Files
paperless-ngx/src/paperless_ai/tests/test_tables.py
T
Trenton HandClaude Sonnet 5 e5b27df99c Feature: vector store schema v2 document_chunks/document_meta side tables, INTEGER document_id, point-delete (#13435)
* Feature: schema v2 -- document_chunks/document_meta side tables, document_id INTEGER, point-delete

Rewrites the sqlite-vec vector store's on-disk schema: document_id becomes
an INTEGER vec0 metadata column (was TEXT), modified moves out of vec0 into
a new document_meta side table, and a new document_chunks side table gives
O(1) per-document chunk lookup for delete/upsert instead of a full vec0
scan. compact() now streams document_chunks and document_meta across the
file-swap rebuild too (previously document_meta would have gone silently
empty after the first compaction). drop_table() clears both side tables.

Adds the single frozen m0001_v1_to_v2 migration, converting a real,
historically-shaped v1 store (the shape shipped since v3.0.0) into the v2
shape in one streaming pass, with its own hardcoded DDL rather than
delegating to any "current schema" helper.

SCHEMA_VERSION bumps 1 -> 2.

* Fix: strengthen two vacuous Task 4 regression tests

test_migration_never_delegates_to_current_schema_helpers never actually ran
the migration (missing check_and_run_migrations() call) and its source-text
assertion was tautological (the "or DROP TABLE in source" clause was always
true). Now runs the real migration and asserts spy call counts instead:
DocumentChunksTable.create/DocumentMetaTable.create are each called exactly
3 times (construction, rebuild temp file, post-swap reopen -- all via
_open_connection, never from inside apply()), and _create_vec_table is
never called from the migration path.

test_drop_table_clears_modified_times asserted via get_modified_times(),
which short-circuits on table_exists() -- checking only the vec0 table that
drop_table() drops first -- so the assertion held even if
DocumentMetaTable.delete_all() were never called. Now asserts directly
against document_meta and document_chunks row counts.

* Perf: dedupe table_exists() lookups, atomic insert counter, fewer connections in update_llm_index()

* Fix: guard compact() against unmigrated stores, apply final-review cleanups

compact() had no migration guard: on a v1-schema store, document_chunks
reads 0 (freshly created empty) while total_inserts reflects the real
cumulative count, so the bloat check nearly always rebuilt -- silently
losing document_meta (copy_all reads from the empty v1 table) while
schema_version copied across unchanged, leaving the store permanently
unmigratable. compact() now calls has_pending_migration() and no-ops with
a warning instead.

Also folds in five minor final-review findings: drop _rebuild_into's
unused int return, hoist test-local imports to module level in
test_vector_store.py, note in TestMigrations' docstring that its fake
structural migrations only exercise dispatch (not full schema
correctness), restore the comment explaining why _row() requires
document_id, and tighten increment_total_inserts' docstring to not imply
general concurrency safety beyond its single atomic statement.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com>
2026-08-01 07:20:29 -07:00

341 lines
11 KiB
Python

import sqlite3
from collections.abc import Generator
import pytest
from pytest_mock import MockerFixture
from paperless_ai.tables import ChunkRow
from paperless_ai.tables import DocumentChunksTable
from paperless_ai.tables import DocumentMetaRow
from paperless_ai.tables import DocumentMetaTable
from paperless_ai.tables import IndexMetaTable
@pytest.fixture
def conn() -> Generator[sqlite3.Connection, None, None]:
connection = sqlite3.connect(":memory:")
connection.row_factory = sqlite3.Row
try:
yield connection
finally:
connection.close()
class TestDocumentChunksTable:
def test_create_is_idempotent(self, conn: sqlite3.Connection) -> None:
"""
GIVEN:
- A bare sqlite3 connection
WHEN:
- create() is called, a row is inserted, then create() is called again
THEN:
- No error is raised and the row survives uncorrupted
"""
DocumentChunksTable.create(conn)
DocumentChunksTable.insert_many(conn, [ChunkRow("c1", 1)])
DocumentChunksTable.create(conn)
assert DocumentChunksTable.chunk_ids_for_document(conn, 1) == ["c1"]
def test_insert_many_then_lookup_by_document_id(
self,
conn: sqlite3.Connection,
) -> None:
"""
GIVEN:
- An empty document_chunks table
WHEN:
- Two chunks for document 1 and one for document 2 are inserted
THEN:
- chunk_ids_for_document returns exactly the matching chunk ids
"""
DocumentChunksTable.create(conn)
DocumentChunksTable.insert_many(
conn,
[ChunkRow("c1", 1), ChunkRow("c2", 1), ChunkRow("c3", 2)],
)
assert sorted(DocumentChunksTable.chunk_ids_for_document(conn, 1)) == [
"c1",
"c2",
]
assert DocumentChunksTable.chunk_ids_for_document(conn, 2) == ["c3"]
assert DocumentChunksTable.chunk_ids_for_document(conn, 999) == []
def test_delete_for_document_removes_only_that_document(
self,
conn: sqlite3.Connection,
) -> None:
"""
GIVEN:
- Chunks for two different documents
WHEN:
- delete_for_document() is called for one of them
THEN:
- Only that document's chunks are removed
"""
DocumentChunksTable.create(conn)
DocumentChunksTable.insert_many(
conn,
[ChunkRow("c1", 1), ChunkRow("c2", 2)],
)
DocumentChunksTable.delete_for_document(conn, 1)
assert DocumentChunksTable.chunk_ids_for_document(conn, 1) == []
assert DocumentChunksTable.chunk_ids_for_document(conn, 2) == ["c2"]
def test_delete_all_clears_every_row(self, conn: sqlite3.Connection) -> None:
"""
GIVEN:
- Chunks for multiple documents
WHEN:
- delete_all() is called
THEN:
- count() returns 0
"""
DocumentChunksTable.create(conn)
DocumentChunksTable.insert_many(
conn,
[ChunkRow("c1", 1), ChunkRow("c2", 2)],
)
DocumentChunksTable.delete_all(conn)
assert DocumentChunksTable.count(conn) == 0
def test_count_reflects_live_rows(self, conn: sqlite3.Connection) -> None:
"""
GIVEN:
- An empty document_chunks table
WHEN:
- Rows are inserted then one document's rows are deleted
THEN:
- count() reflects the remaining row count
"""
DocumentChunksTable.create(conn)
DocumentChunksTable.insert_many(
conn,
[ChunkRow("c1", 1), ChunkRow("c2", 1), ChunkRow("c3", 2)],
)
assert DocumentChunksTable.count(conn) == 3
DocumentChunksTable.delete_for_document(conn, 1)
assert DocumentChunksTable.count(conn) == 1
class TestDocumentMetaTable:
def test_upsert_many_then_all_modified_times(
self,
conn: sqlite3.Connection,
) -> None:
"""
GIVEN:
- An empty document_meta table
WHEN:
- Two documents' modified timestamps are upserted
THEN:
- all_modified_times() returns both, keyed by str(document_id)
"""
DocumentMetaTable.create(conn)
DocumentMetaTable.upsert_many(
conn,
[
DocumentMetaRow(1, "2026-01-01T00:00:00"),
DocumentMetaRow(2, "2026-02-02T00:00:00"),
],
)
assert DocumentMetaTable.all_modified_times(conn) == {
"1": "2026-01-01T00:00:00",
"2": "2026-02-02T00:00:00",
}
def test_upsert_many_overwrites_existing_value(
self,
conn: sqlite3.Connection,
) -> None:
"""
GIVEN:
- A document_meta row for document 1
WHEN:
- upsert_many() is called again with a new modified value for
the same document_id
THEN:
- The stored value is replaced, not duplicated
"""
DocumentMetaTable.create(conn)
DocumentMetaTable.upsert_many(conn, [DocumentMetaRow(1, "old")])
DocumentMetaTable.upsert_many(conn, [DocumentMetaRow(1, "new")])
assert DocumentMetaTable.all_modified_times(conn) == {"1": "new"}
def test_delete_for_document_removes_only_that_row(
self,
conn: sqlite3.Connection,
) -> None:
"""
GIVEN:
- document_meta rows for two documents
WHEN:
- delete_for_document() is called for one of them
THEN:
- Only that document's row is removed
"""
DocumentMetaTable.create(conn)
DocumentMetaTable.upsert_many(
conn,
[DocumentMetaRow(1, "a"), DocumentMetaRow(2, "b")],
)
DocumentMetaTable.delete_for_document(conn, 1)
assert DocumentMetaTable.all_modified_times(conn) == {"2": "b"}
def test_delete_all_clears_every_row(self, conn: sqlite3.Connection) -> None:
"""
GIVEN:
- document_meta rows for multiple documents
WHEN:
- delete_all() is called
THEN:
- all_modified_times() returns an empty dict
"""
DocumentMetaTable.create(conn)
DocumentMetaTable.upsert_many(
conn,
[DocumentMetaRow(1, "a"), DocumentMetaRow(2, "b")],
)
DocumentMetaTable.delete_all(conn)
assert DocumentMetaTable.all_modified_times(conn) == {}
def test_copy_all_streams_every_row_to_destination(
self,
conn: sqlite3.Connection,
) -> None:
"""
GIVEN:
- A source connection with document_meta rows for 5 documents
- A separate, empty destination connection
WHEN:
- copy_all() is called with a batch size smaller than the row
count, forcing multiple fetchmany() cycles
THEN:
- Every row is present on the destination connection
"""
DocumentMetaTable.create(conn)
DocumentMetaTable.upsert_many(
conn,
[DocumentMetaRow(i, f"modified-{i}") for i in range(5)],
)
dst_conn = sqlite3.connect(":memory:")
dst_conn.row_factory = sqlite3.Row
try:
DocumentMetaTable.create(dst_conn)
DocumentMetaTable.copy_all(conn, dst_conn, batch_size=2)
assert DocumentMetaTable.all_modified_times(dst_conn) == {
str(i): f"modified-{i}" for i in range(5)
}
finally:
dst_conn.close()
class TestIndexMetaTable:
@pytest.mark.parametrize(
("setter_name", "getter_name", "value"),
[
("set_dim", "get_dim", 384),
("set_embed_model", "get_embed_model", "model-a"),
("set_schema_version", "get_schema_version", 2),
],
)
def test_typed_accessor_roundtrip(
self,
conn: sqlite3.Connection,
setter_name: str,
getter_name: str,
value: int | str,
) -> None:
"""
GIVEN:
- An empty index_meta table
WHEN:
- A typed accessor's setter is called then the getter is read back
THEN:
- The same value is returned, correctly typed (int or str)
"""
IndexMetaTable.create(conn)
getter = getattr(IndexMetaTable, getter_name)
setter = getattr(IndexMetaTable, setter_name)
assert getter(conn) is None
setter(conn, value)
assert getter(conn) == value
def test_total_inserts_starts_at_zero(self, conn: sqlite3.Connection) -> None:
"""
GIVEN:
- An empty index_meta table
WHEN:
- get_total_inserts() is read before anything is set
THEN:
- 0 is returned
"""
IndexMetaTable.create(conn)
assert IndexMetaTable.get_total_inserts(conn) == 0
def test_increment_total_inserts_accumulates(
self,
conn: sqlite3.Connection,
) -> None:
"""
GIVEN:
- An empty index_meta table
WHEN:
- increment_total_inserts() is called twice
THEN:
- get_total_inserts() returns the running sum
"""
IndexMetaTable.create(conn)
IndexMetaTable.increment_total_inserts(conn, 5)
IndexMetaTable.increment_total_inserts(conn, 3)
assert IndexMetaTable.get_total_inserts(conn) == 8
def test_increment_total_inserts_is_a_single_statement(
self,
mocker: MockerFixture,
) -> None:
"""
GIVEN:
- An empty index_meta table
WHEN:
- increment_total_inserts() is called
THEN:
- Exactly one conn.execute() call is made (a single INSERT ...
ON CONFLICT DO UPDATE, not a separate read then write)
"""
# sqlite3.Connection is an immutable C extension type with no
# instance __dict__, so mocker.spy(conn, "execute") can't shadow
# "execute" on a plain connection ("attribute 'execute' is
# read-only"). A trivial Python subclass gets a normal instance
# __dict__, making the instance spyable while still being a real,
# usable sqlite3.Connection.
class _SpyableConnection(sqlite3.Connection):
pass
conn = sqlite3.connect(":memory:", factory=_SpyableConnection)
try:
conn.row_factory = sqlite3.Row
IndexMetaTable.create(conn)
execute_spy = mocker.spy(conn, "execute")
IndexMetaTable.increment_total_inserts(conn, 5)
assert execute_spy.call_count == 1
finally:
conn.close()
def test_reset_total_inserts_sets_absolute_value(
self,
conn: sqlite3.Connection,
) -> None:
"""
GIVEN:
- A total_inserts counter already at a high value
WHEN:
- reset_total_inserts() is called with a lower value
THEN:
- get_total_inserts() returns exactly that value, not a sum
"""
IndexMetaTable.create(conn)
IndexMetaTable.increment_total_inserts(conn, 100)
IndexMetaTable.reset_total_inserts(conn, 7)
assert IndexMetaTable.get_total_inserts(conn) == 7