[
https://issues.apache.org/jira/browse/IMPALA-12742?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17809492#comment-17809492
]
Noemi Pap-Takacs edited comment on IMPALA-12742 at 1/22/24 3:00 PM:
--------------------------------------------------------------------
Steps to reproduce the issue:
1. CREATE V2 TABLE based on 'functional_parquet.iceberg_alltypes_part'
{code:java}
create table ice_alltypes_part_v2
(i INT NULL, p_bool BOOLEAN NULL, p_int INT NULL, p_bigint BIGINT NULL, p_float
FLOAT NULL, p_double DOUBLE NULL, p_decimal DECIMAL(6,3) NULL, p_date DATE
NULL, p_string STRING NULL)
PARTITIONED BY SPEC(p_bool, p_int, p_bigint, p_float, p_double, p_decimal,
p_date, p_string) STORED AS ICEBERG
TBLPROPERTIES ('engine.hive.enabled'='true',
'iceberg.catalog'='hadoop.catalog',
'iceberg.catalog_location'='/test-warehouse/iceberg_test/hadoop_catalog',
'format-version'='2'){code}
2. INSERT DATA
{code:java}
insert into ice_alltypes_part_v2 select * from
functional_parquet.iceberg_alltypes_part;{code}
select * from ice_alltypes_part_v2;
|i|p_bool|p_int|p_bigint|p_float|p_double|p_decimal|p_date|p_string|
|1|true|1|11|1.10000002384|2.222|123.321|2022-02-22|impala|
|2|true|1|11|1.10000002384|2.222|123.321|2022-02-22|impala|
3. DELETE or UPDATE
{code:java}
delete from ice_alltypes_part_v2 where i=1;{code}
or
{code:java}
update ice_alltypes_part_v2 set p_bigint=100 where p_int=1;
{code}
ERROR: DateTimeParseException: Text '19045' could not be parsed at index 0
impalad logs:
{code:java}
client-request-state.cc:1537] Updating metastore with 2 altered partitions
(p_bool=true/p_int=1/p_bigint=100/p_float=1.100000023841858/p_double=2.222/p_decimal=123.321/p_date=2022-02-22/p_string=impala,
p_bool=true/p_int=1/p_bigint=11/p_float=1.1/p_double=2.222/p_decimal=123.321/p_date=19045/p_string=impala)
client-request-state.cc:1564] Executing FinalizeDml() using CatalogService
client-request-state.cc:1574] ERROR Finalizing DML: DateTimeParseException:
Text '19045' could not be parsed at index 0
{code}
catalogd logs:
{code:java}
java.time.format.DateTimeParseException: Text '19045' could not be parsed at
index 0
at
java.time.format.DateTimeFormatter.parseResolved0(DateTimeFormatter.java:1949)
at java.time.format.DateTimeFormatter.parse(DateTimeFormatter.java:1851)
at java.time.LocalDate.parse(LocalDate.java:400)
at
org.apache.iceberg.expressions.Literals$StringLiteral.to(Literals.java:495)
at
org.apache.iceberg.types.Conversions.fromPartitionString(Conversions.java:70)
at
org.apache.impala.util.IcebergUtil.getPartitionValue(IcebergUtil.java:780)
at
org.apache.impala.util.IcebergUtil.partitionDataFromDataFile(IcebergUtil.java:758)
at
org.apache.impala.service.IcebergCatalogOpExecutor.createDeleteFile(IcebergCatalogOpExecutor.java:443)
{code}
was (Author: noemi):
Steps to reproduce the issue:
1. CREATE V2 TABLE based on 'functional_parquet.iceberg_alltypes_part'
create table ice_alltypes_part_v2
(i INT NULL, p_bool BOOLEAN NULL, p_int INT NULL, p_bigint BIGINT NULL, p_float
FLOAT NULL, p_double DOUBLE NULL, p_decimal DECIMAL(6,3) NULL, p_date DATE
NULL, p_string STRING NULL)
PARTITIONED BY SPEC(p_bool, p_int, p_bigint, p_float, p_double, p_decimal,
p_date, p_string) STORED AS ICEBERG
TBLPROPERTIES ('engine.hive.enabled'='true',
'iceberg.catalog'='hadoop.catalog',
'iceberg.catalog_location'='/test-warehouse/iceberg_test/hadoop_catalog',
'format-version'='2')
2. INSERT DATA
{code:java}
insert into ice_alltypes_part_v2 select * from
functional_parquet.iceberg_alltypes_part;{code}
select * from ice_alltypes_part_v2;
+---+--------+-------+----------+---------------+----------+-----------+------------+----------+
| i | p_bool | p_int | p_bigint | p_float | p_double | p_decimal | p_date
| p_string |
+---+--------+-------+----------+---------------+----------+-----------+------------+----------+
| 1 | true | 1 | 11 | 1.10000002384 | 2.222 | 123.321 |
2022-02-22 | impala |
| 2 | true | 1 | 11 | 1.10000002384 | 2.222 | 123.321 |
2022-02-22 | impala |
+---+--------+-------+----------+---------------+----------+-----------+------------+----------+
3. DELETE or UPDATE
{code:java}
delete from ice_alltypes_part_v2 where i=1;{code}
or
{code:java}
update ice_alltypes_part_v2 set p_bigint=100 where p_int=1;
{code}
ERROR: DateTimeParseException: Text '19045' could not be parsed at index 0
impalad logs:
{code:java}
client-request-state.cc:1537] Updating metastore with 2 altered partitions
(p_bool=true/p_int=1/p_bigint=100/p_float=1.100000023841858/p_double=2.222/p_decimal=123.321/p_date=2022-02-22/p_string=impala,
p_bool=true/p_int=1/p_bigint=11/p_float=1.1/p_double=2.222/p_decimal=123.321/p_date=19045/p_string=impala)
client-request-state.cc:1564] Executing FinalizeDml() using CatalogService
client-request-state.cc:1574] ERROR Finalizing DML: DateTimeParseException:
Text '19045' could not be parsed at index 0
{code}
catalogd logs:
{code:java}
java.time.format.DateTimeParseException: Text '19045' could not be parsed at
index 0
at
java.time.format.DateTimeFormatter.parseResolved0(DateTimeFormatter.java:1949)
at java.time.format.DateTimeFormatter.parse(DateTimeFormatter.java:1851)
at java.time.LocalDate.parse(LocalDate.java:400)
at
org.apache.iceberg.expressions.Literals$StringLiteral.to(Literals.java:495)
at
org.apache.iceberg.types.Conversions.fromPartitionString(Conversions.java:70)
at
org.apache.impala.util.IcebergUtil.getPartitionValue(IcebergUtil.java:780)
at
org.apache.impala.util.IcebergUtil.partitionDataFromDataFile(IcebergUtil.java:758)
at
org.apache.impala.service.IcebergCatalogOpExecutor.createDeleteFile(IcebergCatalogOpExecutor.java:443)
{code}
> DELETE/UPDATE Iceberg table partitioned by DATE gives incorrect value
> ---------------------------------------------------------------------
>
> Key: IMPALA-12742
> URL: https://issues.apache.org/jira/browse/IMPALA-12742
> Project: IMPALA
> Issue Type: Bug
> Components: Backend, Catalog
> Reporter: Noemi Pap-Takacs
> Priority: Major
> Labels: impala-iceberg
>
> Iceberg tables can be identity partitioned by any type, e.g. int, date and
> even float.
> If a table is partitioned, the file path contains the partition value in
> human readable form. When an UPDATE or DELETE command is executed, the delete
> file contains the file path to the referenced data file. It seems that DATE
> type is converted to this form incorrectly, and cannot be parsed by the
> Catalog and throws an error.
>
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-all-unsubscr...@impala.apache.org
For additional commands, e-mail: issues-all-h...@impala.apache.org
