acdc_aws_etl_pipeline 0.6.9__py3-none-any.whl → 0.7.1__py3-none-any.whl

acdc_aws_etl_pipeline/upload/metadata_submitter.py

@@ -1,34 +1,41 @@
 import os
-# redefine to use local cache in /tmp
-os.environ['XDG_CACHE_HOME'] = '/tmp/.cache'
-
+import sys
+import time
 import json
 import boto3
+from botocore.exceptions import BotoCoreError, ClientError
 from gen3.auth import Gen3Auth
-from gen3.index import Gen3Index
 from gen3.submission import Gen3Submission
 import logging
 from datetime import datetime
 import jwt
-from typing import Dict, List
+import requests
+from typing import Any, Dict, List, Optional
 import re
 import pandas as pd
 import uuid
-from acdc_aws_etl_pipeline.validate.validate import write_parquet_to_db
+from acdc_aws_etl_pipeline.validate.validate import (
+    write_parquet_to_db,
+)
+from tenacity import retry, stop_after_attempt, wait_exponential
+
+# redefine to use local cache in /tmp
+os.environ['XDG_CACHE_HOME'] = '/tmp/.cache'
 
 logger = logging.getLogger(__name__)
 
-def create_boto3_session(aws_profile: str = None):
+def create_boto3_session(aws_profile: Optional[str] = None):
     """
     Create and return a boto3 Session object using an optional AWS profile.
 
     Args:
-        aws_profile (str, optional): The AWS CLI named profile to use for credentials. If None, uses default credentials.
+        aws_profile (str, optional): The AWS CLI named profile to use.
+            If None, uses default credentials.
 
     Returns:
         boto3.Session: The created session instance.
     """
-    logger.debug(f"Creating boto3 session with aws_profile={aws_profile}")
+    logger.debug("Creating boto3 session with aws_profile=%s", aws_profile)
     return boto3.Session(profile_name=aws_profile) if aws_profile else boto3.Session()
 
 def is_s3_uri(s3_uri: str) -> bool:
@@ -41,7 +48,7 @@ def is_s3_uri(s3_uri: str) -> bool:
     Returns:
         bool: True if the string starts with 's3://', False otherwise.
     """
-    logger.debug(f"Checking if {s3_uri} is an S3 URI.")
+    logger.debug("Checking if %s is an S3 URI.", s3_uri)
     return s3_uri.startswith("s3://")
 
 def get_filename(file_path: str) -> str:
@@ -55,7 +62,11 @@ def get_filename(file_path: str) -> str:
         str: The filename (with extension).
     """
     filename = file_path.split("/")[-1]
-    logger.debug(f"Extracted filename '{filename}' from file_path '{file_path}'.")
+    logger.debug(
+        "Extracted filename '%s' from file_path '%s'.",
+        filename,
+        file_path,
+    )
     return filename
 
 def get_node_from_file_path(file_path: str) -> str:
@@ -70,7 +81,7 @@ def get_node_from_file_path(file_path: str) -> str:
     """
     filename = get_filename(file_path)
     node = filename.split(".")[0]
-    logger.debug(f"Extracted node '{node}' from filename '{filename}'.")
+    logger.debug("Extracted node '%s' from filename '%s'.", node, filename)
     return node
 
 def list_metadata_jsons(metadata_dir: str) -> list:
@@ -87,11 +98,18 @@ def list_metadata_jsons(metadata_dir: str) -> list:
         Exception: If there is an error reading the directory.
     """
     try:
-        logger.info(f"Listing .json files in metadata directory: {metadata_dir}")
+        logger.info(
+            "Listing .json files in metadata directory: %s",
+            metadata_dir,
+        )
         files = os.listdir(metadata_dir)
-        return [os.path.abspath(os.path.join(metadata_dir, f)) for f in files if f.endswith(".json")]
-    except Exception as e:
-        logger.error(f"Error listing metadata JSONs in {metadata_dir}: {e}")
+        return [
+            os.path.abspath(os.path.join(metadata_dir, file_name))
+            for file_name in files
+            if file_name.endswith(".json")
+        ]
+    except OSError as e:
+        logger.error("Error listing metadata JSONs in %s: %s", metadata_dir, e)
         raise
 
 def find_data_import_order_file(metadata_dir: str) -> str:
@@ -108,16 +126,22 @@ def find_data_import_order_file(metadata_dir: str) -> str:
         FileNotFoundError: If no such file is found.
     """
     try:
-        logger.info(f"Searching for DataImportOrder.txt in {metadata_dir}")
+        logger.info("Searching for DataImportOrder.txt in %s", metadata_dir)
         files = [os.path.join(metadata_dir, f) for f in os.listdir(metadata_dir)]
         order_files = [f for f in files if "DataImportOrder.txt" in f]
         if not order_files:
             logger.error("No DataImportOrder.txt file found in the given directory.")
-            raise FileNotFoundError("No DataImportOrder.txt file found in the given directory.")
-        logger.debug(f"Found DataImportOrder.txt file: {order_files[0]}")
+            raise FileNotFoundError(
+                "No DataImportOrder.txt file found in the given directory."
+            )
+        logger.debug("Found DataImportOrder.txt file: %s", order_files[0])
         return order_files[0]
-    except Exception as e:
-        logger.error(f"Error finding DataImportOrder.txt in {metadata_dir}: {e}")
+    except OSError as e:
+        logger.error(
+            "Error finding DataImportOrder.txt in %s: %s",
+            metadata_dir,
+            e,
+        )
         raise
 
 def list_metadata_jsons_s3(s3_uri: str, session) -> list:
@@ -125,13 +149,14 @@ def list_metadata_jsons_s3(s3_uri: str, session) -> list:
     List all .json files in an S3 "directory" (prefix).
 
     Args:
-        s3_uri (str): S3 URI to the metadata directory (e.g. "s3://my-bucket/path/to/dir").
+        s3_uri (str): S3 URI to the metadata directory
+            (e.g. "s3://my-bucket/path/to/dir").
         session (boto3.Session): An active boto3 Session.
 
     Returns:
         list: List of S3 URIs for all .json files found under the prefix.
     """
-    logger.info(f"Listing .json files in S3 metadata directory: {s3_uri}")
+    logger.info("Listing .json files in S3 metadata directory: %s", s3_uri)
     s3 = session.client('s3')
     bucket = s3_uri.split("/")[2]
     prefix = "/".join(s3_uri.split("/")[3:])
@@ -144,7 +169,7 @@ def list_metadata_jsons_s3(s3_uri: str, session) -> list:
         for obj in objects.get('Contents', [])
         if obj['Key'].endswith(".json")
     ]
-    logger.debug(f"Found {len(result)} .json files in S3 at {s3_uri}")
+    logger.debug("Found %s .json files in S3 at %s", len(result), s3_uri)
     return result
 
 def find_data_import_order_file_s3(s3_uri: str, session) -> str:
@@ -161,16 +186,29 @@ def find_data_import_order_file_s3(s3_uri: str, session) -> str:
     Raises:
         FileNotFoundError: If the file does not exist in the specified prefix.
     """
-    logger.info(f"Searching for DataImportOrder.txt in S3 metadata directory: {s3_uri}")
+    logger.info(
+        "Searching for DataImportOrder.txt in S3 metadata directory: %s",
+        s3_uri,
+    )
     s3 = session.client('s3')
     bucket = s3_uri.split("/")[2]
     prefix = "/".join(s3_uri.split("/")[3:])
     objects = s3.list_objects(Bucket=bucket, Prefix=prefix)
-    order_files = [obj['Key'] for obj in objects.get('Contents', []) if obj['Key'].endswith("DataImportOrder.txt")]
+    order_files = [
+        obj['Key']
+        for obj in objects.get('Contents', [])
+        if obj['Key'].endswith("DataImportOrder.txt")
+    ]
     if not order_files:
         logger.error("No DataImportOrder.txt file found in the given S3 directory.")
-        raise FileNotFoundError("No DataImportOrder.txt file found in the given directory.")
-    logger.debug(f"Found DataImportOrder.txt file in S3: s3://{bucket}/{order_files[0]}")
+        raise FileNotFoundError(
+            "No DataImportOrder.txt file found in the given directory."
+        )
+    logger.debug(
+        "Found DataImportOrder.txt file in S3: s3://%s/%s",
+        bucket,
+        order_files[0],
+    )
     return f"s3://{bucket}/{order_files[0]}"
 
 def read_metadata_json(file_path: str) -> dict:
@@ -183,10 +221,14 @@ def read_metadata_json(file_path: str) -> dict:
     Returns:
         dict or list: Parsed contents of the JSON file.
     """
-    logger.info(f"Reading metadata json from local file: {file_path}")
-    with open(file_path, "r") as f:
+    logger.info("Reading metadata json from local file: %s", file_path)
+    with open(file_path, "r", encoding="utf-8") as f:
         data = json.load(f)
-    logger.debug(f"Read {len(data) if isinstance(data, list) else 'object'} objects from {file_path}")
+    logger.debug(
+        "Read %s objects from %s",
+        len(data) if isinstance(data, list) else 'object',
+        file_path,
+    )
     return data
 
 def read_metadata_json_s3(s3_uri: str, session) -> dict:
@@ -200,11 +242,18 @@ def read_metadata_json_s3(s3_uri: str, session) -> dict:
     Returns:
         dict or list: Parsed JSON object from S3 file.
     """
-    logger.info(f"Reading metadata json from S3 file: {s3_uri}")
+    logger.info("Reading metadata json from S3 file: %s", s3_uri)
     s3 = session.client('s3')
-    obj = s3.get_object(Bucket=s3_uri.split("/")[2], Key="/".join(s3_uri.split("/")[3:]))
+    obj = s3.get_object(
+        Bucket=s3_uri.split("/")[2],
+        Key="/".join(s3_uri.split("/")[3:]),
+    )
     data = json.loads(obj['Body'].read().decode('utf-8'))
-    logger.debug(f"Read {len(data) if isinstance(data, list) else 'object'} objects from {s3_uri}")
+    logger.debug(
+        "Read %s objects from %s",
+        len(data) if isinstance(data, list) else 'object',
+        s3_uri,
+    )
     return data
 
 def read_data_import_order_txt_s3(s3_uri: str, session, exclude_nodes: list = None) -> list:
@@ -224,20 +273,41 @@ def read_data_import_order_txt_s3(s3_uri: str, session, exclude_nodes: list = No
     """
     filename = s3_uri.split("/")[-1]
     if 'DataImportOrder.txt' not in filename:
-        logger.error(f"File {filename} is not a DataImportOrder.txt file")
-        raise ValueError(f"File {filename} is not a DataImportOrder.txt file")
-    logger.info(f"Reading DataImportOrder.txt from S3 file: {s3_uri}")
+        logger.error("File %s is not a DataImportOrder.txt file", filename)
+        raise ValueError(
+            f"File {filename} is not a DataImportOrder.txt file"
+        )
+    logger.info(
+        "Reading DataImportOrder.txt from S3 file: %s",
+        s3_uri,
+    )
     s3 = session.client('s3')
-    obj = s3.get_object(Bucket=s3_uri.split("/")[2], Key="/".join(s3_uri.split("/")[3:]))
+    obj = s3.get_object(
+        Bucket=s3_uri.split("/")[2],
+        Key="/".join(s3_uri.split("/")[3:]),
+    )
     content = obj['Body'].read().decode('utf-8')
-    import_order = [line.rstrip() for line in content.splitlines() if line.strip()]
-    logger.debug(f"Raw import order from S3 file: {import_order}")
+    import_order = [
+        line.rstrip()
+        for line in content.splitlines()
+        if line.strip()
+    ]
+    logger.debug("Raw import order from S3 file: %s", import_order)
     if exclude_nodes is not None:
         import_order = [node for node in import_order if node not in exclude_nodes]
-        logger.debug(f"Import order after excluding nodes {exclude_nodes}: {import_order}")
-    logger.debug(f"Final import order from S3 file {s3_uri}: {import_order}")
+        logger.debug(
+            "Import order after excluding nodes %s: %s",
+            exclude_nodes,
+            import_order,
+        )
+    logger.debug(
+        "Final import order from S3 file %s: %s",
+        s3_uri,
+        import_order,
+    )
     return import_order
 
+
 def read_data_import_order_txt(file_path: str, exclude_nodes: list) -> list:
     """
     Read DataImportOrder.txt from local file, optionally excluding some nodes.
@@ -253,17 +323,26 @@ def read_data_import_order_txt(file_path: str, exclude_nodes: list) -> list:
         FileNotFoundError: If the file is not found.
     """
     try:
-        logger.info(f"Reading DataImportOrder.txt from local file: {file_path}")
-        with open(file_path, "r") as f:
+        logger.info(
+            "Reading DataImportOrder.txt from local file: %s",
+            file_path,
+        )
+        with open(file_path, "r", encoding="utf-8") as f:
             import_order = [line.rstrip() for line in f if line.strip()]
-            logger.debug(f"Raw import order from file: {import_order}")
+            logger.debug("Raw import order from file: %s", import_order)
             if exclude_nodes is not None:
-                import_order = [node for node in import_order if node not in exclude_nodes]
-                logger.debug(f"Import order after excluding nodes {exclude_nodes}: {import_order}")
-        logger.debug(f"Final import order from {file_path}: {import_order}")
+                import_order = [
+                    node for node in import_order if node not in exclude_nodes
+                ]
+                logger.debug(
+                    "Import order after excluding nodes %s: %s",
+                    exclude_nodes,
+                    import_order,
+                )
+        logger.debug("Final import order from %s: %s", file_path, import_order)
         return import_order
     except FileNotFoundError:
-        logger.error(f"Error: DataImportOrder.txt not found in {file_path}")
+        logger.error("Error: DataImportOrder.txt not found in %s", file_path)
         return []
 
 def split_json_objects(json_list, max_size_kb=50, print_results=False) -> list:
@@ -280,7 +359,12 @@ def split_json_objects(json_list, max_size_kb=50, print_results=False) -> list:
     Returns:
         list: List of lists. Each sublist size (JSON-serialized) <= max_size_kb.
     """
-    logger.info(f"Splitting JSON objects into max {max_size_kb} KB chunks. Total items: {len(json_list)}")
+    logger.info(
+        "Splitting JSON objects into max %s KB chunks. Total items: %s",
+        max_size_kb,
+        len(json_list),
+    )
+
     def get_size_in_kb(obj):
         """
         Get the size in kilobytes of the JSON-serialized object.
@@ -291,12 +375,11 @@ def split_json_objects(json_list, max_size_kb=50, print_results=False) -> list:
         Returns:
             float: Size of the object in kilobytes.
         """
-        import sys
         size_kb = sys.getsizeof(json.dumps(obj)) / 1024
-        logger.debug(f"Calculated size: {size_kb:.2f} KB")
+        logger.debug("Calculated size: %.2f KB", size_kb)
         return size_kb
 
-    def split_list(json_list):
+    def split_list(items):
         """
         Recursively split the list so each chunk fits within max_size_kb.
 
@@ -306,20 +389,34 @@ def split_json_objects(json_list, max_size_kb=50, print_results=False) -> list:
         Returns:
             list: List of sublists.
         """
-        if get_size_in_kb(json_list) <= max_size_kb:
-            logger.debug(f"Split length {len(json_list)} is within max size {max_size_kb} KB.")
-            return [json_list]
-        mid = len(json_list) // 2
-        left_list = json_list[:mid]
-        right_list = json_list[mid:]
-        logger.debug(f"Splitting list at index {mid}: left {len(left_list)}, right {len(right_list)}")
+        if get_size_in_kb(items) <= max_size_kb:
+            logger.debug(
+                "Split length %s is within max size %s KB.",
+                len(items),
+                max_size_kb,
+            )
+            return [items]
+        mid = len(items) // 2
+        left_list = items[:mid]
+        right_list = items[mid:]
+        logger.debug(
+            "Splitting list at index %s: left %s, right %s",
+            mid,
+            len(left_list),
+            len(right_list),
+        )
         return split_list(left_list) + split_list(right_list)
 
     split_lists = split_list(json_list)
     if print_results:
         for i, lst in enumerate(split_lists):
-            logger.info(f"List {i+1} size: {get_size_in_kb(lst):.2f} KB, contains {len(lst)} objects")
-    logger.debug(f"Total splits: {len(split_lists)}")
+            logger.info(
+                "List %s size: %.2f KB, contains %s objects",
+                i + 1,
+                get_size_in_kb(lst),
+                len(lst),
+            )
+    logger.debug("Total splits: %s", len(split_lists))
     return split_lists
 
 def get_gen3_api_key_aws_secret(secret_name: str, region_name: str, session) -> dict:
@@ -337,29 +434,40 @@ def get_gen3_api_key_aws_secret(secret_name: str, region_name: str, session) ->
     Raises:
         Exception: On failure to retrieve or parse the secret.
     """
-    logger.info(f"Retrieving Gen3 API key from AWS Secrets Manager: secret_name={secret_name}, region={region_name}")
-    client = session.client(service_name='secretsmanager', region_name=region_name)
+    logger.info(
+        "Retrieving Gen3 API key from AWS Secrets Manager: "
+        "secret_name=%s, region=%s",
+        secret_name,
+        region_name,
+    )
+    client = session.client(
+        service_name='secretsmanager',
+        region_name=region_name,
+    )
     try:
         get_secret_value_response = client.get_secret_value(
-            SecretId=secret_name
+            SecretId=secret_name,
         )
-    except Exception as e:
-        logger.error(f"Error getting secret value from AWS Secrets Manager: {e}")
-        raise e
+    except (BotoCoreError, ClientError) as e:
+        logger.error("Error getting secret value from AWS Secrets Manager: %s", e)
+        raise
 
     secret = get_secret_value_response['SecretString']
 
     try:
         secret = json.loads(secret)
         api_key = secret
-        logger.debug(f"Retrieved Gen3 API key from secret {secret_name}")
+        logger.debug("Retrieved Gen3 API key from secret %s", secret_name)
         return api_key
-    except Exception as e:
-        logger.error(f"Error parsing Gen3 API key from AWS Secrets Manager: {e}")
-        raise e
+    except (json.JSONDecodeError, TypeError) as e:
+        logger.error("Error parsing Gen3 API key from AWS Secrets Manager: %s", e)
+        raise
 
 
-def infer_api_endpoint_from_jwt(jwt_token: str, api_version: str = 'v0') -> str:
+def infer_api_endpoint_from_jwt(
+    jwt_token: str,
+    api_version: str = 'v0',
+) -> str:
     """
     Extracts the URL from a JSON Web Token (JWT) credential.
 
@@ -370,11 +478,14 @@ def infer_api_endpoint_from_jwt(jwt_token: str, api_version: str = 'v0') -> str:
         str: The extracted URL.
     """
     logger.info("Decoding JWT to extract API URL.")
-    url = jwt.decode(jwt_token, options={"verify_signature": False}).get('iss', '')
+    url = jwt.decode(
+        jwt_token,
+        options={"verify_signature": False},
+    ).get('iss', '')
     if '/user' in url:
         url = url.split('/user')[0]
     url = f"{url}/api/{api_version}"
-    logger.info(f"Extracted API URL from JWT: {url}")
+    logger.info("Extracted API URL from JWT: %s", url)
     return url
 
 
@@ -393,190 +504,16 @@ def create_gen3_submission_class(api_key: dict):
     jwt_token = api_key['api_key']
     logger.info("Inferring API endpoint from JWT token.")
     api_endpoint = infer_api_endpoint_from_jwt(jwt_token)
-    logger.debug(f"Inferred API endpoint: {api_endpoint}")
-    logger.info(f"Creating Gen3Submission class for endpoint: {api_endpoint}")
+    logger.debug("Inferred API endpoint: %s", api_endpoint)
+    logger.info(
+        "Creating Gen3Submission class for endpoint: %s",
+        api_endpoint,
+    )
     auth = Gen3Auth(refresh_token=api_key)
     submit = Gen3Submission(endpoint=api_endpoint, auth_provider=auth)
     return submit
 
 
-def submit_data_chunks(
-    split_json_list: list,
-    node: str,
-    gen3_submitter,
-    project_id: str,
-    max_retries: int,
-    file_path: str,
-    program_id: str = "program1"
-) -> List[Dict]:
-    """
-    Submit each chunk of data (in split_json_list) for a given node to Gen3, using retry logic and logging on failures.
-
-    Args:
-        split_json_list (list): List of JSON-serializable chunked data to submit.
-        node (str): Name of the data node being submitted.
-        gen3_submitter: A Gen3Submission instance for making submissions.
-        project_id (str): The project identifier within Gen3.
-        max_retries (int): Maximum number of retry attempts per chunk on failure.
-        file_path (str): Path of the file that was submitted. Used only for data capture.
-        program_id (str, optional): The Gen3 program id (default: "program1").
-
-    Returns:
-        List[Dict]: List of response dictionaries for each submitted chunk.
-
-    Raises:
-        Exception: If submission fails after all retry attempts for any chunk.
-    """
-
-    n_json_data = len(split_json_list)
-    response_results = []
-
-    for index, jsn in enumerate(split_json_list):
-        progress_str = f"{index + 1}/{n_json_data}"
-
-        submission_success = False
-        last_exception = None
-
-        attempt = 0
-        while attempt <= max_retries:
-            try:
-                if attempt == 0:
-                    log_msg = (
-                        f"[SUBMIT]  | Project: {project_id:<10} | Node: {node:<12} | "
-                        f"Split: {progress_str:<5}"
-                    )
-                    logger.info(log_msg)
-                else:
-                    log_msg = (
-                        f"[RETRY]   | Project: {project_id:<10} | Node: {node:<12} | "
-                        f"Split: {progress_str:<5} | Attempt: {attempt}/{max_retries}"
-                    )
-                    logger.warning(log_msg)
-
-                res = gen3_submitter.submit_record(program_id, project_id, jsn)
-                res.update({"file_path": file_path})
-                response_results.append(res)
-                submission_success = True
-                logger.info(
-                    f"\033[92m[SUCCESS]\033[0m | Project: {project_id:<10} | "
-                    f"Node: {node:<12} | Split: {progress_str:<5}"
-                )
-                break  # Success
-
-            except Exception as e:
-                last_exception = e
-                logger.error(
-                    f"Error submitting chunk {progress_str} for node '{node}': {e}"
-                )
-
-                if attempt < max_retries:
-                    import time
-                    time.sleep(0.2)
-                else:
-                    logger.critical(
-                        f"\033[91m[FAILED]\033[0m  | Project: {project_id:<10} | "
-                        f"Node: {node:<12} | Split: {progress_str:<5} | Error: {e}"
-                    )
-            attempt += 1
-
-        if not submission_success:
-            # After retries, still failed
-            raise Exception(
-                f"Failed to submit chunk {progress_str} for node '{node}' after {max_retries + 1} attempts. "
-                f"Last error: {last_exception}"
-            )
-
-    logger.info(f"Finished submitting node '{node}'.")
-    return response_results
-
-
-def flatten_submission_results(submission_results: List[Dict]) -> List[Dict]:
-    """
-    Flattens a list of Gen3 submission result dictionaries into a single list of entity dictionaries.
-
-    For each submission result, this function processes its entities (if any),
-    extracting the 'project_id' and 'submitter_id' from the 'unique_keys' field (if present)
-    into the top-level entity dictionary for easy access.
-
-    Any submission result that does not have a code of 200 or lacks entities is skipped, and a warning is logged.
-
-    Args:
-        submission_results (List[Dict]):
-            A list of Gen3 submission result dictionaries, each containing at least a "code" and "entities" entry.
-
-    Returns:
-        List[Dict]:
-            A flat list, where each element is an entity dictionary (with keys 'project_id' and 'submitter_id' added if available).
-    """
-    flat_list_dict = []
-    total = len(submission_results)
-    logger.info(f"Flattening {total} submission result(s)...")
-
-    for idx, obj in enumerate(submission_results, 1):
-        transaction_id = obj.get("transaction_id")
-        code = obj.get("code")
-        if code != 200:
-            logger.warning(f"Skipping submission result at index {idx-1} (code={code})")
-            continue
-
-        entities = obj.get("entities")
-
-        if entities is None:
-            logger.warning(f"No entities found in submission result at index {idx-1}")
-            continue
-
-        logger.info(f"Processing submission result {idx} of {total}, {len(entities)} entities")
-
-        for entity in entities:
-            unique_keys = entity.get("unique_keys", [{}])
-            if unique_keys and isinstance(unique_keys, list):
-                keys = unique_keys[0]
-                entity["project_id"] = keys.get("project_id")
-                entity["submitter_id"] = keys.get("submitter_id")
-                entity["transaction_id"] = transaction_id
-                entity["file_path"] = obj.get("file_path", '')
-            flat_list_dict.append(entity)
-
-    # renaming cols
-    for entity in flat_list_dict:
-        entity["gen3_guid"] = entity.pop("id", None)
-        entity["node"] = entity.pop("type", None)
-
-    logger.info(f"Finished flattening. Total entities: {len(flat_list_dict)}")
-    return flat_list_dict
-
-
-def find_version_from_path(path):
-    version_pattern = re.compile(r"^v?(\d+\.\d+\.\d+)$")
-    found_versions = []
-
-    for segment in path.split('/'):
-        match = version_pattern.match(segment)
-        if match:
-            found_versions.append(match.group(1))
-
-    if not found_versions:
-        return None
-
-    if len(found_versions) > 1:
-        logger.warning("more than one match found in path for version string")
-
-    return found_versions[-1]
-
-
-def collect_versions_from_metadata_file_list(metadata_file_list):
-    versions = []
-    for file_path in metadata_file_list:
-        version = find_version_from_path(file_path)
-        if version:
-            versions.append(version)
-    versions = list(set(versions))
-    if len(versions) > 1:
-        logger.error(f"more than one version found in metadata file list: {metadata_file_list}")
-        raise
-    return versions[0]
-
-
 class MetadataSubmitter:
     def __init__(
         self,
@@ -584,49 +521,440 @@ class MetadataSubmitter:
         api_key: dict,
         project_id: str,
         data_import_order_path: str,
+        dataset_root: str,
+        database: str,
+        table: str,
         program_id: str = "program1",
         max_size_kb: int = 100,
-        exclude_nodes: list = ["project", "program", "acknowledgement", "publication"],
+        exclude_nodes: Optional[List[str]] = None,
         max_retries: int = 3,
-        aws_profile: str = None
+        aws_profile: str = None,
+        partition_cols: Optional[List[str]] = None,
+        upload_to_database: bool = True
     ):
         """
-        Initialises a MetadataSubmitter for submitting a set of metadata JSON files to a Gen3 data commons endpoint, in order.
+        Initialises a MetadataSubmitter for submitting a set of metadata JSON
+        files to a Gen3 data commons endpoint, in order.
+
+        **Workflow Overview:**
+        1.  **Node Traversal:** The submitter iterates through each node defined in the
+            `data_import_order` list.
+        2.  **File Resolution:** For each node name, it locates the corresponding JSON file
+            (e.g., `node.json`) from the provided file list.
+        3.  **Chunking:** The JSON file is read and split into manageable chunks based on size.
+        4.  **Submission:** Each chunk is submitted to the Gen3 Sheepdog API via `gen3.submission`.
+        5.  **Response Handling:** The API response, which includes the `submission_id` for
+            the records, is captured.
+        6.  **Persistence:** The response data is flattened, converted into a DataFrame, and
+            written to Parquet files in S3. These records are also registered in a specific
+            upload table within the configured database for audit and tracking.
 
         Args:
-            metadata_file_list (list): List of local file paths or S3 URIs to metadata .json files, one per node type.
+            metadata_file_list (list): List of local file paths or S3 URIs to
+                metadata .json files, one per node type.
             api_key (dict): Gen3 API key as a parsed dictionary.
-            project_id (str): Gen3 project ID to submit data to.
-            data_import_order_path (str): Path or S3 URI to DataImportOrder.txt specifying node submission order.
+            project_id (str): Gen3 project ID to submit data to (e.g., "internal-project").
+            data_import_order_path (str): Path or S3 URI to DataImportOrder.txt
+                specifying node submission order.
+            dataset_root (str): S3 path where the parquet files will be stored.
+                Example: "s3://acdc-dataops-metadata/metadata_upload/"
+            database (str): Database name for storing the metadata upload.
+                Example: "acdc_dataops_metadata_db"
+            table (str): Table name for storing the metadata upload.
+                Example: "metadata_upload"
             program_id (str, optional): Gen3 program ID (default: "program1").
-            max_size_kb (int, optional): Maximum size per submission chunk, in KB (default: 100).
-            exclude_nodes (list, optional): List of node names to skip during submission (default: ["project", "program", "acknowledgement", "publication"]).
-            max_retries (int, optional): Maximum number of retry attempts per node chunk (default: 3).
-            aws_profile (str, optional): AWS CLI named profile to use for boto3 session (default: None).
+            max_size_kb (int, optional): Maximum size per submission chunk,
+                in KB (default: 100).
+            exclude_nodes (list, optional): List of node names to skip during
+                submission. Defaults to ["project", "program", "acknowledgement", "publication"].
+            max_retries (int, optional): Maximum number of retry attempts per
+                node chunk (default: 3).
+            aws_profile (str, optional): AWS CLI named profile to use for boto3
+                session (default: None).
+            partition_cols (list, optional): List of column names to partition the parquet table by.
+                Defaults to ["upload_datetime"].
+            upload_to_database (bool, optional): Whether to upload the metadata to a database.
+                Defaults to True. The database is defined by dataset_root, database, and table.
         """
         self.metadata_file_list = metadata_file_list
         self.api_key = api_key
         self.project_id = project_id
         self.data_import_order_path = data_import_order_path
+        self.dataset_root = dataset_root
+        self.database = database
+        self.table = table
         self.program_id = program_id
         self.max_size_kb = max_size_kb
-        self.exclude_nodes = exclude_nodes
+        self.exclude_nodes = exclude_nodes or [
+            "project",
+            "program",
+            "acknowledgement",
+            "publication",
+        ]
         self.max_retries = max_retries
         self.submission_results = []
         self.aws_profile = aws_profile
+        self.partition_cols = partition_cols or ["upload_datetime"]
+        self.upload_to_database = upload_to_database
         self.boto3_session = self._create_boto3_session()
         logger.info("MetadataSubmitter initialised.")
 
     def _create_gen3_submission_class(self):
+        """Helper to instantiate the Gen3Submission class using the provided API key."""
         return create_gen3_submission_class(self.api_key)
-    
+
     def _create_boto3_session(self):
+        """Helper to create a boto3 session using the provided AWS profile."""
         return create_boto3_session(self.aws_profile)
 
-    def _read_data_import_order(self, data_import_order_path: str, exclude_nodes: list[str], boto3_session = None):
+    def _flatten_submission_results(self, submission_results: List[Dict]) -> List[Dict]:
+        """
+        Flattens a list of Gen3 submission result dictionaries into a single
+        list of entity dictionaries.
+
+        For each submission result, this function processes its entities (if any),
+        extracting the 'project_id' and 'submitter_id' from the 'unique_keys'
+        field (if present) into the top-level entity dictionary for easy access.
+
+        Any submission result that does not have a code of 200 or lacks entities
+        is skipped, and a warning is logged.
+
+        Args:
+            submission_results (List[Dict]):
+                A list of Gen3 submission result dictionaries, each containing at
+                least a "code" and "entities" entry.
+
+        Returns:
+            List[Dict]:
+                A flat list, where each element is an entity dictionary
+                (with keys 'project_id' and 'submitter_id' added if available).
+        """
+        flat_list_dict = []
+        total = len(submission_results)
+        logger.info("Flattening %s submission result(s)...", total)
+
+        for idx, obj in enumerate(submission_results, 1):
+            transaction_id = obj.get("transaction_id")
+            code = obj.get("code")
+            if code != 200:
+                logger.warning(
+                    "Skipping submission result at index %s (code=%s)",
+                    idx - 1,
+                    code,
+                )
+                continue
+
+            entities = obj.get("entities")
+
+            if entities is None:
+                logger.warning("No entities found in submission result at index %s", idx - 1)
+                continue
+
+            logger.info(
+                "Processing submission result %s of %s, %s entities",
+                idx,
+                total,
+                len(entities),
+            )
+
+            for entity in entities:
+                unique_keys = entity.get("unique_keys", [{}])
+                if unique_keys and isinstance(unique_keys, list):
+                    keys = unique_keys[0]
+                    entity["project_id"] = keys.get("project_id")
+                    entity["submitter_id"] = keys.get("submitter_id")
+                    entity["transaction_id"] = transaction_id
+                    entity["file_path"] = obj.get("file_path", '')
+                flat_list_dict.append(entity)
+
+        # renaming cols
+        for entity in flat_list_dict:
+            entity["gen3_guid"] = entity.pop("id", None)
+            entity["node"] = entity.pop("type", None)
+
+        logger.info("Finished flattening. Total entities: %s", len(flat_list_dict))
+        return flat_list_dict
+
+    def _find_version_from_path(self, path: str) -> Optional[str]:
+        """
+        Extracts a semantic version string (e.g., '1.0.0' or 'v1.0.0') from a file path.
+
+        Args:
+            path (str): The file path to inspect.
+
+        Returns:
+            Optional[str]: The extracted version string if found, otherwise None.
+        """
+        version_pattern = re.compile(r"^v?(\d+\.\d+\.\d+)$")
+        found_versions = []
+
+        for segment in path.split('/'):
+            match = version_pattern.match(segment)
+            if match:
+                found_versions.append(match.group(1))
+
+        if not found_versions:
+            return None
+
+        if len(found_versions) > 1:
+            logger.warning("more than one match found in path for version string")
+
+        return found_versions[-1]
+
+    def _collect_versions_from_metadata_file_list(self) -> str:
+        """
+        Extract and validate version information from the internal list of metadata
+        file paths (self.metadata_file_list).
+
+        Returns:
+            str: The single version found in the file list.
+
+        Raises:
+            ValueError: If more than one version is found across the files,
+                        or if no version is found at all.
+        """
+        versions = []
+        for file_path in self.metadata_file_list:
+            version = self._find_version_from_path(file_path)
+            if version:
+                versions.append(version)
+        versions = list(set(versions))
+        if len(versions) > 1:
+            logger.error(
+                "more than one version found in metadata file list: %s",
+                self.metadata_file_list,
+            )
+            raise ValueError(
+                "More than one version found in metadata file list: %s"
+                % self.metadata_file_list
+            )
+        if not versions:
+            raise ValueError(
+                "No version found in metadata file list: %s" % self.metadata_file_list
+            )
+        return versions[0]
+
+    def _upload_submission_results(self, submission_results: list):
+        """
+        Uploads the submission results to S3 and a Parquet table.
+
+        This function performs the final step of the pipeline:
+        1.  Flattens the submission response structure.
+        2.  Prepares a DataFrame with metadata (upload_id, datetime, version).
+        3.  Writes the DataFrame to Parquet files in S3 and registers them in the
+            database configured via `self.database` and `self.table`.
+
+        **Retry Mechanism:**
+        Uses the `tenacity` library to retry the upload if it fails.
+        - Stop: After `self.max_retries` attempts.
+        - Wait: Exponential backoff starting at 1s, doubling up to 10s.
+
+        Args:
+            submission_results (list): List of submission results to upload.
+
+        Configuration used (from __init__):
+            dataset_root (str): e.g. "s3://acdc-dataops-metadata/metadata_upload/"
+            database (str): e.g. "acdc_dataops_metadata_db"
+            table (str): e.g. "metadata_upload"
+            partition_cols (list): e.g. ["upload_datetime"]
+        """
+        
+        @retry(
+            stop=stop_after_attempt(self.max_retries),
+            wait=wait_exponential(multiplier=1, max=10)
+        )
+        def inner_upload():
+            logger.debug("Collecting version from metadata file list.")
+            version = self._collect_versions_from_metadata_file_list()
+            logger.debug("Extracted version: %s", version)
+
+            logger.debug("Inferring API endpoint from JWT.")
+            api_endpoint = infer_api_endpoint_from_jwt(self.api_key['api_key'])
+            logger.debug("Using API endpoint: %s", api_endpoint)
+
+            upload_datetime = datetime.now().isoformat()
+            upload_id = str(uuid.uuid4())
+            logger.debug("Upload datetime: %s", upload_datetime)
+            logger.debug("Generated upload ID: %s", upload_id)
+
+            logger.debug("Flattening submission results for upload.")
+            flattened_results = self._flatten_submission_results(submission_results)
+            logger.debug(
+                "Flattened %s submission result entries.",
+                len(flattened_results),
+            )
+
+            logger.debug("Converting flattened results to DataFrame.")
+            flattened_results_df = pd.DataFrame(flattened_results)
+            flattened_results_df['upload_datetime'] = upload_datetime
+            flattened_results_df['upload_id'] = upload_id
+            flattened_results_df['api_endpoint'] = api_endpoint
+            flattened_results_df['version'] = version
+
+            logger.info(
+                "Writing DataFrame to parquet and S3/table: "
+                "dataset_root=%s, database=%s, table=%s, partition_cols=%s",
+                self.dataset_root,
+                self.database,
+                self.table,
+                self.partition_cols,
+            )
+            write_parquet_to_db(
+                df=flattened_results_df,
+                dataset_root=self.dataset_root,
+                database=self.database,
+                table=self.table,
+                partition_cols=self.partition_cols,
+            )
+            logger.info(
+                "\033[94m[SUCCESS]\033[0m Metadata submission results upload complete. "
+                "Uploaded to dataset_root=%s, database=%s, table=%s.",
+                self.dataset_root,
+                self.database,
+                self.table,
+            )
+
+        # Execute the decorated inner function
+        try:
+            inner_upload()
+        except Exception as e:
+            logger.critical("Failed to upload submission results after %s attempts.", self.max_retries)
+            raise e
+
+    def _submit_data_chunks(
+        self,
+        split_json_list: list,
+        node: str,
+        gen3_submitter,
+        file_path: str,
+        upload_to_database: bool = True
+    ) -> List[Dict]:
+        """
+        Submit each chunk of data (in split_json_list) for a given node to Gen3,
+        using retry logic and logging on failures.
+
+        Upon completion of each chunk (success or failure), the response is uploaded
+        to the configured S3 Parquet table using `_upload_submission_results`.
+
+        Args:
+            split_json_list (list): List of JSON-serializable chunked data to
+                submit.
+            node (str): Name of the data node being submitted (e.g., "program").
+            gen3_submitter: A Gen3Submission instance for making submissions.
+            file_path (str): Path of the file that was submitted.
+                Used only for data capture in the result logs.
+
+        Returns:
+            List[Dict]: List of response dictionaries for each submitted chunk.
+
+        Raises:
+            RuntimeError: If submission fails after all retry attempts for any chunk.
+        """
+        n_json_data = len(split_json_list)
+
+        for index, jsn in enumerate(split_json_list):
+            # Holds results for the current chunk
+            current_chunk_response: List[Dict[str, Any]] = []
+            progress_str = f"{index + 1}/{n_json_data}"
+
+            submission_success = False
+            last_exception: Optional[Exception] = None
+
+            attempt = 0
+            while attempt <= self.max_retries:
+                try:
+                    if attempt == 0:
+                        logger.info(
+                            "[SUBMIT]  | Project: %-10s | Node: %-12s | "
+                            "Split: %-5s",
+                            self.project_id,
+                            node,
+                            progress_str,
+                        )
+                    else:
+                        logger.warning(
+                            "[RETRY]   | Project: %-10s | Node: %-12s | "
+                            "Split: %-5s | "
+                            "Attempt: %s/%s",
+                            self.project_id,
+                            node,
+                            progress_str,
+                            attempt,
+                            self.max_retries,
+                        )
+
+                    res = gen3_submitter.submit_record(self.program_id, self.project_id, jsn)
+                    res.update({"file_path": file_path})
+                    current_chunk_response.append(res)
+                    submission_success = True
+                    logger.info(
+                        "\033[92m[SUCCESS]\033[0m | Project: %-10s | "
+                        "Node: %-12s | Split: %-5s",
+                        self.project_id,
+                        node,
+                        progress_str,
+                    )
+                    break  # Success
+
+                except (
+                    requests.exceptions.RequestException,
+                    ValueError,
+                    TypeError,
+                ) as e:
+                    last_exception = e
+                    logger.error(
+                        "Error submitting chunk %s for node '%s': %s",
+                        progress_str,
+                        node,
+                        e,
+                    )
+
+                    if attempt < self.max_retries:
+                        time.sleep(0.2)
+                    else:
+                        logger.critical(
+                            "\033[91m[FAILED]\033[0m  | Project: %-10s | "
+                            "Node: %-12s | Split: %-5s | Error: %s",
+                            self.project_id,
+                            node,
+                            progress_str,
+                            e,
+                        )
+                attempt += 1
+            
+            
+            if upload_to_database:
+                # Also submitting data chunk response info to s3 and parquet table
+                logger.info("Submitting data chunk response info to S3 and Parquet table.")
+                self._upload_submission_results(submission_results=current_chunk_response)
+
+            if not submission_success:
+                # After retries, still failed
+                raise RuntimeError(
+                    (
+                        "Failed to submit chunk %s for node '%s' after %s attempts. "
+                        "Last error: %s"
+                    )
+                    % (progress_str, node, self.max_retries + 1, last_exception)
+                ) from last_exception
+
+        logger.info("Finished submitting node '%s'.", node)
+
+
+    def _read_data_import_order(
+        self,
+        data_import_order_path: str,
+        exclude_nodes: List[str],
+        boto3_session=None,
+    ):
+        """Helper to read the data import order from local disk or S3."""
         if is_s3_uri(data_import_order_path):
             session = boto3_session or self.boto3_session
-            return read_data_import_order_txt_s3(data_import_order_path, session, exclude_nodes)  
+            return read_data_import_order_txt_s3(
+                data_import_order_path,
+                session,
+                exclude_nodes,
+            )
         else:
             return read_data_import_order_txt(data_import_order_path, exclude_nodes)
 
@@ -643,7 +971,7 @@ class MetadataSubmitter:
             list: A list of chunks, where each chunk is a list of dictionaries
                 containing JSON data.
         """
-        logger.info(f"Reading metadata json from {metadata_file_path}")
+        logger.info("Reading metadata json from %s", metadata_file_path)
         if is_s3_uri(metadata_file_path):
             session = self.boto3_session
             data = read_metadata_json_s3(metadata_file_path, session)
@@ -660,113 +988,62 @@ class MetadataSubmitter:
         are the corresponding file paths.
 
         Returns:
-            dict: Dictionary mapping node names (str) to their associated metadata file paths (str).
+            dict: Dictionary mapping node names (str) to their associated metadata file paths.
         """
         file_map = {
-            get_node_from_file_path(file): file
-            for file in self.metadata_file_list
+            get_node_from_file_path(file_path): file_path
+            for file_path in self.metadata_file_list
         }
         return file_map
 
-    def submit_metadata(self) -> List[Dict]:
+    def submit_metadata(self) -> List[Dict[str, Any]]:
         """
         Submits metadata for each node defined in the data import order, except those in the exclude list.
-
-        For each node, this method retrieves the corresponding metadata file, splits the JSON data
-        into size-constrained chunks, and submits each chunk to the Gen3 submission API. Responses
-        from all submissions are gathered and returned as a list.
+        
+        **Detailed Process:**
+        1.  **Order Resolution:** The function reads the import order to determine the sequence of nodes.
+        2.  **File Mapping:** It finds the matching `node.json` file for each node in the order.
+        3.  **Chunk & Submit:** For every file, the JSON content is split into chunks and submitted
+            to the Sheepdog API via `gen3.submission`.
+        4.  **Audit Logging:** The API response (containing `submission_id`) is flattened and
+            converted to a DataFrame. This is then written to Parquet files in S3 and registered
+            in the configured upload table.
 
         Returns:
-            List[Dict]: A list of response dictionaries returned from the Gen3 metadata submissions.
+            List[Dict[str, Any]]: A list of response dictionaries returned from the Gen3 metadata submissions.
+                Each dictionary contains the response from submitting a chunk of metadata for a given node.
+                The keys in the dictionary are "node_name", "response", and "status_code".
         """
         gen3_submitter = self._create_gen3_submission_class()
-        data_import_order = self._read_data_import_order(self.data_import_order_path, self.exclude_nodes, self.boto3_session)
+        data_import_order = self._read_data_import_order(
+            self.data_import_order_path,
+            self.exclude_nodes,
+            self.boto3_session,
+        )
         file_map = self._create_file_map()
-        output_response_list_dict = []
 
         logger.info("Starting metadata submission.")
-        for node in data_import_order:
 
+        for node in data_import_order:
             if node in self.exclude_nodes:
-                logger.info(f"Skipping node '{node}' (in exclude list).")
+                logger.info("Skipping node '%s' (in exclude list).", node)
                 continue
             file_path = file_map.get(node)
             if not file_path:
-                logger.info(f"Skipping node '{node}' (not present in file list).")
+                logger.info("Skipping node '%s' (not present in file list).", node)
                 continue
 
-            logger.info(f"Processing file '{file_path}' for node '{node}'.")
+            logger.info("Processing file '%s' for node '%s'.", file_path, node)
             logger.info("Splitting JSON data into chunks.")
             json_chunks = self._prepare_json_chunks(file_path, self.max_size_kb)
 
             logger.info("Submitting chunks to Gen3.")
-            response_list = submit_data_chunks(
+            self._submit_data_chunks(
                 split_json_list=json_chunks,
                 node=node,
-                file_path=file_path,
                 gen3_submitter=gen3_submitter,
-                project_id=self.project_id,
-                max_retries=self.max_retries,
-                program_id=self.program_id
+                file_path=file_path,
+                upload_to_database=self.upload_to_database
             )
-            output_response_list_dict.extend(response_list)
-
-        self.submission_results = output_response_list_dict
-        return output_response_list_dict
+            
 
-    def upload_metadata_submission_results(
-        self,
-        dataset_root: str,
-        database: str,
-        table: str,
-        partition_cols: list = ["upload_datetime"],
-    ):
-        """
-        Uploads the submission results to s3 and parquet table.
-
-        Args:
-            dataset_root (str): S3 path where the parquet files will be stored 
-                (e.g., "s3://acdc-dataops-metadata/metadata_upload/").
-            database (str): Database name for storing the metadata upload 
-                (e.g., "acdc_dataops_metadata_db").
-            table (str): Table name for storing the metadata upload 
-                (e.g., "metadata_upload").
-            partition_cols (list, optional): List of column names to partition the parquet table by. 
-                Defaults to ["upload_datetime"].
-        """
-        logger.info("Collecting version from metadata file list.")
-        version = collect_versions_from_metadata_file_list(self.metadata_file_list)
-        logger.info(f"Extracted version: {version}")
-
-        logger.info("Inferring API endpoint from JWT.")
-        api_endpoint = infer_api_endpoint_from_jwt(self.api_key['api_key'])
-        logger.info(f"Using API endpoint: {api_endpoint}")
-
-        upload_datetime = datetime.now().isoformat()
-        upload_id = str(uuid.uuid4())
-        logger.info(f"Upload datetime: {upload_datetime}")
-        logger.info(f"Generated upload ID: {upload_id}")
-
-        logger.info("Flattening submission results for upload.")
-        flattened_results = flatten_submission_results(self.submission_results)
-        logger.info(f"Flattened {len(flattened_results)} submission result entries.")
-
-        logger.info("Converting flattened results to DataFrame.")
-        flattened_results_df = pd.DataFrame(flattened_results)
-        flattened_results_df['upload_datetime'] = upload_datetime
-        flattened_results_df['upload_id'] = upload_id
-        flattened_results_df['api_endpoint'] = api_endpoint
-        flattened_results_df['version'] = version
-
-        logger.info(
-            f"Writing DataFrame to parquet and S3/table: "
-            f"dataset_root={dataset_root}, database={database}, table={table}, partition_cols={partition_cols}"
-        )
-        write_parquet_to_db(
-            df=flattened_results_df,
-            dataset_root=dataset_root,
-            database=database,
-            table=table,
-            partition_cols=partition_cols
-        )
-        logger.info("Metadata submission results upload complete.")

{acdc_aws_etl_pipeline-0.6.9.dist-info → acdc_aws_etl_pipeline-0.7.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: acdc_aws_etl_pipeline
-Version: 0.6.9
+Version: 0.7.1
 Summary: Tools for ACDC ETL pipeline
 Author: JoshuaHarris391
 Author-email: harjo391@gmail.com
@@ -23,6 +23,7 @@ Requires-Dist: python-dotenv
 Requires-Dist: pytz (>=2025.2,<2026.0)
 Requires-Dist: pyyaml (>=6.0.2,<7.0.0)
 Requires-Dist: s3fs (==2025.10.0)
+Requires-Dist: tenacity (>=8.2,<10.0)
 Requires-Dist: tzlocal (>=5.3.1,<6.0.0)
 Description-Content-Type: text/markdown
 

{acdc_aws_etl_pipeline-0.6.9.dist-info → acdc_aws_etl_pipeline-0.7.1.dist-info}/RECORD

@@ -3,12 +3,12 @@ acdc_aws_etl_pipeline/ingest/ingest.py,sha256=5Q63PZfUVB5L1WxwElAxG6N-4GvqBuTNp6
 acdc_aws_etl_pipeline/upload/__init__.py,sha256=kRI1wozjK-b9YXMAPwzWHzm967ZiUAM6g8rRo4ONWtI,67
 acdc_aws_etl_pipeline/upload/gen3datasubmitter.py,sha256=bu5d8IOsKFIA1uvvzaxb7YIKwBZKdP-0QvBt-gZMyUc,8625
 acdc_aws_etl_pipeline/upload/metadata_deleter.py,sha256=T4q9xqSE2Beu3zluvAmKh7wJWcCFGz2AZ9h9ZcASfyA,63
-acdc_aws_etl_pipeline/upload/metadata_submitter.py,sha256=k5q5hRkj-dWo25z9nVZI2eNh0xnmQU8TPDffSSnQlUY,29906
+acdc_aws_etl_pipeline/upload/metadata_submitter.py,sha256=2PVuv-mvjnO-FxVZHiYfTDlbioEo-JsTcvNZY6v2n40,38331
 acdc_aws_etl_pipeline/upload/upload_synthdata_s3.py,sha256=Ge5TQzZkWnJNp-q0Ak-Yhv1h1eWLxg-PlWVHrd1m0B8,5155
 acdc_aws_etl_pipeline/utils/athena_utils.py,sha256=QJlBe-07Hkq-BqmcxBu6ZtAmVfZSHuSY4dijcysgPH8,29560
 acdc_aws_etl_pipeline/utils/dbt_utils.py,sha256=5XRFOwNNIeuW2sQuor3h_OZTuXGg6xv2AUYwj9bMAAM,2054
 acdc_aws_etl_pipeline/utils/release_writer.py,sha256=vsxHJ6l-UWPpzeyEPHurX5iFgeCEQ-9FbySAbPNfTTM,7555
 acdc_aws_etl_pipeline/validate/validate.py,sha256=zLqK9i92FsRAaBOGdY-G7-vb0e6tmkoUXhY6zCfbjN8,24895
-acdc_aws_etl_pipeline-0.6.9.dist-info/METADATA,sha256=L02r4oi2Xhtoet7a4HCfV8nGDlmmc2gSVsCN8sMNjTc,2926
-acdc_aws_etl_pipeline-0.6.9.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
-acdc_aws_etl_pipeline-0.6.9.dist-info/RECORD,,
+acdc_aws_etl_pipeline-0.7.1.dist-info/METADATA,sha256=WddwCKf3KV4-JsKtsegk5dxu6dWKvXx8YANvZZKbRGs,2964
+acdc_aws_etl_pipeline-0.7.1.dist-info/WHEEL,sha256=zp0Cn7JsFoX2ATtOhtaFYIiE2rmFAD4OcMhtUki8W3U,88
+acdc_aws_etl_pipeline-0.7.1.dist-info/RECORD,,