BUG: Add type check for encoding_errors in pd.read_csv

doc/source/whatsnew/v3.0.0.rst

@@ -558,6 +558,7 @@ I/O
 - Bug in :meth:`DataFrame.to_stata` when writing :class:`DataFrame` and ``byteorder=`big```. (:issue:`58969`)
 - Bug in :meth:`DataFrame.to_string` that raised ``StopIteration`` with nested DataFrames. (:issue:`16098`)
 - Bug in :meth:`HDFStore.get` was failing to save data of dtype datetime64[s] correctly (:issue:`59004`)
+- Bug in :meth:`read_csv` causing segmentation fault when ``encoding_errors`` is not a string. (:issue:`59059`)
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``index_col`` is specified and ``na_values`` is a dict containing the key ``None``. (:issue:`57547`)
 - Bug in :meth:`read_csv` raising ``TypeError`` when ``nrows`` and ``iterator`` are specified without specifying a ``chunksize``. (:issue:`59079`)
 - Bug in :meth:`read_excel` raising ``ValueError`` when passing array of boolean values when ``dtype="boolean"``. (:issue:`58159`)

pandas/io/parsers/readers.py

@@ -674,6 +674,14 @@ def _read(
     # Extract some of the arguments (pass chunksize on).
     iterator = kwds.get("iterator", False)
     chunksize = kwds.get("chunksize", None)
+
+    # Check type of encoding_errors
+    errors = kwds.get("encoding_errors", "strict")
+    if not isinstance(errors, str):
+        raise ValueError(
+            f"encoding_errors must be a string, got {type(errors).__name__}"
+        )
+
     if kwds.get("engine") == "pyarrow":
         if iterator:
             raise ValueError(

pandas/tests/io/test_common.py

@@ -555,7 +555,7 @@ def test_explicit_encoding(io_class, mode, msg):
             expected.to_csv(buffer, mode=f"w{mode}")
 
 
-@pytest.mark.parametrize("encoding_errors", [None, "strict", "replace"])
+@pytest.mark.parametrize("encoding_errors", ["strict", "replace"])
 @pytest.mark.parametrize("format", ["csv", "json"])
 def test_encoding_errors(encoding_errors, format):
     # GH39450
@@ -590,6 +590,24 @@ def test_encoding_errors(encoding_errors, format):
             tm.assert_frame_equal(df, expected)
 
 
+@pytest.mark.parametrize("encoding_errors", [0, None, "strict"])
+@pytest.mark.parametrize("format", ["csv"])
+def test_encoding_errors_badtype(encoding_errors, format):
+    # GH 59075
+    if format == "csv":
+        content = StringIO("A,B\n1,2\n3,4\n")
+        reader = partial(pd.read_csv, encoding_errors=encoding_errors)
+        if encoding_errors != "strict":
+            expected_error = "encoding_errors must be a string, got "
+            expected_error += f"{type(encoding_errors).__name__}"
+            with pytest.raises(ValueError, match=expected_error):
+                reader(content)
+        else:
+            df = reader(content)
+            expected = pd.DataFrame({"A": [1, 3], "B": [2, 4]})
+            tm.assert_frame_equal(df, expected)
+
+
 def test_bad_encdoing_errors():
     # GH 39777
     with tm.ensure_clean() as path: