commit ccefbf437c5172d7a71ff41d18f94fa18336ecc3 Author: ggman12 Date: Sat Jan 31 21:10:15 2026 -0500 Initial commit diff --git a/.github/workflows/faa-daily-release.yaml b/.github/workflows/faa-daily-release.yaml new file mode 100644 index 0000000..d97ea68 --- /dev/null +++ b/.github/workflows/faa-daily-release.yaml @@ -0,0 +1,61 @@ +name: FAA daily snapshot + release + +on: + schedule: + # 6:00pm UTC every day + - cron: "0 06 * * *" + workflow_dispatch: {} + +permissions: + contents: write + +jobs: + build-and-release: + runs-on: ubuntu-latest + + steps: + - name: Checkout + uses: actions/checkout@v4 + with: + fetch-depth: 0 + + - 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: Run snapshot script + run: | + python src/snapshot_faa.py + ls -lah data/faa_releasable + + - name: Prepare release metadata + id: meta + run: | + DATE=$(date -u +"%Y-%m-%d") + TAG="faa-${DATE}" + echo "date=$DATE" >> "$GITHUB_OUTPUT" + echo "tag=$TAG" >> "$GITHUB_OUTPUT" + echo "name=FAA ReleasableAircraft snapshot ($DATE)" >> "$GITHUB_OUTPUT" + + - name: Create GitHub Release and upload assets + uses: softprops/action-gh-release@v2 + with: + tag_name: ${{ steps.meta.outputs.tag }} + name: ${{ steps.meta.outputs.name }} + body: | + Automated daily snapshot generated at 06:00 UTC for ${{ steps.meta.outputs.date }}. + + Assets: + - ReleasableAircraft.csv + - ReleasableAircraft.zip + files: | + data/faa_releasable/ReleasableAircraft_${{ steps.meta.outputs.date }}.csv + data/faa_releasable/ReleasableAircraft_${{ steps.meta.outputs.date }}.zip + env: + GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} diff --git a/.gitignore b/.gitignore new file mode 100644 index 0000000..74326ca --- /dev/null +++ b/.gitignore @@ -0,0 +1,221 @@ +# Byte-compiled / optimized / DLL files +__pycache__/ +*.py[codz] +*$py.class + +# C extensions +*.so + +# Distribution / packaging +.Python +build/ +develop-eggs/ +dist/ +downloads/ +eggs/ +.eggs/ +lib/ +lib64/ +parts/ +sdist/ +var/ +wheels/ +share/python-wheels/ +*.egg-info/ +.installed.cfg +*.egg +MANIFEST + +# PyInstaller +# Usually these files are written by a python script from a template +# before PyInstaller builds the exe, so as to inject date/other infos into it. +*.manifest +*.spec + +# Installer logs +pip-log.txt +pip-delete-this-directory.txt + +# Unit test / coverage reports +htmlcov/ +.tox/ +.nox/ +.coverage +.coverage.* +.cache +nosetests.xml +coverage.xml +*.cover +*.py.cover +.hypothesis/ +.pytest_cache/ +cover/ + +# Translations +*.mo +*.pot + +# Django stuff: +*.log +local_settings.py +db.sqlite3 +db.sqlite3-journal + +# Flask stuff: +instance/ +.webassets-cache + +# Scrapy stuff: +.scrapy + +# Sphinx documentation +docs/_build/ + +# PyBuilder +.pybuilder/ +target/ + +# Jupyter Notebook +.ipynb_checkpoints + +# IPython +profile_default/ +ipython_config.py + +# pyenv +# For a library or package, you might want to ignore these files since the code is +# intended to run in multiple environments; otherwise, check them in: +# .python-version + +# pipenv +# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. +# However, in case of collaboration, if having platform-specific dependencies or dependencies +# having no cross-platform support, pipenv may install dependencies that don't work, or not +# install all needed dependencies. +# Pipfile.lock + +# UV +# Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +# uv.lock + +# poetry +# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. +# This is especially recommended for binary packages to ensure reproducibility, and is more +# commonly ignored for libraries. +# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control +# poetry.lock +# poetry.toml + +# pdm +# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. +# pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python. +# https://pdm-project.org/en/latest/usage/project/#working-with-version-control +# pdm.lock +# pdm.toml +.pdm-python +.pdm-build/ + +# pixi +# Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control. +# pixi.lock +# Pixi creates a virtual environment in the .pixi directory, just like venv module creates one +# in the .venv directory. It is recommended not to include this directory in version control. +.pixi + +# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm +__pypackages__/ + +# Celery stuff +celerybeat-schedule +celerybeat.pid + +# Redis +*.rdb +*.aof +*.pid + +# RabbitMQ +mnesia/ +rabbitmq/ +rabbitmq-data/ + +# ActiveMQ +activemq-data/ + +# SageMath parsed files +*.sage.py + +# Environments +.env +.envrc +.venv +env/ +venv/ +ENV/ +env.bak/ +venv.bak/ + +# Spyder project settings +.spyderproject +.spyproject + +# Rope project settings +.ropeproject + +# mkdocs documentation +/site + +# mypy +.mypy_cache/ +.dmypy.json +dmypy.json + +# Pyre type checker +.pyre/ + +# pytype static type analyzer +.pytype/ + +# Cython debug symbols +cython_debug/ + +# PyCharm +# JetBrains specific template is maintained in a separate JetBrains.gitignore that can +# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore +# and can be added to the global gitignore or merged into this file. For a more nuclear +# option (not recommended) you can uncomment the following to ignore the entire idea folder. +# .idea/ + +# Abstra +# Abstra is an AI-powered process automation framework. +# Ignore directories containing user credentials, local state, and settings. +# Learn more at https://abstra.io/docs +.abstra/ + +# Visual Studio Code +# Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore +# that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore +# and can be added to the global gitignore or merged into this file. However, if you prefer, +# you could uncomment the following to ignore the entire vscode folder +# .vscode/ + +# Ruff stuff: +.ruff_cache/ + +# PyPI configuration file +.pypirc + +# Marimo +marimo/_static/ +marimo/_lsp/ +__marimo__/ + +# Streamlit +.streamlit/secrets.toml + +# Custom +data/ +.DS_Store +notebooks/ \ No newline at end of file diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..3d4fbf1 --- /dev/null +++ b/LICENSE @@ -0,0 +1,21 @@ +MIT License + +Copyright (c) 2026 PlaneQuery + +Permission is hereby granted, free of charge, to any person obtaining a copy +of this software and associated documentation files (the "Software"), to deal +in the Software without restriction, including without limitation the rights +to use, copy, modify, merge, publish, distribute, sublicense, and/or sell +copies of the Software, and to permit persons to whom the Software is +furnished to do so, subject to the following conditions: + +The above copyright notice and this permission notice shall be included in all +copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR +IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, +FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE +AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER +LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, +OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE +SOFTWARE. diff --git a/README.md b/README.md new file mode 100644 index 0000000..66aaba1 --- /dev/null +++ b/README.md @@ -0,0 +1 @@ +Downloads [`https://registry.faa.gov/database/ReleasableAircraft.zip`](https://registry.faa.gov/database/ReleasableAircraft.zip). Creates a daily GitHub Release at 06:00 UTC containing the unaltered `ReleasableAircraft.zip` and a derived CSV file with all data. The FAA database updates daily at 05:30 UTC. \ No newline at end of file diff --git a/requirements.txt b/requirements.txt new file mode 100644 index 0000000..c30c4f5 --- /dev/null +++ b/requirements.txt @@ -0,0 +1,3 @@ +faa-aircraft-registry==0.1.0 +pandas==3.0.0 + diff --git a/src/snapshot_faa.py b/src/snapshot_faa.py new file mode 100644 index 0000000..f7cf7b0 --- /dev/null +++ b/src/snapshot_faa.py @@ -0,0 +1,48 @@ +from faa_aircraft_registry import read +import pandas as pd +import zipfile +import zipfile +from pathlib import Path +from datetime import datetime, timezone +date_str = datetime.now(timezone.utc).strftime("%Y-%m-%d") + +out_dir = Path("data/faa_releasable") +out_dir.mkdir(parents=True, exist_ok=True) +zip_name = f"ReleasableAircraft_{date_str}.zip" +csv_name = f"ReleasableAircraft_{date_str}.csv" + +zip_path = out_dir / zip_name +csv_path = out_dir / csv_name + +# URL and paths +url = "https://registry.faa.gov/database/ReleasableAircraft.zip" +from urllib.request import Request, urlopen + +req = Request( + url, + headers={"User-Agent": "Mozilla/5.0"}, + method="GET", +) + +with urlopen(req, timeout=120) as r: + body = r.read() + zip_path.write_bytes(body) + +with zipfile.ZipFile(zip_path) as z: + registrations = read(z) + +df = pd.DataFrame(registrations['master'].values()) +col = "transponder_code_hex" +df = df[[col] + [c for c in df.columns if c != col]] +df = df.rename(columns={"transponder_code_hex": "icao"}) +registrant = pd.json_normalize(df["registrant"]).add_prefix("registrant_") +df = df.drop(columns="registrant").join(registrant) +df = df.rename(columns={"aircraft_type": "aircraft_type_2"}) +aircraft = pd.json_normalize(df["aircraft"]).add_prefix("aircraft_") +df = df.drop(columns="aircraft").join(aircraft) +df = df.rename(columns={"engine_type": "engine_type_2"}) +engine = pd.json_normalize(df["engine"].where(df["engine"].notna(), {})).add_prefix("engine_") +df = df.drop(columns="engine").join(engine) +df = df.sort_values(by=["icao"]) +df.to_csv(csv_path, index=False) +