# },
# {
# "_index": "distinct_agg_streaming",
# "_type": "pyflink",
# "_id": "3TfsHWwBHRafi3KHm2Uf",
# "_score": 1,
# "_source": {
# "a": "a",
# "b": "1"
# }
# },
# {
# "_index": "distinct_agg_streaming",
# "_type": "pyflink",
# "_id": "3jfsHWwBHRafi3KHm2Uf",
# "_score": 1,
# "_source": {
# "a": "b",
# "b": "2"
# }
# }
# ]
# }
# }
if __name__ == '__main__':
from table.prepare_environment import prepare_env
prepare_env(need_stream_source=True, need_upsert_sink=True)
distinct_agg_streaming()
.proctime()
.field("a", DataTypes.STRING())
.field("b", DataTypes.STRING())
.field("c", DataTypes.STRING())
) \
.in_append_mode() \
.register_table_source("source")
st_env.register_table_sink("result",
CsvTableSink(["a", "b"],
[DataTypes.STRING(),
DataTypes.STRING()],
result_file))
st_env.scan("source").window(Tumble.over("2.rows").on("proctime").alias("w")) \
.group_by("w, a") \
.select("a, max(b)").insert_into("result")
st_env.execute("tumble row window streaming")
# cat /tmp/tumble_row_window_streaming.csv
# a,3
# b,4
# a 5
if __name__ == '__main__':
from table.prepare_environment import prepare_env
prepare_env(need_stream_source=True)
# tumble_time_window_streaming()
tumble_row_window_streaming()
# "hits": [
# {
# "_index": "group_by_agg_streaming",
# "_type": "group_by_agg_streaming",
# "_id": "b",
# "_score": 1,
# "_source": {
# "a": "b",
# "b": "6"
# }
# },
# {
# "_index": "group_by_agg_streaming",
# "_type": "group_by_agg_streaming",
# "_id": "a",
# "_score": 1,
# "_source": {
# "a": "a",
# "b": "13"
# }
# }
# ]
# }
# }
if __name__ == '__main__':
from table.prepare_environment import prepare_env
prepare_env(need_upsert_sink=True)
group_by_agg_streaming()