ayushtkn commented on code in PR #6152: URL: https://github.com/apache/hive/pull/6152#discussion_r2616947401
########## iceberg/iceberg-handler/src/main/java/org/apache/iceberg/parquet/Parquet.java: ########## @@ -0,0 +1,1524 @@ +/* + * 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.File; +import java.io.IOException; +import java.nio.ByteBuffer; +import java.util.Collection; +import java.util.List; +import java.util.Locale; +import java.util.Map; +import java.util.Objects; +import java.util.function.BiConsumer; +import java.util.function.BiFunction; +import java.util.function.Function; +import java.util.stream.Collectors; +import java.util.stream.IntStream; +import org.apache.hadoop.conf.Configuration; +import org.apache.iceberg.FileFormat; +import org.apache.iceberg.Files; +import org.apache.iceberg.InternalData; +import org.apache.iceberg.MetricsConfig; +import org.apache.iceberg.PartitionSpec; +import org.apache.iceberg.Schema; +import org.apache.iceberg.SchemaParser; +import org.apache.iceberg.SortOrder; +import org.apache.iceberg.StructLike; +import org.apache.iceberg.SystemConfigs; +import org.apache.iceberg.Table; +import org.apache.iceberg.avro.AvroSchemaUtil; +import org.apache.iceberg.data.parquet.GenericParquetWriter; +import org.apache.iceberg.deletes.EqualityDeleteWriter; +import org.apache.iceberg.deletes.PositionDeleteWriter; +import org.apache.iceberg.encryption.EncryptedOutputFile; +import org.apache.iceberg.encryption.EncryptionKeyMetadata; +import org.apache.iceberg.encryption.NativeEncryptionInputFile; +import org.apache.iceberg.encryption.NativeEncryptionOutputFile; +import org.apache.iceberg.exceptions.RuntimeIOException; +import org.apache.iceberg.expressions.Expression; +import org.apache.iceberg.hadoop.HadoopInputFile; +import org.apache.iceberg.hadoop.HadoopOutputFile; +import org.apache.iceberg.io.CloseableIterable; +import org.apache.iceberg.io.DataWriter; +import org.apache.iceberg.io.DeleteSchemaUtil; +import org.apache.iceberg.io.FileAppender; +import org.apache.iceberg.io.InputFile; +import org.apache.iceberg.io.OutputFile; +import org.apache.iceberg.mapping.NameMapping; +import org.apache.iceberg.parquet.ParquetValueWriters.PositionDeleteStructWriter; +import org.apache.iceberg.parquet.ParquetValueWriters.StructWriter; +import org.apache.iceberg.relocated.com.google.common.annotations.VisibleForTesting; +import org.apache.iceberg.relocated.com.google.common.base.Preconditions; +import org.apache.iceberg.relocated.com.google.common.collect.ImmutableMap; +import org.apache.iceberg.relocated.com.google.common.collect.Maps; +import org.apache.iceberg.relocated.com.google.common.collect.Sets; +import org.apache.iceberg.util.ArrayUtil; +import org.apache.iceberg.util.ByteBuffers; +import org.apache.iceberg.util.PropertyUtil; +import org.apache.parquet.HadoopReadOptions; +import org.apache.parquet.ParquetReadOptions; +import org.apache.parquet.avro.AvroReadSupport; +import org.apache.parquet.avro.AvroWriteSupport; +import org.apache.parquet.column.ParquetProperties; +import org.apache.parquet.column.ParquetProperties.WriterVersion; +import org.apache.parquet.conf.PlainParquetConfiguration; +import org.apache.parquet.crypto.FileDecryptionProperties; +import org.apache.parquet.crypto.FileEncryptionProperties; +import org.apache.parquet.hadoop.ParquetFileReader; +import org.apache.parquet.hadoop.ParquetFileWriter; +import org.apache.parquet.hadoop.ParquetOutputFormat; +import org.apache.parquet.hadoop.ParquetReader; +import org.apache.parquet.hadoop.ParquetWriter; +import org.apache.parquet.hadoop.api.ReadSupport; +import org.apache.parquet.hadoop.api.WriteSupport; +import org.apache.parquet.hadoop.metadata.CompressionCodecName; +import org.apache.parquet.schema.MessageType; +import org.apache.parquet.schema.Type.ID; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import static org.apache.iceberg.TableProperties.DELETE_PARQUET_COMPRESSION; +import static org.apache.iceberg.TableProperties.DELETE_PARQUET_COMPRESSION_LEVEL; +import static org.apache.iceberg.TableProperties.DELETE_PARQUET_DICT_SIZE_BYTES; +import static org.apache.iceberg.TableProperties.DELETE_PARQUET_PAGE_ROW_LIMIT; +import static org.apache.iceberg.TableProperties.DELETE_PARQUET_PAGE_SIZE_BYTES; +import static org.apache.iceberg.TableProperties.DELETE_PARQUET_ROW_GROUP_CHECK_MAX_RECORD_COUNT; +import static org.apache.iceberg.TableProperties.DELETE_PARQUET_ROW_GROUP_CHECK_MIN_RECORD_COUNT; +import static org.apache.iceberg.TableProperties.DELETE_PARQUET_ROW_GROUP_SIZE_BYTES; +import static org.apache.iceberg.TableProperties.PARQUET_BLOOM_FILTER_COLUMN_ENABLED_PREFIX; +import static org.apache.iceberg.TableProperties.PARQUET_BLOOM_FILTER_COLUMN_FPP_PREFIX; +import static org.apache.iceberg.TableProperties.PARQUET_BLOOM_FILTER_MAX_BYTES; +import static org.apache.iceberg.TableProperties.PARQUET_BLOOM_FILTER_MAX_BYTES_DEFAULT; +import static org.apache.iceberg.TableProperties.PARQUET_COLUMN_STATS_ENABLED_PREFIX; +import static org.apache.iceberg.TableProperties.PARQUET_COMPRESSION; +import static org.apache.iceberg.TableProperties.PARQUET_COMPRESSION_DEFAULT; +import static org.apache.iceberg.TableProperties.PARQUET_COMPRESSION_LEVEL; +import static org.apache.iceberg.TableProperties.PARQUET_COMPRESSION_LEVEL_DEFAULT; +import static org.apache.iceberg.TableProperties.PARQUET_DICT_SIZE_BYTES; +import static org.apache.iceberg.TableProperties.PARQUET_DICT_SIZE_BYTES_DEFAULT; +import static org.apache.iceberg.TableProperties.PARQUET_PAGE_ROW_LIMIT; +import static org.apache.iceberg.TableProperties.PARQUET_PAGE_ROW_LIMIT_DEFAULT; +import static org.apache.iceberg.TableProperties.PARQUET_PAGE_SIZE_BYTES; +import static org.apache.iceberg.TableProperties.PARQUET_PAGE_SIZE_BYTES_DEFAULT; +import static org.apache.iceberg.TableProperties.PARQUET_ROW_GROUP_CHECK_MAX_RECORD_COUNT; +import static org.apache.iceberg.TableProperties.PARQUET_ROW_GROUP_CHECK_MAX_RECORD_COUNT_DEFAULT; +import static org.apache.iceberg.TableProperties.PARQUET_ROW_GROUP_CHECK_MIN_RECORD_COUNT; +import static org.apache.iceberg.TableProperties.PARQUET_ROW_GROUP_CHECK_MIN_RECORD_COUNT_DEFAULT; +import static org.apache.iceberg.TableProperties.PARQUET_ROW_GROUP_SIZE_BYTES; +import static org.apache.iceberg.TableProperties.PARQUET_ROW_GROUP_SIZE_BYTES_DEFAULT; + +// TODO: remove class once upgraded to Iceberg v1.11.0 (https://github.com/apache/iceberg/pull/14153) Review Comment: they would release it at one point, usually if we need something from a thirdparty lib, we wait for the release, or use the snapshot version till then. We already have copied a lot of iceberg code, one more doesn't make it worse though, but we have to maybe set some precedent one day, what all we can copy & when. Maybe not today or here, but some day. Lets park a ticket for sure so we don't forget to drop it when we upgarde or if someone else does it, they doesn't skip it -- 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]
