From 8325bb53cf188274a8a2a3c92714601b8b50b288 Mon Sep 17 00:00:00 2001
From: Jun-te Kim <junte.kim@mealcraft.com>
Date: Mon, 9 Feb 2026 23:25:52 +0000
Subject: [PATCH] added more logs

---
 backend/postcode_splitter/main.py | 32 ++++++++++++++++++++++++++++---
 1 file changed, 29 insertions(+), 3 deletions(-)

diff --git a/backend/postcode_splitter/main.py b/backend/postcode_splitter/main.py
index e3a8c438..282e432a 100644
--- a/backend/postcode_splitter/main.py
+++ b/backend/postcode_splitter/main.py
@@ -176,8 +176,13 @@ def main():
 
 
 def handler(event, context):
+    print("=" * 60)
+    print("HANDLER INVOKED")
+    print("=" * 60)
     print(f"Function: {context.function_name}")
     print(f"Request ID: {context.aws_request_id}")
+    print(f"Event received: {type(event)}")
+    print(f"Event keys: {event.keys() if isinstance(event, dict) else 'N/A'}")
 
     # Example SQS message for testing (copy and paste into SQS):
     # {
@@ -186,24 +191,33 @@ def handler(event, context):
     # }
 
     # Handle both single event and batch events (SQS, etc.)
+    print("Extracting records from event...")
     records = event.get("Records", [event])
+    print(f"Found {len(records)} record(s) to process")
     results = []
     errors = []
+
+    print("Initializing SubTaskInterface...")
     subtask_interface = SubTaskInterface()
+    print("✓ SubTaskInterface initialized")
 
     for record in records:
+        print("Processing record...")
         task_id = None
         subtask_id = None
         try:
             # Parse body
+            print("Parsing body from record...")
             if isinstance(record.get("body"), str):
                 body = json.loads(record["body"])
             else:
                 body = record.get("body", {})
+            print(f"Body parsed: {body}")
 
             # Validate required fields
             task_id = body.get("task_id")
             s3_uri = body.get("s3_uri")
+            print(f"task_id: {task_id}, s3_uri: {s3_uri}")
 
             if not task_id:
                 errors.append({"error": "Missing required field: task_id"})
@@ -214,13 +228,16 @@ def handler(event, context):
                 continue
 
             # Convert task_id to UUID
+            print("Converting task_id to UUID...")
             try:
                 task_id = UUID(task_id) if isinstance(task_id, str) else task_id
+                print(f"UUID conversion successful: {task_id}")
             except ValueError as e:
                 errors.append({"error": f"Invalid UUID format for task_id: {str(e)}"})
                 continue
 
             # Create a new subtask for this postcode splitter invocation
+            print(f"Creating subtask for task {task_id}...")
             subtask_id = subtask_interface.create_subtask(
                 task_id=task_id, inputs={"s3_uri": s3_uri}
             )
@@ -231,19 +248,26 @@ def handler(event, context):
             print(f"Processing s3_uri: {s3_uri}")
 
             # Read CSV from S3
-            print("Reading CSV from S3...")
+            print("Parsing S3 URI...")
             bucket, key = parse_s3_console_url(s3_uri)
-            print(f"Parsed S3 - Bucket: {bucket}, Key: {key}")
+            print(f"Bucket: {bucket}, Key: {key}")
+
+            print("Fetching CSV from S3...")
             csv_data = read_csv_from_s3_dict(bucket, key)
+            print(f"CSV fetched: {len(csv_data)} rows")
+
+            print("Creating DataFrame...")
             df = pd.DataFrame(csv_data)
-            print(f"CSV loaded: {len(df)} rows, {len(df.columns)} columns")
+            print(f"DataFrame created: {len(df)} rows, {len(df.columns)} columns")
 
             # Get head for demo
+            print("Getting DataFrame head...")
             df_head = df.head()
             print("DataFrame head:")
             print(df_head)
             df_head_dict = df_head.to_dict("records")
 
+            print("Appending result...")
             results.append(
                 {
                     "message": "Postcode splitter processing started",
@@ -252,8 +276,10 @@ def handler(event, context):
                     "subtask_id": str(subtask_id),
                 }
             )
+            print("Result appended")
 
             # Mark subtask as complete after successful processing
+            print("Updating subtask status to complete...")
             subtask_interface.update_subtask_status(
                 subtask_id,
                 "complete",