action.yml

name: 'ValidateX Data Quality Gate'
description: 'Gate your CI/CD pipelines based on data quality scores and validation rules using ValidateX.'
author: 'Kaviarasan Mani'
branding:
  icon: 'shield'
  color: 'purple'

inputs:
  data-path:
    description: 'Path to the data file to validate (e.g., CSV, Parquet).'
    required: true
  suite-path:
    description: 'Path to the expectation suite configuration file (YAML or JSON).'
    required: true
  engine:
    description: 'Validation engine to use (pandas or spark).'
    required: false
    default: 'pandas'
  report-path:
    description: 'Path where the generated HTML quality report should be saved.'
    required: false
  json-report-path:
    description: 'Path where the generated JSON quality report should be saved.'
    required: false

runs:
  using: 'composite'
  steps:
    - name: Install Python dependencies
      shell: bash
      run: |
        python -m pip install --upgrade pip
        if [ "${{ inputs.engine }}" = "spark" ]; then
          echo "Installing ValidateX with Spark support..."
          pip install ".[spark]" pyarrow
        else
          echo "Installing ValidateX..."
          pip install . pyarrow
        fi

    - name: Run ValidateX Data Quality Validation
      shell: bash
      run: |
        CMD="python -m validatex.cli.main validate --data \"${{ inputs.data-path }}\" --suite \"${{ inputs.suite-path }}\" --engine \"${{ inputs.engine }}\""
        if [ -n "${{ inputs.report-path }}" ]; then
          CMD="$CMD --report \"${{ inputs.report-path }}\""
        fi
        if [ -n "${{ inputs.json-report-path }}" ]; then
          CMD="$CMD --json-report \"${{ inputs.json-report-path }}\""
        fi
        echo "Executing: $CMD"
        eval $CMD