From 303a648d522a8301a7b57336100451ec490d3328 Mon Sep 17 00:00:00 2001
From: MarcoGorelli <>
Date: Tue, 20 Dec 2022 18:51:33 +0000
Subject: [PATCH 1/7] wip

---
 doc/source/whatsnew/v2.0.0.rst             |  1 +
 pandas/_libs/tslibs/strptime.pyx           |  3 ++-
 pandas/tests/io/parser/test_parse_dates.py |  5 +++-
 pandas/tests/tools/test_to_datetime.py     | 27 ++++++++++++++++------
 4 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/doc/source/whatsnew/v2.0.0.rst b/doc/source/whatsnew/v2.0.0.rst
index 208bbfa10b9b2..68476f7fa144b 100644
--- a/doc/source/whatsnew/v2.0.0.rst
+++ b/doc/source/whatsnew/v2.0.0.rst
@@ -98,6 +98,7 @@ Other enhancements
 - Added :meth:`Index.infer_objects` analogous to :meth:`Series.infer_objects` (:issue:`50034`)
 - Added ``copy`` parameter to :meth:`Series.infer_objects` and :meth:`DataFrame.infer_objects`, passing ``False`` will avoid making copies for series or columns that are already non-object or where no better dtype can be inferred (:issue:`50096`)
 - :meth:`DataFrame.plot.hist` now recognizes ``xlabel`` and ``ylabel`` arguments (:issue:`49793`)
+- Improved error message in :func:`to_datetime` for non-ISO8601 formats, informing users about the position of the first error (:issue:`50361`)
 -
 
 .. ---------------------------------------------------------------------------
diff --git a/pandas/_libs/tslibs/strptime.pyx b/pandas/_libs/tslibs/strptime.pyx
index 73e9176d3a6d2..06df08d7ddb1d 100644
--- a/pandas/_libs/tslibs/strptime.pyx
+++ b/pandas/_libs/tslibs/strptime.pyx
@@ -396,7 +396,8 @@ def array_strptime(
 
             result_timezone[i] = tz
 
-        except (ValueError, OutOfBoundsDatetime):
+        except (ValueError, OutOfBoundsDatetime) as ex:
+            ex.args = (str(ex) + f" at position {i}", )
             if is_coerce:
                 iresult[i] = NPY_NAT
                 continue
diff --git a/pandas/tests/io/parser/test_parse_dates.py b/pandas/tests/io/parser/test_parse_dates.py
index c366613c2815f..dd1d4e58c8244 100644
--- a/pandas/tests/io/parser/test_parse_dates.py
+++ b/pandas/tests/io/parser/test_parse_dates.py
@@ -1717,7 +1717,10 @@ def test_parse_multiple_delimited_dates_with_swap_warnings():
     # GH46210
     with pytest.raises(
         ValueError,
-        match=r"^time data '31/05/2000' does not match format '%m/%d/%Y' \(match\)$",
+        match=(
+            r"^time data '31/05/2000' does not match format '%m/%d/%Y' \(match\) "
+            "at position 1$"
+        ),
     ):
         pd.to_datetime(["01/01/2000", "31/05/2000", "31/05/2001", "01/02/2000"])
 
diff --git a/pandas/tests/tools/test_to_datetime.py b/pandas/tests/tools/test_to_datetime.py
index 83e40f5f1d98b..b0277f04e360d 100644
--- a/pandas/tests/tools/test_to_datetime.py
+++ b/pandas/tests/tools/test_to_datetime.py
@@ -1093,7 +1093,10 @@ def test_datetime_bool_arrays_mixed(self, cache):
             to_datetime([False, datetime.today()], cache=cache)
         with pytest.raises(
             ValueError,
-            match=r"^time data 'True' does not match format '%Y%m%d' \(match\)$",
+            match=(
+                r"^time data 'True' does not match format '%Y%m%d' "
+                r"\(match\) at position 1$"
+            ),
         ):
             to_datetime(["20130101", True], cache=cache)
         tm.assert_index_equal(
@@ -2072,7 +2075,9 @@ def test_to_datetime_on_datetime64_series(self, cache):
     def test_to_datetime_with_space_in_series(self, cache):
         # GH 6428
         ser = Series(["10/18/2006", "10/18/2008", " "])
-        msg = r"^time data ' ' does not match format '%m/%d/%Y' \(match\)$"
+        msg = (
+            r"^time data ' ' does not match format '%m/%d/%Y' \(match\) at position 2$"
+        )
         with pytest.raises(ValueError, match=msg):
             to_datetime(ser, errors="raise", cache=cache)
         result_coerce = to_datetime(ser, errors="coerce", cache=cache)
@@ -2342,7 +2347,10 @@ def test_dayfirst_warnings_invalid_input(self):
 
         with pytest.raises(
             ValueError,
-            match=r"time data '03/30/2011' does not match format '%d/%m/%Y' \(match\)$",
+            match=(
+                r"time data '03/30/2011' does not match format '%d/%m/%Y' "
+                r"\(match\) at position 1$"
+            ),
         ):
             to_datetime(arr, dayfirst=True)
 
@@ -2923,17 +2931,22 @@ def test_incorrect_value_exception(self):
                 to_datetime(["today", "yesterday"])
 
     @pytest.mark.parametrize(
-        "format, warning", [(None, UserWarning), ("%Y-%m-%d %H:%M:%S", None)]
+        "format, warning",
+        [
+            (None, UserWarning),
+            ("%Y-%m-%d %H:%M:%S", None),
+            ("%Y-%d-%m %H:%M:%S", None),
+        ],
     )
     def test_to_datetime_out_of_bounds_with_format_arg(self, format, warning):
         # see gh-23830
         msg = (
-            "Out of bounds nanosecond timestamp: 2417-10-27 00:00:00 "
-            "present at position 0"
+            r"Out of bounds nanosecond timestamp: 2417-10-10 00:00:00"
+            r".* at position 0"
         )
         with pytest.raises(OutOfBoundsDatetime, match=msg):
             with tm.assert_produces_warning(warning, match="Could not infer format"):
-                to_datetime("2417-10-27 00:00:00", format=format)
+                to_datetime("2417-10-10 00:00:00", format=format)
 
     @pytest.mark.parametrize(
         "arg, origin, expected_str",

From 8e40df407f87b1ccfcc90838a8a0fccc8cd3ae6f Mon Sep 17 00:00:00 2001
From: MarcoGorelli <>
Date: Wed, 21 Dec 2022 10:16:10 +0000
Subject: [PATCH 2/7] unify messages

---
 pandas/_libs/tslib.pyx                     |  6 ++-
 pandas/_libs/tslibs/parsing.pyx            |  6 +--
 pandas/_libs/tslibs/strptime.pyx           | 26 ++++++++----
 pandas/tests/io/parser/test_parse_dates.py |  4 +-
 pandas/tests/tools/test_to_datetime.py     | 46 +++++++++++++---------
 5 files changed, 55 insertions(+), 33 deletions(-)

diff --git a/pandas/_libs/tslib.pyx b/pandas/_libs/tslib.pyx
index c1a30e03235b5..ac1679ef66bc7 100644
--- a/pandas/_libs/tslib.pyx
+++ b/pandas/_libs/tslib.pyx
@@ -515,9 +515,10 @@ cpdef array_to_datetime(
                             iresult[i] = NPY_NAT
                             continue
                         elif is_raise:
+                            match_msg = "match" if exact else "search"
                             raise ValueError(
                                 f"time data \"{val}\" at position {i} doesn't "
-                                f"match format \"{format}\""
+                                f"match format \"{format}\" ({match_msg})"
                             )
                         return values, tz_out
                     # these must be ns unit by-definition
@@ -564,9 +565,10 @@ cpdef array_to_datetime(
                                 iresult[i] = NPY_NAT
                                 continue
                             elif is_raise:
+                                match_msg = "match" if exact else "search"
                                 raise ValueError(
                                     f"time data \"{val}\" at position {i} doesn't "
-                                    f"match format \"{format}\""
+                                    f"match format \"{format}\" ({match_msg})"
                                 )
                             return values, tz_out
 
diff --git a/pandas/_libs/tslibs/parsing.pyx b/pandas/_libs/tslibs/parsing.pyx
index 614db69425f4c..f384e85fb5eb5 100644
--- a/pandas/_libs/tslibs/parsing.pyx
+++ b/pandas/_libs/tslibs/parsing.pyx
@@ -263,7 +263,7 @@ def parse_datetime_string(
         datetime dt
 
     if not _does_string_look_like_datetime(date_string):
-        raise ValueError(f"Given date string {date_string} not likely a datetime")
+        raise ValueError(f'Given date string "{date_string}" not likely a datetime')
 
     if does_string_look_like_time(date_string):
         # use current datetime as default, not pass _DEFAULT_DATETIME
@@ -297,7 +297,7 @@ def parse_datetime_string(
     except TypeError:
         # following may be raised from dateutil
         # TypeError: 'NoneType' object is not iterable
-        raise ValueError(f"Given date string {date_string} not likely a datetime")
+        raise ValueError(f'Given date string "{date_string}" not likely a datetime')
 
     return dt
 
@@ -373,7 +373,7 @@ cdef parse_datetime_string_with_reso(
         int out_tzoffset
 
     if not _does_string_look_like_datetime(date_string):
-        raise ValueError(f"Given date string {date_string} not likely a datetime")
+        raise ValueError(f'Given date string "{date_string}" not likely a datetime')
 
     parsed, reso = _parse_delimited_date(date_string, dayfirst)
     if parsed is not None:
diff --git a/pandas/_libs/tslibs/strptime.pyx b/pandas/_libs/tslibs/strptime.pyx
index 06df08d7ddb1d..196fbd40f0a02 100644
--- a/pandas/_libs/tslibs/strptime.pyx
+++ b/pandas/_libs/tslibs/strptime.pyx
@@ -236,17 +236,22 @@ def array_strptime(
             if exact:
                 found = format_regex.match(val)
                 if not found:
-                    raise ValueError(f"time data '{val}' does not match "
-                                     f"format '{fmt}' (match)")
+                    raise ValueError(f"time data \"{val}\" at position {i} doesn't "
+                                     f"match format \"{fmt}\" (match)")
                 if len(val) != found.end():
-                    raise ValueError(f"unconverted data remains: {val[found.end():]}")
+                    raise ValueError(
+                        f"unconverted data remains at position {i}: "
+                        f'"{val[found.end():]}"'
+                    )
 
             # search
             else:
                 found = format_regex.search(val)
                 if not found:
-                    raise ValueError(f"time data {repr(val)} does not match format "
-                                     f"{repr(fmt)} (search)")
+                    raise ValueError(
+                        f"time data \"{val}\" at position {i} doesn't match "
+                        f"format \"{fmt}\" (search)"
+                    )
 
             iso_year = -1
             year = 1900
@@ -396,8 +401,15 @@ def array_strptime(
 
             result_timezone[i] = tz
 
-        except (ValueError, OutOfBoundsDatetime) as ex:
-            ex.args = (str(ex) + f" at position {i}", )
+        except OutOfBoundsDatetime as ex:
+            ex.args = (f"{str(ex)} present at position {i}",)
+            if is_coerce:
+                iresult[i] = NPY_NAT
+                continue
+            elif is_raise:
+                raise
+            return values, []
+        except ValueError:
             if is_coerce:
                 iresult[i] = NPY_NAT
                 continue
diff --git a/pandas/tests/io/parser/test_parse_dates.py b/pandas/tests/io/parser/test_parse_dates.py
index dd1d4e58c8244..c62e321707bfc 100644
--- a/pandas/tests/io/parser/test_parse_dates.py
+++ b/pandas/tests/io/parser/test_parse_dates.py
@@ -1718,8 +1718,8 @@ def test_parse_multiple_delimited_dates_with_swap_warnings():
     with pytest.raises(
         ValueError,
         match=(
-            r"^time data '31/05/2000' does not match format '%m/%d/%Y' \(match\) "
-            "at position 1$"
+            r'^time data "31/05/2000" at position 1 doesn\'t match format "%m/%d/%Y" '
+            r"\(match\)$"
         ),
     ):
         pd.to_datetime(["01/01/2000", "31/05/2000", "31/05/2001", "01/02/2000"])
diff --git a/pandas/tests/tools/test_to_datetime.py b/pandas/tests/tools/test_to_datetime.py
index b0277f04e360d..e9a318b908767 100644
--- a/pandas/tests/tools/test_to_datetime.py
+++ b/pandas/tests/tools/test_to_datetime.py
@@ -479,7 +479,10 @@ def test_to_datetime_parse_timezone_malformed(self, offset):
         fmt = "%Y-%m-%d %H:%M:%S %z"
         date = "2010-01-01 12:00:00 " + offset
 
-        msg = "does not match format|unconverted data remains"
+        msg = (
+            r'time data ".*" at position 0 doesn\'t match format ".*" \(match\)|'
+            r'unconverted data remains at position 0: ".*"'
+        )
         with pytest.raises(ValueError, match=msg):
             to_datetime([date], format=fmt)
 
@@ -1094,8 +1097,8 @@ def test_datetime_bool_arrays_mixed(self, cache):
         with pytest.raises(
             ValueError,
             match=(
-                r"^time data 'True' does not match format '%Y%m%d' "
-                r"\(match\) at position 1$"
+                r'^time data "True" at position 1 doesn\'t match format "%Y%m%d" '
+                r"\(match\)$"
             ),
         ):
             to_datetime(["20130101", True], cache=cache)
@@ -1136,10 +1139,8 @@ def test_datetime_invalid_scalar(self, value, format, warning):
         assert res is NaT
 
         msg = (
-            "does not match format|"
-            "unconverted data remains:|"
-            "second must be in 0..59|"
-            f"Given date string {value} not likely a datetime"
+            r'^time data "a" at position 0 doesn\'t match format "%H:%M:%S" \(match\)$|'
+            r'^Given date string "a" not likely a datetime$|'
         )
         with pytest.raises(ValueError, match=msg):
             with tm.assert_produces_warning(warning, match="Could not infer format"):
@@ -1160,7 +1161,7 @@ def test_datetime_outofbounds_scalar(self, value, format, warning):
         assert res is NaT
 
         if format is not None:
-            msg = "does not match format|Out of bounds .* present at position 0"
+            msg = r'^time data ".*" at position 0 doesn\'t match format ".*" \(match\)$'
             with pytest.raises(ValueError, match=msg):
                 to_datetime(value, errors="raise", format=format)
         else:
@@ -1185,10 +1186,10 @@ def test_datetime_invalid_index(self, values, format, warning):
         tm.assert_index_equal(res, DatetimeIndex([NaT] * len(values)))
 
         msg = (
-            "does not match format|"
-            "unconverted data remains:|"
-            f"Given date string {values[0]} not likely a datetime|"
-            "second must be in 0..59"
+            r'^(Given date string "a" not likely a datetime present at position 0|'
+            r'time data "a" at position 0 doesn\'t match format "%H:%M:%S" \(match\)|'
+            r'unconverted data remains at position 0: "9"|'
+            r"second must be in 0..59: 00:01:99 present at position 0)$"
         )
         with pytest.raises(ValueError, match=msg):
             with tm.assert_produces_warning(warning, match="Could not infer format"):
@@ -1808,8 +1809,8 @@ def test_dataframe_coerce(self, cache):
         df2 = DataFrame({"year": [2015, 2016], "month": [2, 20], "day": [4, 5]})
 
         msg = (
-            "cannot assemble the datetimes: time data .+ does not "
-            r"match format '%Y%m%d' \(match\)"
+            r'^cannot assemble the datetimes: time data ".+" at position 1 doesn\'t '
+            r'match format "%Y%m%d" \(match\)$'
         )
         with pytest.raises(ValueError, match=msg):
             to_datetime(df2, cache=cache)
@@ -1885,7 +1886,10 @@ def test_dataframe_mixed(self, cache):
     def test_dataframe_float(self, cache):
         # float
         df = DataFrame({"year": [2000, 2001], "month": [1.5, 1], "day": [1, 1]})
-        msg = "cannot assemble the datetimes: unconverted data remains: 1"
+        msg = (
+            r"^cannot assemble the datetimes: unconverted data remains at position "
+            r'0: "1"$'
+        )
         with pytest.raises(ValueError, match=msg):
             to_datetime(df, cache=cache)
 
@@ -2076,7 +2080,7 @@ def test_to_datetime_with_space_in_series(self, cache):
         # GH 6428
         ser = Series(["10/18/2006", "10/18/2008", " "])
         msg = (
-            r"^time data ' ' does not match format '%m/%d/%Y' \(match\) at position 2$"
+            r'^time data " " at position 2 doesn\'t match format "%m/%d/%Y" \(match\)$'
         )
         with pytest.raises(ValueError, match=msg):
             to_datetime(ser, errors="raise", cache=cache)
@@ -2348,8 +2352,8 @@ def test_dayfirst_warnings_invalid_input(self):
         with pytest.raises(
             ValueError,
             match=(
-                r"time data '03/30/2011' does not match format '%d/%m/%Y' "
-                r"\(match\) at position 1$"
+                r'^time data "03/30/2011" at position 1 doesn\'t match format '
+                r'"%d/%m/%Y" \(match\)$'
             ),
         ):
             to_datetime(arr, dayfirst=True)
@@ -2418,7 +2422,11 @@ def test_to_datetime_infer_datetime_format_consistent_format(
     def test_to_datetime_inconsistent_format(self, cache):
         data = ["01/01/2011 00:00:00", "01-02-2011 00:00:00", "2011-01-03T00:00:00"]
         ser = Series(np.array(data))
-        with pytest.raises(ValueError, match="does not match format"):
+        msg = (
+            r'^time data "01-02-2011 00:00:00" at position 1 doesn\'t match format '
+            r'"%m/%d/%Y %H:%M:%S" \(match\)$'
+        )
+        with pytest.raises(ValueError, match=msg):
             to_datetime(ser, cache=cache)
 
     def test_to_datetime_consistent_format(self, cache):

From 9040dcaf41300eebba9bb8c184dea759f61a8db9 Mon Sep 17 00:00:00 2001
From: MarcoGorelli <>
Date: Wed, 21 Dec 2022 10:33:36 +0000
Subject: [PATCH 3/7] fixup regexes

---
 pandas/tests/tools/test_to_datetime.py | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/pandas/tests/tools/test_to_datetime.py b/pandas/tests/tools/test_to_datetime.py
index e9a318b908767..7e0b7a22ed978 100644
--- a/pandas/tests/tools/test_to_datetime.py
+++ b/pandas/tests/tools/test_to_datetime.py
@@ -480,8 +480,8 @@ def test_to_datetime_parse_timezone_malformed(self, offset):
         date = "2010-01-01 12:00:00 " + offset
 
         msg = (
-            r'time data ".*" at position 0 doesn\'t match format ".*" \(match\)|'
-            r'unconverted data remains at position 0: ".*"'
+            r'^(time data ".*" at position 0 doesn\'t match format ".*" \(match\)|'
+            r'unconverted data remains at position 0: ".*")$'
         )
         with pytest.raises(ValueError, match=msg):
             to_datetime([date], format=fmt)
@@ -1139,8 +1139,10 @@ def test_datetime_invalid_scalar(self, value, format, warning):
         assert res is NaT
 
         msg = (
-            r'^time data "a" at position 0 doesn\'t match format "%H:%M:%S" \(match\)$|'
-            r'^Given date string "a" not likely a datetime$|'
+            r'^(time data "a" at position 0 doesn\'t match format "%H:%M:%S" \(match\)|'
+            r'Given date string "a" not likely a datetime present at position 0|'
+            r'unconverted data remains at position 0: "9"|'
+            r"second must be in 0..59: 00:01:99 present at position 0)$"
         )
         with pytest.raises(ValueError, match=msg):
             with tm.assert_produces_warning(warning, match="Could not infer format"):
@@ -2949,8 +2951,8 @@ def test_incorrect_value_exception(self):
     def test_to_datetime_out_of_bounds_with_format_arg(self, format, warning):
         # see gh-23830
         msg = (
-            r"Out of bounds nanosecond timestamp: 2417-10-10 00:00:00"
-            r".* at position 0"
+            r"^Out of bounds nanosecond timestamp: 2417-10-10 00:00:00"
+            r".* at position 0$"
         )
         with pytest.raises(OutOfBoundsDatetime, match=msg):
             with tm.assert_produces_warning(warning, match="Could not infer format"):

From c49640d51da23769faff471ba833ec5e6ef10779 Mon Sep 17 00:00:00 2001
From: MarcoGorelli <>
Date: Wed, 21 Dec 2022 10:36:41 +0000
Subject: [PATCH 4/7] simplify

---
 pandas/tests/tools/test_to_datetime.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pandas/tests/tools/test_to_datetime.py b/pandas/tests/tools/test_to_datetime.py
index 7e0b7a22ed978..febb35aa97d79 100644
--- a/pandas/tests/tools/test_to_datetime.py
+++ b/pandas/tests/tools/test_to_datetime.py
@@ -2951,8 +2951,8 @@ def test_incorrect_value_exception(self):
     def test_to_datetime_out_of_bounds_with_format_arg(self, format, warning):
         # see gh-23830
         msg = (
-            r"^Out of bounds nanosecond timestamp: 2417-10-10 00:00:00"
-            r".* at position 0$"
+            r"^Out of bounds nanosecond timestamp: 2417-10-10 00:00:00 "
+            r"present at position 0$"
         )
         with pytest.raises(OutOfBoundsDatetime, match=msg):
             with tm.assert_produces_warning(warning, match="Could not infer format"):

From 1e7613f1e8db27d93a26840ee3fa908e05e0b310 Mon Sep 17 00:00:00 2001
From: MarcoGorelli <>
Date: Wed, 21 Dec 2022 11:23:39 +0000
Subject: [PATCH 5/7] fix test

---
 pandas/tests/scalar/period/test_period.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pandas/tests/scalar/period/test_period.py b/pandas/tests/scalar/period/test_period.py
index 112f23b3b0f16..0636ecb023530 100644
--- a/pandas/tests/scalar/period/test_period.py
+++ b/pandas/tests/scalar/period/test_period.py
@@ -303,7 +303,7 @@ def test_invalid_arguments(self):
         with pytest.raises(ValueError, match=msg):
             Period(month=1)
 
-        msg = "Given date string -2000 not likely a datetime"
+        msg = '^Given date string "-2000" not likely a datetime$'
         with pytest.raises(ValueError, match=msg):
             Period("-2000", "A")
         msg = "day is out of range for month"

From 3338b431253e6b1c3aae9eb3adea2370574bb487 Mon Sep 17 00:00:00 2001
From: MarcoGorelli <>
Date: Thu, 22 Dec 2022 09:27:57 +0000
Subject: [PATCH 6/7] remove (search) and (match) from messages

---
 pandas/_libs/tslib.pyx                     |  6 +--
 pandas/_libs/tslibs/strptime.pyx           |  4 +-
 pandas/tests/io/parser/test_parse_dates.py |  3 +-
 pandas/tests/tools/test_to_datetime.py     | 49 +++++++++++-----------
 4 files changed, 30 insertions(+), 32 deletions(-)

diff --git a/pandas/_libs/tslib.pyx b/pandas/_libs/tslib.pyx
index ac1679ef66bc7..c1a30e03235b5 100644
--- a/pandas/_libs/tslib.pyx
+++ b/pandas/_libs/tslib.pyx
@@ -515,10 +515,9 @@ cpdef array_to_datetime(
                             iresult[i] = NPY_NAT
                             continue
                         elif is_raise:
-                            match_msg = "match" if exact else "search"
                             raise ValueError(
                                 f"time data \"{val}\" at position {i} doesn't "
-                                f"match format \"{format}\" ({match_msg})"
+                                f"match format \"{format}\""
                             )
                         return values, tz_out
                     # these must be ns unit by-definition
@@ -565,10 +564,9 @@ cpdef array_to_datetime(
                                 iresult[i] = NPY_NAT
                                 continue
                             elif is_raise:
-                                match_msg = "match" if exact else "search"
                                 raise ValueError(
                                     f"time data \"{val}\" at position {i} doesn't "
-                                    f"match format \"{format}\" ({match_msg})"
+                                    f"match format \"{format}\""
                                 )
                             return values, tz_out
 
diff --git a/pandas/_libs/tslibs/strptime.pyx b/pandas/_libs/tslibs/strptime.pyx
index 196fbd40f0a02..72205599e8108 100644
--- a/pandas/_libs/tslibs/strptime.pyx
+++ b/pandas/_libs/tslibs/strptime.pyx
@@ -237,7 +237,7 @@ def array_strptime(
                 found = format_regex.match(val)
                 if not found:
                     raise ValueError(f"time data \"{val}\" at position {i} doesn't "
-                                     f"match format \"{fmt}\" (match)")
+                                     f"match format \"{fmt}\"")
                 if len(val) != found.end():
                     raise ValueError(
                         f"unconverted data remains at position {i}: "
@@ -250,7 +250,7 @@ def array_strptime(
                 if not found:
                     raise ValueError(
                         f"time data \"{val}\" at position {i} doesn't match "
-                        f"format \"{fmt}\" (search)"
+                        f"format \"{fmt}\""
                     )
 
             iso_year = -1
diff --git a/pandas/tests/io/parser/test_parse_dates.py b/pandas/tests/io/parser/test_parse_dates.py
index bf881eb928c2d..597ecc877e30c 100644
--- a/pandas/tests/io/parser/test_parse_dates.py
+++ b/pandas/tests/io/parser/test_parse_dates.py
@@ -1719,8 +1719,7 @@ def test_parse_multiple_delimited_dates_with_swap_warnings():
     with pytest.raises(
         ValueError,
         match=(
-            r'^time data "31/05/2000" at position 1 doesn\'t match format "%m/%d/%Y" '
-            r"\(match\)$"
+            r'^time data "31/05/2000" at position 1 doesn\'t match format "%m/%d/%Y"$'
         ),
     ):
         pd.to_datetime(["01/01/2000", "31/05/2000", "31/05/2001", "01/02/2000"])
diff --git a/pandas/tests/tools/test_to_datetime.py b/pandas/tests/tools/test_to_datetime.py
index febb35aa97d79..927388408cf27 100644
--- a/pandas/tests/tools/test_to_datetime.py
+++ b/pandas/tests/tools/test_to_datetime.py
@@ -479,9 +479,11 @@ def test_to_datetime_parse_timezone_malformed(self, offset):
         fmt = "%Y-%m-%d %H:%M:%S %z"
         date = "2010-01-01 12:00:00 " + offset
 
-        msg = (
-            r'^(time data ".*" at position 0 doesn\'t match format ".*" \(match\)|'
-            r'unconverted data remains at position 0: ".*")$'
+        msg = "|".join(
+            [
+                r'^time data ".*" at position 0 doesn\'t match format ".*"$',
+                r'^unconverted data remains at position 0: ".*"$',
+            ]
         )
         with pytest.raises(ValueError, match=msg):
             to_datetime([date], format=fmt)
@@ -1096,10 +1098,7 @@ def test_datetime_bool_arrays_mixed(self, cache):
             to_datetime([False, datetime.today()], cache=cache)
         with pytest.raises(
             ValueError,
-            match=(
-                r'^time data "True" at position 1 doesn\'t match format "%Y%m%d" '
-                r"\(match\)$"
-            ),
+            match=r'^time data "True" at position 1 doesn\'t match format "%Y%m%d"$',
         ):
             to_datetime(["20130101", True], cache=cache)
         tm.assert_index_equal(
@@ -1138,11 +1137,13 @@ def test_datetime_invalid_scalar(self, value, format, warning):
             res = to_datetime(value, errors="coerce", format=format)
         assert res is NaT
 
-        msg = (
-            r'^(time data "a" at position 0 doesn\'t match format "%H:%M:%S" \(match\)|'
-            r'Given date string "a" not likely a datetime present at position 0|'
-            r'unconverted data remains at position 0: "9"|'
-            r"second must be in 0..59: 00:01:99 present at position 0)$"
+        msg = "|".join(
+            [
+                r'^time data "a" at position 0 doesn\'t match format "%H:%M:%S"$',
+                r'^Given date string "a" not likely a datetime present at position 0$',
+                r'^unconverted data remains at position 0: "9"$',
+                r"^second must be in 0..59: 00:01:99 present at position 0$",
+            ]
         )
         with pytest.raises(ValueError, match=msg):
             with tm.assert_produces_warning(warning, match="Could not infer format"):
@@ -1163,7 +1164,7 @@ def test_datetime_outofbounds_scalar(self, value, format, warning):
         assert res is NaT
 
         if format is not None:
-            msg = r'^time data ".*" at position 0 doesn\'t match format ".*" \(match\)$'
+            msg = r'^time data ".*" at position 0 doesn\'t match format ".*"$'
             with pytest.raises(ValueError, match=msg):
                 to_datetime(value, errors="raise", format=format)
         else:
@@ -1187,11 +1188,13 @@ def test_datetime_invalid_index(self, values, format, warning):
             res = to_datetime(values, errors="coerce", format=format)
         tm.assert_index_equal(res, DatetimeIndex([NaT] * len(values)))
 
-        msg = (
-            r'^(Given date string "a" not likely a datetime present at position 0|'
-            r'time data "a" at position 0 doesn\'t match format "%H:%M:%S" \(match\)|'
-            r'unconverted data remains at position 0: "9"|'
-            r"second must be in 0..59: 00:01:99 present at position 0)$"
+        msg = "|".join(
+            [
+                r'^Given date string "a" not likely a datetime present at position 0$',
+                r'^time data "a" at position 0 doesn\'t match format "%H:%M:%S"$',
+                r'^unconverted data remains at position 0: "9"$',
+                r"^second must be in 0..59: 00:01:99 present at position 0$",
+            ]
         )
         with pytest.raises(ValueError, match=msg):
             with tm.assert_produces_warning(warning, match="Could not infer format"):
@@ -1812,7 +1815,7 @@ def test_dataframe_coerce(self, cache):
 
         msg = (
             r'^cannot assemble the datetimes: time data ".+" at position 1 doesn\'t '
-            r'match format "%Y%m%d" \(match\)$'
+            r'match format "%Y%m%d"$'
         )
         with pytest.raises(ValueError, match=msg):
             to_datetime(df2, cache=cache)
@@ -2081,9 +2084,7 @@ def test_to_datetime_on_datetime64_series(self, cache):
     def test_to_datetime_with_space_in_series(self, cache):
         # GH 6428
         ser = Series(["10/18/2006", "10/18/2008", " "])
-        msg = (
-            r'^time data " " at position 2 doesn\'t match format "%m/%d/%Y" \(match\)$'
-        )
+        msg = r'^time data " " at position 2 doesn\'t match format "%m/%d/%Y"$'
         with pytest.raises(ValueError, match=msg):
             to_datetime(ser, errors="raise", cache=cache)
         result_coerce = to_datetime(ser, errors="coerce", cache=cache)
@@ -2355,7 +2356,7 @@ def test_dayfirst_warnings_invalid_input(self):
             ValueError,
             match=(
                 r'^time data "03/30/2011" at position 1 doesn\'t match format '
-                r'"%d/%m/%Y" \(match\)$'
+                r'"%d/%m/%Y"$'
             ),
         ):
             to_datetime(arr, dayfirst=True)
@@ -2426,7 +2427,7 @@ def test_to_datetime_inconsistent_format(self, cache):
         ser = Series(np.array(data))
         msg = (
             r'^time data "01-02-2011 00:00:00" at position 1 doesn\'t match format '
-            r'"%m/%d/%Y %H:%M:%S" \(match\)$'
+            r'"%m/%d/%Y %H:%M:%S"$'
         )
         with pytest.raises(ValueError, match=msg):
             to_datetime(ser, cache=cache)

From 34a7138f2de2e0f8b589e5fce47bcb7f9385428c Mon Sep 17 00:00:00 2001
From: MarcoGorelli <>
Date: Sat, 24 Dec 2022 17:06:14 +0000
Subject: [PATCH 7/7] simplify

---
 pandas/_libs/tslibs/strptime.pyx | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/pandas/_libs/tslibs/strptime.pyx b/pandas/_libs/tslibs/strptime.pyx
index 72205599e8108..c1bc5fd0910f8 100644
--- a/pandas/_libs/tslibs/strptime.pyx
+++ b/pandas/_libs/tslibs/strptime.pyx
@@ -401,15 +401,9 @@ def array_strptime(
 
             result_timezone[i] = tz
 
-        except OutOfBoundsDatetime as ex:
-            ex.args = (f"{str(ex)} present at position {i}",)
-            if is_coerce:
-                iresult[i] = NPY_NAT
-                continue
-            elif is_raise:
-                raise
-            return values, []
-        except ValueError:
+        except (ValueError, OutOfBoundsDatetime) as ex:
+            if isinstance(ex, OutOfBoundsDatetime):
+                ex.args = (f"{str(ex)} present at position {i}",)
             if is_coerce:
                 iresult[i] = NPY_NAT
                 continue