the-other-tim-brown commented on code in PR #13445:
URL: https://github.com/apache/hudi/pull/13445#discussion_r2152654287
##########
hudi-common/src/main/java/org/apache/hudi/metadata/HoodieTableMetadataUtil.java:
##########
@@ -2376,35 +2383,29 @@ public static HoodieData<HoodieRecord>
readRecordKeysFromFileSlices(HoodieEngine
final int parallelism = Math.min(partitionFileSlicePairs.size(),
recordIndexMaxParallelism);
final StoragePath basePath = metaClient.getBasePath();
final StorageConfiguration<?> storageConf = metaClient.getStorageConf();
+ final Schema tableSchema;
+ try {
+ tableSchema = new TableSchemaResolver(metaClient).getTableAvroSchema();
+ } catch (Exception e) {
+ throw new HoodieException("Unable to resolve table schema for table", e);
+ }
+ ReaderContextFactory<T> readerContextFactory =
engineContext.getReaderContextFactory(metaClient);
return engineContext.parallelize(partitionFileSlicePairs,
parallelism).flatMap(partitionAndBaseFile -> {
final String partition = partitionAndBaseFile.getKey();
final FileSlice fileSlice = partitionAndBaseFile.getValue();
if (!fileSlice.getBaseFile().isPresent()) {
- List<String> logFilePaths =
fileSlice.getLogFiles().sorted(HoodieLogFile.getLogFileComparator())
- .map(l -> l.getPath().toString()).collect(Collectors.toList());
- HoodieMergedLogRecordScanner mergedLogRecordScanner =
HoodieMergedLogRecordScanner.newBuilder()
- .withStorage(metaClient.getStorage())
- .withBasePath(basePath)
- .withLogFilePaths(logFilePaths)
- .withReaderSchema(HoodieAvroUtils.getRecordKeySchema())
-
.withLatestInstantTime(metaClient.getActiveTimeline().filterCompletedInstants().lastInstant().map(HoodieInstant::requestedTime).orElse(""))
- .withReverseReader(false)
- .withMaxMemorySizeInBytes(storageConf.getLong(
- MAX_MEMORY_FOR_COMPACTION.key(),
DEFAULT_MAX_MEMORY_FOR_SPILLABLE_MAP_IN_BYTES))
-
.withSpillableMapBasePath(FileIOUtils.getDefaultSpillableMapBasePath())
- .withPartition(fileSlice.getPartitionPath())
-
.withOptimizedLogBlocksScan(storageConf.getBoolean(ENABLE_OPTIMIZED_LOG_BLOCKS_SCAN.key(),
false))
-
.withDiskMapType(storageConf.getEnum(SPILLABLE_DISK_MAP_TYPE.key(),
SPILLABLE_DISK_MAP_TYPE.defaultValue()))
- .withBitCaskDiskMapCompressionEnabled(storageConf.getBoolean(
- DISK_MAP_BITCASK_COMPRESSION_ENABLED.key(),
DISK_MAP_BITCASK_COMPRESSION_ENABLED.defaultValue()))
- .withRecordMerger(HoodieRecordUtils.createRecordMerger(
- metaClient.getBasePath().toString(),
- engineType,
- Collections.emptyList(), // TODO: support different merger
classes, which is currently only known to write config
- metaClient.getTableConfig().getRecordMergeStrategyId()))
- .withTableMetaClient(metaClient)
+ HoodieFileGroupReader fileGroupReader =
HoodieFileGroupReader.<T>newBuilder()
+ .withReaderContext(readerContextFactory.getContext())
+ .withHoodieTableMetaClient(metaClient)
+ .withFileSlice(fileSlice)
+ .withDataSchema(tableSchema)
+ .withRequestedSchema(HoodieAvroUtils.getRecordKeySchema())
+
.withLatestCommitTime(metaClient.getActiveTimeline().filterCompletedInstants().lastInstant().map(HoodieInstant::requestedTime).orElse(""))
Review Comment:
Yes, updated
--
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]
