fix(cache): the atexit stat-index flush must not resurrect a deleted corpus (#2974)

graphify/cache.py

@@ -379,6 +379,20 @@ def _flush_stat_index() -> None:
             continue
         dk = _stat_key_to_relative(k, _stat_index_anchor) if _stat_index_anchor is not None else k
         on_disk[dk] = v
+    # Never resurrect a corpus that was deleted while graphify was running
+    # (#2974): a hook-launched `graphify update . &` in a short-lived worktree
+    # outlives `git worktree remove`, and an unconditional `mkdir -p` here
+    # rebuilt the dead path as a husk holding nothing but this index. The
+    # index is a pure optimisation, so when its root is gone it is simply not
+    # written. Creating graphify-out/cache/ under a root that still exists is
+    # unchanged (a first run writes the index before anything else does).
+    try:
+        if not _stat_index_root.is_dir():
+            _stat_index_dirty = False
+            return
+    except OSError:
+        _stat_index_dirty = False
+        return
     try:
         p.parent.mkdir(parents=True, exist_ok=True)
         fd, tmp = tempfile.mkstemp(dir=p.parent, prefix="stat-index.", suffix=".tmp")

tests/test_stat_index_husk.py

@@ -0,0 +1,69 @@
+"""The atexit stat-index flush must not resurrect a deleted directory (#2974).
+
+A post-commit hook runs `graphify update . &` in a short-lived worktree; the
+branch merges and `git worktree remove` deletes the tree while the rebuild
+is still running. The exit-time flush then `mkdir -p`'d the dead path back
+into existence, leaving a husk holding nothing but
+`graphify-out/cache/stat-index.json` — 81 of them over a few weeks.
+"""
+from __future__ import annotations
+
+import shutil
+from pathlib import Path
+
+import pytest
+
+from graphify import cache
+
+
+@pytest.fixture(autouse=True)
+def _fresh_index():
+    def reset():
+        cache._stat_index_root = None
+        cache._stat_index_anchor = None
+        cache._stat_index = {}
+        cache._stat_index_dirty = False
+    reset()
+    yield
+    reset()
+
+
+def _dirty(corpus: Path) -> Path:
+    f = corpus / "a.md"
+    f.write_text("# hello\nbody\n", encoding="utf-8")
+    cache.file_hash(f, corpus)  # loads + dirties the index for this corpus
+    assert cache._stat_index_dirty
+    return f
+
+
+def test_a_corpus_deleted_mid_run_stays_deleted(tmp_path):
+    corpus = tmp_path / "husk-race-corpus"
+    corpus.mkdir()
+    _dirty(corpus)
+    shutil.rmtree(corpus)
+    cache._flush_stat_index()  # what atexit does
+    assert not corpus.exists(), "the flush resurrected the deleted corpus"
+    assert not cache._stat_index_dirty  # nothing left pending for a second attempt
+
+
+def test_a_redirected_cache_root_that_vanished_is_not_recreated(tmp_path):
+    corpus = tmp_path / "c"
+    corpus.mkdir()
+    elsewhere = tmp_path / "out"
+    elsewhere.mkdir()
+    f = corpus / "a.md"
+    f.write_text("x\n", encoding="utf-8")
+    cache.file_hash(f, corpus, cache_root=elsewhere)
+    shutil.rmtree(elsewhere)
+    cache._flush_stat_index()
+    assert not elsewhere.exists()
+
+
+def test_the_index_is_still_written_for_a_live_run(tmp_path):
+    """A first run writes the index before graphify-out/ exists at all; that
+    stays as it was — the root is live, so creating cache/ under it is fine."""
+    corpus = tmp_path / "c"
+    corpus.mkdir()
+    _dirty(corpus)
+    cache._flush_stat_index()
+    assert (corpus / "graphify-out" / "cache" / "stat-index.json").is_file()