RussellSpitzer commented on a change in pull request #3557: URL: https://github.com/apache/iceberg/pull/3557#discussion_r765392034
########## File path: spark/v3.2/spark/src/main/java/org/apache/iceberg/spark/data/vectorized/ColumnBatchWithRowMapping.java ########## @@ -0,0 +1,156 @@ +/* + * 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.Iterator; +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; + +class ColumnBatchWithRowMapping { + private final DeleteFilter<InternalRow> deletes; + private int[] rowIdMapping; // the rowId mapping to skip deleted rows for all column vectors inside a batch + private int numRows; + private ColumnarBatch batch; + + ColumnBatchWithRowMapping(DeleteFilter<InternalRow> deletes, int numRowsToRead, long rowStartPosInBatch) { + this.deletes = deletes; + initRowIdMapping(numRowsToRead, rowStartPosInBatch); + } + + ColumnarBatch createColumnBatch(ColumnVector[] columns) { + batch = new ColumnarBatch(columns); + batch.setNumRows(numRows); + + if (hasEqDeletes()) { + applyEqDelete(); + } + return batch; + } + + boolean hasDeletes() { + return rowIdMapping != null; + } + + private boolean hasEqDeletes() { + return deletes != null && deletes.hasEqDeletes(); + } + + int[] rowIdMapping() { + return rowIdMapping; + } + + int numRows() { + return numRows; + } + + private void initRowIdMapping(int numRowsToRead, long rowStartPosInBatch) { + Pair<int[], Integer> posDeleteRowIdMapping = posDelRowIdMapping(numRowsToRead, rowStartPosInBatch); + if (posDeleteRowIdMapping != null) { + rowIdMapping = posDeleteRowIdMapping.first(); + numRows = posDeleteRowIdMapping.second(); + } else { + numRows = numRowsToRead; + rowIdMapping = initEqDeleteRowIdMapping(numRowsToRead); + } + } + + private Pair<int[], Integer> posDelRowIdMapping(int numRowsToRead, long rowStartPosInBatch) { + if (deletes != null && deletes.hasPosDeletes()) { + return buildPosDelRowIdMapping(deletes.deletedRowPositions(), numRowsToRead, rowStartPosInBatch); + } else { + return null; + } + } + + /** + * Build a row id mapping inside a batch, which skips delete rows. For example, if the 1st and 3rd rows are deleted in Review comment: "skips delete" -> "skips deleted" -- 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] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
