From df0cae94416aef4f7370e68c0e504d96b57b8b17 Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Mon, 8 Apr 2024 11:30:50 -0700
Subject: [PATCH 1/4] Clean up logic in union_indexes

---
 pandas/_libs/lib.pyx       | 12 ++---
 pandas/core/indexes/api.py | 90 ++++++++++++--------------------------
 2 files changed, 33 insertions(+), 69 deletions(-)

diff --git a/pandas/_libs/lib.pyx b/pandas/_libs/lib.pyx
index a2205454a5a46..c75a1ffc90da1 100644
--- a/pandas/_libs/lib.pyx
+++ b/pandas/_libs/lib.pyx
@@ -320,8 +320,8 @@ def fast_unique_multiple_list(lists: list, sort: bool | None = True) -> list:
         Py_ssize_t k = len(lists)
         Py_ssize_t i, j, n
         list uniques = []
-        dict table = {}
-        object val, stub = 0
+        set table = set()
+        object val
 
     for i in range(k):
         buf = lists[i]
@@ -329,7 +329,7 @@ def fast_unique_multiple_list(lists: list, sort: bool | None = True) -> list:
         for j in range(n):
             val = buf[j]
             if val not in table:
-                table[val] = stub
+                table.add(val)
                 uniques.append(val)
     if sort:
         try:
@@ -361,15 +361,15 @@ def fast_unique_multiple_list_gen(object gen, bint sort=True) -> list:
         list buf
         Py_ssize_t j, n
         list uniques = []
-        dict table = {}
-        object val, stub = 0
+        set table = set()
+        object val
 
     for buf in gen:
         n = len(buf)
         for j in range(n):
             val = buf[j]
             if val not in table:
-                table[val] = stub
+                table.add(val)
                 uniques.append(val)
     if sort:
         try:
diff --git a/pandas/core/indexes/api.py b/pandas/core/indexes/api.py
index 9b05eb42c6d6e..e65eb5b3b4240 100644
--- a/pandas/core/indexes/api.py
+++ b/pandas/core/indexes/api.py
@@ -209,60 +209,6 @@ def union_indexes(indexes, sort: bool | None = True) -> Index:
 
     indexes, kind = _sanitize_and_check(indexes)
 
-    def _unique_indices(inds, dtype) -> Index:
-        """
-        Concatenate indices and remove duplicates.
-
-        Parameters
-        ----------
-        inds : list of Index or list objects
-        dtype : dtype to set for the resulting Index
-
-        Returns
-        -------
-        Index
-        """
-        if all(isinstance(ind, Index) for ind in inds):
-            inds = [ind.astype(dtype, copy=False) for ind in inds]
-            result = inds[0].unique()
-            other = inds[1].append(inds[2:])
-            diff = other[result.get_indexer_for(other) == -1]
-            if len(diff):
-                result = result.append(diff.unique())
-            if sort:
-                result = result.sort_values()
-            return result
-
-        def conv(i):
-            if isinstance(i, Index):
-                i = i.tolist()
-            return i
-
-        return Index(
-            lib.fast_unique_multiple_list([conv(i) for i in inds], sort=sort),
-            dtype=dtype,
-        )
-
-    def _find_common_index_dtype(inds):
-        """
-        Finds a common type for the indexes to pass through to resulting index.
-
-        Parameters
-        ----------
-        inds: list of Index or list objects
-
-        Returns
-        -------
-        The common type or None if no indexes were given
-        """
-        dtypes = [idx.dtype for idx in indexes if isinstance(idx, Index)]
-        if dtypes:
-            dtype = find_common_type(dtypes)
-        else:
-            dtype = None
-
-        return dtype
-
     if kind == "special":
         result = indexes[0]
 
@@ -294,18 +240,36 @@ def _find_common_index_dtype(inds):
         return result
 
     elif kind == "array":
-        dtype = _find_common_index_dtype(indexes)
-        index = indexes[0]
-        if not all(index.equals(other) for other in indexes[1:]):
-            index = _unique_indices(indexes, dtype)
+        if not all_indexes_same(indexes):
+            dtype = find_common_type([idx.dtype for idx in indexes])
+            inds = [ind.astype(dtype, copy=False) for ind in indexes]
+            index = inds[0].unique()
+            other = inds[1].append(inds[2:])
+            diff = other[index.get_indexer_for(other) == -1]
+            if len(diff):
+                index = index.append(diff.unique())
+            if sort:
+                index = index.sort_values()
+        else:
+            index = indexes[0]
 
         name = get_unanimous_names(*indexes)[0]
         if name != index.name:
             index = index.rename(name)
         return index
-    else:  # kind='list'
-        dtype = _find_common_index_dtype(indexes)
-        return _unique_indices(indexes, dtype)
+    elif kind == "list":
+        dtypes = [idx.dtype for idx in indexes if isinstance(idx, Index)]
+        if dtypes:
+            dtype = find_common_type(dtypes)
+        else:
+            dtype = None
+        all_lists = [idx.tolist() if isinstance(idx, Index) else idx for idx in indexes]
+        return Index(
+            lib.fast_unique_multiple_list(all_lists, sort=sort),
+            dtype=dtype,
+        )
+    else:
+        raise ValueError(f"{kind=} must be 'special', 'array' or 'list'.")
 
 
 def _sanitize_and_check(indexes):
@@ -329,14 +293,14 @@ def _sanitize_and_check(indexes):
     sanitized_indexes : list of Index or list objects
     type : {'list', 'array', 'special'}
     """
-    kinds = list({type(index) for index in indexes})
+    kinds = {type(index) for index in indexes}
 
     if list in kinds:
         if len(kinds) > 1:
             indexes = [
                 Index(list(x)) if not isinstance(x, Index) else x for x in indexes
             ]
-            kinds.remove(list)
+            kinds -= {list}
         else:
             return indexes, "list"
 

From 480cffde09c796fe9ec9723cc5307d207c754605 Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Mon, 8 Apr 2024 11:34:37 -0700
Subject: [PATCH 2/4] add typing

---
 pandas/core/indexes/api.py | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/pandas/core/indexes/api.py b/pandas/core/indexes/api.py
index e65eb5b3b4240..8b17e33909d06 100644
--- a/pandas/core/indexes/api.py
+++ b/pandas/core/indexes/api.py
@@ -2,6 +2,7 @@
 
 from typing import (
     TYPE_CHECKING,
+    Literal,
     cast,
 )
 
@@ -272,7 +273,9 @@ def union_indexes(indexes, sort: bool | None = True) -> Index:
         raise ValueError(f"{kind=} must be 'special', 'array' or 'list'.")
 
 
-def _sanitize_and_check(indexes):
+def _sanitize_and_check(
+    indexes,
+) -> tuple[list[Index | list], Literal["list", "array", "special"]]:
     """
     Verify the type of indexes and convert lists to Index.
 

From 6d6fe04619db2b91f06c96d34a82133143897ff0 Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Mon, 8 Apr 2024 12:29:27 -0700
Subject: [PATCH 3/4] Just use the generator version

---
 pandas/_libs/lib.pyi       |  1 -
 pandas/_libs/lib.pyx       | 28 ----------------------------
 pandas/core/indexes/api.py |  4 ++--
 3 files changed, 2 insertions(+), 31 deletions(-)

diff --git a/pandas/_libs/lib.pyi b/pandas/_libs/lib.pyi
index b39d32d069619..daaaacee3487d 100644
--- a/pandas/_libs/lib.pyi
+++ b/pandas/_libs/lib.pyi
@@ -67,7 +67,6 @@ def fast_multiget(
     default=...,
 ) -> ArrayLike: ...
 def fast_unique_multiple_list_gen(gen: Generator, sort: bool = ...) -> list: ...
-def fast_unique_multiple_list(lists: list, sort: bool | None = ...) -> list: ...
 @overload
 def map_infer(
     arr: np.ndarray,
diff --git a/pandas/_libs/lib.pyx b/pandas/_libs/lib.pyx
index c75a1ffc90da1..7aa1cb715521e 100644
--- a/pandas/_libs/lib.pyx
+++ b/pandas/_libs/lib.pyx
@@ -312,34 +312,6 @@ def item_from_zerodim(val: object) -> object:
     return val
 
 
-@cython.wraparound(False)
-@cython.boundscheck(False)
-def fast_unique_multiple_list(lists: list, sort: bool | None = True) -> list:
-    cdef:
-        list buf
-        Py_ssize_t k = len(lists)
-        Py_ssize_t i, j, n
-        list uniques = []
-        set table = set()
-        object val
-
-    for i in range(k):
-        buf = lists[i]
-        n = len(buf)
-        for j in range(n):
-            val = buf[j]
-            if val not in table:
-                table.add(val)
-                uniques.append(val)
-    if sort:
-        try:
-            uniques.sort()
-        except TypeError:
-            pass
-
-    return uniques
-
-
 @cython.wraparound(False)
 @cython.boundscheck(False)
 def fast_unique_multiple_list_gen(object gen, bint sort=True) -> list:
diff --git a/pandas/core/indexes/api.py b/pandas/core/indexes/api.py
index 8b17e33909d06..8fb7efbe90066 100644
--- a/pandas/core/indexes/api.py
+++ b/pandas/core/indexes/api.py
@@ -264,9 +264,9 @@ def union_indexes(indexes, sort: bool | None = True) -> Index:
             dtype = find_common_type(dtypes)
         else:
             dtype = None
-        all_lists = [idx.tolist() if isinstance(idx, Index) else idx for idx in indexes]
+        all_lists = (idx.tolist() if isinstance(idx, Index) else idx for idx in indexes)
         return Index(
-            lib.fast_unique_multiple_list(all_lists, sort=sort),
+            lib.fast_unique_multiple_list_gen(all_lists, sort=bool(sort)),
             dtype=dtype,
         )
     else:

From 938e1c15edcb0bb70b88082c52ace5e6d37925be Mon Sep 17 00:00:00 2001
From: Matthew Roeschke <10647082+mroeschke@users.noreply.github.com>
Date: Mon, 8 Apr 2024 13:31:35 -0700
Subject: [PATCH 4/4] Undo typing

---
 pandas/core/indexes/api.py | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/pandas/core/indexes/api.py b/pandas/core/indexes/api.py
index 8fb7efbe90066..c5e3f3a50e10d 100644
--- a/pandas/core/indexes/api.py
+++ b/pandas/core/indexes/api.py
@@ -2,7 +2,6 @@
 
 from typing import (
     TYPE_CHECKING,
-    Literal,
     cast,
 )
 
@@ -273,9 +272,7 @@ def union_indexes(indexes, sort: bool | None = True) -> Index:
         raise ValueError(f"{kind=} must be 'special', 'array' or 'list'.")
 
 
-def _sanitize_and_check(
-    indexes,
-) -> tuple[list[Index | list], Literal["list", "array", "special"]]:
+def _sanitize_and_check(indexes):
     """
     Verify the type of indexes and convert lists to Index.