task2 completed

.github/workflows/main.yml

@@ -2,9 +2,9 @@ name: AWS DevOps CI/CD Pipeline
 
 on:
   push:
-    branches: [main, master]
+    branches: main
   pull_request:
-    branches: [main, master]
+    branches: main
   workflow_dispatch:
 
 jobs:

README.md

@@ -42,7 +42,7 @@ Detailed documentation for AWS resources setup is available in [docs/task1_aws.m
    - S3 event-triggered function
    - CloudWatch logging integration
    - Screenshot:
-     ![Lambda Function Configuration](screenshots/lambda-function.png)
+     ![Lambda Function Configuration](screenshots/lambda-function.png) 
 
 ## Task 2: Scripting
 
@@ -53,12 +53,16 @@ Python scripts that utilize AWS SDK (boto3) to:
    - Lists all S3 buckets in your AWS account
    - Displays object count in a specified bucket
    - Usage: `python scripts/list_s3_buckets.py --bucket <bucket-name>`
+   - Screenshot:
+     ![Lambda Function Configuration](screenshots/S3Bucket.png) 
 
 2. **csv_analyzer.py**
 
    - Analyzes a CSV file (name, age, grade)
    - Prints students with grades above a threshold
    - Usage: `python scripts/csv_analyzer.py scripts/sample_students.csv --threshold 80`
+   - Screenshot:
+     ![Lambda Function Configuration](screenshots/Csv.png) 
 
 3. **SDK Documentation References**
    - See [docs/sdk_documentation.md](docs/sdk_documentation.md) for links to the AWS SDK documentation

lambda/s3_event_logger.py

@@ -5,19 +5,19 @@
 logger = logging.getLogger()
 logger.setLevel(logging.INFO)
 
-def lambda_handler(event, context):
+def lambda_handler(event, _):
     # Log the full event
-    logger.info('Received S3 event: ' + json.dumps(event))
+    logger.info('Received S3 event: %s', json.dumps(event))
 
     # Extract and log key details
     for record in event.get('Records', []):
         bucket = record.get('s3', {}).get('bucket', {}).get('name', 'unknown')
         key = record.get('s3', {}).get('object', {}).get('key', 'unknown')
         event_name = record.get('eventName', 'unknown')
 
-        logger.info(f'Event: {event_name}, Bucket: {bucket}, Key: {key}')
+        logger.info('Event: %s, Bucket: %s, Key: %s', event_name, bucket, key)
 
     return {
         'statusCode': 200,
         'body': json.dumps('Event processed successfully!')
-    } 
+    }   

lambda/test_s3_event_logger.py

@@ -5,8 +5,7 @@
 
 import json
 import unittest
-import logging
-from unittest.mock import patch, MagicMock
+from unittest.mock import patch
 from s3_event_logger import lambda_handler
 
 class TestS3EventLogger(unittest.TestCase):
@@ -64,8 +63,13 @@ def test_lambda_handler_logs_event(self, mock_logger):
         result = lambda_handler(self.event, self.context)
 
         # Check that logger.info was called with the expected arguments
-        mock_logger.info.assert_any_call('Received S3 event: ' + json.dumps(self.event))
-        mock_logger.info.assert_any_call('Event: ObjectCreated:Put, Bucket: test-bucket, Key: test-object.txt')
+        mock_logger.info.assert_any_call('Received S3 event: %s', json.dumps(self.event))
+        mock_logger.info.assert_any_call(
+            'Event: %s, Bucket: %s, Key: %s',
+            'ObjectCreated:Put',
+            'test-bucket',
+            'test-object.txt'
+        )
 
         # Verify the return structure
         self.assertEqual(result['statusCode'], 200)
@@ -80,7 +84,7 @@ def test_lambda_handler_handles_empty_event(self, mock_logger):
         result = lambda_handler(empty_event, self.context)
 
         # Check logger.info was called with the event but not with details
-        mock_logger.info.assert_called_with('Received S3 event: ' + json.dumps(empty_event))
+        mock_logger.info.assert_called_with('Received S3 event: %s', json.dumps(empty_event))
 
         # Verify the function completed successfully
         self.assertEqual(result['statusCode'], 200)
@@ -105,10 +109,10 @@ def test_lambda_handler_handles_missing_fields(self, mock_logger):
         result = lambda_handler(event_missing_fields, self.context)
 
         # Check that logger.info was called with "unknown" for missing fields
-        mock_logger.info.assert_any_call('Event: ObjectCreated:Put, Bucket: unknown, Key: unknown')
+        mock_logger.info.assert_any_call('Event: %s, Bucket: %s, Key: %s', 'ObjectCreated:Put', 'unknown', 'unknown')
 
         # Verify the function completed successfully
         self.assertEqual(result['statusCode'], 200)
 
 if __name__ == '__main__':
-    unittest.main() 
+    unittest.main()  

scripts/csv_analyzer.py

@@ -25,7 +25,7 @@ def analyze_csv(file_path, threshold):
 
         # Read the CSV file
         students = []
-        with open(file_path, 'r', newline='') as csvfile:
+        with open(file_path, 'r', newline='', encoding='utf-8') as csvfile:
             reader = csv.reader(csvfile)
             # Skip header if it exists (we'll check first row)
             header = next(reader, None)
@@ -48,14 +48,14 @@ def analyze_csv(file_path, threshold):
         above_threshold = [student for student in students if student['grade'] > threshold]
 
         # Print results
-        print(f"\nCSV Analysis Results:")
-        print(f"=====================")
+        print("\nCSV Analysis Results:")
+        print("=====================")
         print(f"File: {file_path}")
         print(f"Total students: {len(students)}")
         print(f"Average grade: {avg_grade:.2f}")
         print(f"Threshold: {threshold}")
         print(f"\nStudents with grade above {threshold}:")
-        print(f"--------------------------------------")
+        print("--------------------------------------")
 
         if above_threshold:
             # Sort by grade in descending order
@@ -65,8 +65,20 @@ def analyze_csv(file_path, threshold):
         else:
             print("No students found with grade above the threshold.")
 
-    except Exception as e:
-        print(f"Error analyzing CSV: {e}")
+    except FileNotFoundError as e:
+        print(f"File not found error: {e}")
+        sys.exit(1)
+    except csv.Error as e:
+        print(f"CSV parsing error: {e}")
+        sys.exit(1)
+    except ValueError as e:
+        print(f"Value error: {e}")
+        sys.exit(1)
+    except IOError as e:
+        print(f"I/O error: {e}")
+        sys.exit(1)
+    except Exception as e:  # pylint: disable=W0718
+        print(f"Unexpected error analyzing CSV: {e}")
         sys.exit(1)
 
 def process_row(row):
@@ -113,4 +125,4 @@ def main():
     analyze_csv(args.file, args.threshold)
 
 if __name__ == "__main__":
-    main() 
+    main()   

scripts/list_s3_buckets.py

@@ -1,98 +0,0 @@
-#!/usr/bin/env python3
-"""
-Script to interact with AWS S3 using boto3:
-- Lists all S3 buckets in your AWS account
-- Displays the total number of objects in a specified S3 bucket
-"""
-
-import boto3
-import sys
-import argparse
-
-def list_all_buckets():
-    """List all S3 buckets in the AWS account"""
-    try:
-        # Create an S3 client
-        s3 = boto3.client('s3')
-
-        # Get all buckets
-        response = s3.list_buckets()
-
-        # Print bucket info
-        print("S3 Buckets in your AWS account:")
-        print("-" * 40)
-        if not response['Buckets']:
-            print("No buckets found.")
-            return
-
-        for i, bucket in enumerate(response['Buckets'], 1):
-            print(f"{i}. {bucket['Name']} (Created: {bucket['CreationDate']})")
-
-        print(f"\nTotal buckets: {len(response['Buckets'])}")
-
-    except Exception as e:
-        print(f"Error listing buckets: {e}")
-        sys.exit(1)
-
-def count_objects_in_bucket(bucket_name):
-    """Count objects in a specified S3 bucket"""
-    try:
-        # Create an S3 client
-        s3 = boto3.client('s3')
-
-        # Check if bucket exists
-        try:
-            s3.head_bucket(Bucket=bucket_name)
-        except Exception as e:
-            print(f"Error: Bucket '{bucket_name}' does not exist or you don't have access to it.")
-            return
-
-        # List all objects in the bucket
-        paginator = s3.get_paginator('list_objects_v2')
-        total_objects = 0
-        total_size = 0
-
-        print(f"\nObjects in bucket '{bucket_name}':")
-        print("-" * 40)
-
-        for page in paginator.paginate(Bucket=bucket_name):
-            if 'Contents' in page:
-                total_objects += len(page['Contents'])
-                # Sum up the size of all objects
-                for obj in page['Contents']:
-                    total_size += obj['Size']
-
-        # Convert size to a readable format
-        size_str = format_size(total_size)
-
-        print(f"Total objects: {total_objects}")
-        print(f"Total size: {size_str}")
-
-    except Exception as e:
-        print(f"Error counting objects: {e}")
-        sys.exit(1)
-
-def format_size(size_bytes):
-    """Format bytes to a human-readable size"""
-    for unit in ['B', 'KB', 'MB', 'GB', 'TB']:
-        if size_bytes < 1024.0:
-            return f"{size_bytes:.2f} {unit}"
-        size_bytes /= 1024.0
-    return f"{size_bytes:.2f} PB"
-
-def main():
-    # Set up argument parser
-    parser = argparse.ArgumentParser(description='AWS S3 Bucket and Object Management')
-    parser.add_argument('--bucket', '-b', type=str, help='Specify a bucket name to count objects')
-
-    args = parser.parse_args()
-
-    # List all buckets
-    list_all_buckets()
-
-    # If a bucket name is provided, count objects in that bucket
-    if args.bucket:
-        count_objects_in_bucket(args.bucket)
-
-if __name__ == "__main__":
-    main() 

scripts/test_csv_analyzer.py

@@ -5,20 +5,18 @@
 
 import os
 import sys
-import tempfile
-from pathlib import Path
 
 # Add the parent directory to sys.path so we can import the module
-sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
-from scripts.csv_analyzer import process_row, is_numeric
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from csv_analyzer import process_row, is_numeric  # pylint: disable=C0413
 
 def test_is_numeric():
     """Test the is_numeric function"""
-    assert is_numeric("123") == True
-    assert is_numeric("123.45") == True
-    assert is_numeric("-123.45") == True
-    assert is_numeric("abc") == False
-    assert is_numeric("") == False
+    assert is_numeric("123") is True
+    assert is_numeric("123.45") is True
+    assert is_numeric("-123.45") is True
+    assert is_numeric("abc") is False
+    assert is_numeric("") is False
 
 def test_process_row():
     """Test the process_row function"""
@@ -50,4 +48,4 @@ def test_process_row_with_invalid_data():
     result = process_row(row)
     assert result["name"] == "Bob Smith"
     assert result["age"] == 20
-    assert result["grade"] == 0.0  # Should default to 0.0 
+    assert result["grade"] == 0.0  # Should default to 0.0