629e1ba4ea
engine.py held four unrelated things: what the tables are, how to open a connection, how to read a database's state, and the Store that coordinates writes. At 1240 lines the Store's own concerns — locks, migrations, vacuum, tags — were hard to find among them. Table records, Arrow schemas, index_specs, ensure_indexes, REQUIRED_TABLES and query_to_pydantic move to store/schema.py, which imports nothing from haiku.rag: it describes the tables and never opens or mutates one. gather_database_info, get_database_stats, DatabaseInfo and its result models move to store/info.py. Nothing in Store calls them — they are read paths for the CLI, doctor, inspector and ingester API — so info depends on engine and not the reverse. engine.py keeps the Store, ConnectionMode, connect_lancedb, the tag helpers and the restore-order and retention constants. No re-exports: importers point at the new modules. test_app_info_uses_connect_lancedb_for_remote patched haiku.rag.store.engine.connect_lancedb; gather_database_info now binds that name in info.py, so the patch targets where the call is looked up.
161 lines
6.7 KiB
Python
161 lines
6.7 KiB
Python
import lancedb
|
|
import pytest
|
|
|
|
from haiku.rag.store.engine import Store
|
|
from haiku.rag.store.exceptions import MigrationRequiredError
|
|
from haiku.rag.store.models.document import Document
|
|
from haiku.rag.store.repositories.document import DocumentRepository
|
|
from tests.store.legacy_documents import (
|
|
LegacyDocumentRecord,
|
|
seed_legacy_documents,
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_create_rolls_back_meta_when_documents_write_fails(temp_db_path):
|
|
"""A failed documents write must not leave an orphan document_meta row that
|
|
list_all/count would surface (they read document_meta). The rollback must be
|
|
targeted — it deletes only the failed row, leaving other documents intact."""
|
|
async with Store(temp_db_path, create=True, skip_migration_check=True) as store:
|
|
repo = DocumentRepository(store)
|
|
|
|
# A pre-existing document that must survive the failed create's rollback.
|
|
good = await repo.create(Document(content="keep", uri="mem://keep"))
|
|
assert good.id is not None
|
|
|
|
original_add = store.documents_table.add
|
|
|
|
async def boom(*_args, **_kwargs):
|
|
raise RuntimeError("documents write failed")
|
|
|
|
store.documents_table.add = boom
|
|
with pytest.raises(RuntimeError, match="documents write failed"):
|
|
await repo.create(Document(content="x", uri="mem://ghost"))
|
|
store.documents_table.add = original_add
|
|
|
|
# The ghost's meta row was deleted; the good document is untouched.
|
|
assert await repo.count() == 1
|
|
assert [d.id for d in await repo.list_all()] == [good.id]
|
|
assert await store.document_meta_table.count_rows() == 1
|
|
assert await repo.get_by_uri("mem://ghost") is None
|
|
fetched = await repo.get_by_id(good.id)
|
|
assert fetched is not None and fetched.uri == "mem://keep"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_update_missing_id_does_not_create_ghost(temp_db_path):
|
|
"""update()/update_meta() for an id with no documents row must not insert a
|
|
document_meta row — otherwise it would show up in list_all/count while
|
|
get_by_id returns None."""
|
|
async with Store(temp_db_path, create=True, skip_migration_check=True) as store:
|
|
repo = DocumentRepository(store)
|
|
|
|
await repo.update(Document(id="missing", content="x", uri="u"))
|
|
|
|
assert await repo.count() == 0
|
|
assert await repo.list_all() == []
|
|
assert await store.documents_table.count_rows() == 0
|
|
assert await store.document_meta_table.count_rows() == 0
|
|
assert await repo.get_by_id("missing") is None
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_opening_legacy_db_raises_migration_without_mutating(temp_db_path):
|
|
"""Opening a pre-0.58 DB (no document_meta) must raise MigrationRequiredError
|
|
up front — in both writable and read-only mode — and must not mutate the DB
|
|
by creating the new table on open."""
|
|
async with Store(temp_db_path, create=True, skip_migration_check=True) as store:
|
|
await seed_legacy_documents(
|
|
store,
|
|
[LegacyDocumentRecord(id="d", content="x", uri="u", metadata="{}")],
|
|
)
|
|
# A real pre-0.58 DB has no document_meta table.
|
|
await store.db.drop_table("document_meta")
|
|
await store.set_haiku_version("0.56.0")
|
|
|
|
# Writable open: pending migration surfaces before any table creation.
|
|
with pytest.raises(MigrationRequiredError):
|
|
async with Store(temp_db_path):
|
|
pass
|
|
|
|
# Read-only open: must also be MigrationRequiredError (not ReadOnlyError).
|
|
with pytest.raises(MigrationRequiredError):
|
|
async with Store(temp_db_path, read_only=True):
|
|
pass
|
|
|
|
# The failed opens did not create document_meta.
|
|
raw = await lancedb.connect_async(str(temp_db_path))
|
|
assert "document_meta" not in (await raw.list_tables()).tables
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_migrate_creates_and_populates_document_meta(temp_db_path):
|
|
"""The migrate path (skip_migration_check) still creates and fills
|
|
document_meta for a legacy DB."""
|
|
async with Store(temp_db_path, create=True, skip_migration_check=True) as store:
|
|
await seed_legacy_documents(
|
|
store,
|
|
[LegacyDocumentRecord(id="d", content="x", uri="u", metadata="{}")],
|
|
)
|
|
await store.db.drop_table("document_meta")
|
|
await store.set_haiku_version("0.56.0")
|
|
|
|
async with Store(temp_db_path, skip_migration_check=True) as store:
|
|
await store.migrate()
|
|
assert "document_meta" in (await store.db.list_tables()).tables
|
|
repo = DocumentRepository(store)
|
|
doc = await repo.get_by_id("d")
|
|
assert doc is not None and doc.uri == "u"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_repository_empty_and_missing_id_paths(temp_db_path):
|
|
"""Cover the repository's early-return branches for empty input and
|
|
missing ids, plus get_content."""
|
|
async with Store(temp_db_path, create=True, skip_migration_check=True) as store:
|
|
repo = DocumentRepository(store)
|
|
|
|
assert await repo.create([]) == []
|
|
assert await repo.get_content("nope") is None
|
|
assert await repo.get_docling_data("nope") is None
|
|
assert await repo.get_pages_data("nope") is None
|
|
assert await repo.delete("nope") is False
|
|
|
|
doc = await repo.create(Document(content="hello body", uri="u1"))
|
|
assert doc.id is not None
|
|
assert await repo.get_content(doc.id) == "hello body"
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_batch_create_rolls_back_meta_on_failure(temp_db_path, monkeypatch):
|
|
"""The list create path also rolls back its document_meta rows if the
|
|
documents write fails."""
|
|
async with Store(temp_db_path, create=True, skip_migration_check=True) as store:
|
|
repo = DocumentRepository(store)
|
|
|
|
async def boom(*_a, **_k):
|
|
raise RuntimeError("documents add failed")
|
|
|
|
monkeypatch.setattr(store.documents_table, "add", boom)
|
|
with pytest.raises(RuntimeError, match="documents add failed"):
|
|
await repo.create(
|
|
[Document(content="x", uri="u1"), Document(content="y", uri="u2")]
|
|
)
|
|
monkeypatch.undo()
|
|
|
|
assert await store.documents_table.count_rows() == 0
|
|
assert await store.document_meta_table.count_rows() == 0
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_get_by_uri_with_orphan_meta_returns_none(temp_db_path):
|
|
"""Defensive: a document_meta row whose documents row is missing (an
|
|
invariant violation) resolves to None, not a half-hydrated document."""
|
|
from haiku.rag.store.schema import DocumentMetaRecord
|
|
|
|
async with Store(temp_db_path, create=True, skip_migration_check=True) as store:
|
|
repo = DocumentRepository(store)
|
|
await store.document_meta_table.add(
|
|
[DocumentMetaRecord(id="ghost", uri="u-ghost", metadata="{}")]
|
|
)
|
|
assert await repo.get_by_uri("u-ghost") is None
|