Preserve list-like target inputs and avoid double-tz in test

Per copilot review on PR #251:

- _coerce_targets: detect non-DatetimeIndex iterables (Series, ndarray)
  via pd.api.types.is_scalar so the elements are preserved instead of
  being wrapped in a single-element list. Add a regression test passing
  a pd.Series of two timestamps and assert both are processed.
- Tests: drop the redundant tz='UTC' on pd.Timestamp inputs that already
  carry a Z suffix; pandas 2.x raises on double timezone specification.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: thodson-usgs

dataretrieval/waterdata/nearest.py

@@ -181,13 +181,15 @@ def _coerce_targets(targets) -> pd.DatetimeIndex:
     """Accept anything ``pandas.to_datetime`` consumes, including a single value.
 
     A bare scalar (string, ``Timestamp``, ``datetime``, …) becomes a
-    one-element ``DatetimeIndex``; an iterable round-trips through
-    ``pd.to_datetime`` directly.
+    one-element ``DatetimeIndex``; an iterable (list, ``Series``, ``ndarray``)
+    is wrapped directly so its elements are preserved.
     """
     parsed = pd.to_datetime(targets, utc=True)
     if isinstance(parsed, pd.DatetimeIndex):
         return parsed
-    return pd.DatetimeIndex([parsed])
+    if pd.api.types.is_scalar(parsed):
+        return pd.DatetimeIndex([parsed])
+    return pd.DatetimeIndex(parsed)
 
 
 def _check_nearest_kwargs(kwargs: dict, on_tie: OnTie) -> None:

tests/waterdata_nearest_test.py

@@ -282,9 +282,7 @@ def test_accepts_single_string_target(patch_get_continuous):
         "2023-06-15T10:30:31Z", monitoring_location_id="USGS-02238500"
     )
     assert len(result) == 1
-    assert result["target_time"].iloc[0] == pd.Timestamp(
-        "2023-06-15T10:30:31Z", tz="UTC"
-    )
+    assert result["target_time"].iloc[0] == pd.Timestamp("2023-06-15T10:30:31Z")
 
 
 def test_accepts_single_timestamp_target(patch_get_continuous):
@@ -293,11 +291,27 @@ def test_accepts_single_timestamp_target(patch_get_continuous):
         _fake_df([{"time": "2023-06-15T10:30:00Z", "value": 22.4}]),
         mock.Mock(),
     )
-    target = pd.Timestamp("2023-06-15T10:30:31Z", tz="UTC")
+    target = pd.Timestamp("2023-06-15T10:30:31Z")
     result, _ = get_nearest_continuous(target, monitoring_location_id="USGS-02238500")
     assert len(result) == 1
 
 
+def test_accepts_pandas_series_targets(patch_get_continuous):
+    """A ``pd.Series`` of timestamps preserves all elements (not just the first)."""
+    patch_get_continuous.return_value = (
+        _fake_df(
+            [
+                {"time": "2023-06-15T10:30:00Z", "value": 22.4},
+                {"time": "2023-06-16T10:30:00Z", "value": 22.5},
+            ]
+        ),
+        mock.Mock(),
+    )
+    targets = pd.Series(["2023-06-15T10:30:31Z", "2023-06-16T10:30:31Z"])
+    result, _ = get_nearest_continuous(targets, monitoring_location_id="USGS-02238500")
+    assert len(result) == 2
+
+
 def test_missing_time_column_raises_helpful_error(patch_get_continuous):
     """If the response has no 'time' column (e.g. user passed `properties`
     that excluded it), raise ValueError instead of crashing with KeyError.