aokolnychyi commented on a change in pull request #1738:
URL: https://github.com/apache/iceberg/pull/1738#discussion_r520895579
##########
File path:
spark3/src/main/java/org/apache/iceberg/spark/source/SparkBatchScan.java
##########
@@ -20,81 +20,61 @@
package org.apache.iceberg.spark.source;
import java.io.IOException;
-import java.io.Serializable;
-import java.util.Collection;
import java.util.List;
+import java.util.Map;
import java.util.Objects;
+import java.util.Set;
import java.util.stream.Collectors;
import org.apache.iceberg.CombinedScanTask;
-import org.apache.iceberg.FileFormat;
import org.apache.iceberg.FileScanTask;
import org.apache.iceberg.Schema;
-import org.apache.iceberg.SchemaParser;
import org.apache.iceberg.SnapshotSummary;
import org.apache.iceberg.Table;
-import org.apache.iceberg.TableProperties;
import org.apache.iceberg.TableScan;
import org.apache.iceberg.encryption.EncryptionManager;
import org.apache.iceberg.exceptions.RuntimeIOException;
import org.apache.iceberg.expressions.Expression;
-import org.apache.iceberg.hadoop.HadoopInputFile;
-import org.apache.iceberg.hadoop.Util;
import org.apache.iceberg.io.CloseableIterable;
import org.apache.iceberg.io.FileIO;
-import org.apache.iceberg.mapping.NameMapping;
-import org.apache.iceberg.mapping.NameMappingParser;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.spark.Spark3Util;
import org.apache.iceberg.spark.SparkSchemaUtil;
import org.apache.iceberg.util.PropertyUtil;
import org.apache.iceberg.util.TableScanUtil;
import org.apache.spark.broadcast.Broadcast;
-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;
-import org.apache.spark.sql.connector.read.Scan;
import org.apache.spark.sql.connector.read.Statistics;
-import org.apache.spark.sql.connector.read.SupportsReportStatistics;
-import org.apache.spark.sql.types.StructType;
+import org.apache.spark.sql.connector.read.SupportsFileFilter;
import org.apache.spark.sql.util.CaseInsensitiveStringMap;
-import org.apache.spark.sql.vectorized.ColumnarBatch;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
-class SparkBatchScan implements Scan, Batch, SupportsReportStatistics {
+import static org.apache.iceberg.TableProperties.SPLIT_LOOKBACK;
+import static org.apache.iceberg.TableProperties.SPLIT_LOOKBACK_DEFAULT;
+import static org.apache.iceberg.TableProperties.SPLIT_OPEN_FILE_COST;
+import static org.apache.iceberg.TableProperties.SPLIT_OPEN_FILE_COST_DEFAULT;
+import static org.apache.iceberg.TableProperties.SPLIT_SIZE;
+import static org.apache.iceberg.TableProperties.SPLIT_SIZE_DEFAULT;
+
+class SparkBatchScan extends BaseBatchScan implements SupportsFileFilter {
Review comment:
I think we no longer need `BaseBatchScan` as I got rid of the other scan.
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
