[GitHub] [hudi] bhasudha commented on a change in pull request #1817: [HUDI-651] Fix incremental queries in MOR tables

[GitBox <gi...@apache.org>]

bhasudha commented on a change in pull request #1817:
URL: https://github.com/apache/hudi/pull/1817#discussion_r453131365



##########
File path: hudi-hadoop-mr/src/main/java/org/apache/hudi/hadoop/realtime/HoodieMergedFileSlicesScanner.java
##########
@@ -0,0 +1,244 @@
+/*
+ * 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.hadoop.realtime;
+
+import java.io.IOException;
+import java.util.Comparator;
+import java.util.HashMap;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Map;
+import java.util.Map.Entry;
+import java.util.stream.Collectors;
+import org.apache.avro.generic.GenericRecord;
+import org.apache.hadoop.fs.FileStatus;
+import org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat;
+import org.apache.hadoop.io.ArrayWritable;
+import org.apache.hadoop.io.NullWritable;
+import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.mapred.FileSplit;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.RecordReader;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hudi.avro.HoodieAvroUtils;
+import org.apache.hudi.common.fs.FSUtils;
+import org.apache.hudi.common.model.FileSlice;
+import org.apache.hudi.common.model.HoodieLogFile;
+import org.apache.hudi.common.model.HoodieRecord;
+import org.apache.hudi.common.model.HoodieRecordPayload;
+import org.apache.hudi.common.table.log.HoodieMergedLogRecordScanner;
+import org.apache.hudi.common.util.Option;
+import org.apache.hudi.exception.HoodieIOException;
+import org.apache.log4j.LogManager;
+import org.apache.log4j.Logger;
+
+import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.COMPACTION_LAZY_BLOCK_READ_ENABLED_PROP;
+import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.DEFAULT_COMPACTION_LAZY_BLOCK_READ_ENABLED;
+import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.DEFAULT_MAX_DFS_STREAM_BUFFER_SIZE;
+import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.DEFAULT_SPILLABLE_MAP_BASE_PATH;
+import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.MAX_DFS_STREAM_BUFFER_SIZE_PROP;
+import static org.apache.hudi.hadoop.config.HoodieRealtimeConfig.SPILLABLE_MAP_BASE_PATH_PROP;
+import static org.apache.hudi.hadoop.utils.HoodieInputFormatUtils.HOODIE_RECORD_KEY_COL_POS;
+import static org.apache.hudi.hadoop.utils.HoodieRealtimeRecordReaderUtils.arrayWritableToString;
+import static org.apache.hudi.hadoop.utils.HoodieRealtimeRecordReaderUtils.avroToArrayWritable;
+
+/**
+ * Scans through all files in a file slice. Constructs a map of records from Parquet file if present. Constructs merged
+ * log records if log files are present in the slice. Merges records from log files on top of records from base parquet
+ * file.
+ *
+ */
+public class HoodieMergedFileSlicesScanner {
+
+  private static final Logger LOG = LogManager.getLogger(HoodieMergedFileSlicesScanner.class);
+
+  private final transient MapredParquetInputFormat mapredParquetInputFormat;
+  private final HoodieMORIncrementalFileSplit split;
+  private final List<FileSlice> fileSlices;
+
+  // Final map of compacted/merged records
+  // TODO change map to external spillable map. But ArrayWritable is not implementing Serializable

Review comment:
       We are merging parquet and log files and need to assume either of the files can be absent. I kept the Map interface as <String, ArrayWritable>. But since ArrayWritable is not implementing Serializable, that prevents the use of ExternalSpillableMap. Appreciate any ideas.




----------------------------------------------------------------
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.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org