huaxingao commented on code in PR #11933: URL: https://github.com/apache/iceberg/pull/11933#discussion_r1924605026
########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/ColumnarBatchUtil.java: ########## @@ -0,0 +1,165 @@ +/* + * 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.data.vectorized; + +import java.util.Arrays; +import java.util.function.Predicate; +import org.apache.iceberg.data.DeleteFilter; +import org.apache.iceberg.deletes.PositionDeleteIndex; +import org.apache.iceberg.util.Pair; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.vectorized.ColumnVector; +import org.apache.spark.sql.vectorized.ColumnarBatch; +import org.apache.spark.sql.vectorized.ColumnarBatchRow; + +public class ColumnarBatchUtil { + + private ColumnarBatchUtil() {} + + /** Review Comment: Fixed. ########## spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/ColumnarBatchUtil.java: ########## @@ -0,0 +1,165 @@ +/* + * 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.data.vectorized; + +import java.util.Arrays; +import java.util.function.Predicate; +import org.apache.iceberg.data.DeleteFilter; +import org.apache.iceberg.deletes.PositionDeleteIndex; +import org.apache.iceberg.util.Pair; +import org.apache.spark.sql.catalyst.InternalRow; +import org.apache.spark.sql.vectorized.ColumnVector; +import org.apache.spark.sql.vectorized.ColumnarBatch; +import org.apache.spark.sql.vectorized.ColumnarBatchRow; + +public class ColumnarBatchUtil { + + private ColumnarBatchUtil() {} + + /** + * Build a row id mapping inside a batch, which skips deleted rows. Here is an example of how we + * delete 2 rows in a batch with 8 rows in total. [0,1,2,3,4,5,6,7] -- Original status of the row + * id mapping array [F,F,F,F,F,F,F,F] -- Original status of the isDeleted array Position delete 2, + * 6 [0,1,3,4,5,7,-,-] -- After applying position deletes [Set Num records to 6] [F,F,T,F,F,F,T,F] + * -- After applying position deletes + * + * @param vectors The array of ColumnVectors for the batch. + * @param deletes The delete filter containing delete information. + * @param rowStartPosInBatch The starting position of the row in the batch. + * @param batchSize The size of the batch. + * @return the mapping array and the new num of rows in a batch, null if no row is deleted + */ + public static Pair<int[], Integer> buildRowIdMapping( + ColumnVector[] vectors, Review Comment: I changed all of them to `columnVectors` -- 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-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
