[ 
https://issues.apache.org/jira/browse/GOBBLIN-2159?focusedWorklogId=936294&page=com.atlassian.jira.plugin.system.issuetabpanels:worklog-tabpanel#worklog-936294
 ]

ASF GitHub Bot logged work on GOBBLIN-2159:
-------------------------------------------

                Author: ASF GitHub Bot
            Created on: 25/Sep/24 05:38
            Start Date: 25/Sep/24 05:38
    Worklog Time Spent: 10m 
      Work Description: Blazer-007 commented on code in PR #4058:
URL: https://github.com/apache/gobblin/pull/4058#discussion_r1774529681


##########
gobblin-data-management/src/test/java/org/apache/gobblin/data/management/copy/iceberg/IcebergTableTest.java:
##########
@@ -333,4 +338,120 @@ protected static <T> void verifyAnyOrder(Collection<T> 
actual, Collection<T> exp
   protected static <T, C extends Collection<T>> List<T> flatten(Collection<C> 
cc) {
     return cc.stream().flatMap(x -> x.stream()).collect(Collectors.toList());
   }
+
+  @Test
+  public void testGetPartitionSpecificDataFiles() throws IOException {
+    TableIdentifier testTableId = TableIdentifier.of(dbName, "testTable");
+    Table testTable = catalog.createTable(testTableId, icebergSchema, 
icebergPartitionSpec);
+
+    List<String> paths = Arrays.asList(
+        "/path/tableName/data/id=1/file1.orc",
+        "/path/tableName/data/id=1/file3.orc",
+        "/path/tableName/data/id=1/file5.orc",
+        "/path/tableName/data/id=1/file4.orc",
+        "/path/tableName/data/id=1/file2.orc"
+    );
+    // Using the schema defined in start of this class
+    PartitionData partitionData = new 
PartitionData(icebergPartitionSpec.partitionType());
+    partitionData.set(0, 1L);
+    List<PartitionData> partitionDataList = Collections.nCopies(5, 
partitionData);
+
+    addPartitionDataFiles(testTable, paths, partitionDataList);
+
+    IcebergTable icebergTable = new IcebergTable(testTableId,
+        catalog.newTableOps(testTableId),
+        catalogUri,
+        catalog.loadTable(testTableId));
+    // Using AlwaysTrue & AlwaysFalse Predicate to avoid mocking of predicate 
class
+    Predicate<StructLike> alwaysTruePredicate = partition -> true;
+    Predicate<StructLike> alwaysFalsePredicate = partition -> false;
+    
Assert.assertEquals(icebergTable.getPartitionSpecificDataFiles(alwaysTruePredicate).size(),
 5);
+    
Assert.assertEquals(icebergTable.getPartitionSpecificDataFiles(alwaysFalsePredicate).size(),
 0);
+
+    catalog.dropTable(testTableId);
+  }
+
+  @Test
+  public void testReplacePartitions() throws IOException {
+    TableIdentifier testTableId = TableIdentifier.of(dbName, "testTable");
+    Table testTable = catalog.createTable(testTableId, icebergSchema, 
icebergPartitionSpec);
+
+    List<String> paths = Arrays.asList(
+        "/path/tableName/data/id=1/file1.orc",
+        "/path/tableName/data/id=1/file2.orc"
+    );
+    // Using the schema defined in start of this class
+    PartitionData partitionData = new 
PartitionData(icebergPartitionSpec.partitionType());
+    partitionData.set(0, 1L);
+    PartitionData partitionData2 = new 
PartitionData(icebergPartitionSpec.partitionType());
+    partitionData2.set(0, 1L);
+    List<PartitionData> partitionDataList = Arrays.asList(partitionData, 
partitionData2);

Review Comment:
   I wanted to make sure we use two distinct objects (for testing) and not a 
copy of the same object, that's why this way here.





Issue Time Tracking
-------------------

    Worklog Id:     (was: 936294)
    Time Spent: 2h  (was: 1h 50m)

> Support Partition Based Copy in Iceberg Distcp
> ----------------------------------------------
>
>                 Key: GOBBLIN-2159
>                 URL: https://issues.apache.org/jira/browse/GOBBLIN-2159
>             Project: Apache Gobblin
>          Issue Type: Task
>            Reporter: Vivek Rai
>            Priority: Major
>          Time Spent: 2h
>  Remaining Estimate: 0h
>




--
This message was sent by Atlassian Jira
(v8.20.10#820010)

Reply via email to