BUG: catch decimal.InvalidOperation exception from dateutil (#51157)

* catch InvalidOperation exception from dateutil

* add tests to verify decimal.InvalidOperation is caught

Author: kcaashish

doc/source/whatsnew/v2.0.0.rst

@@ -1136,6 +1136,7 @@ Datetimelike
 - Bug in :meth:`Series.interpolate` and :meth:`DataFrame.interpolate` with datetime or timedelta dtypes incorrectly raising ``ValueError`` (:issue:`11312`)
 - Bug in :func:`to_datetime` was not returning input with ``errors='ignore'`` when input was out-of-bounds (:issue:`50587`)
 - Bug in :func:`DataFrame.from_records` when given a :class:`DataFrame` input with timezone-aware datetime64 columns incorrectly dropping the timezone-awareness (:issue:`51162`)
+- Bug in :func:`to_datetime` was raising ``decimal.InvalidOperation`` when parsing date strings with ``errors='coerce'`` (:issue:`51084`)
 -
 
 Timedelta

pandas/_libs/tslibs/parsing.pyx

@@ -40,6 +40,8 @@ cnp.import_array()
 
 # dateutil compat
 
+from decimal import InvalidOperation
+
 from dateutil.parser import (
     DEFAULTPARSER,
     parse as du_parse,
@@ -646,7 +648,10 @@ cdef datetime dateutil_parse(
         str reso = None
         dict repl = {}
 
-    res, _ = DEFAULTPARSER._parse(timestr, dayfirst=dayfirst, yearfirst=yearfirst)
+    try:
+        res, _ = DEFAULTPARSER._parse(timestr, dayfirst=dayfirst, yearfirst=yearfirst)
+    except InvalidOperation:
+        res = None
 
     if res is None:
         raise DateParseError(
@@ -891,7 +896,7 @@ def guess_datetime_format(dt_str: str, bint dayfirst=False) -> str | None:
 
     try:
         parsed_datetime = du_parse(dt_str, dayfirst=dayfirst)
-    except (ValueError, OverflowError):
+    except (ValueError, OverflowError, InvalidOperation):
         # In case the datetime can't be parsed, its format cannot be guessed
         return None
 

pandas/tests/tools/test_to_datetime.py

@@ -2501,6 +2501,16 @@ def test_to_datetime_overflow(self):
         with pytest.raises(OutOfBoundsTimedelta, match=msg):
             date_range(start="1/1/1700", freq="B", periods=100000)
 
+    def test_string_invalid_operation(self, cache):
+        invalid = np.array(["87156549591102612381000001219H5"], dtype=object)
+        # GH #51084
+
+        with pytest.raises(ValueError, match="Unknown datetime string format"):
+            with tm.assert_produces_warning(
+                UserWarning, match="Could not infer format"
+            ):
+                to_datetime(invalid, errors="raise", cache=cache)
+
     def test_string_na_nat_conversion(self, cache):
         # GH #999, #858
 

pandas/tests/tslibs/test_parsing.py

@@ -246,6 +246,7 @@ def test_guess_datetime_format_with_locale_specific_formats(string, fmt):
         "13/2019",
         "202001",  # YYYYMM isn't ISO8601
         "2020/01",  # YYYY/MM isn't ISO8601 either
+        "87156549591102612381000001219H5",
     ],
 )
 def test_guess_datetime_format_invalid_inputs(invalid_dt):