Enhance on_bad_lines

Author: sanggon6107

pandas/io/parsers/python_parser.py

@@ -1201,7 +1201,7 @@ def _rows_to_cols(self, content: list[list[Scalar]]) -> list[np.ndarray]:
 
                 if actual_len > col_len:
                     if callable(self.on_bad_lines):
-                        new_l = self.on_bad_lines(_content)
+                        new_l = self.on_bad_lines(_content, col_len, actual_len, i + 2)
                         if new_l is not None:
                             content.append(new_l)  # pyright: ignore[reportArgumentType]
                     elif self.on_bad_lines in (

pandas/io/parsers/readers.py

@@ -414,8 +414,11 @@ class _read_shared(TypedDict, Generic[HashableT], total=False):
     - ``'skip'``, skip bad lines without raising or warning when they are encountered.
     - Callable, function that will process a single bad line.
         - With ``engine='python'``, function with signature
-          ``(bad_line: list[str]) -> list[str] | None``.
+          ``(bad_line: list[str], expected_columns: int, actual_columns: int, row: int) -> list[str] | None``.
           ``bad_line`` is a list of strings split by the ``sep``.
+          ``expected_columns`` is the expected number of columns.
+          ``actual_columns`` is the actual number of columns.
+          ``row`` is the row number of the bad line.
           If the function returns ``None``, the bad line will be ignored.
           If the function returns a new ``list`` of strings with more elements than
           expected, a ``ParserWarning`` will be emitted while dropping extra elements.