From e7eeee740f2a70b64b79935e40df36994325b4de Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Wed, 18 Aug 2021 11:18:32 -0700
Subject: [PATCH 1/2] REF: ensure to_arrays returns matched-length
 arrays/columns

---
 pandas/core/frame.py                  |  2 ++
 pandas/core/internals/construction.py | 17 +++++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/pandas/core/frame.py b/pandas/core/frame.py
index 823de2133f0b3..c6b5803c3053a 100644
--- a/pandas/core/frame.py
+++ b/pandas/core/frame.py
@@ -2323,6 +2323,8 @@ def _from_arrays(
 
         manager = get_option("mode.data_manager")
         columns = ensure_index(columns)
+        if len(columns) != len(arrays):
+            raise ValueError("len(columns) must match len(arrays)")
         mgr = arrays_to_mgr(
             arrays,
             columns,
diff --git a/pandas/core/internals/construction.py b/pandas/core/internals/construction.py
index 7f3d246a6fda6..638a21e3250cb 100644
--- a/pandas/core/internals/construction.py
+++ b/pandas/core/internals/construction.py
@@ -433,6 +433,7 @@ def dict_to_mgr(
             arrays.loc[missing] = [val] * missing.sum()
 
         arrays = list(arrays)
+        data_names = columns
 
     else:
         keys = list(data.keys())
@@ -738,6 +739,17 @@ def to_arrays(
 ) -> tuple[list[ArrayLike], Index]:
     """
     Return list of arrays, columns.
+
+    Returns
+    -------
+    list[ArrayLike]
+        These will become columns in a DataFrame.
+    Index
+        This will become frame.columns.
+
+    Notes
+    -----
+    Ensures that len(result_arrays) == len(result_index).
     """
     if isinstance(data, ABCDataFrame):
         # see test_from_records_with_index_data, test_from_records_bad_index_column
@@ -783,6 +795,11 @@ def to_arrays(
         )
         if columns is None:
             columns = ibase.default_index(len(data))
+        elif len(columns) > len(data):
+            raise ValueError("len(columns) > len(data)")
+        elif len(columns) < len(data):
+            # doing this here is akin to a pre-emptive reindex
+            data = data[: len(columns)]
         return data, columns
 
     elif isinstance(data, np.ndarray) and data.dtype.names is not None:

From 70c1e4582082e30b63ff52ad9643a257c169f870 Mon Sep 17 00:00:00 2001
From: Brock <jbrockmendel@gmail.com>
Date: Wed, 18 Aug 2021 12:01:50 -0700
Subject: [PATCH 2/2] ensure_index on data_names

---
 pandas/core/internals/construction.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/core/internals/construction.py b/pandas/core/internals/construction.py
index 638a21e3250cb..33568e4a72c4b 100644
--- a/pandas/core/internals/construction.py
+++ b/pandas/core/internals/construction.py
@@ -433,7 +433,7 @@ def dict_to_mgr(
             arrays.loc[missing] = [val] * missing.sum()
 
         arrays = list(arrays)
-        data_names = columns
+        data_names = ensure_index(columns)
 
     else:
         keys = list(data.keys())