Merge remote-tracking branch 'upstream/main' into deps/optional/bump

Author: mroeschke

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ ci:
     skip: [pyright, mypy]
 repos:
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.7
+    rev: v0.12.11
     hooks:
     -   id: ruff
         args: [--exit-non-zero-on-fix]
@@ -51,7 +51,7 @@ repos:
     -   id: cython-lint
     -   id: double-quote-cython-strings
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v6.0.0
     hooks:
     -   id: check-case-conflict
     -   id: check-toml
@@ -64,8 +64,6 @@ repos:
         args: [--fix=auto]
         exclude: ^pandas/tests/io/parser/data/utf16_ex.txt$
     -   id: fix-byte-order-marker
-    -   id: fix-encoding-pragma
-        args: [--remove]
     -   id: trailing-whitespace
         args: [--markdown-linebreak-ext=md]
 -   repo: https://github.com/PyCQA/isort
@@ -94,19 +92,19 @@ repos:
     - id: sphinx-lint
       args: ["--enable", "all", "--disable", "line-too-long"]
 -   repo: https://github.com/pre-commit/mirrors-clang-format
-    rev: v20.1.8
+    rev: v21.1.0
     hooks:
     - id: clang-format
       files: ^pandas/_libs/src|^pandas/_libs/include
       args: [-i]
       types_or: [c, c++]
 -   repo: https://github.com/trim21/pre-commit-mirror-meson
-    rev: v1.8.3
+    rev: v1.9.0
     hooks:
     - id: meson-fmt
       args: ['--inplace']
 -   repo: https://github.com/shellcheck-py/shellcheck-py
-    rev: v0.10.0.1
+    rev: v0.11.0.1
     hooks:
     -   id: shellcheck
         args: ["--severity=warning"]
@@ -266,6 +264,11 @@ repos:
         language: python
         entry: python scripts/validate_unwanted_patterns.py --validation-type="nodefault_used_not_only_for_typing"
         types: [python]
+    -   id: unwanted-patterns-doesnt-use-pandas-warnings
+        name: Check that warning classes for deprecations use pandas' warning classes
+        language: python
+        entry: python scripts/validate_unwanted_patterns.py --validation-type="doesnt_use_pandas_warnings"
+        types: [ python ]
     -   id: no-return-exception
         name: Use raise instead of return for exceptions
         language: pygrep

pandas/_config/config.py

@@ -73,6 +73,7 @@
 
 class DeprecatedOption(NamedTuple):
     key: str
+    category: type[Warning]
     msg: str | None
     rkey: str | None
     removal_ver: str | None
@@ -589,6 +590,7 @@ def register_option(
 
 def deprecate_option(
     key: str,
+    category: type[Warning],
     msg: str | None = None,
     rkey: str | None = None,
     removal_ver: str | None = None,
@@ -608,6 +610,8 @@ def deprecate_option(
     key : str
         Name of the option to be deprecated.
         must be a fully-qualified option name (e.g "x.y.z.rkey").
+    category : Warning
+        Warning class for the deprecation.
     msg : str, optional
         Warning message to output when the key is referenced.
         if no message is given a default message will be emitted.
@@ -631,7 +635,7 @@ def deprecate_option(
     if key in _deprecated_options:
         raise OptionError(f"Option '{key}' has already been defined as deprecated.")
 
-    _deprecated_options[key] = DeprecatedOption(key, msg, rkey, removal_ver)
+    _deprecated_options[key] = DeprecatedOption(key, category, msg, rkey, removal_ver)
 
 
 #
@@ -716,7 +720,7 @@ def _warn_if_deprecated(key: str) -> bool:
         if d.msg:
             warnings.warn(
                 d.msg,
-                FutureWarning,
+                d.category,
                 stacklevel=find_stack_level(),
             )
         else:
@@ -728,7 +732,11 @@ def _warn_if_deprecated(key: str) -> bool:
             else:
                 msg += ", please refrain from using it."
 
-            warnings.warn(msg, FutureWarning, stacklevel=find_stack_level())
+            warnings.warn(
+                msg,
+                d.category,
+                stacklevel=find_stack_level(),
+            )
         return True
     return False
 

pandas/_libs/src/vendored/ujson/python/objToJSON.c

@@ -51,6 +51,8 @@ Numeric decoder derived from TCL library
 #include <numpy/ndarraytypes.h>
 #include <numpy/npy_math.h>
 
+static const int CSTR_SIZE = 20;
+
 npy_int64 get_nat(void) { return NPY_MIN_INT64; }
 
 typedef const char *(*PFN_PyTypeToUTF8)(JSOBJ obj, JSONTypeContext *ti,
@@ -106,7 +108,7 @@ typedef struct __TypeContext {
   double doubleValue;
   JSINT64 longValue;
 
-  const char *cStr;
+  char *cStr;
   NpyArrContext *npyarr;
   PdBlockContext *pdblock;
   int transpose;
@@ -347,7 +349,8 @@ static const char *PyDateTimeToIsoCallback(JSOBJ obj, JSONTypeContext *tc,
   }
 
   NPY_DATETIMEUNIT base = ((PyObjectEncoder *)tc->encoder)->datetimeUnit;
-  return PyDateTimeToIso(obj, base, len);
+  GET_TC(tc)->cStr = PyDateTimeToIso(obj, base, len);
+  return GET_TC(tc)->cStr;
 }
 
 static const char *PyTimeToJSON(JSOBJ _obj, JSONTypeContext *tc,
@@ -1007,16 +1010,24 @@ static const char *List_iterGetName(JSOBJ Py_UNUSED(obj),
 //=============================================================================
 static void Index_iterBegin(JSOBJ Py_UNUSED(obj), JSONTypeContext *tc) {
   GET_TC(tc)->index = 0;
+  GET_TC(tc)->cStr = PyObject_Malloc(CSTR_SIZE);
+  if (!GET_TC(tc)->cStr) {
+    PyErr_NoMemory();
+  }
 }
 
 static int Index_iterNext(JSOBJ obj, JSONTypeContext *tc) {
   const Py_ssize_t index = GET_TC(tc)->index;
   Py_XDECREF(GET_TC(tc)->itemValue);
+  if (!GET_TC(tc)->cStr) {
+    return 0;
+  }
+
   if (index == 0) {
-    GET_TC(tc)->cStr = "name";
+    strcpy(GET_TC(tc)->cStr, "name");
     GET_TC(tc)->itemValue = PyObject_GetAttrString(obj, "name");
   } else if (index == 1) {
-    GET_TC(tc)->cStr = "data";
+    strcpy(GET_TC(tc)->cStr, "data");
     GET_TC(tc)->itemValue = get_values(obj);
     if (!GET_TC(tc)->itemValue) {
       return 0;
@@ -1049,19 +1060,27 @@ static void Series_iterBegin(JSOBJ Py_UNUSED(obj), JSONTypeContext *tc) {
   PyObjectEncoder *enc = (PyObjectEncoder *)tc->encoder;
   GET_TC(tc)->index = 0;
   enc->outputFormat = VALUES; // for contained series
+  GET_TC(tc)->cStr = PyObject_Malloc(CSTR_SIZE);
+  if (!GET_TC(tc)->cStr) {
+    PyErr_NoMemory();
+  }
 }
 
 static int Series_iterNext(JSOBJ obj, JSONTypeContext *tc) {
   const Py_ssize_t index = GET_TC(tc)->index;
   Py_XDECREF(GET_TC(tc)->itemValue);
+  if (!GET_TC(tc)->cStr) {
+    return 0;
+  }
+
   if (index == 0) {
-    GET_TC(tc)->cStr = "name";
+    strcpy(GET_TC(tc)->cStr, "name");
     GET_TC(tc)->itemValue = PyObject_GetAttrString(obj, "name");
   } else if (index == 1) {
-    GET_TC(tc)->cStr = "index";
+    strcpy(GET_TC(tc)->cStr, "index");
     GET_TC(tc)->itemValue = PyObject_GetAttrString(obj, "index");
   } else if (index == 2) {
-    GET_TC(tc)->cStr = "data";
+    strcpy(GET_TC(tc)->cStr, "data");
     GET_TC(tc)->itemValue = get_values(obj);
     if (!GET_TC(tc)->itemValue) {
       return 0;
@@ -1096,19 +1115,27 @@ static void DataFrame_iterBegin(JSOBJ Py_UNUSED(obj), JSONTypeContext *tc) {
   PyObjectEncoder *enc = (PyObjectEncoder *)tc->encoder;
   GET_TC(tc)->index = 0;
   enc->outputFormat = VALUES; // for contained series & index
+  GET_TC(tc)->cStr = PyObject_Malloc(CSTR_SIZE);
+  if (!GET_TC(tc)->cStr) {
+    PyErr_NoMemory();
+  }
 }
 
 static int DataFrame_iterNext(JSOBJ obj, JSONTypeContext *tc) {
   const Py_ssize_t index = GET_TC(tc)->index;
   Py_XDECREF(GET_TC(tc)->itemValue);
+  if (!GET_TC(tc)->cStr) {
+    return 0;
+  }
+
   if (index == 0) {
-    GET_TC(tc)->cStr = "columns";
+    strcpy(GET_TC(tc)->cStr, "columns");
     GET_TC(tc)->itemValue = PyObject_GetAttrString(obj, "columns");
   } else if (index == 1) {
-    GET_TC(tc)->cStr = "index";
+    strcpy(GET_TC(tc)->cStr, "index");
     GET_TC(tc)->itemValue = PyObject_GetAttrString(obj, "index");
   } else if (index == 2) {
-    GET_TC(tc)->cStr = "data";
+    strcpy(GET_TC(tc)->cStr, "data");
     Py_INCREF(obj);
     GET_TC(tc)->itemValue = obj;
   } else {
@@ -1880,6 +1907,7 @@ static void Object_endTypeContext(JSOBJ Py_UNUSED(obj), JSONTypeContext *tc) {
     GET_TC(tc)->rowLabels = NULL;
     NpyArr_freeLabels(GET_TC(tc)->columnLabels, GET_TC(tc)->columnLabelsLen);
     GET_TC(tc)->columnLabels = NULL;
+    PyObject_Free(GET_TC(tc)->cStr);
     GET_TC(tc)->cStr = NULL;
     PyObject_Free(tc->prv);
     tc->prv = NULL;

pandas/core/arrays/string_.py

@@ -177,7 +177,7 @@ def __init__(
                 "'pd.options.future.infer_string = True' option globally and use "
                 'the "str" alias as a shorthand notation to specify a dtype '
                 '(instead of "string[pyarrow_numpy]").',
-                FutureWarning,
+                FutureWarning,  # pdlint: ignore[warning_class]
                 stacklevel=find_stack_level(),
             )
             storage = "pyarrow"

pandas/core/arrays/string_arrow.py

@@ -247,7 +247,7 @@ def _convert_bool_result(self, values, na=lib.no_default, method_name=None):
             warnings.warn(
                 f"Allowing a non-bool 'na' in obj.str.{method_name} is deprecated "
                 "and will raise in a future version.",
-                FutureWarning,
+                FutureWarning,  # pdlint: ignore[warning_class]
                 stacklevel=find_stack_level(),
             )
             na = bool(na)

pandas/core/dtypes/dtypes.py

@@ -1053,7 +1053,7 @@ def __new__(cls, freq) -> PeriodDtype:  # noqa: PYI034
             warnings.warn(
                 "PeriodDtype[B] is deprecated and will be removed in a future "
                 "version. Use a DatetimeIndex with freq='B' instead",
-                FutureWarning,
+                FutureWarning,  # pdlint: ignore[warning_class]
                 stacklevel=find_stack_level(),
             )
 

pandas/core/generic.py

@@ -9139,7 +9139,7 @@ def resample(
                 "deprecated and will be removed in a future version. "
                 "Explicitly cast PeriodIndex to DatetimeIndex before resampling "
                 "instead.",
-                FutureWarning,
+                FutureWarning,  # pdlint: ignore[warning_class]
                 stacklevel=find_stack_level(),
             )
         else:

pandas/core/groupby/groupby.py

@@ -61,6 +61,7 @@ class providing the base-class of operations.
 from pandas.errors import (
     AbstractMethodError,
     DataError,
+    Pandas4Warning,
 )
 from pandas.util._decorators import (
     Appender,
@@ -557,7 +558,7 @@ def groups(self) -> dict[Hashable, Index]:
                 "and will be removed. In a future version `groups` by one element "
                 "list will return tuple. Use ``df.groupby(by='a').groups`` "
                 "instead of ``df.groupby(by=['a']).groups`` to avoid this warning",
-                FutureWarning,
+                Pandas4Warning,
                 stacklevel=find_stack_level(),
             )
         return self._grouper.groups

pandas/core/resample.py

@@ -1949,7 +1949,7 @@ def _resampler_for_grouping(self):
         warnings.warn(
             "Resampling a groupby with a PeriodIndex is deprecated. "
             "Cast to DatetimeIndex before resampling instead.",
-            FutureWarning,
+            FutureWarning,  # pdlint: ignore[warning_class]
             stacklevel=find_stack_level(),
         )
         return PeriodIndexResamplerGroupby
@@ -2293,11 +2293,12 @@ def _get_resampler(self, obj: NDFrame) -> Resampler:
             )
         elif isinstance(ax, PeriodIndex):
             if isinstance(ax, PeriodIndex):
+                # TODO: Enforce in 3.0 (#53481)
                 # GH#53481
                 warnings.warn(
                     "Resampling with a PeriodIndex is deprecated. "
                     "Cast index to DatetimeIndex before resampling instead.",
-                    FutureWarning,
+                    FutureWarning,  # pdlint: ignore[warning_class]
                     stacklevel=find_stack_level(),
                 )
             return PeriodIndexResampler(

pandas/core/strings/object_array.py

@@ -159,35 +159,38 @@ def _str_contains(
                 upper_pat = pat.upper()
                 f = lambda x: upper_pat in x.upper()
         if na is not lib.no_default and not isna(na) and not isinstance(na, bool):
+            # TODO: Enforce in 3.0 (#59615)
             # GH#59561
             warnings.warn(
                 "Allowing a non-bool 'na' in obj.str.contains is deprecated "
                 "and will raise in a future version.",
-                FutureWarning,
+                FutureWarning,  # pdlint: ignore[warning_class]
                 stacklevel=find_stack_level(),
             )
         return self._str_map(f, na, dtype=np.dtype("bool"))
 
     def _str_startswith(self, pat, na=lib.no_default):
         f = lambda x: x.startswith(pat)
         if na is not lib.no_default and not isna(na) and not isinstance(na, bool):
+            # TODO: Enforce in 3.0 (#59615)
             # GH#59561
             warnings.warn(
                 "Allowing a non-bool 'na' in obj.str.startswith is deprecated "
                 "and will raise in a future version.",
-                FutureWarning,
+                FutureWarning,  # pdlint: ignore[warning_class]
                 stacklevel=find_stack_level(),
             )
         return self._str_map(f, na_value=na, dtype=np.dtype(bool))
 
     def _str_endswith(self, pat, na=lib.no_default):
         f = lambda x: x.endswith(pat)
         if na is not lib.no_default and not isna(na) and not isinstance(na, bool):
+            # TODO: Enforce in 3.0 (#59615)
             # GH#59561
             warnings.warn(
                 "Allowing a non-bool 'na' in obj.str.endswith is deprecated "
                 "and will raise in a future version.",
-                FutureWarning,
+                FutureWarning,  # pdlint: ignore[warning_class]
                 stacklevel=find_stack_level(),
             )
         return self._str_map(f, na_value=na, dtype=np.dtype(bool))