blog-post-validation.yml

name: Blog Post Validation

on:
  pull_request:
    paths:
      - "blog/posts/*.md"
      - "blog/_template.md"

permissions:
  contents: read

jobs:
  validate-blog-posts:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Collect changed blog posts
        env:
          BASE_SHA: ${{ github.event.pull_request.base.sha }}
          HEAD_SHA: ${{ github.event.pull_request.head.sha }}
        run: |
          git diff --name-only "$BASE_SHA" "$HEAD_SHA" -- 'blog/posts/*.md' > changed_blog_posts.txt
          echo "Changed posts:"
          cat changed_blog_posts.txt || true

      - name: Validate metadata and local links
        run: |
          python - <<'PY'
          from pathlib import Path
          from datetime import datetime
          import re
          import sys

          changed_file_list = Path("changed_blog_posts.txt")
          changed_files = []
          if changed_file_list.exists():
              changed_files = [line.strip() for line in changed_file_list.read_text(encoding="utf-8").splitlines() if line.strip()]

          if not changed_files:
              print("No changed blog post files detected.")
              raise SystemExit(0)

          required_fields = ["title", "author", "date", "tags", "summary"]
          all_errors = []

          for rel_path in changed_files:
              path = Path(rel_path)
              if not path.exists():
                  continue

              text = path.read_text(encoding="utf-8")
              lines = text.splitlines()
              errors = []

              if not lines or lines[0].strip() != "---":
                  errors.append("Missing YAML front matter opening delimiter '---'.")
              else:
                  end_idx = None
                  for idx in range(1, len(lines)):
                      if lines[idx].strip() == "---":
                          end_idx = idx
                          break
                  if end_idx is None:
                      errors.append("Missing YAML front matter closing delimiter '---'.")
                      front_matter_lines = []
                  else:
                      front_matter_lines = lines[1:end_idx]

                  if end_idx is not None:
                      front_matter_text = "\n".join(front_matter_lines)
                      for field in required_fields:
                          if not re.search(rf"(?m)^{field}\s*:", front_matter_text):
                              errors.append(f"Missing required metadata field: {field}")

                      date_match = re.search(r'(?m)^date\s*:\s*"?(.*?)"?\s*$', front_matter_text)
                      if date_match:
                          date_value = date_match.group(1).strip()
                          try:
                              post_date = datetime.strptime(date_value, "%Y-%m-%d").date()
                              if post_date > datetime.now().date():
                                  errors.append("Date cannot be in the future.")
                          except ValueError:
                              errors.append("Invalid date format. Expected YYYY-MM-DD.")

              for link in re.findall(r"\[[^\]]+\]\(([^)]+)\)", text):
                  target = link.strip()
                  if not target or target.startswith(("http://", "https://", "mailto:", "#")):
                      continue
                  target = target.split("#", 1)[0].split("?", 1)[0]
                  if not target:
                      continue
                  resolved = (path.parent / target).resolve()
                  if not resolved.exists():
                      errors.append(f"Broken local link: {link}")

              if errors:
                  all_errors.append(f"{rel_path}:")
                  all_errors.extend([f"  - {err}" for err in errors])

          if all_errors:
              print("Validation failed:\n")
              print("\n".join(all_errors))
              sys.exit(1)

          print("All changed blog posts passed metadata and local link validation.")
          PY