-
-
Notifications
You must be signed in to change notification settings - Fork 18.4k
ERR non-ISO formats don't show position of error #50366
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Changes from 4 commits
303a648
8e40df4
9040dca
c49640d
1e7613f
93c3026
3338b43
ba48f33
34a7138
8543fc9
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -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 | ||
|
@@ -396,7 +401,15 @@ def array_strptime( | |
|
||
result_timezone[i] = tz | ||
|
||
except (ValueError, OutOfBoundsDatetime): | ||
except OutOfBoundsDatetime as ex: | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Rather than breaking off this branch can we not keep the existing one and just specialize for the OOB exception within? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. you're right, that's better - thanks! |
||
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 | ||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -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) | ||
|
||
|
@@ -1093,7 +1096,10 @@ 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" at position 1 doesn\'t match format "%Y%m%d" ' | ||
r"\(match\)$" | ||
), | ||
): | ||
to_datetime(["20130101", True], cache=cache) | ||
tm.assert_index_equal( | ||
|
@@ -1133,10 +1139,10 @@ def test_datetime_invalid_scalar(self, value, format, warning): | |
assert res is NaT | ||
|
||
msg = ( | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. nitpick can you use |
||
"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 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"): | ||
|
@@ -1157,7 +1163,7 @@ 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: | ||
|
@@ -1182,10 +1188,10 @@ 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"): | ||
|
@@ -1805,8 +1811,8 @@ 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" \(match\)$' | ||
) | ||
with pytest.raises(ValueError, match=msg): | ||
to_datetime(df2, cache=cache) | ||
|
@@ -1882,7 +1888,10 @@ def test_dataframe_mixed(self, cache): | |
def test_dataframe_float(self, cache): | ||
# float | ||
df = DataFrame({"year": [2000, 2001], "month": [1.5, 1], "day": [1, 1]}) | ||
msg = "cannot assemble the datetimes: unconverted data remains: 1" | ||
msg = ( | ||
r"^cannot assemble the datetimes: unconverted data remains at position " | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. NBD but is the "r" necessary? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Shouldn't be, it's just a habit to always use that in regular expressions |
||
r'0: "1"$' | ||
) | ||
with pytest.raises(ValueError, match=msg): | ||
to_datetime(df, cache=cache) | ||
|
||
|
@@ -2072,7 +2081,9 @@ 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 " " at position 2 doesn\'t match format "%m/%d/%Y" \(match\)$' | ||
) | ||
with pytest.raises(ValueError, match=msg): | ||
to_datetime(ser, errors="raise", cache=cache) | ||
result_coerce = to_datetime(ser, errors="coerce", cache=cache) | ||
|
@@ -2342,7 +2353,10 @@ 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" at position 1 doesn\'t match format ' | ||
r'"%d/%m/%Y" \(match\)$' | ||
), | ||
): | ||
to_datetime(arr, dayfirst=True) | ||
|
||
|
@@ -2410,7 +2424,11 @@ 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" \(match\)$' | ||
) | ||
with pytest.raises(ValueError, match=msg): | ||
to_datetime(ser, cache=cache) | ||
|
||
def test_to_datetime_consistent_format(self, cache): | ||
|
@@ -2923,17 +2941,22 @@ def test_incorrect_value_exception(self): | |
to_datetime(["today", "yesterday"]) | ||
|
||
@pytest.mark.parametrize( | ||
"format, warning", [(None, UserWarning), ("%Y-%m-%d %H:%M:%S", None)] | ||
"format, warning", | ||
[ | ||
(None, UserWarning), | ||
("%Y-%m-%d %H:%M:%S", None), | ||
("%Y-%d-%m %H:%M:%S", None), | ||
], | ||
) | ||
def test_to_datetime_out_of_bounds_with_format_arg(self, format, warning): | ||
# see gh-23830 | ||
msg = ( | ||
"Out of bounds nanosecond timestamp: 2417-10-27 00:00:00 " | ||
"present at position 0" | ||
r"^Out of bounds nanosecond timestamp: 2417-10-10 00:00:00 " | ||
r"present at position 0$" | ||
) | ||
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) | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. slightly changing the input here so we can parametrise of it with both |
||
|
||
@pytest.mark.parametrize( | ||
"arg, origin, expected_str", | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
ending this with "search" seems weird (and i dont see it in any test cases)
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It's true that it wasn't tested, but it's been like this since pandas 0.24:
Maybe we can just remove it - people typically know whether they've passed
exact
, and it doesn't really add muchEspecially as it was never there for (more common) ISO formats:
Let's just unify them to