alexeykudinkin commented on a change in pull request #4333:
URL: https://github.com/apache/hudi/pull/4333#discussion_r797123287
##########
File path:
hudi-common/src/main/java/org/apache/hudi/common/table/log/block/HoodieDataBlock.java
##########
@@ -18,151 +18,173 @@
package org.apache.hudi.common.table.log.block;
-import org.apache.hudi.common.model.HoodieRecord;
-import org.apache.hudi.common.util.Option;
-import org.apache.hudi.exception.HoodieException;
-import org.apache.hudi.exception.HoodieIOException;
-
import org.apache.avro.Schema;
import org.apache.avro.generic.IndexedRecord;
import org.apache.hadoop.fs.FSDataInputStream;
-
-import javax.annotation.Nonnull;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.exception.HoodieIOException;
import java.io.IOException;
+import java.util.HashSet;
import java.util.List;
import java.util.Map;
+import java.util.stream.Collectors;
+
+import static org.apache.hudi.common.util.ValidationUtils.checkState;
/**
* DataBlock contains a list of records serialized using formats compatible
with the base file format.
* For each base file format there is a corresponding DataBlock format.
- *
+ * <p>
* The Datablock contains:
* 1. Data Block version
* 2. Total number of records in the block
* 3. Actual serialized content of the records
*/
public abstract class HoodieDataBlock extends HoodieLogBlock {
- protected List<IndexedRecord> records;
- protected Schema schema;
- protected String keyField;
+ // TODO rebase records/content to leverage Either to warrant
+ // that they are mutex (used by read/write flows respectively)
+ private Option<List<IndexedRecord>> records;
- public HoodieDataBlock(@Nonnull Map<HeaderMetadataType, String>
logBlockHeader,
- @Nonnull Map<HeaderMetadataType, String> logBlockFooter,
- @Nonnull Option<HoodieLogBlockContentLocation> blockContentLocation,
@Nonnull Option<byte[]> content,
- FSDataInputStream inputStream, boolean readBlockLazily) {
- super(logBlockHeader, logBlockFooter, blockContentLocation, content,
inputStream, readBlockLazily);
- this.keyField = HoodieRecord.RECORD_KEY_METADATA_FIELD;
- }
+ /**
+ * Dot-path notation reference to the key field w/in the record's schema
+ */
+ private final String keyFieldRef;
Review comment:
Double-checked this is indeed expected to just be a field-name (w/in the
record's schema) not dot-path notation.
--
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]
