From 92f1de68ac57a82bc219da35e69e346d8dfbb1da Mon Sep 17 00:00:00 2001
From: Simon Hawkins <simonjayhawkins@gmail.com>
Date: Tue, 11 May 2021 12:46:03 +0100
Subject: [PATCH 1/2] [ArrowStringArray] REF: str.extract argument validation

---
 pandas/core/strings/accessor.py | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/pandas/core/strings/accessor.py b/pandas/core/strings/accessor.py
index 9f8c9fa2f0515..ddea691e105d1 100644
--- a/pandas/core/strings/accessor.py
+++ b/pandas/core/strings/accessor.py
@@ -2,15 +2,18 @@
 from functools import wraps
 import re
 from typing import (
+    TYPE_CHECKING,
     Dict,
     List,
     Optional,
+    Union,
 )
 import warnings
 
 import numpy as np
 
 import pandas._libs.lib as lib
+from pandas._typing import FrameOrSeriesUnion
 from pandas.util._decorators import Appender
 
 from pandas.core.dtypes.common import (
@@ -31,6 +34,9 @@
 
 from pandas.core.base import NoNewAttributesMixin
 
+if TYPE_CHECKING:
+    from pandas import Index
+
 _shared_docs: Dict[str, str] = {}
 _cpython_optimized_encoders = (
     "utf-8",
@@ -2274,7 +2280,9 @@ def findall(self, pat, flags=0):
         return self._wrap_result(result, returns_string=False)
 
     @forbid_nonstring_types(["bytes"])
-    def extract(self, pat, flags=0, expand=True):
+    def extract(
+        self, pat: str, flags: int = 0, expand: bool = True
+    ) -> Union[FrameOrSeriesUnion, "Index"]:
         r"""
         Extract capture groups in the regex `pat` as columns in a DataFrame.
 
@@ -2355,6 +2363,16 @@ def extract(self, pat, flags=0, expand=True):
         2    NaN
         dtype: object
         """
+        if not isinstance(expand, bool):
+            raise ValueError("expand must be True or False")
+
+        regex = re.compile(pat, flags=flags)
+        if regex.groups == 0:
+            raise ValueError("pattern contains no capture groups")
+
+        if not expand and regex.groups > 1 and isinstance(self._data, ABCIndex):
+            raise ValueError("only one regex group is supported with Index")
+
         # TODO: dispatch
         return str_extract(self, pat, flags, expand=expand)
 
@@ -3008,8 +3026,6 @@ def cat_core(list_of_columns: List, sep: str):
 
 def _groups_or_na_fun(regex):
     """Used in both extract_noexpand and extract_frame"""
-    if regex.groups == 0:
-        raise ValueError("pattern contains no capture groups")
     empty_row = [np.nan] * regex.groups
 
     def f(x):
@@ -3066,8 +3082,6 @@ def _str_extract_noexpand(arr, pat, flags=0):
         # not dispatching, so we have to reconstruct here.
         result = pd_array(result, dtype=result_dtype)
     else:
-        if isinstance(arr, ABCIndex):
-            raise ValueError("only one regex group is supported with Index")
         name = None
         names = dict(zip(regex.groupindex.values(), regex.groupindex.keys()))
         columns = [names.get(1 + i, i) for i in range(regex.groups)]
@@ -3120,8 +3134,6 @@ def _str_extract_frame(arr, pat, flags=0):
 
 
 def str_extract(arr, pat, flags=0, expand=True):
-    if not isinstance(expand, bool):
-        raise ValueError("expand must be True or False")
     if expand:
         result = _str_extract_frame(arr._orig, pat, flags=flags)
         return result.__finalize__(arr._orig, method="str_extract")

From b627de9a7ffec731013d48ffd56d0209c13dbdc4 Mon Sep 17 00:00:00 2001
From: Simon Hawkins <simonjayhawkins@gmail.com>
Date: Wed, 12 May 2021 09:28:22 +0100
Subject: [PATCH 2/2] isort

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

diff --git a/pandas/core/strings/accessor.py b/pandas/core/strings/accessor.py
index 55cc5123a23d1..2646ddfa45b58 100644
--- a/pandas/core/strings/accessor.py
+++ b/pandas/core/strings/accessor.py
@@ -7,8 +7,8 @@
     Hashable,
     List,
     Optional,
-    Union,
     Pattern,
+    Union,
 )
 import warnings