jonvex commented on issue #9333:
URL: https://github.com/apache/hudi/issues/9333#issuecomment-1665803100
I tried the following with Hudi 0.12.0 Spark 3.2.3 and it failed with the
exception `java.lang.IllegalArgumentException: Wrong basePath
file:/tmp/test2/A2 for the root path: file:/tmp/test2/B2/.hoodie`
Is there anything I am missing from my setup?
```
val basePath = "/tmp/test2"
val tableA = "A2"
val tableB = "B2"
// Create source table
spark.sql(
s"""
| create table $tableA (
| id int,
| name string,
| price double,
| ts long
| ) using hudi
| location '$basePath/$tableA'
| tblproperties (
| primaryKey ='id',
| preCombineField = 'ts'
| )
""".stripMargin)
// Create target table
spark.sql(
s"""
|create table $tableB (
| id int,
| name string,
| price double,
| ts long
|) using hudi
| location '$basePath/$tableB'
| tblproperties (
| primaryKey ='id',
| preCombineField = 'ts'
| )
""".stripMargin)
// Insert data to source table
spark.sql(s"insert into $tableA values(1, 'a1', 10, 1000)")
spark.sql(s"insert into $tableA values(2, 'a2', 11, 1000)")
spark.sql(s"insert into $tableB values(3, 'a3', 12, 1000)")
spark.sql(s"insert into $tableB values(4, 'a4', 13, 1000)")
val path_A = s"$basePath/$tableA/*"
val path_B = s"$basePath/$tableB/*"
val multi_path = path_A + "," + path_B
val df =
spark.read.format("hudi").option("hoodie.datasource.query.type",
"read_optimized").option("hoodie.datasource.read.paths", multi_path).load()
df.show(100,false)
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
