Merge branch 'main' into feature/multi-format-support

Author: Abhi2006-cloud

.gitignore

@@ -1 +1,9 @@
-node_modules
+node_modules
+# Ignore virtual environments
+myenv/
+venv/
+.env
+.venv
+ENV/
+env.bak/
+venv.bak/

app/__init__.py

@@ -0,0 +1 @@
+# i just created this file so python know this directory is package and can import from it (needed to import extract function in root/tests/test_extract.py)

app/__pycache__/__init__.cpython-310.pyc

@@ -0,0 +1 @@
+# i just created this file so python know this directory is package and can import from it (needed to import extract function in root/tests/test_extract.py)

app/etl/__init__.py

@@ -28,6 +28,8 @@ def extract(path: str = "xyz.csv") -> pd.DataFrame:
     supported_formats = ['.csv', '.xlsx', '.xls', '.json']
     if file_ext not in supported_formats:
         raise ValueError(f"❌ Unsupported file format: {file_ext}. Supported formats: {supported_formats}")
+    if not str(path).lower().endswith('.csv'):
+        raise ValueError(f"❌ File must be a CSV: {path}")
 
     try:
         df = None
@@ -64,12 +66,18 @@ def extract(path: str = "xyz.csv") -> pd.DataFrame:
             try:
                 df = pd.read_json(path)
                 print(f"Successfully read JSON file: {path}")
+                # TODO (Find & Fix)
+                pass 
+            except UnicodeDecodeError:
+                print(f"Failed to read with encoding '{encoding}'")  # Log the encoding that failed
+                continue
             except Exception as e:
                 raise ValueError(f"❌ Error reading JSON file: {e}")
 
         # Validate data
         if df is None:
             raise ValueError("❌ Failed to read data from file")
+            raise ValueError(f"Could not read CSV with tried encodings: {encodings}")
 
         if df.empty:
             raise ValueError(" File contains no data")
@@ -82,4 +90,5 @@ def extract(path: str = "xyz.csv") -> pd.DataFrame:
     except pd.errors.ParserError as e:
         raise ValueError(f"❌ Error parsing file: {e}")
     except Exception as e:
-        raise ValueError(f"❌ Unexpected error reading file: {e}")
+        raise ValueError(f"❌ Unexpected error reading file: {e}")
+        raise ValueError(f"❌ Error parsing CSV: {e}")

app/etl/__pycache__/__init__.cpython-310.pyc

@@ -0,0 +1 @@
+# i just created this file so python know this directory is package and can import from it (needed to import extract function in root/tests/test_extract.py)