# Anti-AI lint rules: textual fingerprints typical of LLM-generated content.
#
# Severity:
#   warn — build proceeds, message printed
#   fail — build aborts (exit 1) unless build.sh --skip-lint
#
# Whitelisting matches:
#   In an HTML file:        <!-- anti-ai-allow: term -->
#                            <!-- anti-ai-allow: term1, term2 -->
#   Per site (site.yaml):    anti_ai_allow:
#                              - leverage
#                              - em-dash-3-bullet
#
# Vocab matches are case-insensitive substring matches against the visible
# text of the rendered HTML (script/style/comments stripped). Pattern matches
# are regex (Python re), case-insensitive by default, against the same.
#
# Source: docs/geo-seo-guideline.md §3.6 (Wikipedia AI-content signals).

vocab:
  de:
    warn:
      - "nahtlos"
      - "robust"
      - "umfassend"
      - "ganzheitlich"
      - "fungiert als"
      - "dient als Brücke"
      - "Symbiose"
      - "im Bereich der"
      - "in der heutigen schnelllebigen"
      - "ein Meilenstein"
      - "ein Beweis für"
      - "hat Spuren hinterlassen"
      - "Es ist wichtig zu erwähnen"
      - "Es ist wichtig zu beachten"
      - "bahnbrechend"
      - "revolutionär"
    fail:
      - "in der sich entwickelnden Landschaft"
      - "Herausforderungen und Zukunftsaussichten"
      - "Herausforderungen und Perspektiven"

  en:
    warn:
      - "delve"
      - "tapestry"
      - "testament"
      - "intricate"
      - "garnered"
      - "bolstered"
      - "enduring"
      - "robust"
      - "comprehensive"
      - "meticulous"
      - "interplay"
      - "pivotal"
      - "underscore"
      - "moreover"
      - "furthermore"
      - "additionally"
      - "crucial"
      - "showcasing"
      - "highlighting"
      - "leverage"
      - "streamline"
      - "holistic"
      - "seamless"
      - "unleash"
      - "ecosystem"
      - "in the realm of"
      - "dive into"
      - "It's important to note that"
      - "It is important to note that"
      - "In this article, we'll"
    fail:
      - "in today's evolving landscape"
      - "in the ever-evolving landscape"
      - "Challenges and Future Prospects"

patterns:
  - name: em-dash-3-bullet
    description: |
      Three "Word: text — Word: text — Word: …" segments in one block.
      Classic AI bullet pattern.
    regex: '(\w[\w\s]{0,30}:\s+[^—\n]{2,80}—\s*){2,}\w[\w\s]{0,30}:'
    severity: warn

  - name: not-only-but-also
    description: '"not only X, but also Y" / "nicht nur X, sondern auch Y" filler.'
    regex: '\b(?:not only|nicht nur)\b[^.,;\n]{1,80}\b(?:but also|sondern auch)\b'
    severity: warn

  - name: as-an-ai
    description: Leftover AI self-disclosure.
    regex: '\b(?:as an? (?:AI|language model)|als (?:eine?|eine\s+)?(?:KI|Sprachmodell))\b'
    severity: fail