jprdonnelly/impala
1
0
Fork 0
mirror of https://github.com/apache/impala.git synced 2026-01-09 06:05:09 -05:00
Code Issues Projects Releases Wiki Activity
Files
6f1fe4ebe7ca9998218e0909b4ea6f8b2d27f31a
impala/testdata/avro_schema_resolution/create_table.sql
Anuj Phadke a915293109 IMPALA-1850: Allow fs.defaultFS to be set to a non-HDFS filesystem 
This change whitelists the supported filesystems which can be set
as Default FS for Impala to run on.
This patch configures Impala to use S3 as the default filesystem, rather
than a secondary filesystem as before.

Change-Id: I2f45bef6c94ece634045acb906d12591587ccfed
Reviewed-on: http://gerrit.cloudera.org:8080/1121
Reviewed-by: anujphadke <aphadke@cloudera.com>
Tested-by: Internal Jenkins
2016-05-12 14:17:40 -07:00

190 lines
7.4 KiB
SQL
Raw Blame History

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 '${hiveconf:hive.metastore.warehouse.dir}/avro_schema_resolution_test/';
LOAD DATA LOCAL INPATH '${env:IMPALA_HOME}/testdata/avro_schema_resolution/records1.avro' OVERWRITE INTO TABLE schema_resolution_test;
LOAD DATA LOCAL INPATH '${env:IMPALA_HOME}/testdata/avro_schema_resolution/records2.avro' INTO TABLE schema_resolution_test;
-- The following tables are used to test Impala's handling of HIVE-6308 which causes
-- COMPUTE STATS and Hive's ANALYZE TABLE to fail for Avro tables with mismatched
-- column definitions and Avro-schema columns. In such cases, COMPUTE STATS is expected to
-- fail in analysis and not after actually computing stats (IMPALA-867).
-- TODO: The creation of these tables should migrate into our regular data loading
-- framework. There are issues with beeline for these CREATE TABLE stmts (NPEs).
-- No explicit column definitions for an Avro table.
DROP TABLE IF EXISTS alltypes_no_coldef;
CREATE EXTERNAL TABLE IF NOT EXISTS alltypes_no_coldef
ROW FORMAT SERDE 'org.apache.hadoop.hive.serde2.avro.AvroSerDe'
STORED AS
INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
LOCATION '/test-warehouse/alltypes_avro_snap'
TBLPROPERTIES ('avro.schema.url'='${env:DEFAULT_FS}/${hiveconf:hive.metastore.warehouse.dir}/avro_schemas/functional/alltypes.json');
-- Column definition list has one more column than the Avro schema.
DROP TABLE IF EXISTS alltypes_extra_coldef;
CREATE EXTERNAL TABLE IF NOT EXISTS alltypes_extra_coldef (
id int,
bool_col boolean,
tinyint_col tinyint,
smallint_col smallint,
int_col int,
bigint_col bigint,
float_col float,
double_col double,
date_string_col string,
string_col string,
timestamp_col timestamp,
extra_col string)
PARTITIONED BY (year int, month int)
STORED AS
INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
LOCATION '/test-warehouse/alltypes_avro_snap'
TBLPROPERTIES ('avro.schema.url'='${env:DEFAULT_FS}/${hiveconf:hive.metastore.warehouse.dir}/avro_schemas/functional/alltypes.json');
-- Column definition list is missing 'tinyint_col' and 'timestamp_col' from the Avro schema.
DROP TABLE IF EXISTS alltypes_missing_coldef;
CREATE EXTERNAL TABLE IF NOT EXISTS alltypes_missing_coldef (
id int,
bool_col boolean,
smallint_col smallint,
int_col int,
bigint_col bigint,
float_col float,
double_col double,
date_string_col string,
string_col string)
PARTITIONED BY (year int, month int)
STORED AS
INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
LOCATION '/test-warehouse/alltypes_avro_snap'
TBLPROPERTIES ('avro.schema.url'='${env:DEFAULT_FS}/${hiveconf:hive.metastore.warehouse.dir}/avro_schemas/functional/alltypes.json');
-- Matching number of columns and column names, but mismatched type (bigint_col is a string).
DROP TABLE IF EXISTS alltypes_type_mismatch;
CREATE EXTERNAL TABLE IF NOT EXISTS alltypes_type_mismatch (
id int,
bool_col boolean,
tinyint_col tinyint,
smallint_col smallint,
int_col int,
bigint_col string,
float_col float,
double_col double,
date_string_col string,
string_col string,
timestamp_col timestamp)
PARTITIONED BY (year int, month int)
STORED AS
INPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerInputFormat'
OUTPUTFORMAT 'org.apache.hadoop.hive.ql.io.avro.AvroContainerOutputFormat'
LOCATION '/test-warehouse/alltypes_avro_snap'
TBLPROPERTIES ('avro.schema.url'='${env:DEFAULT_FS}/${hiveconf:hive.metastore.warehouse.dir}/avro_schemas/functional/alltypes.json');
-- IMPALA-2798, create two avro tables with same underlying data location, one table
-- has an extra column at the end. Validate Impala doesn't use codegen decoding function
-- if table schema is not the same as file schema.
DROP TABLE IF EXISTS avro_coldef;
CREATE EXTERNAL TABLE IF NOT EXISTS avro_coldef (
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 timestamp)
PARTITIONED BY (year int, month int)
STORED AS avro
LOCATION '/test-warehouse/avro_coldef_snap'
TBLPROPERTIES ('avro.schema.literal'='{
"name": "a",
"type": "record",
"fields": [
{"name":"bool_col", "type":"boolean"},
{"name":"tinyint_col", "type":"int"},
{"name":"smallint_col", "type":"int"},
{"name":"int_col", "type":"int"},
{"name":"bigint_col", "type":"long"},
{"name":"float_col", "type":"float"},
{"name":"double_col", "type": "double"},
{"name":"date_string_col", "type": "string"},
{"name":"string_col", "type": "string"},
{"name":"timestamp_col", "type": "long"}
]}');
INSERT OVERWRITE TABLE avro_coldef PARTITION(year=2014, month=1)
SELECT bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col, timestamp_col
FROM (select * from functional.alltypes order by id limit 5) a;
DROP TABLE IF EXISTS avro_extra_coldef;
CREATE EXTERNAL TABLE IF NOT EXISTS avro_extra_coldef (
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 timestamp,
extra_col string)
PARTITIONED BY (year int, month int)
STORED AS avro
LOCATION '/test-warehouse/avro_coldef_snap'
TBLPROPERTIES ('avro.schema.literal'='{
"name": "a",
"type": "record",
"fields": [
{"name":"bool_col", "type":"boolean"},
{"name":"tinyint_col", "type":"int"},
{"name":"smallint_col", "type":"int"},
{"name":"int_col", "type":"int"},
{"name":"bigint_col", "type":"long"},
{"name":"float_col", "type":"float"},
{"name":"double_col", "type": "double"},
{"name":"date_string_col", "type": "string"},
{"name":"string_col", "type": "string"},
{"name":"timestamp_col", "type": "long"},
{"name":"extra_col", "type": "string", "default": "null"}
]}');
INSERT OVERWRITE TABLE avro_extra_coldef PARTITION(year=2014, month=2)
SELECT bool_col, tinyint_col, smallint_col, int_col, bigint_col,
float_col, double_col, date_string_col, string_col,
timestamp_col, "avro" AS extra_col FROM
(select * from functional.alltypes order by id limit 5) a;
MSCK REPAIR TABLE avro_coldef;
MSCK REPAIR TABLE avro_extra_coldef;
Reference in New Issue View Git Blame Copy Permalink