monthly_data_fetch.yml

name: Monthly Data Fetch

on:
  schedule:
    - cron: '0 0 1 * *'  # Runs at 00:00 on the first day of every month
  workflow_dispatch:  # Allows for manual triggering of the workflow

jobs:
  fetch-and-commit:
    runs-on: ubuntu-latest

    steps:
    - name: Checkout repository
      uses: actions/checkout@v4

    - name: Set up Python
      uses: actions/setup-python@v5
      with:
        python-version: '3.10'

    - name: Install Poetry
      run: |
        pip install poetry

    - name: Install dependencies
      run: poetry install

    - name: Run data fetcher script
      run: poetry run python iata_code_fetcher/fetcher.py

    - name: Sort and remove duplicates
      run: |
        cat carrier_data_full.jsonl | sort | uniq > carrier_data_full_unique.jsonl
        cat airport_data_full.jsonl | sort | uniq > airport_data_full_unique.jsonl  

    - name: Commit changes
      run: |
        git config --global user.name 'github-actions[bot]'
        git config --global user.email 'github-actions[bot]@users.noreply.github.com'
        git add carrier_data_full_unique.jsonl airport_data_full_unique.jsonl
        git commit -m 'Update unique data files [skip ci]'
        git push
      env:
        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}