US09-03: Write the Architecture Overview (#109)

tests/integration/test_architecture_overview.py

@@ -0,0 +1,164 @@
+"""US09-03: the architecture overview, checked against the architecture.
+
+An architecture document is the one that rots most quietly: nothing breaks when it
+describes a module that was renamed two epics ago, it just quietly misleads the next
+person. So the parts of it that the code also knows — module names, state machines,
+table names, the modules an invariant is claimed to live in — are compared with the
+code, and a missing one fails the suite.
+
+The diagrams' rendering is proven in ``tests/e2e/test_docs_ui.py``.
+"""
+
+from __future__ import annotations
+
+import re
+from pathlib import Path
+
+import photo_pipeline.models  # noqa: F401  (registers every table on Base.metadata)
+from photo_pipeline.db import Base
+from photo_pipeline.services import jobs, rename_journal, upload_batches
+
+REPO = Path(__file__).resolve().parents[2]
+PACKAGE = REPO / "photo_pipeline"
+OVERVIEW = REPO / "docs" / "architecture.md"
+TEXT = OVERVIEW.read_text()
+
+# Names the map does not owe the reader individually: the package markers, the CLI
+# entry point, and the two modules that exist to be small and obvious.
+UNMAPPED = {"__init__", "__main__", "logging"}
+
+
+def modules() -> set[str]:
+    """Every module and package under photo_pipeline, by the name it is imported as."""
+    names = set()
+    for path in PACKAGE.rglob("*.py"):
+        relative = path.relative_to(PACKAGE)
+        names.add(relative.parts[0] if len(relative.parts) > 1 else relative.stem)
+    return {name.removesuffix(".py") for name in names} - UNMAPPED
+
+
+def states(container: type) -> set[str]:
+    return {
+        value
+        for name, value in vars(container).items()
+        if name.isupper() and isinstance(value, str)
+    }
+
+
+# ── the module map ───────────────────────────────────────────────────────────
+
+
+def test_every_module_appears_in_the_map():
+    """A service nobody documented is a service the next person re-implements."""
+    missing = sorted(name for name in modules() if name not in TEXT)
+    assert missing == [], f"absent from the architecture overview: {missing}"
+
+
+def test_every_service_is_named_individually():
+    """The package table says what `services/` is for; this is the list that actually
+    drifts, because a new service is added roughly every story."""
+    services = {path.stem for path in (PACKAGE / "services").glob("*.py")} - UNMAPPED
+    missing = sorted(name for name in services if not re.search(rf"\b{name}\b", TEXT))
+    assert missing == [], f"services missing from the overview: {missing}"
+
+
+def test_the_map_names_no_module_that_does_not_exist():
+    """Every `services/<name>` or backticked module path in the document resolves."""
+    referenced = set(re.findall(r"`(?:photo_pipeline/)?([a-z_]+)/([a-z_]+)\.py`", TEXT))
+    referenced |= {("", name) for name in re.findall(r"`([a-z_]+)\.py`", TEXT)}
+    missing = [
+        f"{package}/{module}.py" if package else f"{module}.py"
+        for package, module in referenced
+        if not (PACKAGE / package / f"{module}.py").is_file()
+    ]
+    assert missing == [], f"documented but absent from the source: {missing}"
+
+
+# ── the state machines ───────────────────────────────────────────────────────
+
+
+def test_every_job_state_is_documented():
+    missing = sorted(state for state in states(jobs.JobState) if state not in TEXT)
+    assert missing == [], f"job states missing from the overview: {missing}"
+
+
+def test_every_rename_journal_state_is_documented():
+    missing = sorted(state for state in states(rename_journal.JournalState) if state not in TEXT)
+    assert missing == [], f"journal states missing from the overview: {missing}"
+
+
+def test_every_upload_batch_state_is_documented():
+    missing = sorted(state for state in states(upload_batches.BatchState) if state not in TEXT)
+    assert missing == [], f"batch states missing from the overview: {missing}"
+
+
+def test_the_unsafe_journal_states_are_named_as_the_ones_that_block():
+    """The reason an unrelated mutation is refused has to be findable."""
+    for state in rename_journal.UNSAFE_STATES:
+        assert state in TEXT
+    assert "rename_recovery_required" in TEXT
+
+
+def test_an_uncertain_upload_is_documented_as_not_retryable():
+    assert upload_batches.BatchState.UNKNOWN not in upload_batches.RUNNABLE_STATES
+    assert "not** restartable" in TEXT or "not restartable" in TEXT
+
+
+# ── the data model ───────────────────────────────────────────────────────────
+
+
+def test_every_table_is_listed():
+    missing = sorted(name for name in Base.metadata.tables if name not in TEXT)
+    assert missing == [], f"tables missing from the overview: {missing}"
+
+
+def test_the_document_lists_no_table_that_does_not_exist():
+    listed = set(re.findall(r"`([a-z_]+)`", TEXT))
+    plausible = {name for name in listed if name.endswith("s") and "_" in name}
+    invented = sorted(
+        name
+        for name in plausible
+        if name not in Base.metadata.tables
+        and not (PACKAGE / "services" / f"{name}.py").is_file()
+        and name not in {"library_roots", "trusted_proxies", "allowed_hosts", "asset_paths"}
+    )
+    assert invented == [], f"looks like a table but is not one: {invented}"
+
+
+# ── the invariants ───────────────────────────────────────────────────────────
+
+
+def test_each_invariant_points_at_a_module_that_enforces_it():
+    """The point of the table is to answer 'where do I look'. A wrong answer there
+    costs more than no answer."""
+    claims = {
+        "path_policy.is_excluded": PACKAGE / "path_policy.py",
+        "path_policy.resolve_in_roots": PACKAGE / "path_policy.py",
+        "services/app_lock.py": PACKAGE / "services" / "app_lock.py",
+        "services/exif_checkpoint.py": PACKAGE / "services" / "exif_checkpoint.py",
+        "services/archive_transfer.py": PACKAGE / "services" / "archive_transfer.py",
+        "api/security.py": PACKAGE / "api" / "security.py",
+        "imaging.py": PACKAGE / "imaging.py",
+    }
+    for claim, path in claims.items():
+        assert claim in TEXT, f"the invariant table does not mention {claim}"
+        assert path.is_file(), f"{claim} does not exist"
+        function = claim.rpartition(".")[2] if "/" not in claim else ""
+        if function and function != "py":
+            assert f"def {function}" in path.read_text(), f"{claim} is not defined there"
+
+
+def test_the_lock_order_matches_the_ranks_in_the_code():
+    from photo_pipeline.jobs import locks
+
+    order = [name for name, _ in sorted(locks.LOCK_RANK.items(), key=lambda item: item[1])]
+    assert order[0].startswith("library"), "the broadest lock is no longer the library"
+    assert "library → stage/job → album/folder → asset" in TEXT
+
+
+def test_the_frozen_donor_archive_is_described_as_provenance_not_a_dependency():
+    """That production never imports the frozen sources is proven by
+    ``tests/unit/test_legacy_archive.py`` — which also forbids any other test from
+    naming that directory, so this one checks the claim by its consequence."""
+    assert "must not import" in TEXT
+    assert "provenance and rollback evidence" in TEXT