vinothchandar commented on code in PR #12313:
URL: https://github.com/apache/hudi/pull/12313#discussion_r1853046463
##########
hudi-common/src/main/java/org/apache/hudi/common/model/HoodieWriteStat.java:
##########
@@ -159,6 +159,9 @@ public class HoodieWriteStat implements Serializable {
@Nullable
private Long maxEventTime;
+ @Nullable
+ private String prevBaseFile;
Review Comment:
so you just need the basefile? not the entire previous file slice?
##########
hudi-common/src/main/java/org/apache/hudi/metadata/HoodieTableMetadataUtil.java:
##########
@@ -759,6 +769,120 @@ public static HoodieData<HoodieRecord>
convertMetadataToColumnStatsRecords(Hoodi
});
}
+ static HoodieData<HoodieRecord>
convertMetadataToRecordIndexRecords(HoodieEngineContext engineContext,
+
HoodieCommitMetadata commitMetadata,
+
HoodieMetadataConfig metadataConfig,
+
HoodieTableMetaClient dataTableMetaClient,
+ int
writesFileIdEncoding,
Review Comment:
should this be enum
##########
hudi-common/src/main/java/org/apache/hudi/metadata/HoodieTableMetadataUtil.java:
##########
@@ -759,6 +769,120 @@ public static HoodieData<HoodieRecord>
convertMetadataToColumnStatsRecords(Hoodi
});
}
+ static HoodieData<HoodieRecord>
convertMetadataToRecordIndexRecords(HoodieEngineContext engineContext,
+
HoodieCommitMetadata commitMetadata,
+
HoodieMetadataConfig metadataConfig,
+
HoodieTableMetaClient dataTableMetaClient,
+ int
writesFileIdEncoding,
Review Comment:
method bit long, IMO. we need small methods that can be easily tested?
##########
hudi-common/src/main/java/org/apache/hudi/common/table/log/HoodieUnMergedLogRecordScanner.java:
##########
@@ -42,16 +43,19 @@
public class HoodieUnMergedLogRecordScanner extends
AbstractHoodieLogRecordScanner {
private final LogRecordScannerCallback callback;
+ private final CallbackForDeletedKeys callbackForDeletedKeys;
Review Comment:
rename: DeletionCallback
##########
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java:
##########
@@ -1056,17 +1055,17 @@ public void
updateFromWriteStatuses(HoodieCommitMetadata commitMetadata, HoodieD
engineContext, dataWriteConfig, commitMetadata, instantTime,
dataMetaClient,
enabledPartitionTypes, dataWriteConfig.getBloomFilterType(),
dataWriteConfig.getBloomIndexParallelism(),
dataWriteConfig.isMetadataColumnStatsIndexEnabled(),
- dataWriteConfig.getColumnStatsIndexParallelism(),
dataWriteConfig.getColumnsEnabledForColumnStatsIndex(),
dataWriteConfig.getMetadataConfig());
+ dataWriteConfig.getColumnStatsIndexParallelism(),
dataWriteConfig.getColumnsEnabledForColumnStatsIndex(),
dataWriteConfig.getWritesFileIdEncoding(),
+ dataWriteConfig.getMetadataConfig());
// Updates for record index are created by parsing the WriteStatus which
is a hudi-client object. Hence, we cannot yet move this code
// to the HoodieTableMetadataUtil class in hudi-common.
if (dataWriteConfig.isRecordIndexEnabled()) {
- HoodieData<HoodieRecord> updatesFromWriteStatuses =
getRecordIndexUpserts(writeStatus);
- HoodieData<HoodieRecord> additionalUpdates =
getRecordIndexAdditionalUpserts(updatesFromWriteStatuses, commitMetadata);
- partitionToRecordMap.put(RECORD_INDEX.getPartitionPath(),
updatesFromWriteStatuses.union(additionalUpdates));
+ HoodieData<HoodieRecord> additionalUpdates =
getRecordIndexAdditionalUpserts(partitionToRecordMap.get(MetadataPartitionType.RECORD_INDEX.getPartitionPath()),
commitMetadata);
+ partitionToRecordMap.put(RECORD_INDEX.getPartitionPath(),
partitionToRecordMap.get(MetadataPartitionType.RECORD_INDEX.getPartitionPath()).union(additionalUpdates));
}
updateFunctionalIndexIfPresent(commitMetadata, instantTime,
partitionToRecordMap);
- updateSecondaryIndexIfPresent(commitMetadata, partitionToRecordMap,
writeStatus);
+ updateSecondaryIndexIfPresent(commitMetadata, partitionToRecordMap,
instantTime);
Review Comment:
how come we still have the `updateFromWriteStatuses` method..
##########
hudi-client/hudi-client-common/src/main/java/org/apache/hudi/metadata/HoodieBackedTableMetadataWriter.java:
##########
@@ -1056,17 +1055,17 @@ public void
updateFromWriteStatuses(HoodieCommitMetadata commitMetadata, HoodieD
engineContext, dataWriteConfig, commitMetadata, instantTime,
dataMetaClient,
enabledPartitionTypes, dataWriteConfig.getBloomFilterType(),
dataWriteConfig.getBloomIndexParallelism(),
dataWriteConfig.isMetadataColumnStatsIndexEnabled(),
- dataWriteConfig.getColumnStatsIndexParallelism(),
dataWriteConfig.getColumnsEnabledForColumnStatsIndex(),
dataWriteConfig.getMetadataConfig());
+ dataWriteConfig.getColumnStatsIndexParallelism(),
dataWriteConfig.getColumnsEnabledForColumnStatsIndex(),
dataWriteConfig.getWritesFileIdEncoding(),
+ dataWriteConfig.getMetadataConfig());
// Updates for record index are created by parsing the WriteStatus which
is a hudi-client object. Hence, we cannot yet move this code
// to the HoodieTableMetadataUtil class in hudi-common.
if (dataWriteConfig.isRecordIndexEnabled()) {
- HoodieData<HoodieRecord> updatesFromWriteStatuses =
getRecordIndexUpserts(writeStatus);
- HoodieData<HoodieRecord> additionalUpdates =
getRecordIndexAdditionalUpserts(updatesFromWriteStatuses, commitMetadata);
- partitionToRecordMap.put(RECORD_INDEX.getPartitionPath(),
updatesFromWriteStatuses.union(additionalUpdates));
+ HoodieData<HoodieRecord> additionalUpdates =
getRecordIndexAdditionalUpserts(partitionToRecordMap.get(MetadataPartitionType.RECORD_INDEX.getPartitionPath()),
commitMetadata);
+ partitionToRecordMap.put(RECORD_INDEX.getPartitionPath(),
partitionToRecordMap.get(MetadataPartitionType.RECORD_INDEX.getPartitionPath()).union(additionalUpdates));
}
updateFunctionalIndexIfPresent(commitMetadata, instantTime,
partitionToRecordMap);
- updateSecondaryIndexIfPresent(commitMetadata, partitionToRecordMap,
writeStatus);
+ updateSecondaryIndexIfPresent(commitMetadata, partitionToRecordMap,
instantTime);
Review Comment:
still rename `writeStatus` to `writeStatuses`. plural
##########
hudi-common/src/main/java/org/apache/hudi/metadata/BaseFileRecordParsingUtils.java:
##########
@@ -0,0 +1,127 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.hudi.metadata;
+
+import org.apache.hudi.common.fs.FSUtils;
+import org.apache.hudi.common.model.HoodieFileFormat;
+import org.apache.hudi.common.model.HoodieRecord;
+import org.apache.hudi.common.model.HoodieWriteStat;
+import org.apache.hudi.common.util.FileFormatUtils;
+import org.apache.hudi.common.util.StringUtils;
+import org.apache.hudi.io.storage.HoodieIOFactory;
+import org.apache.hudi.storage.HoodieStorage;
+import org.apache.hudi.storage.StoragePath;
+
+import org.apache.hadoop.fs.Path;
+
+import java.io.IOException;
+import java.util.Collections;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Set;
+
+import static java.util.stream.Collectors.toList;
+
+public class BaseFileRecordParsingUtils {
+
+ /**
+ * Generates RLI Metadata records for base files.
+ * If base file is a added to a new file group, all record keys are treated
as inserts.
+ * If a base file is added to an existing file group, we read previous base
file in addition to the latest base file of interest. Find deleted records and
generate RLI Metadata records
+ * for the same in addition to new insert records.
+ * @param basePath base path of the table.
+ * @param writeStat {@link HoodieWriteStat} of interest.
+ * @param writesFileIdEncoding fileID encoding for the table.
+ * @param instantTime instant time of interest.
+ * @param storage instance of {@link HoodieStorage}.
+ * @return Iterator of {@link HoodieRecord}s for RLI Metadata partition.
+ * @throws IOException
+ */
+ public static Iterator<HoodieRecord>
generateRLIMetadataHoodieRecordsForBaseFile(String basePath,
Review Comment:
UT? all methods in file.
##########
hudi-common/src/main/java/org/apache/hudi/metadata/BaseFileRecordParsingUtils.java:
##########
@@ -0,0 +1,127 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.hudi.metadata;
+
+import org.apache.hudi.common.fs.FSUtils;
+import org.apache.hudi.common.model.HoodieFileFormat;
+import org.apache.hudi.common.model.HoodieRecord;
+import org.apache.hudi.common.model.HoodieWriteStat;
+import org.apache.hudi.common.util.FileFormatUtils;
+import org.apache.hudi.common.util.StringUtils;
+import org.apache.hudi.io.storage.HoodieIOFactory;
+import org.apache.hudi.storage.HoodieStorage;
+import org.apache.hudi.storage.StoragePath;
+
+import org.apache.hadoop.fs.Path;
+
+import java.io.IOException;
+import java.util.Collections;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Set;
+
+import static java.util.stream.Collectors.toList;
+
+public class BaseFileRecordParsingUtils {
Review Comment:
do we need a new Utils class? adding lots of short utils classes, makes the
code harder to maintain
--
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]
