fix: auto-detect encoding for metadata

peakina/datasource.py

@@ -74,6 +74,15 @@ def get_metadata(self) -> Dict[str, Any]:
             return {}  # no metadata for matched datasources
         with self.fetcher.open(self.uri) as f:
             assert self.type is not None
+
+            allowed_params = get_reader_allowed_params(self.type)
+            # Auto-detect encoding if not present
+            encoding = self.reader_kwargs.get("encoding")
+            if "encoding" in allowed_params:
+                if not validate_encoding(f.name, encoding):
+                    encoding = detect_encoding(f.name)
+                self.reader_kwargs["encoding"] = encoding
+
             return get_metadata(f.name, self.type, self.reader_kwargs)
 
     @staticmethod

tests/test_datasource.py

@@ -102,6 +102,13 @@ def test_csv_western_encoding(path):
     df_meta = ds.get_metadata()
     assert df_meta == {"df_rows": 2, "total_rows": 2}
 
+    # Encoding auto-detection
+    ds = DataSource(path("encoded_western_short.csv"))
+    df = ds.get_df()
+    assert df.shape == (2, 19)
+    df_meta = ds.get_metadata()
+    assert df_meta == {"df_rows": 2, "total_rows": 2}
+
 
 def test_csv_header_row(path):
     """