[GitHub] [iceberg] bryanck commented on a diff in pull request #5740: Spark 3.3: Add SparkChangelogTable

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

bryanck commented on code in PR #5740:
URL: https://github.com/apache/iceberg/pull/5740#discussion_r967657781


##########
spark/v3.3/spark/src/main/java/org/apache/iceberg/spark/source/SparkChangelogBatch.java:
##########
@@ -0,0 +1,129 @@
+/*
+ * 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.iceberg.spark.source;
+
+import java.util.List;
+import org.apache.iceberg.ChangelogScanTask;
+import org.apache.iceberg.ScanTaskGroup;
+import org.apache.iceberg.Schema;
+import org.apache.iceberg.SchemaParser;
+import org.apache.iceberg.Table;
+import org.apache.iceberg.spark.SparkReadConf;
+import org.apache.iceberg.util.Tasks;
+import org.apache.iceberg.util.ThreadPools;
+import org.apache.spark.api.java.JavaSparkContext;
+import org.apache.spark.broadcast.Broadcast;
+import org.apache.spark.sql.SparkSession;
+import org.apache.spark.sql.catalyst.InternalRow;
+import org.apache.spark.sql.connector.read.Batch;
+import org.apache.spark.sql.connector.read.InputPartition;
+import org.apache.spark.sql.connector.read.PartitionReader;
+import org.apache.spark.sql.connector.read.PartitionReaderFactory;
+
+public class SparkChangelogBatch implements Batch {
+
+  private final JavaSparkContext sparkContext;
+  private final Table table;
+  private final Schema expectedSchema;
+  private final boolean caseSensitive;
+  private final boolean localityEnabled;
+  private final SparkChangelogScan scan;
+
+  SparkChangelogBatch(
+      SparkSession spark,
+      Table table,
+      SparkReadConf readConf,
+      Schema expectedSchema,
+      SparkChangelogScan scan) {
+    this.sparkContext = JavaSparkContext.fromSparkContext(spark.sparkContext());
+    this.table = table;
+    this.expectedSchema = expectedSchema;
+    this.caseSensitive = readConf.caseSensitive();
+    this.localityEnabled = readConf.localityEnabled();
+    this.scan = scan;
+  }
+
+  @Override
+  public InputPartition[] planInputPartitions() {
+    Table serializableTable = SerializableTableWithSize.copyOf(table);
+    Broadcast<Table> tableBroadcast = sparkContext.broadcast(serializableTable);
+    String expectedSchemaString = SchemaParser.toJson(expectedSchema);
+    List<ScanTaskGroup<ChangelogScanTask>> taskGroups = scan.taskGroups();
+
+    InputPartition[] partitions = new InputPartition[taskGroups.size()];
+
+    Tasks.range(partitions.length)
+        .stopOnFailure()
+        .executeWith(localityEnabled ? ThreadPools.getWorkerPool() : null)
+        .run(
+            index ->
+                partitions[index] =
+                    new SparkInputPartition(
+                        taskGroups.get(index),
+                        tableBroadcast,
+                        expectedSchemaString,
+                        caseSensitive,
+                        localityEnabled));
+
+    return partitions;
+  }
+
+  @Override
+  public PartitionReaderFactory createReaderFactory() {
+    return new ReaderFactory();
+  }
+
+  @Override
+  public boolean equals(Object o) {
+    if (this == o) {
+      return true;
+    }
+
+    if (o == null || getClass() != o.getClass()) {
+      return false;
+    }
+
+    SparkChangelogBatch that = (SparkChangelogBatch) o;
+    return scan.equals(that.scan);

Review Comment:
   Yes, that was what I found, the equals call returned false and the filters weren't pushed down. I had a workaround for that, but IIRC I ran into some other issues. Unfortunately I didn't delve deeper at that point and I went with reverting the change. It could be that implementing equals resolves the issue. I could run a benchmark test to confirm if interested.



-- 
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: issues-unsubscribe@iceberg.apache.org

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


---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@iceberg.apache.org
For additional commands, e-mail: issues-help@iceberg.apache.org