@Override public DatasetSplit apply(SplitWork input) { return input.getSplit(); }}).toList(); return new ElasticsearchSubScan(
@Override public HBaseSubScanSpec apply(SplitWork input) { return toSubScan(input.getSplit()); }}).toList();
@Override public SubScan getSpecificScan(List<SplitWork> work) throws ExecutionSetupException { final BatchSchema schema = cachedRelDataType == null ? getDataset().getSchema(): BatchSchema.fromCalciteRowType(cachedRelDataType); // Create an abridged version of the splits to save network bytes. List<DatasetSplit> splits = work.stream().map( workSplit -> ProtostuffUtil.copy(workSplit.getSplit()) .setExtendedProperty(convertToScanXAttr(workSplit.getSplit().getExtendedProperty())) ).collect(Collectors.toList()); return new ParquetSubScan(dataset.getFormatSettings(), splits, getUserName(), schema, getDataset().getName().getPathComponents(), filter == null ? null : filter.getConditions(), dataset.getStoragePluginId(), columns, dataset.getReadDefinition().getPartitionColumnsList(), globalDictionaryEncodedColumns, dataset.getReadDefinition().getExtendedProperty()); }
@Override public SubScan getSpecificScan(List<SplitWork> work) throws ExecutionSetupException { List<DatasetSplit> splits = new ArrayList<>(work.size()); BatchSchema schema = getDataset().getSchema(); for(SplitWork split : work){ splits.add(split.getSplit()); } boolean storageImpersonationEnabled = dataset.getStoragePluginId().getCapabilities().getCapability(SourceCapabilities.STORAGE_IMPERSONATION); String userName = storageImpersonationEnabled ? getUserName() : ImpersonationUtil.getProcessUserName(); final ReadDefinition readDefinition = dataset.getReadDefinition(); return new HiveSubScan(splits, userName, schema, dataset.getName().getPathComponents(), filter, dataset.getStoragePluginId(), columns, readDefinition.getPartitionColumnsList()); }
@Override public SubScan getSpecificScan(List<SplitWork> work) throws ExecutionSetupException { final List<DatasetSplit> splits = new ArrayList<>(work.size()); final BatchSchema schema = getDataset().getSchema(); for(SplitWork split : work){ splits.add(split.getSplit()); } return new EasySubScan( getDataset().getFormatSettings(), splits, getUserName(), schema, getDataset().getName().getPathComponents(), dataset.getStoragePluginId(), columns, getDataset().getReadDefinition().getPartitionColumnsList(), getDataset().getReadDefinition().getExtendedProperty()); }