rdblue commented on code in PR #6935: URL: https://github.com/apache/iceberg/pull/6935#discussion_r1118134733
########## parquet/src/main/java/org/apache/iceberg/parquet/ParquetIndexPageFilter.java: ########## @@ -0,0 +1,516 @@ +/* + * 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.parquet; + +import java.io.IOException; +import java.math.BigDecimal; +import java.math.BigInteger; +import java.nio.ByteBuffer; +import java.nio.charset.StandardCharsets; +import java.util.Comparator; +import java.util.List; +import java.util.Map; +import java.util.Optional; +import java.util.Set; +import org.apache.commons.compress.utils.Lists; +import org.apache.iceberg.Schema; +import org.apache.iceberg.expressions.Binder; +import org.apache.iceberg.expressions.BoundReference; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.expressions.ExpressionVisitors; +import org.apache.iceberg.expressions.Expressions; +import org.apache.iceberg.expressions.Literal; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.types.Type; +import org.apache.iceberg.util.ByteBuffers; +import org.apache.parquet.column.ColumnDescriptor; +import org.apache.parquet.hadoop.ParquetFileReader; +import org.apache.parquet.hadoop.metadata.BlockMetaData; +import org.apache.parquet.hadoop.metadata.ColumnChunkMetaData; +import org.apache.parquet.internal.column.columnindex.ColumnIndex; +import org.apache.parquet.internal.column.columnindex.OffsetIndex; +import org.apache.parquet.internal.filter2.columnindex.RowRanges; +import org.apache.parquet.internal.filter2.columnindex.RowRanges.Range; +import org.apache.parquet.schema.LogicalTypeAnnotation; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.PrimitiveType; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +public class ParquetIndexPageFilter { + private static final Logger LOG = LoggerFactory.getLogger(ParquetIndexPageFilter.class); + + private final Schema schema; + private final MessageType fileSchema; + private final Expression expr; + + public ParquetIndexPageFilter(Schema schema, MessageType fileSchema, Expression expr, boolean caseSensitive) { + this.schema = schema; + this.fileSchema = fileSchema; + this.expr = Binder.bind(schema.asStruct(), Expressions.rewriteNot(expr), caseSensitive); + } + + public long applyIndex(ParquetFileReader reader, int rowGroupIndex) { + RowRanges ranges = new EvalVisitor(reader.getRowGroups().get(rowGroupIndex), reader).eval(); + ParquetRanges.setRanges(reader, rowGroupIndex, ranges); Review Comment: @zhongyujiang, this is where we set the ranges for each row group. The `ParquetRanges` class uses reflection to do it. I'm all for getting a public API to be able to create `RowRanges` and pass them to the reader. I just don't think that we need to wait when we should be able to use reflection in the meantime. -- 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]
