zhangyue19921010 commented on a change in pull request #4078: URL: https://github.com/apache/hudi/pull/4078#discussion_r770425379
########## File path: hudi-client/hudi-spark-client/src/test/java/org/apache/hudi/io/TestHoodieTimelineArchiveLog.java ########## @@ -183,6 +217,41 @@ public void testArchiveTableWithArchival(boolean enableMetadata) throws Exceptio } } + @ParameterizedTest + @MethodSource("testArchiveTableWithArchivalTrim") + public void testArchiveTableWithArchivalCleanUp(boolean enableMetadata, boolean enableArchiveTrim, int archiveFilesToKeep) throws Exception { + HashSet<String> archiveFilesExisted = new HashSet<>(); + ArrayList<String> currentExistArchiveFiles = new ArrayList<>(); + HoodieWriteConfig writeConfig = initTestTableAndGetWriteConfig(enableMetadata, 2, 3, 2, enableArchiveTrim, archiveFilesToKeep); + String archivePath = metaClient.getArchivePath(); + for (int i = 1; i < 10; i++) { + testTable.doWriteOperation("0000000" + i, WriteOperationType.UPSERT, i == 1 ? Arrays.asList("p1", "p2") : Collections.emptyList(), Arrays.asList("p1", "p2"), 2); + // trigger archival + archiveAndGetCommitsList(writeConfig); + RemoteIterator<LocatedFileStatus> iter = metaClient.getFs().listFiles(new Path(archivePath), false); + ArrayList<String> files = new ArrayList<>(); + while (iter.hasNext()) { + files.add(iter.next().getPath().toString()); + } + archiveFilesExisted.addAll(files); + currentExistArchiveFiles = files; + } + + assertEquals(archiveFilesToKeep, currentExistArchiveFiles.size()); + + if (enableArchiveTrim) { + // sort archive files path + List<String> sorted = archiveFilesExisted.stream().sorted().collect(Collectors.toList()); + List<String> archiveFilesDeleted = sorted.subList(0, 3 - archiveFilesToKeep); + List<String> archiveFilesKept = sorted.subList(3 - archiveFilesToKeep, sorted.size()); + + // assert older archive files are deleted + assertFalse(currentExistArchiveFiles.containsAll(archiveFilesDeleted)); + // assert most recent archive files are preserved + assertTrue(currentExistArchiveFiles.containsAll(archiveFilesKept)); + } Review comment: Added. -- 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: commits-unsubscr...@hudi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org