tmater commented on code in PR #16714: URL: https://github.com/apache/iceberg/pull/16714#discussion_r3541926004
########## parquet/src/main/java/org/apache/iceberg/parquet/VariantExtractionPathResolver.java: ########## @@ -0,0 +1,127 @@ +/* + * 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.util.List; +import org.apache.iceberg.expressions.PathUtil; +import org.apache.iceberg.relocated.com.google.common.collect.Lists; +import org.apache.parquet.schema.GroupType; +import org.apache.parquet.schema.Type; + +/** Resolves shredded Parquet paths for variant extraction pushdown. */ +class VariantExtractionPathResolver { + private static final String VALUE = "value"; + private static final String TYPED_VALUE = "typed_value"; + + private VariantExtractionPathResolver() {} + + static List<String> readerPath( + Iterable<String> variantColumnPath, List<PathUtil.PathSegment> objectPathParts) { + List<String> path = Lists.newArrayList(variantColumnPath); + path.add(TYPED_VALUE); + for (PathUtil.PathSegment seg : objectPathParts) { + path.add(((PathUtil.PathSegment.Name) seg).name()); + } + return path; + } + + static String[] pathArray(Iterable<String> variantColumnPath, String... suffix) { + List<String> path = Lists.newArrayList(variantColumnPath); + for (String part : suffix) { + path.add(part); + } + return path.toArray(new String[0]); + } + + static GroupType resolveShreddedFieldGroup( + GroupType variantGroup, List<PathUtil.PathSegment> objectPathParts) { + if (!ParquetSchemaUtil.hasField(variantGroup, TYPED_VALUE)) { + return null; + } + + Type typedValue = variantGroup.getType(TYPED_VALUE); + if (typedValue.isPrimitive()) { + return objectPathParts.isEmpty() ? variantGroup : null; + } + + GroupType current = typedValue.asGroupType(); Review Comment: I think this mishandles root extraction (`"$"`). Eaerlier `PathUtil.parse("$")` returns an empty path, and for a shredded object `resolveShreddedFieldGroup(variantGroup, emptyPath)` returns the root `typed_value` group. That group contains object fields, not a variant value group with its own `value`/`typed_value`, so the leaf-reader check below fails and no reader is built unless the root serialized `value` fallback exists. -- 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]
