# FreeCrawl SEO — example GitLab CI/CD pipeline
#
# Crawls your site with the headless FreeCrawl CLI, fails the pipeline when
# broken links exceed BROKEN_LINK_THRESHOLD, validates the sitemap, and stores
# the crawl as a job artifact. Adapt TARGET_URL and the thresholds.
#
# Save this as `.gitlab-ci.yml` (or include it as a template). Schedule daily
# runs via GitLab → CI/CD → Schedules.
#
# 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.

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

stages:
  - audit

freecrawl-audit:
  stage: audit
  image: node:22
  timeout: 30 minutes
  before_script:
    - apt-get update -qq && apt-get install -y -qq git ca-certificates
    - git clone --depth 1 https://github.com/kemalai/FreeCrawl-SEO-Tool.git freecrawl
    - cd freecrawl
    # --ignore-scripts skips the Playwright browser download (the default
    # undici crawl needs no Chromium). `tsc -b apps/cli` builds the CLI AND
    # its workspace deps (shared-types → db → core) — `npm run build:cli`
    # alone would not, and the crawl would fail to resolve its imports.
    - npm ci --ignore-scripts
    - npx tsc -b apps/cli
  script:
    # --json → machine-readable summary on stdout (captured for the gate);
    # --out → full per-URL dump for the artifact. `|| true` lets the gate
    # below decide pass/fail (the CLI exits 1 on ANY 4xx/5xx on its own).
    - >-
      node apps/cli/dist/index.js "$TARGET_URL"
      --max "$MAX_URLS" --json
      --out "$CI_PROJECT_DIR/crawl.json"
      > "$CI_PROJECT_DIR/summary.json" || true
    - cat "$CI_PROJECT_DIR/summary.json"
    # Count 4xx/5xx from the summary's byStatus map (robust + cheap).
    - |
      BROKEN=$(node -e "
        const s = require('$CI_PROJECT_DIR/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 "Broken-URL count $BROKEN exceeds threshold $BROKEN_LINK_THRESHOLD" >&2
        exit 1
      fi
    # Sitemap validation is advisory — never fails the pipeline.
    - node apps/cli/dist/index.js validate-sitemap "$TARGET_URL/sitemap.xml" || true
  artifacts:
    paths:
      - crawl.json
      - summary.json
    expire_in: 30 days
    when: always