#!/usr/bin/env bash
# Checks the documentation set: every markdown file links to every other one, and every relative link resolves.
# Usage: scripts/check-docs.sh   (exit 1 on any problem, lists them all)
set -u
cd "$(dirname "$0")/.."

DOCS=(README.md SPEC.md COMPARISON.md AGENTS.md CHANGELOG.md docs/ARCHITECTURE.md docs/RESEARCH.md docs/CI.md)
bad=0
fail() { echo "docs: $*"; bad=$((bad+1)); }

# no markdown file may exist outside the checked set (so a new doc cannot dodge the rule)
while IFS= read -r f; do
  f=${f#./}
  printf '%s\n' "${DOCS[@]}" | grep -qxF "$f" || fail "$f is not in the DOCS list of scripts/check-docs.sh"
done < <(find . -name '*.md' -not -path './build/*' -not -path './.git/*' -not -path './prompt.md' -not -path './audit/*' -not -path './review.md' -not -path './review2.md' -not -path './valgrind/*')
# prompt.md: the original task statement, not documentation.
# audit/*, valgrind/*: separate, self-contained doc sets (one README per CVE check, one for the
# valgrind setup); linked from the main docs but not forced into their full cross-link mesh.
# review.md, review2.md: standalone one-off reviews, not part of the maintained doc set.

for f in "${DOCS[@]}"; do
  [ -f "$f" ] || { fail "$f is missing"; continue; }
  dir=$(dirname "$f")
  # every other document must be linked
  for g in "${DOCS[@]}"; do
    [ "$f" = "$g" ] && continue
    rel=$(realpath --relative-to="$dir" "$g")
    grep -qE "\]\(${rel//./\\.}(#[^)]*)?\)" "$f" || fail "$f does not link to $g (expected ]($rel))"
  done
  # every relative link must point at something that exists
  while IFS= read -r target; do
    case "$target" in http://*|https://*|mailto:*|\#*) continue ;; esac
    path=${target%%#*}
    [ -z "$path" ] && continue
    [ -e "$dir/$path" ] || fail "$f links to missing $target"
  done < <(grep -oE '\]\([^)]+\)' "$f" | sed -E 's/^\]\(//; s/\)$//')
done

[ "$bad" -eq 0 ] && echo "docs: ${#DOCS[@]} documents, all cross-linked, all links resolve" || { echo "docs: $bad problem(s)"; exit 1; }