make faa work with no new data

.github/ISSUE_TEMPLATE/community_submission.yaml

@@ -14,7 +14,7 @@ body:
         - Each object must include **at least one** of:
           - `registration_number`
           - `transponder_code_hex` (6 uppercase hex chars, e.g., `ABC123`)
-          - `planequery_airframe_id`
+          - `openairframes_id`
         - Your contributor name (entered below) will be applied to all objects.
         - `contributor_uuid` is derived from your GitHub account automatically.
         - `creation_timestamp` is created by the system (you may omit it).

.github/workflows/historical-adsb.yaml

@@ -48,7 +48,7 @@ jobs:
       matrix:
         chunk: ${{ fromJson(needs.generate-matrix.outputs.chunks) }}
       max-parallel: 3
-      fail-fast: false
+      fail-fast: true
     steps:
       - name: Checkout
         uses: actions/checkout@v4
@@ -220,11 +220,11 @@ jobs:
           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/
+          ls -lah data/openairframes/
 
       - 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
+          name: openairframes_adsb-${{ needs.generate-matrix.outputs.global_start }}-${{ needs.generate-matrix.outputs.global_end }}
+          path: data/openairframes/*.csv
           retention-days: 30

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

@@ -1,4 +1,4 @@
-name: planequery-aircraft Daily Release
+name: OpenAirframes Daily Release
 
 on:
   schedule:
@@ -22,7 +22,7 @@ jobs:
             await github.rest.actions.createWorkflowDispatch({
               owner: context.repo.owner,
               repo: context.repo.repo,
-              workflow_id: 'planequery-aircraft-daily-release.yaml',
+              workflow_id: 'openairframes-daily-release.yaml',
               ref: 'main'
             });
       
@@ -33,7 +33,7 @@ jobs:
             await github.rest.actions.createWorkflowDispatch({
               owner: context.repo.owner,
               repo: context.repo.repo,
-              workflow_id: 'planequery-aircraft-daily-release.yaml',
+              workflow_id: 'openairframes-daily-release.yaml',
               ref: 'develop'
             });
 
@@ -58,16 +58,16 @@ jobs:
 
       - name: Run FAA release script
         run: |
-          python src/create_daily_planequery_aircraft_release.py
+          python src/create_daily_faa_release.py
           ls -lah data/faa_releasable
-          ls -lah data/planequery_aircraft
+          ls -lah data/openairframes
 
       - name: Upload FAA artifacts
         uses: actions/upload-artifact@v4
         with:
           name: faa-release
           path: |
-            data/planequery_aircraft/planequery_aircraft_faa_*.csv
+            data/openairframes/openairframes_faa_*.csv
             data/faa_releasable/ReleasableAircraft_*.zip
           retention-days: 1
 
@@ -214,13 +214,13 @@ jobs:
           mkdir -p data/output/adsb_chunks
           ls -lah data/output/adsb_chunks/ || echo "Directory empty or does not exist"
           python -m src.adsb.combine_chunks_to_csv --chunks-dir data/output/adsb_chunks
-          ls -lah data/planequery_aircraft/
+          ls -lah data/openairframes/
 
       - name: Upload ADS-B artifacts
         uses: actions/upload-artifact@v4
         with:
           name: adsb-release
-          path: data/planequery_aircraft/planequery_aircraft_adsb_*.csv
+          path: data/openairframes/openairframes_adsb_*.csv
           retention-days: 1
 
   build-community:
@@ -245,13 +245,13 @@ jobs:
       - name: Run Community release script
         run: |
           python -m src.contributions.create_daily_community_release
-          ls -lah data/planequery_aircraft
+          ls -lah data/openairframes
 
       - name: Upload Community artifacts
         uses: actions/upload-artifact@v4
         with:
           name: community-release
-          path: data/planequery_aircraft/planequery_aircraft_community_*.csv
+          path: data/openairframes/openairframes_community_*.csv
           retention-days: 1
 
   create-release:
@@ -297,16 +297,16 @@ jobs:
           elif [ "$BRANCH_NAME" = "develop" ]; then
             BRANCH_SUFFIX="-develop"
           fi
-          TAG="planequery-aircraft-${DATE}${BRANCH_SUFFIX}"
+          TAG="openairframes-${DATE}${BRANCH_SUFFIX}"
           
-          # Find files from artifacts
-          CSV_FILE_FAA=$(ls artifacts/faa/data/planequery_aircraft/planequery_aircraft_faa_*.csv | head -1)
+          # Find files from artifacts using find (handles nested structures)
+          CSV_FILE_FAA=$(find artifacts/faa -name "openairframes_faa_*.csv" | head -1)
           CSV_BASENAME_FAA=$(basename "$CSV_FILE_FAA")
-          CSV_FILE_ADSB=$(ls artifacts/adsb/planequery_aircraft_adsb_*.csv | head -1)
+          CSV_FILE_ADSB=$(find artifacts/adsb -name "openairframes_adsb_*.csv" | head -1)
           CSV_BASENAME_ADSB=$(basename "$CSV_FILE_ADSB")
-          CSV_FILE_COMMUNITY=$(ls artifacts/community/planequery_aircraft_community_*.csv 2>/dev/null | head -1 || echo "")
+          CSV_FILE_COMMUNITY=$(find artifacts/community -name "openairframes_community_*.csv" 2>/dev/null | head -1 || echo "")
           CSV_BASENAME_COMMUNITY=$(basename "$CSV_FILE_COMMUNITY" 2>/dev/null || echo "")
-          ZIP_FILE=$(ls artifacts/faa/data/faa_releasable/ReleasableAircraft_*.zip | head -1)
+          ZIP_FILE=$(find artifacts/faa -name "ReleasableAircraft_*.zip" | head -1)
           ZIP_BASENAME=$(basename "$ZIP_FILE")
           
           echo "date=$DATE" >> "$GITHUB_OUTPUT"
@@ -319,12 +319,15 @@ jobs:
           echo "csv_basename_community=$CSV_BASENAME_COMMUNITY" >> "$GITHUB_OUTPUT"
           echo "zip_file=$ZIP_FILE" >> "$GITHUB_OUTPUT"
           echo "zip_basename=$ZIP_BASENAME" >> "$GITHUB_OUTPUT"
-          echo "name=planequery-aircraft snapshot ($DATE)${BRANCH_SUFFIX}" >> "$GITHUB_OUTPUT"
+          echo "name=OpenAirframes snapshot ($DATE)${BRANCH_SUFFIX}" >> "$GITHUB_OUTPUT"
+
+      - name: Checkout for gh CLI
+        uses: actions/checkout@v4
 
       - name: Delete existing release if exists
         run: |
-          gh release delete "${{ steps.meta.outputs.tag }}" --yes 2>/dev/null || true
-          git push --delete origin "refs/tags/${{ steps.meta.outputs.tag }}" 2>/dev/null || true
+          echo "Attempting to delete release: ${{ steps.meta.outputs.tag }}"
+          gh release delete "${{ steps.meta.outputs.tag }}" --yes --cleanup-tag || echo "No existing release to delete"
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 

.github/workflows/process-historical-faa.yaml

@@ -0,0 +1,171 @@
+name: Process Historical FAA Data
+
+on:
+  workflow_dispatch:  # Manual trigger
+
+jobs:
+  generate-matrix:
+    runs-on: ubuntu-latest
+    outputs:
+      matrix: ${{ steps.set-matrix.outputs.matrix }}
+    steps:
+      - name: Generate date ranges
+        id: set-matrix
+        run: |
+          python3 << 'EOF'
+          import json
+          from datetime import datetime, timedelta
+          
+          start = datetime(2023, 8, 16)
+          end = datetime(2026, 1, 1)
+          
+          ranges = []
+          current = start
+          
+          # Process in 4-day chunks
+          while current < end:
+            chunk_end = current + timedelta(days=4)
+            # Don't go past the end date
+            if chunk_end > end:
+              chunk_end = end
+            
+            ranges.append({
+              "since": current.strftime("%Y-%m-%d"),
+              "until": chunk_end.strftime("%Y-%m-%d")
+            })
+            
+            current = chunk_end
+          
+          print(f"::set-output name=matrix::{json.dumps(ranges)}")
+          EOF
+
+  clone-faa-repo:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Cache FAA repository
+        id: cache-faa-repo
+        uses: actions/cache@v4
+        with:
+          path: data/scrape-faa-releasable-aircraft
+          key: faa-repo-v1
+          
+      - name: Clone FAA repository
+        if: steps.cache-faa-repo.outputs.cache-hit != 'true'
+        run: |
+          mkdir -p data
+          git clone https://github.com/simonw/scrape-faa-releasable-aircraft data/scrape-faa-releasable-aircraft
+          echo "Repository cloned successfully"
+
+  process-chunk:
+    needs: [generate-matrix, clone-faa-repo]
+    runs-on: ubuntu-latest
+    strategy:
+      max-parallel: 5  # Process 5 chunks at a time
+      matrix:
+        range: ${{ fromJson(needs.generate-matrix.outputs.matrix) }}
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      
+      - name: Restore FAA repository cache
+        uses: actions/cache/restore@v4
+        with:
+          path: data/scrape-faa-releasable-aircraft
+          key: faa-repo-v1
+          fail-on-cache-miss: true
+      
+      - name: Install dependencies
+        run: |
+          pip install -r requirements.txt
+      
+      - name: Process chunk ${{ matrix.range.since }} to ${{ matrix.range.until }}
+        run: |
+          python src/get_historical_faa.py "${{ matrix.range.since }}" "${{ matrix.range.until }}"
+      
+      - name: Upload CSV artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: csv-${{ matrix.range.since }}-to-${{ matrix.range.until }}
+          path: data/faa_releasable_historical/*.csv
+          retention-days: 1
+
+  create-release:
+    needs: process-chunk
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Download all artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: artifacts
+      
+      - name: Prepare release files
+        run: |
+          mkdir -p release-files
+          find artifacts -name "*.csv" -exec cp {} release-files/ \;
+          ls -lh release-files/
+      
+      - name: Create Release
+        uses: softprops/action-gh-release@v1
+        with:
+          tag_name: historical-faa-${{ github.run_number }}
+          name: Historical FAA Data Release ${{ github.run_number }}
+          body: |
+            Automated release of historical FAA aircraft data
+            Processing period: 2023-08-16 to 2026-01-01
+            Generated: ${{ github.event.repository.updated_at }}
+          files: release-files/*.csv
+          draft: false
+          prerelease: false
+
+  concatenate-and-release:
+    needs: process-chunk
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+      
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      
+      - name: Install dependencies
+        run: |
+          pip install -r requirements.txt
+      
+      - name: Download all artifacts
+        uses: actions/download-artifact@v4
+        with:
+          path: artifacts
+      
+      - name: Prepare CSVs for concatenation
+        run: |
+          mkdir -p data/faa_releasable_historical
+          find artifacts -name "*.csv" -exec cp {} data/faa_releasable_historical/ \;
+          ls -lh data/faa_releasable_historical/
+      
+      - name: Concatenate all CSVs
+        run: |
+          python scripts/concat_csvs.py
+      
+      - name: Create Combined Release
+        uses: softprops/action-gh-release@v1
+        with:
+          tag_name: historical-faa-combined-${{ github.run_number }}
+          name: Historical FAA Data Combined Release ${{ github.run_number }}
+          body: |
+            Combined historical FAA aircraft data (all chunks concatenated)
+            Processing period: 2023-08-16 to 2026-01-01
+            Generated: ${{ github.event.repository.updated_at }}
+          files: data/openairframes/*.csv
+          draft: false
+          prerelease: false

.github/workflows/update-community-prs.yaml

@@ -5,7 +5,7 @@ on:
     branches: [main]
     paths:
       - 'community/**'
-      - 'schemas/community_submission.*.schema.json'
+      - 'schemas/community_submission.v1.schema.json'
 
 permissions:
   contents: write
@@ -29,18 +29,9 @@ jobs:
       - name: Install dependencies
         run: pip install jsonschema
 
-      - name: Get current schema version
-        id: schema
-        run: |
-          # Find the latest schema version on main
-          latest=$(ls schemas/community_submission.v*.schema.json 2>/dev/null | sed 's/.*\.v\([0-9]*\)\.schema\.json/\1/' | sort -n | tail -1)
-          echo "latest_version=${latest:-1}" >> "$GITHUB_OUTPUT"
-          echo "Latest schema version: ${latest:-1}"
-
       - name: Find and update open community PRs
         env:
           GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          LATEST_SCHEMA_VERSION: ${{ steps.schema.outputs.latest_version }}
         run: |
           # Get list of open community PRs
           prs=$(gh pr list --label community --state open --json number,headRefName --jq '.[] | "\(.number) \(.headRefName)"')
@@ -57,35 +48,28 @@ jobs:
             git fetch origin "$branch_name"
             git checkout "$branch_name"
             
-            # Check if this PR has a schema file that needs updating
-            pr_schema=$(ls schemas/community_submission.v*.schema.json 2>/dev/null | sed 's/.*\.v\([0-9]*\)\.schema\.json/\1/' | sort -n | tail -1)
+            # Merge main into PR branch
+            git config user.name "github-actions[bot]"
+            git config user.email "github-actions[bot]@users.noreply.github.com"
             
-            if [ "$pr_schema" -le "$LATEST_SCHEMA_VERSION" ] 2>/dev/null; then
-              echo "  PR schema version ($pr_schema) <= main version ($LATEST_SCHEMA_VERSION)"
+            if git merge origin/main -m "Merge main to update schema"; then
+              # Regenerate schema for this PR's submission (adds any new tags)
+              python -m src.contributions.regenerate_pr_schema || true
               
-              # Merge main into PR branch
-              git config user.name "github-actions[bot]"
-              git config user.email "github-actions[bot]@users.noreply.github.com"
-              
-              if git merge origin/main -m "Merge main to update schema baseline"; then
-                # Regenerate schema for this PR's submission
-                python -m src.contributions.regenerate_pr_schema || true
-                
-                # If there are changes, commit and push
-                if [ -n "$(git status --porcelain schemas/)" ]; then
-                  new_version=$((LATEST_SCHEMA_VERSION + 1))
-                  git add schemas/
-                  git commit -m "Update schema to v${new_version} (rebased on main)"
-                  git push origin "$branch_name"
-                  echo "  Updated PR #$pr_number with new schema"
-                else
-                  git push origin "$branch_name"
-                  echo "  Merged main into PR #$pr_number"
-                fi
+              # If there are changes, commit and push
+              if [ -n "$(git status --porcelain schemas/)" ]; then
+                git add schemas/
+                git commit -m "Update schema with new tags"
+                git push origin "$branch_name"
+                echo "  Updated PR #$pr_number with schema changes"
               else
-                echo "  Merge conflict in PR #$pr_number, adding comment"
-                gh pr comment "$pr_number" --body $'⚠️ **Merge Conflict**\n\nAnother community submission was merged and this PR has conflicts.\n\nA maintainer may need to:\n1. Close this PR\n2. Remove the `approved` label from the original issue\n3. Re-add the `approved` label to regenerate the PR'
-                git merge --abort
+                git push origin "$branch_name"
+                echo "  Merged main into PR #$pr_number"
+              fi
+            else
+              echo "  Merge conflict in PR #$pr_number, adding comment"
+              gh pr comment "$pr_number" --body $'⚠️ **Merge Conflict**\n\nAnother community submission was merged and this PR has conflicts.\n\nA maintainer may need to:\n1. Close this PR\n2. Remove the `approved` label from the original issue\n3. Re-add the `approved` label to regenerate the PR'
+              git merge --abort
               fi
             fi
             

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2026 PlaneQuery
+Copyright (c) 2026 OpenAirframes
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

infra/stack.py

@@ -23,7 +23,7 @@ class AdsbProcessingStack(Stack):
         # --- S3 bucket for intermediate and final results ---
         bucket = s3.Bucket(
             self, "ResultsBucket",
-            bucket_name="planequery-aircraft-dev",
+            bucket_name="openairframes-dev",
             removal_policy=RemovalPolicy.DESTROY,
             auto_delete_objects=True,
             lifecycle_rules=[

notebooks/planequery_adsb_read.ipynb

@@ -1,640 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "06ae0319",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import clickhouse_connect\n",
-    "client = clickhouse_connect.get_client(\n",
-    "    host=os.environ[\"CLICKHOUSE_HOST\"],\n",
-    "    username=os.environ[\"CLICKHOUSE_USERNAME\"],\n",
-    "    password=os.environ[\"CLICKHOUSE_PASSWORD\"],\n",
-    "    secure=True,\n",
-    ")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "779710f0",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df = client.query_df(\"SELECT time, icao,r,t,dbFlags,ownOp,year,desc,aircraft FROM adsb_messages Where time > '2024-01-01 00:00:00' AND time < '2024-01-02 00:00:00'\")\n",
-    "df_copy = df.copy()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bf024da8",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# -- military = dbFlags & 1; interesting = dbFlags & 2; PIA = dbFlags & 4; LADD = dbFlags & 8;"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "270607b5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df = load_raw_adsb_for_day(datetime(2024,1,1))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "ac06a30e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['aircraft']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "91edab3e",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "COLUMNS = ['dbFlags', 'ownOp', 'year', 'desc', 'aircraft_category', 'r', 't']\n",
-    "def compress_df(df):\n",
-    "    icao = df.name\n",
-    "    df[\"_signature\"] = df[COLUMNS].astype(str).agg('|'.join, axis=1)\n",
-    "    original_df = df.copy()\n",
-    "    df = df.groupby(\"_signature\", as_index=False).last() # check if it works with both last and first.\n",
-    "    # For each row, create a dict of non-empty column values. This is using sets and subsets...\n",
-    "    def get_non_empty_dict(row):\n",
-    "        return {col: row[col] for col in COLUMNS if row[col] != ''}\n",
-    "    \n",
-    "    df['_non_empty_dict'] = df.apply(get_non_empty_dict, axis=1)\n",
-    "    df['_non_empty_count'] = df['_non_empty_dict'].apply(len)\n",
-    "    \n",
-    "    # Check if row i's non-empty values are a subset of row j's non-empty values\n",
-    "    def is_subset_of_any(idx):\n",
-    "        row_dict = df.loc[idx, '_non_empty_dict']\n",
-    "        row_count = df.loc[idx, '_non_empty_count']\n",
-    "        \n",
-    "        for other_idx in df.index:\n",
-    "            if idx == other_idx:\n",
-    "                continue\n",
-    "            other_dict = df.loc[other_idx, '_non_empty_dict']\n",
-    "            other_count = df.loc[other_idx, '_non_empty_count']\n",
-    "            \n",
-    "            # Check if all non-empty values in current row match those in other row\n",
-    "            if all(row_dict.get(k) == other_dict.get(k) for k in row_dict.keys()):\n",
-    "                # If they match and other has more defined columns, current row is redundant\n",
-    "                if other_count > row_count:\n",
-    "                    return True\n",
-    "        return False\n",
-    "    \n",
-    "    # Keep rows that are not subsets of any other row\n",
-    "    keep_mask = ~df.index.to_series().apply(is_subset_of_any)\n",
-    "    df = df[keep_mask]\n",
-    "\n",
-    "    if len(df) > 1:\n",
-    "        original_df = original_df[original_df['_signature'].isin(df['_signature'])]\n",
-    "        value_counts = original_df[\"_signature\"].value_counts()\n",
-    "        max_signature = value_counts.idxmax()\n",
-    "        df = df[df['_signature'] == max_signature]\n",
-    "\n",
-    "    df['icao'] = icao\n",
-    "    df = df.drop(columns=['_non_empty_dict', '_non_empty_count', '_signature'])\n",
-    "    return df\n",
-    "\n",
-    "# df = df_copy\n",
-    "# df = df_copy.iloc[0:100000]\n",
-    "# df = df[df['r'] == \"N4131T\"]\n",
-    "# df = df[(df['icao'] == \"008081\")]\n",
-    "# df = df.iloc[0:500]\n",
-    "df['aircraft_category'] = df['aircraft'].apply(lambda x: x.get('category') if isinstance(x, dict) else None)\n",
-    "df = df.drop(columns=['aircraft'])\n",
-    "df = df.sort_values(['icao', 'time'])\n",
-    "df[COLUMNS] = df[COLUMNS].fillna('')\n",
-    "ORIGINAL_COLUMNS = df.columns.tolist()\n",
-    "df_compressed = df.groupby('icao',group_keys=False).apply(compress_df)\n",
-    "cols = df_compressed.columns.tolist()\n",
-    "cols.remove(\"icao\")\n",
-    "cols.insert(1, \"icao\")\n",
-    "df_compressed = df_compressed[cols]\n",
-    "df_compressed"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "efdfcb2c",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df['aircraft_category'] = df['aircraft'].apply(lambda x: x.get('category') if isinstance(x, dict) else None)\n",
-    "df[~df['aircraft_category'].isna()]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "495c5025",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# SOME KIND OF MAP REDUCE SYSTEM\n",
-    "import os\n",
-    "\n",
-    "COLUMNS = ['dbFlags', 'ownOp', 'year', 'desc', 'aircraft_category', 'r', 't']\n",
-    "def compress_df(df):\n",
-    "    icao = df.name\n",
-    "    df[\"_signature\"] = df[COLUMNS].astype(str).agg('|'.join, axis=1)\n",
-    "    \n",
-    "    # Compute signature counts before grouping (avoid copy)\n",
-    "    signature_counts = df[\"_signature\"].value_counts()\n",
-    "    \n",
-    "    df = df.groupby(\"_signature\", as_index=False).first() # check if it works with both last and first.\n",
-    "    # For each row, create a dict of non-empty column values. This is using sets and subsets...\n",
-    "    def get_non_empty_dict(row):\n",
-    "        return {col: row[col] for col in COLUMNS if row[col] != ''}\n",
-    "    \n",
-    "    df['_non_empty_dict'] = df.apply(get_non_empty_dict, axis=1)\n",
-    "    df['_non_empty_count'] = df['_non_empty_dict'].apply(len)\n",
-    "    \n",
-    "    # Check if row i's non-empty values are a subset of row j's non-empty values\n",
-    "    def is_subset_of_any(idx):\n",
-    "        row_dict = df.loc[idx, '_non_empty_dict']\n",
-    "        row_count = df.loc[idx, '_non_empty_count']\n",
-    "        \n",
-    "        for other_idx in df.index:\n",
-    "            if idx == other_idx:\n",
-    "                continue\n",
-    "            other_dict = df.loc[other_idx, '_non_empty_dict']\n",
-    "            other_count = df.loc[other_idx, '_non_empty_count']\n",
-    "            \n",
-    "            # Check if all non-empty values in current row match those in other row\n",
-    "            if all(row_dict.get(k) == other_dict.get(k) for k in row_dict.keys()):\n",
-    "                # If they match and other has more defined columns, current row is redundant\n",
-    "                if other_count > row_count:\n",
-    "                    return True\n",
-    "        return False\n",
-    "    \n",
-    "    # Keep rows that are not subsets of any other row\n",
-    "    keep_mask = ~df.index.to_series().apply(is_subset_of_any)\n",
-    "    df = df[keep_mask]\n",
-    "\n",
-    "    if len(df) > 1:\n",
-    "        # Use pre-computed signature counts instead of original_df\n",
-    "        remaining_sigs = df['_signature']\n",
-    "        sig_counts = signature_counts[remaining_sigs]\n",
-    "        max_signature = sig_counts.idxmax()\n",
-    "        df = df[df['_signature'] == max_signature]\n",
-    "\n",
-    "    df['icao'] = icao\n",
-    "    df = df.drop(columns=['_non_empty_dict', '_non_empty_count', '_signature'])\n",
-    "    return df\n",
-    "\n",
-    "# names of releases something like\n",
-    "# planequery_aircraft_adsb_2024-06-01T00-00-00Z.csv.gz\n",
-    "\n",
-    "# Let's build historical first. \n",
-    "\n",
-    "_ch_client = None\n",
-    "\n",
-    "def _get_clickhouse_client():\n",
-    "    \"\"\"Return a reusable ClickHouse client, with retry/backoff for transient DNS or connection errors.\"\"\"\n",
-    "    global _ch_client\n",
-    "    if _ch_client is not None:\n",
-    "        return _ch_client\n",
-    "\n",
-    "    import clickhouse_connect\n",
-    "    import time\n",
-    "\n",
-    "    max_retries = 5\n",
-    "    for attempt in range(1, max_retries + 1):\n",
-    "        try:\n",
-    "            _ch_client = clickhouse_connect.get_client(\n",
-    "                host=os.environ[\"CLICKHOUSE_HOST\"],\n",
-    "                username=os.environ[\"CLICKHOUSE_USERNAME\"],\n",
-    "                password=os.environ[\"CLICKHOUSE_PASSWORD\"],\n",
-    "                secure=True,\n",
-    "            )\n",
-    "            return _ch_client\n",
-    "        except Exception as e:\n",
-    "            wait = min(2 ** attempt, 30)\n",
-    "            print(f\"  ClickHouse connect attempt {attempt}/{max_retries} failed: {e}\")\n",
-    "            if attempt == max_retries:\n",
-    "                raise\n",
-    "            print(f\"  Retrying in {wait}s...\")\n",
-    "            time.sleep(wait)\n",
-    "\n",
-    "\n",
-    "def load_raw_adsb_for_day(day):\n",
-    "    \"\"\"Load raw ADS-B data for a day from cache or ClickHouse.\"\"\"\n",
-    "    from datetime import timedelta\n",
-    "    from pathlib import Path\n",
-    "    import pandas as pd\n",
-    "    import time\n",
-    "    \n",
-    "    start_time = day.replace(hour=0, minute=0, second=0, microsecond=0)\n",
-    "    end_time = start_time + timedelta(days=1)\n",
-    "    \n",
-    "    # Set up caching\n",
-    "    cache_dir = Path(\"data/adsb\")\n",
-    "    cache_dir.mkdir(parents=True, exist_ok=True)\n",
-    "    cache_file = cache_dir / f\"adsb_raw_{start_time.strftime('%Y-%m-%d')}.csv.zst\"\n",
-    "    \n",
-    "    # Check if cache exists\n",
-    "    if cache_file.exists():\n",
-    "        print(f\"  Loading from cache: {cache_file}\")\n",
-    "        df = pd.read_csv(cache_file, compression='zstd')\n",
-    "        df['time'] = pd.to_datetime(df['time'])\n",
-    "    else:\n",
-    "        # Format dates for the query\n",
-    "        start_str = start_time.strftime('%Y-%m-%d %H:%M:%S')\n",
-    "        end_str = end_time.strftime('%Y-%m-%d %H:%M:%S')\n",
-    "        \n",
-    "        max_retries = 3\n",
-    "        for attempt in range(1, max_retries + 1):\n",
-    "            try:\n",
-    "                client = _get_clickhouse_client()\n",
-    "                print(f\"  Querying ClickHouse for {start_time.strftime('%Y-%m-%d')}\")\n",
-    "                df = client.query_df(f\"SELECT time, icao,r,t,dbFlags,ownOp,year,desc,aircraft FROM adsb_messages Where time > '{start_str}' AND time < '{end_str}'\")\n",
-    "                break\n",
-    "            except Exception as e:\n",
-    "                wait = min(2 ** attempt, 30)\n",
-    "                print(f\"  Query attempt {attempt}/{max_retries} failed: {e}\")\n",
-    "                if attempt == max_retries:\n",
-    "                    raise\n",
-    "                # Reset client in case connection is stale\n",
-    "                global _ch_client\n",
-    "                _ch_client = None\n",
-    "                print(f\"  Retrying in {wait}s...\")\n",
-    "                time.sleep(wait)\n",
-    "        \n",
-    "        # Save to cache\n",
-    "        df.to_csv(cache_file, index=False, compression='zstd')\n",
-    "        print(f\"  Saved to cache: {cache_file}\")\n",
-    "    \n",
-    "    return df\n",
-    "\n",
-    "def load_historical_for_day(day):\n",
-    "    from pathlib import Path\n",
-    "    import pandas as pd\n",
-    "    \n",
-    "    df = load_raw_adsb_for_day(day)\n",
-    "    print(df)\n",
-    "    df['aircraft_category'] = df['aircraft'].apply(lambda x: x.get('category') if isinstance(x, dict) else None)\n",
-    "    df = df.drop(columns=['aircraft'])\n",
-    "    df = df.sort_values(['icao', 'time'])\n",
-    "    df[COLUMNS] = df[COLUMNS].fillna('')\n",
-    "    df_compressed = df.groupby('icao',group_keys=False).apply(compress_df)\n",
-    "    cols = df_compressed.columns.tolist()\n",
-    "    cols.remove('time')\n",
-    "    cols.insert(0, 'time')\n",
-    "    cols.remove(\"icao\")\n",
-    "    cols.insert(1, \"icao\")\n",
-    "    df_compressed = df_compressed[cols]\n",
-    "    return df_compressed\n",
-    "\n",
-    "\n",
-    "def concat_compressed_dfs(df_base, df_new):\n",
-    "    \"\"\"Concatenate base and new compressed dataframes, keeping the most informative row per ICAO.\"\"\"\n",
-    "    import pandas as pd\n",
-    "    \n",
-    "    # Combine both dataframes\n",
-    "    df_combined = pd.concat([df_base, df_new], ignore_index=True)\n",
-    "    \n",
-    "    # Sort by ICAO and time\n",
-    "    df_combined = df_combined.sort_values(['icao', 'time'])\n",
-    "    \n",
-    "    # Fill NaN values\n",
-    "    df_combined[COLUMNS] = df_combined[COLUMNS].fillna('')\n",
-    "    \n",
-    "    # Apply compression logic per ICAO to get the best row\n",
-    "    df_compressed = df_combined.groupby('icao', group_keys=False).apply(compress_df)\n",
-    "    \n",
-    "    # Sort by time\n",
-    "    df_compressed = df_compressed.sort_values('time')\n",
-    "    \n",
-    "    return df_compressed\n",
-    "\n",
-    "\n",
-    "def get_latest_aircraft_adsb_csv_df():\n",
-    "    \"\"\"Download and load the latest ADS-B CSV from GitHub releases.\"\"\"\n",
-    "    from get_latest_planequery_aircraft_release import download_latest_aircraft_adsb_csv\n",
-    "    \n",
-    "    import pandas as pd\n",
-    "    import re\n",
-    "    \n",
-    "    csv_path = download_latest_aircraft_adsb_csv()\n",
-    "    df = pd.read_csv(csv_path)\n",
-    "    df = df.fillna(\"\")\n",
-    "    \n",
-    "    # Extract start date from filename pattern: planequery_aircraft_adsb_{start_date}_{end_date}.csv\n",
-    "    match = re.search(r\"planequery_aircraft_adsb_(\\d{4}-\\d{2}-\\d{2})_\", str(csv_path))\n",
-    "    if not match:\n",
-    "        raise ValueError(f\"Could not extract date from filename: {csv_path.name}\")\n",
-    "    \n",
-    "    date_str = match.group(1)\n",
-    "    return df, date_str\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "7f66acf7",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# SOME KIND OF MAP REDUCE SYSTEM\n",
-    "\n",
-    "\n",
-    "COLUMNS = ['dbFlags', 'ownOp', 'year', 'desc', 'aircraft_category', 'r', 't']\n",
-    "def compress_df(df):\n",
-    "    icao = df.name\n",
-    "    df[\"_signature\"] = df[COLUMNS].astype(str).agg('|'.join, axis=1)\n",
-    "    original_df = df.copy()\n",
-    "    df = df.groupby(\"_signature\", as_index=False).first() # check if it works with both last and first.\n",
-    "    # For each row, create a dict of non-empty column values. This is using sets and subsets...\n",
-    "    def get_non_empty_dict(row):\n",
-    "        return {col: row[col] for col in COLUMNS if row[col] != ''}\n",
-    "    \n",
-    "    df['_non_empty_dict'] = df.apply(get_non_empty_dict, axis=1)\n",
-    "    df['_non_empty_count'] = df['_non_empty_dict'].apply(len)\n",
-    "    \n",
-    "    # Check if row i's non-empty values are a subset of row j's non-empty values\n",
-    "    def is_subset_of_any(idx):\n",
-    "        row_dict = df.loc[idx, '_non_empty_dict']\n",
-    "        row_count = df.loc[idx, '_non_empty_count']\n",
-    "        \n",
-    "        for other_idx in df.index:\n",
-    "            if idx == other_idx:\n",
-    "                continue\n",
-    "            other_dict = df.loc[other_idx, '_non_empty_dict']\n",
-    "            other_count = df.loc[other_idx, '_non_empty_count']\n",
-    "            \n",
-    "            # Check if all non-empty values in current row match those in other row\n",
-    "            if all(row_dict.get(k) == other_dict.get(k) for k in row_dict.keys()):\n",
-    "                # If they match and other has more defined columns, current row is redundant\n",
-    "                if other_count > row_count:\n",
-    "                    return True\n",
-    "        return False\n",
-    "    \n",
-    "    # Keep rows that are not subsets of any other row\n",
-    "    keep_mask = ~df.index.to_series().apply(is_subset_of_any)\n",
-    "    df = df[keep_mask]\n",
-    "\n",
-    "    if len(df) > 1:\n",
-    "        original_df = original_df[original_df['_signature'].isin(df['_signature'])]\n",
-    "        value_counts = original_df[\"_signature\"].value_counts()\n",
-    "        max_signature = value_counts.idxmax()\n",
-    "        df = df[df['_signature'] == max_signature]\n",
-    "\n",
-    "    df['icao'] = icao\n",
-    "    df = df.drop(columns=['_non_empty_dict', '_non_empty_count', '_signature'])\n",
-    "    return df\n",
-    "\n",
-    "# names of releases something like\n",
-    "# planequery_aircraft_adsb_2024-06-01T00-00-00Z.csv.gz\n",
-    "\n",
-    "# Let's build historical first. \n",
-    "\n",
-    "def load_raw_adsb_for_day(day):\n",
-    "    \"\"\"Load raw ADS-B data for a day from cache or ClickHouse.\"\"\"\n",
-    "    from datetime import timedelta\n",
-    "    import clickhouse_connect\n",
-    "    from pathlib import Path\n",
-    "    import pandas as pd\n",
-    "    \n",
-    "    start_time = day.replace(hour=0, minute=0, second=0, microsecond=0)\n",
-    "    end_time = start_time + timedelta(days=1)\n",
-    "    \n",
-    "    # Set up caching\n",
-    "    cache_dir = Path(\"data/adsb\")\n",
-    "    cache_dir.mkdir(parents=True, exist_ok=True)\n",
-    "    cache_file = cache_dir / f\"adsb_raw_{start_time.strftime('%Y-%m-%d')}.csv.zst\"\n",
-    "    \n",
-    "    # Check if cache exists\n",
-    "    if cache_file.exists():\n",
-    "        print(f\"  Loading from cache: {cache_file}\")\n",
-    "        df = pd.read_csv(cache_file, compression='zstd')\n",
-    "        df['time'] = pd.to_datetime(df['time'])\n",
-    "    else:\n",
-    "        # Format dates for the query\n",
-    "        start_str = start_time.strftime('%Y-%m-%d %H:%M:%S')\n",
-    "        end_str = end_time.strftime('%Y-%m-%d %H:%M:%S')\n",
-    "        \n",
-    "        client = clickhouse_connect.get_client(\n",
-    "            host=os.environ[\"CLICKHOUSE_HOST\"],\n",
-    "            username=os.environ[\"CLICKHOUSE_USERNAME\"],\n",
-    "            password=os.environ[\"CLICKHOUSE_PASSWORD\"],\n",
-    "            secure=True,\n",
-    "        )\n",
-    "        print(f\"  Querying ClickHouse for {start_time.strftime('%Y-%m-%d')}\")\n",
-    "        df = client.query_df(f\"SELECT time, icao,r,t,dbFlags,ownOp,year,desc,aircraft FROM adsb_messages Where time > '{start_str}' AND time < '{end_str}'\")\n",
-    "        \n",
-    "        # Save to cache\n",
-    "        df.to_csv(cache_file, index=False, compression='zstd')\n",
-    "        print(f\"  Saved to cache: {cache_file}\")\n",
-    "    \n",
-    "    return df\n",
-    "\n",
-    "def load_historical_for_day(day):\n",
-    "    from pathlib import Path\n",
-    "    import pandas as pd\n",
-    "    \n",
-    "    df = load_raw_adsb_for_day(day)\n",
-    "    \n",
-    "    df['aircraft_category'] = df['aircraft'].apply(lambda x: x.get('category') if isinstance(x, dict) else None)\n",
-    "    df = df.drop(columns=['aircraft'])\n",
-    "    df = df.sort_values(['icao', 'time'])\n",
-    "    df[COLUMNS] = df[COLUMNS].fillna('')\n",
-    "    df_compressed = df.groupby('icao',group_keys=False).apply(compress_df)\n",
-    "    cols = df_compressed.columns.tolist()\n",
-    "    cols.remove('time')\n",
-    "    cols.insert(0, 'time')\n",
-    "    cols.remove(\"icao\")\n",
-    "    cols.insert(1, \"icao\")\n",
-    "    df_compressed = df_compressed[cols]\n",
-    "    return df_compressed\n",
-    "\n",
-    "\n",
-    "def concat_compressed_dfs(df_base, df_new):\n",
-    "    \"\"\"Concatenate base and new compressed dataframes, keeping the most informative row per ICAO.\"\"\"\n",
-    "    import pandas as pd\n",
-    "    \n",
-    "    # Combine both dataframes\n",
-    "    df_combined = pd.concat([df_base, df_new], ignore_index=True)\n",
-    "    \n",
-    "    # Sort by ICAO and time\n",
-    "    df_combined = df_combined.sort_values(['icao', 'time'])\n",
-    "    \n",
-    "    # Fill NaN values\n",
-    "    df_combined[COLUMNS] = df_combined[COLUMNS].fillna('')\n",
-    "    \n",
-    "    # Apply compression logic per ICAO to get the best row\n",
-    "    df_compressed = df_combined.groupby('icao', group_keys=False).apply(compress_df)\n",
-    "    \n",
-    "    # Sort by time\n",
-    "    df_compressed = df_compressed.sort_values('time')\n",
-    "    \n",
-    "    return df_compressed\n",
-    "\n",
-    "\n",
-    "def get_latest_aircraft_adsb_csv_df():\n",
-    "    \"\"\"Download and load the latest ADS-B CSV from GitHub releases.\"\"\"\n",
-    "    from get_latest_planequery_aircraft_release import download_latest_aircraft_adsb_csv\n",
-    "    \n",
-    "    import pandas as pd\n",
-    "    import re\n",
-    "    \n",
-    "    csv_path = download_latest_aircraft_adsb_csv()\n",
-    "    df = pd.read_csv(csv_path)\n",
-    "    df = df.fillna(\"\")\n",
-    "    \n",
-    "    # Extract start date from filename pattern: planequery_aircraft_adsb_{start_date}_{end_date}.csv\n",
-    "    match = re.search(r\"planequery_aircraft_adsb_(\\d{4}-\\d{2}-\\d{2})_\", str(csv_path))\n",
-    "    if not match:\n",
-    "        raise ValueError(f\"Could not extract date from filename: {csv_path.name}\")\n",
-    "    \n",
-    "    date_str = match.group(1)\n",
-    "    return df, date_str\n",
-    "\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e14c8363",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from datetime import datetime\n",
-    "df = load_historical_for_day(datetime(2024,1,1))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "3874ba4d",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "len(df)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "bcae50ad",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df[(df['icao'] == \"008081\")]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "50921c86",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df[df['icao'] == \"a4e1d2\"]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "8194d9aa",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df[df['r'] == \"N4131T\"]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "1e3b7aa2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "df_compressed[df_compressed['icao'].duplicated(keep=False)]\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "40613bc1",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import gzip\n",
-    "import json\n",
-    "\n",
-    "path = \"/Users/jonahgoode/Downloads/test_extract/traces/fb/trace_full_acbbfb.json\"\n",
-    "\n",
-    "with gzip.open(path, \"rt\", encoding=\"utf-8\") as f:\n",
-    "    data = json.load(f)\n",
-    "\n",
-    "print(type(data))\n",
-    "# use `data` here\n",
-    "import json\n",
-    "print(json.dumps(data, indent=2)[:2000])\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "320109b2",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# First, load the JSON to inspect its structure\n",
-    "import json\n",
-    "with open(\"/Users/jonahgoode/Documents/PlaneQuery/Other-Code/readsb-protobuf/webapp/src/db/aircrafts.json\", 'r') as f:\n",
-    "    data = json.load(f)\n",
-    "\n",
-    "# Check the structure\n",
-    "print(type(data))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "590134f4",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "data['AC97E3']"
-   ]
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": ".venv",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.12.10"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

schemas/community_submission.v1.schema.json

@@ -1,9 +1,8 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "title": "PlaneQuery Aircraft Community Submission (v1)",
+  "title": "OpenAirframes Community Submission (v1)",
   "type": "object",
   "additionalProperties": false,
-
   "properties": {
     "registration_number": {
       "type": "string",
@@ -13,11 +12,10 @@
       "type": "string",
       "pattern": "^[0-9A-F]{6}$"
     },
-    "planequery_airframe_id": {
+    "openairframes_id": {
       "type": "string",
       "minLength": 1
     },
-
     "contributor_uuid": {
       "type": "string",
       "format": "uuid"
@@ -28,14 +26,12 @@
       "maxLength": 150,
       "description": "Display name (may be blank)"
     },
-
     "creation_timestamp": {
       "type": "string",
       "format": "date-time",
       "description": "Set by the system when the submission is persisted/approved.",
       "readOnly": true
     },
-
     "start_date": {
       "type": "string",
       "format": "date",
@@ -48,7 +44,6 @@
       "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
       "description": "Optional end date for when this submission's tags are valid (ISO 8601, e.g., 2025-07-03)."
     },
-
     "tags": {
       "type": "object",
       "description": "Additional community-defined tags as key/value pairs (values may be scalar, array, or object).",
@@ -56,38 +51,63 @@
         "type": "string",
         "pattern": "^[a-z][a-z0-9_]{0,63}$"
       },
-      "additionalProperties": { "$ref": "#/$defs/tagValue" }
+      "additionalProperties": {
+        "$ref": "#/$defs/tagValue"
+      },
+      "properties": {}
     }
   },
-
   "allOf": [
     {
       "anyOf": [
-        { "required": ["registration_number"] },
-        { "required": ["transponder_code_hex"] },
-        { "required": ["planequery_airframe_id"] }
+        {
+          "required": [
+            "registration_number"
+          ]
+        },
+        {
+          "required": [
+            "transponder_code_hex"
+          ]
+        },
+        {
+          "required": [
+            "openairframes_id"
+          ]
+        }
       ]
     }
   ],
-
   "$defs": {
     "tagScalar": {
-      "type": ["string", "number", "integer", "boolean", "null"]
+      "type": [
+        "string",
+        "number",
+        "integer",
+        "boolean",
+        "null"
+      ]
     },
     "tagValue": {
       "anyOf": [
-        { "$ref": "#/$defs/tagScalar" },
+        {
+          "$ref": "#/$defs/tagScalar"
+        },
         {
           "type": "array",
           "maxItems": 50,
-          "items": { "$ref": "#/$defs/tagScalar" }
+          "items": {
+            "$ref": "#/$defs/tagScalar"
+          }
         },
         {
           "type": "object",
           "maxProperties": 50,
-          "additionalProperties": { "$ref": "#/$defs/tagScalar" }
+          "additionalProperties": {
+            "$ref": "#/$defs/tagScalar"
+          }
         }
       ]
     }
   }
-}
+}

src/adsb/combine_chunks_to_csv.py

@@ -27,7 +27,7 @@ from src.adsb.compress_adsb_to_aircraft_data import compress_multi_icao_df, COLU
 
 
 DEFAULT_CHUNK_DIR = os.path.join(OUTPUT_DIR, "adsb_chunks")
-FINAL_OUTPUT_DIR = "./data/planequery_aircraft"
+FINAL_OUTPUT_DIR = "./data/openairframes"
 os.makedirs(FINAL_OUTPUT_DIR, exist_ok=True)
 
 
@@ -85,12 +85,12 @@ def combine_compressed_chunks(compressed_dfs: list[pl.DataFrame]) -> pl.DataFram
 
 def download_and_merge_base_release(compressed_df: pl.DataFrame) -> pl.DataFrame:
     """Download base release and merge with new data."""
-    from src.get_latest_planequery_aircraft_release import download_latest_aircraft_adsb_csv
+    from src.get_latest_release import download_latest_aircraft_adsb_csv
     
     print("Downloading base ADS-B release...")
     try:
         base_path = download_latest_aircraft_adsb_csv(
-            output_dir="./data/planequery_aircraft_base"
+            output_dir="./data/openairframes_base"
         )
         print(f"Download returned: {base_path}")
         
@@ -176,10 +176,10 @@ def main():
     if args.start_date and args.end_date:
         # Historical mode
         output_id = f"{args.start_date}_{args.end_date}"
-        output_filename = f"planequery_aircraft_adsb_{args.start_date}_{args.end_date}.csv"
+        output_filename = f"openairframes_adsb_{args.start_date}_{args.end_date}.csv"
         print(f"Combining chunks for date range: {args.start_date} to {args.end_date}")
     else:
-        # Daily mode
+        # Daily mode - use same date for start and end
         if args.date:
             target_day = datetime.strptime(args.date, "%Y-%m-%d")
         else:
@@ -187,7 +187,7 @@ def main():
         
         date_str = target_day.strftime("%Y-%m-%d")
         output_id = date_str
-        output_filename = f"planequery_aircraft_adsb_{date_str}.csv"
+        output_filename = f"openairframes_adsb_{date_str}_{date_str}.csv"
         print(f"Combining chunks for {date_str}")
     
     chunks_dir = args.chunks_dir

src/adsb/compress_adsb_to_aircraft_data.py

@@ -253,7 +253,7 @@ def concat_compressed_dfs(df_base, df_new):
 
 def get_latest_aircraft_adsb_csv_df():
     """Download and load the latest ADS-B CSV from GitHub releases."""
-    from get_latest_planequery_aircraft_release import download_latest_aircraft_adsb_csv
+    from get_latest_release import download_latest_aircraft_adsb_csv
     import re
     
     csv_path = download_latest_aircraft_adsb_csv()
@@ -264,8 +264,8 @@ 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: planequery_aircraft_adsb_{start_date}_{end_date}.csv
-    match = re.search(r"planequery_aircraft_adsb_(\d{4}-\d{2}-\d{2})_", str(csv_path))
+    # Extract start date from filename pattern: openairframes_adsb_{start_date}_{end_date}.csv
+    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/adsb/download_adsb_data_to_parquet.py

@@ -82,7 +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"
-    PATTERN = f"{version_date}-planes-readsb-prod-0"
+    # Match exact release name, exclude tmp releases
+    PATTERN = rf"^{re.escape(version_date)}-planes-readsb-prod-\d+$"
     releases = []
     page = 1
     
@@ -187,19 +188,23 @@ def extract_split_archive(file_paths: list, extract_dir: str) -> bool:
         cat_proc = subprocess.Popen(
             ["cat"] + file_paths,
             stdout=subprocess.PIPE,
-            stderr=subprocess.DEVNULL
+            stderr=subprocess.PIPE
         )
         tar_cmd = ["tar", "xf", "-", "-C", extract_dir, "--strip-components=1"]
-        subprocess.run(
+        result = subprocess.run(
             tar_cmd,
             stdin=cat_proc.stdout,
-            stdout=subprocess.DEVNULL,
-            stderr=subprocess.DEVNULL,
+            stdout=subprocess.PIPE,
+            stderr=subprocess.PIPE,
             check=True
         )
         cat_proc.stdout.close()
+        cat_stderr = cat_proc.stderr.read().decode() if cat_proc.stderr else ""
         cat_proc.wait()
         
+        if cat_stderr:
+            print(f"cat stderr: {cat_stderr}")
+        
         print(f"Successfully extracted archive to {extract_dir}")
         
         # Delete tar files immediately after extraction
@@ -217,7 +222,10 @@ def extract_split_archive(file_paths: list, extract_dir: str) -> bool:
         
         return True
     except subprocess.CalledProcessError as e:
+        stderr_output = e.stderr.decode() if e.stderr else ""
         print(f"Failed to extract split archive: {e}")
+        if stderr_output:
+            print(f"tar stderr: {stderr_output}")
         return False
 
 

src/adsb/reducer.py

@@ -76,8 +76,8 @@ def main():
     print(f"After dedup: {df_accumulated.height} rows")
 
     # Write and upload final result
-    output_name = f"planequery_aircraft_adsb_{global_start}_{global_end}.csv.gz"
-    csv_output = Path(f"/tmp/planequery_aircraft_adsb_{global_start}_{global_end}.csv")
+    output_name = f"openairframes_adsb_{global_start}_{global_end}.csv.gz"
+    csv_output = Path(f"/tmp/openairframes_adsb_{global_start}_{global_end}.csv")
     gz_output = Path(f"/tmp/{output_name}")
     
     df_accumulated.write_csv(csv_output)

src/contributions/approve_submission.py

@@ -21,13 +21,13 @@ import urllib.request
 import urllib.error
 from datetime import datetime, timezone
 
-from .schema import extract_json_from_issue_body, extract_contributor_name_from_issue_body, parse_and_validate, get_latest_schema_version, load_schema
+from .schema import extract_json_from_issue_body, extract_contributor_name_from_issue_body, parse_and_validate, load_schema, SCHEMAS_DIR
 from .contributor import (
     generate_contributor_uuid,
     generate_submission_filename,
     compute_content_hash,
 )
-from .update_schema import generate_new_schema, check_for_new_tags, get_existing_tag_definitions
+from .update_schema import generate_updated_schema, check_for_new_tags, get_existing_tag_definitions
 from .read_community_data import build_tag_type_registry
 
 
@@ -100,14 +100,30 @@ def create_branch(branch_name: str, sha: str) -> None:
             raise
 
 
+def get_file_sha(path: str, branch: str) -> str | None:
+    """Get the SHA of an existing file, or None if it doesn't exist."""
+    try:
+        response = github_api_request("GET", f"/contents/{path}?ref={branch}")
+        return response.get("sha")
+    except Exception:
+        return None
+
+
 def create_or_update_file(path: str, content: str, message: str, branch: str) -> None:
     """Create or update a file in the repository."""
     content_b64 = base64.b64encode(content.encode()).decode()
-    github_api_request("PUT", f"/contents/{path}", {
+    payload = {
         "message": message,
         "content": content_b64,
         "branch": branch,
-    })
+    }
+    
+    # If file exists, we need to include its SHA to update it
+    sha = get_file_sha(path, branch)
+    if sha:
+        payload["sha"] = sha
+    
+    github_api_request("PUT", f"/contents/{path}", payload)
 
 
 def create_pull_request(title: str, head: str, base: str, body: str) -> dict:
@@ -190,17 +206,15 @@ def process_submission(
     commit_message = f"Add community submission from @{author_username} (closes #{issue_number})"
     create_or_update_file(file_path, content_json, commit_message, branch_name)
     
-    # Update schema with any new tags (creates new version if needed)
+    # Update schema with any new tags (modifies v1 in place)
     schema_updated = False
-    new_version = None
     new_tags = []
     try:
         # Build tag registry from new submissions
         tag_registry = build_tag_type_registry(submissions)
         
         # Get current schema and merge existing tags
-        current_version = get_latest_schema_version()
-        current_schema = load_schema(current_version)
+        current_schema = load_schema()
         existing_tags = get_existing_tag_definitions(current_schema)
         
         # Merge existing tags into registry
@@ -213,15 +227,14 @@ def process_submission(
         new_tags = check_for_new_tags(tag_registry, current_schema)
         
         if new_tags:
-            # Generate new schema version
-            new_version = current_version + 1
-            new_schema = generate_new_schema(current_schema, tag_registry, new_version)
-            schema_json = json.dumps(new_schema, indent=2) + "\n"
+            # Generate updated schema
+            updated_schema = generate_updated_schema(current_schema, tag_registry)
+            schema_json = json.dumps(updated_schema, indent=2) + "\n"
             
             create_or_update_file(
-                f"schemas/community_submission.v{new_version}.schema.json",
+                "schemas/community_submission.v1.schema.json",
                 schema_json,
-                f"Create schema v{new_version} with new tags: {', '.join(new_tags)}",
+                f"Update schema with new tags: {', '.join(new_tags)}",
                 branch_name
             )
             schema_updated = True
@@ -231,7 +244,7 @@ def process_submission(
     # Create PR
     schema_note = ""
     if schema_updated:
-        schema_note = f"\n**Schema Updated:** Created v{new_version} with new tags: `{', '.join(new_tags)}`\n"
+        schema_note = f"\n**Schema Updated:** Added new tags: `{', '.join(new_tags)}`\n"
     
     pr_body = f"""## Community Submission
 

src/contributions/create_daily_community_release.py

@@ -17,7 +17,7 @@ import pandas as pd
 
 
 COMMUNITY_DIR = Path(__file__).parent.parent.parent / "community"
-OUT_ROOT = Path("data/planequery_aircraft")
+OUT_ROOT = Path("data/openairframes")
 
 
 def read_all_submissions(community_dir: Path) -> list[dict]:
@@ -47,7 +47,7 @@ def submissions_to_dataframe(submissions: list[dict]) -> pd.DataFrame:
     - creation_timestamp (first)
     - transponder_code_hex
     - registration_number  
-    - planequery_airframe_id
+    - openairframes_id
     - contributor_name
     - [other columns alphabetically]
     - contributor_uuid (last)
@@ -62,7 +62,7 @@ def submissions_to_dataframe(submissions: list[dict]) -> pd.DataFrame:
         "creation_timestamp",
         "transponder_code_hex",
         "registration_number",
-        "planequery_airframe_id",
+        "openairframes_id",
         "contributor_name",
         "contributor_uuid",
     ]
@@ -78,7 +78,7 @@ def submissions_to_dataframe(submissions: list[dict]) -> pd.DataFrame:
         "creation_timestamp",
         "transponder_code_hex",
         "registration_number",
-        "planequery_airframe_id",
+        "openairframes_id",
         "contributor_name",
     ]
     last_cols = ["contributor_uuid"]
@@ -108,7 +108,7 @@ def main():
             "creation_timestamp",
             "transponder_code_hex",
             "registration_number",
-            "planequery_airframe_id",
+            "openairframes_id",
             "contributor_name",
             "tags",
             "contributor_uuid",
@@ -127,7 +127,7 @@ def main():
     
     # Output
     OUT_ROOT.mkdir(parents=True, exist_ok=True)
-    output_file = OUT_ROOT / f"planequery_aircraft_community_{start_date_str}_{date_str}.csv"
+    output_file = OUT_ROOT / f"openairframes_community_{start_date_str}_{date_str}.csv"
     
     df.to_csv(output_file, index=False)
     

src/contributions/read_community_data.py

@@ -112,8 +112,8 @@ def group_by_identifier(submissions: list[dict]) -> dict[str, list[dict]]:
             key = f"reg:{submission['registration_number']}"
         elif "transponder_code_hex" in submission:
             key = f"icao:{submission['transponder_code_hex']}"
-        elif "planequery_airframe_id" in submission:
-            key = f"id:{submission['planequery_airframe_id']}"
+        elif "openairframes_id" in submission:
+            key = f"id:{submission['openairframes_id']}"
         else:
             key = "_unknown"
         

src/contributions/regenerate_pr_schema.py

@@ -1,8 +1,8 @@
 #!/usr/bin/env python3
 """
 Regenerate schema for a PR branch after main has been merged in.
-This script looks at the submission files in this branch and generates
-an updated schema version if new tags were introduced.
+This script looks at the submission files in this branch and updates
+the schema if new tags were introduced.
 
 Usage: python -m src.contributions.regenerate_pr_schema
 """
@@ -18,15 +18,14 @@ from src.contributions.read_community_data import read_all_submissions, build_ta
 from src.contributions.update_schema import (
     get_existing_tag_definitions,
     check_for_new_tags,
-    generate_new_schema,
+    generate_updated_schema,
 )
-from src.contributions.schema import get_latest_schema_version, load_schema, SCHEMAS_DIR
+from src.contributions.schema import load_schema, SCHEMAS_DIR
 
 
 def main():
     """Main entry point."""
-    # Get current schema version and load it
-    current_version = get_latest_schema_version()
+    # Load current schema
     current_schema = load_schema()
     
     # Get existing tag definitions from schema
@@ -46,20 +45,19 @@ def main():
     new_tags = check_for_new_tags(tag_registry, current_schema)
     
     if new_tags:
-        # Generate new schema version
-        new_version = current_version + 1
         print(f"Found new tags: {new_tags}")
-        print(f"Generating schema v{new_version}")
+        print("Updating schema...")
         
-        # Generate new schema with updated tag definitions
-        new_schema = generate_new_schema(current_schema, tag_registry, new_version)
+        # Generate updated schema
+        updated_schema = generate_updated_schema(current_schema, tag_registry)
         
-        # Write new schema version
-        new_schema_path = SCHEMAS_DIR / f"community_submission.v{new_version}.schema.json"
-        with open(new_schema_path, 'w') as f:
-            json.dump(new_schema, f, indent=2)
+        # Write updated schema (in place)
+        schema_path = SCHEMAS_DIR / "community_submission.v1.schema.json"
+        with open(schema_path, 'w') as f:
+            json.dump(updated_schema, f, indent=2)
+            f.write("\n")
         
-        print(f"Created {new_schema_path}")
+        print(f"Updated {schema_path}")
     else:
         print("No new tags found, schema is up to date")
 

src/contributions/schema.py

@@ -111,7 +111,7 @@ def download_github_attachment(url: str) -> str | None:
     import urllib.error
     
     try:
-        req = urllib.request.Request(url, headers={"User-Agent": "PlaneQuery-Bot"})
+        req = urllib.request.Request(url, headers={"User-Agent": "OpenAirframes-Bot"})
         with urllib.request.urlopen(req, timeout=30) as response:
             return response.read().decode("utf-8")
     except (urllib.error.URLError, urllib.error.HTTPError, UnicodeDecodeError) as e:

src/contributions/update_schema.py

@@ -40,40 +40,27 @@ def type_name_to_json_schema(type_name: str) -> dict:
     return type_map.get(type_name, {"$ref": "#/$defs/tagValue"})
 
 
-def generate_new_schema(base_schema: dict, tag_registry: dict[str, str], new_version: int) -> dict:
+def generate_updated_schema(base_schema: dict, tag_registry: dict[str, str]) -> dict:
     """
-    Generate a new schema version with explicit tag definitions.
+    Generate an updated schema with explicit tag definitions.
     
     Args:
-        base_schema: The current schema to base the new one on
+        base_schema: The current schema to update
         tag_registry: Dict mapping tag name to type name
-        new_version: The new version number
         
     Returns:
-        Complete new schema dict
+        Updated schema dict
     """
     schema = json.loads(json.dumps(base_schema))  # Deep copy
     
-    # Update title with new version
-    schema["title"] = f"PlaneQuery Aircraft Community Submission (v{new_version})"
-    
     # Build tag properties with explicit types
     tag_properties = {}
     for tag_name, type_name in sorted(tag_registry.items()):
         tag_properties[tag_name] = type_name_to_json_schema(type_name)
     
-    # Update tags definition
-    schema["properties"]["tags"] = {
-        "type": "object",
-        "description": "Community-defined tags. New tags can be added, but must use consistent types.",
-        "propertyNames": {
-            "type": "string",
-            "pattern": "^[a-z][a-z0-9_]{0,63}$"
-        },
-        "properties": tag_properties,
-        # Still allow additional properties for new tags
-        "additionalProperties": {"$ref": "#/$defs/tagValue"}
-    }
+    # Only add/update the properties key within tags, preserve everything else
+    if "properties" in schema and "tags" in schema["properties"]:
+        schema["properties"]["tags"]["properties"] = tag_properties
     
     return schema
 
@@ -89,57 +76,55 @@ def check_for_new_tags(tag_registry: dict[str, str], current_schema: dict) -> li
     return [tag for tag in tag_registry if tag not in existing_tags]
 
 
-def create_new_schema_version(
+def update_schema_file(
     tag_registry: dict[str, str],
     check_only: bool = False
-) -> tuple[int | None, list[str]]:
+) -> tuple[bool, list[str]]:
     """
-    Create a new schema version if there are new tags.
+    Update the v1 schema file with new tag definitions.
     
     Args:
         tag_registry: Dict mapping tag name to type name
         check_only: If True, only check if update is needed without writing
         
     Returns:
-        Tuple of (new_version or None if no update, list_of_new_tags)
+        Tuple of (was_updated, list_of_new_tags)
     """
-    current_version = get_latest_schema_version()
-    current_schema = load_schema(current_version)
+    current_schema = load_schema()
     
     # Find new tags
     new_tags = check_for_new_tags(tag_registry, current_schema)
     
     if not new_tags:
-        return None, []
+        return False, []
     
     if check_only:
-        return current_version + 1, new_tags
+        return True, new_tags
     
-    # Generate and write new schema
-    new_version = current_version + 1
-    new_schema = generate_new_schema(current_schema, tag_registry, new_version)
-    new_schema_path = get_schema_path(new_version)
+    # Generate and write updated schema (in place)
+    updated_schema = generate_updated_schema(current_schema, tag_registry)
+    schema_path = get_schema_path()
     
-    with open(new_schema_path, "w") as f:
-        json.dump(new_schema, f, indent=2)
+    with open(schema_path, "w") as f:
+        json.dump(updated_schema, f, indent=2)
         f.write("\n")
     
-    return new_version, new_tags
+    return True, new_tags
 
 
-def update_schema_from_submissions(check_only: bool = False) -> tuple[int | None, list[str]]:
+def update_schema_from_submissions(check_only: bool = False) -> tuple[bool, list[str]]:
     """
-    Read all submissions and create a new schema version if needed.
+    Read all submissions and update the schema if needed.
     
     Args:
         check_only: If True, only check if update is needed without writing
         
     Returns:
-        Tuple of (new_version or None if no update, list_of_new_tags)
+        Tuple of (was_updated, list_of_new_tags)
     """
     submissions = read_all_submissions()
     tag_registry = build_tag_type_registry(submissions)
-    return create_new_schema_version(tag_registry, check_only)
+    return update_schema_file(tag_registry, check_only)
 
 
 def main():
@@ -148,21 +133,21 @@ def main():
     
     args = parser.parse_args()
     
-    new_version, new_tags = update_schema_from_submissions(check_only=args.check)
+    was_updated, new_tags = update_schema_from_submissions(check_only=args.check)
     
     if args.check:
-        if new_version:
-            print(f"Schema update needed -> v{new_version}. New tags: {', '.join(new_tags)}")
+        if was_updated:
+            print(f"Schema update needed. New tags: {', '.join(new_tags)}")
             sys.exit(1)
         else:
-            print(f"Schema is up to date (v{get_latest_schema_version()})")
+            print("Schema is up to date")
             sys.exit(0)
     else:
-        if new_version:
-            print(f"Created {get_schema_path(new_version)}")
+        if was_updated:
+            print(f"Updated {get_schema_path()}")
             print(f"Added tags: {', '.join(new_tags)}")
         else:
-            print(f"No update needed (v{get_latest_schema_version()})")
+            print("No update needed")
 
 
 if __name__ == "__main__":

src/create_daily_adsb_release.py

@@ -74,10 +74,10 @@ if __name__ == '__main__':
             )
 
     # Save the result
-    OUT_ROOT = Path("data/planequery_aircraft")
+    OUT_ROOT = Path("data/openairframes")
     OUT_ROOT.mkdir(parents=True, exist_ok=True)
 
-    output_file = OUT_ROOT / f"planequery_aircraft_adsb_{start_date_str}_{date_str}.csv"
+    output_file = OUT_ROOT / f"openairframes_adsb_{start_date_str}_{date_str}.csv"
     df_combined.write_csv(output_file)
 
     print(f"Saved: {output_file}")

src/create_daily_faa_release.py

@@ -22,12 +22,19 @@ if not zip_path.exists():
         body = r.read()
         zip_path.write_bytes(body)
 
-OUT_ROOT = Path("data/planequery_aircraft")
+OUT_ROOT = Path("data/openairframes")
 OUT_ROOT.mkdir(parents=True, exist_ok=True)
 from derive_from_faa_master_txt import convert_faa_master_txt_to_df, concat_faa_historical_df
-from get_latest_planequery_aircraft_release import get_latest_aircraft_faa_csv_df
+from get_latest_release import get_latest_aircraft_faa_csv_df
 df_new = convert_faa_master_txt_to_df(zip_path, date_str)
-df_base, start_date_str = get_latest_aircraft_faa_csv_df()
-df_base = concat_faa_historical_df(df_base, df_new)
-assert df_base['download_date'].is_monotonic_increasing, "download_date is not monotonic increasing"
-df_base.to_csv(OUT_ROOT / f"planequery_aircraft_faa_{start_date_str}_{date_str}.csv", index=False)
+
+try:
+    df_base, start_date_str = get_latest_aircraft_faa_csv_df()
+    df_base = concat_faa_historical_df(df_base, df_new)
+    assert df_base['download_date'].is_monotonic_increasing, "download_date is not monotonic increasing"
+except Exception as e:
+    print(f"No existing FAA release found, using only new data: {e}")
+    df_base = df_new
+    start_date_str = date_str
+
+df_base.to_csv(OUT_ROOT / f"openairframes_faa_{start_date_str}_{date_str}.csv", index=False)

src/derive_from_faa_master_txt.py

@@ -29,8 +29,8 @@ def convert_faa_master_txt_to_df(zip_path: Path, date: str):
     certification = pd.json_normalize(df["certification"].where(df["certification"].notna(), {})).add_prefix("certificate_")
     df = df.drop(columns="certification").join(certification)
     
-    # Create planequery_airframe_id
-    df["planequery_airframe_id"] = (
+    # Create openairframes_id
+    df["openairframes_id"] = (
         normalize(df["aircraft_manufacturer"])
         + "|"
         + normalize(df["aircraft_model"])
@@ -38,11 +38,11 @@ def convert_faa_master_txt_to_df(zip_path: Path, date: str):
         + normalize(df["serial_number"])
     )
     
-    # Move planequery_airframe_id to come after registration_number
+    # Move openairframes_id to come after registration_number
     cols = df.columns.tolist()
-    cols.remove("planequery_airframe_id")
+    cols.remove("openairframes_id")
     reg_idx = cols.index("registration_number")
-    cols.insert(reg_idx + 1, "planequery_airframe_id")
+    cols.insert(reg_idx + 1, "openairframes_id")
     df = df[cols]
     
     # Convert all NaN to empty strings

src/get_latest_release.py

@@ -9,7 +9,7 @@ import urllib.error
 import json
 
 
-REPO = "PlaneQuery/planequery-aircraft"
+REPO = "PlaneQuery/openairframes"
 LATEST_RELEASE_URL = f"https://api.github.com/repos/{REPO}/releases/latest"
 
 
@@ -31,7 +31,7 @@ def get_latest_release_assets(repo: str = REPO, github_token: Optional[str] = No
     url = f"https://api.github.com/repos/{repo}/releases/latest"
     headers = {
         "Accept": "application/vnd.github+json",
-        "User-Agent": "planequery-aircraft-downloader/1.0",
+        "User-Agent": "openairframes-downloader/1.0",
     }
     if github_token:
         headers["Authorization"] = f"Bearer {github_token}"
@@ -80,7 +80,7 @@ def download_asset(asset: ReleaseAsset, out_path: Path, github_token: Optional[s
     out_path.parent.mkdir(parents=True, exist_ok=True)
 
     headers = {
-        "User-Agent": "planequery-aircraft-downloader/1.0",
+        "User-Agent": "openairframes-downloader/1.0",
         "Accept": "application/octet-stream",
     }
     if github_token:
@@ -109,7 +109,7 @@ def download_latest_aircraft_csv(
     repo: str = REPO,
 ) -> Path:
     """
-    Download the latest planequery_aircraft_faa_*.csv file from the latest GitHub release.
+    Download the latest openairframes_faa_*.csv file from the latest GitHub release.
 
     Args:
         output_dir: Directory to save the downloaded file (default: "downloads")
@@ -121,10 +121,10 @@ def download_latest_aircraft_csv(
     """
     assets = get_latest_release_assets(repo, github_token=github_token)
     try:
-        asset = pick_asset(assets, name_regex=r"^planequery_aircraft_faa_.*\.csv$")
+        asset = pick_asset(assets, name_regex=r"^openairframes_faa_.*\.csv$")
     except FileNotFoundError:
         # Fallback to old naming pattern
-        asset = pick_asset(assets, name_regex=r"^planequery_aircraft_\d{4}-\d{2}-\d{2}_.*\.csv$")
+        asset = pick_asset(assets, name_regex=r"^openairframes_\d{4}-\d{2}-\d{2}_.*\.csv$")
     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
@@ -136,11 +136,11 @@ def get_latest_aircraft_faa_csv_df():
            'unique_regulatory_id': str, 
            'registrant_county': str})
     df = df.fillna("")
-    # Extract start date from filename pattern: planequery_aircraft_faa_{start_date}_{end_date}.csv
-    match = re.search(r"planequery_aircraft_faa_(\d{4}-\d{2}-\d{2})_", str(csv_path))
+    # Extract start date from filename pattern: openairframes_faa_{start_date}_{end_date}.csv
+    match = re.search(r"openairframes_faa_(\d{4}-\d{2}-\d{2})_", str(csv_path))
     if not match:
-        # Fallback to old naming pattern: planequery_aircraft_{start_date}_{end_date}.csv
-        match = re.search(r"planequery_aircraft_(\d{4}-\d{2}-\d{2})_", str(csv_path))
+        # Fallback to old naming pattern: openairframes_{start_date}_{end_date}.csv
+        match = re.search(r"openairframes_(\d{4}-\d{2}-\d{2})_", str(csv_path))
     if not match:
         raise ValueError(f"Could not extract date from filename: {csv_path.name}")
     
@@ -154,7 +154,7 @@ def download_latest_aircraft_adsb_csv(
     repo: str = REPO,
 ) -> Path:
     """
-    Download the latest planequery_aircraft_adsb_*.csv file from the latest GitHub release.
+    Download the latest openairframes_adsb_*.csv file from the latest GitHub release.
 
     Args:
         output_dir: Directory to save the downloaded file (default: "downloads")
@@ -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"^planequery_aircraft_adsb_.*\.csv$")
+    asset = pick_asset(assets, name_regex=r"^openairframes_adsb_.*\.csv$")
     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
@@ -176,8 +176,8 @@ 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: planequery_aircraft_adsb_{start_date}_{end_date}.csv
-    match = re.search(r"planequery_aircraft_adsb_(\d{4}-\d{2}-\d{2})_", str(csv_path))
+    # Extract start date from filename pattern: openairframes_adsb_{start_date}_{end_date}.csv
+    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}")