name: Docs CI

# Lightweight checks for documentation changes. Intentionally MINIMAL (Nathan,
# 2026-07-18): NOT a Markdown style linter — no line length, heading levels, list
# markers, or cosmetic rules. It runs only two things, and only when docs change:
#   1. critical_markdown_check.py — flags ONLY a rendering break (a link whose
#      destination token is split across a newline, or an unclosed inline link).
#   2. lychee link check — flags broken/dead links (informational, non-blocking).
#
# Runs on docs paths only; does NOT gate code PRs. This job is NOT a required
# status check — it's an informational quality gate; promote it via the ruleset
# later if desired.
#
# SECURITY: changed filenames on a fork PR are UNTRUSTED. They are never
# interpolated into `run:` source via ${{ }} (which Bash would re-evaluate,
# executing $(...) in a crafted filename). The file list is passed through an
# `env:` variable and referenced as "$DOC_FILES", and lychee is handed a FIXED
# glob rather than an attacker-controlled explicit list.

on:
  pull_request:
    branches: [master]
    paths:
      - '**/*.md'
      - '**/*.markdown'
      - '**/*.rst'
      - 'docs/**'
      - 'CHANGELOG*'
      - '**/README*'
  push:
    branches: [master]
    paths:
      - '**/*.md'
      - '**/*.markdown'
      - '**/*.rst'
      - 'docs/**'
      - 'CHANGELOG*'
      - '**/README*'

# Read-only; no secrets needed. Fork PRs already get a read-only token, but pin it.
permissions:
  contents: read

jobs:
  docs-ci:
    runs-on: ubuntu-latest
    timeout-minutes: 8
    steps:
      - uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.12'

      - name: Resolve changed doc files (NUL-safe, untrusted names)
        id: docs
        env:
          BASE_SHA: ${{ github.event.pull_request.base.sha }}
          HEAD_SHA: ${{ github.event.pull_request.head.sha }}
        run: |
          set -uo pipefail
          # Compute the changed markdown/doc files and write them to a file, ONE PER
          # LINE. We never echo untrusted names into another shell; downstream steps
          # read this file. Fall back to all tracked docs if the diff can't compute.
          if [ -n "${BASE_SHA:-}" ] && [ -n "${HEAD_SHA:-}" ]; then
            git fetch --no-tags --depth=1 origin "$BASE_SHA" 2>/dev/null || git fetch --no-tags origin master || true
            RANGE="$BASE_SHA...$HEAD_SHA"
          else
            RANGE="${{ github.event.before }}...${{ github.sha }}"
          fi
          : > doc_files.txt
          if CHANGED="$(git diff --name-only --no-renames --diff-filter=ACMR "$RANGE" 2>/dev/null)"; then
            printf '%s\n' "$CHANGED" | grep -Ei '\.(md|markdown|rst)$' > doc_files.txt || true
          fi
          if [ ! -s doc_files.txt ]; then
            git ls-files '*.md' '*.markdown' '*.rst' > doc_files.txt 2>/dev/null || true
          fi
          # Keep only files that still exist (skip deletions), preserving exact names.
          : > doc_files_existing.txt
          while IFS= read -r f; do
            [ -n "$f" ] && [ -f "$f" ] && printf '%s\n' "$f" >> doc_files_existing.txt
          done < doc_files.txt
          mv doc_files_existing.txt doc_files.txt
          echo "Doc files to check:"; cat doc_files.txt
          echo "count=$(wc -l < doc_files.txt)" >> "$GITHUB_OUTPUT"

      - name: Critical Markdown check (rendering-breaks only, not style)
        if: steps.docs.outputs.count != '0'
        run: |
          set -uo pipefail
          # Read the NUL-safe-ish file list (one path per line) into an array. Names
          # are passed as ARGUMENTS to python, never evaluated as shell.
          mapfile -t FILES < doc_files.txt
          if [ "${#FILES[@]}" -eq 0 ]; then echo "No doc files."; exit 0; fi
          python3 scripts/critical_markdown_check.py "${FILES[@]}"

      # Broken-link check. Handed a FIXED glob (not the attacker-controlled list) so
      # no untrusted filename ever reaches lychee's `eval`. Over-checking docs is
      # harmless. Informational only: continue-on-error keeps it from blocking.
      - name: Broken-link check (lychee)
        uses: lycheeverse/lychee-action@v2
        with:
          args: >-
            --no-progress
            --max-concurrency 4
            --accept 200,206,301,302,303,307,308,401,403,429
            --timeout 20
            --max-retries 2
            "**/*.md"
            "**/*.markdown"
            "**/*.rst"
          fail: true
        continue-on-error: true