the-other-tim-brown commented on code in PR #728: URL: https://github.com/apache/incubator-xtable/pull/728#discussion_r2236782132
########## xtable-core/src/main/java/org/apache/xtable/parquet/ParquetConversionSource.java: ########## @@ -0,0 +1,264 @@ +/* + * 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.xtable.parquet; + +import java.io.IOException; +import java.time.Instant; +import java.util.*; +import java.util.stream.Collectors; + +import lombok.Builder; +import lombok.NonNull; + +import org.apache.hadoop.conf.Configuration; +import org.apache.hadoop.fs.*; +import org.apache.hadoop.util.functional.RemoteIterators; +import org.apache.parquet.hadoop.metadata.ParquetMetadata; +import org.apache.parquet.schema.MessageType; + +import org.apache.xtable.model.*; +import org.apache.xtable.model.CommitsBacklog; +import org.apache.xtable.model.InstantsForIncrementalSync; +import org.apache.xtable.model.TableChange; +import org.apache.xtable.model.schema.InternalPartitionField; +import org.apache.xtable.model.schema.InternalSchema; +import org.apache.xtable.model.storage.*; +import org.apache.xtable.model.storage.FileFormat; +import org.apache.xtable.model.storage.InternalDataFile; +import org.apache.xtable.spi.extractor.ConversionSource; + +@Builder +// @NoArgsConstructor(access = AccessLevel.PRIVATE) +public class ParquetConversionSource implements ConversionSource<Long> { + @Builder.Default + private static final ParquetSchemaExtractor schemaExtractor = + ParquetSchemaExtractor.getInstance(); + + @Builder.Default + private static final ParquetMetadataExtractor parquetMetadataExtractor = + ParquetMetadataExtractor.getInstance(); + @Builder.Default + private static final ParquetStatsExtractor parquetStatsExtractor = + ParquetStatsExtractor.getInstance(); + private final ParquetPartitionValueExtractor partitionValueExtractor; + private final String tableName; + private final String basePath; + private final String configPath; + @NonNull + private final Configuration hadoopConf; + + private InternalTable createInternalTableFromTable(LocatedFileStatus latestFile) { + ParquetMetadata parquetMetadata = + parquetMetadataExtractor.readParquetMetadata(hadoopConf, latestFile.getPath()); + + List<InternalPartitionField> partitionFields = Review Comment: The spec of the partitions is different from the values of the partitions. When you define a table, you define the partitioning of that table as a whole. For example, you would describe the table as "partitioned on date with day granularity" instead of "partition is 2025-07-29." The `extractParquetPartitions` is still required for attaching the partition values to the files. -- 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: commits-unsubscr...@xtable.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
