Search in sources :

Example 1 with TaskContextSupplier

use of org.apache.hudi.common.engine.TaskContextSupplier in project hudi by apache.

the class TestHoodieOrcReaderWriter method createOrcWriter.

private HoodieOrcWriter createOrcWriter(Schema avroSchema) throws Exception {
    BloomFilter filter = BloomFilterFactory.createBloomFilter(1000, 0.00001, -1, BloomFilterTypeCode.SIMPLE.name());
    Configuration conf = new Configuration();
    int orcStripSize = Integer.parseInt(HoodieStorageConfig.ORC_STRIPE_SIZE.defaultValue());
    int orcBlockSize = Integer.parseInt(HoodieStorageConfig.ORC_BLOCK_SIZE.defaultValue());
    int maxFileSize = Integer.parseInt(HoodieStorageConfig.ORC_FILE_MAX_SIZE.defaultValue());
    HoodieOrcConfig config = new HoodieOrcConfig(conf, CompressionKind.ZLIB, orcStripSize, orcBlockSize, maxFileSize, filter);
    TaskContextSupplier mockTaskContextSupplier = Mockito.mock(TaskContextSupplier.class);
    String instantTime = "000";
    return new HoodieOrcWriter(instantTime, filePath, config, avroSchema, mockTaskContextSupplier);
}
Also used : Configuration(org.apache.hadoop.conf.Configuration) BloomFilter(org.apache.hudi.common.bloom.BloomFilter) TaskContextSupplier(org.apache.hudi.common.engine.TaskContextSupplier)

Example 2 with TaskContextSupplier

use of org.apache.hudi.common.engine.TaskContextSupplier in project hudi by apache.

the class SingleSparkJobExecutionStrategy method performClustering.

@Override
public HoodieWriteMetadata<HoodieData<WriteStatus>> performClustering(final HoodieClusteringPlan clusteringPlan, final Schema schema, final String instantTime) {
    JavaSparkContext engineContext = HoodieSparkEngineContext.getSparkContext(getEngineContext());
    final TaskContextSupplier taskContextSupplier = getEngineContext().getTaskContextSupplier();
    final SerializableSchema serializableSchema = new SerializableSchema(schema);
    final List<ClusteringGroupInfo> clusteringGroupInfos = clusteringPlan.getInputGroups().stream().map(clusteringGroup -> ClusteringGroupInfo.create(clusteringGroup)).collect(Collectors.toList());
    String umask = engineContext.hadoopConfiguration().get("fs.permissions.umask-mode");
    Broadcast<String> umaskBroadcastValue = engineContext.broadcast(umask);
    JavaRDD<ClusteringGroupInfo> groupInfoJavaRDD = engineContext.parallelize(clusteringGroupInfos, clusteringGroupInfos.size());
    LOG.info("number of partitions for clustering " + groupInfoJavaRDD.getNumPartitions());
    JavaRDD<WriteStatus> writeStatusRDD = groupInfoJavaRDD.mapPartitions(clusteringOps -> {
        Configuration configuration = new Configuration();
        configuration.set("fs.permissions.umask-mode", umaskBroadcastValue.getValue());
        Iterable<ClusteringGroupInfo> clusteringOpsIterable = () -> clusteringOps;
        List<ClusteringGroupInfo> groupsInPartition = StreamSupport.stream(clusteringOpsIterable.spliterator(), false).collect(Collectors.toList());
        return groupsInPartition.stream().flatMap(clusteringOp -> runClusteringForGroup(clusteringOp, clusteringPlan.getStrategy().getStrategyParams(), Option.ofNullable(clusteringPlan.getPreserveHoodieMetadata()).orElse(false), serializableSchema, taskContextSupplier, instantTime)).iterator();
    });
    HoodieWriteMetadata<HoodieData<WriteStatus>> writeMetadata = new HoodieWriteMetadata<>();
    writeMetadata.setWriteStatuses(HoodieJavaRDD.of(writeStatusRDD));
    return writeMetadata;
}
Also used : HoodieTable(org.apache.hudi.table.HoodieTable) KeyGenUtils(org.apache.hudi.keygen.KeyGenUtils) HoodieAvroUtils(org.apache.hudi.avro.HoodieAvroUtils) RewriteAvroPayload(org.apache.hudi.common.model.RewriteAvroPayload) ConcatenatingIterator(org.apache.hudi.client.utils.ConcatenatingIterator) SerializableSchema(org.apache.hudi.common.config.SerializableSchema) JavaSparkContext(org.apache.spark.api.java.JavaSparkContext) Option(org.apache.hudi.common.util.Option) HoodieEngineContext(org.apache.hudi.common.engine.HoodieEngineContext) HoodieJavaRDD(org.apache.hudi.data.HoodieJavaRDD) BaseKeyGenerator(org.apache.hudi.keygen.BaseKeyGenerator) Logger(org.apache.log4j.Logger) HoodieFileReaderFactory(org.apache.hudi.io.storage.HoodieFileReaderFactory) Configuration(org.apache.hadoop.conf.Configuration) Map(java.util.Map) Path(org.apache.hadoop.fs.Path) HoodieSparkEngineContext(org.apache.hudi.client.common.HoodieSparkEngineContext) StreamSupport(java.util.stream.StreamSupport) HoodieWriteMetadata(org.apache.hudi.table.action.HoodieWriteMetadata) HoodieFileGroupId(org.apache.hudi.common.model.HoodieFileGroupId) HoodieSparkKeyGeneratorFactory(org.apache.hudi.keygen.factory.HoodieSparkKeyGeneratorFactory) ClusteringExecutionStrategy(org.apache.hudi.table.action.cluster.strategy.ClusteringExecutionStrategy) IndexedRecord(org.apache.avro.generic.IndexedRecord) JavaRDD(org.apache.spark.api.java.JavaRDD) Broadcast(org.apache.spark.broadcast.Broadcast) HoodieRecord(org.apache.hudi.common.model.HoodieRecord) GenericRecord(org.apache.avro.generic.GenericRecord) HoodieData(org.apache.hudi.common.data.HoodieData) Schema(org.apache.avro.Schema) TypedProperties(org.apache.hudi.common.config.TypedProperties) HoodieWriteConfig(org.apache.hudi.config.HoodieWriteConfig) Iterator(java.util.Iterator) TaskContextSupplier(org.apache.hudi.common.engine.TaskContextSupplier) HoodieClusteringPlan(org.apache.hudi.avro.model.HoodieClusteringPlan) HoodieClusteringException(org.apache.hudi.exception.HoodieClusteringException) ClusteringOperation(org.apache.hudi.common.model.ClusteringOperation) IOException(java.io.IOException) Collectors(java.util.stream.Collectors) HoodieAvroRecord(org.apache.hudi.common.model.HoodieAvroRecord) WriteStatus(org.apache.hudi.client.WriteStatus) ClusteringGroupInfo(org.apache.hudi.common.model.ClusteringGroupInfo) HoodieRecordPayload(org.apache.hudi.common.model.HoodieRecordPayload) List(java.util.List) Stream(java.util.stream.Stream) HoodieKey(org.apache.hudi.common.model.HoodieKey) HoodieIOException(org.apache.hudi.exception.HoodieIOException) LogManager(org.apache.log4j.LogManager) HoodieData(org.apache.hudi.common.data.HoodieData) Configuration(org.apache.hadoop.conf.Configuration) ClusteringGroupInfo(org.apache.hudi.common.model.ClusteringGroupInfo) TaskContextSupplier(org.apache.hudi.common.engine.TaskContextSupplier) SerializableSchema(org.apache.hudi.common.config.SerializableSchema) HoodieWriteMetadata(org.apache.hudi.table.action.HoodieWriteMetadata) JavaSparkContext(org.apache.spark.api.java.JavaSparkContext) WriteStatus(org.apache.hudi.client.WriteStatus)

Example 3 with TaskContextSupplier

use of org.apache.hudi.common.engine.TaskContextSupplier in project hudi by apache.

the class TestHoodieHFileReaderWriter method createHFileWriter.

private HoodieHFileWriter createHFileWriter(Schema avroSchema, boolean populateMetaFields) throws Exception {
    BloomFilter filter = BloomFilterFactory.createBloomFilter(1000, 0.00001, -1, BloomFilterTypeCode.SIMPLE.name());
    Configuration conf = new Configuration();
    TaskContextSupplier mockTaskContextSupplier = Mockito.mock(TaskContextSupplier.class);
    Supplier<Integer> partitionSupplier = Mockito.mock(Supplier.class);
    when(mockTaskContextSupplier.getPartitionIdSupplier()).thenReturn(partitionSupplier);
    when(partitionSupplier.get()).thenReturn(10);
    String instantTime = "000";
    HoodieHFileConfig hoodieHFileConfig = new HoodieHFileConfig(conf, Compression.Algorithm.GZ, 1024 * 1024, 120 * 1024 * 1024, HoodieHFileReader.KEY_FIELD_NAME, PREFETCH_ON_OPEN, CACHE_DATA_IN_L1, DROP_BEHIND_CACHE_COMPACTION, filter, HFILE_COMPARATOR);
    return new HoodieHFileWriter(instantTime, filePath, hoodieHFileConfig, avroSchema, mockTaskContextSupplier, populateMetaFields);
}
Also used : Configuration(org.apache.hadoop.conf.Configuration) BloomFilter(org.apache.hudi.common.bloom.BloomFilter) TaskContextSupplier(org.apache.hudi.common.engine.TaskContextSupplier)

Example 4 with TaskContextSupplier

use of org.apache.hudi.common.engine.TaskContextSupplier in project hudi by apache.

the class HoodieCompactor method compact.

/**
 * Execute a single compaction operation and report back status.
 */
public List<WriteStatus> compact(HoodieCompactionHandler compactionHandler, HoodieTableMetaClient metaClient, HoodieWriteConfig config, CompactionOperation operation, String instantTime, TaskContextSupplier taskContextSupplier) throws IOException {
    FileSystem fs = metaClient.getFs();
    Schema readerSchema = HoodieAvroUtils.addMetadataFields(new Schema.Parser().parse(config.getSchema()), config.allowOperationMetadataField());
    LOG.info("Compacting base " + operation.getDataFileName() + " with delta files " + operation.getDeltaFileNames() + " for commit " + instantTime);
    // TODO - FIX THIS
    // Reads the entire avro file. Always only specific blocks should be read from the avro file
    // (failure recover).
    // Load all the delta commits since the last compaction commit and get all the blocks to be
    // loaded and load it using CompositeAvroLogReader
    // Since a DeltaCommit is not defined yet, reading all the records. revisit this soon.
    String maxInstantTime = metaClient.getActiveTimeline().getTimelineOfActions(CollectionUtils.createSet(HoodieTimeline.COMMIT_ACTION, HoodieTimeline.ROLLBACK_ACTION, HoodieTimeline.DELTA_COMMIT_ACTION)).filterCompletedInstants().lastInstant().get().getTimestamp();
    long maxMemoryPerCompaction = IOUtils.getMaxMemoryPerCompaction(taskContextSupplier, config);
    LOG.info("MaxMemoryPerCompaction => " + maxMemoryPerCompaction);
    List<String> logFiles = operation.getDeltaFileNames().stream().map(p -> new Path(FSUtils.getPartitionPath(metaClient.getBasePath(), operation.getPartitionPath()), p).toString()).collect(toList());
    HoodieMergedLogRecordScanner scanner = HoodieMergedLogRecordScanner.newBuilder().withFileSystem(fs).withBasePath(metaClient.getBasePath()).withLogFilePaths(logFiles).withReaderSchema(readerSchema).withLatestInstantTime(maxInstantTime).withMaxMemorySizeInBytes(maxMemoryPerCompaction).withReadBlocksLazily(config.getCompactionLazyBlockReadEnabled()).withReverseReader(config.getCompactionReverseLogReadEnabled()).withBufferSize(config.getMaxDFSStreamBufferSize()).withSpillableMapBasePath(config.getSpillableMapBasePath()).withDiskMapType(config.getCommonConfig().getSpillableDiskMapType()).withBitCaskDiskMapCompressionEnabled(config.getCommonConfig().isBitCaskDiskMapCompressionEnabled()).withOperationField(config.allowOperationMetadataField()).withPartition(operation.getPartitionPath()).build();
    Option<HoodieBaseFile> oldDataFileOpt = operation.getBaseFile(metaClient.getBasePath(), operation.getPartitionPath());
    // But in this case, we need to give it a base file. Otherwise, it will lose base file in following fileSlice.
    if (!scanner.iterator().hasNext()) {
        if (!oldDataFileOpt.isPresent()) {
            scanner.close();
            return new ArrayList<>();
        } else {
        // TODO: we may directly rename original parquet file if there is not evolution/devolution of schema
        /*
        TaskContextSupplier taskContextSupplier = hoodieCopyOnWriteTable.getTaskContextSupplier();
        String newFileName = FSUtils.makeDataFileName(instantTime,
            FSUtils.makeWriteToken(taskContextSupplier.getPartitionIdSupplier().get(), taskContextSupplier.getStageIdSupplier().get(), taskContextSupplier.getAttemptIdSupplier().get()),
            operation.getFileId(), hoodieCopyOnWriteTable.getBaseFileExtension());
        Path oldFilePath = new Path(oldDataFileOpt.get().getPath());
        Path newFilePath = new Path(oldFilePath.getParent(), newFileName);
        FileUtil.copy(fs,oldFilePath, fs, newFilePath, false, fs.getConf());
        */
        }
    }
    // Compacting is very similar to applying updates to existing file
    Iterator<List<WriteStatus>> result;
    // If the dataFile is present, perform updates else perform inserts into a new base file.
    if (oldDataFileOpt.isPresent()) {
        result = compactionHandler.handleUpdate(instantTime, operation.getPartitionPath(), operation.getFileId(), scanner.getRecords(), oldDataFileOpt.get());
    } else {
        result = compactionHandler.handleInsert(instantTime, operation.getPartitionPath(), operation.getFileId(), scanner.getRecords());
    }
    scanner.close();
    Iterable<List<WriteStatus>> resultIterable = () -> result;
    return StreamSupport.stream(resultIterable.spliterator(), false).flatMap(Collection::stream).peek(s -> {
        s.getStat().setTotalUpdatedRecordsCompacted(scanner.getNumMergedRecordsInLog());
        s.getStat().setTotalLogFilesCompacted(scanner.getTotalLogFiles());
        s.getStat().setTotalLogRecords(scanner.getTotalLogRecords());
        s.getStat().setPartitionPath(operation.getPartitionPath());
        s.getStat().setTotalLogSizeCompacted(operation.getMetrics().get(CompactionStrategy.TOTAL_LOG_FILE_SIZE).longValue());
        s.getStat().setTotalLogBlocks(scanner.getTotalLogBlocks());
        s.getStat().setTotalCorruptLogBlock(scanner.getTotalCorruptBlocks());
        s.getStat().setTotalRollbackBlocks(scanner.getTotalRollbacks());
        RuntimeStats runtimeStats = new RuntimeStats();
        runtimeStats.setTotalScanTime(scanner.getTotalTimeTakenToReadAndMergeBlocks());
        s.getStat().setRuntimeStats(runtimeStats);
    }).collect(toList());
}
Also used : HoodieTable(org.apache.hudi.table.HoodieTable) HoodieAvroUtils(org.apache.hudi.avro.HoodieAvroUtils) FileSystem(org.apache.hadoop.fs.FileSystem) HoodieInstant(org.apache.hudi.common.table.timeline.HoodieInstant) CollectionUtils(org.apache.hudi.common.util.CollectionUtils) Option(org.apache.hudi.common.util.Option) HoodieEngineContext(org.apache.hudi.common.engine.HoodieEngineContext) ArrayList(java.util.ArrayList) Logger(org.apache.log4j.Logger) HoodieTableType(org.apache.hudi.common.model.HoodieTableType) HoodieAccumulator(org.apache.hudi.common.data.HoodieAccumulator) HoodieTableMetaClient(org.apache.hudi.common.table.HoodieTableMetaClient) RuntimeStats(org.apache.hudi.common.model.HoodieWriteStat.RuntimeStats) Path(org.apache.hadoop.fs.Path) HoodieLogFile(org.apache.hudi.common.model.HoodieLogFile) StreamSupport(java.util.stream.StreamSupport) HoodieFileGroupId(org.apache.hudi.common.model.HoodieFileGroupId) HoodieActiveTimeline(org.apache.hudi.common.table.timeline.HoodieActiveTimeline) HoodieTimeline(org.apache.hudi.common.table.timeline.HoodieTimeline) ValidationUtils(org.apache.hudi.common.util.ValidationUtils) HoodieData(org.apache.hudi.common.data.HoodieData) TableSchemaResolver(org.apache.hudi.common.table.TableSchemaResolver) HoodieMergedLogRecordScanner(org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner) Schema(org.apache.avro.Schema) HoodieWriteConfig(org.apache.hudi.config.HoodieWriteConfig) Iterator(java.util.Iterator) TaskContextSupplier(org.apache.hudi.common.engine.TaskContextSupplier) Collection(java.util.Collection) Set(java.util.Set) IOException(java.io.IOException) CompactionStrategy(org.apache.hudi.table.action.compact.strategy.CompactionStrategy) Serializable(java.io.Serializable) CompactionOperation(org.apache.hudi.common.model.CompactionOperation) HoodieCompactionOperation(org.apache.hudi.avro.model.HoodieCompactionOperation) WriteStatus(org.apache.hudi.client.WriteStatus) HoodieRecordPayload(org.apache.hudi.common.model.HoodieRecordPayload) HoodieBaseFile(org.apache.hudi.common.model.HoodieBaseFile) HoodieCompactionHandler(org.apache.hudi.table.HoodieCompactionHandler) List(java.util.List) Collectors.toList(java.util.stream.Collectors.toList) HoodieCompactionPlan(org.apache.hudi.avro.model.HoodieCompactionPlan) SliceView(org.apache.hudi.common.table.view.TableFileSystemView.SliceView) IOUtils(org.apache.hudi.io.IOUtils) LogManager(org.apache.log4j.LogManager) FSUtils(org.apache.hudi.common.fs.FSUtils) CompactionUtils(org.apache.hudi.common.util.CompactionUtils) Pair(org.apache.hudi.common.util.collection.Pair) Path(org.apache.hadoop.fs.Path) HoodieBaseFile(org.apache.hudi.common.model.HoodieBaseFile) HoodieMergedLogRecordScanner(org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner) RuntimeStats(org.apache.hudi.common.model.HoodieWriteStat.RuntimeStats) Schema(org.apache.avro.Schema) ArrayList(java.util.ArrayList) FileSystem(org.apache.hadoop.fs.FileSystem) Collection(java.util.Collection) ArrayList(java.util.ArrayList) List(java.util.List) Collectors.toList(java.util.stream.Collectors.toList)

Example 5 with TaskContextSupplier

use of org.apache.hudi.common.engine.TaskContextSupplier in project hudi by apache.

the class HoodieCompactor method compact.

/**
 * Execute compaction operations and report back status.
 */
public HoodieData<WriteStatus> compact(HoodieEngineContext context, HoodieCompactionPlan compactionPlan, HoodieTable table, HoodieWriteConfig config, String compactionInstantTime, HoodieCompactionHandler compactionHandler) {
    if (compactionPlan == null || (compactionPlan.getOperations() == null) || (compactionPlan.getOperations().isEmpty())) {
        return context.emptyHoodieData();
    }
    HoodieActiveTimeline timeline = table.getActiveTimeline();
    HoodieInstant instant = HoodieTimeline.getCompactionRequestedInstant(compactionInstantTime);
    // Mark instant as compaction inflight
    timeline.transitionCompactionRequestedToInflight(instant);
    table.getMetaClient().reloadActiveTimeline();
    HoodieTableMetaClient metaClient = table.getMetaClient();
    TableSchemaResolver schemaResolver = new TableSchemaResolver(metaClient);
    // the same with the table schema.
    try {
        Schema readerSchema = schemaResolver.getTableAvroSchema(false);
        config.setSchema(readerSchema.toString());
    } catch (Exception e) {
    // If there is no commit in the table, just ignore the exception.
    }
    // Compacting is very similar to applying updates to existing file
    List<CompactionOperation> operations = compactionPlan.getOperations().stream().map(CompactionOperation::convertFromAvroRecordInstance).collect(toList());
    LOG.info("Compactor compacting " + operations + " files");
    context.setJobStatus(this.getClass().getSimpleName(), "Compacting file slices");
    TaskContextSupplier taskContextSupplier = table.getTaskContextSupplier();
    return context.parallelize(operations).map(operation -> compact(compactionHandler, metaClient, config, operation, compactionInstantTime, taskContextSupplier)).flatMap(List::iterator);
}
Also used : HoodieInstant(org.apache.hudi.common.table.timeline.HoodieInstant) HoodieTableMetaClient(org.apache.hudi.common.table.HoodieTableMetaClient) HoodieTable(org.apache.hudi.table.HoodieTable) HoodieAvroUtils(org.apache.hudi.avro.HoodieAvroUtils) FileSystem(org.apache.hadoop.fs.FileSystem) HoodieInstant(org.apache.hudi.common.table.timeline.HoodieInstant) CollectionUtils(org.apache.hudi.common.util.CollectionUtils) Option(org.apache.hudi.common.util.Option) HoodieEngineContext(org.apache.hudi.common.engine.HoodieEngineContext) ArrayList(java.util.ArrayList) Logger(org.apache.log4j.Logger) HoodieTableType(org.apache.hudi.common.model.HoodieTableType) HoodieAccumulator(org.apache.hudi.common.data.HoodieAccumulator) HoodieTableMetaClient(org.apache.hudi.common.table.HoodieTableMetaClient) RuntimeStats(org.apache.hudi.common.model.HoodieWriteStat.RuntimeStats) Path(org.apache.hadoop.fs.Path) HoodieLogFile(org.apache.hudi.common.model.HoodieLogFile) StreamSupport(java.util.stream.StreamSupport) HoodieFileGroupId(org.apache.hudi.common.model.HoodieFileGroupId) HoodieActiveTimeline(org.apache.hudi.common.table.timeline.HoodieActiveTimeline) HoodieTimeline(org.apache.hudi.common.table.timeline.HoodieTimeline) ValidationUtils(org.apache.hudi.common.util.ValidationUtils) HoodieData(org.apache.hudi.common.data.HoodieData) TableSchemaResolver(org.apache.hudi.common.table.TableSchemaResolver) HoodieMergedLogRecordScanner(org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner) Schema(org.apache.avro.Schema) HoodieWriteConfig(org.apache.hudi.config.HoodieWriteConfig) Iterator(java.util.Iterator) TaskContextSupplier(org.apache.hudi.common.engine.TaskContextSupplier) Collection(java.util.Collection) Set(java.util.Set) IOException(java.io.IOException) CompactionStrategy(org.apache.hudi.table.action.compact.strategy.CompactionStrategy) Serializable(java.io.Serializable) CompactionOperation(org.apache.hudi.common.model.CompactionOperation) HoodieCompactionOperation(org.apache.hudi.avro.model.HoodieCompactionOperation) WriteStatus(org.apache.hudi.client.WriteStatus) HoodieRecordPayload(org.apache.hudi.common.model.HoodieRecordPayload) HoodieBaseFile(org.apache.hudi.common.model.HoodieBaseFile) HoodieCompactionHandler(org.apache.hudi.table.HoodieCompactionHandler) List(java.util.List) Collectors.toList(java.util.stream.Collectors.toList) HoodieCompactionPlan(org.apache.hudi.avro.model.HoodieCompactionPlan) SliceView(org.apache.hudi.common.table.view.TableFileSystemView.SliceView) IOUtils(org.apache.hudi.io.IOUtils) LogManager(org.apache.log4j.LogManager) FSUtils(org.apache.hudi.common.fs.FSUtils) CompactionUtils(org.apache.hudi.common.util.CompactionUtils) Pair(org.apache.hudi.common.util.collection.Pair) CompactionOperation(org.apache.hudi.common.model.CompactionOperation) HoodieCompactionOperation(org.apache.hudi.avro.model.HoodieCompactionOperation) HoodieActiveTimeline(org.apache.hudi.common.table.timeline.HoodieActiveTimeline) Schema(org.apache.avro.Schema) TableSchemaResolver(org.apache.hudi.common.table.TableSchemaResolver) ArrayList(java.util.ArrayList) List(java.util.List) Collectors.toList(java.util.stream.Collectors.toList) IOException(java.io.IOException) TaskContextSupplier(org.apache.hudi.common.engine.TaskContextSupplier)

Aggregations

TaskContextSupplier (org.apache.hudi.common.engine.TaskContextSupplier)5 IOException (java.io.IOException)3 Iterator (java.util.Iterator)3 List (java.util.List)3 StreamSupport (java.util.stream.StreamSupport)3 Schema (org.apache.avro.Schema)3 Path (org.apache.hadoop.fs.Path)3 HoodieAvroUtils (org.apache.hudi.avro.HoodieAvroUtils)3 WriteStatus (org.apache.hudi.client.WriteStatus)3 HoodieData (org.apache.hudi.common.data.HoodieData)3 HoodieEngineContext (org.apache.hudi.common.engine.HoodieEngineContext)3 HoodieFileGroupId (org.apache.hudi.common.model.HoodieFileGroupId)3 HoodieRecordPayload (org.apache.hudi.common.model.HoodieRecordPayload)3 Option (org.apache.hudi.common.util.Option)3 Serializable (java.io.Serializable)2 ArrayList (java.util.ArrayList)2 Collection (java.util.Collection)2 Set (java.util.Set)2 Collectors.toList (java.util.stream.Collectors.toList)2 Configuration (org.apache.hadoop.conf.Configuration)2