water-column-sonar-processing 0.0.7__tar.gz → 0.0.8__tar.gz

{water_column_sonar_processing-0.0.7/src/water_column_sonar_processing.egg-info → water_column_sonar_processing-0.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: water_column_sonar_processing
-Version: 0.0.7
+Version: 0.0.8
 Summary: A processing tool for water column sonar data.
 Author-email: Rudy Klucik <rudy.klucik@noaa.gov>
 Project-URL: Homepage, https://github.com/CI-CMG/water-column-sonar-processing
@@ -11,26 +11,27 @@ Classifier: Operating System :: OS Independent
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: aiobotocore~=2.9.0
-Requires-Dist: aiohttp~=3.10.10
-Requires-Dist: boto3==1.33.13
-Requires-Dist: botocore~=1.33.13
+Requires-Dist: aiobotocore==2.15.2
+Requires-Dist: boto3==1.35.36
+Requires-Dist: botocore==1.35.36
 Requires-Dist: echopype==0.9.0
 Requires-Dist: fiona==1.10.1
 Requires-Dist: geopandas==1.0.1
-Requires-Dist: mock~=5.1.0
-Requires-Dist: moto~=5.0.18
+Requires-Dist: mock==5.1.0
+Requires-Dist: moto[all]==5.0.21
+Requires-Dist: moto[server]==5.0.21
 Requires-Dist: numcodecs==0.13.1
 Requires-Dist: numpy==1.26.4
 Requires-Dist: pandas==2.2.3
-Requires-Dist: pytest~=8.3.3
+Requires-Dist: pyarrow==18.1.0
 Requires-Dist: python-dotenv==1.0.0
 Requires-Dist: requests==2.32.3
-Requires-Dist: s3fs==2024.10.0
+Requires-Dist: s3fs==2023.12.1
 Requires-Dist: scipy==1.14.1
+Requires-Dist: setuptools==75.6.0
 Requires-Dist: shapely==2.0.3
 Requires-Dist: typing-extensions==4.10.0
-Requires-Dist: xarray==2022.12.0
+Requires-Dist: xarray==2024.10.0
 Requires-Dist: zarr==2.18.3
 
 # Water Column Sonar Processing
@@ -85,6 +86,8 @@ Processing tool for converting L0 data to L1 and L2 as well as generating geospa
 ```commandline
 pytest --disable-warnings
 ```
+or
+> pytest --cache-clear --cov=src tests/ --cov-report=xml
 
 # Instructions
 Following this tutorial:
@@ -122,3 +125,10 @@ https://plugins.jetbrains.com/plugin/20574-ruff
 
 # Colab Test
 https://colab.research.google.com/drive/1KiLMueXiz9WVB9o4RuzYeGjNZ6PsZU7a#scrollTo=AayVyvpBdfIZ
+
+# Test Coverage
+20241124
+8 failed, 32 passed, 3 skipped, 1 warning in 6.92s
+20241125
+5 failed, 35 passed, 3 skipped, 1 warning in 9.71s
+3 failed, 38 passed, 3 skipped, 1 warning in 7.24s

{water_column_sonar_processing-0.0.7 → water_column_sonar_processing-0.0.8}/README.md

@@ -50,6 +50,8 @@ Processing tool for converting L0 data to L1 and L2 as well as generating geospa
 ```commandline
 pytest --disable-warnings
 ```
+or
+> pytest --cache-clear --cov=src tests/ --cov-report=xml
 
 # Instructions
 Following this tutorial:
@@ -86,4 +88,11 @@ Ruff
 https://plugins.jetbrains.com/plugin/20574-ruff
 
 # Colab Test
-https://colab.research.google.com/drive/1KiLMueXiz9WVB9o4RuzYeGjNZ6PsZU7a#scrollTo=AayVyvpBdfIZ
+https://colab.research.google.com/drive/1KiLMueXiz9WVB9o4RuzYeGjNZ6PsZU7a#scrollTo=AayVyvpBdfIZ
+
+# Test Coverage
+20241124
+8 failed, 32 passed, 3 skipped, 1 warning in 6.92s
+20241125
+5 failed, 35 passed, 3 skipped, 1 warning in 9.71s
+3 failed, 38 passed, 3 skipped, 1 warning in 7.24s

{water_column_sonar_processing-0.0.7 → water_column_sonar_processing-0.0.8}/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "water_column_sonar_processing"
-version = "0.0.7"
+version = "0.0.8"
 authors = [
   { name="Rudy Klucik", email="rudy.klucik@noaa.gov" },
 ]
@@ -25,19 +25,29 @@ dynamic = ["dependencies"]
 Homepage = "https://github.com/CI-CMG/water-column-sonar-processing"
 Issues = "https://github.com/CI-CMG/water-column-sonar-processing/issues"
 
-#[pytest]
+#[tool.pytest.ini_options]
+#filterwarnings = [
+#    "error",
+#    "ignore::UserWarning",
+#    # note the use of single quote below to denote "raw" strings in TOML
+#    'ignore:function ham\(\) is deprecated:DeprecationWarning',
+#]
 #pythonpath = "src"
 #testpaths = "tests"
+#[pytest]
+#addopts = [
+#    "-p no:warnings"
+#]
 
-[tool.pytest.ini_options]
-minversion = "6.0"
-#addopts = "-ra -q"
-testpaths = [
-    "tests",
-]
+#[tool.pytest.ini_options]
+#minversion = "6.0"
+##addopts = "-ra -q"
+#testpaths = [
+#    "tests",
+#]
 
 [tool.setuptools.dynamic]
 dependencies = {file = ["requirements.txt"]}
-optional-dependencies = {dev = { file = ["requirements-dev.txt"] }}
+optional-dependencies = {dev = { file = ["requirements_dev.txt"] }}
 
 # https://packaging.python.org/en/latest/guides/writing-pyproject-toml/

{water_column_sonar_processing-0.0.7 → water_column_sonar_processing-0.0.8}/requirements.txt

@@ -2,26 +2,27 @@
 # defined for Python 3.12
 # Note: be careful with conversions for pandas >=2.0.0, timestamps will have a lot of problems
 
-aiobotocore~=2.9.0
-aiohttp~=3.10.10
-boto3==1.33.13
-botocore~=1.33.13
+aiobotocore==2.15.2
+boto3==1.35.36
+botocore==1.35.36
 echopype==0.9.0
 fiona==1.10.1
+# Alternative to geopandas: pyogrio
 geopandas==1.0.1
-mock~=5.1.0
-moto~=5.0.18
+mock==5.1.0
+moto[all]==5.0.21
+moto[server]==5.0.21
 numcodecs==0.13.1
 numpy==1.26.4
 pandas==2.2.3
-pytest~=8.3.3
+pyarrow==18.1.0
 python-dotenv==1.0.0
 requests==2.32.3
-#s3fs==2023.12.2
-s3fs==2024.10.0
+#s3fs==2024.10.0 # this version creates problems
+s3fs==2023.12.1
 scipy==1.14.1
+setuptools==75.6.0
 shapely==2.0.3
 typing-extensions==4.10.0
-xarray==2022.12.0
-#zarr==2.16.1
+xarray==2024.10.0
 zarr==2.18.3

water_column_sonar_processing-0.0.8/src/water_column_sonar_processing/__init__.py

@@ -0,0 +1,15 @@
+from __future__ import absolute_import
+
+from . import aws, cruise, geometry, index, model, processing, utility
+# from .model import ZarrManager
+# from .process import Process
+
+__all__ = [
+    "aws",
+    "cruise",
+    "geometry",
+    "index",
+    "model",
+    "processing",
+    "utility",
+]

{water_column_sonar_processing-0.0.7 → water_column_sonar_processing-0.0.8}/src/water_column_sonar_processing/aws/dynamodb_manager.py

@@ -8,7 +8,11 @@ from boto3.dynamodb.types import TypeDeserializer, TypeSerializer
 #########################################################################
 class DynamoDBManager:
     #####################################################################
-    def __init__(self):
+    def __init__(
+            self,
+            # endpoint_url
+    ):
+        # self.endpoint_url = endpoint_url
         self.__dynamodb_session = boto3.Session(
             aws_access_key_id=os.environ.get("ACCESS_KEY_ID"),
             aws_secret_access_key=os.environ.get("SECRET_ACCESS_KEY"),
@@ -16,9 +20,11 @@ class DynamoDBManager:
         )
         self.__dynamodb_resource = self.__dynamodb_session.resource(
             service_name="dynamodb",
+            # endpoint_url=self.endpoint_url
         )
         self.__dynamodb_client = self.__dynamodb_session.client(
             service_name="dynamodb",
+            # endpoint_url=self.endpoint_url
         )
         self.type_serializer = TypeSerializer()  # https://stackoverflow.com/a/46738251
         self.type_deserializer = TypeDeserializer()
@@ -35,31 +41,14 @@ class DynamoDBManager:
     #     assert (status_code == 200), "Problem, unable to update dynamodb table."
 
     #####################################################################
-    def create_table(
-        self,
-        table_name,
-        key_schema,
-        attribute_definitions,
-    ):
-        self.__dynamodb_client.create_table(
-            AttributeDefinitions=attribute_definitions,
-            TableName=table_name,
-            KeySchema=key_schema,
-            BillingMode="PAY_PER_REQUEST",  # "PROVISIONED",
-            # ProvisionedThroughput={
-            #     'ReadCapacityUnits': 1_000,
-            #     'WriteCapacityUnits': 1_000
-            # }
-        )
-
     #####################################################################
     def create_water_column_sonar_table(
         self,
         table_name,
     ):
-        self.create_table(
-            table_name=table_name,
-            key_schema=[
+        self.__dynamodb_client.create_table(
+            TableName=table_name,
+            KeySchema=[
                 {
                     "AttributeName": "FILE_NAME",
                     "KeyType": "HASH",
@@ -69,20 +58,50 @@ class DynamoDBManager:
                     "KeyType": "RANGE",
                 },
             ],
-            attribute_definitions=[
+            AttributeDefinitions=[
                 {"AttributeName": "FILE_NAME", "AttributeType": "S"},
                 {"AttributeName": "CRUISE_NAME", "AttributeType": "S"},
             ],
+            BillingMode="PAY_PER_REQUEST"
+            # ProvisionedThroughput={
+            #     'ReadCapacityUnits': 1_000,
+            #     'WriteCapacityUnits': 1_000
+            # }
         )
+        # TODO: after creating status is 'CREATING', wait until 'ACTIVE'
+        response = self.__dynamodb_client.describe_table(TableName=table_name)
+        print(response) # https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/dynamodb/client/describe_table.html
+        # sleep then response['Table']['TableStatus'] == 'ACTIVE'
+
+    #####################################################################
+    # don't think this is used?
+    # def get_item(
+    #         self,
+    #         table_name,
+    #         key
+    # ):
+    #     response = self.__dynamodb_client.get_item(TableName=table_name, Key=key)
+    #     item = None
+    #     if response["ResponseMetadata"]["HTTPStatusCode"] == 200:
+    #         if "Item" in response:
+    #             item = response["Item"]
+    #     return item
 
     #####################################################################
-    def get_item(self, table_name, key):
-        response = self.__dynamodb_client.get_item(TableName=table_name, Key=key)
-        item = None
-        if response["ResponseMetadata"]["HTTPStatusCode"] == 200:
-            if "Item" in response:
-                item = response["Item"]
-        return item
+    def get_table_item(
+        self,
+        table_name,
+        key,
+    ):
+        """
+        Gets a single row from the db.
+        """
+        table = self.__dynamodb_resource.Table(table_name)
+        response = table.get_item(Key=key)
+        # TODO:
+        # if response["ResponseMetadata"]["HTTPStatusCode"] != 200:
+        #     throw error
+        return response
 
     #####################################################################
     def update_item(
@@ -101,17 +120,22 @@ class DynamoDBManager:
             UpdateExpression=update_expression,
         )
         status_code = response["ResponseMetadata"]["HTTPStatusCode"]
-        # TODO: change to exception
+        assert response['ConsumedCapacity']['TableName'] == table_name
         assert status_code == 200, "Problem, unable to update dynamodb table."
 
     #####################################################################
+    # TODO: change to "get_cruise_as_df"
     def get_table_as_df(
         self,
         ship_name,
         cruise_name,
         sensor_name,
         table_name,
-    ):
+    ) -> pd.DataFrame:
+        """
+        To be used to initialize a cruise, deletes all entries associated with that cruise
+        in the database.
+        """
         expression_attribute_values = {
             ":cr": {"S": cruise_name},
             ":se": {"S": sensor_name},
@@ -128,6 +152,9 @@ class DynamoDBManager:
             FilterExpression=filter_expression,
         )
         # Note: table.scan() has 1 MB limit on results so pagination is used
+        if len(response["Items"]) == 0:
+            return pd.DataFrame() # If no results, return empty dataframe
+
         data = response["Items"]
 
         while "LastEvaluatedKey" in response:
@@ -146,25 +173,104 @@ class DynamoDBManager:
         return df.sort_values(by="START_TIME", ignore_index=True)
 
     #####################################################################
-    # is this used?
-    def get_table_item(
+    # TODO: WIP
+    def delete_item(
         self,
         table_name,
-        key,
+        cruise_name,
+        file_name,
     ):
-        # a bit more high level, uses resource to get table item
-        table = self.__dynamodb_resource.Table(table_name)
-        response = table.get_item(Key=key)
+        """
+        Finds all rows associated with a cruise and deletes them.
+        """
+        response = self.__dynamodb_client.delete_item(
+            Key={
+                "CRUISE_NAME": {
+                    "S": cruise_name
+                },
+                "FILE_NAME": {
+                    "S": file_name
+                }
+            },
+            TableName=table_name,
+            ReturnConsumedCapacity="TOTALS",
+        )
+        # TODO: there should be attributes included in response but they are missing
+        # if response["ResponseMetadata"]["HTTPStatusCode"] != 200:
+        #     throw error
         return response
 
     #####################################################################
-    # TODO: add helper method to delete the data
-    def delete_cruise(
-        self,
-        table_name,
-        cruise_name,
+    def describe_table(
+            self,
+            table_name,
     ):
-        pass
+        """
+        Get a description of the table. Used to verify that records were added/removed.
+        """
+        response = self.__dynamodb_client.describe_table(TableName=table_name)
+        print(response)
+        return response
+
+
 
+    #####################################################################
+    # TODO: from test_raw_to_zarr get enum and use here
+    # def __update_processing_status(
+    #         self,
+    #         file_name: str,
+    #         cruise_name: str,
+    #         pipeline_status: str,
+    #         error_message: str = None,
+    # ):
+    #     print(f"Updating processing status to {pipeline_status}.")
+    #     if error_message:
+    #         print(f"Error message: {error_message}")
+    #         self.__dynamo.update_item(
+    #             table_name=self.__table_name,
+    #             key={
+    #                 'FILE_NAME': {'S': file_name},  # Partition Key
+    #                 'CRUISE_NAME': {'S': cruise_name},  # Sort Key
+    #             },
+    #             attribute_names={
+    #                 '#PT': 'PIPELINE_TIME',
+    #                 '#PS': 'PIPELINE_STATUS',
+    #                 '#EM': 'ERROR_MESSAGE',
+    #             },
+    #             expression='SET #PT = :pt, #PS = :ps, #EM = :em',
+    #             attribute_values={
+    #                 ':pt': {
+    #                     'S': datetime.now().isoformat(timespec="seconds") + "Z"
+    #                 },
+    #                 ':ps': {
+    #                     'S': pipeline_status
+    #                 },
+    #                 ':em': {
+    #                     'S': error_message
+    #                 }
+    #             }
+    #         )
+    #     else:
+    #         self.__dynamo.update_item(
+    #             table_name=self.__table_name,
+    #             key={
+    #                 'FILE_NAME': {'S': file_name},  # Partition Key
+    #                 'CRUISE_NAME': {'S': cruise_name},  # Sort Key
+    #             },
+    #             attribute_names={
+    #                 '#PT': 'PIPELINE_TIME',
+    #                 '#PS': 'PIPELINE_STATUS',
+    #             },
+    #             expression='SET #PT = :pt, #PS = :ps',
+    #             attribute_values={
+    #                 ':pt': {
+    #                     'S': datetime.now().isoformat(timespec="seconds") + "Z"
+    #                 },
+    #                 ':ps': {
+    #                     'S': pipeline_status
+    #                 }
+    #             }
+    #         )
+    #     print("Done updating processing status.")
 
 #########################################################################

{water_column_sonar_processing-0.0.7 → water_column_sonar_processing-0.0.8}/src/water_column_sonar_processing/aws/s3_manager.py

@@ -1,9 +1,8 @@
 import json
 import os
+import boto3
 from collections.abc import Generator
 from concurrent.futures import ThreadPoolExecutor, as_completed
-
-import boto3
 from boto3.s3.transfer import TransferConfig
 from botocore.config import Config
 from botocore.exceptions import ClientError
@@ -25,10 +24,16 @@ class S3Manager:
     #####################################################################
     def __init__(
         self,
+        # input_endpoint_url: str,
+        # output_endpoint_url: str,
+        # endpoint_url
         # TODO: Need to allow passing in of credentials when writing to protected bucket
     ):
         self.input_bucket_name = os.environ.get("INPUT_BUCKET_NAME")
         self.output_bucket_name = os.environ.get("OUTPUT_BUCKET_NAME")
+        # self.endpoint_url = endpoint_url
+        # self.input_endpoint_url = input_endpoint_url
+        # self.output_endpoint_url = output_endpoint_url
         self.s3_region = os.environ.get("AWS_REGION", default="us-east-1")
         self.s3_client_config = Config(max_pool_connections=MAX_POOL_CONNECTIONS)
         self.s3_transfer_config = TransferConfig(
@@ -46,6 +51,7 @@ class S3Manager:
             service_name="s3",
             config=self.s3_client_config,
             region_name=self.s3_region,
+            # endpoint_url=endpoint_url, # TODO: temporary
         )
         self.s3_resource = boto3.resource(
             service_name="s3",
@@ -53,7 +59,6 @@ class S3Manager:
             region_name=self.s3_region,
         )
         # self.paginator = self.s3_client.get_paginator(operation_name='list_objects_v2')
-        # TODO: create both "s3_client_input" and "s3_client_output" ???
         self.s3_session_noaa_wcsd_zarr_pds = boto3.Session(
             aws_access_key_id=os.environ.get("OUTPUT_BUCKET_ACCESS_KEY"),
             aws_secret_access_key=os.environ.get("OUTPUT_BUCKET_SECRET_ACCESS_KEY"),
@@ -63,19 +68,20 @@ class S3Manager:
             service_name="s3",
             config=self.s3_client_config,
             region_name=self.s3_region,
+            # endpoint_url=endpoint_url, # TODO: temporary
         )
-        self.s3_resource_noaa_wcsd_zarr_pds = (
-            self.s3_session_noaa_wcsd_zarr_pds.resource(
-                service_name="s3",
-                config=self.s3_client_config,
-                region_name=self.s3_region,
-            )
+        self.s3_resource_noaa_wcsd_zarr_pds = self.s3_session_noaa_wcsd_zarr_pds.resource(
+            service_name="s3",
+            config=self.s3_client_config,
+            region_name=self.s3_region,
         )
+        self.paginator = self.s3_client.get_paginator('list_objects_v2')
+        self.paginator_noaa_wcsd_zarr_pds = self.s3_client_noaa_wcsd_zarr_pds.get_paginator('list_objects_v2')
 
-    def get_client(self):
+    def get_client(self): # TODO: do i need this?
         return self.s3_session.client(
             service_name="s3",
-            config=self.__s3_client_config,
+            config=self.s3_client_config,
             region_name=self.s3_region,
         )
 
@@ -103,17 +109,18 @@ class S3Manager:
         self,
         file_name: str,
         key: str,
+        output_bucket_name: str,
     ):
-        self.s3_client_noaa_wcsd_zarr_pds.upload_file(
-            Filename=file_name,
-            Bucket=self.output_bucket_name,
-            Key=key,
-        )
+        """
+        Used to upload a single file, e.g. the GeoJSON file to the NODD bucket
+        """
+        self.s3_resource_noaa_wcsd_zarr_pds.Bucket(output_bucket_name).upload_file(Filename=file_name, Key=key)
         return key
 
     #####################################################################
     def upload_files_with_thread_pool_executor(
         self,
+        output_bucket_name: str,
         all_files: list,
     ):
         # 'all_files' is passed a list of lists: [[local_path, s3_key], [...], ...]
@@ -122,21 +129,45 @@ class S3Manager:
             with ThreadPoolExecutor(max_workers=MAX_WORKERS) as executor:
                 futures = [
                     executor.submit(
-                        self.upload_nodd_file,
+                        self.upload_nodd_file,  # TODO: verify which one is using this
                         all_file[0],  # file_name
                         all_file[1],  # key
+                        output_bucket_name,  # output_bucket_name
                     )
                     for all_file in all_files
                 ]
                 for future in as_completed(futures):
                     result = future.result()
                     if result:
-                        all_uploads.extend(result)
+                        all_uploads.extend([result])
         except Exception as err:
             print(err)
         print("Done uploading files using threading pool.")
         return all_uploads
 
+    #####################################################################
+    # def upload_nodd_file2(
+    #         self,
+    #         body: str,
+    #         bucket: str,
+    #         key: str,
+    # ):
+    #     self.s3_client_noaa_wcsd_zarr_pds.put_object(
+    #         Body=body,
+    #         Bucket=bucket,
+    #         Key=key,
+    #     )
+
+    # TODO: this uses resource, try to use client
+    def upload_file(
+            self,
+            filename: str,
+            bucket_name: str,
+            key: str,
+    ):
+        # self.s3_client.upload_file(Filename=filename, Bucket=bucket, Key=key)
+        self.s3_resource.Bucket(bucket_name).upload_file(Filename=filename, Key=key)
+
     #####################################################################
     def upload_zarr_files_to_bucket(  # noaa-wcsd-model-pds
         self,
@@ -165,32 +196,34 @@ class S3Manager:
         return all_uploads
 
     #####################################################################
-    # used: raw-to-model
-    def list_objects(  # noaa-wcsd-pds and noaa-wcsd-model-pds
-        self, bucket_name, prefix
+    # used: raw-to-zarr
+    def list_objects(  # noaa-wcsd-pds and noaa-wcsd-zarr-pds
+        self,
+        bucket_name,
+        prefix
     ):
         # analog to "find_children_objects"
         # Returns a list of key strings for each object in bucket defined by prefix
-        s3_client = self.s3_client
+        # s3_client = self.s3_client
         keys = []
-        paginator = s3_client.get_paginator("list_objects_v2")
-        page_iterator = paginator.paginate(Bucket=bucket_name, Prefix=prefix)
+        # paginator = s3_client.get_paginator("list_objects_v2")
+        page_iterator = self.paginator.paginate(Bucket=bucket_name, Prefix=prefix)
         for page in page_iterator:
             if "Contents" in page.keys():
                 keys.extend([k["Key"] for k in page["Contents"]])
         return keys
 
-    def list_nodd_objects(  # These are used by the geometry for uploading data
-        self,
-        prefix,
-    ):
-        # Returns a list of key strings for each object in bucket defined by prefix
-        keys = []
-        paginator = self.s3_client_noaa_wcsd_zarr_pds.get_paginator("list_objects_v2")
-        for page in paginator.paginate(Bucket=self.output_bucket_name, Prefix=prefix):
-            if "Contents" in page.keys():
-                keys.extend([k["Key"] for k in page["Contents"]])
-        return keys
+    # def list_nodd_objects(  # These are used by the geometry for uploading data
+    #     self,
+    #     prefix,
+    # ):
+    #     # Returns a list of key strings for each object in bucket defined by prefix
+    #     keys = []
+    #     page_iterator = self.paginator_noaa_wcsd_zarr_pds.paginate(Bucket=self.output_bucket_name, Prefix=prefix):
+    #     for page in paginator.paginate(Bucket=self.output_bucket_name, Prefix=prefix):
+    #         if "Contents" in page.keys():
+    #             keys.extend([k["Key"] for k in page["Contents"]])
+    #     return keys
 
     #####################################################################
     # TODO: change name to "directory"
@@ -279,9 +312,10 @@ class S3Manager:
         self,
         bucket_name,
         key,
-        file_name,
+        file_name, # where the file will be saved
     ):
         self.s3_client.download_file(Bucket=bucket_name, Key=key, Filename=file_name)
+        # TODO: if bottom file doesn't exist, don't fail downloader
         print("downloaded file")
 
     #####################################################################
@@ -318,7 +352,7 @@ class S3Manager:
     #####################################################################
     # not used TODO: remove
     def put(self, bucket_name, key, body):  # noaa-wcsd-model-pds
-        self.s3_client.put_object(Bucket=bucket_name, Key=key, Body=body)
+        self.s3_client.put_object(Bucket=bucket_name, Key=key, Body=body) # "Body" can be a file
 
     #####################################################################
     def read_s3_json(