Spark:3.2
StarRocks:2.5.12
主键模型，建表语句如下，分区字段是 date 类型
CREATE TABLE test_user (
user_id bigint(20) NOT NULL DEFAULT “0” COMMENT “id 。”,
user_name varchar(65533) NOT NULL DEFAULT “0” COMMENT “name 。”,
state_time date NOT NULL DEFAULT “1971-01-01” COMMENT “time。”,
) ENGINE=OLAP
PRIMARY KEY( user_id , state_time )
COMMENT “test”
PARTITION BY RANGE( state_time )
(PARTITION p20231218 VALUES [(“2023-12-18”), (“2023-12-19”)),
)
DISTRIBUTED BY HASH( user_id ) BUCKETS 10
PROPERTIES (
“replication_num” = “3”,
“dynamic_partition.enable” = “true”,
“dynamic_partition.time_unit” = “DAY”,
“dynamic_partition.time_zone” = “Asia/Shanghai”,
“dynamic_partition.start” = “-66”,
“dynamic_partition.end” = “1”,
“dynamic_partition.prefix” = “p”,
“dynamic_partition.buckets” = “10”,
“dynamic_partition.history_partition_num” = “0”,
“in_memory” = “false”,
“storage_format” = “DEFAULT”,
“enable_persistent_index” = “false”,
“compression” = “LZ4”
);
临时视图：
create temporary view sr_temp_table USING starrocks OPTIONS
(
“starrocks.filter.query” = “id=123”
)
查询sql：
select user_id
,user_name
,state_time
from sr_temp_table
错误堆栈：
Caused by: java.lang.RuntimeException: Error while encoding: java.lang.RuntimeException: java.sql.Date is not a valid external type for schema of date
if (assertnotnull(input[0, org.apache.spark.sql.Row, true]).isNullAt) null else validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true]), 0, id), LongType) AS id#58L
if (assertnotnull(input[0, org.apache.spark.sql.Row, true]).isNullAt) null else validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true]), 1, wo_id), LongType) AS wo_id#59L
if (assertnotnull(input[0, org.apache.spark.sql.Row, true]).isNullAt) null else staticinvoke(class org.apache.spark.sql.catalyst.util.DateTimeUtils$, DateType, localDateToDays, validateexternaltype(getexternalrowfield(assertnotnull(input[0, org.apache.spark.sql.Row, true]), 2, state_time), DateType), true, false) AS state_time#60
at org.apache.spark.sql.errors.QueryExecutionErrors$.expressionEncodingError(QueryExecutionErrors.scala:1052)
at org.apache.spark.sql.catalyst.encoders.ExpressionEncoder$Serializer.apply(ExpressionEncoder.scala:210)
at org.apache.spark.sql.catalyst.encoders.ExpressionEncoder$Serializer.apply(ExpressionEncoder.scala:193)
at scala.collection.Iterator$$anon$10.next(Iterator.scala:461)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:759)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.executeTask(FileFormatWriter.scala:291)
at org.apache.spark.sql.execution.datasources.FileFormatWriter$.$anonfun$write$16(FileFormatWriter.scala:234)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:506)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1463)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:509)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)