lint check for List --> list, Tuple --> tuple; tried addressing TODO in code

Author: mdr223

src/palimpzest/query/execution/execution_strategy.py

@@ -1,7 +1,6 @@
 import time
 from abc import ABC, abstractmethod
 from enum import Enum
-from typing import List, Tuple
 
 from palimpzest.core.data.dataclasses import ExecutionStats, PlanStats
 from palimpzest.core.elements.records import DataRecord
@@ -26,7 +25,7 @@ def __init__(self,
                  scan_start_idx: int = 0, 
                  datadir: DataDirectory | None = None,
                  max_workers: int | None = None,
-                 nocache: bool = False,
+                 nocache: bool = True,
                  verbose: bool = False):
         self.scan_start_idx = scan_start_idx
         self.datadir = datadir
@@ -42,23 +41,23 @@ def execute_plan(
         plan: PhysicalPlan,
         num_samples: int | float = float("inf"),
         workers: int = 1
-    ) -> Tuple[List[DataRecord], PlanStats]:
+    ) -> tuple[list[DataRecord], PlanStats]:
         """Execute a single plan according to strategy"""
         pass
 
 
     @abstractmethod
     def _should_stop_execution(
         self,
-        records: List[DataRecord],
-        plan_stats: List[PlanStats]
+        records: list[DataRecord],
+        plan_stats: list[PlanStats]
     ) -> bool:
         """Override to implement early stopping logic"""
         return False
 
     def _create_execution_stats(
         self,
-        plan_stats: List[PlanStats],
+        plan_stats: list[PlanStats],
         start_time: float
     ) -> ExecutionStats:
         """Create execution statistics"""
@@ -71,8 +70,8 @@ def _create_execution_stats(
 
     def _should_stop_execution(
         self,
-        records: List[DataRecord],
-        plan_stats: List[PlanStats]
+        records: list[DataRecord],
+        plan_stats: list[PlanStats]
     ) -> bool:
         """Override to implement early stopping logic"""
         return False

src/palimpzest/query/operators/datasource.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import time
+from abc import ABC, abstractmethod
 
 from palimpzest.constants import (
     LOCAL_SCAN_TIME_PER_KB,
@@ -12,7 +13,7 @@
 from palimpzest.query.operators.physical import PhysicalOperator
 
 
-class DataSourcePhysicalOp(PhysicalOperator):
+class DataSourcePhysicalOp(PhysicalOperator, ABC):
     """
     Physical operators which implement DataSources require slightly more information
     in order to accurately compute naive cost estimates. Thus, we use a slightly
@@ -59,8 +60,9 @@ def naive_cost_estimates(
         raise NotImplementedError("Abstract method")
 
     # TODO: we need to revisit this to make get_datasource() unified for DataScan operators
+    @abstractmethod
     def get_datasource(self):
-        return self.datadir.get_registered_dataset(self.dataset_id)
+        raise NotImplementedError("Abstract method")
 
 
 class MarshalAndScanDataOp(DataSourcePhysicalOp):
@@ -196,3 +198,6 @@ def __call__(self, candidate: DataRecord) -> DataRecordSet:
         record_set = DataRecordSet(records, record_op_stats_lst)
 
         return record_set
+
+    def get_datasource(self):
+        return self.datadir.get_cached_result(self.dataset_id)