267 lines
7.9 KiB
Python
267 lines
7.9 KiB
Python
|
import json
|
||
|
|
import snowflake.connector
|
||
|
|
|
||
|
|
|
||
|
|
"""
|
||
|
|
Sample input event for Insert operation:
|
||
|
|
{
|
||
|
|
"operation": "insert",
|
||
|
|
"data": {
|
||
|
|
"BATCH_ID": 12345,
|
||
|
|
"JOB_ID": "job_67890",
|
||
|
|
"STAGE": "Preprocessing",
|
||
|
|
"TEXTRACT_STATUS": "Pending",
|
||
|
|
"BUCKET_NAME": "my-bucket",
|
||
|
|
"FILE_NAME": "document.pdf",
|
||
|
|
"FILE_PATH": "/path/to/document.pdf",
|
||
|
|
"DOCUMENT_TYPE": "Type A",
|
||
|
|
"PAYER_SIGNED": False,
|
||
|
|
"PROVIDER_SIGNED": True,
|
||
|
|
"GROUP_ID": "group_123",
|
||
|
|
"CREATED_TIME": "2023-01-01 12:00:00",
|
||
|
|
"MODIFIED_TIME": "2023-01-01 12:00:00",
|
||
|
|
"CREATED_BY": "user_1",
|
||
|
|
"MODIFIED_BY": "user_1",
|
||
|
|
"ORIGINAL_FILE_EXTENSION": "pdf",
|
||
|
|
"NO_OF_PAGES": 10,
|
||
|
|
"FILE_SIZE": 204800
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
Sample input event for Update operation:
|
||
|
|
{
|
||
|
|
"operation": "update",
|
||
|
|
"data": {
|
||
|
|
"DOCUMENT_ID": 1001,
|
||
|
|
"TEXTRACT_STATUS": "Completed",
|
||
|
|
"MODIFIED_TIME": "2023-01-02 13:00:00",
|
||
|
|
"MODIFIED_BY": "user_2",
|
||
|
|
"NO_OF_PAGES": 12,
|
||
|
|
"FILE_SIZE": 304800
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
Operation can be: 'insert' or 'update'
|
||
|
|
Data is a dictionary with the columns and values to be inserted or updated
|
||
|
|
|
||
|
|
"""
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
def construct_doc_insert_sql(data):
|
||
|
|
"""
|
||
|
|
Constructs the SQL for an insert operation
|
||
|
|
|
||
|
|
Sample return value:
|
||
|
|
INSERT INTO STG.DOCUMENT_LOGS (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 (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};"
|
||
|
|
return sql
|
||
|
|
|
||
|
|
|
||
|
|
def construct_batch_insert_sql(data):
|
||
|
|
"""
|
||
|
|
Constructs the SQL for an insert operation
|
||
|
|
|
||
|
|
Sample return value:
|
||
|
|
INSERT INTO STG.BATCH_LOGS (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
|
||
|
|
|
||
|
|
|
||
|
|
operation = event['operation'] # 'insert' or 'update'
|
||
|
|
data = event['data']
|
||
|
|
table = event['table']
|
||
|
|
|
||
|
|
# Get conn from Secrets Manager
|
||
|
|
|
||
|
|
try:
|
||
|
|
# with conn.cursor() as cursor:
|
||
|
|
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.")
|
||
|
|
print(sql)
|
||
|
|
# cursor.execute(sql)
|
||
|
|
return {'statusCode': 200, 'body': json.dumps('Operation successful')}
|
||
|
|
|
||
|
|
except Exception as e:
|
||
|
|
return {'statusCode': 400, 'body': json.dumps(str(e))}
|
||
|
|
finally:
|
||
|
|
# conn.close()
|
||
|
|
pass
|
||
|
|
|
||
|
|
|
||
|
|
# Sample input events
|
||
|
|
doc_input_event = {
|
||
|
|
"operation": "insert",
|
||
|
|
"table": "DOCUMENT_LOGS",
|
||
|
|
"data": {
|
||
|
|
"BATCH_ID": 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": 1001,
|
||
|
|
"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": 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"
|
||
|
|
}
|
||
|
|
}
|
||
|
|
|
||
|
|
|
||
|
|
lambda_handler(doc_input_event, None)
|
||
|
|
|
||
|
|
lambda_handler(doc_update_event, None)
|
||
|
|
|
||
|
|
lambda_handler(batch_insert_event, None)
|
||
|
|
|
||
|
|
lambda_handler(batch_update_event, None)
|
||
|
|
|
||
|
|
lambda_handler(client_insert_event, None)
|
||
|
|
|
||
|
|
lambda_handler(client_update_event, None)
|
||
|
|
|