csv_linter.yml

name: CSV Linter and Trailing Whitespaces

on:
  push:
  pull_request:

jobs:
  lint_and_check_trailing_whitespaces:
    runs-on: ubuntu-latest
    steps:
    - uses: actions/checkout@v3
    
    - name: Set up Python
      uses: actions/setup-python@v2
      with:
        python-version: '3.8'
    
    - name: Install dependencies
      run: |
        python -m pip install --upgrade pip
        python -m pip install csvkit
    
    - name: Validate CSV structure
      run: |
        echo "Checking CSV structure..."
        if ! csvclean -n prompts.csv 2>&1 | tee /tmp/csv_errors.log; then
          echo "::error::CSV validation failed"
          cat /tmp/csv_errors.log
          exit 1
        fi
    
    - name: Check CSV format
      run: |
        echo "Checking CSV format..."
        if ! python -c '
        import csv
        with open("prompts.csv", "r", encoding="utf-8") as f:
            reader = csv.reader(f)
            headers = next(reader)
            if headers != ["act", "prompt"]:
                print("Error: CSV headers must be exactly [act, prompt]")
                exit(1)
            for row_num, row in enumerate(reader, 2):
                if len(row) != 2:
                    print(f"Error: Row {row_num} has {len(row)} columns, expected 2")
                    exit(1)
                if not row[0] or not row[1]:
                    print(f"Error: Row {row_num} has empty values")
                    exit(1)
        '; then
          echo "::error::CSV format check failed"
          exit 1
        fi
    
    - name: Check Trailing Whitespaces
      run: |
        echo "Checking for trailing whitespaces..."
        if grep -q "[[:space:]]$" prompts.csv; then
          echo "::error::Found trailing whitespaces in prompts.csv"
          grep -n "[[:space:]]$" prompts.csv | while read -r line; do
            echo "Line with trailing whitespace: $line"
          done
          exit 1
        fi
        echo "No trailing whitespaces found"
    
    - name: Check for UTF-8 BOM and line endings
      run: |
        echo "Checking for UTF-8 BOM and line endings..."
        if file prompts.csv | grep -q "with BOM"; then
          echo "::error::File contains UTF-8 BOM marker"
          exit 1
        fi
        if file prompts.csv | grep -q "CRLF"; then
          echo "::error::File contains Windows-style (CRLF) line endings"
          exit 1
        fi