Lokesh Jain created HUDI-8312:
---------------------------------
Summary: Support YYYY-MM-DD partition format with hive
Key: HUDI-8312
URL: https://issues.apache.org/jira/browse/HUDI-8312
Project: Apache Hudi
Issue Type: Bug
Reporter: Lokesh Jain
Currently a format like YYYY-MM-DD fails when syncing with hive. The Jira aims
to add a fix so that such a format is supported.
Steps to reproduce: The table created below uses a custom keygen with
combination of simple and timestamp keygen. Timestamp keygen produces an output
of format - YYYY-MM-DD
{code:java}
import org.apache.hudi.HoodieSparkUtils
import org.apache.hudi.common.config.TypedProperties
import org.apache.hudi.common.util.StringUtils
import org.apache.hudi.exception.HoodieException
import org.apache.hudi.functional.TestSparkSqlWithCustomKeyGenerator._
import org.apache.hudi.testutils.HoodieClientTestUtils.createMetaClient
import org.apache.hudi.util.SparkKeyGenUtilsimport org.apache.spark.sql.SaveMode
import org.apache.spark.sql.hudi.common.HoodieSparkSqlTestBase
import org.joda.time.DateTime
import org.joda.time.format.DateTimeFormat
import org.junit.jupiter.api.Assertions.{assertEquals, assertFalse, assertTrue}
import org.slf4j.LoggerFactory
val df = spark.sql(
s"""SELECT 1 as id, 'a1' as name, 1.6 as price, 1704121827 as ts, 'cat1'
as segment
| UNION
| SELECT 2 as id, 'a2' as name, 10.8 as price, 1704121827 as ts,
'cat1' as segment
| UNION
| SELECT 3 as id, 'a3' as name, 30.0 as price, 1706800227 as ts,
'cat1' as segment
| UNION
| SELECT 4 as id, 'a4' as name, 103.4 as price, 1701443427 as ts,
'cat2' as segment
| UNION
| SELECT 5 as id, 'a5' as name, 1999.0 as price, 1704121827 as ts,
'cat2' as segment
| UNION
| SELECT 6 as id, 'a6' as name, 80.0 as price, 1704121827 as ts,
'cat3' as segment
|""".stripMargin)
df.write.format("hudi").option("hoodie.datasource.write.table.type",
"MERGE_ON_READ").option("hoodie.datasource.write.keygenerator.class<span
class="code-quote">",
"org.apache.hudi.keygen.CustomAvroKeyGenerator").option("hoodie.datasource.write.partitionpath.field",
"segment:simple,ts:timestamp").option("hoodie.datasource.write.recordkey.field",
"id").option("hoodie.datasource.write.precombine.field",
"name").option("hoodie.table.name",
"hudi_table_2").option("hoodie.insert.shuffle.parallelism",
"1").option("hoodie.upsert.shuffle.parallelism",
"1").option("hoodie.bulkinsert.shuffle.parallelism",
"1").option("hoodie.keygen.timebased.timestamp.type",
"SCALAR").option("hoodie.keygen.timebased.output.dateformat",
"yyyy-MM-DD").option("hoodie.keygen.timebased.timestamp.scalar.time.unit",
"seconds").mode(SaveMode.Overwrite).save("/user/hive/warehouse/hudi_table_2")
// Sync with hive
/var/hoodie/ws/hudi-sync/hudi-hive-sync/run_sync_tool.sh \
--jdbc-url jdbc:hive2://hiveserver:10000 \
--user hive \
--pass hive \
--partitioned-by segment,ts \
--base-path /user/hive/warehouse/hudi_table_2 \
--database default \
--table hudi_table_2 \
--partition-value-extractor org.apache.hudi.hive.MultiPartKeysValueExtractor
{code}
Error
{code:java}
2024-10-06 15:18:22,220 INFO [main] ddl.JDBCExecutor
(JDBCExecutor.java:runSQL(67)) - Executing SQL ALTER TABLE
`default`.`hudi_table_2_ro` ADD IF NOT EXISTS PARTITION
(`segment`='cat1',`ts`='2024-10-01') LOCATION
'/user/hive/warehouse/hudi_table_2/cat1/2024-10-01' PARTITION
(`segment`='cat2',`ts`='2023-10-01') LOCATION
'/user/hive/warehouse/hudi_table_2/cat2/2023-10-01' PARTITION
(`segment`='cat2',`ts`='2024-10-01') LOCATION
'/user/hive/warehouse/hudi_table_2/cat2/2024-10-01' PARTITION
(`segment`='cat3',`ts`='2024-10-01') LOCATION
'/user/hive/warehouse/hudi_table_2/cat3/2024-10-01'
2024-10-06 15:18:22,299 INFO [main] hive.metastore
(HiveMetaStoreClient.java:close(564)) - Closed a connection to metastore,
current connections: 0
Exception in thread "main" org.apache.hudi.exception.HoodieException: Got
runtime exception when hive syncing hudi_table_2
at org.apache.hudi.hive.HiveSyncTool.syncHoodieTable(HiveSyncTool.java:180)
at org.apache.hudi.hive.HiveSyncTool.main(HiveSyncTool.java:547)
Caused by: org.apache.hudi.hive.HoodieHiveSyncException: failed to sync the
table hudi_table_2_ro
at org.apache.hudi.hive.HiveSyncTool.syncHoodieTable(HiveSyncTool.java:272)
at org.apache.hudi.hive.HiveSyncTool.doSync(HiveSyncTool.java:203)
at org.apache.hudi.hive.HiveSyncTool.syncHoodieTable(HiveSyncTool.java:177)
... 1 more
Caused by: org.apache.hudi.hive.HoodieHiveSyncException: Failed to sync
partitions for table hudi_table_2_ro
at
org.apache.hudi.hive.HiveSyncTool.syncAllPartitions(HiveSyncTool.java:474)
at
org.apache.hudi.hive.HiveSyncTool.validateAndSyncPartitions(HiveSyncTool.java:321)
at org.apache.hudi.hive.HiveSyncTool.syncHoodieTable(HiveSyncTool.java:261)
... 3 more
Caused by: org.apache.hudi.hive.HoodieHiveSyncException: Failed in executing
SQL ALTER TABLE `default`.`hudi_table_2_ro` ADD IF NOT EXISTS PARTITION
(`segment`='cat1',`ts`='2024-10-01') LOCATION
'/user/hive/warehouse/hudi_table_2/cat1/2024-10-01' PARTITION
(`segment`='cat2',`ts`='2023-10-01') LOCATION
'/user/hive/warehouse/hudi_table_2/cat2/2023-10-01' PARTITION
(`segment`='cat2',`ts`='2024-10-01') LOCATION
'/user/hive/warehouse/hudi_table_2/cat2/2024-10-01' PARTITION
(`segment`='cat3',`ts`='2024-10-01') LOCATION
'/user/hive/warehouse/hudi_table_2/cat3/2024-10-01'
at org.apache.hudi.hive.ddl.JDBCExecutor.runSQL(JDBCExecutor.java:70)
at
org.apache.hudi.hive.ddl.QueryBasedDDLExecutor.lambda$addPartitionsToTable$0(QueryBasedDDLExecutor.java:125)
at
java.util.ArrayList$ArrayListSpliterator.forEachRemaining(ArrayList.java:1382)
at
java.util.stream.ReferencePipeline$Head.forEach(ReferencePipeline.java:580)
at
org.apache.hudi.hive.ddl.QueryBasedDDLExecutor.addPartitionsToTable(QueryBasedDDLExecutor.java:125)
at
org.apache.hudi.hive.HoodieHiveSyncClient.addPartitionsToTable(HoodieHiveSyncClient.java:118)
at org.apache.hudi.hive.HiveSyncTool.syncPartitions(HiveSyncTool.java:516)
at
org.apache.hudi.hive.HiveSyncTool.syncAllPartitions(HiveSyncTool.java:470)
... 5 more
Caused by: org.apache.hive.service.cli.HiveSQLException: Error while compiling
statement: FAILED: SemanticException [Error 10248]: Cannot add partition column
ts of type string as it cannot be converted to type int
at org.apache.hive.jdbc.Utils.verifySuccess(Utils.java:267)
-Dspark3.5 -Dscala-2.12
at org.apache.hive.jdbc.Utils.verifySuccessWithInfo(Utils.java:253)
at
org.apache.hive.jdbc.HiveStatement.runAsyncOnServer(HiveStatement.java:313)
at org.apache.hive.jdbc.HiveStatement.execute(HiveStatement.java:253)
at org.apache.hudi.hive.ddl.JDBCExecutor.runSQL(JDBCExecutor.java:68)
... 12 more
Caused by: org.apache.hive.service.cli.HiveSQLException: Error while compiling
statement: FAILED: SemanticException [Error 10248]: Cannot add partition column
ts of type string as it cannot be converted to type int
at
org.apache.hive.service.cli.operation.Operation.toSQLException(Operation.java:380)
at
org.apache.hive.service.cli.operation.SQLOperation.prepare(SQLOperation.java:206)
at
org.apache.hive.service.cli.operation.SQLOperation.runInternal(SQLOperation.java:290)
at org.apache.hive.service.cli.operation.Operation.run(Operation.java:320)
at
org.apache.hive.service.cli.session.HiveSessionImpl.executeStatementInternal(HiveSessionImpl.java:530)
at
org.apache.hive.service.cli.session.HiveSessionImpl.executeStatementAsync(HiveSessionImpl.java:517)
at
org.apache.hive.service.cli.CLIService.executeStatementAsync(CLIService.java:310)
at
org.apache.hive.service.cli.thrift.ThriftCLIService.ExecuteStatement(ThriftCLIService.java:530)
at
org.apache.hive.service.rpc.thrift.TCLIService$Processor$ExecuteStatement.getResult(TCLIService.java:1437)
at
org.apache.hive.service.rpc.thrift.TCLIService$Processor$ExecuteStatement.getResult(TCLIService.java:1422)
at org.apache.thrift.ProcessFunction.process(ProcessFunction.java:39)
at org.apache.thrift.TBaseProcessor.process(TBaseProcessor.java:39)
at
org.apache.hive.service.auth.TSetIpAddressProcessor.process(TSetIpAddressProcessor.java:56)
at
org.apache.thrift.server.TThreadPoolServer$WorkerProcess.run(TThreadPoolServer.java:286)
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.hadoop.hive.ql.parse.SemanticException: Cannot add
partition column ts of type string as it cannot be converted to type int
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.validatePartColumnType(BaseSemanticAnalyzer.java:1582)
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.validatePartSpec(BaseSemanticAnalyzer.java:1536)
at
org.apache.hadoop.hive.ql.parse.DDLSemanticAnalyzer.getValidatedPartSpec(DDLSemanticAnalyzer.java:2096)
at
org.apache.hadoop.hive.ql.parse.DDLSemanticAnalyzer.analyzeAlterTableAddParts(DDLSemanticAnalyzer.java:2866)
at
org.apache.hadoop.hive.ql.parse.DDLSemanticAnalyzer.analyzeInternal(DDLSemanticAnalyzer.java:285)
at
org.apache.hadoop.hive.ql.parse.BaseSemanticAnalyzer.analyze(BaseSemanticAnalyzer.java:258)
at org.apache.hadoop.hive.ql.Driver.compile(Driver.java:512)
at org.apache.hadoop.hive.ql.Driver.compileInternal(Driver.java:1317)
at org.apache.hadoop.hive.ql.Driver.compileAndRespond(Driver.java:1295)
at
org.apache.hive.service.cli.operation.SQLOperation.prepare(SQLOperation.java:204)
... 15 more {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
