wgtmac commented on code in PR #3199: URL: https://github.com/apache/parquet-java/pull/3199#discussion_r2057928127
########## parquet-avro/src/main/java/org/apache/parquet/avro/ReflectClassValidator.java: ########## @@ -0,0 +1,94 @@ +/** + * 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 + * <p> + * http://www.apache.org/licenses/LICENSE-2.0 + * <p> + * 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.parquet.avro; + +import java.util.Arrays; +import java.util.HashSet; +import java.util.List; +import java.util.Set; +import java.util.stream.Collectors; +import java.util.stream.Stream; + +abstract class ReflectClassValidator { + + abstract void validate(String className); + + static class PackageValidator extends ReflectClassValidator { + + private final List<String> trustedPackagePrefixes = Stream.of(AvroConverters.SERIALIZABLE_PACKAGES) + .map(p -> p.endsWith(".") ? p : p + ".") + .collect(Collectors.toList()); + private final boolean trustAllPackages = + trustedPackagePrefixes.size() == 1 && "*".equals(trustedPackagePrefixes.get(0)); + // The primitive "class names" based on Class.isPrimitive() + private static final Set<String> PRIMITIVES = new HashSet<>(Arrays.asList( Review Comment: Why do we need this? ########## parquet-avro/README.md: ########## @@ -26,21 +26,22 @@ Apache Avro integration ### Configuration for reading -| Name | Type | Description | -|-----------------------------------------|-----------|----------------------------------------------------------------------| -| `parquet.avro.data.supplier` | `Class` | The implementation of the interface org.apache.parquet.avro.AvroDataSupplier. Available implementations in the library: GenericDataSupplier, ReflectDataSupplier, SpecificDataSupplier.<br/>The default value is `org.apache.parquet.avro.SpecificDataSupplier` | -| `parquet.avro.read.schema` | `String` | The Avro schema to be used for reading. It shall be compatible with the file schema. The file schema will be used directly if not set. | -| `parquet.avro.projection` | `String` | The Avro schema to be used for projection. | -| `parquet.avro.compatible` | `boolean` | Flag for compatibility mode. `true` for materializing Avro `IndexedRecord` objects, `false` for materializing the related objects for either generic, specific, or reflect records.<br/>The default value is `true`. | -| `parquet.avro.readInt96AsFixed` | `boolean` | Flag for handling the `INT96` Parquet types. `true` for converting it to the `fixed` Avro type, `false` for not handling `INT96` types (throwing exception).<br/>The default value is `false`.<br/>**NOTE: The `INT96` Parquet type is deprecated. This option is only to support old data.** | +| Name | Type | Description | +|-------------------------------------|-----------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| +| `parquet.avro.data.supplier` | `Class` | The implementation of the interface org.apache.parquet.avro.AvroDataSupplier. Available implementations in the library: GenericDataSupplier, ReflectDataSupplier, SpecificDataSupplier.<br/>The default value is `org.apache.parquet.avro.SpecificDataSupplier` | +| `parquet.avro.read.schema` | `String` | The Avro schema to be used for reading. It shall be compatible with the file schema. The file schema will be used directly if not set. | +| `parquet.avro.projection` | `String` | The Avro schema to be used for projection. | +| `parquet.avro.compatible` | `boolean` | Flag for compatibility mode. `true` for materializing Avro `IndexedRecord` objects, `false` for materializing the related objects for either generic, specific, or reflect records.<br/>The default value is `true`. | +| `parquet.avro.readInt96AsFixed` | `boolean` | Flag for handling the `INT96` Parquet types. `true` for converting it to the `fixed` Avro type, `false` for not handling `INT96` types (throwing exception).<br/>The default value is `false`.<br/>**NOTE: The `INT96` Parquet type is deprecated. This option is only to support old data.** | +| `parquet.avro.serializable.classes` | `String` | List of the fully qualified class names separated by ',' that may be referenced from the Avro schema by "java-class" or "java-key-class" and are allowed to be loaded. | ### Configuration for writing -| Name | Type | Description | -|-----------------------------------------|-----------|----------------------------------------------------------------------| -| `parquet.avro.write.data.supplier` | `Class` | The implementation of the interface org.apache.parquet.avro.AvroDataSupplier. Available implementations in the library: GenericDataSupplier, ReflectDataSupplier, SpecificDataSupplier.<br/>The default value is `org.apache.parquet.avro.SpecificDataSupplier` | -| `parquet.avro.schema` | `String` | The Avro schema to be used for generating the Parquet schema of the file. | -| `parquet.avro.write-old-list-structure` | `boolean` | Flag whether to write list structures in the old way (2 levels) or the new one (3 levels). When writing at 2 levels no null values are available at the element level.<br/>The default value is `true` | -| `parquet.avro.add-list-element-records` | `boolean` | Flag whether to assume that any repeated element in the schema is a list element.<br/>The default value is `true`. | -| `parquet.avro.write-parquet-uuid` | `boolean` | Flag whether to write the [Parquet UUID logical type](https://github.com/apache/parquet-format/blob/master/LogicalTypes.md#uuid) in case of an [Avro UUID type](https://avro.apache.org/docs/current/spec.html#UUID) is present.<br/>The default value is `false`. | -| `parquet.avro.writeFixedAsInt96` | `String` | Comma separated list of paths pointing to Avro schema elements which are to be converted to `INT96` Parquet types.<br/>The path is a `'.'` separated list of field names and does not contain the name of the schema nor the namespace. The type of the referenced schema elements must be `fixed` with the size of 12 bytes.<br/>**NOTE: The `INT96` Parquet type is deprecated. This option is only to support old data.** | +| Name | Type | Description | Review Comment: Could we avoid these irrelevant changes? Does IntelliJ IDEA format it automatically? -- 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]
