rdblue commented on a change in pull request #723: Arrow changes for supporting vectorized reads URL: https://github.com/apache/incubator-iceberg/pull/723#discussion_r367670127
########## File path: arrow/src/main/java/org/apache/iceberg/arrow/vectorized/parquet/VectorizedColumnIterator.java ########## @@ -0,0 +1,258 @@ +/* + * 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.arrow.vectorized.parquet; + +import java.io.IOException; +import org.apache.arrow.vector.FieldVector; +import org.apache.arrow.vector.IntVector; +import org.apache.iceberg.arrow.vectorized.NullabilityHolder; +import org.apache.parquet.column.ColumnDescriptor; +import org.apache.parquet.column.Dictionary; +import org.apache.parquet.column.page.DataPage; +import org.apache.parquet.column.page.DictionaryPage; +import org.apache.parquet.column.page.PageReadStore; +import org.apache.parquet.column.page.PageReader; +import org.apache.parquet.io.ParquetDecodingException; + +/** + * Vectorized version of the ColumnIterator that reads column values in data pages of a column in a row group in a + * batched fashion. + */ +public class VectorizedColumnIterator { + + private final ColumnDescriptor desc; + private final VectorizedPageIterator vectorizedPageIterator; + + // state reset for each row group + private PageReader columnPageReader = null; + private long totalValuesCount = 0L; + private long valuesRead = 0L; + private long advanceNextPageCount = 0L; + private final int batchSize; + + public VectorizedColumnIterator(ColumnDescriptor desc, String writerVersion, int batchSize) { + this.desc = desc; + this.batchSize = batchSize; + this.vectorizedPageIterator = new VectorizedPageIterator(desc, writerVersion, batchSize); + } + + public Dictionary setRowGroupInfo(PageReadStore store, boolean allPagesDictEncoded) { + this.columnPageReader = store.getPageReader(desc); + this.totalValuesCount = columnPageReader.getTotalValueCount(); Review comment: The other iterator uses `store.getTotalValueCount`, not the one in `columnPageReader`. Are those guaranteed to be the same? ---------------------------------------------------------------- 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: us...@infra.apache.org With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
