }}
             - ${{ steps.meta.outputs.zip_basename }}
             - ${{ steps.meta.outputs.json_basename_adsbx }}
-            - ${{ steps.meta.outputs.zip_basename_mictronics }}
+            ${{ steps.meta.outputs.zip_basename_mictronics && format('- {0}', steps.meta.outputs.zip_basename_mictronics) || '' }}
           files: |
             ${{ steps.meta.outputs.csv_file_faa }}
             ${{ steps.meta.outputs.csv_file_adsb }}

src/adsb/download_adsb_data_to_parquet.py

@@ -82,8 +82,8 @@ def fetch_releases(version_date: str) -> list:
     if version_date == "v2024.12.31":
         year = "2025"
     BASE_URL = f"https://api.github.com/repos/adsblol/globe_history_{year}/releases"
-    # Match exact release name, exclude tmp releases
-    PATTERN = rf"^{re.escape(version_date)}-planes-readsb-prod-\d+$"
+    # Match both normal and tmp releases
+    PATTERN = rf"^{re.escape(version_date)}-planes-readsb-prod-\d+(tmp)?$"
     releases = []
     page = 1
     
@@ -582,6 +582,12 @@ def process_version_date(version_date: str, keep_folders: bool = False):
             print(f"No releases found for {vd}.")
             return None
         
+        # Prefer non-tmp releases; only use tmp if no normal releases exist
+        normal_releases = [r for r in releases if "tmp" not in r["tag_name"]]
+        tmp_releases = [r for r in releases if "tmp" in r["tag_name"]]
+        releases = normal_releases if normal_releases else tmp_releases
+        print(f"Using {'normal' if normal_releases else 'tmp'} releases ({len(releases)} found)")
+        
         downloaded_files = []
         for release in releases:
             tag_name = release["tag_name"]

src/adsb/download_and_list_icaos.py

@@ -59,6 +59,12 @@ def download_and_extract(version_date: str) -> str | None:
             print(f"No releases found for {version_date}")
             return None
         
+        # Prefer non-tmp releases; only use tmp if no normal releases exist
+        normal_releases = [r for r in releases if "tmp" not in r["tag_name"]]
+        tmp_releases = [r for r in releases if "tmp" in r["tag_name"]]
+        releases = normal_releases if normal_releases else tmp_releases
+        print(f"Using {'normal' if normal_releases else 'tmp'} releases ({len(releases)} found)")
+        
         downloaded_files = []
         for release in releases:
             tag_name = release["tag_name"]

src/adsb/run_local.py

@@ -0,0 +1,155 @@
+#!/usr/bin/env python3
+"""
+Run the full ADS-B processing pipeline locally.
+
+Downloads adsb.lol data, processes trace files, and outputs openairframes_adsb CSV.
+
+Usage:
+    # Single day (yesterday by default)
+    python -m src.adsb.run_local
+    
+    # Single day (specific date)
+    python -m src.adsb.run_local 2024-01-15
+    
+    # Date range (inclusive)
+    python -m src.adsb.run_local 2024-01-01 2024-01-07
+"""
+import argparse
+import os
+import subprocess
+import sys
+from datetime import datetime, timedelta
+
+
+def run_cmd(cmd: list[str], description: str) -> None:
+    """Run a command and exit on failure."""
+    print(f"\n>>> {' '.join(cmd)}")
+    result = subprocess.run(cmd)
+    if result.returncode != 0:
+        print(f"ERROR: {description} failed with exit code {result.returncode}")
+        sys.exit(result.returncode)
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Run full ADS-B processing pipeline locally",
+        usage="python -m src.adsb.run_local [start_date] [end_date]"
+    )
+    parser.add_argument(
+        "start_date",
+        nargs="?",
+        help="Start date (YYYY-MM-DD). Default: yesterday"
+    )
+    parser.add_argument(
+        "end_date",
+        nargs="?",
+        help="End date (YYYY-MM-DD, inclusive). If omitted, processes single day"
+    )
+    parser.add_argument(
+        "--chunks",
+        type=int,
+        default=4,
+        help="Number of parallel chunks (default: 4)"
+    )
+    parser.add_argument(
+        "--skip-base",
+        action="store_true",
+        help="Skip downloading and merging with base release"
+    )
+    args = parser.parse_args()
+
+    # Determine dates
+    if args.start_date:
+        start_date = datetime.strptime(args.start_date, "%Y-%m-%d")
+    else:
+        start_date = datetime.utcnow() - timedelta(days=1)
+    
+    end_date = None
+    if args.end_date:
+        end_date = datetime.strptime(args.end_date, "%Y-%m-%d")
+    
+    start_str = start_date.strftime("%Y-%m-%d")
+    end_str = end_date.strftime("%Y-%m-%d") if end_date else None
+    
+    print("=" * 60)
+    print("ADS-B Processing Pipeline")
+    print("=" * 60)
+    if end_str:
+        print(f"Date range: {start_str} to {end_str}")
+    else:
+        print(f"Date: {start_str}")
+    print(f"Chunks: {args.chunks}")
+    print("=" * 60)
+    
+    # Step 1: Download and extract
+    print("\n" + "=" * 60)
+    print("Step 1: Download and Extract")
+    print("=" * 60)
+    
+    if end_str:
+        cmd = ["python", "-m", "src.adsb.download_and_list_icaos",
+               "--start-date", start_str, "--end-date", end_str]
+    else:
+        cmd = ["python", "-m", "src.adsb.download_and_list_icaos",
+               "--date", start_str]
+    run_cmd(cmd, "Download and extract")
+    
+    # Step 2: Process chunks
+    print("\n" + "=" * 60)
+    print("Step 2: Process Chunks")
+    print("=" * 60)
+    
+    for chunk_id in range(args.chunks):
+        print(f"\n--- Chunk {chunk_id + 1}/{args.chunks} ---")
+        if end_str:
+            cmd = ["python", "-m", "src.adsb.process_icao_chunk",
+                   "--chunk-id", str(chunk_id),
+                   "--total-chunks", str(args.chunks),
+                   "--start-date", start_str,
+                   "--end-date", end_str]
+        else:
+            cmd = ["python", "-m", "src.adsb.process_icao_chunk",
+                   "--chunk-id", str(chunk_id),
+                   "--total-chunks", str(args.chunks),
+                   "--date", start_str]
+        run_cmd(cmd, f"Process chunk {chunk_id}")
+    
+    # Step 3: Combine chunks to CSV
+    print("\n" + "=" * 60)
+    print("Step 3: Combine to CSV")
+    print("=" * 60)
+    
+    chunks_dir = "./data/output/adsb_chunks"
+    cmd = ["python", "-m", "src.adsb.combine_chunks_to_csv",
+           "--chunks-dir", chunks_dir]
+    
+    if end_str:
+        cmd.extend(["--start-date", start_str, "--end-date", end_str])
+    else:
+        cmd.extend(["--date", start_str])
+    
+    if args.skip_base:
+        cmd.append("--skip-base")
+    
+    run_cmd(cmd, "Combine chunks")
+    
+    print("\n" + "=" * 60)
+    print("Done!")
+    print("=" * 60)
+    
+    # Show output
+    output_dir = "./data/openairframes"
+    if end_str:
+        output_file = f"openairframes_adsb_{start_str}_{end_str}.csv"
+    else:
+        output_file = f"openairframes_adsb_{start_str}_{start_str}.csv"
+    
+    output_path = os.path.join(output_dir, output_file)
+    if os.path.exists(output_path):
+        size_mb = os.path.getsize(output_path) / (1024 * 1024)
+        print(f"Output: {output_path}")
+        print(f"Size: {size_mb:.1f} MB")
+
+
+if __name__ == "__main__":
+    main()

src/contributions/create_daily_microtonics_release.py

@@ -9,12 +9,17 @@ from __future__ import annotations
 
 import argparse
 import shutil
+import sys
+import time
 from datetime import datetime, timezone
 from pathlib import Path
+from urllib.error import URLError
 from urllib.request import Request, urlopen
 
 URL = "https://www.mictronics.de/aircraft-database/indexedDB_old.php"
 OUT_ROOT = Path("data/openairframes")
+MAX_RETRIES = 3
+RETRY_DELAY = 30  # seconds
 
 
 def main() -> None:
@@ -28,12 +33,22 @@ def main() -> None:
 
     zip_path = OUT_ROOT / f"mictronics-db_{date_str}.zip"
 
-    print(f"Downloading {URL}...")
-    req = Request(URL, headers={"User-Agent": "openairframes-downloader/1.0"}, method="GET")
-    with urlopen(req, timeout=300) as r, zip_path.open("wb") as f:
-        shutil.copyfileobj(r, f)
-
-    print(f"Wrote: {zip_path}")
+    for attempt in range(1, MAX_RETRIES + 1):
+        try:
+            print(f"Downloading {URL} (attempt {attempt}/{MAX_RETRIES})...")
+            req = Request(URL, headers={"User-Agent": "Mozilla/5.0 (compatible; openairframes-downloader/1.0)"}, method="GET")
+            with urlopen(req, timeout=120) as r, zip_path.open("wb") as f:
+                shutil.copyfileobj(r, f)
+            print(f"Wrote: {zip_path}")
+            return
+        except (URLError, TimeoutError) as e:
+            print(f"Attempt {attempt} failed: {e}")
+            if attempt < MAX_RETRIES:
+                print(f"Retrying in {RETRY_DELAY} seconds...")
+                time.sleep(RETRY_DELAY)
+            else:
+                print("All retries exhausted. Mictronics download failed.")
+                sys.exit(1)
 
 
 if __name__ == "__main__":

src/derive_from_faa_master_txt.py

@@ -47,6 +47,9 @@ def convert_faa_master_txt_to_df(zip_path: Path, date: str):
     
     # Convert all NaN to empty strings
     df = df.fillna("")
+    # The FAA parser can produce the literal string "None" for missing values;
+    # replace those so they match the empty-string convention used everywhere else.
+    df = df.replace("None", "")
     
     return df
 
@@ -84,8 +87,8 @@ def concat_faa_historical_df(df_base, df_new):
             # Convert to string
             val_str = str(val).strip()
             
-            # Handle empty strings
-            if val_str == "" or val_str == "nan":
+            # Handle empty strings and null-like literals
+            if val_str == "" or val_str == "nan" or val_str == "None":
                 return ""
             
             # Check if it looks like a list representation (starts with [ )