Last active
May 11, 2020 19:22
-
-
Save sjwiesman/ed64867c266fec44fb973366cf22374b to your computer and use it in GitHub Desktop.
Flink Avro Reader Parquet Writer
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
CREATE TABLE kafka_table ( | |
user_id STRING, | |
order_amount double, | |
log_ts TIMESTAMP(3), | |
WATERMARK FOR log_ts AS log_ts - INTERVAL '5' SECOND | |
) WITH ( | |
'connector.type' = 'kafka', | |
'connector.topic' = 'users', | |
'connector.properties.bootstrap.servers' = 'localhost:9092', | |
'connector.properties.group.id' = 'parquet-writer', | |
'format.type' = 'avro' | |
); | |
CREATE TABLE filesystem_table ( | |
user_id STRING, | |
order_amount DOUBLE, | |
day_ts STRING, | |
hour_ts STRING | |
) PARTITIONED BY (day_ts, hour_ts) WITH ( | |
'connector' = 'filesystem', | |
'path' = 'hdfs:///path/to/whatever', | |
'format' = 'parquet', | |
'connector.sink.partition-commit.policy' = 'metastore' | |
); | |
INSERT INTO filesystem_table | |
SELECT user_id, order_amount, DATE_FORMAT(log_ts, 'yyyy-MM-dd'), DATE_FORMAT(log_ts, 'HH') | |
FROM kafka_table; |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment