rahil-c commented on code in PR #18432:
URL: https://github.com/apache/hudi/pull/18432#discussion_r3035946544
##########
hudi-spark-datasource/hudi-spark/pom.xml:
##########
@@ -270,6 +270,11 @@
<artifactId>spark-hive_${scala.binary.version}</artifactId>
</dependency>
+ <dependency>
+ <groupId>org.apache.spark</groupId>
+ <artifactId>spark-mllib-local_${scala.binary.version}</artifactId>
+ </dependency>
Review Comment:
When i removed this it caused a class not found exception so for now opting
to keep it
```
java.lang.NoClassDefFoundError: org/apache/spark/ml/linalg/Vector
at
org.apache.spark.sql.hudi.analysis.BruteForceSearchAlgorithm$.buildSingleQueryPlan(HoodieVectorSearchPlanBuilder.scala:266)
at
org.apache.spark.sql.hudi.analysis.ResolveReferences$$anonfun$apply$1.applyOrElse(HoodieSparkBaseAnalysis.scala:159)
at
org.apache.spark.sql.hudi.analysis.ResolveReferences$$anonfun$apply$1.applyOrElse(HoodieSparkBaseAnalysis.scala:60)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsUpWithPruning$3(AnalysisHelper.scala:138)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(origin.scala:76)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsUpWithPruning$1(AnalysisHelper.scala:138)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:323)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUpWithPruning(AnalysisHelper.scala:134)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUpWithPruning$(AnalysisHelper.scala:130)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUpWithPruning(LogicalPlan.scala:32)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsUpWithPruning$2(AnalysisHelper.scala:135)
at
org.apache.spark.sql.catalyst.trees.UnaryLike.mapChildren(TreeNode.scala:1216)
at
org.apache.spark.sql.catalyst.trees.UnaryLike.mapChildren$(TreeNode.scala:1215)
at
org.apache.spark.sql.catalyst.plans.logical.Project.mapChildren(basicLogicalOperators.scala:71)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsUpWithPruning$1(AnalysisHelper.scala:135)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:323)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUpWithPruning(AnalysisHelper.scala:134)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUpWithPruning$(AnalysisHelper.scala:130)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUpWithPruning(LogicalPlan.scala:32)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsUpWithPruning$2(AnalysisHelper.scala:135)
at
org.apache.spark.sql.catalyst.trees.UnaryLike.mapChildren(TreeNode.scala:1216)
at
org.apache.spark.sql.catalyst.trees.UnaryLike.mapChildren$(TreeNode.scala:1215)
at
org.apache.spark.sql.catalyst.plans.logical.Sort.mapChildren(basicLogicalOperators.scala:920)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsUpWithPruning$1(AnalysisHelper.scala:135)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:323)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUpWithPruning(AnalysisHelper.scala:134)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUpWithPruning$(AnalysisHelper.scala:130)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUpWithPruning(LogicalPlan.scala:32)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUp(AnalysisHelper.scala:111)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsUp$(AnalysisHelper.scala:110)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsUp(LogicalPlan.scala:32)
at
org.apache.spark.sql.hudi.analysis.ResolveReferences.apply(HoodieSparkBaseAnalysis.scala:60)
at
org.apache.spark.sql.hudi.analysis.ResolveReferences.apply(HoodieSparkBaseAnalysis.scala:57)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$2(RuleExecutor.scala:222)
at
scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126)
at
scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122)
at scala.collection.immutable.List.foldLeft(List.scala:91)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1(RuleExecutor.scala:219)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1$adapted(RuleExecutor.scala:211)
at scala.collection.immutable.List.foreach(List.scala:431)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:211)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:240)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.$anonfun$execute$1(Analyzer.scala:236)
at
org.apache.spark.sql.catalyst.analysis.AnalysisContext$.withNewAnalysisContext(Analyzer.scala:187)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:236)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:202)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$executeAndTrack$1(RuleExecutor.scala:182)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:89)
at
org.apache.spark.sql.catalyst.rules.RuleExecutor.executeAndTrack(RuleExecutor.scala:182)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.$anonfun$executeAndCheck$1(Analyzer.scala:223)
at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:330)
at
org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:222)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$analyzed$1(QueryExecution.scala:77)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:138)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$2(QueryExecution.scala:219)
at
org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:546)
at
org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:219)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at
org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:218)
at
org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:77)
at
org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:74)
at
org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:66)
at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:99)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:97)
at
org.apache.spark.sql.SparkSession.$anonfun$sql$4(SparkSession.scala:691)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:900)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:682)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:713)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:744)
at
org.apache.hudi.functional.TestHoodieVectorSearchFunction.testSingleQueryDefaultMetric(TestHoodieVectorSearchFunction.scala:268)
at java.base/java.lang.reflect.Method.invoke(Method.java:566)
at java.base/java.util.ArrayList.forEach(ArrayList.java:1541)
at java.base/java.util.ArrayList.forEach(ArrayList.java:1541)
Caused by: java.lang.ClassNotFoundException:
org.apache.spark.ml.linalg.Vector
at
java.base/jdk.internal.loader.BuiltinClassLoader.loadClass(BuiltinClassLoader.java:581)
at
java.base/jdk.internal.loader.ClassLoaders$AppClassLoader.loadClass(ClassLoaders.java:178)
at java.base/java.lang.ClassLoader.loadClass(ClassLoader.java:527)
... 74 more
```
--
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]
