[root@master pyflink]# cat test.txt
aaaaa 111111
bbbbb 222222
ccccc 333333
ddddd 444444
eeeee 555555
[root@master pyflink]# cat test.py
# -*- coding: utf-8 -*-
from pyflink.datastream import StreamExecutionEnvironment
from pyflink.datastream.functions import MapFunction, RuntimeContext, KeyedProcessFunction
from abc import ABC, abstractmethod
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
from datetime import datetime
from elasticsearch import Elasticsearch
from pyflink.datastream.functions import RuntimeContext, FlatMapFunction
import re
import redis
# 创建 StreamExecutionEnvironment 对象
env = StreamExecutionEnvironment.get_execution_environment()
env.set_parallelism(1)
# 读取文件，创建 DataStream 对象
data_stream = env.read_text_file('/root/pyflink/test.txt')
def my_map_func(value):
return int(value.split(' ')[1]) + 1
new_stream = data_stream.map(my_map_func)
# 输出到控制台
new_stream.print()
# 执行任务
env.execute('Add "bus_seq" to each line')
def map(self, func: Union[Callable, MapFunction], output_type: TypeInformation = None) \
-> 'DataStream':
"""
Applies a Map transformation on a DataStream. The transformation calls a MapFunction for
each element of the DataStream. Each MapFunction call returns exactly one element.
[root@master pyflink]# python test.py
111112
222223
333334
444445
555556