Added doc and renamed args

Author: ca-nguyen

src/stepfunctions/steps/sagemaker.py

@@ -478,10 +478,6 @@ class ProcessingStep(Task):
 
     """
     Creates a Task State to execute a SageMaker Processing Job.
-
-    The following properties can be passed down as kwargs to the sagemaker.processing.Processor to be used dynamically
-    in the processing job (compatible with Placeholders): role, image_uri, instance_count, instance_type,
-    volume_size_in_gb, volume_kms_key, output_kms_key
     """
 
     def __init__(self, state_id, processor, job_name, inputs=None, outputs=None, experiment_config=None,
@@ -507,7 +503,10 @@ def __init__(self, state_id, processor, job_name, inputs=None, outputs=None, exp
                 The KmsKeyId is applied to all outputs.
             wait_for_completion (bool, optional): Boolean value set to `True` if the Task state should wait for the processing job to complete before proceeding to the next step in the workflow. Set to `False` if the Task state should submit the processing job and proceed to the next step. (default: True)
             tags (list[dict] or Placeholder, optional): `List to tags <https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html>`_ to associate with the resource.
-            parameters(dict, optional): The value of this field becomes the effective input for the state.
+            parameters(dict, optional): The value of this field becomes the request for the
+                `CreateProcessingJob<https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateProcessingJob.html>`_ created by the processing step.
+                All parameters fields are compatible with `Placeholders<https://aws-step-functions-data-science-sdk.readthedocs.io/en/stable/placeholders.html?highlight=placeholder#stepfunctions.inputs.Placeholder>`_.
+                Any value defined in the parameters argument will overwrite the ones defined in the other arguments, including properties that were previously defined in the processor.
         """
         if wait_for_completion:
             """

src/stepfunctions/steps/utils.py

@@ -48,22 +48,28 @@ def get_aws_partition():
     return cur_partition
 
 
-def merge_dicts(first, second, first_name, second_name):
+def merge_dicts(target, source, target_name, source_name):
     """
-    Merges first and second dictionaries into the first one.
-    Values in the first dict are updated with the values of the second one.
+    Merges source dictionary into the target dictionary.
+    Values in the target dict are updated with the values of the source dict.
+    Args:
+        target (dict): Base dictionary into which source is merged
+        source (dict): Dictionary used to update target. If the same key is present in both dictionaries, source's value
+             will overwrite target's value for the corresponding key
+        target_name (str): Name of target dictionary used for logging purposes
+        source_name (str): Name of source dictionary used for logging purposes
     """
-    if all(isinstance(d, dict) for d in [first, second]):
-        for key, value in second.items():
-            if key in first:
-                if isinstance(first[key], dict) and isinstance(second[key], dict):
-                    merge_dicts(first[key], second[key], first_name, second_name)
-                elif first[key] == value:
+    if isinstance(target, dict) and isinstance(source, dict):
+        for key, value in source.items():
+            if key in target:
+                if isinstance(target[key], dict) and isinstance(source[key], dict):
+                    merge_dicts(target[key], source[key], target_name, source_name)
+                elif target[key] == value:
                     pass
                 else:
                     logger.info(
-                        f"{first_name} property: <{key}> with value: <{first[key]}>"
-                        f" will be overwritten with value provided in {second_name} : <{value}>")
-                    first[key] = second[key]
+                        f"{target_name} property: <{key}> with value: <{target[key]}>"
+                        f" will be overwritten with value provided in {source_name} : <{value}>")
+                    target[key] = source[key]
             else:
-                first[key] = second[key]
+                target[key] = source[key]

tests/unit/test_steps_utils.py

@@ -13,7 +13,7 @@
 
 # Test if boto3 session can fetch correct aws partition info from test environment
 
-from stepfunctions.steps.utils import get_aws_partition
+from stepfunctions.steps.utils import get_aws_partition, merge_dicts
 from stepfunctions.steps.integration_resources import IntegrationPattern, get_service_integration_arn
 import boto3
 from unittest.mock import patch
@@ -51,3 +51,10 @@ def test_arn_builder_sagemaker_wait_completion():
                                       IntegrationPattern.WaitForCompletion)
     assert arn == "arn:aws:states:::sagemaker:createTrainingJob.sync"
 
+
+def test_merge_dicts():
+    d1 = {'a': {'aa': 1, 'bb': 2, 'cc': 3}, 'b': 1}
+    d2 = {'a': {'bb': {'aaa': 1, 'bbb': 2}}, 'b': 2, 'c': 3}
+
+    merge_dicts(d1, d2, 'd1', 'd2')
+    assert d1 == {'a': {'aa': 1, 'bb': {'aaa': 1, 'bbb': 2}, 'cc': 3}, 'b': 2, 'c': 3}