name: Extract Data from Content

on:
  push:
    branches:
      - master
    paths:
      - 'content/**/*.md'
      - 'scripts/*.go'
  workflow_dispatch:

# Prevent concurrent runs to avoid conflicts
concurrency:
  group: data-extraction
  cancel-in-progress: true

jobs:
  extract-data:
    name: Extract Data from Content
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: Setup Go
        uses: actions/setup-go@v5
        with:
          go-version: '1.21'

      - name: Extract highlights
        run: go run scripts/extract_highlights.go

      - name: Generate external link rank
        run: go run scripts/get_external_link_rank.go

      - name: Generate internal link graph
        run: go run scripts/get_internal_link_graph.go

      - name: Commit all data
        uses: stefanzweifel/git-auto-commit-action@v5
        with:
          commit_message: 'chore: update data from scripts'
          file_pattern: 'data/highlights.json data/externallinks.json static/link-graph.json'