Usar trabalhos do Flink pelo Zeppelin no Amazon EMR

%flink: cria ExecutionEnvironment, StreamExecutionEnvironment, BatchTableEnvironment, StreamTableEnvironment e fornece um ambiente Scala

%flink.pyflink: fornece um ambiente Python

%flink.ssql: fornece um ambiente SQL de transmissão

%flink.bsql: fornece um ambiente SQL em lote

A integração do Zeppelin com o Flink é compatível com clusters criados com o Amazon EMR 6.10.0 e versões posteriores.

Para visualizar as interfaces Web hospedadas em clusters do EMR conforme necessário para essas etapas, é necessário configurar um túnel SSH para permitir o acesso de entrada. Para obter mais informações, consulte Configure proxy settings to view websites hosted on the primary node.

Exemplo 1, Flink Scala

a) WordCount Exemplo de Batch (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) WordCount Exemplo de streaming (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()

Exemplo 2, Flink Streaming 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;

Exemplo 3, Pyflink. Observe que você deve fazer upload da sua própria amostra de arquivo de texto chamada word.txt no bucket do S3.

%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")