mirror of
https://github.com/apache/impala.git
synced 2026-01-04 18:00:57 -05:00
c6ce32b3b6
Since it is possible to create an Avro table with both column definitions and an Avro schema, Impala attempts to reconcile inconsistencies in the two schema definitions, generally preferring the Avro schema. The only exception to this rule was with CHAR/VARCHAR/STRING columns, where the column definition was preferred in order to support tables with CHAR/VARCHAR columns although Avro only supports STRING. This exception is confusing because the name for such a column will be taken from the column definition (and not from the Avro schema). This patch prefers name, comment from Avro schema definition and uses column type from column definition for CHAR/VARCHAR/STRING columns. Change-Id: Ia3e43b2885853c2b4f207a45a873c9d7f31379cd Reviewed-on: http://gerrit.cloudera.org:8080/3331 Reviewed-by: Huaisi Xu <hxu@cloudera.com> Tested-by: Internal Jenkins
70 lines
2.0 KiB
Plaintext
70 lines
2.0 KiB
Plaintext
====
|
|
---- QUERY
|
|
# Create a table with default fileformat and later change it to Avro using
|
|
# alter sql. The query runs with stale metadata and a warning should be raised.
|
|
# Invalidating metadata should cause the Avro schema to be properly set upon the
|
|
# next metadata load.
|
|
CREATE EXTERNAL TABLE alltypesagg_staleschema (
|
|
id INT,
|
|
bool_col BOOLEAN,
|
|
tinyint_col INT,
|
|
smallint_col INT,
|
|
int_col INT,
|
|
bigint_col BIGINT,
|
|
float_col FLOAT,
|
|
double_col DOUBLE,
|
|
date_string_col STRING,
|
|
string_col STRING,
|
|
timestamp_col STRING
|
|
)
|
|
LOCATION '$FILESYSTEM_PREFIX/test-warehouse/alltypesaggmultifilesnopart_avro_snap'
|
|
TBLPROPERTIES ('avro.schema.url'= '$FILESYSTEM_PREFIX/test-warehouse/avro_schemas/functional/alltypesaggmultifilesnopart.json')
|
|
====
|
|
---- QUERY
|
|
alter table alltypesagg_staleschema set fileformat avro
|
|
====
|
|
---- QUERY
|
|
select count(*) from alltypesagg_staleschema
|
|
---- CATCH
|
|
Missing Avro schema in scan node. This could be due to stale metadata.
|
|
====
|
|
---- QUERY
|
|
invalidate metadata alltypesagg_staleschema
|
|
====
|
|
---- QUERY
|
|
select count(*) from alltypesagg_staleschema
|
|
---- RESULTS
|
|
11000
|
|
---- TYPES
|
|
bigint
|
|
====
|
|
---- QUERY
|
|
# IMPALA-3092. Create an Avro table without column definitions and add columns via ALTER
|
|
# TABLE. Querying the table should work.
|
|
CREATE EXTERNAL TABLE avro_alter_table_add_new_column (
|
|
a string,
|
|
b string)
|
|
STORED AS AVRO
|
|
LOCATION '$FILESYSTEM_PREFIX/test-warehouse/tinytable_avro';
|
|
|
|
ALTER TABLE avro_alter_table_add_new_column ADD COLUMNS (
|
|
bool_col boolean,
|
|
int_col int,
|
|
bigint_col bigint,
|
|
float_col float,
|
|
double_col double,
|
|
timestamp_col timestamp,
|
|
decimal_col decimal(2,0),
|
|
string_col string)
|
|
====
|
|
---- QUERY
|
|
# Every new column just added should have NULL filled
|
|
select * from avro_alter_table_add_new_column
|
|
---- RESULTS
|
|
'aaaaaaa','bbbbbbb',NULL,NULL,NULL,NULL,NULL,'NULL',NULL,'NULL'
|
|
'ccccc','dddd',NULL,NULL,NULL,NULL,NULL,'NULL',NULL,'NULL'
|
|
'eeeeeeee','f',NULL,NULL,NULL,NULL,NULL,'NULL',NULL,'NULL'
|
|
---- TYPES
|
|
string, string, boolean, int, bigint, float, double, string, decimal, string
|
|
====
|