mirror of
https://github.com/apache/impala.git
synced 2026-01-06 15:01:43 -05:00
fc7733d530
Fixes a bug (regression) where the catalog server was not properly resolving column names when a table's column definition did not match its Avro schema definition. The expected behavior in this case is that the the Avro scehma definition should be used instead of the table columns. We had no test tables that were mismatched so this wasn't caught. This loading of the schema and columns happens when a table's metadata is loaded, so the fix is to just add a toThrift() to Column and not reference metastore.getSd().getCols() directly since it might be the "wrong" set of columns. Change-Id: I341a3a8834f5748f90c246d2093ddb983ecfdd4f Reviewed-on: http://gerrit.ent.cloudera.com:8080/770 Reviewed-by: Lenni Kuff <lskuff@cloudera.com> Tested-by: Lenni Kuff <lskuff@cloudera.com>
30 lines
1.4 KiB
SQL
30 lines
1.4 KiB
SQL
USE functional_avro_snap;
|
|
|
|
DROP TABLE IF EXISTS schema_resolution_test;
|
|
|
|
-- Specify the Avro schema in SERDEPROPERTIES instead of TBLPROPERTIES to validate
|
|
-- IMPALA-538. Also, give the table a different column definition (col1, col2) than what
|
|
-- is defined in the Avro schema for testing mismatched table/deserializer schemas.
|
|
CREATE EXTERNAL TABLE schema_resolution_test (col1 string, col2 string)
|
|
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
|
|
WITH SERDEPROPERTIES ('avro.schema.literal'='{
|
|
"name": "a",
|
|
"type": "record",
|
|
"fields": [
|
|
{"name":"boolean1", "type":"boolean", "default": true},
|
|
{"name":"int1", "type":"int", "default": 1},
|
|
{"name":"long1", "type":"long", "default": 1},
|
|
{"name":"float1", "type":"float", "default": 1.0},
|
|
{"name":"double1", "type":"double", "default": 1.0},
|
|
{"name":"string1", "type":"string", "default": "default string"},
|
|
{"name":"string2", "type": ["string", "null"], "default": ""},
|
|
{"name":"string3", "type": ["null", "string"], "default": null}
|
|
]}')
|
|
STORED AS
|
|
INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
|
|
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
|
|
LOCATION '${hiveconf:hive.metastore.warehouse.dir}/avro_schema_resolution_test/';
|
|
|
|
LOAD DATA LOCAL INPATH 'records1.avro' OVERWRITE INTO TABLE schema_resolution_test;
|
|
LOAD DATA LOCAL INPATH 'records2.avro' INTO TABLE schema_resolution_test;
|