BUG (string dtype): fix escaping of newline/tab characters in the repr (#60215)

* BUG (string dtype): fix escaping of newline/tab characters in the repr

* parametrize existing test for all string dtypes

* remove xfail

Author: jorisvandenbossche

pandas/core/arrays/string_.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+from functools import partial
 import operator
 from typing import (
     TYPE_CHECKING,
@@ -64,6 +65,8 @@
 from pandas.core.indexers import check_array_indexer
 from pandas.core.missing import isna
 
+from pandas.io.formats import printing
+
 if TYPE_CHECKING:
     import pyarrow
 
@@ -391,6 +394,14 @@ def _from_scalars(cls, scalars, dtype: DtypeObj) -> Self:
             raise ValueError
         return cls._from_sequence(scalars, dtype=dtype)
 
+    def _formatter(self, boxed: bool = False):
+        formatter = partial(
+            printing.pprint_thing,
+            escape_chars=("\t", "\r", "\n"),
+            quote_strings=not boxed,
+        )
+        return formatter
+
     def _str_map(
         self,
         f,

pandas/tests/frame/test_repr.py

@@ -7,8 +7,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 from pandas import (
     NA,
     Categorical,
@@ -176,7 +174,6 @@ def test_repr_mixed_big(self):
 
         repr(biggie)
 
-    @pytest.mark.xfail(using_string_dtype(), reason="/r in")
     def test_repr(self):
         # columns but no index
         no_index = DataFrame(columns=[0, 1, 3])

pandas/tests/series/test_formats.py

@@ -6,8 +6,6 @@
 import numpy as np
 import pytest
 
-from pandas._config import using_string_dtype
-
 import pandas as pd
 from pandas import (
     Categorical,
@@ -143,11 +141,13 @@ def test_tidy_repr_name_0(self, arg):
         rep_str = repr(ser)
         assert "Name: 0" in rep_str
 
-    @pytest.mark.xfail(
-        using_string_dtype(), reason="TODO(infer_string): investigate failure"
-    )
-    def test_newline(self):
-        ser = Series(["a\n\r\tb"], name="a\n\r\td", index=["a\n\r\tf"])
+    def test_newline(self, any_string_dtype):
+        ser = Series(
+            ["a\n\r\tb"],
+            name="a\n\r\td",
+            index=Index(["a\n\r\tf"], dtype=any_string_dtype),
+            dtype=any_string_dtype,
+        )
         assert "\t" not in repr(ser)
         assert "\r" not in repr(ser)
         assert "a\n" not in repr(ser)