KeyBy
DataStream → KeyedStream
在逻辑上将流划分为不相交的分区。具有相同 key 的记录都分配到同一个分区。
在内部, keyBy() 是通过哈希分区实现的。有多种指定 key的方式。
[root@master pyflink]# cat flik_6.py
# -*- coding: utf-8 -*-
from pyflink.datastream import StreamExecutionEnvironment
from pyflink.datastream.functions import MapFunction, RuntimeContext, KeyedProcessFunction
from pyflink.datastream.state import MapStateDescriptor
from pyflink.datastream.connectors.kafka import FlinkKafkaConsumer
from pyflink.common.typeinfo import Types, TypeInformation
from pyflink.datastream.connectors.elasticsearch import Elasticsearch7SinkBuilder, ElasticsearchEmitter, FlushBackoffType
from pyflink.datastream.connectors import DeliveryGuarantee
from pyflink.common.serialization import SimpleStringSchema
import json
import re
env = StreamExecutionEnvironment.get_execution_environment()
data_stream = env.from_collection(collection=[(1, 'a'), (2, 'a'), (3, 'b')])
data_stream=data_stream.key_by(lambda x: x[1], key_type=Types.STRING())
# 输出到控制台
data_stream.print()
# 执行任务
env.execute('Add "aaaa" to each line')
[root@master pyflink]# python flik_6.py
3> (1, 'a')
3> (2, 'a')
3> (3, 'b')