issue_comments: 899915829
This data as json
| html_url | issue_url | id | node_id | user | created_at | updated_at | author_association | body | reactions | issue | performed_via_github_app |
|---|---|---|---|---|---|---|---|---|---|---|---|
| https://github.com/simonw/datasette/issues/1293#issuecomment-899915829 | https://api.github.com/repos/simonw/datasette/issues/1293 | 899915829 | IC_kwDOBm6k_c41o6A1 | 9599 | 2021-08-17T01:02:35Z | 2021-08-17T01:02:35Z | OWNER | New approach: this time I'm building a simplified executor for the bytecode operations themselves. ```python def execute_operations(operations, max_iterations = 100, trace=None): trace = trace or (lambda *args: None) registers: Dict[int, Any] = {} cursors: Dict[int, Tuple[str, Dict]] = {} instruction_pointer = 0 iterations = 0 result_row = None while True: iterations += 1 if iterations > max_iterations: break operation = operations[instruction_pointer] trace(instruction_pointer, dict(operation)) opcode = operation["opcode"] if opcode == "Init": if operation["p2"] != 0: instruction_pointer = operation["p2"] continue else: instruction_pointer += 1 continue elif opcode == "Goto": instruction_pointer = operation["p2"] continue elif opcode == "Halt": break elif opcode == "OpenRead": cursors[operation["p1"]] = ("database_table", { "rootpage": operation["p2"], "connection": operation["p3"], }) elif opcode == "OpenEphemeral": cursors[operation["p1"]] = ("ephemeral", { "num_columns": operation["p2"], "index_keys": [], }) elif opcode == "MakeRecord": registers[operation["p3"]] = ("MakeRecord", { "registers": list(range(operation["p1"] + operation["p2"])) }) elif opcode == "IdxInsert": record = registers[operation["p2"]] cursors[operation["p1"]][1]["index_keys"].append(record) elif opcode == "Rowid": registers[operation["p2"]] = ("rowid", { "table": operation["p1"] }) elif opcode == "Sequence": registers[operation["p2"]] = ("sequence", { "next_from_cursor": operation["p1"] }) elif opcode == "Column": registers[operation["p3"]] = ("column", { "cursor": operation["p1"], "column_offset": operation["p2"] }) elif opcode == "ResultRow": p1 = operation["p1"] p2 = operation["p2"] trace("ResultRow: ", list(range(p1, p1 + p2)), registers) result_row = [registers.get(i) for i in range(p1, p1 + p2)] elif opcode == "Integer": registers[operation["p2"]] = ("Integer", operation["p1"]) elif opcode == "String8": registers[operation["p2"]] = ("String", operation["p4"]) instruction_pointer += 1 return {"registers": registers, "cursors": cursors, "result_row": result_row} ``` Results are promising! ``` execute_operations(db.execute("explain select 'hello', 55, rowid, * from searchable").fetchall()) {'registers': {1: ('String', 'hello'), 2: ('Integer', 55), 3: ('rowid', {'table': 0}), 4: ('rowid', {'table': 0}), 5: ('column', {'cursor': 0, 'column_offset': 1}), 6: ('column', {'cursor': 0, 'column_offset': 2}), 7: ('column', {'cursor': 0, 'column_offset': 3})}, 'cursors': {0: ('database_table', {'rootpage': 32, 'connection': 0})}, 'result_row': [('String', 'hello'), ('Integer', 55), ('rowid', {'table': 0}), ('rowid', {'table': 0}), ('column', {'cursor': 0, 'column_offset': 1}), ('column', {'cursor': 0, 'column_offset': 2}), ('column', {'cursor': 0, 'column_offset': 3})]} ``` Here's what happens with a union across three tables: ``` execute_operations(db.execute(f""" explain select data as content from binary_data union select pk as content from complex_foreign_keys union select name as content from facet_cities """}).fetchall()) {'registers': {1: ('column', {'cursor': 4, 'column_offset': 0}), 2: ('MakeRecord', {'registers': [0, 1, 2, 3]}), 3: ('column', {'cursor': 0, 'column_offset': 1}), 4: ('column', {'cursor': 3, 'column_offset': 0})}, 'cursors': {3: ('ephemeral', {'num_columns': 1, 'index_keys': [('MakeRecord', {'registers': [0, 1]}), ('MakeRecord', {'registers': [0, 1]}), ('MakeRecord', {'registers': [0, 1, 2, 3]})]}), 2: ('database_table', {'rootpage': 44, 'connection': 0}), 4: ('database_table', {'rootpage': 24, 'connection': 0}), 0: ('database_table', {'rootpage': 42, 'connection': 0})}, 'result_row': [('column', {'cursor': 3, 'column_offset': 0})]} ``` Note how the result_row refers to cursor 3, which is an ephemeral table which had three different sets of `MakeRecord` index keys assigned to it - indicating that the output column is NOT from the same underlying table source. | {"total_count": 0, "+1": 0, "-1": 0, "laugh": 0, "hooray": 0, "confused": 0, "heart": 0, "rocket": 0, "eyes": 0} | 849978964 |