LadyForest commented on code in PR #138:
URL: https://github.com/apache/flink-table-store/pull/138#discussion_r885259036
##########
flink-table-store-connector/src/main/java/org/apache/flink/table/store/connector/TableStoreManagedFactory.java:
##########
@@ -183,6 +204,84 @@ public void onDropTable(Context context, boolean
ignoreIfNotExists) {
@Override
public Map<String, String> onCompactTable(
Context context, CatalogPartitionSpec catalogPartitionSpec) {
- throw new UnsupportedOperationException("Not implement yet");
+ Map<String, String> newOptions = new
HashMap<>(context.getCatalogTable().getOptions());
+ FileStore fileStore = buildTableStore(context).buildFileStore();
+ FileStoreScan.Plan plan =
+ fileStore
+ .newScan()
+ .withPartitionFilter(
+ PredicateConverter.CONVERTER.fromMap(
+
catalogPartitionSpec.getPartitionSpec(),
+ fileStore.partitionType()))
+ .plan();
+
+ Preconditions.checkState(
+ plan.snapshotId() != null && !plan.files().isEmpty(),
+ "The specified %s to compact does not exist any snapshot",
+ catalogPartitionSpec.getPartitionSpec().isEmpty()
+ ? "table"
+ : String.format("partition %s",
catalogPartitionSpec.getPartitionSpec()));
+ Map<BinaryRowData, Map<Integer, List<DataFileMeta>>> groupBy =
plan.groupByPartFiles();
+ if
(!Boolean.parseBoolean(newOptions.get(COMPACTION_RESCALE_BUCKET.key()))) {
+ groupBy =
+ pickManifest(
+ groupBy,
+ new
FileStoreOptions(Configuration.fromMap(newOptions))
+ .mergeTreeOptions(),
+ new
KeyComparatorSupplier(fileStore.partitionType()).get());
+ }
+ try {
+ newOptions.put(
+ COMPACTION_SCANNED_MANIFEST.key(),
+ Base64.getEncoder()
+ .encodeToString(
+ InstantiationUtil.serializeObject(
+ new PartitionedManifestMeta(
+ plan.snapshotId(),
groupBy))));
+ } catch (IOException e) {
+ throw new RuntimeException(e);
+ }
+ return newOptions;
+ }
+
+ @VisibleForTesting
+ Map<BinaryRowData, Map<Integer, List<DataFileMeta>>> pickManifest(
+ Map<BinaryRowData, Map<Integer, List<DataFileMeta>>> groupBy,
+ MergeTreeOptions options,
+ Comparator<RowData> keyComparator) {
+ Map<BinaryRowData, Map<Integer, List<DataFileMeta>>> filtered = new
HashMap<>();
+
+ for (Map.Entry<BinaryRowData, Map<Integer, List<DataFileMeta>>>
partEntry :
+ groupBy.entrySet()) {
+ Map<Integer, List<DataFileMeta>> manifests = new HashMap<>();
+ for (Map.Entry<Integer, List<DataFileMeta>> bucketEntry :
+ partEntry.getValue().entrySet()) {
+ List<DataFileMeta> smallFiles =
Review Comment:
> inputs: File1(0-9) File2(10-89) File3(90-100)
merged: File4(0-100) File2(10-89)
Good example. It is a problem when they're already sitting at the highest
level. And even though they're not at the highest level, the compaction cannot
get rid of key range overlap.
--
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]
