# FreeCrawl SEO — example GitHub Actions workflow
#
# Crawls your site with the headless CLI on every push and on a daily
# schedule, fails the build when broken links exceed a threshold, validates
# the sitemap, and uploads the crawl as a build artifact. Adapt TARGET_URL
# and the thresholds to your site.
#
# Save this as `.github/workflows/freecrawl-audit.yml` in your own repo.
# No FreeCrawl install is required on the runner — the workflow clones the
# source and builds the CLI (plus its workspace packages) from it.
#
# See docs/ci/README.md for the CLI exit-code contract, a zero-tolerance
# (no-script) gate variant, and how to add a regression-compare job.

name: FreeCrawl SEO Audit

on:
  push:
    branches: [main]
  schedule:
    - cron: '0 4 * * *' # 04:00 UTC daily
  workflow_dispatch:

env:
  TARGET_URL: https://example.com
  MAX_URLS: '5000'
  BROKEN_LINK_THRESHOLD: '10'

jobs:
  audit:
    runs-on: ubuntu-latest
    timeout-minutes: 30
    steps:
      - uses: actions/checkout@v4
        with:
          repository: kemalai/FreeCrawl-SEO-Tool
          path: freecrawl

      - uses: actions/setup-node@v4
        with:
          node-version: '22'
          cache: npm
          cache-dependency-path: freecrawl/package-lock.json

      - name: Install + build CLI
        working-directory: freecrawl
        run: |
          # --ignore-scripts skips the Playwright browser download; the CLI's
          # default crawl is undici-based and needs no Chromium. Drop the flag
          # only if you enable JS rendering through a --config file.
          npm ci --ignore-scripts
          # Build the CLI and its workspace deps (shared-types → db → core) in
          # dependency order via project references. The heavy Electron desktop
          # build is intentionally skipped — `npm run build:cli` alone would
          # NOT build the packages the CLI imports and the crawl would fail.
          npx tsc -b apps/cli

      - name: Crawl ${{ env.TARGET_URL }}
        working-directory: freecrawl
        run: |
          # --json prints a machine-readable summary to stdout (captured for
          # the gate); --out writes the full per-URL dump for the artifact.
          # `|| true` hands pass/fail to the threshold gate below — the CLI
          # itself exits 1 on ANY 4xx/5xx (see the zero-tolerance variant in
          # docs/ci/README.md).
          node apps/cli/dist/index.js "$TARGET_URL" \
            --max "$MAX_URLS" \
            --json \
            --out "$GITHUB_WORKSPACE/crawl.json" \
            > "$GITHUB_WORKSPACE/summary.json" || true
          cat "$GITHUB_WORKSPACE/summary.json"

      - name: Gate on broken links
        run: |
          # Count 4xx/5xx from the summary's byStatus map — robust against the
          # full dump's column layout, and cheap (no multi-MB file parse).
          BROKEN=$(node -e "
            const s = require('$GITHUB_WORKSPACE/summary.json');
            const by = (s.summary && s.summary.byStatus) || {};
            let n = 0;
            for (const [code, count] of Object.entries(by)) {
              if (Number(code) >= 400) n += count;
            }
            console.log(n);
          ")
          echo "Broken-URL count: $BROKEN (threshold: $BROKEN_LINK_THRESHOLD)"
          if [ "$BROKEN" -gt "$BROKEN_LINK_THRESHOLD" ]; then
            echo "::error::Broken-URL count $BROKEN exceeds threshold $BROKEN_LINK_THRESHOLD"
            exit 1
          fi

      - name: Validate sitemap (non-blocking)
        working-directory: freecrawl
        continue-on-error: true
        run: node apps/cli/dist/index.js validate-sitemap "$TARGET_URL/sitemap.xml"

      - uses: actions/upload-artifact@v4
        if: always()
        with:
          name: freecrawl-audit-${{ github.run_number }}
          path: |
            crawl.json
            summary.json
          retention-days: 30