在 Amazon EMR 中通过 Zeppelin 使用 Flink 作业

%flink – 创建 ExecutionEnvironment、StreamExecutionEnvironment、BatchTableEnvironment、StreamTableEnvironment 并提供 Scala 环境

%flink.pyflink – 提供一个 Python 环境

%flink.ssql – 提供流式 SQL 环境

%flink.bsql – 提供批处理 SQL 环境

使用 Amazon EMR 6.10.0 及更高版本创建的集群支持 Zeppelin 与 Flink 集成。

要根据这些步骤的要求查看 EMR 集群上托管的 Web 界面，必须配置 SSH 隧道以允许入站访问。有关更多信息，请参阅 Configure proxy settings to view websites hosted on the primary node。

示例 1，Flink Scala

a) Batch Ex WordCount ample (SCALA)

%flink

val data = benv.fromElements("hello world", "hello flink", "hello hadoop")
data.flatMap(line => line.split("\\s"))
             .map(w => (w, 1))
             .groupBy(0)
             .sum(1)
             .print()

b) 直播 WordCount 示例 (SCALA)

%flink

val data = senv.fromElements("hello world", "hello flink", "hello hadoop")
data.flatMap(line => line.split("\\s"))
  .map(w => (w, 1))
  .keyBy(0)
  .sum(1)
  .print

senv.execute()

示例 2，Flink 流式传输 SQL

%flink.ssql
SET 'sql-client.execution.result-mode' = 'tableau';
SET 'table.dml-sync' = 'true';
SET 'execution.runtime-mode' = 'streaming';

create table dummy_table (
  id int,
  data string
) with (
  'connector' = 'filesystem',
  'path' = 's3://s3-bucket/dummy_table',
  'format' = 'csv'
);

INSERT INTO dummy_table SELECT * FROM (VALUES (1, 'Hello World'), (2, 'Hi'), (2, 'Hi'), (3, 'Hello'), (3, 'World'), (4, 'ADD'), (5, 'LINE'));

SELECT * FROM dummy_table;

示例 3，Pyflink。请注意，您必须将名为 word.txt 的示例文本文件上传到 S3 存储桶。

%flink.pyflink

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

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().set("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()


logging.basicConfig(stream=sys.stdout, level=logging.INFO, format="%(message)s")


word_count("s3://s3_bucket/word.txt", "s3://s3_bucket/demo_output.txt")