Merge pull request #283 from posit-dev/fix-pre-isolate

fix: usage of `pre=` should be isolated to steps using it

Author: rich-iannone

pointblank/_utils.py

@@ -240,6 +240,46 @@ def _select_df_lib(preference: str = "polars") -> Any:
     return pl if pl is not None else pd
 
 
+def _copy_dataframe(df):
+    """
+    Create a copy of a DataFrame, handling different DataFrame types.
+
+    This function attempts to create a proper copy of the DataFrame using
+    the most appropriate method for each DataFrame type.
+    """
+    # Try standard copy methods first
+    if hasattr(df, "copy") and callable(getattr(df, "copy")):
+        try:
+            return df.copy()
+        except Exception:
+            pass
+
+    if hasattr(df, "clone") and callable(getattr(df, "clone")):
+        try:
+            return df.clone()
+        except Exception:
+            pass
+
+    # Try the select('*') approach for DataFrames that support it
+    # This works well for PySpark and other SQL-like DataFrames
+    if hasattr(df, "select") and callable(getattr(df, "select")):
+        try:
+            return df.select("*")
+        except Exception:
+            pass
+
+    # For DataFrames that can't be copied, return original
+    # This provides some protection while avoiding crashes
+    try:
+        import copy
+
+        return copy.deepcopy(df)
+    except Exception:
+        # If all else fails, return the original DataFrame
+        # This is better than crashing the validation
+        return df
+
+
 def _convert_to_narwhals(df: FrameT) -> nw.DataFrame:
     # Convert the DataFrame to a format that narwhals can work with
     return nw.from_native(df)

pointblank/validate.py

@@ -75,6 +75,7 @@
     _check_any_df_lib,
     _check_invalid_fields,
     _column_test_prep,
+    _copy_dataframe,
     _count_null_values_in_column,
     _count_true_values_in_column,
     _derive_bounds,
@@ -9986,8 +9987,9 @@ def interrogate(
                 validation.active = False
                 continue
 
-            # Make a copy of the table for this step
-            data_tbl_step = data_tbl
+            # Make a deep copy of the table for this step to ensure proper isolation
+            # This prevents modifications from one validation step affecting others
+            data_tbl_step = _copy_dataframe(data_tbl)
 
             # ------------------------------------------------
             # Preprocessing stage