fix: correct path parsing in test_set_file_copier for nested directory structures

- Fix path_parts[2] bug in _copy_baseline_from_testset function
- Fix same bug in handler baseline validation logic
- Use '/'.join(path_parts[2:]) to preserve full nested paths
- Add unit test for baseline path extraction logic
- Resolves performance issues with testset baseline copying

Author: Taniya Mathur

lib/idp_common_pkg/tests/unit/test_test_set_file_copier.py

@@ -25,6 +25,35 @@ def test_path_extraction_logic():
     assert dest_key == expected
 
 
+@pytest.mark.unit
+def test_baseline_path_extraction_logic():
+    """Test the path extraction logic for baseline files from testset bucket"""
+    # Simulate the path extraction logic from _copy_baseline_from_testset
+    file_key = "fcc_benchmark/input/fcc_benchmark/033f718b16cb597c065930410752c294.pdf"
+    test_set_id = "demo_test_set"
+
+    # Extract test set name and file name from path (format: test_set_name/input/file_name)
+    path_parts = file_key.split("/")
+    if len(path_parts) >= 3 and path_parts[1] == "input":
+        source_test_set_name = path_parts[0]
+        file_name = "/".join(path_parts[2:])  # Get full path after 'input/'
+
+        # Source baseline path in testset bucket
+        source_baseline_prefix = f"{source_test_set_name}/baseline/{file_name}/"
+        # Destination baseline path
+        dest_baseline_prefix = f"{test_set_id}/baseline/{file_name}/"
+
+    expected_source = (
+        "fcc_benchmark/baseline/fcc_benchmark/033f718b16cb597c065930410752c294.pdf/"
+    )
+    expected_dest = (
+        "demo_test_set/baseline/fcc_benchmark/033f718b16cb597c065930410752c294.pdf/"
+    )
+
+    assert source_baseline_prefix == expected_source
+    assert dest_baseline_prefix == expected_dest
+
+
 @pytest.mark.unit
 def test_path_extraction_edge_cases():
     """Test edge cases for path extraction"""

src/lambda/test_set_file_copier/index.py

@@ -60,7 +60,7 @@ def handler(event, context):
                         path_parts = file_key.split('/')
                         if len(path_parts) >= 3 and path_parts[1] == 'input':
                             test_set_name = path_parts[0]
-                            file_name = path_parts[2]
+                            file_name = '/'.join(path_parts[2:])  # Get full path after 'input/'
                             baseline_prefix = f"{test_set_name}/baseline/{file_name}/"
                             baseline_check_bucket = source_bucket
                         else:
@@ -185,7 +185,7 @@ def _copy_baseline_from_testset(test_set_id, files):
         path_parts = file_key.split('/')
         if len(path_parts) >= 3 and path_parts[1] == 'input':
             source_test_set_name = path_parts[0]
-            file_name = path_parts[2]
+            file_name = '/'.join(path_parts[2:])  # Get full path after 'input/'
 
             # Source baseline path in testset bucket
             source_baseline_prefix = f"{source_test_set_name}/baseline/{file_name}/"