change: use copy library and re-spawn tests

Author: Brock Wade

src/sagemaker/processing.py

@@ -23,6 +23,7 @@
 import logging
 from textwrap import dedent
 from typing import Dict, List, Optional, Union
+from copy import copy
 
 import attr
 
@@ -1829,9 +1830,7 @@ def _patch_inputs_with_payload(self, inputs, s3_payload) -> List[ProcessingInput
             inputs = []
 
         # make a shallow copy of user inputs
-        patched_inputs = []
-        for user_input in inputs:
-            patched_inputs.append(user_input)
+        patched_inputs = copy(inputs)
         patched_inputs.append(
             ProcessingInput(
                 input_name="code",

src/sagemaker/spark/processing.py

@@ -30,6 +30,7 @@
 from enum import Enum
 from io import BytesIO
 from urllib.parse import urlparse
+from copy import copy
 
 from typing import Union, List, Dict, Optional
 
@@ -279,11 +280,9 @@ def run(
     def _extend_processing_args(self, inputs, outputs, **kwargs):
         """Extends processing job args such as inputs."""
 
-        # make a copy of user outputs
+        # make a shallow copy of user outputs
         outputs = outputs or []
-        extended_outputs = []
-        for user_output in outputs:
-            extended_outputs.append(user_output)
+        extended_outputs = copy(outputs)
 
         if kwargs.get("spark_event_logs_s3_uri"):
             spark_event_logs_s3_uri = kwargs.get("spark_event_logs_s3_uri")
@@ -305,11 +304,9 @@ def _extend_processing_args(self, inputs, outputs, **kwargs):
 
             extended_outputs.append(output)
 
-        # make a copy of user inputs
+        # make a shallow copy of user inputs
         inputs = inputs or []
-        extended_inputs = []
-        for user_input in inputs:
-            extended_inputs.append(user_input)
+        extended_inputs = copy(inputs)
 
         if kwargs.get("configuration"):
             configuration = kwargs.get("configuration")
@@ -958,9 +955,7 @@ def _extend_processing_args(self, inputs, outputs, **kwargs):
             inputs = []
 
         # make a shallow copy of user inputs
-        extended_inputs = []
-        for user_input in inputs:
-            extended_inputs.append(user_input)
+        extended_inputs = copy(inputs)
 
         self.command = [_SparkProcessorBase._default_command]
         extended_inputs = self._handle_script_dependencies(
@@ -1225,9 +1220,7 @@ def _extend_processing_args(self, inputs, outputs, **kwargs):
             inputs = []
 
         # make a shallow copy of user inputs
-        extended_inputs = []
-        for user_input in inputs:
-            extended_inputs.append(user_input)
+        extended_inputs = copy(inputs)
 
         extended_inputs = self._handle_script_dependencies(
             extended_inputs, kwargs.get("submit_jars"), FileType.JAR