Merge pull request #33 from Abhi2006-cloud/feature/multi-format-support-clean

fix#15 : Support Other File Formats in Extract Function #15

Author: Dheerajyadav1

app/etl/extract.py

@@ -4,13 +4,13 @@
 
 def extract(path: str = "xyz.csv") -> pd.DataFrame :
     """
-    Extracts data from CSV file.
+    Extracts data from CSV, Excel, or JSON file.
     
     Args:
-        path: Path to the CSV file
+        path: Path to the data file (supports .csv, .xlsx, .json)
         
     Returns:
-        DataFrame containing the extracted data  # TODO (Find & Fix): Should specify pd.DataFrame in docstring
+        pd.DataFrame: DataFrame containing the extracted data
         
     Raises:
         FileNotFoundError: If the file doesn't exist
@@ -20,27 +20,41 @@ def extract(path: str = "xyz.csv") -> pd.DataFrame :
     if not os.path.exists(path):
         raise FileNotFoundError(f"❌ File not found: {path}")
 
-    if not str(path).lower().endswith('.csv'):
-        raise ValueError(f"❌ File must be a CSV: {path}")
+    # Get file extension
+    ext = os.path.splitext(path)[-1].lower()
+    
+    # Check if file format is supported
+    if ext not in ['.csv', '.xlsx', '.xls', '.json']:
+        raise ValueError(f"Unsupported file format: {ext}")
 
     try:
-        # Try different encodings
-        encodings = ['utf-8', 'latin-1', 'cp1252', 'iso-8859-1']
-        df = None
-        
-        for encoding in encodings:
-            try:
-                # TODO (Find & Fix)
-                pass 
-            except UnicodeDecodeError:
-                print(f"Failed to read with encoding '{encoding}'")  # Log the encoding that failed
-                continue
-            except Exception as e:
-                print(f"Error reading with encoding '{encoding}': {e}")
-                continue
-        
-        if df is None:
-            raise ValueError(f"Could not read CSV with tried encodings: {encodings}")
+        if ext == '.csv':
+            # Try different encodings for CSV files
+            encodings = ['utf-8', 'latin-1', 'cp1252', 'iso-8859-1']
+            df = None
+            
+            for encoding in encodings:
+                try:
+                    df = pd.read_csv(path, encoding=encoding)
+                    print(f"Successfully read CSV with encoding: {encoding}")
+                    break
+                except UnicodeDecodeError:
+                    print(f"Failed to read with encoding '{encoding}'")
+                    continue
+                except Exception as e:
+                    print(f"Error reading with encoding '{encoding}': {e}")
+                    continue
+            
+            if df is None:
+                raise ValueError(f"Could not read CSV with tried encodings: {encodings}")
+                
+        elif ext in ['.xls', '.xlsx']:
+            df = pd.read_excel(path)
+            print(f"Successfully read Excel file: {path}")
+            
+        elif ext == '.json':
+            df = pd.read_json(path)
+            print(f"Successfully read JSON file: {path}")
 
         # Validate data
         if df.empty:
@@ -52,6 +66,6 @@ def extract(path: str = "xyz.csv") -> pd.DataFrame :
     except pd.errors.EmptyDataError:
         raise ValueError("❌ File contains no data")
     except pd.errors.ParserError as e:
-        raise ValueError(f"❌ Error parsing CSV: {e}")
+        raise ValueError(f"❌ Error parsing file: {e}")
     except Exception as e:
         raise ValueError(f"❌ Unexpected error reading file: {e}")

app/requirements.txt

@@ -1 +1,2 @@
 pandas>=2.0.0
+openpyxl>=3.0.0