doczyai-pipelines/textract-pipeline/src/lambda/database-interface/index.py

import json
import snowflake.connector
import boto3 
import snowflake.connector
import logging
import os


"""
# Sample input events

doc_input_event = {
  "operation": "insert",
  "table": "DOCUMENT_LOGS",
  "data": {
    "DOCUMENT_ID" : "abc_xyz"
    "BATCH_ID": "Batch_101",
    "JOB_ID": "J123456",
    "STAGE": "Processing",
    "TEXTRACT_STATUS": "Success",
    "BUCKET_NAME": "doc-bucket",
    "FILE_NAME": "file1.pdf",
    "FILE_PATH": "/documents/2023/",
    "DOCUMENT_TYPE": "Report",
    "PAYER_SIGNED": "True",
    "PROVIDER_SIGNED": "False",
    "GROUP_ID": "G100",
    "CREATED_TIME": "2024-03-21 10:00:00",
    "MODIFIED_TIME": "2024-03-21 10:00:00",
    "CREATED_BY": "admin",
    "MODIFIED_BY": "admin",
    "ORIGINAL_FILE_EXTENSION": "pdf",
    "NO_OF_PAGES": 10,
    "FILE_SIZE": 1048576
  }
}



doc_update_event =     {
  "operation": "update",
  "table": "DOCUMENT_LOGS",
  "data": {
    "DOCUMENT_ID": "abc_xyz",
    "TEXTRACT_STATUS": "Failed",
    "MODIFIED_TIME": "2024-03-22 15:00:00",
    "MODIFIED_BY": "admin"
  }
}



batch_insert_event = {
  "operation": "insert",
  "table": "BATCH_LOGS",
  "data": {
    "CLIENT_ID": "C200",
    "EXECUTION_START_TIME": "2024-03-21 09:00:00",
    "NO_OF_DOCUMENTS": 150,
    "USER_NAME": "batch_processor"
  }
}

batch_update_event = {
  "operation": "update",
  "table": "BATCH_LOGS",
  "data": {
    "BATCH_ID": "batch_102",
    "NO_OF_DOCUMENTS": 155,
    "USER_NAME": "updated_processor"
  }
}

client_insert_event = {
  "operation": "insert",
  "table": "CLIENT_LOGS",
  "data": {
    "CLIENT_ID": "CL300",
    "CLIENT_NAME": "Acme Corporation",
    "BUCKET_NAME": "acme-docs"
  }
}

client_update_event = {
  "operation": "update",
  "table": "CLIENT_LOGS",
  "data": {
    "CLIENT_ID": "CL300",
    "BUCKET_NAME": "new-acme-docs"
  }
}
Operation can be: 'insert' or 'update'
Data is a dictionary with the columns and values to be inserted or updated

"""


logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s', force=True)
logging.getLogger('snowflake.connector').setLevel(logging.WARNING)
logging.getLogger("botocore").setLevel(logging.WARNING)
logger = logging.getLogger(__name__)
logger.setLevel(logging.INFO)


def get_secret(secrets_name: str):
    """Get credentials from Secret Manager as dict"""
    secrets_manager = boto3.client('secretsmanager')
    get_secret_value_response = secrets_manager.get_secret_value(SecretId=secrets_name)

    if 'SecretString' in get_secret_value_response:
        secret_json = get_secret_value_response['SecretString']
    else:
        secret_json = base64.b64decode(get_secret_value_response['SecretBinary'])

    return json.loads(secret_json)


def get_snowflake_db_connection(secrets_name: str):
    """Create connection to Snowflake db."""
    try:
        con_params = get_secret(secrets_name)
        account = con_params['account_locator']
        user = con_params['user']
        password = con_params['password']
        database = con_params['database'].upper()
        warehouse = con_params['warehouse']
        role= con_params['role']
        logger.info(f'Using credentials: account={account}, user={user}, password=***, database={database}, '
                    f'warehouse={warehouse}')
        snowflake_connection = snowflake.connector.connect(account=account, user=user, password=password, database=database,
                                                           warehouse=warehouse, autocommit=True, schema='STG')
        logger.info(snowflake_connection)
        cursor = snowflake_connection.cursor()
        cursor.execute("SELECT * FROM STG.DIM_AUDIT LIMIT 10;")
        logger.info(f"RESULT:: {cursor.fetchone()[0]}")
        return snowflake_connection
    except Exception as e:
        return e
    

# Leaving this statement outside the lambda_handler function to reuse the connection
    # Secret has been setup to use the logging service account
SECRET_MANAGER_NAME = os.environ.get('SECRET_MANAGER_NAME', '')
conn = get_snowflake_db_connection(SECRET_MANAGER_NAME)
# cur = conn.cursor()
# logger.info(f"CURSOR OBJECT: {cur}")

def construct_doc_insert_sql(data):
    """
    Constructs the SQL for an insert operation

    Sample return value:
    INSERT INTO STG.DOCUMENT_LOGS (DOCUMENT_ID,BATCH_ID, JOB_ID, STAGE, TEXTRACT_STATUS, BUCKET_NAME, FILE_NAME, FILE_PATH, DOCUMENT_TYPE, PAYER_SIGNED, PROVIDER_SIGNED, GROUP_ID, CREATED_TIME, MODIFIED_TIME, CREATED_BY, MODIFIED_BY, ORIGINAL_FILE_EXTENSION, NO_OF_PAGES, FILE_SIZE) 
        VALUES ('doc_1212','batch_101', 'J123456', 'Processing', 'Success', 'doc-bucket', 'file1.pdf', '/documents/2023/', 'Report', True, False, 'G100', '2024-03-21 10:00:00', '2024-03-21 10:00:00', 'admin', 'admin', 'pdf', 10, 1048576);
    """
    columns = ', '.join(data.keys())
    values = ', '.join(["'" + str(value).replace("'", "''") + "'" if isinstance(value, str) else str(value) for value in data.values()])
    sql = f"INSERT INTO STG.DOCUMENT_LOGS ({columns}) VALUES ({values});"
    return sql


def construct_doc_update_sql(data, document_id):
    """
    Constructs the SQL for an update operation

    Sample return value: 
    UPDATE STG.DOCUMENT_LOGS SET TEXTRACT_STATUS = 'Failed', MODIFIED_TIME = '2024-03-22 15:00:00', MODIFIED_BY = 'admin' WHERE DOCUMENT_ID = 1001;
    """
    set_clauses = ', '.join([f"{key} = '" + str(value).replace("'", "''") + "'" if isinstance(value, str) else f"{key} = {value}" for key, value in data.items()])
    sql = f"UPDATE STG.DOCUMENT_LOGS SET {set_clauses} WHERE DOCUMENT_ID = '{document_id}';"
    logger.info(f"Executing the following logging SQL statement: {sql}")
    return sql


def construct_batch_insert_sql(data):
    """
    Constructs the SQL for an insert operation

    Sample return value:
    INSERT INTO STG.BATCH_LOGS (BATCH_ID,CLIENT_ID, EXECUTION_START_TIME, NO_OF_DOCUMENTS, USER_NAME) VALUES ('C200', '2024-03-21 09:00:00', 150, 'batch_processor');
    """
    columns = ', '.join(data.keys())
    values = ', '.join(["'" + str(value).replace("'", "''") + "'" if isinstance(value, str) else str(value) for value in data.values()])
    sql = f"INSERT INTO STG.BATCH_LOGS ({columns}) VALUES ({values});"
    return sql

def construct_client_insert_sql(data):
    """
    Constructs the SQL for an insert operation

    Sample return value:
    INSERT INTO STG.CLIENT_LOGS (CLIENT_ID, CLIENT_NAME, BUCKET_NAME) VALUES ('CL300', 'Acme Corporation', 'acme-docs');
    """
    columns = ', '.join(data.keys())
    values = ', '.join(["'" + str(value).replace("'", "''") + "'" if isinstance(value, str) else str(value) for value in data.values()])
    sql = f"INSERT INTO STG.CLIENT_LOGS ({columns}) VALUES ({values});"
    return sql


def construct_client_update_sql(data, client_id):
    """
    Constructs the SQL for an update operation

    Sample return value:
    UPDATE STG.CLIENT_LOGS SET BUCKET_NAME = 'new-acme-docs' WHERE CLIENT_ID = 'CL300';
    """
    set_clauses = ', '.join([f"{key} = '" + str(value).replace("'", "''") + "'" if isinstance(value, str) else f"{key} = {value}" for key, value in data.items()])
    sql = f"UPDATE STG.CLIENT_LOGS SET {set_clauses} WHERE CLIENT_ID = '{client_id}';"
    return sql

def construct_batch_update_sql(data, batch_id):
    """
    Constructs the SQL for an update operation

    Sample return value:
    UPDATE STG.BATCH_LOGS SET NO_OF_DOCUMENTS = 155, USER_NAME = 'updated_processor' WHERE BATCH_ID = 1;
    """
    set_clauses = ', '.join([f"{key} = '" + str(value).replace("'", "''") + "'" if isinstance(value, str) else f"{key} = {value}" for key, value in data.items()])
    sql = f"UPDATE STG.BATCH_LOGS SET {set_clauses} WHERE BATCH_ID = '{batch_id}';"
    return sql


# Main Lambda handler
def lambda_handler(event, context):
    # Extract operation type and payload from event
    # res = cur.execute("SELECT CURRENT_DATABASE();").fetchone()
    # logger.info(f"current database: {res}")
    operation = event['operation']  # 'insert' or 'update'
    data = event['data']
    table = event['table']
    
    with conn.cursor() as cur:
        try:
            if table == 'DOCUMENT_LOGS':
                if operation == 'insert':
                    sql = construct_doc_insert_sql(data)
                elif operation == 'update':
                    document_id = data.pop('DOCUMENT_ID', None)
                    sql = construct_doc_update_sql(data, document_id)
    
            elif table == 'BATCH_LOGS':
                if operation == 'insert':
                    sql = construct_batch_insert_sql(data)
                elif operation == 'update':
                    batch_id = data.pop('BATCH_ID', None)
                    sql = construct_batch_update_sql(data, batch_id)
    
            elif table == 'CLIENT_LOGS':
                if operation == 'insert':
                    sql = construct_client_insert_sql(data)
                elif operation == 'update':
                    client_id = data.pop('CLIENT_ID', None)
                    sql = construct_client_update_sql(data, client_id)
            else:
                raise ValueError("Unsupported table.")
            
            response = cur.execute(sql)
            logger.info(f"Executing the following logging SQL statement: {sql}")
            return {'statusCode': 200, 'body': json.dumps('Operation successful')}
    
        except Exception as e:
            return {'statusCode': 400, 'body': json.dumps(str(e))}
        finally:
            # conn.close()
            # Need to close the connection to avoid reaching the limit of open connections
            # However, we need the conn to be in hot state for subsequent concurrent executions
            # Need to decide the best approach to handle this
            pass