mirror of
https://github.com/apache/impala.git
synced 2025-12-30 12:02:10 -05:00
dee6911b20
This patch contains the following changes:
- Add a metastore_snapshot_file parameter to build.sh
- Enable skipping loading the metadata.
- create-load-data.sh is refactored into functions.
- A lot of scripts source impala-config, which creates a lot of log spew. This has now
been muted.
- Unecessary log spew from compute-table-stats has been muted.
- build_thirdparty.sh determins its parallelism from the system, it was previously hard
coded to 4
- Only force load data of the particular dataset if a schema change is detected.
Change-Id: I909336451e5c1ca57d21f040eb94c0e831546837
Reviewed-on: http://gerrit.sjc.cloudera.com:8080/5540
Reviewed-by: Ishaan Joshi <ishaan@cloudera.com>
Tested-by: jenkins
61 lines
2.4 KiB
SQL
61 lines
2.4 KiB
SQL
-- Create and load tables that depend upon data in the hive test-warehouse already existing
|
|
|
|
-- Load a mixed-format table. Hive behaves oddly when mixing formats,
|
|
-- but the following incantation ensures that the result is a
|
|
-- three-partition table. First is text format, second is sequence
|
|
-- file, third is RC file. Must be called after test-warehouse is
|
|
-- successfully populated
|
|
USE functional;
|
|
DROP TABLE IF EXISTS alltypesmixedformat;
|
|
CREATE EXTERNAL TABLE alltypesmixedformat (
|
|
id int,
|
|
bool_col boolean,
|
|
tinyint_col tinyint,
|
|
smallint_col smallint,
|
|
int_col int,
|
|
bigint_col bigint,
|
|
float_col float,
|
|
double_col double,
|
|
date_string_col string,
|
|
string_col string,
|
|
timestamp_col timestamp)
|
|
partitioned by (year int, month int)
|
|
row format delimited fields terminated by ',' escaped by '\\'
|
|
stored as TEXTFILE
|
|
LOCATION '${hiveconf:hive.metastore.warehouse.dir}/alltypesmixedformat';
|
|
|
|
INSERT OVERWRITE TABLE alltypesmixedformat PARTITION (year=2009, month=1)
|
|
SELECT id, bool_col, tinyint_col, smallint_col, int_col, bigint_col,
|
|
float_col, double_col, date_string_col, string_col, timestamp_col
|
|
FROM alltypes
|
|
WHERE year=2009 and month=1;
|
|
|
|
ALTER TABLE alltypesmixedformat SET FILEFORMAT SEQUENCEFILE;
|
|
LOAD DATA INPATH '/tmp/alltypes_seq/year=2009/month=2/'
|
|
OVERWRITE INTO TABLE alltypesmixedformat PARTITION (year=2009, month=2);
|
|
|
|
ALTER TABLE alltypesmixedformat SET FILEFORMAT RCFILE;
|
|
LOAD DATA INPATH '/tmp/alltypes_rc/year=2009/month=3/'
|
|
OVERWRITE INTO TABLE alltypesmixedformat PARTITION (year=2009, month=3);
|
|
|
|
ALTER TABLE alltypesmixedformat PARTITION (year=2009, month=1)
|
|
SET SERDEPROPERTIES('field.delim'=',', 'escape.delim'='\\');
|
|
ALTER TABLE alltypesmixedformat PARTITION (year=2009, month=1)
|
|
SET FILEFORMAT TEXTFILE;
|
|
ALTER TABLE alltypesmixedformat PARTITION (year=2009, month=2)
|
|
SET SERDEPROPERTIES('field.delim'=',', 'escape.delim'='\\');
|
|
ALTER TABLE alltypesmixedformat PARTITION (year=2009, month=2)
|
|
SET FILEFORMAT SEQUENCEFILE;
|
|
ALTER TABLE alltypesmixedformat PARTITION (year=2009, month=3)
|
|
SET FILEFORMAT RCFILE;
|
|
|
|
---- Unsupported Impala table types
|
|
USE functional;
|
|
CREATE VIEW IF NOT EXISTS hive_view AS SELECT 1 AS int_col FROM alltypes limit 1;
|
|
|
|
USE functional;
|
|
DROP INDEX IF EXISTS hive_index ON alltypes;
|
|
CREATE INDEX hive_index ON TABLE alltypes (int_col)
|
|
AS 'org.apache.hadoop.hive.ql.index.compact.CompactIndexHandler'
|
|
WITH DEFERRED REBUILD IN TABLE hive_index_tbl
|