mirror of
https://github.com/apache/impala.git
synced 2026-01-17 21:00:36 -05:00
67bb870aa3
Before this patch if an argument of a GenericUDF was NULL, then Impala passed it as null instead of a DeferredObject. This was incorrect, as a DeferredObject is expected with a get() function that returns null. See the Jira for more details and GenericUDF examples in Hive. TestGenericUdf's NULL handling was further broken in IMPALA-11549, leading to throwing null pointer exceptions when the UDF's result is NULL. This test bug was not detected, because Hive udf tests were running with default abort_java_udf_on_exception=false, which means that exceptions from Hive UDFs only led to warnings and returning NULL, which was the expected result in all affected test queries. This patch fixes the behavior in HiveUdfExecutorGeneric and improves FE/EE tests to catch null handling related issues. Most Hive UDF tests are run with abort_java_udf_on_exception=true after this patch to treat exceptions in UDFs as errors. The ones where the test checks that NULL is returned if an exception is thrown while abort_java_udf_on_exception is false are moved to new .test files. TestGenericUdf is also fixed (and simplified) to handle NULL return values correctly. Change-Id: I53238612f4037572abb6d2cc913dd74ee830a9c9 Reviewed-on: http://gerrit.cloudera.org:8080/19499 Reviewed-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com> Tested-by: Impala Public Jenkins <impala-public-jenkins@cloudera.com>
338 lines
9.2 KiB
Plaintext
338 lines
9.2 KiB
Plaintext
====
|
|
---- QUERY
|
|
select hive_bround(cast(3.14 as double))
|
|
---- RESULTS
|
|
3.0
|
|
---- TYPES
|
|
DOUBLE
|
|
====
|
|
---- QUERY
|
|
select hive_bround(cast(3.14 as int))
|
|
---- RESULTS
|
|
3
|
|
---- TYPES
|
|
INT
|
|
====
|
|
---- QUERY
|
|
select hive_upper('hello')
|
|
---- RESULTS
|
|
'HELLO'
|
|
---- TYPES
|
|
STRING
|
|
====
|
|
---- QUERY
|
|
#Test GenericUDF functions
|
|
select generic_identity(true), generic_identity(cast(NULL as boolean)),
|
|
generic_identity_java_ret_type(true),
|
|
generic_identity_java_ret_type(cast(NULL as boolean));
|
|
---- TYPES
|
|
boolean, boolean, boolean, boolean
|
|
---- RESULTS
|
|
true,NULL,true,NULL
|
|
====
|
|
---- QUERY
|
|
select generic_identity(cast(10 as tinyint)), generic_identity(cast(NULL as tinyint)),
|
|
generic_identity_java_ret_type(cast(10 as tinyint)),
|
|
generic_identity_java_ret_type(cast(NULL as tinyint));
|
|
---- TYPES
|
|
tinyint, tinyint, tinyint, tinyint
|
|
---- RESULTS
|
|
10,NULL,10,NULL
|
|
====
|
|
---- QUERY
|
|
select generic_identity(cast(10 as smallint)), generic_identity(cast(NULL as smallint)),
|
|
generic_identity_java_ret_type(cast(10 as smallint)),
|
|
generic_identity_java_ret_type(cast(NULL as smallint));
|
|
---- TYPES
|
|
smallint, smallint, smallint, smallint
|
|
---- RESULTS
|
|
10,NULL,10,NULL
|
|
====
|
|
---- QUERY
|
|
select generic_identity(cast(10 as int)), generic_identity(cast(NULL as int)),
|
|
generic_identity_java_ret_type(cast(10 as int)),
|
|
generic_identity_java_ret_type(cast(NULL as int));
|
|
---- TYPES
|
|
int, int, int, int
|
|
---- RESULTS
|
|
10,NULL,10,NULL
|
|
====
|
|
---- QUERY
|
|
select generic_identity(cast(10 as bigint)), generic_identity(cast(NULL as bigint)),
|
|
generic_identity_java_ret_type(cast(10 as bigint)),
|
|
generic_identity_java_ret_type(cast(NULL as bigint));
|
|
---- TYPES
|
|
bigint, bigint, bigint, bigint
|
|
---- RESULTS
|
|
10,NULL,10,NULL
|
|
====
|
|
---- QUERY
|
|
select generic_identity(cast(10.0 as float)), generic_identity(cast(NULL as float)),
|
|
generic_identity_java_ret_type(cast(10.0 as float)),
|
|
generic_identity_java_ret_type(cast(NULL as float));
|
|
---- TYPES
|
|
float, float, float, float
|
|
---- RESULTS
|
|
10,NULL,10,NULL
|
|
====
|
|
---- QUERY
|
|
select generic_identity(cast(10.0 as double)), generic_identity(cast(NULL as double)),
|
|
generic_identity_java_ret_type(cast(10.0 as double)),
|
|
generic_identity_java_ret_type(cast(NULL as double));
|
|
---- TYPES
|
|
double, double, double, double
|
|
---- RESULTS
|
|
10,NULL,10,NULL
|
|
====
|
|
---- QUERY
|
|
select generic_identity(cast("a" as binary)), generic_identity(cast(NULL as binary)),
|
|
generic_identity_java_ret_type(cast("a" as binary)),
|
|
generic_identity_java_ret_type(cast(NULL as binary))
|
|
---- TYPES
|
|
binary, binary, binary, binary
|
|
---- RESULTS
|
|
'a','NULL','a','NULL'
|
|
====
|
|
---- QUERY
|
|
# IMPALA-1134. Tests that strings are copied correctly
|
|
select length(generic_identity("0123456789")),
|
|
length(generic_add("0123456789", "0123456789")),
|
|
length(generic_add("0123456789", "0123456789", "0123456789"));
|
|
---- TYPES
|
|
int, int, int
|
|
---- RESULTS
|
|
10,20,30
|
|
====
|
|
---- QUERY
|
|
# IMPALA-1134. Tests that binaries are copied correctly
|
|
select length(generic_identity(cast("0123456789" as binary))),
|
|
length(generic_add(cast("0123456789" as binary), cast("0123456789" as binary))),
|
|
length(generic_add(cast("0123456789" as binary), cast("0123456789" as binary),
|
|
cast("0123456789" as binary)));
|
|
---- TYPES
|
|
int, int, int
|
|
---- RESULTS
|
|
10,20,30
|
|
====
|
|
---- QUERY
|
|
# Test UDFs with java return types with multiple arguements.
|
|
select generic_add_java_ret_type(1, 2),
|
|
generic_add_java_ret_type("a", "bc", "d");
|
|
---- TYPES
|
|
int, string
|
|
---- RESULTS
|
|
3,'abcd'
|
|
====
|
|
---- QUERY
|
|
select generic_throws_exception();
|
|
---- CATCH
|
|
Test exception
|
|
====
|
|
---- QUERY
|
|
select generic_throws_exception() from functional.alltypestiny;
|
|
---- CATCH
|
|
Test exception
|
|
====
|
|
---- QUERY
|
|
select generic_add(cast(1 as int), cast(2 as int));
|
|
---- TYPES
|
|
int
|
|
---- RESULTS
|
|
3
|
|
====
|
|
---- QUERY
|
|
select generic_add(generic_add(cast(1 as int), cast(2 as int)), cast(2 as int));
|
|
---- TYPES
|
|
int
|
|
---- RESULTS
|
|
5
|
|
====
|
|
---- QUERY
|
|
select generic_add(cast(generic_add(cast(1 as int), cast(2 as int)) - generic_add(cast(2 as int), cast(1 as int)) as int), cast(2 as int));
|
|
---- TYPES
|
|
int
|
|
---- RESULTS
|
|
2
|
|
====
|
|
---- QUERY
|
|
select generic_add(cast(1 as smallint), cast(2 as smallint));
|
|
---- TYPES
|
|
smallint
|
|
---- RESULTS
|
|
3
|
|
====
|
|
---- QUERY
|
|
select generic_add(cast(3.0 as float), cast(4.0 as float));
|
|
---- TYPES
|
|
float
|
|
---- RESULTS
|
|
7.0
|
|
====
|
|
---- QUERY
|
|
select generic_add(cast(1.0 as double), cast(2.0 as double));
|
|
---- TYPES
|
|
double
|
|
---- RESULTS
|
|
3.0
|
|
====
|
|
---- QUERY
|
|
select generic_add(cast(1 as boolean), cast(0 as boolean));
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
true
|
|
====
|
|
---- QUERY
|
|
select generic_add(cast(1 as boolean), cast(1 as boolean));
|
|
---- TYPES
|
|
boolean
|
|
---- RESULTS
|
|
true
|
|
====
|
|
---- QUERY
|
|
# IMPALA-3378: test many Java UDFs being opened and run concurrently
|
|
select * from
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(bool_col) union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(tinyint_col) > 1 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(smallint_col) > 1 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(int_col) > 1 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(bigint_col) > 1 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(float_col) > 1.0 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(double_col) > 1.0 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(string_col) > '1' union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where not generic_identity(bool_col) union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(tinyint_col) > 2 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(smallint_col) > 2 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(int_col) > 2 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(bigint_col) > 2 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(float_col) > 2.0 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(double_col) > 2.0 union all
|
|
(select max(int_col) from functional.alltypesagg
|
|
where generic_identity(string_col) > '2'
|
|
)))))))))))))))) v
|
|
---- TYPES
|
|
INT
|
|
---- RESULTS
|
|
998
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
999
|
|
====
|
|
---- QUERY
|
|
drop table if exists replace_string_input
|
|
====
|
|
---- QUERY
|
|
create table replace_string_input as
|
|
values('toast'), ('scone'), ('stuff'), ('sssss'), ('yes'), ('scone'), ('stuff');
|
|
====
|
|
---- QUERY
|
|
# Regression test for IMPALA-4266: memory management bugs with output strings from
|
|
# Java UDFS, exposed by using the UDF as a grouping key in an aggregation.
|
|
# The UDF replaces "s" with "ss" in the strings.
|
|
select distinct generic_replace_string(_c0) as es
|
|
from replace_string_input
|
|
order by 1;
|
|
---- TYPES
|
|
string
|
|
---- RESULTS
|
|
'sscone'
|
|
'ssssssssss'
|
|
'sstuff'
|
|
'toasst'
|
|
'yess'
|
|
====
|
|
---- QUERY
|
|
# Regression test for IMPALA-8016; this UDF loads another class in the same jar.
|
|
select generic_import_nearby_classes("placeholder");
|
|
---- TYPES
|
|
string
|
|
---- RESULTS
|
|
'Hello'
|
|
====
|
|
---- QUERY
|
|
# Java Generic UDFs for DATE are not allowed yet
|
|
create function identity(Date) returns Date
|
|
location '$FILESYSTEM_PREFIX/test-warehouse/impala-hive-udfs.jar'
|
|
symbol='org.apache.impala.TestGenericUdf';
|
|
---- CATCH
|
|
AnalysisException: Type DATE is not supported for Java UDFs.
|
|
====
|
|
---- QUERY
|
|
# Java Generic UDFs for DECIMAL are not allowed yet
|
|
create function identity(decimal(5,0)) returns decimal(5,0)
|
|
location '$FILESYSTEM_PREFIX/test-warehouse/impala-hive-udfs.jar'
|
|
symbol='org.apache.impala.TestGenericUdf';
|
|
---- CATCH
|
|
AnalysisException: Type DECIMAL(5,0) is not supported for Java UDFs.
|
|
====
|
|
---- QUERY
|
|
# Java Generic UDFs for TIMESTAMP are not allowed yet
|
|
create function identity(Timestamp) returns Timestamp
|
|
location '$FILESYSTEM_PREFIX/test-warehouse/impala-hive-udfs.jar'
|
|
symbol='org.apache.impala.TestGenericUdf';
|
|
---- CATCH
|
|
AnalysisException: Type TIMESTAMP is not supported for Java UDFs.
|
|
====
|
|
---- QUERY
|
|
create function identity(ARRAY<STRING>) returns INT
|
|
location '$FILESYSTEM_PREFIX/test-warehouse/impala-hive-udfs.jar'
|
|
symbol='org.apache.impala.TestGenericUdf';
|
|
---- CATCH
|
|
AnalysisException: Type 'ARRAY<STRING>' is not supported in UDFs/UDAs.
|
|
====
|
|
---- QUERY
|
|
create function identity(MAP<STRING, STRING>) returns INT
|
|
location '$FILESYSTEM_PREFIX/test-warehouse/impala-hive-udfs.jar'
|
|
symbol='org.apache.impala.TestGenericUdf';
|
|
---- CATCH
|
|
AnalysisException: Type 'MAP<STRING,STRING>' is not supported in UDFs/UDAs.
|
|
====
|
|
---- QUERY
|
|
create function identity(STRUCT<employer: STRING>) returns INT
|
|
location '$FILESYSTEM_PREFIX/test-warehouse/impala-hive-udfs.jar'
|
|
symbol='org.apache.impala.TestGenericUdf';
|
|
---- CATCH
|
|
AnalysisException: Type 'STRUCT<employer:STRING>' is not supported in UDFs/UDAs.
|
|
====
|
|
---- QUERY
|
|
create function generic_add_fail(smallint, smallint) returns int
|
|
location '$FILESYSTEM_PREFIX/test-warehouse/impala-hive-udfs.jar'
|
|
symbol='org.apache.impala.TestGenericUdf';
|
|
---- CATCH
|
|
CatalogException: Function expected return type smallint but was created with INT
|
|
====
|
|
---- QUERY
|
|
create function var_args_func(int...) returns int
|
|
location '$FILESYSTEM_PREFIX/test-warehouse/impala-hive-udfs.jar'
|
|
symbol='org.apache.impala.TestUdf';
|
|
---- CATCH
|
|
CatalogException: Variable arguments not supported in Hive UDFs.
|
|
====
|