Merge remote-tracking branch 'upstream/2.3.x' into backport-61995

Author: jorisvandenbossche

doc/source/whatsnew/v2.3.2.rst

@@ -26,8 +26,8 @@ Bug fixes
   "string" type in the JSON Table Schema for :class:`StringDtype` columns
   (:issue:`61889`)
 - Boolean operations (``|``, ``&``, ``^``) with bool-dtype objects on the left and :class:`StringDtype` objects on the right now cast the string to bool, with a deprecation warning (:issue:`60234`)
-- Fixed ``~Series.str.match`` and ``~Series.str.fullmatch`` with compiled regex
-  for the Arrow-backed string dtype (:issue:`61964`)
+- Fixed ``~Series.str.match``, ``~Series.str.fullmatch`` and ``~Series.str.contains``
+  with compiled regex for the Arrow-backed string dtype (:issue:`61964`, :issue:`61942`)
 
 .. ---------------------------------------------------------------------------
 .. _whatsnew_232.contributors:

pandas/core/arrays/string_arrow.py

@@ -355,6 +355,8 @@ def _str_contains(
     ):
         if flags:
             return super()._str_contains(pat, case, flags, na, regex)
+        if isinstance(pat, re.Pattern):
+            pat = pat.pattern
 
         return ArrowStringArrayMixin._str_contains(self, pat, case, flags, na, regex)
 

pandas/core/indexing.py

@@ -2575,6 +2575,22 @@ def __getitem__(self, key):
         return super().__getitem__(key)
 
     def __setitem__(self, key, value) -> None:
+        if not PYPY and using_copy_on_write():
+            if sys.getrefcount(self.obj) <= 2:
+                warnings.warn(
+                    _chained_assignment_msg, ChainedAssignmentError, stacklevel=2
+                )
+        elif not PYPY and not using_copy_on_write():
+            ctr = sys.getrefcount(self.obj)
+            ref_count = 2
+            if not warn_copy_on_write() and _check_cacher(self.obj):
+                # see https://github.com/pandas-dev/pandas/pull/56060#discussion_r1399245221
+                ref_count += 1
+            if ctr <= ref_count:
+                warnings.warn(
+                    _chained_assignment_warning_msg, FutureWarning, stacklevel=2
+                )
+
         if self.ndim == 2 and not self._axes_are_unique:
             # GH#33041 fall back to .loc
             if not isinstance(key, tuple) or not all(is_scalar(x) for x in key):
@@ -2599,6 +2615,25 @@ def _convert_key(self, key):
                 raise ValueError("iAt based indexing can only have integer indexers")
         return key
 
+    def __setitem__(self, key, value) -> None:
+        if not PYPY and using_copy_on_write():
+            if sys.getrefcount(self.obj) <= 2:
+                warnings.warn(
+                    _chained_assignment_msg, ChainedAssignmentError, stacklevel=2
+                )
+        elif not PYPY and not using_copy_on_write():
+            ctr = sys.getrefcount(self.obj)
+            ref_count = 2
+            if not warn_copy_on_write() and _check_cacher(self.obj):
+                # see https://github.com/pandas-dev/pandas/pull/56060#discussion_r1399245221
+                ref_count += 1
+            if ctr <= ref_count:
+                warnings.warn(
+                    _chained_assignment_warning_msg, FutureWarning, stacklevel=2
+                )
+
+        return super().__setitem__(key, value)
+
 
 def _tuplify(ndim: int, loc: Hashable) -> tuple[Hashable | slice, ...]:
     """

pandas/tests/copy_view/test_chained_assignment_deprecation.py

@@ -172,3 +172,83 @@ def test_frame_setitem(indexer, using_copy_on_write):
     with option_context("chained_assignment", "warn"):
         with tm.raises_chained_assignment_error(extra_warnings=extra_warnings):
             df[0:3][indexer] = 10
+
+
+@pytest.mark.parametrize(
+    "indexer", [0, [0, 1], slice(0, 2), np.array([True, False, True])]
+)
+def test_series_iloc_setitem(indexer):
+    df = DataFrame({"a": [1, 2, 3], "b": 1})
+
+    with option_context("chained_assignment", "warn"):
+        with tm.raises_chained_assignment_error():
+            df["a"].iloc[indexer] = 0
+
+
+@pytest.mark.parametrize(
+    "indexer", [0, [0, 1], slice(0, 2), np.array([True, False, True])]
+)
+def test_frame_iloc_setitem(indexer, using_copy_on_write):
+    df = DataFrame({"a": [1, 2, 3, 4, 5], "b": 1})
+
+    extra_warnings = () if using_copy_on_write else (SettingWithCopyWarning,)
+
+    with option_context("chained_assignment", "warn"):
+        with tm.raises_chained_assignment_error(extra_warnings=extra_warnings):
+            df[0:3].iloc[indexer] = 10
+
+
+@pytest.mark.parametrize(
+    "indexer", [0, [0, 1], slice(0, 2), np.array([True, False, True])]
+)
+def test_series_loc_setitem(indexer):
+    df = DataFrame({"a": [1, 2, 3], "b": 1})
+
+    with option_context("chained_assignment", "warn"):
+        with tm.raises_chained_assignment_error():
+            df["a"].loc[indexer] = 0
+
+
+@pytest.mark.parametrize(
+    "indexer", [0, [0, 1], (0, "a"), slice(0, 2), np.array([True, False, True])]
+)
+def test_frame_loc_setitem(indexer, using_copy_on_write):
+    df = DataFrame({"a": [1, 2, 3, 4, 5], "b": 1})
+
+    extra_warnings = () if using_copy_on_write else (SettingWithCopyWarning,)
+
+    with option_context("chained_assignment", "warn"):
+        with tm.raises_chained_assignment_error(extra_warnings=extra_warnings):
+            df[0:3].loc[indexer] = 10
+
+
+def test_series_at_setitem():
+    df = DataFrame({"a": [1, 2, 3], "b": 1})
+
+    with option_context("chained_assignment", "warn"):
+        with tm.raises_chained_assignment_error():
+            df["a"].at[0] = 0
+
+
+def test_frame_at_setitem():
+    df = DataFrame({"a": [1, 2, 3, 4, 5], "b": 1})
+
+    with option_context("chained_assignment", "warn"):
+        with tm.raises_chained_assignment_error():
+            df[0:3].at[0, "a"] = 10
+
+
+def test_series_iat_setitem():
+    df = DataFrame({"a": [1, 2, 3], "b": 1})
+
+    with option_context("chained_assignment", "warn"):
+        with tm.raises_chained_assignment_error():
+            df["a"].iat[0] = 0
+
+
+def test_frame_iat_setitem():
+    df = DataFrame({"a": [1, 2, 3, 4, 5], "b": 1})
+
+    with option_context("chained_assignment", "warn"):
+        with tm.raises_chained_assignment_error():
+            df[0:3].iat[0, 0] = 10

pandas/tests/strings/test_find_replace.py

@@ -290,6 +290,19 @@ def test_contains_nan(any_string_dtype):
     tm.assert_series_equal(result, expected)
 
 
+def test_contains_compiled_regex(any_string_dtype):
+    # GH#61942
+    ser = Series(["foo", "bar", "baz"], dtype=any_string_dtype)
+    pat = re.compile("ba.")
+    result = ser.str.contains(pat)
+
+    expected_dtype = (
+        np.bool_ if is_object_or_nan_string_dtype(any_string_dtype) else "boolean"
+    )
+    expected = Series([False, True, True], dtype=expected_dtype)
+    tm.assert_series_equal(result, expected)
+
+
 # --------------------------------------------------------------------------------------
 # str.startswith
 # --------------------------------------------------------------------------------------

pandas/tests/tslibs/test_parsing.py

@@ -395,7 +395,8 @@ def test_hypothesis_delimited_date(
         request.applymarker(
             pytest.mark.xfail(
                 reason="parse_datetime_string cannot reliably tell whether "
-                "e.g. %m.%Y is a float or a date"
+                "e.g. %m.%Y is a float or a date",
+                strict=False,
             )
         )
     date_string = test_datetime.strftime(date_format.replace(" ", delimiter))