说在最前面的
目前pyflink的接口都是对已有的java api的python再次封装，都是通过py4j实现python和java的互通。🥳
Tips
- Tips📢📢📢:这里的Python版本建议选用python3.8（或者3.6，3.7），我使用python3.9，python3.10报错如下：
- Tips📢📢📢:这里的Java版本建议选用jdk11（或java8），我使用jdk17出现报错。
py4j.protocol.Py4JJavaError: An error occurred while calling o58.flatMap.
安装
pip安装
# 官方下载，可能比较慢 pip install apache-flink # 使用清华源下载 pip install -i https://pypi.tuna.tsinghua.edu.cn/simple apache-flink
官方例子
Table API
import argparse import logging import sys from pyflink.common import Row from pyflink.table import (EnvironmentSettings, TableEnvironment, TableDescriptor, Schema, DataTypes, FormatDescriptor) from pyflink.table.expressions import lit, col from pyflink.table.udf import udtf word_count_data = ["To be, or not to be,--that is the question:--", "Whether 'tis nobler in the mind to suffer", "The slings and arrows of outrageous fortune", "Or to take arms against a sea of troubles,", "And by opposing end them?--To die,--to sleep,--", "No more; and by a sleep to say we end", "The heartache, and the thousand natural shocks", "That flesh is heir to,--'tis a consummation", "Devoutly to be wish'd. To die,--to sleep;--", "To sleep! perchance to dream:--ay, there's the rub;", "For in that sleep of death what dreams may come,", "When we have shuffled off this mortal coil,", "Must give us pause: there's the respect", "That makes calamity of so long life;", "For who would bear the whips and scorns of time,", "The oppressor's wrong, the proud man's contumely,", "The pangs of despis'd love, the law's delay,", "The insolence of office, and the spurns", "That patient merit of the unworthy takes,", "When he himself might his quietus make", "With a bare bodkin? who would these fardels bear,", "To grunt and sweat under a weary life,", "But that the dread of something after death,--", "The undiscover'd country, from whose bourn", "No traveller returns,--puzzles the will,", "And makes us rather bear those ills we have", "Than fly to others that we know not of?", "Thus conscience does make cowards of us all;", "And thus the native hue of resolution", "Is sicklied o'er with the pale cast of thought;", "And enterprises of great pith and moment,", "With this regard, their currents turn awry,", "And lose the name of action.--Soft you now!", "The fair Ophelia!--Nymph, in thy orisons", "Be all my sins remember'd."] def word_count(input_path, output_path): t_env = TableEnvironment.create(EnvironmentSettings.in_streaming_mode()) # write all the data to one file t_env.get_config().get_configuration().set_string("parallelism.default", "1") # define the source if input_path is not None: t_env.create_temporary_table( 'source', TableDescriptor.for_connector('filesystem') .schema(Schema.new_builder() .column('word', DataTypes.STRING()) .build()) .option('path', input_path) .format('csv') .build()) tab = t_env.from_path('source') else: print("Executing word_count example with default input data set.") print("Use --input to specify file input.") tab = t_env.from_elements(map(lambda i: (i,), word_count_data), DataTypes.ROW([DataTypes.FIELD('line', DataTypes.STRING())])) # define the sink if output_path is not None: t_env.create_temporary_table( 'sink', TableDescriptor.for_connector('filesystem') .schema(Schema.new_builder() .column('word', DataTypes.STRING()) .column('count', DataTypes.BIGINT()) .build()) .option('path', output_path) .format(FormatDescriptor.for_format('canal-json') .build()) .build()) else: print("Printing result to stdout. Use --output to specify output path.") t_env.create_temporary_table( 'sink', TableDescriptor.for_connector('print') .schema(Schema.new_builder() .column('word', DataTypes.STRING()) .column('count', DataTypes.BIGINT()) .build()) .build()) @udtf(result_types=[DataTypes.STRING()]) def split(line: Row): for s in line[0].split(): yield Row(s) # compute word count tab.flat_map(split).alias('word') \ .group_by(col('word')) \ .select(col('word'), lit(1).count) \ .execute_insert('sink') \ .wait() # remove .wait if submitting to a remote cluster, refer to # https://nightlies.apache.org/flink/flink-docs-stable/docs/dev/python/faq/#wait-for-jobs-to-finish-when-executing-jobs-in-mini-cluster # for more details if __name__ == '__main__': logging.basicConfig(stream=sys.stdout, level=logging.INFO, format="%(message)s") parser = argparse.ArgumentParser() parser.add_argument( '--input', dest='input', required=False, help='Input file to process.') parser.add_argument( '--output', dest='output', required=False, help='Output file to write results to.') argv = sys.argv[1:] known_args, _ = parser.parse_known_args(argv) word_count(known_args.input, known_args.output)
Data Stream API
''' Description: henggao_note version: v1.0.0 Date: 2022-03-14 10:17:18 LastEditors: henggao LastEditTime: 2022-03-14 10:17:18 ''' import argparse import logging import sys from pyflink.common import WatermarkStrategy, Encoder, Types from pyflink.datastream import StreamExecutionEnvironment, RuntimeExecutionMode from pyflink.datastream.connectors import (FileSource, StreamFormat, FileSink, OutputFileConfig, RollingPolicy) word_count_data = ["To be, or not to be,--that is the question:--", "Whether 'tis nobler in the mind to suffer", "The slings and arrows of outrageous fortune", "Or to take arms against a sea of troubles,", "And by opposing end them?--To die,--to sleep,--", "No more; and by a sleep to say we end", "The heartache, and the thousand natural shocks", "That flesh is heir to,--'tis a consummation", "Devoutly to be wish'd. To die,--to sleep;--", "To sleep! perchance to dream:--ay, there's the rub;", "For in that sleep of death what dreams may come,", "When we have shuffled off this mortal coil,", "Must give us pause: there's the respect", "That makes calamity of so long life;", "For who would bear the whips and scorns of time,", "The oppressor's wrong, the proud man's contumely,", "The pangs of despis'd love, the law's delay,", "The insolence of office, and the spurns", "That patient merit of the unworthy takes,", "When he himself might his quietus make", "With a bare bodkin? who would these fardels bear,", "To grunt and sweat under a weary life,", "But that the dread of something after death,--", "The undiscover'd country, from whose bourn", "No traveller returns,--puzzles the will,", "And makes us rather bear those ills we have", "Than fly to others that we know not of?", "Thus conscience does make cowards of us all;", "And thus the native hue of resolution", "Is sicklied o'er with the pale cast of thought;", "And enterprises of great pith and moment,", "With this regard, their currents turn awry,", "And lose the name of action.--Soft you now!", "The fair Ophelia!--Nymph, in thy orisons", "Be all my sins remember'd."] def word_count(input_path, output_path): env = StreamExecutionEnvironment.get_execution_environment() env.set_runtime_mode(RuntimeExecutionMode.BATCH) # write all the data to one file env.set_parallelism(1) # define the source if input_path is not None: ds = env.from_source( source=FileSource.for_record_stream_format(StreamFormat.text_line_format(), input_path) .process_static_file_set().build(), watermark_strategy=WatermarkStrategy.for_monotonous_timestamps(), source_name="file_source" ) else: print("Executing word_count example with default input data set.") print("Use --input to specify file input.") ds = env.from_collection(word_count_data) def split(line): yield from line.split() # compute word count ds = ds.flat_map(split) \ .map(lambda i: (i, 1), output_type=Types.TUPLE([Types.STRING(), Types.INT()])) \ .key_by(lambda i: i[0]) \ .reduce(lambda i, j: (i[0], i[1] + j[1])) # define the sink if output_path is not None: ds.sink_to( sink=FileSink.for_row_format( base_path=output_path, encoder=Encoder.simple_string_encoder()) .with_output_file_config( OutputFileConfig.builder() .with_part_prefix("prefix") .with_part_suffix(".ext") .build()) .with_rolling_policy(RollingPolicy.default_rolling_policy()) .build() ) else: print("Printing result to stdout. Use --output to specify output path.") ds.print() # submit for execution env.execute() if __name__ == '__main__': logging.basicConfig(stream=sys.stdout, level=logging.INFO, format="%(message)s") parser = argparse.ArgumentParser() parser.add_argument( '--input', dest='input', required=False, help='Input file to process.') parser.add_argument( '--output', dest='output', required=False, help='Output file to write results to.') argv = sys.argv[1:] known_args, _ = parser.parse_known_args(argv) word_count(known_args.input, known_args.output)
DataStream测试
''' Description: henggao_note version: v1.0.0 Author: henggao Date: 2022-03-11 20:31:24 LastEditors: henggao LastEditTime: 2022-03-11 20:45:02 ''' #-*- coding:utf-8 -*- from pyflink.datastream import StreamExecutionEnvironment from pyflink.table import EnvironmentSettings, StreamTableEnvironment def hello_world(): """ 从随机Source读取数据，然后直接利用PrintSink输出。 """ settings = EnvironmentSettings.new_instance().in_streaming_mode().use_blink_planner().build() env = StreamExecutionEnvironment.get_execution_environment() t_env = StreamTableEnvironment.create(stream_execution_environment=env, environment_settings=settings) source_ddl = """ CREATE TABLE random_source ( f_sequence INT, f_random INT, f_random_str STRING ) WITH ( 'connector' = 'datagen', 'rows-per-second'='5', 'fields.f_sequence.kind'='sequence', 'fields.f_sequence.start'='1', 'fields.f_sequence.end'='1000', 'fields.f_random.min'='1', 'fields.f_random.max'='1000', 'fields.f_random_str.length'='10' ) """ sink_ddl = """ CREATE TABLE print_sink ( f_sequence INT, f_random INT, f_random_str STRING ) WITH ( 'connector' = 'print' ) """ # 注册source和sink t_env.execute_sql(source_ddl) t_env.execute_sql(sink_ddl) # 数据提取 tab = t_env.from_path("random_source") # 这里我们暂时先使用 标注了 deprecated 的API, 因为新的异步提交测试有待改进... tab.execute_insert("print_sink").wait() # 执行作业 t_env.execute_sql("Flink Hello World") if __name__ == '__main__': hello_world()
运行效果如下：
