BUG: Invalid format to to_datetime with errors='coerce' doesn't raise · Issue #50266 · pandas-dev/pandas (original) (raw)

Pandas version checks

Reproducible Example

In [2]: pd.to_datetime("00:01:18", format='H%:M%:S%') # raises, as expected

KeyError Traceback (most recent call last) File ~/pandas-dev/pandas/_libs/tslibs/strptime.pyx:136, in pandas._libs.tslibs.strptime.array_strptime() 135 try: --> 136 format_regex = _TimeRE_cache.compile(fmt) 137 # KeyError raised when a bad format is found; can be specified as

File ~/mambaforge/envs/pandas-dev/lib/python3.8/_strptime.py:263, in TimeRE.compile(self, format) 262 """Return a compiled re object for the format string.""" --> 263 return re_compile(self.pattern(format), IGNORECASE)

File ~/mambaforge/envs/pandas-dev/lib/python3.8/_strptime.py:257, in TimeRE.pattern(self, format) 254 directive_index = format.index('%')+1 255 processed_format = "%s%s%s" % (processed_format, 256 format[:directive_index-1], --> 257 self[format[directive_index]]) 258 format = format[directive_index+1:]

File ~/pandas-dev/pandas/_libs/tslibs/strptime.pyx:461, in pandas._libs.tslibs.strptime.TimeRE.getitem() 460 return self._Z --> 461 return super().getitem(key) 462

KeyError: ':'

During handling of the above exception, another exception occurred:

ValueError Traceback (most recent call last) Cell In[2], line 1 ----> 1 pd.to_datetime("00:01:18", format='H%:M%:S%')

File ~/pandas-dev/pandas/core/tools/datetimes.py:1100, in to_datetime(arg, errors, dayfirst, yearfirst, utc, format, exact, unit, infer_datetime_format, origin, cache) 1098 result = convert_listlike(argc, format) 1099 else: -> 1100 result = convert_listlike(np.array([arg]), format)[0] 1101 if isinstance(arg, bool) and isinstance(result, np.bool_): 1102 result = bool(result) # TODO: avoid this kludge.

File ~/pandas-dev/pandas/core/tools/datetimes.py:442, in _convert_listlike_datetimes(arg, format, name, utc, unit, errors, dayfirst, yearfirst, exact) 439 require_iso8601 = format is not None and format_is_iso(format) 441 if format is not None and not require_iso8601: --> 442 return _to_datetime_with_format( 443 arg, 444 orig_arg, 445 name, 446 utc, 447 format, 448 exact, 449 errors, 450 ) 452 result, tz_parsed = objects_to_datetime64ns( 453 arg, 454 dayfirst=dayfirst, (...) 461 exact=exact, 462 ) 464 if tz_parsed is not None: 465 # We can take a shortcut since the datetime64 numpy array 466 # is in UTC

File ~/pandas-dev/pandas/core/tools/datetimes.py:543, in _to_datetime_with_format(arg, orig_arg, name, utc, fmt, exact, errors) 540 return _box_as_indexlike(result, utc=utc, name=name) 542 # fallback --> 543 res = _array_strptime_with_fallback(arg, name, utc, fmt, exact, errors) 544 return res

File ~/pandas-dev/pandas/core/tools/datetimes.py:485, in _array_strptime_with_fallback(arg, name, utc, fmt, exact, errors) 481 """ 482 Call array_strptime, with fallback behavior depending on 'errors'. 483 """ 484 try: --> 485 result, timezones = array_strptime( 486 arg, fmt, exact=exact, errors=errors, utc=utc 487 ) 488 except OutOfBoundsDatetime: 489 if errors == "raise":

File ~/pandas-dev/pandas/_libs/tslibs/strptime.pyx:126, in pandas._libs.tslibs.strptime.array_strptime() 124 125 global _TimeRE_cache, _regex_cache --> 126 with _cache_lock: 127 if _getlang() != _TimeRE_cache.locale_time.lang: 128 _TimeRE_cache = TimeRE()

File ~/pandas-dev/pandas/_libs/tslibs/strptime.pyx:144, in pandas._libs.tslibs.strptime.array_strptime() 142 bad_directive = "%" 143 del err --> 144 raise ValueError(f"'{bad_directive}' is a bad directive " 145 f"in format '{fmt}'") 146 # IndexError only occurs when the format string is "%"

ValueError: ':' is a bad directive in format 'H%:M%:S%'

In [3]: pd.to_datetime("00:01:18", format='H%:M%:S%', errors='coerce') # doesn't raise Out[3]: NaT

Issue Description

The issue with this overly broad try-except:

try:
result, timezones = array_strptime(
arg, fmt, exact=exact, errors=errors, utc=utc
)
except OutOfBoundsDatetime:
if errors == "raise":
raise
if errors == "coerce":
result = np.empty(arg.shape, dtype="M8[ns]")
iresult = result.view("i8")
iresult.fill(iNaT)
else:
result = arg
except ValueError:
if errors == "raise":
raise
if errors == "coerce":
result = np.empty(arg.shape, dtype="M8[ns]")
iresult = result.view("i8")
iresult.fill(iNaT)
else:
result = arg

The try-except should happen within the loop, as is done in tslib.pyx:

for i in range(n):
val = values[i]
try:

Related: #24763, but I really disagree that this is desirable behaviour

Expected Behavior

pd.to_datetime("00:01:18", format='H%:M%:S%', errors='coerce') should still raise

errors='coerce' controls what happens during parsing - here, however, the error happens before the parsing even begins, because the format is invalid

Installed Versions

INSTALLED VERSIONS

commit : a5cbd1e
python : 3.8.15.final.0
python-bits : 64
OS : Linux
OS-release : 5.10.102.1-microsoft-standard-WSL2
Version : #1 SMP Wed Mar 2 00:30:59 UTC 2022
machine : x86_64
processor : x86_64
byteorder : little
LC_ALL : None
LANG : en_GB.UTF-8
LOCALE : en_GB.UTF-8

pandas : 2.0.0.dev0+923.ga5cbd1e52e
numpy : 1.23.5
pytz : 2022.6
dateutil : 2.8.2
setuptools : 65.5.1
pip : 22.3.1
Cython : 0.29.32
pytest : 7.2.0
hypothesis : 6.61.0
sphinx : 4.5.0
blosc : None
feather : None
xlsxwriter : 3.0.3
lxml.etree : 4.9.1
html5lib : 1.1
pymysql : 1.0.2
psycopg2 : 2.9.3
jinja2 : 3.1.2
IPython : 8.7.0
pandas_datareader: None
bs4 : 4.11.1
bottleneck : 1.3.5
brotli :
fastparquet : 2022.12.0
fsspec : 2021.11.0
gcsfs : 2021.11.0
matplotlib : 3.6.2
numba : 0.56.4
numexpr : 2.8.3
odfpy : None
openpyxl : 3.0.10
pandas_gbq : None
pyarrow : 9.0.0
pyreadstat : 1.2.0
pyxlsb : 1.0.10
s3fs : 2021.11.0
scipy : 1.9.3
snappy :
sqlalchemy : 1.4.45
tables : 3.7.0
tabulate : 0.9.0
xarray : 2022.12.0
xlrd : 2.0.1
zstandard : 0.19.0
tzdata : None
qtpy : None
pyqt5 : None
None