[
https://issues.apache.org/jira/browse/HUDI-5977?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
voon updated HUDI-5977:
-----------------------
Description:
When a Date -> String type conversion is performed and when the non-vectorized
reader is used, the table becomes unreadable.
Test casae to replicate this issue
{code:java}
test("Test Date -> String conversion when vectorized reading is not enabled") {
val tableName = generateTableName
spark.sql(
s"""
| create table $tableName (
| id int,
| name string,
| price double,
| ts long
|) using hudi
| partitioned by (ts)
|tblproperties (
| primaryKey = 'id'
)
""".stripMargin)
spark.sql(
s"""
| insert into $tableName
| select 1 as id, 'a1' as name, 10 as price, 1000 as ts
""".stripMargin)
spark.sql("set hoodie.schema.on.read.enable = true") // adding a struct
column to force reads reads to fallback to non-vectorized reading
spark.sql(s"alter table $tableName add column (`new_struct_col` STRUCT<f0:
INTEGER, f1: STRING>)")
spark.sql(
s"""
| insert into $tableName
| values (2, 'a2', 20, struct(2, 'f_2'), 1001)
""".stripMargin) spark.sql(s"alter table $tableName add column
(`date_to_string_col` date)")
spark.sql(
s"""
| insert into $tableName
| values (3, 'a3', 30, struct(3, 'f_3'), date '2023-03-22', 1002)
""".stripMargin)
spark.sql(s"alter table $tableName alter column `date_to_string_col` type
string")
spark.sql(s"select * from $tableName").show(false)
}{code}
was:
When a Date -> String type conversion is performed and when the non-vectorized
reader is used, the table becomes unreadable.
Test casae to replicate this issue
{code:java}
test("Test Date -> String conversion when vectorized reading is not enabled") {
val tableName = generateTableName
spark.sql(
s"""
| create table $tableName (
| id int,
| name string,
| price double,
| ts long
|) using hudi
| partitioned by (ts)
|tblproperties (
| primaryKey = 'id'
)
""".stripMargin)
spark.sql(
s"""
| insert into $tableName
| select 1 as id, 'a1' as name, 10 as price, 1000 as ts
""".stripMargin)
spark.sql("set hoodie.schema.on.read.enable = true") // adding a struct
column to force reads future reads to fallback to a non-vectorized reader
spark.sql(s"alter table $tableName add column (`new_struct_col` STRUCT<f0:
INTEGER, f1: STRING>)")
spark.sql(
s"""
| insert into $tableName
| values (2, 'a2', 20, struct(2, 'f_2'), 1001)
""".stripMargin) spark.sql(s"alter table $tableName add column
(`date_to_string_col` date)")
spark.sql(
s"""
| insert into $tableName
| values (3, 'a3', 30, struct(3, 'f_3'), date '2023-03-22', 1002)
""".stripMargin)
spark.sql(s"alter table $tableName alter column `date_to_string_col` type
string")
spark.sql(s"select * from $tableName").show(false)
}{code}
> Fix Date to String casts when non-vectorized reader is used
> -----------------------------------------------------------
>
> Key: HUDI-5977
> URL: https://issues.apache.org/jira/browse/HUDI-5977
> Project: Apache Hudi
> Issue Type: Bug
> Reporter: voon
> Assignee: voon
> Priority: Major
>
> When a Date -> String type conversion is performed and when the
> non-vectorized reader is used, the table becomes unreadable.
>
> Test casae to replicate this issue
>
> {code:java}
> test("Test Date -> String conversion when vectorized reading is not enabled")
> {
> val tableName = generateTableName
> spark.sql(
> s"""
> | create table $tableName (
> | id int,
> | name string,
> | price double,
> | ts long
> |) using hudi
> | partitioned by (ts)
> |tblproperties (
> | primaryKey = 'id'
> )
> """.stripMargin)
> spark.sql(
> s"""
> | insert into $tableName
> | select 1 as id, 'a1' as name, 10 as price, 1000 as ts
> """.stripMargin)
> spark.sql("set hoodie.schema.on.read.enable = true") // adding a struct
> column to force reads reads to fallback to non-vectorized reading
> spark.sql(s"alter table $tableName add column (`new_struct_col` STRUCT<f0:
> INTEGER, f1: STRING>)")
> spark.sql(
> s"""
> | insert into $tableName
> | values (2, 'a2', 20, struct(2, 'f_2'), 1001)
> """.stripMargin) spark.sql(s"alter table $tableName add column
> (`date_to_string_col` date)")
> spark.sql(
> s"""
> | insert into $tableName
> | values (3, 'a3', 30, struct(3, 'f_3'), date '2023-03-22', 1002)
> """.stripMargin)
> spark.sql(s"alter table $tableName alter column `date_to_string_col` type
> string")
> spark.sql(s"select * from $tableName").show(false)
> }{code}
>
>
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
