fix(python): treat naive lit(datetime) as UTC wall clock (#3262) (#3775)

## Summary

Fixes naive `lit(datetime)` equality filters against table timestamp
columns on non-UTC hosts, and adds the integration matrix from #3262.

## Failure (before)

On a machine in US Eastern (UTC−4 / EDT), with PyPI `lancedb==0.36.0`:

```python
from datetime import datetime
import lancedb
from lancedb.expr import col, lit

db = lancedb.connect("memory://")
ts = datetime(2024, 7, 1, 10, 0, 0)  # naive
table = db.create_table("t", [{"id": 1, "ts": ts}])
rows = table.search().where(col("ts") == lit(ts)).to_list()
# actual: []  (0 rows)
# expected: 1 row
```

### Root cause

In `python/src/expr.rs`, `expr_lit` converted every `datetime` via
Python's `.timestamp()`:

- **naive** `.timestamp()` = local wall → UTC epoch (shifted by host
offset)
- **PyArrow naive** storage = UTC wall-clock microseconds (no local
shift)

So `lit(naive)` became `CAST('2024-07-01 14:00:00' AS TIMESTAMP)` on EDT
while the table held `10:00:00`.

## After

Naive datetimes are interpreted as UTC wall clock
(`replace(tzinfo=timezone.utc).timestamp()`), matching Arrow storage.
Aware datetimes still use `.timestamp()` (correct epoch).

Same repro on this branch: **1 matching row**.

## Tests

Added `TestExprDatetimeTimezoneIntegration` covering:

| Case | Result |
|------|--------|
| both naive | match |
| both same TZ (UTC) | match |
| different TZs, same instant | match |
| table TZ + naive lit | match (wall clock) |
| table naive + aware lit | match |
| naive lit SQL is wall clock, not local-shifted | asserts `10:00:00` in
SQL |

### Verification

```bash
cd python
maturin develop
pytest python/tests/test_expr.py -v
```

**102 passed** (full `test_expr.py`, including the 6 new cases).

Closes #3262

---------

Co-authored-by: Will Jones <willjones127@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>

python/python/tests/test_expr.py

@@ -632,3 +632,101 @@ class TestExprBytesIntegration:
             .to_arrow()
         )
         assert result.num_rows == 2
+
+
+# ── datetime / timezone integration for lit() (issue #3262) ──────────────────
+
+
+class TestExprDatetimeTimezoneIntegration:
+    """Integration coverage for lit(datetime) against table timestamp columns.
+
+    PyArrow stores naive timestamps as UTC wall-clock microseconds. Python's
+    datetime.timestamp() treats naive values as *local* time, which used to
+    shift lit(naive) by the host UTC offset and break equality filters on
+    non-UTC machines. These cases lock the expected semantics.
+    """
+
+    def test_both_naive_match(self, tmp_path):
+        """Table naive + lit naive with the same wall clock must match."""
+        db = lancedb.connect(str(tmp_path / "naive"))
+        ts = datetime(2024, 7, 1, 10, 0, 0)
+        table = db.create_table(
+            "t", [{"id": 1, "ts": ts}, {"id": 2, "ts": datetime(2024, 7, 2, 10, 0, 0)}]
+        )
+        result = table.search().where(col("ts") == lit(ts)).to_list()
+        assert len(result) == 1
+        assert result[0]["id"] == 1
+
+    def test_both_same_timezone_match(self, tmp_path):
+        """Table UTC + lit UTC for the same instant must match."""
+        db = lancedb.connect(str(tmp_path / "utc"))
+        ts = datetime(2024, 7, 1, 10, 0, 0, tzinfo=timezone.utc)
+        table = db.create_table(
+            "t",
+            pa.table(
+                {
+                    "id": [1, 2],
+                    "ts": pa.array(
+                        [ts, datetime(2024, 7, 2, 10, 0, 0, tzinfo=timezone.utc)],
+                        type=pa.timestamp("us", tz="UTC"),
+                    ),
+                }
+            ),
+        )
+        result = table.search().where(col("ts") == lit(ts)).to_list()
+        assert len(result) == 1
+        assert result[0]["id"] == 1
+
+    def test_different_timezones_same_instant(self, tmp_path):
+        """UTC table row equals lit of the same instant in a different zone."""
+        db = lancedb.connect(str(tmp_path / "diff_tz"))
+        ts_utc = datetime(2024, 7, 1, 10, 0, 0, tzinfo=timezone.utc)
+        # Same instant as 06:00 in UTC-4
+        ts_est = datetime(2024, 7, 1, 6, 0, 0, tzinfo=timezone(timedelta(hours=-4)))
+        table = db.create_table(
+            "t",
+            pa.table(
+                {
+                    "id": [1],
+                    "ts": pa.array([ts_utc], type=pa.timestamp("us", tz="UTC")),
+                }
+            ),
+        )
+        result = table.search().where(col("ts") == lit(ts_est)).to_list()
+        assert len(result) == 1
+        assert result[0]["id"] == 1
+
+    def test_table_tz_literal_naive(self, tmp_path):
+        """UTC table + naive lit uses wall-clock equality (10:00 == 10:00 UTC)."""
+        db = lancedb.connect(str(tmp_path / "tz_naive"))
+        ts_utc = datetime(2024, 7, 1, 10, 0, 0, tzinfo=timezone.utc)
+        ts_naive = datetime(2024, 7, 1, 10, 0, 0)
+        table = db.create_table(
+            "t",
+            pa.table(
+                {
+                    "id": [1],
+                    "ts": pa.array([ts_utc], type=pa.timestamp("us", tz="UTC")),
+                }
+            ),
+        )
+        result = table.search().where(col("ts") == lit(ts_naive)).to_list()
+        assert len(result) == 1
+        assert result[0]["id"] == 1
+
+    def test_table_naive_literal_aware(self, tmp_path):
+        """Naive table + UTC lit with the same wall clock must match."""
+        db = lancedb.connect(str(tmp_path / "naive_aware"))
+        ts_naive = datetime(2024, 7, 1, 10, 0, 0)
+        ts_utc = datetime(2024, 7, 1, 10, 0, 0, tzinfo=timezone.utc)
+        table = db.create_table("t", [{"id": 1, "ts": ts_naive}])
+        result = table.search().where(col("ts") == lit(ts_utc)).to_list()
+        assert len(result) == 1
+        assert result[0]["id"] == 1
+
+    def test_naive_lit_sql_is_wall_clock_not_local_shifted(self):
+        """Regression: naive lit must not apply the host local UTC offset."""
+        ts = datetime(2024, 7, 1, 10, 0, 0)
+        sql = lit(ts).to_sql()
+        # Must encode 10:00 wall clock, not 10:00+local_offset.
+        assert "2024-07-01 10:00:00" in sql

python/src/expr.rs

@@ -191,8 +191,27 @@ pub fn expr_lit(value: Bound<'_, PyAny>) -> PyResult<PyExpr> {
     }
 
     // datetime.datetime is a subclass of datetime.date, so it must be checked first.
+    //
+    // Python's datetime.timestamp() treats *naive* datetimes as local wall time.
+    // PyArrow (and therefore Lance table storage) encodes naive timestamps as
+    // UTC wall-clock microseconds. Using .timestamp() for naive values therefore
+    // shifts the literal by the local UTC offset on non-UTC machines, so
+    // `col("ts") == lit(naive_dt)` fails against a table that holds the same
+    // naive value. Fix: treat naive datetimes as UTC wall clock (match Arrow);
+    // keep aware datetimes on the real .timestamp() path (correct epoch).
     if let Ok(dt) = value.cast::<PyDateTime>() {
-        let ts: f64 = dt.call_method0("timestamp")?.extract()?;
+        let ts: f64 = if dt.getattr("tzinfo")?.is_none() {
+            // Force UTC interpretation of the naive wall clock.
+            let utc = pyo3::types::PyModule::import(value.py(), "datetime")?
+                .getattr("timezone")?
+                .getattr("utc")?;
+            let kwargs = pyo3::types::PyDict::new(value.py());
+            kwargs.set_item("tzinfo", utc)?;
+            let aware = dt.call_method("replace", (), Some(&kwargs))?;
+            aware.call_method0("timestamp")?.extract()?
+        } else {
+            dt.call_method0("timestamp")?.extract()?
+        };
         let micros = (ts * 1_000_000.0).round() as i64;
         return Ok(PyExpr(df_lit(ScalarValue::TimestampMicrosecond(
             Some(micros),