refactor(server): move the metadata-enrichment subsystem into lib/enrichment.py (R3) (#861)

* refactor(server): move the metadata-enrichment subsystem into lib/enrichment.py (R3)

MusicBrainz / Cover-Art-Archive / AcoustID transport, the match-scorer glue, and
the background enrichment worker (~930 lines, 61 defs) leave server.py as one
cohesive unit. Bodies are verbatim; the only changes are seam reads:

  meta_db / config_dir / sloppak_cache_dir / art_cache_dir -> appstate.<slot>
  _song_pack_art_exists / _art_override_paths (stay in server.py for the art +
    delete routes) -> appstate.<callable> (new seam slots, injected by reference)
  _env_flag -> env_compat.env_flag_compat (the existing identical helper)
  _artist_title_from_filename -> imported from metadata_db (its home)
  the User-Agent VERSION lookup: Path(__file__).parent ->
    Path(__file__).resolve().parents[1] (lib/enrichment.py -> app root)

server.py drives the worker through the module (import enrichment; the routes +
scan lifecycle call enrichment.X). Tests that faked the network on `server`
(_mb_http_get, _enrich_network_enabled, _caa_http_get, ...) now patch the same
names on `enrichment` — the module attribute is resolved at call time, so one
setattr reaches both the routes and the worker's internal callers. Acyclic:
enrichment imports appstate/appconfig/dlc_paths/metadata_db/mb_match/
acoustid_match/sloppak/loosefolder, never server.

server.py: 6,917 -> 5,988 (-929).

Verified: pyflakes clean (bar the pre-existing File/safe_join/tuning_name/ET);
route table IDENTICAL (143); full pytest 2400 passed (140 enrichment/art cases
incl the offline-safety + transport-error-pauses-pass contracts that fake the
network); test_packaging 44 passed (enrichment.py resolves under lib/); eslint 0.
Boot smoke: /api/enrichment/status + POST /kick serve from the new module.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: reset enrichment worker state between tests (CodeRabbit)

lib/enrichment.py now owns the worker, and it stays imported for the whole
session while the `server` fixtures pop-and-reimport `server` — so the cancel
Event / status dict / caches would leak across tests, and a stale `_enrich_cancel`
could short-circuit a later direct `_background_enrich()`. An autouse conftest
fixture clears that process-global state before each test.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: tighten the enrichment-reset fixture (CodeRabbit)

Narrow the import guard to ImportError (not blind Exception, BLE001), and stop
clearing _caa_index_locks — it's guarded by _caa_index_locks_guard, so an
unlocked clear() would race a still-alive worker, and its per-release mutexes
carry no test state.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Byron Gamatos
2026-07-11 11:32:21 +02:00
committed by GitHub
co-authored by Claude Opus 4.8
parent 508829c012
commit 165475d115
14 changed files with 1346 additions and 1126 deletions
+19 -18
View File
@@ -7,6 +7,7 @@ here opens a socket, and the offline default is itself asserted.
"""
import importlib
import enrichment
import io as _io
import sys
@@ -176,15 +177,15 @@ def caa(server, monkeypatch):
calls.append(release_id)
return art.get(release_id)
fake.calls, fake.art = calls, art
monkeypatch.setattr(server, "_caa_http_get", fake)
monkeypatch.setattr(server, "_enrich_network_enabled", lambda: True)
monkeypatch.setattr(enrichment, "_caa_http_get", fake)
monkeypatch.setattr(enrichment, "_enrich_network_enabled", lambda: True)
return fake
def test_caa_fetch_fills_missing_art(server, client, caa):
make_sloppak(server, "a.sloppak") # no pack art
_match_row(server, "a.sloppak")
server._background_enrich()
enrichment._background_enrich()
row = server.meta_db.get_enrichment("a.sloppak")
assert row["art_state"] == "caa"
assert row["art_cache_path"] and row["art_cache_path"].endswith("caa_rel-1.jpg")
@@ -193,7 +194,7 @@ def test_caa_fetch_fills_missing_art(server, client, caa):
assert r.headers["content-type"] == "image/jpeg"
# Settled: the next pass never re-fetches.
n = len(caa.calls)
server._background_enrich()
enrichment._background_enrich()
assert len(caa.calls) == n
@@ -204,7 +205,7 @@ def test_caa_skips_pack_art_and_dedupes_by_release(server, caa):
_match_row(server, "haspack.sloppak")
_match_row(server, "b.sloppak") # same release as c
_match_row(server, "c.sloppak")
server._background_enrich()
enrichment._background_enrich()
assert server.meta_db.get_enrichment("haspack.sloppak")["art_state"] == "pack"
assert server.meta_db.get_enrichment("b.sloppak")["art_state"] == "caa"
assert server.meta_db.get_enrichment("c.sloppak")["art_state"] == "caa"
@@ -214,10 +215,10 @@ def test_caa_skips_pack_art_and_dedupes_by_release(server, caa):
def test_caa_404_marks_none(server, caa):
make_sloppak(server, "a.sloppak")
_match_row(server, "a.sloppak", release_id="rel-missing")
server._background_enrich()
enrichment._background_enrich()
assert server.meta_db.get_enrichment("a.sloppak")["art_state"] == "none"
n = len(caa.calls)
server._background_enrich()
enrichment._background_enrich()
assert len(caa.calls) == n # never re-hammered
@@ -226,13 +227,13 @@ def test_caa_transport_error_leaves_row_unevaluated(server, caa, monkeypatch):
_match_row(server, "a.sloppak")
def _down(release_id):
raise server.EnrichTransportError("down")
monkeypatch.setattr(server, "_caa_http_get", _down)
server._background_enrich()
raise enrichment.EnrichTransportError("down")
monkeypatch.setattr(enrichment, "_caa_http_get", _down)
enrichment._background_enrich()
assert server.meta_db.get_enrichment("a.sloppak")["art_state"] is None
# Network back → next pass completes it.
monkeypatch.setattr(server, "_caa_http_get", caa)
server._background_enrich()
monkeypatch.setattr(enrichment, "_caa_http_get", caa)
enrichment._background_enrich()
assert server.meta_db.get_enrichment("a.sloppak")["art_state"] == "caa"
@@ -240,22 +241,22 @@ def test_offline_default_skips_art_worker(server, monkeypatch):
"""Under the plain test env the whole art phase is skipped with the rest
of the network work."""
calls = []
monkeypatch.setattr(server, "_caa_http_get", lambda rid: calls.append(rid))
monkeypatch.setattr(enrichment, "_caa_http_get", lambda rid: calls.append(rid))
make_sloppak(server, "a.sloppak")
_match_row(server, "a.sloppak")
server._background_enrich()
enrichment._background_enrich()
assert calls == []
assert server.meta_db.get_enrichment("a.sloppak")["art_state"] is None
def test_lru_prune_evicts_oldest_and_resets_rows(server, caa, monkeypatch):
monkeypatch.setattr(server, "_CAA_CACHE_CAP_BYTES", 1) # everything over cap
monkeypatch.setattr(enrichment, "_CAA_CACHE_CAP_BYTES", 1) # everything over cap
make_sloppak(server, "a.sloppak", title="One")
make_sloppak(server, "b.sloppak", title="Two")
caa.art["rel-2"] = png_bytes((1, 1, 1))
_match_row(server, "a.sloppak", release_id="rel-1")
_match_row(server, "b.sloppak", release_id="rel-2")
server._background_enrich()
enrichment._background_enrich()
# With a 1-byte cap every fetch immediately evicts — the rows that pointed
# at evicted files were reset to unevaluated.
caa_files = list(server.ART_CACHE_DIR.glob("caa_*.jpg"))
@@ -282,13 +283,13 @@ def test_delete_override_restores_caa_fallback(server, client, caa):
_match_row(server, "a.sloppak")
# Pin an override BEFORE the art worker runs → the pass stamps art_state='user'.
client.post("/api/song/a.sloppak/art/upload", json={"image": b64(png_bytes())})
server._background_enrich()
enrichment._background_enrich()
assert server.meta_db.get_enrichment("a.sloppak")["art_state"] == "user"
# Remove it → the row resets to unevaluated…
assert client.delete("/api/art/a.sloppak/override").json()["removed"]
assert server.meta_db.get_enrichment("a.sloppak")["art_state"] is None
# …and the next pass fetches + serves the release's front cover.
server._background_enrich()
enrichment._background_enrich()
assert server.meta_db.get_enrichment("a.sloppak")["art_state"] == "caa"
r = client.get("/api/song/a.sloppak/art")
assert r.status_code == 200