[python] Support window joins in temporal alignment

docs/docs/pypaimon/multimodal-reading.md

@@ -102,6 +102,29 @@ states_at_steps = aligned.interpolate(
 )
 ```
 
+Use `join_window(left, right, ...)` directly or chain
+`aligned.join_window(...)`. Unlike single-table `rolling().agg()`, it joins
+each left row to right rows in the same `by` group and
+`[left - preceding, left + following]` time window, then aggregates them.
+`following` defaults to zero. `mean`, `min`, and `max` require integer or
+floating-point scalars; `count`, `first`, and `last` also accept non-numeric
+values. `closed` is `both`, `left`, `right`, or `neither` and refers to the
+interval endpoints. Nulls are skipped; empty windows return null, except
+`count` returns zero. Use `(source, operation)` pairs to aggregate one source
+column more than once; `{"value": "mean"}` remains valid shorthand.
+
+```python
+steps_with_imu = aligned.join_window(
+    imu.scan().select("acceleration"),
+    preceding=timedelta(milliseconds=50),
+    following=timedelta(milliseconds=50),
+    aggregations={
+        "acceleration_mean": ("acceleration", "mean"),
+        "acceleration_max": ("acceleration", "max"),
+    },
+)
+```
+
 ### Reading BLOB columns
 
 `scan().read_blobs(column)` bulk-fetches a BLOB column's bytes for the filtered

paimon-python/pypaimon/multimodal/__init__.py

@@ -46,6 +46,7 @@
     TemporalAlignment,
     interpolate,
     join_asof,
+    join_window,
 )
 from pypaimon.multimodal.video import VideoFrameCollator
 from pypaimon.table.row.blob import Blob, BlobDescriptor, VideoFrameDescriptor
@@ -79,6 +80,7 @@
     "connect",
     "interpolate",
     "join_asof",
+    "join_window",
     "lit",
     "source_col",
     "target_col",