mirror of
https://github.com/asg017/sqlite-vec.git
synced 2026-04-25 00:36:56 +02:00
Auxiliary column support (#123)
* initial pass at PARTITION KEY support. * Initial pass, allow auxiliary columns on vec0 virtual tables * update TODO * unit tests * gha this PR branch * fixup tests * doc internal * fix tests, KNN/rowids in * define SQLITE_INDEX_CONSTRAINT_OFFSET * whoops * update tests, syrupy, use uv * un ignore pyproject.toml * dot * tests/ * type error? * win: .exe, update error name * try fix macos python, paren around expr? * win bash? * dbg :( * explicit error * op * dbg win * win ./tests/.venv/Scripts/python.exe * block UPDATEs on partition key values for now * test this branch * accidentally removved "partition key type mistmatch" block during merge * typo ugh * bruv * start aux snapshots * drop aux shadow table on destroy * enforce column types * block WHERE constraints on auxiliary columns in KNN queries * support delete * support UPDATE on auxiliary columns
This commit is contained in:
Alex Garcia
GitHub
parent
6658624172
commit
9bfeaa7842
6 changed files with 1249 additions and 8 deletions
642
tests/__snapshots__/test-auxiliary.ambr
Normal file
642
tests/__snapshots__/test-auxiliary.ambr
Normal file
|
|
@ -0,0 +1,642 @@
|
|||
# serializer version: 1
|
||||
# name: test_constructor_limit[max 16 auxiliary columns]
|
||||
dict({
|
||||
'error': 'OperationalError',
|
||||
'message': 'vec0 constructor error: More than 16 auxiliary columns were provided',
|
||||
})
|
||||
# ---
|
||||
# name: test_deletes
|
||||
OrderedDict({
|
||||
'sql': 'select rowid, * from v',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vector': b'\x00\x00\x80?',
|
||||
'name': 'alex',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'vector': b'\x00\x00\x00@',
|
||||
'name': 'brian',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'vector': b'\x00\x00@@',
|
||||
'name': 'craig',
|
||||
}),
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_deletes.1
|
||||
dict({
|
||||
'v_auxiliary': OrderedDict({
|
||||
'sql': 'select * from v_auxiliary',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'value00': 'alex',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'value00': 'brian',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'value00': 'craig',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_chunks': OrderedDict({
|
||||
'sql': 'select * from v_chunks',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'chunk_id': 1,
|
||||
'size': 8,
|
||||
'validity': b'\x07',
|
||||
'rowids': b'\x01\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_rowids': OrderedDict({
|
||||
'sql': 'select * from v_rowids',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 0,
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 1,
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 2,
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_vector_chunks00': OrderedDict({
|
||||
'sql': 'select * from v_vector_chunks00',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vectors': b'\x00\x00\x80?\x00\x00\x00@\x00\x00@@\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
})
|
||||
# ---
|
||||
# name: test_deletes.2
|
||||
OrderedDict({
|
||||
'sql': 'delete from v where rowid = 1',
|
||||
'rows': list([
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_deletes.3
|
||||
OrderedDict({
|
||||
'sql': 'select rowid, * from v',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'vector': b'\x00\x00\x00@',
|
||||
'name': 'brian',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'vector': b'\x00\x00@@',
|
||||
'name': 'craig',
|
||||
}),
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_deletes.4
|
||||
dict({
|
||||
'v_auxiliary': OrderedDict({
|
||||
'sql': 'select * from v_auxiliary',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'value00': 'brian',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'value00': 'craig',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_chunks': OrderedDict({
|
||||
'sql': 'select * from v_chunks',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'chunk_id': 1,
|
||||
'size': 8,
|
||||
'validity': b'\x06',
|
||||
'rowids': b'\x01\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_rowids': OrderedDict({
|
||||
'sql': 'select * from v_rowids',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 1,
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 2,
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_vector_chunks00': OrderedDict({
|
||||
'sql': 'select * from v_vector_chunks00',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vectors': b'\x00\x00\x80?\x00\x00\x00@\x00\x00@@\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
})
|
||||
# ---
|
||||
# name: test_knn
|
||||
OrderedDict({
|
||||
'sql': 'select * from v',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vector': b'\x00\x00\x80?',
|
||||
'name': 'alex',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'vector': b'\x00\x00\x00@',
|
||||
'name': 'brian',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'vector': b'\x00\x00@@',
|
||||
'name': 'craig',
|
||||
}),
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_knn[illegal KNN w/ aux]
|
||||
dict({
|
||||
'error': 'OperationalError',
|
||||
'message': 'An illegal WHERE constraint was provided on a vec0 auxiliary column in a KNN query.',
|
||||
})
|
||||
# ---
|
||||
# name: test_knn[legal KNN w/ aux]
|
||||
OrderedDict({
|
||||
'sql': "select *, distance from v where vector match '[5]' and k = 10",
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'vector': b'\x00\x00@@',
|
||||
'name': 'craig',
|
||||
'distance': 2.0,
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'vector': b'\x00\x00\x00@',
|
||||
'name': 'brian',
|
||||
'distance': 3.0,
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vector': b'\x00\x00\x80?',
|
||||
'name': 'alex',
|
||||
'distance': 4.0,
|
||||
}),
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_normal.1
|
||||
OrderedDict({
|
||||
'sql': 'select * from v',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'a': b'\x11\x11\x11\x11',
|
||||
'name': 'alex',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'a': b'""""',
|
||||
'name': 'brian',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'a': b'3333',
|
||||
'name': 'craig',
|
||||
}),
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_normal.2
|
||||
dict({
|
||||
'v_auxiliary': OrderedDict({
|
||||
'sql': 'select * from v_auxiliary',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'value00': 'alex',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'value00': 'brian',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'value00': 'craig',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_chunks': OrderedDict({
|
||||
'sql': 'select * from v_chunks',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'chunk_id': 1,
|
||||
'size': 8,
|
||||
'validity': b'\x07',
|
||||
'rowids': b'\x01\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_rowids': OrderedDict({
|
||||
'sql': 'select * from v_rowids',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 0,
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 1,
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 2,
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_vector_chunks00': OrderedDict({
|
||||
'sql': 'select * from v_vector_chunks00',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vectors': b'\x11\x11\x11\x11""""3333\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
})
|
||||
# ---
|
||||
# name: test_normal[sqlite_master post drop]
|
||||
OrderedDict({
|
||||
'sql': 'select * from sqlite_master order by name',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'type': 'table',
|
||||
'name': 'sqlite_sequence',
|
||||
'tbl_name': 'sqlite_sequence',
|
||||
'rootpage': 3,
|
||||
'sql': 'CREATE TABLE sqlite_sequence(name,seq)',
|
||||
}),
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_normal[sqlite_master]
|
||||
OrderedDict({
|
||||
'sql': 'select * from sqlite_master order by name',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'type': 'index',
|
||||
'name': 'sqlite_autoindex_v_vector_chunks00_1',
|
||||
'tbl_name': 'v_vector_chunks00',
|
||||
'rootpage': 6,
|
||||
'sql': None,
|
||||
}),
|
||||
OrderedDict({
|
||||
'type': 'table',
|
||||
'name': 'sqlite_sequence',
|
||||
'tbl_name': 'sqlite_sequence',
|
||||
'rootpage': 3,
|
||||
'sql': 'CREATE TABLE sqlite_sequence(name,seq)',
|
||||
}),
|
||||
OrderedDict({
|
||||
'type': 'table',
|
||||
'name': 'v',
|
||||
'tbl_name': 'v',
|
||||
'rootpage': 0,
|
||||
'sql': 'CREATE VIRTUAL TABLE v using vec0(a float[1], +name text, chunk_size=8)',
|
||||
}),
|
||||
OrderedDict({
|
||||
'type': 'table',
|
||||
'name': 'v_auxiliary',
|
||||
'tbl_name': 'v_auxiliary',
|
||||
'rootpage': 7,
|
||||
'sql': 'CREATE TABLE "v_auxiliary"( rowid integer PRIMARY KEY , value00)',
|
||||
}),
|
||||
OrderedDict({
|
||||
'type': 'table',
|
||||
'name': 'v_chunks',
|
||||
'tbl_name': 'v_chunks',
|
||||
'rootpage': 2,
|
||||
'sql': 'CREATE TABLE "v_chunks"(chunk_id INTEGER PRIMARY KEY AUTOINCREMENT,size INTEGER NOT NULL,validity BLOB NOT NULL,rowids BLOB NOT NULL)',
|
||||
}),
|
||||
OrderedDict({
|
||||
'type': 'table',
|
||||
'name': 'v_rowids',
|
||||
'tbl_name': 'v_rowids',
|
||||
'rootpage': 4,
|
||||
'sql': 'CREATE TABLE "v_rowids"(rowid INTEGER PRIMARY KEY AUTOINCREMENT,id,chunk_id INTEGER,chunk_offset INTEGER)',
|
||||
}),
|
||||
OrderedDict({
|
||||
'type': 'table',
|
||||
'name': 'v_vector_chunks00',
|
||||
'tbl_name': 'v_vector_chunks00',
|
||||
'rootpage': 5,
|
||||
'sql': 'CREATE TABLE "v_vector_chunks00"(rowid PRIMARY KEY,vectors BLOB NOT NULL)',
|
||||
}),
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_types
|
||||
OrderedDict({
|
||||
'sql': 'select * from v',
|
||||
'rows': list([
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_types.1
|
||||
OrderedDict({
|
||||
'sql': 'insert into v(vector, aux_int, aux_float, aux_text, aux_blob) values (?, ?, ?, ?, ?)',
|
||||
'rows': list([
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_types.2
|
||||
OrderedDict({
|
||||
'sql': 'select * from v',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vector': b'\x11\x11\x11\x11',
|
||||
'aux_int': 1,
|
||||
'aux_float': 1.22,
|
||||
'aux_text': 'text',
|
||||
'aux_blob': b'blob',
|
||||
}),
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_types.3
|
||||
dict({
|
||||
'error': 'OperationalError',
|
||||
'message': 'Auxiliary column type mismatch: The auxiliary column aux_int has type INTEGER, but TEXT was provided.',
|
||||
})
|
||||
# ---
|
||||
# name: test_types.4
|
||||
dict({
|
||||
'error': 'OperationalError',
|
||||
'message': 'Auxiliary column type mismatch: The auxiliary column aux_float has type FLOAT, but TEXT was provided.',
|
||||
})
|
||||
# ---
|
||||
# name: test_types.5
|
||||
dict({
|
||||
'error': 'OperationalError',
|
||||
'message': 'Auxiliary column type mismatch: The auxiliary column aux_text has type TEXT, but INTEGER was provided.',
|
||||
})
|
||||
# ---
|
||||
# name: test_types.6
|
||||
dict({
|
||||
'error': 'OperationalError',
|
||||
'message': 'Auxiliary column type mismatch: The auxiliary column aux_blob has type BLOB, but INTEGER was provided.',
|
||||
})
|
||||
# ---
|
||||
# name: test_types.7
|
||||
OrderedDict({
|
||||
'sql': 'insert into v(vector, aux_int, aux_float, aux_text, aux_blob) values (?, ?, ?, ?, ?)',
|
||||
'rows': list([
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_types.8
|
||||
OrderedDict({
|
||||
'sql': 'select * from v',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vector': b'\x11\x11\x11\x11',
|
||||
'aux_int': 1,
|
||||
'aux_float': 1.22,
|
||||
'aux_text': 'text',
|
||||
'aux_blob': b'blob',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'vector': b'\x11\x11\x11\x11',
|
||||
'aux_int': None,
|
||||
'aux_float': None,
|
||||
'aux_text': None,
|
||||
'aux_blob': None,
|
||||
}),
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_updates
|
||||
OrderedDict({
|
||||
'sql': 'select rowid, * from v',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vector': b'\x00\x00\x80?',
|
||||
'name': 'alex',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'vector': b'\x00\x00\x00@',
|
||||
'name': 'brian',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'vector': b'\x00\x00@@',
|
||||
'name': 'craig',
|
||||
}),
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_updates.1
|
||||
dict({
|
||||
'v_auxiliary': OrderedDict({
|
||||
'sql': 'select * from v_auxiliary',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'value00': 'alex',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'value00': 'brian',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'value00': 'craig',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_chunks': OrderedDict({
|
||||
'sql': 'select * from v_chunks',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'chunk_id': 1,
|
||||
'size': 8,
|
||||
'validity': b'\x07',
|
||||
'rowids': b'\x01\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_rowids': OrderedDict({
|
||||
'sql': 'select * from v_rowids',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 0,
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 1,
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 2,
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_vector_chunks00': OrderedDict({
|
||||
'sql': 'select * from v_vector_chunks00',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vectors': b'\x00\x00\x80?\x00\x00\x00@\x00\x00@@\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
})
|
||||
# ---
|
||||
# name: test_updates.2
|
||||
OrderedDict({
|
||||
'sql': "update v set name = 'ALEX' where rowid = 1",
|
||||
'rows': list([
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_updates.3
|
||||
OrderedDict({
|
||||
'sql': 'select rowid, * from v',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vector': b'\x00\x00\x80?',
|
||||
'name': 'ALEX',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'vector': b'\x00\x00\x00@',
|
||||
'name': 'brian',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'vector': b'\x00\x00@@',
|
||||
'name': 'craig',
|
||||
}),
|
||||
]),
|
||||
})
|
||||
# ---
|
||||
# name: test_updates.4
|
||||
dict({
|
||||
'v_auxiliary': OrderedDict({
|
||||
'sql': 'select * from v_auxiliary',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'value00': 'ALEX',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'value00': 'brian',
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'value00': 'craig',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_chunks': OrderedDict({
|
||||
'sql': 'select * from v_chunks',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'chunk_id': 1,
|
||||
'size': 8,
|
||||
'validity': b'\x07',
|
||||
'rowids': b'\x01\x00\x00\x00\x00\x00\x00\x00\x02\x00\x00\x00\x00\x00\x00\x00\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_rowids': OrderedDict({
|
||||
'sql': 'select * from v_rowids',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 0,
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 2,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 1,
|
||||
}),
|
||||
OrderedDict({
|
||||
'rowid': 3,
|
||||
'id': None,
|
||||
'chunk_id': 1,
|
||||
'chunk_offset': 2,
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
'v_vector_chunks00': OrderedDict({
|
||||
'sql': 'select * from v_vector_chunks00',
|
||||
'rows': list([
|
||||
OrderedDict({
|
||||
'rowid': 1,
|
||||
'vectors': b'\x00\x00\x80?\x00\x00\x00@\x00\x00@@\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00',
|
||||
}),
|
||||
]),
|
||||
}),
|
||||
})
|
||||
# ---
|
||||
155
tests/test-auxiliary.py
Normal file
155
tests/test-auxiliary.py
Normal file
|
|
@ -0,0 +1,155 @@
|
|||
import sqlite3
|
||||
from collections import OrderedDict
|
||||
|
||||
|
||||
def test_constructor_limit(db, snapshot):
|
||||
assert exec(
|
||||
db,
|
||||
f"""
|
||||
create virtual table v using vec0(
|
||||
{",".join([f"+aux{x} integer" for x in range(17)])}
|
||||
v float[1]
|
||||
)
|
||||
""",
|
||||
) == snapshot(name="max 16 auxiliary columns")
|
||||
|
||||
|
||||
def test_normal(db, snapshot):
|
||||
db.execute(
|
||||
"create virtual table v using vec0(a float[1], +name text, chunk_size=8)"
|
||||
)
|
||||
assert exec(db, "select * from sqlite_master order by name") == snapshot(
|
||||
name="sqlite_master"
|
||||
)
|
||||
|
||||
db.execute("insert into v(a, name) values (?, ?)", [b"\x11\x11\x11\x11", "alex"])
|
||||
db.execute("insert into v(a, name) values (?, ?)", [b"\x22\x22\x22\x22", "brian"])
|
||||
db.execute("insert into v(a, name) values (?, ?)", [b"\x33\x33\x33\x33", "craig"])
|
||||
|
||||
assert exec(db, "select * from v") == snapshot()
|
||||
assert vec0_shadow_table_contents(db, "v") == snapshot()
|
||||
|
||||
db.execute("drop table v;")
|
||||
assert exec(db, "select * from sqlite_master order by name") == snapshot(
|
||||
name="sqlite_master post drop"
|
||||
)
|
||||
|
||||
|
||||
def test_types(db, snapshot):
|
||||
db.execute(
|
||||
"""
|
||||
create virtual table v using vec0(
|
||||
vector float[1],
|
||||
+aux_int integer,
|
||||
+aux_float float,
|
||||
+aux_text text,
|
||||
+aux_blob blob
|
||||
)
|
||||
"""
|
||||
)
|
||||
assert exec(db, "select * from v") == snapshot()
|
||||
INSERT = "insert into v(vector, aux_int, aux_float, aux_text, aux_blob) values (?, ?, ?, ?, ?)"
|
||||
|
||||
assert (
|
||||
exec(db, INSERT, [b"\x11\x11\x11\x11", 1, 1.22, "text", b"blob"]) == snapshot()
|
||||
)
|
||||
assert exec(db, "select * from v") == snapshot()
|
||||
|
||||
# bad types
|
||||
assert (
|
||||
exec(db, INSERT, [b"\x11\x11\x11\x11", "not int", 1.2, "text", b"blob"])
|
||||
== snapshot()
|
||||
)
|
||||
assert (
|
||||
exec(db, INSERT, [b"\x11\x11\x11\x11", 1, "not float", "text", b"blob"])
|
||||
== snapshot()
|
||||
)
|
||||
assert exec(db, INSERT, [b"\x11\x11\x11\x11", 1, 1.2, 1, b"blob"]) == snapshot()
|
||||
assert exec(db, INSERT, [b"\x11\x11\x11\x11", 1, 1.2, "text", 1]) == snapshot()
|
||||
|
||||
# NULLs are totally chill
|
||||
assert exec(db, INSERT, [b"\x11\x11\x11\x11", None, None, None, None]) == snapshot()
|
||||
assert exec(db, "select * from v") == snapshot()
|
||||
|
||||
|
||||
def test_updates(db, snapshot):
|
||||
db.execute(
|
||||
"create virtual table v using vec0(vector float[1], +name text, chunk_size=8)"
|
||||
)
|
||||
db.executemany(
|
||||
"insert into v(vector, name) values (?, ?)",
|
||||
[("[1]", "alex"), ("[2]", "brian"), ("[3]", "craig")],
|
||||
)
|
||||
assert exec(db, "select rowid, * from v") == snapshot()
|
||||
assert vec0_shadow_table_contents(db, "v") == snapshot()
|
||||
|
||||
assert exec(db, "update v set name = 'ALEX' where rowid = 1") == snapshot()
|
||||
assert exec(db, "select rowid, * from v") == snapshot()
|
||||
assert vec0_shadow_table_contents(db, "v") == snapshot()
|
||||
|
||||
|
||||
def test_deletes(db, snapshot):
|
||||
db.execute(
|
||||
"create virtual table v using vec0(vector float[1], +name text, chunk_size=8)"
|
||||
)
|
||||
db.executemany(
|
||||
"insert into v(vector, name) values (?, ?)",
|
||||
[("[1]", "alex"), ("[2]", "brian"), ("[3]", "craig")],
|
||||
)
|
||||
assert exec(db, "select rowid, * from v") == snapshot()
|
||||
assert vec0_shadow_table_contents(db, "v") == snapshot()
|
||||
|
||||
assert exec(db, "delete from v where rowid = 1") == snapshot()
|
||||
assert exec(db, "select rowid, * from v") == snapshot()
|
||||
assert vec0_shadow_table_contents(db, "v") == snapshot()
|
||||
|
||||
|
||||
def test_knn(db, snapshot):
|
||||
db.execute("create virtual table v using vec0(vector float[1], +name text)")
|
||||
db.executemany(
|
||||
"insert into v(vector, name) values (?, ?)",
|
||||
[("[1]", "alex"), ("[2]", "brian"), ("[3]", "craig")],
|
||||
)
|
||||
assert exec(db, "select * from v") == snapshot()
|
||||
assert exec(
|
||||
db, "select *, distance from v where vector match '[5]' and k = 10"
|
||||
) == snapshot(name="legal KNN w/ aux")
|
||||
|
||||
# EVIDENCE-OF: V25623_09693 No aux constraint allowed on KNN queries
|
||||
assert exec(
|
||||
db,
|
||||
"select *, distance from v where vector match '[5]' and k = 10 and name = 'alex'",
|
||||
) == snapshot(name="illegal KNN w/ aux")
|
||||
|
||||
|
||||
def exec(db, sql, parameters=[]):
|
||||
try:
|
||||
rows = db.execute(sql, parameters).fetchall()
|
||||
except (sqlite3.OperationalError, sqlite3.DatabaseError) as e:
|
||||
return {
|
||||
"error": e.__class__.__name__,
|
||||
"message": str(e),
|
||||
}
|
||||
a = []
|
||||
for row in rows:
|
||||
o = OrderedDict()
|
||||
for k in row.keys():
|
||||
o[k] = row[k]
|
||||
a.append(o)
|
||||
result = OrderedDict()
|
||||
result["sql"] = sql
|
||||
result["rows"] = a
|
||||
return result
|
||||
|
||||
|
||||
def vec0_shadow_table_contents(db, v):
|
||||
shadow_tables = [
|
||||
row[0]
|
||||
for row in db.execute(
|
||||
"select name from sqlite_master where name like ? order by 1", [f"{v}_%"]
|
||||
).fetchall()
|
||||
]
|
||||
o = {}
|
||||
for shadow_table in shadow_tables:
|
||||
o[shadow_table] = exec(db, f"select * from {shadow_table}")
|
||||
return o
|
||||
Loading…
Add table
Add a link
Reference in a new issue