name: Historical ADS-B Processing on: workflow_dispatch: inputs: start_date: description: 'Start date (YYYY-MM-DD, inclusive)' required: true type: string end_date: description: 'End date (YYYY-MM-DD, exclusive)' required: true type: string chunk_days: description: 'Days per job chunk (default: 7)' required: false type: number default: 7 jobs: generate-matrix: runs-on: ubuntu-latest outputs: chunks: ${{ steps.generate.outputs.chunks }} global_start: ${{ inputs.start_date }} global_end: ${{ inputs.end_date }} steps: - name: Checkout uses: actions/checkout@v4 - name: Setup Python uses: actions/setup-python@v5 with: python-version: '3.12' - name: Generate date chunks id: generate env: INPUT_START_DATE: ${{ inputs.start_date }} INPUT_END_DATE: ${{ inputs.end_date }} INPUT_CHUNK_DAYS: ${{ inputs.chunk_days }} run: python src/adsb/historical_generate_matrix.py adsb-extract: needs: generate-matrix runs-on: ubuntu-24.04-arm strategy: matrix: chunk: ${{ fromJson(needs.generate-matrix.outputs.chunks) }} max-parallel: 3 fail-fast: false steps: - name: Checkout uses: actions/checkout@v4 - name: Setup Python uses: actions/setup-python@v5 with: python-version: '3.12' - name: Install dependencies run: | python -m pip install --upgrade pip pip install -r requirements.txt - name: Free disk space run: | sudo rm -rf /usr/share/dotnet sudo rm -rf /opt/ghc sudo rm -rf /usr/local/share/boost df -h - name: Download and extract ADS-B data env: START_DATE: ${{ matrix.chunk.start_date }} END_DATE: ${{ matrix.chunk.end_date }} run: | python -m src.adsb.download_and_list_icaos --start-date "$START_DATE" --end-date "$END_DATE" ls -lah data/output/ - name: Create tar of extracted data run: | cd data/output echo "=== Disk space before tar ===" df -h . echo "=== Files to tar ===" ls -lah *-planes-readsb-prod-0.tar_0 icao_manifest_*.txt 2>/dev/null || echo "No files found" # Create tar with explicit error checking if ls *-planes-readsb-prod-0.tar_0 1>/dev/null 2>&1; then tar -cvf extracted_data.tar *-planes-readsb-prod-0.tar_0 icao_manifest_*.txt echo "=== Tar file created ===" ls -lah extracted_data.tar # Verify tar integrity tar -tf extracted_data.tar > /dev/null && echo "Tar integrity check passed" || { echo "Tar integrity check FAILED"; exit 1; } else echo "ERROR: No extracted directories found, cannot create tar" exit 1 fi - name: Upload extracted data uses: actions/upload-artifact@v4 with: name: adsb-extracted-${{ matrix.chunk.start_date }}-${{ matrix.chunk.end_date }} path: data/output/extracted_data.tar retention-days: 1 compression-level: 0 if-no-files-found: warn adsb-map: needs: [generate-matrix, adsb-extract] runs-on: ubuntu-24.04-arm strategy: fail-fast: true matrix: chunk: ${{ fromJson(needs.generate-matrix.outputs.chunks) }} icao_chunk: [0, 1, 2, 3] steps: - name: Checkout uses: actions/checkout@v4 - name: Setup Python uses: actions/setup-python@v5 with: python-version: '3.12' - name: Install dependencies run: | python -m pip install --upgrade pip pip install -r requirements.txt - name: Free disk space run: | sudo rm -rf /usr/share/dotnet sudo rm -rf /opt/ghc sudo rm -rf /usr/local/share/boost df -h - name: Download extracted data uses: actions/download-artifact@v4 with: name: adsb-extracted-${{ matrix.chunk.start_date }}-${{ matrix.chunk.end_date }} path: data/output/ continue-on-error: true - name: Extract tar id: extract run: | cd data/output if [ -f extracted_data.tar ]; then echo "=== Tar file info ===" ls -lah extracted_data.tar echo "=== Verifying tar integrity ===" tar -tf extracted_data.tar > /dev/null || { echo "ERROR: Tar file is corrupted"; exit 1; } echo "=== Extracting ===" tar -xvf extracted_data.tar rm extracted_data.tar echo "has_data=true" >> "$GITHUB_OUTPUT" echo "=== Contents of data/output ===" ls -lah else echo "No extracted_data.tar found" echo "has_data=false" >> "$GITHUB_OUTPUT" fi - name: Process ICAO chunk if: steps.extract.outputs.has_data == 'true' env: START_DATE: ${{ matrix.chunk.start_date }} END_DATE: ${{ matrix.chunk.end_date }} run: | python -m src.adsb.process_icao_chunk --chunk-id ${{ matrix.icao_chunk }} --total-chunks 4 --start-date "$START_DATE" --end-date "$END_DATE" ls -lah data/output/adsb_chunks/ || echo "No chunks created" - name: Upload chunk artifacts if: steps.extract.outputs.has_data == 'true' uses: actions/upload-artifact@v4 with: name: adsb-map-${{ matrix.chunk.start_date }}-${{ matrix.chunk.end_date }}-chunk-${{ matrix.icao_chunk }} path: data/output/adsb_chunks/ retention-days: 1 if-no-files-found: ignore adsb-reduce: needs: [generate-matrix, adsb-map] runs-on: ubuntu-24.04-arm steps: - name: Checkout uses: actions/checkout@v4 - name: Setup Python uses: actions/setup-python@v5 with: python-version: '3.12' - name: Install dependencies run: | python -m pip install --upgrade pip pip install -r requirements.txt - name: Download all chunk artifacts uses: actions/download-artifact@v4 with: pattern: adsb-map-* path: data/output/adsb_chunks/ merge-multiple: true - name: Debug downloaded files run: | echo "=== Disk space before processing ===" df -h echo "=== Listing data/output/adsb_chunks/ ===" find data/output/adsb_chunks/ -type f 2>/dev/null | wc -l echo "=== Total parquet size ===" du -sh data/output/adsb_chunks/ || echo "No chunks dir" - name: Combine chunks to CSV env: START_DATE: ${{ needs.generate-matrix.outputs.global_start }} END_DATE: ${{ needs.generate-matrix.outputs.global_end }} run: | python -m src.adsb.combine_chunks_to_csv --chunks-dir data/output/adsb_chunks --start-date "$START_DATE" --end-date "$END_DATE" --skip-base --stream ls -lah data/planequery_aircraft/ - name: Upload final artifact uses: actions/upload-artifact@v4 with: name: planequery_aircraft_adsb-${{ needs.generate-matrix.outputs.global_start }}-${{ needs.generate-matrix.outputs.global_end }} path: data/planequery_aircraft/*.csv retention-days: 30