Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[FLINK-20525][python] Fix StreamArrowPythonGroupWindowAggregateFunctionOperator incorrect handling of rowtime and proctime fields #14327

Closed
wants to merge 1 commit into from
Closed

[FLINK-20525][python] Fix StreamArrowPythonGroupWindowAggregateFunctionOperator incorrect handling of rowtime and proctime fields #14327

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 9 additions & 7 deletions flink-python/pyflink/table/tests/test_pandas_udaf.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -442,24 +442,26 @@ def test_tumbling_group_window_over_time(self):
t = self.t_env.from_path("source_table")

table_sink = source_sink_utils.TestAppendSink(
['a', 'b', 'c', 'd'],
['a', 'b', 'c', 'd', 'e'],
[
DataTypes.TINYINT(),
DataTypes.TIMESTAMP(3),
DataTypes.TIMESTAMP(3),
DataTypes.TIMESTAMP(3),
DataTypes.FLOAT()])
self.t_env.register_table_sink("Results", table_sink)
t.window(Tumble.over("1.hours").on("rowtime").alias("w")) \
.group_by("a, b, w") \
.select("a, w.start, w.end, mean_udaf(c) as b") \
.select("a, w.start, w.end, w.rowtime, mean_udaf(c) as b") \
.execute_insert("Results") \
.wait()
actual = source_sink_utils.results()
self.assert_equals(actual,
["1,2018-03-11 03:00:00.0,2018-03-11 04:00:00.0,2.5",
"1,2018-03-11 04:00:00.0,2018-03-11 05:00:00.0,8.0",
"2,2018-03-11 03:00:00.0,2018-03-11 04:00:00.0,2.0",
"3,2018-03-11 03:00:00.0,2018-03-11 04:00:00.0,2.0"])
self.assert_equals(actual, [
"1,2018-03-11 03:00:00.0,2018-03-11 04:00:00.0,2018-03-11 03:59:59.999,2.5",
"1,2018-03-11 04:00:00.0,2018-03-11 05:00:00.0,2018-03-11 04:59:59.999,8.0",
"2,2018-03-11 03:00:00.0,2018-03-11 04:00:00.0,2018-03-11 03:59:59.999,2.0",
"3,2018-03-11 03:00:00.0,2018-03-11 04:00:00.0,2018-03-11 03:59:59.999,2.0",
])
os.remove(source_path)

def test_tumbling_group_window_over_count(self):
Expand Down
4 changes: 3 additions & 1 deletion .../python/aggregate/arrow/stream/StreamArrowPythonGroupWindowAggregateFunctionOperator.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -380,8 +380,10 @@ private void setWindowProperty(W currentWindow) {
windowProperty.setField(i, TimestampData.fromEpochMillis(((TimeWindow) currentWindow).getEnd()));
break;
case 2:
windowProperty.setField(i, TimestampData.fromEpochMillis(currentWindow.maxTimestamp()));
windowProperty.setField(i, TimestampData.fromEpochMillis(((TimeWindow) currentWindow).getEnd() - 1));
break;
case 3:
windowProperty.setField(i, TimestampData.fromEpochMillis(-1));
}
}
}
Expand Down
3 changes: 2 additions & 1 deletion ...flink/table/planner/plan/nodes/physical/stream/StreamExecPythonGroupWindowAggregate.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@ import org.apache.flink.table.functions.python.PythonFunctionInfo
import org.apache.flink.table.planner.calcite.FlinkRelBuilder.PlannerNamedWindowProperty
import org.apache.flink.table.planner.calcite.FlinkTypeFactory
import org.apache.flink.table.planner.delegation.StreamPlanner
import org.apache.flink.table.planner.expressions.{PlannerRowtimeAttribute, PlannerWindowEnd, PlannerWindowStart}
import org.apache.flink.table.planner.expressions.{PlannerProctimeAttribute, PlannerRowtimeAttribute, PlannerWindowEnd, PlannerWindowStart}
import org.apache.flink.table.planner.plan.logical.{LogicalWindow, SlidingGroupWindow, TumblingGroupWindow}
import org.apache.flink.table.planner.plan.nodes.common.CommonPythonAggregate
import org.apache.flink.table.planner.plan.nodes.physical.stream.StreamExecPythonGroupWindowAggregate.ARROW_STREAM_PYTHON_GROUP_WINDOW_AGGREGATE_FUNCTION_OPERATOR_NAME
Expand Down Expand Up @@ -219,6 +219,7 @@ class StreamExecPythonGroupWindowAggregate(
case PlannerWindowStart(_) => 0
case PlannerWindowEnd(_) => 1
case PlannerRowtimeAttribute(_) => 2
case PlannerProctimeAttribute(_) => 3
}
}.toArray

Expand Down