diff --git a/scripts/check-doc-refs.sh b/scripts/check-doc-refs.sh index 24894438..d6ae0a8f 100755 --- a/scripts/check-doc-refs.sh +++ b/scripts/check-doc-refs.sh @@ -9,12 +9,18 @@ # Emits a CI error annotation per hit and exits 1 if any pointer is dead, 0 # otherwise. Runs as its own job; seconds, pure git+grep. # -# Two arms, because a pointer is written two ways: +# Three arms, because a pointer is written three ways: # root — a repo-root-relative path in prose or a comment, `docs//.md` # rel — a markdown link resolved against the linking file, [x](..//.md) +# path — any repo-relative source path, `/src/.rs`, `nix/.nix` # (spelled with placeholders on purpose: a literal example path here would be # a dead pointer this script then reports against itself) # +# The third arm carries no skip-list, and could only be built after the prose +# it would have flagged was fixed: every false positive was a sentence naming +# where something *used to* live. Tolerating those needs a past-tense +# heuristic — the permanent carve-out that teaches readers to ignore a gate. +# # Scope is every tracked file, deliberately unrestricted by type: prose # describes a path in words, and a stale path in a config file (an ignore # rule, a build input) is a live defect rather than a stale comment. @@ -98,10 +104,45 @@ done < "$tmp/rel" # something that resolves before a clean run means anything: if a rename, a # pattern edit or a tree move silences the search, that is a failure of this # script, not a property of the tree. +# Third arm: repo-relative paths to any tracked file, not just `docs/**.md`. +# A comment naming a moved `.rs` or `.nix` file misleads exactly as much as a +# dead doc link, and nothing was checking it. +# +# Both ends are anchored, and each anchor is there because its absence +# invented a path: unanchored, a `.js` extension matched the prefix of a +# `.json` one, and a bare `/` matched mid-path inside `nix//…`, +# conjuring a top-level twin of a real nested file. (Placeholders, per the +# header — a literal here would be a dead path this arm reports against +# itself.) `grep -o` has no lookaround, so the boundary char is stripped below. +prefix_pattern='(nix|scripts|docs|frontend|branding|hive-[a-z0-9-]+/src|hivectl/src|swarmctl/src|swarm-controller/src)' +ext_pattern='(nix|sh|rs|md|ts|tsx|js|css|toml)' +path_pattern="(^|[^A-Za-z0-9._/-])${prefix_pattern}/[A-Za-z0-9._/-]+\\.${ext_pattern}($|[^A-Za-z0-9])" + +git ls-files -z | xargs -0 -r grep -nEo "$path_pattern" /dev/null 2>/dev/null \ + > "$tmp/paths0" || true +sed -E 's/^([^:]*:[0-9]+:)[^A-Za-z0-9]?/\1/; s/[^A-Za-z0-9]$//' "$tmp/paths0" \ + > "$tmp/paths" || true + +while IFS=: read -r file lineno ref; do + [ -n "${ref:-}" ] || continue + exempt "$file" "$lineno" && continue + if [ -f "$ref" ]; then + alive=$((alive + 1)) + else + dead=$((dead + 1)) + printf '::error file=%s,line=%s::repo path does not resolve: %s\n' \ + "$file" "$lineno" "$ref" + fi +done < "$tmp/paths" + if [ "$(wc -l < "$tmp/root")" -eq 0 ]; then echo 'check-doc-refs: root-pointer search matched nothing — pattern or tree changed' >&2 exit 1 fi +if [ "$(wc -l < "$tmp/paths")" -eq 0 ]; then + echo 'check-doc-refs: repo-path search matched nothing — pattern or tree changed' >&2 + exit 1 +fi if [ "$(wc -l < "$tmp/rel")" -eq 0 ]; then echo 'check-doc-refs: relative-link search matched nothing — pattern or tree changed' >&2 exit 1