[
https://issues.apache.org/jira/browse/HIVE-24878?focusedWorklogId=568029&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-568029
]
ASF GitHub Bot logged work on HIVE-24878:
-----------------------------------------
Author: ASF GitHub Bot
Created on: 18/Mar/21 00:28
Start Date: 18/Mar/21 00:28
Worklog Time Spent: 10m
Work Description: pkumarsinha commented on a change in pull request #2067:
URL: https://github.com/apache/hive/pull/2067#discussion_r596464219
##########
File path:
ql/src/java/org/apache/hadoop/hive/ql/parse/repl/load/message/CreateFunctionHandler.java
##########
@@ -206,7 +206,7 @@ ResourceUri destinationResourceUri(ResourceUri resourceUri)
return ReplCopyTask.getLoadCopyTask(metadata.getReplicationSpec(), new
Path(sourceUri), dest, context.hiveConf,
context.getDumpDirectory(), context.getMetricCollector());
} else {
- return TaskFactory.get(new CopyWork(new Path(sourceUri), dest, true,
false,
+ return TaskFactory.get(new CopyWork(new Path(sourceUri),
dest.getParent(), true, false,
Review comment:
Just wondering how was this working earlier.
##########
File path:
itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/parse/TestReplicationScenariosAcrossInstances.java
##########
@@ -2237,4 +2242,27 @@ private void assertExternalFileInfo(List<String>
expected, String dumplocation,
}
ReplicationTestUtils.assertExternalFileInfo(warehouseInstance, expected,
externalTableInfoFile);
}
+
+ private void assertFunctionJarsOnTarget(String functionName, List<String>
expectedJars) throws IOException {
+ //correct location of jars on target is
functionRoot/dbName/funcName/nanoTs/jarFile
+ FileStatus[] fileStatuses = replica.miniDFSCluster.getFileSystem()
+ .globStatus(
+ new Path(replica.functionsRoot + "/" +
replicatedDbName.toLowerCase() + "/" +
+ functionName.toLowerCase() + "/*/*"), path ->
path.toString().endsWith("jar")
+ );
+ assertEquals(fileStatuses.length, expectedJars.size());
+ List<String> jars = Arrays.stream(fileStatuses).map(f -> {
+ String[] splits = f.getPath().toString().split("/");
+ return splits[splits.length - 1];
Review comment:
Do you need just file name from the path? Wouldn't just return
f.getPath().getName() be fine
##########
File path:
itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/parse/TestReplicationScenariosAcrossInstances.java
##########
@@ -2237,4 +2242,27 @@ private void assertExternalFileInfo(List<String>
expected, String dumplocation,
}
ReplicationTestUtils.assertExternalFileInfo(warehouseInstance, expected,
externalTableInfoFile);
}
+
+ private void assertFunctionJarsOnTarget(String functionName, List<String>
expectedJars) throws IOException {
+ //correct location of jars on target is
functionRoot/dbName/funcName/nanoTs/jarFile
+ FileStatus[] fileStatuses = replica.miniDFSCluster.getFileSystem()
+ .globStatus(
+ new Path(replica.functionsRoot + "/" +
replicatedDbName.toLowerCase() + "/" +
+ functionName.toLowerCase() + "/*/*"), path ->
path.toString().endsWith("jar")
+ );
+ assertEquals(fileStatuses.length, expectedJars.size());
+ List<String> jars = Arrays.stream(fileStatuses).map(f -> {
+ String[] splits = f.getPath().toString().split("/");
+ return splits[splits.length - 1];
+ }).collect(Collectors.toList());
+ assertThat(jars, containsInAnyOrder(expectedJars.toArray()));
Review comment:
Does this also do a match on size
##########
File path:
itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/parse/TestReplicationScenariosAcrossInstances.java
##########
@@ -2237,4 +2242,27 @@ private void assertExternalFileInfo(List<String>
expected, String dumplocation,
}
ReplicationTestUtils.assertExternalFileInfo(warehouseInstance, expected,
externalTableInfoFile);
}
+
+ private void assertFunctionJarsOnTarget(String functionName, List<String>
expectedJars) throws IOException {
+ //correct location of jars on target is
functionRoot/dbName/funcName/nanoTs/jarFile
+ FileStatus[] fileStatuses = replica.miniDFSCluster.getFileSystem()
+ .globStatus(
+ new Path(replica.functionsRoot + "/" +
replicatedDbName.toLowerCase() + "/" +
+ functionName.toLowerCase() + "/*/*"), path ->
path.toString().endsWith("jar")
+ );
+ assertEquals(fileStatuses.length, expectedJars.size());
+ List<String> jars = Arrays.stream(fileStatuses).map(f -> {
+ String[] splits = f.getPath().toString().split("/");
+ return splits[splits.length - 1];
+ }).collect(Collectors.toList());
+ assertThat(jars, containsInAnyOrder(expectedJars.toArray()));
+
+ //confirm no jars in nested directories
+ FileStatus[] nestedFileStatuses = replica.miniDFSCluster.getFileSystem()
+ .globStatus(
+ new Path(replica.functionsRoot + "/" +
replicatedDbName.toLowerCase() + "/" + functionName + "/*/*/*")
+ ,path -> path.toString().endsWith("jar")
+ );
+ assertEquals(nestedFileStatuses.length, 0);
Review comment:
There should not be any directory itself right?
##########
File path:
itests/hive-unit/src/test/java/org/apache/hadoop/hive/ql/parse/TestReplicationScenariosAcrossInstances.java
##########
@@ -2237,4 +2242,27 @@ private void assertExternalFileInfo(List<String>
expected, String dumplocation,
}
ReplicationTestUtils.assertExternalFileInfo(warehouseInstance, expected,
externalTableInfoFile);
}
+
+ private void assertFunctionJarsOnTarget(String functionName, List<String>
expectedJars) throws IOException {
+ //correct location of jars on target is
functionRoot/dbName/funcName/nanoTs/jarFile
+ FileStatus[] fileStatuses = replica.miniDFSCluster.getFileSystem()
+ .globStatus(
+ new Path(replica.functionsRoot + "/" +
replicatedDbName.toLowerCase() + "/" +
+ functionName.toLowerCase() + "/*/*"), path ->
path.toString().endsWith("jar")
Review comment:
endsWith(".jar")?
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
Issue Time Tracking
-------------------
Worklog Id: (was: 568029)
Time Spent: 20m (was: 10m)
> ClassNotFound exception for function replication.
> -------------------------------------------------
>
> Key: HIVE-24878
> URL: https://issues.apache.org/jira/browse/HIVE-24878
> Project: Hive
> Issue Type: Bug
> Reporter: Arko Sharma
> Assignee: Arko Sharma
> Priority: Major
> Labels: pull-request-available
> Time Spent: 20m
> Remaining Estimate: 0h
>
> Jar is copied to path <functionRoot>/dbName/funcName/nanoTS/jarName/jarName
> Correct path should be <functionRoot>/dbName/funcName/nanoTS/jarName
> Output of hdfs dfs -find on sample function root.
> /user/hive/repl/functions/bn9/udf6/28312880814467788/testudf6.jar
> /user/hive/repl/functions/bn9/udf6/28312880814467788/testudf6.jar/testudf6.jar
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
