6edf0b9def
- [HUDI-172] Cleanup Maven POM/Classpath - Fix ordering of dependencies in poms, to enable better resolution - Idea is to place more specific ones at the top - And place dependencies which use them below them - [HUDI-68] : Automate demo steps on docker setup - Move hive queries from hive cli to beeline - Standardize on taking query input from text command files - Deltastreamer ingest, also does hive sync in a single step - Spark Incremental Query materialized as a derived Hive table using datasource - Fix flakiness in HDFS spin up and output comparison - Code cleanup around streamlining and loc reduction - Also fixed pom to not shade some hive classs in spark, to enable hive sync
30 lines
1.6 KiB
Plaintext
30 lines
1.6 KiB
Plaintext
/*
|
|
* Licensed to the Apache Software Foundation (ASF) under one
|
|
* or more contributor license agreements. See the NOTICE file
|
|
* distributed with this work for additional information
|
|
* regarding copyright ownership. The ASF licenses this file
|
|
* to you under the Apache License, Version 2.0 (the
|
|
* "License"); you may not use this file except in compliance
|
|
* with the License. You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*/
|
|
|
|
// Copy-On-Write table
|
|
spark.sql("select symbol, max(ts) from stock_ticks_cow group by symbol HAVING symbol = 'GOOG'").show(100, false)
|
|
spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, close from stock_ticks_cow where symbol = 'GOOG'").show(100, false)
|
|
|
|
// Merge-On-Read table
|
|
spark.sql("select symbol, max(ts) from stock_ticks_mor group by symbol HAVING symbol = 'GOOG'").show(100, false)
|
|
spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, close from stock_ticks_mor where symbol = 'GOOG'").show(100, false)
|
|
spark.sql("select symbol, max(ts) from stock_ticks_mor_rt group by symbol HAVING symbol = 'GOOG'").show(100, false)
|
|
spark.sql("select `_hoodie_commit_time`, symbol, ts, volume, open, close from stock_ticks_mor_rt where symbol = 'GOOG'").show(100, false)
|
|
|
|
System.exit(0)
|