REF: remove sanitize_index (#40089)

Author: jbrockmendel

pandas/core/common.py

@@ -3,6 +3,7 @@
 
 Note: pandas.core.common is *not* part of the public API.
 """
+from __future__ import annotations
 
 from collections import (
     abc,
@@ -12,6 +13,7 @@
 from functools import partial
 import inspect
 from typing import (
+    TYPE_CHECKING,
     Any,
     Callable,
     Collection,
@@ -51,6 +53,9 @@
 from pandas.core.dtypes.inference import iterable_not_string
 from pandas.core.dtypes.missing import isna
 
+if TYPE_CHECKING:
+    from pandas import Index
+
 
 class SettingWithCopyError(ValueError):
     pass
@@ -512,3 +517,16 @@ def temp_setattr(obj, attr: str, value) -> Iterator[None]:
     setattr(obj, attr, value)
     yield obj
     setattr(obj, attr, old_value)
+
+
+def require_length_match(data, index: Index):
+    """
+    Check the length of data matches the length of the index.
+    """
+    if len(data) != len(index):
+        raise ValueError(
+            "Length of values "
+            f"({len(data)}) "
+            "does not match length of index "
+            f"({len(index)})"
+        )

pandas/core/frame.py

@@ -183,7 +183,6 @@
     ndarray_to_mgr,
     nested_data_to_arrays,
     reorder_arrays,
-    sanitize_index,
     to_arrays,
     treat_as_nested,
 )
@@ -4207,15 +4206,14 @@ def _sanitize_column(self, value) -> ArrayLike:
             value = _reindex_for_setitem(value, self.index)
 
         elif isinstance(value, ExtensionArray):
-            # Explicitly copy here, instead of in sanitize_index,
-            # as sanitize_index won't copy an EA, even with copy=True
+            # Explicitly copy here
             value = value.copy()
-            value = sanitize_index(value, self.index)
+            com.require_length_match(value, self.index)
 
         elif is_sequence(value):
+            com.require_length_match(value, self.index)
 
             # turn me into an ndarray
-            value = sanitize_index(value, self.index)
             if not isinstance(value, (np.ndarray, Index)):
                 if isinstance(value, list) and len(value) > 0:
                     value = maybe_convert_platform(value)

pandas/core/internals/construction.py

@@ -35,7 +35,6 @@
     maybe_convert_platform,
     maybe_infer_to_datetimelike,
     maybe_upcast,
-    sanitize_to_nanoseconds,
 )
 from pandas.core.dtypes.common import (
     is_datetime64tz_dtype,
@@ -810,28 +809,3 @@ def convert(arr):
     arrays = [convert(arr) for arr in content]
 
     return arrays
-
-
-# ---------------------------------------------------------------------
-# Series-Based
-
-
-def sanitize_index(data, index: Index):
-    """
-    Sanitize an index type to return an ndarray of the underlying, pass
-    through a non-Index.
-    """
-    if len(data) != len(index):
-        raise ValueError(
-            "Length of values "
-            f"({len(data)}) "
-            "does not match length of index "
-            f"({len(index)})"
-        )
-
-    if isinstance(data, np.ndarray):
-
-        # coerce datetimelike types to ns
-        data = sanitize_to_nanoseconds(data)
-
-    return data

pandas/core/series.py

@@ -126,7 +126,6 @@
 from pandas.core.indexes.timedeltas import TimedeltaIndex
 from pandas.core.indexing import check_bool_indexer
 from pandas.core.internals import SingleBlockManager
-from pandas.core.internals.construction import sanitize_index
 from pandas.core.shared_docs import _shared_docs
 from pandas.core.sorting import (
     ensure_key_mapped,
@@ -388,7 +387,7 @@ def __init__(
                     data = [data]
                 index = ibase.default_index(len(data))
             elif is_list_like(data):
-                sanitize_index(data, index)
+                com.require_length_match(data, index)
 
             # create/copy the manager
             if isinstance(data, SingleBlockManager):