test non-padded

Author: MarcoGorelli

pandas/tests/tools/test_to_datetime.py

@@ -146,7 +146,8 @@ def test_to_datetime_format_YYYYMM_with_nat(self, cache):
         result = to_datetime(ser, format="%Y%m", cache=cache)
         tm.assert_series_equal(result, expected)
 
-    def test_to_datetime_format_YYYYMM_with_nat(self, cache):
+    def test_to_datetime_format_YYYYMM_with_nat_2(self, cache):
+        # is this different from above? can remove?
         # https://github.com/pandas-dev/pandas/issues/50237
         ser = Series([198012, 198012] + [198101] * 5)
         expected = Series(
@@ -1748,8 +1749,8 @@ 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 '.*' does not match "
+            r"format '%Y%m%d' \(match\)"
         )
         with pytest.raises(ValueError, match=msg):
             to_datetime(df2, cache=cache)
@@ -1825,10 +1826,7 @@ 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: time data "20000151" at position 0 '
-            'doesn\'t match format "%Y%m%d"'
-        )
+        msg = "cannot assemble the datetimes: unconverted data remains: 1"
         with pytest.raises(ValueError, match=msg):
             to_datetime(df, cache=cache)
 
@@ -1887,10 +1885,7 @@ def test_to_datetime_iso8601_fails(self, input, format, exact):
         # `format` is longer than the string, so this fails regardless of `exact`
         with pytest.raises(
             ValueError,
-            match=(
-                rf"time data \"{input}\" at position 0 doesn't match format "
-                rf"\"{format}\""
-            ),
+            match=(rf"time data '{input}' does not match format '{format}'"),
         ):
             to_datetime(input, format=format, exact=exact)
 
@@ -1909,10 +1904,7 @@ def test_to_datetime_iso8601_exact_fails(self, input, format):
         # `format` is shorter than the date string, so only fails with `exact=True`
         with pytest.raises(
             ValueError,
-            match=(
-                rf"time data \"{input}\" at position 0 doesn't match format "
-                rf"\"{format}\""
-            ),
+            match=("unconverted data remains: |does not match format"),
         ):
             to_datetime(input, format=format)
 
@@ -1948,10 +1940,7 @@ def test_to_datetime_iso8601_separator(self, input, format):
         # https://github.com/pandas-dev/pandas/issues/12649
         with pytest.raises(
             ValueError,
-            match=(
-                rf"time data \"{input}\" at position 0 doesn\'t match format "
-                rf"\"{format}\""
-            ),
+            match=(rf"time data \'{input}\' does not match format '{format}'"),
         ):
             to_datetime(input, format=format)
 
@@ -1977,6 +1966,28 @@ def test_to_datetime_iso8601_valid(self, input, format):
         result = to_datetime(input, format=format)
         assert result == expected
 
+    @pytest.mark.parametrize(
+        "input, format",
+        [
+            ("2020-1", "%Y-%m"),
+            ("2020-1-1", "%Y-%m-%d"),
+            ("2020-1-1 0", "%Y-%m-%d %H"),
+            ("2020-1-1T0", "%Y-%m-%dT%H"),
+            ("2020-1-1 0:0", "%Y-%m-%d %H:%M"),
+            ("2020-1-1T0:0", "%Y-%m-%dT%H:%M"),
+            ("2020-1-1 0:0:0", "%Y-%m-%d %H:%M:%S"),
+            ("2020-1-1T0:0:0", "%Y-%m-%dT%H:%M:%S"),
+            ("2020-1-1T0:0:0.000", "%Y-%m-%dT%H:%M:%S.%f"),
+            ("2020-1-1T0:0:0.000000", "%Y-%m-%dT%H:%M:%S.%f"),
+            ("2020-1-1T0:0:0.000000000", "%Y-%m-%dT%H:%M:%S.%f"),
+        ],
+    )
+    def test_to_datetime_iso8601_non_padded(self, input, format):
+        # https://github.com/pandas-dev/pandas/issues/21422
+        expected = Timestamp(2020, 1, 1)
+        result = to_datetime(input, format=format)
+        assert result == expected
+
     @pytest.mark.parametrize(
         "input, format",
         [
@@ -2479,7 +2490,7 @@ 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 = "day is out of range for month|unconverted data remains"
         with pytest.raises(ValueError, match=msg):
             to_datetime(arg, errors="raise", format="%Y-%m-%d", cache=cache)