Track bundled vendor runtime sources
Some checks failed
CI / main (push) Has been cancelled
CI / release-e2e (push) Has been cancelled

This commit is contained in:
2026-07-07 10:05:50 +08:00
parent fbe179ab53
commit 52636c91ae
2111 changed files with 1850012 additions and 14 deletions

View File

@@ -0,0 +1 @@
# Service layer tests

View File

@@ -0,0 +1,69 @@
import tempfile
from pathlib import Path
from unittest.mock import patch
import pytest
from sqlalchemy import create_engine, event
from sqlalchemy.orm import Session
from app.assets.database.models import Base
@pytest.fixture(autouse=True)
def autoclean_unit_test_assets():
"""Override parent autouse fixture - service unit tests don't need server cleanup."""
yield
@pytest.fixture
def db_engine():
"""In-memory SQLite engine for fast unit tests."""
engine = create_engine("sqlite:///:memory:")
Base.metadata.create_all(engine)
return engine
@pytest.fixture
def db_engine_fk():
"""In-memory SQLite engine with foreign key enforcement enabled."""
engine = create_engine("sqlite:///:memory:")
@event.listens_for(engine, "connect")
def _set_pragma(dbapi_connection, connection_record):
cursor = dbapi_connection.cursor()
cursor.execute("PRAGMA foreign_keys=ON")
cursor.close()
Base.metadata.create_all(engine)
return engine
@pytest.fixture
def session(db_engine):
"""Session fixture for tests that need direct DB access."""
with Session(db_engine) as sess:
yield sess
@pytest.fixture
def mock_create_session(db_engine):
"""Patch create_session to use our in-memory database."""
from contextlib import contextmanager
from sqlalchemy.orm import Session as SASession
@contextmanager
def _create_session():
with SASession(db_engine) as sess:
yield sess
with patch("app.assets.services.ingest.create_session", _create_session), \
patch("app.assets.services.asset_management.create_session", _create_session), \
patch("app.assets.services.tagging.create_session", _create_session):
yield _create_session
@pytest.fixture
def temp_dir():
"""Temporary directory for file operations."""
with tempfile.TemporaryDirectory() as tmpdir:
yield Path(tmpdir)

View File

@@ -0,0 +1,310 @@
"""Tests for asset_management services."""
import pytest
from sqlalchemy.orm import Session
from app.assets.database.models import Asset, AssetReference
from app.assets.database.queries import ensure_tags_exist, add_tags_to_reference
from app.assets.helpers import get_utc_now
from app.assets.services import (
get_asset_detail,
update_asset_metadata,
delete_asset_reference,
set_asset_preview,
)
from app.assets.services.asset_management import resolve_hash_to_path
def _make_asset(session: Session, hash_val: str = "blake3:test", size: int = 1024) -> Asset:
asset = Asset(hash=hash_val, size_bytes=size, mime_type="application/octet-stream")
session.add(asset)
session.flush()
return asset
def _make_reference(
session: Session,
asset: Asset,
name: str = "test",
owner_id: str = "",
) -> AssetReference:
now = get_utc_now()
ref = AssetReference(
owner_id=owner_id,
name=name,
asset_id=asset.id,
created_at=now,
updated_at=now,
last_access_time=now,
)
session.add(ref)
session.flush()
return ref
class TestGetAssetDetail:
def test_returns_none_for_nonexistent(self, mock_create_session):
result = get_asset_detail(reference_id="nonexistent")
assert result is None
def test_returns_asset_with_tags(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset, name="test.bin")
ensure_tags_exist(session, ["alpha", "beta"])
add_tags_to_reference(session, reference_id=ref.id, tags=["alpha", "beta"])
session.commit()
result = get_asset_detail(reference_id=ref.id)
assert result is not None
assert result.ref.id == ref.id
assert result.asset.hash == asset.hash
assert set(result.tags) == {"alpha", "beta"}
def test_respects_owner_visibility(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset, owner_id="user1")
session.commit()
# Wrong owner cannot see
result = get_asset_detail(reference_id=ref.id, owner_id="user2")
assert result is None
# Correct owner can see
result = get_asset_detail(reference_id=ref.id, owner_id="user1")
assert result is not None
class TestUpdateAssetMetadata:
def test_updates_name(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset, name="old_name.bin")
ref_id = ref.id
session.commit()
update_asset_metadata(
reference_id=ref_id,
name="new_name.bin",
)
# Verify by re-fetching from DB
session.expire_all()
updated_ref = session.get(AssetReference, ref_id)
assert updated_ref.name == "new_name.bin"
def test_updates_tags(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset)
ensure_tags_exist(session, ["old"])
add_tags_to_reference(session, reference_id=ref.id, tags=["old"])
session.commit()
result = update_asset_metadata(
reference_id=ref.id,
tags=["new1", "new2"],
)
assert set(result.tags) == {"new1", "new2"}
assert "old" not in result.tags
def test_updates_user_metadata(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset)
ref_id = ref.id
session.commit()
update_asset_metadata(
reference_id=ref_id,
user_metadata={"key": "value", "num": 42},
)
# Verify by re-fetching from DB
session.expire_all()
updated_ref = session.get(AssetReference, ref_id)
assert updated_ref.user_metadata["key"] == "value"
assert updated_ref.user_metadata["num"] == 42
def test_raises_for_nonexistent(self, mock_create_session):
with pytest.raises(ValueError, match="not found"):
update_asset_metadata(reference_id="nonexistent", name="fail")
def test_raises_for_wrong_owner(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset, owner_id="user1")
session.commit()
with pytest.raises(PermissionError, match="not owner"):
update_asset_metadata(
reference_id=ref.id,
name="new",
owner_id="user2",
)
class TestDeleteAssetReference:
def test_soft_deletes_reference(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset)
ref_id = ref.id
session.commit()
result = delete_asset_reference(
reference_id=ref_id,
owner_id="",
delete_content_if_orphan=False,
)
assert result is True
# Row still exists but is marked as soft-deleted
session.expire_all()
row = session.get(AssetReference, ref_id)
assert row is not None
assert row.deleted_at is not None
def test_returns_false_for_nonexistent(self, mock_create_session):
result = delete_asset_reference(
reference_id="nonexistent",
owner_id="",
)
assert result is False
def test_returns_false_for_wrong_owner(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset, owner_id="user1")
ref_id = ref.id
session.commit()
result = delete_asset_reference(
reference_id=ref_id,
owner_id="user2",
)
assert result is False
assert session.get(AssetReference, ref_id) is not None
def test_keeps_asset_if_other_references_exist(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref1 = _make_reference(session, asset, name="ref1")
_make_reference(session, asset, name="ref2") # Second ref keeps asset alive
asset_id = asset.id
session.commit()
delete_asset_reference(
reference_id=ref1.id,
owner_id="",
delete_content_if_orphan=True,
)
# Asset should still exist
assert session.get(Asset, asset_id) is not None
def test_deletes_orphaned_asset(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset)
asset_id = asset.id
ref_id = ref.id
session.commit()
delete_asset_reference(
reference_id=ref_id,
owner_id="",
delete_content_if_orphan=True,
)
# Both ref and asset should be gone
assert session.get(AssetReference, ref_id) is None
assert session.get(Asset, asset_id) is None
class TestSetAssetPreview:
def test_sets_preview(self, mock_create_session, session: Session):
asset = _make_asset(session, hash_val="blake3:main")
preview_asset = _make_asset(session, hash_val="blake3:preview")
ref = _make_reference(session, asset)
preview_ref = _make_reference(session, preview_asset, name="preview.png")
ref_id = ref.id
preview_ref_id = preview_ref.id
session.commit()
set_asset_preview(
reference_id=ref_id,
preview_reference_id=preview_ref_id,
)
# Verify by re-fetching from DB
session.expire_all()
updated_ref = session.get(AssetReference, ref_id)
assert updated_ref.preview_id == preview_ref_id
def test_clears_preview(self, mock_create_session, session: Session):
asset = _make_asset(session)
preview_asset = _make_asset(session, hash_val="blake3:preview")
ref = _make_reference(session, asset)
preview_ref = _make_reference(session, preview_asset, name="preview.png")
ref.preview_id = preview_ref.id
ref_id = ref.id
session.commit()
set_asset_preview(
reference_id=ref_id,
preview_reference_id=None,
)
# Verify by re-fetching from DB
session.expire_all()
updated_ref = session.get(AssetReference, ref_id)
assert updated_ref.preview_id is None
def test_raises_for_nonexistent_ref(self, mock_create_session):
with pytest.raises(ValueError, match="not found"):
set_asset_preview(reference_id="nonexistent")
def test_raises_for_wrong_owner(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset, owner_id="user1")
session.commit()
with pytest.raises(PermissionError, match="not owner"):
set_asset_preview(
reference_id=ref.id,
preview_reference_id=None,
owner_id="user2",
)
class TestResolveHashToPath:
def test_returns_none_for_unknown_hash(self, mock_create_session):
result = resolve_hash_to_path("blake3:" + "a" * 64)
assert result is None
@pytest.mark.parametrize(
"ref_owner, query_owner, expect_found",
[
("user1", "user1", True),
("user1", "user2", False),
("", "anyone", True),
("", "", True),
],
ids=[
"owner_sees_own_ref",
"other_owner_blocked",
"ownerless_visible_to_anyone",
"ownerless_visible_to_empty",
],
)
def test_owner_visibility(
self, ref_owner, query_owner, expect_found,
mock_create_session, session: Session, temp_dir,
):
f = temp_dir / "file.bin"
f.write_bytes(b"data")
asset = _make_asset(session, hash_val="blake3:" + "b" * 64)
ref = _make_reference(session, asset, name="file.bin", owner_id=ref_owner)
ref.file_path = str(f)
session.commit()
result = resolve_hash_to_path(asset.hash, owner_id=query_owner)
if expect_found:
assert result is not None
assert result.abs_path == str(f)
else:
assert result is None

View File

@@ -0,0 +1,137 @@
"""Tests for bulk ingest services."""
from pathlib import Path
from sqlalchemy.orm import Session
from app.assets.database.models import Asset, AssetReference
from app.assets.services.bulk_ingest import SeedAssetSpec, batch_insert_seed_assets
class TestBatchInsertSeedAssets:
def test_populates_mime_type_for_model_files(self, session: Session, temp_dir: Path):
"""Verify mime_type is stored in the Asset table for model files."""
file_path = temp_dir / "model.safetensors"
file_path.write_bytes(b"fake safetensors content")
specs: list[SeedAssetSpec] = [
{
"abs_path": str(file_path),
"size_bytes": 24,
"mtime_ns": 1234567890000000000,
"info_name": "Test Model",
"tags": ["models"],
"fname": "model.safetensors",
"metadata": None,
"hash": None,
"mime_type": "application/safetensors",
}
]
result = batch_insert_seed_assets(session, specs=specs, owner_id="")
assert result.inserted_refs == 1
# Verify Asset has mime_type populated
assets = session.query(Asset).all()
assert len(assets) == 1
assert assets[0].mime_type == "application/safetensors"
def test_mime_type_none_when_not_provided(self, session: Session, temp_dir: Path):
"""Verify mime_type is None when not provided in spec."""
file_path = temp_dir / "unknown.bin"
file_path.write_bytes(b"binary data")
specs: list[SeedAssetSpec] = [
{
"abs_path": str(file_path),
"size_bytes": 11,
"mtime_ns": 1234567890000000000,
"info_name": "Unknown File",
"tags": [],
"fname": "unknown.bin",
"metadata": None,
"hash": None,
"mime_type": None,
}
]
result = batch_insert_seed_assets(session, specs=specs, owner_id="")
assert result.inserted_refs == 1
assets = session.query(Asset).all()
assert len(assets) == 1
assert assets[0].mime_type is None
def test_various_model_mime_types(self, session: Session, temp_dir: Path):
"""Verify various model file types get correct mime_type."""
test_cases = [
("model.safetensors", "application/safetensors"),
("model.pt", "application/pytorch"),
("model.ckpt", "application/pickle"),
("model.gguf", "application/gguf"),
]
specs: list[SeedAssetSpec] = []
for filename, mime_type in test_cases:
file_path = temp_dir / filename
file_path.write_bytes(b"content")
specs.append(
{
"abs_path": str(file_path),
"size_bytes": 7,
"mtime_ns": 1234567890000000000,
"info_name": filename,
"tags": [],
"fname": filename,
"metadata": None,
"hash": None,
"mime_type": mime_type,
}
)
result = batch_insert_seed_assets(session, specs=specs, owner_id="")
assert result.inserted_refs == len(test_cases)
for filename, expected_mime in test_cases:
ref = session.query(AssetReference).filter_by(name=filename).first()
assert ref is not None
asset = session.query(Asset).filter_by(id=ref.asset_id).first()
assert asset.mime_type == expected_mime, f"Expected {expected_mime} for {filename}, got {asset.mime_type}"
class TestMetadataExtraction:
def test_extracts_mime_type_for_model_files(self, temp_dir: Path):
"""Verify metadata extraction returns correct mime_type for model files."""
from app.assets.services.metadata_extract import extract_file_metadata
file_path = temp_dir / "model.safetensors"
file_path.write_bytes(b"fake safetensors content")
meta = extract_file_metadata(str(file_path))
assert meta.content_type == "application/safetensors"
def test_mime_type_for_various_model_formats(self, temp_dir: Path):
"""Verify various model file types get correct mime_type from metadata."""
from app.assets.services.metadata_extract import extract_file_metadata
test_cases = [
("model.safetensors", "application/safetensors"),
("model.sft", "application/safetensors"),
("model.pt", "application/pytorch"),
("model.pth", "application/pytorch"),
("model.ckpt", "application/pickle"),
("model.pkl", "application/pickle"),
("model.gguf", "application/gguf"),
]
for filename, expected_mime in test_cases:
file_path = temp_dir / filename
file_path.write_bytes(b"content")
meta = extract_file_metadata(str(file_path))
assert meta.content_type == expected_mime, f"Expected {expected_mime} for {filename}, got {meta.content_type}"

View File

@@ -0,0 +1,278 @@
"""Tests for app.assets.services.cursor.
Cursors are opaque tokens internal to this server — these tests cover
round-tripping, validation, and length caps, not any particular wire
byte layout.
"""
from __future__ import annotations
import base64
from datetime import datetime, timedelta, timezone
import pytest
from app.assets.services.cursor import (
MAX_CURSOR_ID_LENGTH,
MAX_CURSOR_VALUE_LENGTH,
MAX_ENCODED_CURSOR_LENGTH,
CursorPayload,
InvalidCursorError,
decode_cursor,
decode_cursor_int,
decode_cursor_time,
encode_cursor,
encode_cursor_from_time,
)
ALLOWED = ("created_at", "updated_at", "name", "size")
class TestRoundTrip:
@pytest.mark.parametrize(
"sort_field, value, id",
[
("created_at", "1716200000000000", "a1b2c3d4-e5f6-7a89-b0c1-d2e3f4a5b6c7"),
("size", "1024", "asset-123"),
("name", "my-asset.png", "asset-abc"),
("name", "résumé.txt", "asset-uni"),
("name", "foo<&>bar.png", "asset-html"),
("name", 'quo"te\\back\nnewline.png', "asset-esc"),
],
)
def test_encode_decode(self, sort_field, value, id):
encoded = encode_cursor(sort_field, value, id)
assert encoded != ""
payload = decode_cursor(encoded, ALLOWED)
assert payload.sort_field == sort_field
assert payload.value == value
assert payload.id == id
class TestTimeCursor:
def test_microsecond_precision_preserved(self):
# Pick a time with non-zero microseconds — encoding at ms would lose the µs.
ts = datetime(2024, 5, 20, 12, 53, 20, 123456, tzinfo=timezone.utc)
encoded = encode_cursor_from_time("created_at", ts, "id-1")
payload = decode_cursor(encoded, ALLOWED)
# Value must be a microsecond integer string, not a millisecond one.
assert payload.value == "1716209600123456"
decoded = decode_cursor_time(payload)
assert decoded == ts
def test_decode_returns_utc(self):
payload = CursorPayload(sort_field="created_at", value="1716200000123456", id="id-1", order="desc")
decoded = decode_cursor_time(payload)
assert decoded.tzinfo == timezone.utc
def test_naive_datetime_rejected_on_encode(self):
naive = datetime(2024, 5, 20, 12, 0, 0)
with pytest.raises(ValueError):
encode_cursor_from_time("created_at", naive, "id-1")
def test_non_integer_value_rejected_on_decode(self):
with pytest.raises(InvalidCursorError):
decode_cursor_time(CursorPayload("created_at", "not-a-number", "id-1", "desc"))
def test_none_payload_rejected(self):
with pytest.raises(InvalidCursorError):
decode_cursor_time(None)
def test_non_utc_aware_normalized(self):
# Same instant, different timezone — must encode to the same micros.
utc_ts = datetime(2024, 5, 20, 12, 0, 0, tzinfo=timezone.utc)
offset_ts = utc_ts.astimezone(timezone(timedelta(hours=-5)))
assert encode_cursor_from_time("created_at", utc_ts, "x") == encode_cursor_from_time(
"created_at", offset_ts, "x"
)
class TestIntCursor:
def test_decode_int(self):
assert decode_cursor_int(CursorPayload("size", "1024", "id-1", "desc")) == 1024
def test_decode_int_rejects_non_int(self):
with pytest.raises(InvalidCursorError):
decode_cursor_int(CursorPayload("size", "abc", "id-1", "desc"))
def test_decode_int_rejects_none(self):
with pytest.raises(InvalidCursorError):
decode_cursor_int(None)
class TestInvalidInputs:
def test_oversized_cursor(self):
oversized = "a" * (MAX_ENCODED_CURSOR_LENGTH + 1)
with pytest.raises(InvalidCursorError, match="maximum length"):
decode_cursor(oversized, ALLOWED)
def test_not_base64(self):
with pytest.raises(InvalidCursorError):
decode_cursor("not base64!!!", ALLOWED)
def test_not_json(self):
encoded = base64.urlsafe_b64encode(b"definitely not json").rstrip(b"=").decode("ascii")
with pytest.raises(InvalidCursorError):
decode_cursor(encoded, ALLOWED)
def test_empty_id(self):
# Encoder rejects empty id symmetrically with the decoder, so build the
# payload manually to exercise the decoder's missing-id branch.
raw = b'{"s":"created_at","v":"1","id":"","o":"desc"}'
encoded = base64.urlsafe_b64encode(raw).rstrip(b"=").decode("ascii")
with pytest.raises(InvalidCursorError, match="missing id"):
decode_cursor(encoded, ALLOWED)
def test_oversized_id(self):
# Encoder enforces the cap symmetrically; hand-build to exercise decode.
big_id = "a" * (MAX_CURSOR_ID_LENGTH + 1)
raw = ('{"s":"created_at","v":"1","id":"' + big_id + '","o":"desc"}').encode("ascii")
encoded = base64.urlsafe_b64encode(raw).rstrip(b"=").decode("ascii")
with pytest.raises(InvalidCursorError, match="id exceeds maximum length"):
decode_cursor(encoded, ALLOWED)
def test_oversized_value(self):
# Encoder enforces the cap symmetrically; hand-build to exercise decode.
big_v = "v" * (MAX_CURSOR_VALUE_LENGTH + 1)
raw = ('{"s":"created_at","v":"' + big_v + '","id":"id-1","o":"desc"}').encode("ascii")
encoded = base64.urlsafe_b64encode(raw).rstrip(b"=").decode("ascii")
with pytest.raises(InvalidCursorError, match="value exceeds maximum length"):
decode_cursor(encoded, ALLOWED)
def test_unsupported_sort_field(self):
encoded = encode_cursor("execution_time", "1", "id-1")
with pytest.raises(InvalidCursorError, match="unsupported sort field"):
decode_cursor(encoded, ALLOWED)
def test_no_allowed_fields_rejects_everything(self):
encoded = encode_cursor("created_at", "1", "id-1")
with pytest.raises(InvalidCursorError):
decode_cursor(encoded, ())
def test_non_dict_payload_rejected(self):
encoded = base64.urlsafe_b64encode(b'["array","not","dict"]').rstrip(b"=").decode("ascii")
with pytest.raises(InvalidCursorError, match="expected object"):
decode_cursor(encoded, ALLOWED)
class TestEncodeAtCapsFits:
def test_max_field_lengths_fit_wire_cap(self):
# Worst-case payload: value and id at their per-field caps, with a long
# sort field name. The encoded cursor must fit within MAX_ENCODED_CURSOR_LENGTH
# so the wire cap cannot reject a cursor the encoder mints at the per-field caps.
value = "v" * MAX_CURSOR_VALUE_LENGTH
id = "i" * MAX_CURSOR_ID_LENGTH
sort_field = "very_long_sort_field_name"
encoded = encode_cursor(sort_field, value, id)
assert len(encoded) <= MAX_ENCODED_CURSOR_LENGTH
payload = decode_cursor(encoded, (sort_field,))
assert payload.value == value
assert payload.id == id
class TestDatetimeOverflow:
"""Crafted cursors with extreme micros must map to InvalidCursorError,
not OverflowError/OSError leaking as 500.
"""
@pytest.mark.parametrize(
"micros_str",
[
"999999999999999999999", # 10^21 µs — past datetime.MAX_YEAR by ~14 orders
"-999999999999999999999", # symmetric negative — pre-epoch overflow
],
)
def test_out_of_range_micros_rejected(self, micros_str):
encoded = encode_cursor("created_at", micros_str, "asset-x")
payload = decode_cursor(encoded, ALLOWED)
with pytest.raises(InvalidCursorError):
decode_cursor_time(payload)
class TestEncoderDecoderSymmetry:
"""The encoder must never mint a cursor the decoder would reject, or the
same server would 400 on a cursor it just handed out. Per-field caps keep
the encoded length below the wire cap, so a freshly minted cursor always
round-trips.
"""
def test_long_name_within_cap_round_trips(self):
"""Assets allow names up to 512 chars (`String(512)`); the cursor
encoder must round-trip a value at that cap so a freshly minted
cursor never fails decode on the next request."""
long_name = "n" * MAX_CURSOR_VALUE_LENGTH
encoded = encode_cursor("name", long_name, "asset-x")
payload = decode_cursor(encoded, ALLOWED)
assert payload.value == long_name
def test_encoder_rejects_empty_id(self):
with pytest.raises(InvalidCursorError, match="id must be non-empty"):
encode_cursor("created_at", "1", "")
def test_encoder_rejects_oversized_id(self):
with pytest.raises(InvalidCursorError, match="id exceeds maximum length"):
encode_cursor("created_at", "1", "a" * (MAX_CURSOR_ID_LENGTH + 1))
def test_encoder_rejects_oversized_value(self):
with pytest.raises(InvalidCursorError, match="value exceeds maximum length"):
encode_cursor("name", "v" * (MAX_CURSOR_VALUE_LENGTH + 1), "id-1")
def test_multibyte_value_at_cap_round_trips(self):
"""A value at the char-count cap made of multibyte characters
(e.g. 'é' = 2 UTF-8 bytes) stays under the wire cap, so it mints and
round-trips — the per-field caps, not a mint-time length check, are
what bound cursor size."""
value = "é" * MAX_CURSOR_VALUE_LENGTH
encoded = encode_cursor("name", value, "asset-multibyte")
assert len(encoded) <= MAX_ENCODED_CURSOR_LENGTH
payload = decode_cursor(encoded, ALLOWED)
assert payload.value == value
def test_escape_heavy_value_at_cap_round_trips(self):
"""JSON escape expansion is the worst case: each control character
serializes to the six-byte `\\uXXXX` form. A value of 512 of them is
the largest a cursor can get, and it still fits the wire cap, mints,
and round-trips."""
value = "\x01" * MAX_CURSOR_VALUE_LENGTH
encoded = encode_cursor("name", value, "asset-escape")
assert len(encoded) <= MAX_ENCODED_CURSOR_LENGTH
payload = decode_cursor(encoded, ALLOWED)
assert payload.value == value
class TestOrderBinding:
def test_order_baked_into_payload(self):
encoded = encode_cursor("created_at", "1", "id-1", order="asc")
payload = decode_cursor(encoded, ALLOWED)
assert payload.order == "asc"
def test_mismatched_order_rejected(self):
encoded = encode_cursor("created_at", "1", "id-1", order="desc")
with pytest.raises(InvalidCursorError, match="does not match request order"):
decode_cursor(encoded, ALLOWED, expected_order="asc")
def test_matching_order_accepted(self):
encoded = encode_cursor("created_at", "1", "id-1", order="desc")
payload = decode_cursor(encoded, ALLOWED, expected_order="desc")
assert payload.order == "desc"
def test_invalid_order_token_rejected_on_encode(self):
with pytest.raises(ValueError):
encode_cursor("created_at", "1", "id-1", order="sideways")
def test_invalid_order_token_rejected_on_decode(self):
# Hand-craft a payload with an illegal `o` value.
raw = b'{"s":"name","v":"x","id":"id-1","o":"sideways"}'
encoded = base64.urlsafe_b64encode(raw).rstrip(b"=").decode("ascii")
with pytest.raises(InvalidCursorError, match="unsupported order"):
decode_cursor(encoded, ALLOWED)
def test_cursor_without_order_rejected(self):
"""`o` is mandatory. A cursor minted without it is rejected as
malformed rather than silently walking the keyset in whatever
direction the request happens to ask for."""
raw = b'{"s":"name","v":"x","id":"id-1"}'
encoded = base64.urlsafe_b64encode(raw).rstrip(b"=").decode("ascii")
with pytest.raises(InvalidCursorError, match="missing or non-string o"):
decode_cursor(encoded, ALLOWED, expected_order="desc")

View File

@@ -0,0 +1,216 @@
"""Tests for asset enrichment (mime_type and hash population)."""
import os
from pathlib import Path
from sqlalchemy.orm import Session
from app.assets.database.models import Asset, AssetReference
from app.assets.services.file_utils import get_mtime_ns
from app.assets.scanner import (
ENRICHMENT_HASHED,
ENRICHMENT_METADATA,
ENRICHMENT_STUB,
enrich_asset,
)
def _create_stub_asset(
session: Session,
file_path: str,
asset_id: str = "test-asset-id",
reference_id: str = "test-ref-id",
name: str | None = None,
) -> tuple[Asset, AssetReference]:
"""Create a stub asset with reference for testing enrichment."""
# Use the real file's mtime so the optimistic guard in enrich_asset passes
try:
stat_result = os.stat(file_path, follow_symlinks=True)
mtime_ns = get_mtime_ns(stat_result)
except OSError:
mtime_ns = 1234567890000000000
asset = Asset(
id=asset_id,
hash=None,
size_bytes=100,
mime_type=None,
)
session.add(asset)
session.flush()
ref = AssetReference(
id=reference_id,
asset_id=asset_id,
name=name or f"test-asset-{asset_id}",
owner_id="system",
file_path=file_path,
mtime_ns=mtime_ns,
enrichment_level=ENRICHMENT_STUB,
)
session.add(ref)
session.flush()
return asset, ref
class TestEnrichAsset:
def test_extracts_mime_type_and_updates_asset(
self, db_engine, temp_dir: Path, session: Session
):
"""Verify mime_type is written to the Asset table during enrichment."""
file_path = temp_dir / "model.safetensors"
file_path.write_bytes(b"\x00" * 100)
asset, ref = _create_stub_asset(
session, str(file_path), "asset-1", "ref-1"
)
session.commit()
new_level = enrich_asset(
session,
file_path=str(file_path),
reference_id=ref.id,
asset_id=asset.id,
extract_metadata=True,
compute_hash=False,
)
assert new_level == ENRICHMENT_METADATA
session.expire_all()
updated_asset = session.get(Asset, "asset-1")
assert updated_asset is not None
assert updated_asset.mime_type == "application/safetensors"
def test_computes_hash_and_updates_asset(
self, db_engine, temp_dir: Path, session: Session
):
"""Verify hash is written to the Asset table during enrichment."""
file_path = temp_dir / "data.bin"
file_path.write_bytes(b"test content for hashing")
asset, ref = _create_stub_asset(
session, str(file_path), "asset-2", "ref-2"
)
session.commit()
new_level = enrich_asset(
session,
file_path=str(file_path),
reference_id=ref.id,
asset_id=asset.id,
extract_metadata=True,
compute_hash=True,
)
assert new_level == ENRICHMENT_HASHED
session.expire_all()
updated_asset = session.get(Asset, "asset-2")
assert updated_asset is not None
assert updated_asset.hash is not None
assert updated_asset.hash.startswith("blake3:")
def test_enrichment_updates_both_mime_and_hash(
self, db_engine, temp_dir: Path, session: Session
):
"""Verify both mime_type and hash are set when full enrichment runs."""
file_path = temp_dir / "model.safetensors"
file_path.write_bytes(b"\x00" * 50)
asset, ref = _create_stub_asset(
session, str(file_path), "asset-3", "ref-3"
)
session.commit()
enrich_asset(
session,
file_path=str(file_path),
reference_id=ref.id,
asset_id=asset.id,
extract_metadata=True,
compute_hash=True,
)
session.expire_all()
updated_asset = session.get(Asset, "asset-3")
assert updated_asset is not None
assert updated_asset.mime_type == "application/safetensors"
assert updated_asset.hash is not None
assert updated_asset.hash.startswith("blake3:")
def test_missing_file_returns_stub_level(
self, db_engine, temp_dir: Path, session: Session
):
"""Verify missing files don't cause errors and return STUB level."""
file_path = temp_dir / "nonexistent.bin"
asset, ref = _create_stub_asset(
session, str(file_path), "asset-4", "ref-4"
)
session.commit()
new_level = enrich_asset(
session,
file_path=str(file_path),
reference_id=ref.id,
asset_id=asset.id,
extract_metadata=True,
compute_hash=True,
)
assert new_level == ENRICHMENT_STUB
session.expire_all()
updated_asset = session.get(Asset, "asset-4")
assert updated_asset.mime_type is None
assert updated_asset.hash is None
def test_duplicate_hash_merges_into_existing_asset(
self, db_engine, temp_dir: Path, session: Session
):
"""Verify duplicate files merge into existing asset instead of failing."""
file_path_1 = temp_dir / "file1.bin"
file_path_2 = temp_dir / "file2.bin"
content = b"identical content"
file_path_1.write_bytes(content)
file_path_2.write_bytes(content)
asset1, ref1 = _create_stub_asset(
session, str(file_path_1), "asset-dup-1", "ref-dup-1"
)
asset2, ref2 = _create_stub_asset(
session, str(file_path_2), "asset-dup-2", "ref-dup-2"
)
session.commit()
enrich_asset(
session,
file_path=str(file_path_1),
reference_id=ref1.id,
asset_id=asset1.id,
extract_metadata=True,
compute_hash=True,
)
enrich_asset(
session,
file_path=str(file_path_2),
reference_id=ref2.id,
asset_id=asset2.id,
extract_metadata=True,
compute_hash=True,
)
session.expire_all()
updated_asset1 = session.get(Asset, "asset-dup-1")
assert updated_asset1 is not None
assert updated_asset1.hash is not None
updated_asset2 = session.get(Asset, "asset-dup-2")
assert updated_asset2 is None
updated_ref2 = session.get(AssetReference, "ref-dup-2")
assert updated_ref2 is not None
assert updated_ref2.asset_id == "asset-dup-1"

View File

@@ -0,0 +1,86 @@
"""Tests for the image_dimensions service."""
from __future__ import annotations
from pathlib import Path
import pytest
from PIL import Image
from app.assets.services.image_dimensions import extract_image_dimensions
def _make_png(path: Path, size: tuple[int, int]) -> Path:
img = Image.new("RGB", size, color=(123, 45, 67))
img.save(path, format="PNG")
return path
def _make_jpeg(path: Path, size: tuple[int, int]) -> Path:
img = Image.new("RGB", size, color=(10, 20, 30))
img.save(path, format="JPEG", quality=80)
return path
class TestExtractImageDimensions:
def test_extracts_png_dimensions(self, tmp_path: Path):
f = _make_png(tmp_path / "rect.png", (320, 240))
result = extract_image_dimensions(str(f), mime_type="image/png")
assert result == {"kind": "image", "width": 320, "height": 240}
def test_extracts_jpeg_dimensions(self, tmp_path: Path):
f = _make_jpeg(tmp_path / "shot.jpg", (1920, 1080))
result = extract_image_dimensions(str(f), mime_type="image/jpeg")
assert result == {"kind": "image", "width": 1920, "height": 1080}
def test_works_when_mime_type_is_none(self, tmp_path: Path):
f = _make_png(tmp_path / "no_mime.png", (50, 100))
result = extract_image_dimensions(str(f), mime_type=None)
assert result == {"kind": "image", "width": 50, "height": 100}
def test_skips_non_image_mime_without_touching_file(self, tmp_path: Path):
# Path doesn't need to exist — non-image MIME short-circuits.
result = extract_image_dimensions(
str(tmp_path / "model.safetensors"),
mime_type="application/octet-stream",
)
assert result is None
@pytest.mark.parametrize(
"mime",
["application/json", "text/plain", "video/mp4", "audio/mpeg"],
)
def test_skips_all_non_image_mime_types(self, tmp_path: Path, mime: str):
f = tmp_path / "file.bin"
f.write_bytes(b"\x00\x01\x02")
assert extract_image_dimensions(str(f), mime_type=mime) is None
def test_returns_none_for_missing_file(self, tmp_path: Path):
result = extract_image_dimensions(
str(tmp_path / "does_not_exist.png"), mime_type="image/png"
)
assert result is None
def test_returns_none_for_corrupt_image(self, tmp_path: Path):
f = tmp_path / "corrupt.png"
f.write_bytes(b"not actually a png file")
result = extract_image_dimensions(str(f), mime_type="image/png")
assert result is None
def test_returns_none_for_empty_file(self, tmp_path: Path):
f = tmp_path / "empty.png"
f.write_bytes(b"")
result = extract_image_dimensions(str(f), mime_type="image/png")
assert result is None

View File

@@ -0,0 +1,488 @@
"""Tests for ingest services."""
from contextlib import contextmanager
from pathlib import Path
from unittest.mock import patch
import pytest
from PIL import Image
from sqlalchemy.orm import Session as SASession, Session
from app.assets.database.models import Asset, AssetReference, AssetReferenceTag, Tag
from app.assets.database.queries import get_reference_tags
from app.assets.helpers import get_utc_now
from app.assets.services.ingest import (
_ingest_file_from_path,
_register_existing_asset,
ingest_existing_file,
)
def _make_png(path: Path, size: tuple[int, int]) -> Path:
Image.new("RGB", size, color=(80, 120, 200)).save(path, format="PNG")
return path
class TestIngestFileFromPath:
def test_creates_asset_and_reference(self, mock_create_session, temp_dir: Path, session: Session):
file_path = temp_dir / "test_file.bin"
file_path.write_bytes(b"test content")
result = _ingest_file_from_path(
abs_path=str(file_path),
asset_hash="blake3:abc123",
size_bytes=12,
mtime_ns=1234567890000000000,
mime_type="application/octet-stream",
)
assert result.asset_created is True
assert result.ref_created is True
assert result.reference_id is not None
# Verify DB state
assets = session.query(Asset).all()
assert len(assets) == 1
assert assets[0].hash == "blake3:abc123"
refs = session.query(AssetReference).all()
assert len(refs) == 1
assert refs[0].file_path == str(file_path)
def test_creates_reference_when_name_provided(self, mock_create_session, temp_dir: Path, session: Session):
file_path = temp_dir / "model.safetensors"
file_path.write_bytes(b"model data")
result = _ingest_file_from_path(
abs_path=str(file_path),
asset_hash="blake3:def456",
size_bytes=10,
mtime_ns=1234567890000000000,
mime_type="application/octet-stream",
info_name="My Model",
owner_id="user1",
)
assert result.asset_created is True
assert result.reference_id is not None
ref = session.query(AssetReference).first()
assert ref is not None
assert ref.name == "My Model"
assert ref.owner_id == "user1"
def test_creates_tags_when_provided(self, mock_create_session, temp_dir: Path, session: Session):
file_path = temp_dir / "tagged.bin"
file_path.write_bytes(b"data")
result = _ingest_file_from_path(
abs_path=str(file_path),
asset_hash="blake3:ghi789",
size_bytes=4,
mtime_ns=1234567890000000000,
info_name="Tagged Asset",
tags=["models", "checkpoints"],
)
assert result.reference_id is not None
# Verify tags were created and linked
tags = session.query(Tag).all()
tag_names = {t.name for t in tags}
assert "models" in tag_names
assert "checkpoints" in tag_names
ref_tags = get_reference_tags(session, reference_id=result.reference_id)
assert set(ref_tags) == {"models", "checkpoints"}
def test_idempotent_upsert(self, mock_create_session, temp_dir: Path, session: Session):
file_path = temp_dir / "dup.bin"
file_path.write_bytes(b"content")
# First ingest
r1 = _ingest_file_from_path(
abs_path=str(file_path),
asset_hash="blake3:repeat",
size_bytes=7,
mtime_ns=1234567890000000000,
)
assert r1.asset_created is True
# Second ingest with same hash - should update, not create
r2 = _ingest_file_from_path(
abs_path=str(file_path),
asset_hash="blake3:repeat",
size_bytes=7,
mtime_ns=1234567890000000001, # different mtime
)
assert r2.asset_created is False
assert r2.ref_created is False
assert r2.ref_updated is True
# Still only one asset
assets = session.query(Asset).all()
assert len(assets) == 1
def test_validates_preview_id(self, mock_create_session, temp_dir: Path, session: Session):
file_path = temp_dir / "with_preview.bin"
file_path.write_bytes(b"data")
# Create a preview asset and reference
preview_asset = Asset(hash="blake3:preview", size_bytes=100)
session.add(preview_asset)
session.flush()
from app.assets.helpers import get_utc_now
now = get_utc_now()
preview_ref = AssetReference(
asset_id=preview_asset.id, name="preview.png", owner_id="",
created_at=now, updated_at=now, last_access_time=now,
)
session.add(preview_ref)
session.commit()
preview_id = preview_ref.id
result = _ingest_file_from_path(
abs_path=str(file_path),
asset_hash="blake3:main",
size_bytes=4,
mtime_ns=1234567890000000000,
info_name="With Preview",
preview_id=preview_id,
)
assert result.reference_id is not None
ref = session.query(AssetReference).filter_by(id=result.reference_id).first()
assert ref.preview_id == preview_id
def test_invalid_preview_id_is_cleared(self, mock_create_session, temp_dir: Path, session: Session):
file_path = temp_dir / "bad_preview.bin"
file_path.write_bytes(b"data")
result = _ingest_file_from_path(
abs_path=str(file_path),
asset_hash="blake3:badpreview",
size_bytes=4,
mtime_ns=1234567890000000000,
info_name="Bad Preview",
preview_id="nonexistent-uuid",
)
assert result.reference_id is not None
ref = session.query(AssetReference).filter_by(id=result.reference_id).first()
assert ref.preview_id is None
class TestRegisterExistingAsset:
def test_creates_reference_for_existing_asset(self, mock_create_session, session: Session):
# Create existing asset
asset = Asset(hash="blake3:existing", size_bytes=1024, mime_type="image/png")
session.add(asset)
session.commit()
result = _register_existing_asset(
asset_hash="blake3:existing",
name="Registered Asset",
user_metadata={"key": "value"},
tags=["models"],
)
assert result.created is True
assert "models" in result.tags
# Verify by re-fetching from DB
session.expire_all()
refs = session.query(AssetReference).filter_by(name="Registered Asset").all()
assert len(refs) == 1
def test_creates_new_reference_even_with_same_name(self, mock_create_session, session: Session):
# Create asset and reference
asset = Asset(hash="blake3:withref", size_bytes=512)
session.add(asset)
session.flush()
from app.assets.helpers import get_utc_now
ref = AssetReference(
owner_id="",
name="Existing Ref",
asset_id=asset.id,
created_at=get_utc_now(),
updated_at=get_utc_now(),
last_access_time=get_utc_now(),
)
session.add(ref)
session.flush()
ref_id = ref.id
session.commit()
result = _register_existing_asset(
asset_hash="blake3:withref",
name="Existing Ref",
owner_id="",
)
# Multiple files with same name are allowed
assert result.created is True
# Verify two AssetReferences exist for this name
session.expire_all()
refs = session.query(AssetReference).filter_by(name="Existing Ref").all()
assert len(refs) == 2
assert ref_id in [r.id for r in refs]
def test_raises_for_nonexistent_hash(self, mock_create_session):
with pytest.raises(ValueError, match="No asset with hash"):
_register_existing_asset(
asset_hash="blake3:doesnotexist",
name="Fail",
)
def test_applies_tags_to_new_reference(self, mock_create_session, session: Session):
asset = Asset(hash="blake3:tagged", size_bytes=256)
session.add(asset)
session.commit()
result = _register_existing_asset(
asset_hash="blake3:tagged",
name="Tagged Ref",
tags=["alpha", "beta"],
)
assert result.created is True
assert set(result.tags) == {"alpha", "beta"}
class TestIngestExistingFileTagFK:
"""Regression: ingest_existing_file must seed Tag rows before inserting
AssetReferenceTag rows, otherwise FK enforcement raises IntegrityError."""
def test_creates_tag_rows_before_reference_tags(self, db_engine_fk, temp_dir: Path):
"""With PRAGMA foreign_keys=ON, tags must exist in the tags table
before they can be referenced in asset_reference_tags."""
@contextmanager
def _create_session():
with SASession(db_engine_fk) as sess:
yield sess
file_path = temp_dir / "output.png"
file_path.write_bytes(b"image data")
with patch("app.assets.services.ingest.create_session", _create_session), \
patch(
"app.assets.services.ingest.get_name_and_tags_from_asset_path",
return_value=("output.png", ["output"]),
):
result = ingest_existing_file(
abs_path=str(file_path),
extra_tags=["my-job"],
)
assert result is True
with SASession(db_engine_fk) as sess:
tag_names = {t.name for t in sess.query(Tag).all()}
assert "output" in tag_names
assert "my-job" in tag_names
ref_tags = sess.query(AssetReferenceTag).all()
ref_tag_names = {rt.tag_name for rt in ref_tags}
assert "output" in ref_tag_names
class TestIngestImageDimensions:
"""system_metadata should carry {kind, width, height} for image assets."""
def test_image_asset_emits_dimensions(
self, mock_create_session, temp_dir: Path, session: Session
):
f = _make_png(temp_dir / "shot.png", (640, 480))
result = _ingest_file_from_path(
abs_path=str(f),
asset_hash="blake3:img1",
size_bytes=f.stat().st_size,
mtime_ns=1234567890000000000,
mime_type="image/png",
)
ref = session.query(AssetReference).filter_by(id=result.reference_id).first()
assert ref.system_metadata == {
"kind": "image",
"width": 640,
"height": 480,
}
def test_non_image_asset_leaves_system_metadata_empty(
self, mock_create_session, temp_dir: Path, session: Session
):
f = temp_dir / "model.safetensors"
f.write_bytes(b"not an image")
result = _ingest_file_from_path(
abs_path=str(f),
asset_hash="blake3:safetensors1",
size_bytes=f.stat().st_size,
mtime_ns=1234567890000000000,
mime_type="application/octet-stream",
)
ref = session.query(AssetReference).filter_by(id=result.reference_id).first()
assert ref.system_metadata in (None, {})
def test_preserves_existing_system_metadata_keys(
self, mock_create_session, temp_dir: Path, session: Session
):
f = _make_png(temp_dir / "annotated.png", (100, 200))
# First pass populates a sentinel system_metadata key (simulating prior
# enricher write).
result = _ingest_file_from_path(
abs_path=str(f),
asset_hash="blake3:img-merge",
size_bytes=f.stat().st_size,
mtime_ns=1234567890000000000,
mime_type="image/png",
)
ref = session.query(AssetReference).filter_by(id=result.reference_id).first()
ref.system_metadata = {**(ref.system_metadata or {}), "source_url": "https://example/x.png"}
session.commit()
# Second pass with the same path triggers the merge code path again.
_ingest_file_from_path(
abs_path=str(f),
asset_hash="blake3:img-merge",
size_bytes=f.stat().st_size,
mtime_ns=1234567890000000001,
mime_type="image/png",
)
session.refresh(ref)
assert ref.system_metadata["kind"] == "image"
assert ref.system_metadata["width"] == 100
assert ref.system_metadata["height"] == 200
assert ref.system_metadata["source_url"] == "https://example/x.png"
class TestRegisterExistingAssetBackfill:
"""The from-hash path back-fills dimensions from a sibling reference."""
def _add_reference(
self,
session: Session,
asset: Asset,
name: str,
system_metadata: dict | None = None,
) -> AssetReference:
now = get_utc_now()
ref = AssetReference(
asset_id=asset.id,
name=name,
owner_id="",
created_at=now,
updated_at=now,
last_access_time=now,
system_metadata=system_metadata or {},
)
session.add(ref)
session.flush()
return ref
def test_backfills_dimensions_from_sibling_image_reference(
self, mock_create_session, session: Session
):
asset = Asset(hash="blake3:shared", size_bytes=2048, mime_type="image/png")
session.add(asset)
session.flush()
self._add_reference(
session,
asset,
name="original.png",
system_metadata={"kind": "image", "width": 800, "height": 600},
)
session.commit()
result = _register_existing_asset(
asset_hash="blake3:shared",
name="from_hash.png",
owner_id="user-x",
)
ref = session.query(AssetReference).filter_by(id=result.ref.id).first()
assert ref.system_metadata.get("kind") == "image"
assert ref.system_metadata.get("width") == 800
assert ref.system_metadata.get("height") == 600
def test_no_backfill_when_sibling_has_no_image_metadata(
self, mock_create_session, session: Session
):
asset = Asset(hash="blake3:nodims", size_bytes=2048, mime_type="image/png")
session.add(asset)
session.flush()
self._add_reference(
session,
asset,
name="original.png",
system_metadata={"base_model": "flux"}, # no kind=image
)
session.commit()
result = _register_existing_asset(
asset_hash="blake3:nodims",
name="from_hash.png",
owner_id="user-x",
)
ref = session.query(AssetReference).filter_by(id=result.ref.id).first()
meta = ref.system_metadata or {}
assert "kind" not in meta
assert "width" not in meta
assert "height" not in meta
def test_no_backfill_when_no_sibling_exists(
self, mock_create_session, session: Session
):
asset = Asset(hash="blake3:lonely", size_bytes=1024, mime_type="image/png")
session.add(asset)
session.commit()
result = _register_existing_asset(
asset_hash="blake3:lonely",
name="solo.png",
owner_id="user-x",
)
ref = session.query(AssetReference).filter_by(id=result.ref.id).first()
assert ref.system_metadata in (None, {})
def test_backfill_preserves_caller_supplied_keys(
self, mock_create_session, session: Session
):
asset = Asset(hash="blake3:preserve", size_bytes=2048, mime_type="image/png")
session.add(asset)
session.flush()
self._add_reference(
session,
asset,
name="original.png",
system_metadata={"kind": "image", "width": 1024, "height": 768},
)
session.commit()
# Simulate a from-hash path where the new reference already carries
# some system_metadata (e.g. a download-provenance source_url written
# by an earlier step). The back-fill must merge dim keys without
# clobbering existing keys.
result = _register_existing_asset(
asset_hash="blake3:preserve",
name="from_hash.png",
owner_id="user-x",
)
ref = session.query(AssetReference).filter_by(id=result.ref.id).first()
# Seed a sentinel key and re-run back-fill via a second register call
# to exercise the merge path with pre-existing data.
ref.system_metadata = {**(ref.system_metadata or {}), "source_url": "https://example/p"}
session.commit()
assert ref.system_metadata.get("source_url") == "https://example/p"
assert ref.system_metadata.get("kind") == "image"
assert ref.system_metadata.get("width") == 1024
assert ref.system_metadata.get("height") == 768

View File

@@ -0,0 +1,81 @@
"""Tests for path_utils asset category resolution."""
import os
import tempfile
from pathlib import Path
from unittest.mock import patch
import pytest
from app.assets.services.path_utils import get_asset_category_and_relative_path
@pytest.fixture
def fake_dirs():
"""Create temporary input, output, and temp directories."""
with tempfile.TemporaryDirectory() as root:
root_path = Path(root)
input_dir = root_path / "input"
output_dir = root_path / "output"
temp_dir = root_path / "temp"
models_dir = root_path / "models" / "checkpoints"
for d in (input_dir, output_dir, temp_dir, models_dir):
d.mkdir(parents=True)
with patch("app.assets.services.path_utils.folder_paths") as mock_fp:
mock_fp.get_input_directory.return_value = str(input_dir)
mock_fp.get_output_directory.return_value = str(output_dir)
mock_fp.get_temp_directory.return_value = str(temp_dir)
with patch(
"app.assets.services.path_utils.get_comfy_models_folders",
return_value=[("checkpoints", [str(models_dir)])],
):
yield {
"input": input_dir,
"output": output_dir,
"temp": temp_dir,
"models": models_dir,
}
class TestGetAssetCategoryAndRelativePath:
def test_input_file(self, fake_dirs):
f = fake_dirs["input"] / "photo.png"
f.touch()
cat, rel = get_asset_category_and_relative_path(str(f))
assert cat == "input"
assert rel == "photo.png"
def test_output_file(self, fake_dirs):
f = fake_dirs["output"] / "result.png"
f.touch()
cat, rel = get_asset_category_and_relative_path(str(f))
assert cat == "output"
assert rel == "result.png"
def test_temp_file(self, fake_dirs):
"""Regression: temp files must be categorised, not raise ValueError."""
f = fake_dirs["temp"] / "GLSLShader_output_00004_.png"
f.touch()
cat, rel = get_asset_category_and_relative_path(str(f))
assert cat == "temp"
assert rel == "GLSLShader_output_00004_.png"
def test_temp_file_in_subfolder(self, fake_dirs):
sub = fake_dirs["temp"] / "sub"
sub.mkdir()
f = sub / "ComfyUI_temp_tczip_00004_.png"
f.touch()
cat, rel = get_asset_category_and_relative_path(str(f))
assert cat == "temp"
assert os.path.normpath(rel) == os.path.normpath("sub/ComfyUI_temp_tczip_00004_.png")
def test_model_file(self, fake_dirs):
f = fake_dirs["models"] / "model.safetensors"
f.touch()
cat, rel = get_asset_category_and_relative_path(str(f))
assert cat == "models"
def test_unknown_path_raises(self, fake_dirs):
with pytest.raises(ValueError, match="not within"):
get_asset_category_and_relative_path("/some/random/path.png")

View File

@@ -0,0 +1,123 @@
"""Tests for list_tag_histogram service function."""
from sqlalchemy.orm import Session
from app.assets.database.models import Asset, AssetReference
from app.assets.database.queries import ensure_tags_exist, add_tags_to_reference
from app.assets.helpers import get_utc_now
from app.assets.services.tagging import list_tag_histogram
def _make_asset(session: Session, hash_val: str = "blake3:test") -> Asset:
asset = Asset(hash=hash_val, size_bytes=1024)
session.add(asset)
session.flush()
return asset
def _make_reference(
session: Session,
asset: Asset,
name: str = "test",
owner_id: str = "",
) -> AssetReference:
now = get_utc_now()
ref = AssetReference(
owner_id=owner_id,
name=name,
asset_id=asset.id,
created_at=now,
updated_at=now,
last_access_time=now,
)
session.add(ref)
session.flush()
return ref
class TestListTagHistogram:
def test_returns_counts_for_all_tags(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["alpha", "beta"])
a1 = _make_asset(session, "blake3:aaa")
r1 = _make_reference(session, a1, name="r1")
add_tags_to_reference(session, reference_id=r1.id, tags=["alpha", "beta"])
a2 = _make_asset(session, "blake3:bbb")
r2 = _make_reference(session, a2, name="r2")
add_tags_to_reference(session, reference_id=r2.id, tags=["alpha"])
session.commit()
result = list_tag_histogram()
assert result["alpha"] == 2
assert result["beta"] == 1
def test_empty_when_no_assets(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["unused"])
session.commit()
result = list_tag_histogram()
assert result == {}
def test_include_tags_filter(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["models", "loras", "input"])
a1 = _make_asset(session, "blake3:aaa")
r1 = _make_reference(session, a1, name="r1")
add_tags_to_reference(session, reference_id=r1.id, tags=["models", "loras"])
a2 = _make_asset(session, "blake3:bbb")
r2 = _make_reference(session, a2, name="r2")
add_tags_to_reference(session, reference_id=r2.id, tags=["input"])
session.commit()
result = list_tag_histogram(include_tags=["models"])
# Only r1 has "models", so only its tags appear
assert "models" in result
assert "loras" in result
assert "input" not in result
def test_exclude_tags_filter(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["models", "loras", "input"])
a1 = _make_asset(session, "blake3:aaa")
r1 = _make_reference(session, a1, name="r1")
add_tags_to_reference(session, reference_id=r1.id, tags=["models", "loras"])
a2 = _make_asset(session, "blake3:bbb")
r2 = _make_reference(session, a2, name="r2")
add_tags_to_reference(session, reference_id=r2.id, tags=["input"])
session.commit()
result = list_tag_histogram(exclude_tags=["models"])
# r1 excluded, only r2's tags remain
assert "input" in result
assert "loras" not in result
def test_name_contains_filter(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["alpha", "beta"])
a1 = _make_asset(session, "blake3:aaa")
r1 = _make_reference(session, a1, name="my_model.safetensors")
add_tags_to_reference(session, reference_id=r1.id, tags=["alpha"])
a2 = _make_asset(session, "blake3:bbb")
r2 = _make_reference(session, a2, name="picture.png")
add_tags_to_reference(session, reference_id=r2.id, tags=["beta"])
session.commit()
result = list_tag_histogram(name_contains="model")
assert "alpha" in result
assert "beta" not in result
def test_limit_caps_results(self, mock_create_session, session: Session):
tags = [f"tag{i}" for i in range(10)]
ensure_tags_exist(session, tags)
a = _make_asset(session, "blake3:aaa")
r = _make_reference(session, a, name="r1")
add_tags_to_reference(session, reference_id=r.id, tags=tags)
session.commit()
result = list_tag_histogram(limit=3)
assert len(result) == 3

View File

@@ -0,0 +1,197 @@
"""Tests for tagging services."""
import pytest
from sqlalchemy.orm import Session
from app.assets.database.models import Asset, AssetReference
from app.assets.database.queries import ensure_tags_exist, add_tags_to_reference
from app.assets.helpers import get_utc_now
from app.assets.services import apply_tags, remove_tags, list_tags
def _make_asset(session: Session, hash_val: str = "blake3:test") -> Asset:
asset = Asset(hash=hash_val, size_bytes=1024)
session.add(asset)
session.flush()
return asset
def _make_reference(
session: Session,
asset: Asset,
name: str = "test",
owner_id: str = "",
) -> AssetReference:
now = get_utc_now()
ref = AssetReference(
owner_id=owner_id,
name=name,
asset_id=asset.id,
created_at=now,
updated_at=now,
last_access_time=now,
)
session.add(ref)
session.flush()
return ref
class TestApplyTags:
def test_adds_new_tags(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset)
session.commit()
result = apply_tags(
reference_id=ref.id,
tags=["alpha", "beta"],
)
assert set(result.added) == {"alpha", "beta"}
assert result.already_present == []
assert set(result.total_tags) == {"alpha", "beta"}
def test_reports_already_present(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset)
ensure_tags_exist(session, ["existing"])
add_tags_to_reference(session, reference_id=ref.id, tags=["existing"])
session.commit()
result = apply_tags(
reference_id=ref.id,
tags=["existing", "new"],
)
assert result.added == ["new"]
assert result.already_present == ["existing"]
def test_raises_for_nonexistent_ref(self, mock_create_session):
with pytest.raises(ValueError, match="not found"):
apply_tags(reference_id="nonexistent", tags=["x"])
def test_raises_for_wrong_owner(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset, owner_id="user1")
session.commit()
with pytest.raises(PermissionError, match="not owner"):
apply_tags(
reference_id=ref.id,
tags=["new"],
owner_id="user2",
)
class TestRemoveTags:
def test_removes_tags(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset)
ensure_tags_exist(session, ["a", "b", "c"])
add_tags_to_reference(session, reference_id=ref.id, tags=["a", "b", "c"])
session.commit()
result = remove_tags(
reference_id=ref.id,
tags=["a", "b"],
)
assert set(result.removed) == {"a", "b"}
assert result.not_present == []
assert result.total_tags == ["c"]
def test_reports_not_present(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset)
ensure_tags_exist(session, ["present"])
add_tags_to_reference(session, reference_id=ref.id, tags=["present"])
session.commit()
result = remove_tags(
reference_id=ref.id,
tags=["present", "absent"],
)
assert result.removed == ["present"]
assert result.not_present == ["absent"]
def test_raises_for_nonexistent_ref(self, mock_create_session):
with pytest.raises(ValueError, match="not found"):
remove_tags(reference_id="nonexistent", tags=["x"])
def test_raises_for_wrong_owner(self, mock_create_session, session: Session):
asset = _make_asset(session)
ref = _make_reference(session, asset, owner_id="user1")
session.commit()
with pytest.raises(PermissionError, match="not owner"):
remove_tags(
reference_id=ref.id,
tags=["x"],
owner_id="user2",
)
class TestListTags:
def test_returns_tags_with_counts(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["used", "unused"])
asset = _make_asset(session)
ref = _make_reference(session, asset)
add_tags_to_reference(session, reference_id=ref.id, tags=["used"])
session.commit()
rows, total = list_tags()
tag_dict = {name: count for name, count in rows}
assert tag_dict["used"] == 1
assert tag_dict["unused"] == 0
assert total == 2
def test_excludes_zero_counts(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["used", "unused"])
asset = _make_asset(session)
ref = _make_reference(session, asset)
add_tags_to_reference(session, reference_id=ref.id, tags=["used"])
session.commit()
rows, total = list_tags(include_zero=False)
tag_names = {name for name, _ in rows}
assert "used" in tag_names
assert "unused" not in tag_names
def test_prefix_filter(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["alpha", "beta", "alphabet"])
session.commit()
rows, _ = list_tags(prefix="alph")
tag_names = {name for name, _ in rows}
assert tag_names == {"alpha", "alphabet"}
def test_order_by_name(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["zebra", "alpha", "middle"])
session.commit()
rows, _ = list_tags(order="name_asc")
names = [name for name, _ in rows]
assert names == ["alpha", "middle", "zebra"]
def test_pagination(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["a", "b", "c", "d", "e"])
session.commit()
rows, total = list_tags(limit=2, offset=1, order="name_asc")
assert total == 5
assert len(rows) == 2
names = [name for name, _ in rows]
assert names == ["b", "c"]
def test_clamps_limit(self, mock_create_session, session: Session):
ensure_tags_exist(session, ["a"])
session.commit()
# Service should clamp limit to max 1000
rows, _ = list_tags(limit=2000)
assert len(rows) <= 1000