jellytau/scripts/check-doc-links.sh

#!/usr/bin/env bash
# Documentation link integrity: every relative markdown link must point at a
# file that exists.
#
# Implements DR-208 (see docs/requirements.md).
#
# Why this exists: docs/traceability.md is generated into docs/ while its file
# links were emitted repo-root-relative, so all ~2,800 of them resolved to
# docs/src-tauri/… and 404'd — in the Gitea repo browser and on the published
# mdBook site alike. Nobody clicks 2,800 links, so it went unnoticed for months.
# Several hand-written docs had the same defect at smaller scale: links to files
# that had been deleted, and links written as if the doc lived at the repo root.
# A link that does not resolve is a documentation defect of the same kind as a
# compile error, and a grep is enough to catch the whole class.
#
# What it checks: for every tracked `.md` file, every inline markdown link
# `[text](target)` whose target is a *path* — the target is resolved relative to
# the directory of the file containing it, and must exist on disk.
#
# ⚠️ It validates PATHS, NOT ANCHORS. A green run does not mean the links land
# where the text claims.
#
# 🔴 What it deliberately CANNOT see (do not read a green run as proof):
#   - **Anchor fragments.** `foo.md#some-heading` is checked only as `foo.md`.
#     Resolving the fragment needs a markdown renderer's heading-slug rules
#     (which differ between Gitea, GitHub and mdBook), so a link to a heading
#     that was renamed still passes here. That is a deliberate scope cut, not an
#     oversight.
#   - **External URLs.** http(s):// and mailto: are skipped. Checking them means
#     network I/O in a gate, which makes the gate flaky and slow; link rot in an
#     external URL is also not something a commit can break.
#   - **Reference-style links** (`[text][ref]` with a separate `[ref]: target`
#     definition) and bare autolinks. This project writes inline links; add the
#     pattern here if that changes.
#   - **Links inside fenced code blocks**, which are intentionally skipped —
#     a template being *shown* to the reader (e.g. the release-notes template in
#     docs/release-checklist.md) is sample text, not a live link, and its targets
#     are resolved wherever it is eventually pasted, not from the docs tree.
#   - **A link that resolves to the wrong existing file.** Existence is not
#     correctness.
#
# Usage:  bash scripts/check-doc-links.sh
# Exits non-zero, listing file:line and the unresolved target, on any failure.

set -euo pipefail

cd "$(dirname "$0")/.."

# Generated, vendored or build-output trees. Their markdown is not authored here
# and their link targets are not ours to fix.
#
# Only consulted when this is NOT a git checkout — inside one, the tracked-file
# list does this job and does not need maintaining. Kept for the tarball case.
EXCLUDES=(
  "./node_modules/*"
  "./.svelte-kit/*"
  "./build/*"
  "./dist/*"
  "./src-tauri/gen/*"
  "./src-tauri/target/*"
  "./.git/*"
  # Agent/dev scratch worktrees (.claude/worktrees is itself git-ignored). These
  # are full checkouts of the repo, so without this the checker walks every
  # in-flight branch and reports its links as if they were ours.
  "./.claude/*"
)

# Targets that do not exist in the repo *by design* because the publish-docs job
# writes them into docs/ at build time (see .gitea/workflows/publish-docs.yml).
# Keep this list to genuinely generated pages — anything else here is a broken
# link being hidden.
GENERATED_TARGETS=(
  "./docs/README.md"        # the site's landing page, written by publish-docs
  "./docs/api-redirect.md"  # the rustdoc redirect stub, likewise
)

is_generated() {
  local candidate="$1"
  for generated in "${GENERATED_TARGETS[@]}"; do
    [[ "$candidate" == "$generated" ]] && return 0
  done
  return 1
}

echo "🔎 Checking relative markdown links resolve to files on disk…"

# Ask git which markdown files are ours, rather than walking the filesystem.
#
# This started as a find(1) with a hand-maintained prune list, and that list was
# wrong three times in a row: it walked the scratch worktrees under .claude/,
# then makepkg's vendored cargo registry under packaging/arch/src/ — each time
# reporting a dependency's broken README as if it were ours. Every one of those
# directories is already git-ignored, so the tracked-file list is the exclusion
# rule, and it cannot drift out of date the way EXCLUDES did. It also matches
# what this script always claimed to do.
#
# Untracked-but-not-ignored files are deliberately included: a new doc added in
# a working tree should be checked before it is committed, not after.
if git rev-parse --git-dir >/dev/null 2>&1; then
  mapfile -t md_files < <(
    { git ls-files -z --cached --others --exclude-standard -- '*.md' | tr '\0' '\n'; } \
      | sed 's|^|./|' | sort -u
  )
else
  # Not a git checkout (an exported tarball, say): fall back to walking, with
  # the prune list below as the only defence.
  find_args=(. )
  for pattern in "${EXCLUDES[@]}"; do
    find_args+=(-path "$pattern" -prune -o)
  done
  find_args+=(-name "*.md" -type f -print)
  mapfile -t md_files < <(find "${find_args[@]}" | sort)
fi

echo "   ${#md_files[@]} markdown files"

broken=""
checked=0

for md in "${md_files[@]}"; do
  dir="$(dirname "$md")"

  # One documented exception: docs-site/SUMMARY.md is mdBook's table of
  # contents, and the publish-docs job copies it *into* docs/ before rendering
  # (book.toml sets src = "../docs"). Its links are therefore written relative
  # to docs/, not to the directory the file is stored in. Resolving it from
  # docs/ is what actually validates it — and it is the check that catches a
  # SUMMARY entry pointing at a page that does not exist, which mdBook itself
  # only warns about.
  if [[ "$md" == "./docs-site/SUMMARY.md" ]]; then
    dir="./docs"
  fi

  # Strip fenced code blocks (``` and ~~~) before extracting links, so sample
  # markdown shown to the reader is not checked as if it were a live link.
  # Line numbers are preserved by blanking the lines rather than deleting them.
  #
  # Then emit "lineno<TAB>target" for each inline link on each surviving line.
  while IFS=$'\t' read -r lineno target; do
    [[ -z "${target:-}" ]] && continue

    # Skip external schemes and pure-anchor links.
    case "$target" in
      http://*|https://*|mailto:*|ftp://*|"#"*|"") continue ;;
      # A protocol-relative or scheme-ish target we do not resolve.
      //*) continue ;;
    esac

    # Drop any anchor fragment and query string — we check the path only.
    path="${target%%#*}"
    path="${path%%\?*}"
    [[ -z "$path" ]] && continue

    # Percent-decode: SvelteKit route directories are literally named `[id]`,
    # which docs link as `%5Bid%5D`, and spaces appear as `%20`.
    if [[ "$path" == *%* ]]; then
      path="$(printf '%b' "${path//%/\\x}")"
    fi

    checked=$((checked + 1))

    if is_generated "$dir/$path"; then
      continue
    fi

    if [[ ! -e "$dir/$path" ]]; then
      broken+="${md}:${lineno}  ->  ${target}"$'\n'
    fi
  done < <(
    awk '
      /^[[:space:]]*(```|~~~)/ { fence = !fence; print ""; next }
      fence { print ""; next }
      { print }
    ' "$md" |
    grep -noE '\]\([^)[:space:]]+' |
    sed -E 's/^([0-9]+):\]\(/\1\t/'
  )
done

echo "   $checked relative links checked"

if [[ -n "$broken" ]]; then
  echo ""
  echo "❌ Broken documentation links — these targets do not exist on disk:"
  echo ""
  echo "$broken" | sed 's/^/   /'
  echo "   Each link is resolved relative to the directory of the file it is in."
  echo "   The usual causes:"
  echo "     • the target file was moved or deleted — update or drop the link;"
  echo "     • the link was written as if the doc lived at the repo root — a doc"
  echo "       in docs/ needs '../' to reach src/, scripts/ or CHANGELOG.md;"
  echo "     • a generated doc emits repo-root-relative hrefs — fix the"
  echo "       generator, not the output (see scripts/extract-traces.ts)."
  exit 1
fi

echo "✅ All relative documentation links resolve."
echo "   (Reminder: paths only — anchors and external URLs are NOT checked.)"