ERR: "day out of range" doesn't show position of error (#50464)

* show position of error if out-of-bounds non-ISO

* fixup some more tests

Co-authored-by: MarcoGorelli <>

Author: MarcoGorelli

pandas/_libs/tslib.pyx

@@ -550,8 +550,8 @@ cpdef array_to_datetime(
                             continue
                         elif is_raise:
                             raise ValueError(
-                                f"time data \"{val}\" at position {i} doesn't "
-                                f"match format \"{format}\""
+                                f"time data \"{val}\" doesn't "
+                                f"match format \"{format}\", at position {i}"
                             )
                         return values, tz_out
                     # these must be ns unit by-definition
@@ -599,8 +599,8 @@ cpdef array_to_datetime(
                                 continue
                             elif is_raise:
                                 raise ValueError(
-                                    f"time data \"{val}\" at position {i} doesn't "
-                                    f"match format \"{format}\""
+                                    f"time data \"{val}\" doesn't "
+                                    f"match format \"{format}\", at position {i}"
                                 )
                             return values, tz_out
 
@@ -617,8 +617,8 @@ cpdef array_to_datetime(
                                 iresult[i] = NPY_NAT
                                 continue
                             raise TypeError(
-                                f"invalid string coercion to datetime for \"{val}\" "
-                                f"at position {i}"
+                                f"invalid string coercion to datetime "
+                                f"for \"{val}\", at position {i}"
                             )
 
                         if tz is not None:
@@ -661,7 +661,7 @@ cpdef array_to_datetime(
                         raise TypeError(f"{type(val)} is not convertible to datetime")
 
             except OutOfBoundsDatetime as ex:
-                ex.args = (str(ex) + f" present at position {i}", )
+                ex.args = (f"{ex}, at position {i}",)
                 if is_coerce:
                     iresult[i] = NPY_NAT
                     continue
@@ -821,7 +821,7 @@ cdef _array_to_datetime_object(
                 pydatetime_to_dt64(oresult[i], &dts)
                 check_dts_bounds(&dts)
             except (ValueError, OverflowError) as ex:
-                ex.args = (f"{ex} present at position {i}", )
+                ex.args = (f"{ex}, at position {i}", )
                 if is_coerce:
                     oresult[i] = <object>NaT
                     continue

pandas/_libs/tslibs/strptime.pyx

@@ -236,11 +236,11 @@ def array_strptime(
             if exact:
                 found = format_regex.match(val)
                 if not found:
-                    raise ValueError(f"time data \"{val}\" at position {i} doesn't "
+                    raise ValueError(f"time data \"{val}\" doesn't "
                                      f"match format \"{fmt}\"")
                 if len(val) != found.end():
                     raise ValueError(
-                        f"unconverted data remains at position {i}: "
+                        f"unconverted data remains: "
                         f'"{val[found.end():]}"'
                     )
 
@@ -249,7 +249,7 @@ def array_strptime(
                 found = format_regex.search(val)
                 if not found:
                     raise ValueError(
-                        f"time data \"{val}\" at position {i} doesn't match "
+                        f"time data \"{val}\" doesn't match "
                         f"format \"{fmt}\""
                     )
 
@@ -402,8 +402,7 @@ def array_strptime(
             result_timezone[i] = tz
 
         except (ValueError, OutOfBoundsDatetime) as ex:
-            if isinstance(ex, OutOfBoundsDatetime):
-                ex.args = (f"{str(ex)} present at position {i}",)
+            ex.args = (f"{str(ex)}, at position {i}",)
             if is_coerce:
                 iresult[i] = NPY_NAT
                 continue

pandas/tests/frame/test_block_internals.py

@@ -259,7 +259,7 @@ def f(dtype):
             f("float64")
 
         # 10822
-        msg = "Unknown string format: aa present at position 0"
+        msg = "^Unknown string format: aa, at position 0$"
         with pytest.raises(ValueError, match=msg):
             f("M8[ns]")
 

pandas/tests/indexes/datetimes/test_constructors.py

@@ -547,7 +547,7 @@ def test_construction_outofbounds(self):
         # coerces to object
         tm.assert_index_equal(Index(dates), exp)
 
-        msg = "Out of bounds .* present at position 0"
+        msg = "^Out of bounds nanosecond timestamp: 3000-01-01 00:00:00, at position 0$"
         with pytest.raises(OutOfBoundsDatetime, match=msg):
             # can't create DatetimeIndex
             DatetimeIndex(dates)

pandas/tests/indexes/datetimes/test_scalar_compat.py

@@ -38,7 +38,7 @@ def test_dti_date(self):
     @pytest.mark.parametrize("data", [["1400-01-01"], [datetime(1400, 1, 1)]])
     def test_dti_date_out_of_range(self, data):
         # GH#1475
-        msg = "Out of bounds .* present at position 0"
+        msg = "^Out of bounds nanosecond timestamp: 1400-01-01 00:00:00, at position 0$"
         with pytest.raises(OutOfBoundsDatetime, match=msg):
             DatetimeIndex(data)
 

pandas/tests/io/parser/test_parse_dates.py

@@ -1721,7 +1721,7 @@ 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"$'
+            r'^time data "31/05/2000" doesn\'t match format "%m/%d/%Y", at position 1$'
         ),
     ):
         pd.to_datetime(["01/01/2000", "31/05/2000", "31/05/2001", "01/02/2000"])

pandas/tests/series/test_constructors.py

@@ -76,7 +76,7 @@ def test_infer_with_date_and_datetime(self):
     def test_unparseable_strings_with_dt64_dtype(self):
         # pre-2.0 these would be silently ignored and come back with object dtype
         vals = ["aa"]
-        msg = "Unknown string format: aa present at position 0"
+        msg = "^Unknown string format: aa, at position 0$"
         with pytest.raises(ValueError, match=msg):
             Series(vals, dtype="datetime64[ns]")
 

pandas/tests/tools/test_to_datetime.py

@@ -480,8 +480,8 @@ def test_to_datetime_parse_timezone_malformed(self, offset):
 
         msg = "|".join(
             [
-                r'^time data ".*" at position 0 doesn\'t match format ".*"$',
-                r'^unconverted data remains at position 0: ".*"$',
+                r'^time data ".*" doesn\'t match format ".*", at position 0$',
+                r'^unconverted data remains: ".*", at position 0$',
             ]
         )
         with pytest.raises(ValueError, match=msg):
@@ -858,7 +858,7 @@ def test_to_datetime_dt64s_and_str(self, arg, format):
         "dt", [np.datetime64("1000-01-01"), np.datetime64("5000-01-02")]
     )
     def test_to_datetime_dt64s_out_of_bounds(self, cache, dt):
-        msg = "Out of bounds .* present at position 0"
+        msg = "^Out of bounds nanosecond timestamp: .*, at position 0$"
         with pytest.raises(OutOfBoundsDatetime, match=msg):
             to_datetime(dt, errors="raise")
 
@@ -1097,7 +1097,7 @@ 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"$',
+            match=r'^time data "True" doesn\'t match format "%Y%m%d", at position 1$',
         ):
             to_datetime(["20130101", True], cache=cache)
         tm.assert_index_equal(
@@ -1138,10 +1138,10 @@ def test_datetime_invalid_scalar(self, value, format, warning):
 
         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"$',
-                r"^second must be in 0..59: 00:01:99 present at position 0$",
+                r'^time data "a" doesn\'t match format "%H:%M:%S", at position 0$',
+                r'^Given date string "a" not likely a datetime, at position 0$',
+                r'^unconverted data remains: "9", at position 0$',
+                r"^second must be in 0..59: 00:01:99, at position 0$",
             ]
         )
         with pytest.raises(ValueError, match=msg):
@@ -1163,11 +1163,11 @@ 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 ".*"$'
+            msg = r'^time data ".*" doesn\'t match format ".*", at position 0$'
             with pytest.raises(ValueError, match=msg):
                 to_datetime(value, errors="raise", format=format)
         else:
-            msg = "Out of bounds .* present at position 0"
+            msg = "^Out of bounds .*, at position 0$"
             with pytest.raises(
                 OutOfBoundsDatetime, match=msg
             ), tm.assert_produces_warning(warning, match="Could not infer format"):
@@ -1189,10 +1189,10 @@ def test_datetime_invalid_index(self, values, format, warning):
 
         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"$',
-                r"^second must be in 0..59: 00:01:99 present at position 0$",
+                r'^Given date string "a" not likely a datetime, at position 0$',
+                r'^time data "a" doesn\'t match format "%H:%M:%S", at position 0$',
+                r'^unconverted data remains: "9", at position 0$',
+                r"^second must be in 0..59: 00:01:99, at position 0$",
             ]
         )
         with pytest.raises(ValueError, match=msg):
@@ -1372,7 +1372,7 @@ def test_to_datetime_malformed_raise(self):
         ts_strings = ["200622-12-31", "111111-24-11"]
         with pytest.raises(
             ValueError,
-            match=r"^hour must be in 0\.\.23: 111111-24-11 present at position 1$",
+            match=r"^hour must be in 0\.\.23: 111111-24-11, at position 1$",
         ):
             with tm.assert_produces_warning(
                 UserWarning, match="Could not infer format"
@@ -1845,8 +1845,8 @@ def test_dataframe_coerce(self, cache):
         df2 = DataFrame({"year": [2015, 2016], "month": [2, 20], "day": [4, 5]})
 
         msg = (
-            r'^cannot assemble the datetimes: time data ".+" at position 1 doesn\'t '
-            r'match format "%Y%m%d"$'
+            r'^cannot assemble the datetimes: time data ".+" doesn\'t '
+            r'match format "%Y%m%d", at position 1$'
         )
         with pytest.raises(ValueError, match=msg):
             to_datetime(df2, cache=cache)
@@ -1923,8 +1923,8 @@ def test_dataframe_float(self, cache):
         # float
         df = DataFrame({"year": [2000, 2001], "month": [1.5, 1], "day": [1, 1]})
         msg = (
-            r"^cannot assemble the datetimes: unconverted data remains at position "
-            r'0: "1"$'
+            r"^cannot assemble the datetimes: unconverted data remains: "
+            r'"1", at position 0$'
         )
         with pytest.raises(ValueError, match=msg):
             to_datetime(df, cache=cache)
@@ -1946,7 +1946,7 @@ def test_to_datetime_barely_out_of_bounds(self):
         # in an in-bounds datetime
         arr = np.array(["2262-04-11 23:47:16.854775808"], dtype=object)
 
-        msg = "Out of bounds .* present at position 0"
+        msg = "^Out of bounds nanosecond timestamp: .*, at position 0"
         with pytest.raises(OutOfBoundsDatetime, match=msg):
             with tm.assert_produces_warning(
                 UserWarning, match="Could not infer format"
@@ -1985,8 +1985,8 @@ def test_to_datetime_iso8601_fails(self, input, format, exact):
         with pytest.raises(
             ValueError,
             match=(
-                rf"time data \"{input}\" at position 0 doesn't match format "
-                rf"\"{format}\""
+                rf"time data \"{input}\" doesn't match format "
+                rf"\"{format}\", at position 0"
             ),
         ):
             to_datetime(input, format=format, exact=exact)
@@ -2007,8 +2007,8 @@ def test_to_datetime_iso8601_exact_fails(self, input, format):
         with pytest.raises(
             ValueError,
             match=(
-                rf"time data \"{input}\" at position 0 doesn't match format "
-                rf"\"{format}\""
+                rf"time data \"{input}\" doesn't match format "
+                rf"\"{format}\", at position 0"
             ),
         ):
             to_datetime(input, format=format)
@@ -2046,8 +2046,8 @@ def test_to_datetime_iso8601_separator(self, input, format):
         with pytest.raises(
             ValueError,
             match=(
-                rf"time data \"{input}\" at position 0 doesn\'t match format "
-                rf"\"{format}\""
+                rf"time data \"{input}\" doesn\'t match format "
+                rf"\"{format}\", at position 0"
             ),
         ):
             to_datetime(input, format=format)
@@ -2115,7 +2115,7 @@ 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"$'
+        msg = r'^time data " " doesn\'t match format "%m/%d/%Y", at position 2$'
         with pytest.raises(ValueError, match=msg):
             to_datetime(ser, errors="raise", cache=cache)
         result_coerce = to_datetime(ser, errors="coerce", cache=cache)
@@ -2386,8 +2386,8 @@ def test_dayfirst_warnings_invalid_input(self):
         with pytest.raises(
             ValueError,
             match=(
-                r'^time data "03/30/2011" at position 1 doesn\'t match format '
-                r'"%d/%m/%Y"$'
+                r'^time data "03/30/2011" doesn\'t match format '
+                r'"%d/%m/%Y", at position 1$'
             ),
         ):
             to_datetime(arr, dayfirst=True)
@@ -2457,8 +2457,8 @@ 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))
         msg = (
-            r'^time data "01-02-2011 00:00:00" at position 1 doesn\'t match format '
-            r'"%m/%d/%Y %H:%M:%S"$'
+            r'^time data "01-02-2011 00:00:00" doesn\'t match format '
+            r'"%m/%d/%Y %H:%M:%S", at position 1$'
         )
         with pytest.raises(ValueError, match=msg):
             to_datetime(ser, cache=cache)
@@ -2581,11 +2581,49 @@ def test_day_not_in_month_raise(self, cache):
             ):
                 to_datetime("2015-02-29", errors="raise", cache=cache)
 
-    @pytest.mark.parametrize("arg", ["2015-02-29", "2015-02-32", "2015-04-31"])
-    def test_day_not_in_month_raise_value(self, cache, arg):
-        msg = f'time data "{arg}" at position 0 doesn\'t match format "%Y-%m-%d"'
+    @pytest.mark.parametrize(
+        "arg, format, msg",
+        [
+            (
+                "2015-02-29",
+                "%Y-%m-%d",
+                '^time data "2015-02-29" doesn\'t match format "%Y-%m-%d", '
+                "at position 0$",
+            ),
+            (
+                "2015-29-02",
+                "%Y-%d-%m",
+                "^day is out of range for month, at position 0$",
+            ),
+            (
+                "2015-02-32",
+                "%Y-%m-%d",
+                '^time data "2015-02-32" doesn\'t match format "%Y-%m-%d", '
+                "at position 0$",
+            ),
+            (
+                "2015-32-02",
+                "%Y-%d-%m",
+                '^time data "2015-32-02" doesn\'t match format "%Y-%d-%m", '
+                "at position 0$",
+            ),
+            (
+                "2015-04-31",
+                "%Y-%m-%d",
+                '^time data "2015-04-31" doesn\'t match format "%Y-%m-%d", '
+                "at position 0$",
+            ),
+            (
+                "2015-31-04",
+                "%Y-%d-%m",
+                "^day is out of range for month, at position 0$",
+            ),
+        ],
+    )
+    def test_day_not_in_month_raise_value(self, cache, arg, format, msg):
+        # https://github.com/pandas-dev/pandas/issues/50462
         with pytest.raises(ValueError, match=msg):
-            to_datetime(arg, errors="raise", format="%Y-%m-%d", cache=cache)
+            to_datetime(arg, errors="raise", format=format, cache=cache)
 
     @pytest.mark.parametrize(
         "expected, format, warning",
@@ -2965,7 +3003,7 @@ def test_invalid_origins_tzinfo(self):
     def test_incorrect_value_exception(self):
         # GH47495
         with pytest.raises(
-            ValueError, match="Unknown string format: yesterday present at position 1"
+            ValueError, match="Unknown string format: yesterday, at position 1"
         ):
             with tm.assert_produces_warning(
                 UserWarning, match="Could not infer format"
@@ -2983,8 +3021,7 @@ 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"present at position 0$"
+            r"^Out of bounds nanosecond timestamp: 2417-10-10 00:00:00, at position 0$"
         )
         with pytest.raises(OutOfBoundsDatetime, match=msg):
             with tm.assert_produces_warning(warning, match="Could not infer format"):

pandas/tests/tslibs/test_array_to_datetime.py

@@ -126,7 +126,7 @@ def test_coerce_outside_ns_bounds(invalid_date, errors):
     kwargs = {"values": arr, "errors": errors}
 
     if errors == "raise":
-        msg = "Out of bounds .* present at position 0"
+        msg = "^Out of bounds nanosecond timestamp: .*, at position 0$"
 
         with pytest.raises(ValueError, match=msg):
             tslib.array_to_datetime(**kwargs)
@@ -171,9 +171,7 @@ def test_to_datetime_barely_out_of_bounds():
     # Close enough to bounds that dropping nanos
     # would result in an in-bounds datetime.
     arr = np.array(["2262-04-11 23:47:16.854775808"], dtype=object)
-    msg = (
-        "Out of bounds nanosecond timestamp: 2262-04-11 23:47:16 present at position 0"
-    )
+    msg = "^Out of bounds nanosecond timestamp: 2262-04-11 23:47:16, at position 0$"
 
     with pytest.raises(tslib.OutOfBoundsDatetime, match=msg):
         tslib.array_to_datetime(arr)