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

Author: MarcoGorelli

pandas/_libs/tslib.pyx

@@ -508,7 +508,7 @@ cpdef array_to_datetime(
                             continue
                         elif is_raise:
                             raise ValueError(
-                                f"time data \"{val}\" at position {i} doesn't "
+                                f"at position {i}: time data \"{val}\" doesn't "
                                 f"match format \"{format}\""
                             )
                         return values, tz_out
@@ -557,7 +557,7 @@ cpdef array_to_datetime(
                                 continue
                             elif is_raise:
                                 raise ValueError(
-                                    f"time data \"{val}\" at position {i} doesn't "
+                                    f"at position {i}: time data \"{val}\" doesn't "
                                     f"match format \"{format}\""
                                 )
                             return values, tz_out
@@ -575,8 +575,8 @@ cpdef array_to_datetime(
                                 iresult[i] = NPY_NAT
                                 continue
                             raise TypeError(
-                                f"invalid string coercion to datetime for \"{val}\" "
-                                f"at position {i}"
+                                f"at position {i}: invalid string coercion to datetime "
+                                f"for \"{val}\""
                             )
 
                         if tz is not None:
@@ -619,7 +619,7 @@ 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"at position {i}: {str(ex)}",)
                 if is_coerce:
                     iresult[i] = NPY_NAT
                     continue
@@ -779,7 +779,7 @@ 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"at position {i}: {ex}", )
                 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"at position {i}: {str(ex)}",)
             if is_coerce:
                 iresult[i] = NPY_NAT
                 continue

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

pandas/tests/tools/test_to_datetime.py

@@ -481,8 +481,8 @@ 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'^at position 0: time data ".*" doesn\'t match format ".*"$',
+                r'^at position 0: unconverted data remains: ".*"$',
             ]
         )
         with pytest.raises(ValueError, match=msg):
@@ -859,7 +859,7 @@ 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 = "^at position 0: Out of bounds nanosecond timestamp: .*$"
         with pytest.raises(OutOfBoundsDatetime, match=msg):
             to_datetime(dt, errors="raise")
 
@@ -1098,7 +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"$',
+            match=r'^at position 1: time data "True" doesn\'t match format "%Y%m%d"$',
         ):
             to_datetime(["20130101", True], cache=cache)
         tm.assert_index_equal(
@@ -1139,10 +1139,10 @@ 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'^at position 0: time data "a" doesn\'t match format "%H:%M:%S"$',
+                r'^at position 0: Given date string "a" not likely a datetime$',
+                r'^at position 0: unconverted data remains: "9"$',
+                r"^at position 0: second must be in 0..59: 00:01:99$",
             ]
         )
         with pytest.raises(ValueError, match=msg):
@@ -1164,11 +1164,11 @@ 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 ".*"$'
+            msg = r'^at position 0: time data ".*" doesn\'t match format ".*"$'
             with pytest.raises(ValueError, match=msg):
                 to_datetime(value, errors="raise", format=format)
         else:
-            msg = "Out of bounds .* present at position 0"
+            msg = "^at position 0: Out of bounds .*$"
             with pytest.raises(
                 OutOfBoundsDatetime, match=msg
             ), tm.assert_produces_warning(warning, match="Could not infer format"):
@@ -1190,10 +1190,10 @@ 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'^at position 0: Given date string "a" not likely a datetime$',
+                r'^at position 0: time data "a" doesn\'t match format "%H:%M:%S"$',
+                r'^at position 0: unconverted data remains: "9"$',
+                r"^at position 0: second must be in 0..59: 00:01:99$",
             ]
         )
         with pytest.raises(ValueError, match=msg):
@@ -1373,7 +1373,7 @@ 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$",
+            match=r"^at position 1: hour must be in 0\.\.23: 111111-24-11$",
         ):
             with tm.assert_produces_warning(
                 UserWarning, match="Could not infer format"
@@ -1814,7 +1814,7 @@ 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'^cannot assemble the datetimes: at position 1: time data ".+" doesn\'t '
             r'match format "%Y%m%d"$'
         )
         with pytest.raises(ValueError, match=msg):
@@ -1892,8 +1892,8 @@ def test_dataframe_float(self, cache):
         # float
         df = DataFrame({"year": [2000, 2001], "month": [1.5, 1], "day": [1, 1]})
         msg = (
-            r"^cannot assemble the datetimes: unconverted data remains at position "
-            r'0: "1"$'
+            r"^cannot assemble the datetimes: at position 0: unconverted data remains: "
+            r'"1"$'
         )
         with pytest.raises(ValueError, match=msg):
             to_datetime(df, cache=cache)
@@ -1915,7 +1915,7 @@ 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 = "^at position 0: Out of bounds .*$"
         with pytest.raises(OutOfBoundsDatetime, match=msg):
             with tm.assert_produces_warning(
                 UserWarning, match="Could not infer format"
@@ -1954,7 +1954,7 @@ def test_to_datetime_iso8601_fails(self, input, format, exact):
         with pytest.raises(
             ValueError,
             match=(
-                rf"time data \"{input}\" at position 0 doesn't match format "
+                rf"at position 0: time data \"{input}\" doesn't match format "
                 rf"\"{format}\""
             ),
         ):
@@ -1976,7 +1976,7 @@ def test_to_datetime_iso8601_exact_fails(self, input, format):
         with pytest.raises(
             ValueError,
             match=(
-                rf"time data \"{input}\" at position 0 doesn't match format "
+                rf"at position 0: time data \"{input}\" doesn't match format "
                 rf"\"{format}\""
             ),
         ):
@@ -2015,7 +2015,7 @@ def test_to_datetime_iso8601_separator(self, input, format):
         with pytest.raises(
             ValueError,
             match=(
-                rf"time data \"{input}\" at position 0 doesn\'t match format "
+                rf"at position 0: time data \"{input}\" doesn\'t match format "
                 rf"\"{format}\""
             ),
         ):
@@ -2084,7 +2084,7 @@ def test_to_datetime_on_datetime64_series(self, cache):
     def test_to_datetime_with_space_in_series(self, cache):
         # GH 6428
         ser = Series(["10/18/2006", "10/18/2008", " "])
-        msg = r'^time data " " at position 2 doesn\'t match format "%m/%d/%Y"$'
+        msg = r'^at position 2: time data " " doesn\'t match format "%m/%d/%Y"$'
         with pytest.raises(ValueError, match=msg):
             to_datetime(ser, errors="raise", cache=cache)
         result_coerce = to_datetime(ser, errors="coerce", cache=cache)
@@ -2355,7 +2355,7 @@ def test_dayfirst_warnings_invalid_input(self):
         with pytest.raises(
             ValueError,
             match=(
-                r'^time data "03/30/2011" at position 1 doesn\'t match format '
+                r'^at position 1: time data "03/30/2011" doesn\'t match format '
                 r'"%d/%m/%Y"$'
             ),
         ):
@@ -2426,7 +2426,7 @@ 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'^at position 1: time data "01-02-2011 00:00:00" doesn\'t match format '
             r'"%m/%d/%Y %H:%M:%S"$'
         )
         with pytest.raises(ValueError, match=msg):
@@ -2552,7 +2552,7 @@ def test_day_not_in_month_raise(self, 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"'
+        msg = f'at position 0: time data "{arg}" doesn\'t match format "%Y-%m-%d"'
         with pytest.raises(ValueError, match=msg):
             to_datetime(arg, errors="raise", format="%Y-%m-%d", cache=cache)
 
@@ -2934,7 +2934,7 @@ 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="at position 1: Unknown string format: yesterday"
         ):
             with tm.assert_produces_warning(
                 UserWarning, match="Could not infer format"
@@ -2952,8 +2952,7 @@ 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$"
+            r"^at position 0: Out of bounds nanosecond timestamp: 2417-10-10 00:00:00$"
         )
         with pytest.raises(OutOfBoundsDatetime, match=msg):
             with tm.assert_produces_warning(warning, match="Could not infer format"):