mirror of
https://github.com/apache/impala.git
synced 2026-01-22 18:02:34 -05:00
a154b2d6e7
Testing: Added regression test based on JIRA and a targeted test for all HDFS file formats. Change-Id: I7a927c6a4f0b8055608cb7a5e2b550a1610cef89 Reviewed-on: http://gerrit.cloudera.org:8080/12332 Reviewed-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
41 lines
1.1 KiB
Plaintext
41 lines
1.1 KiB
Plaintext
====
|
|
---- QUERY
|
|
# Check that data from mixed format partitions can be read
|
|
# transparently. Compute sum in order to force deserialisation
|
|
select count(*), sum(int_col) from functional.alltypesmixedformat
|
|
---- TYPES
|
|
bigint, bigint
|
|
---- RESULTS
|
|
1200,5400
|
|
====
|
|
---- QUERY
|
|
# Restrict set of partitions (still multi-format)
|
|
select count(*), sum(int_col) from functional.alltypesmixedformat where month = 1 or month = 3
|
|
---- TYPES
|
|
bigint, bigint
|
|
---- RESULTS
|
|
620,2790
|
|
====
|
|
---- QUERY
|
|
# Read single partition alone
|
|
select count(*), sum(int_col) from functional.alltypesmixedformat where month = 2
|
|
---- TYPES
|
|
bigint, bigint
|
|
---- RESULTS
|
|
280,1260
|
|
====
|
|
---- QUERY
|
|
# IMPALA-5861: RowsRead counter should be accurate for table scan that returns
|
|
# zero slots. This test is run with various batch_size values, which helps
|
|
# reproduce the bug. Scanning multiple file formats triggers the bug because
|
|
# the Parquet count(*) rewrite is disabled when non-Parquet file formats are
|
|
# present.
|
|
select count(*) from functional.alltypesmixedformat
|
|
---- TYPES
|
|
bigint
|
|
---- RESULTS
|
|
1200
|
|
---- RUNTIME_PROFILE
|
|
aggregation(SUM, RowsRead): 1200
|
|
====
|