badalprasadsingh commented on code in PR #1214: URL: https://github.com/apache/iceberg-go/pull/1214#discussion_r3499702978
########## table/data_file_meta.go: ########## @@ -0,0 +1,270 @@ +// 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 table + +import ( + "errors" + "fmt" + + "github.com/apache/arrow-go/v18/parquet/metadata" + "github.com/apache/iceberg-go" + tblutils "github.com/apache/iceberg-go/table/internal" +) + +// DataFileArgs collects everything needed to compute a fully populated +// [iceberg.DataFile] (data, equality-delete, or positional-delete) from +// a file's in-memory, format-specific metadata object without performing +// any filesystem reads. +type DataFileArgs struct { + // Schema is the Iceberg schema the file's contents conform to. The + // file's columns MUST carry per-leaf field-ID metadata whose values + // match this schema's field IDs (for Parquet this is the + // "PARQUET:field_id" key on each leaf). + Schema *iceberg.Schema + + // Spec is the partition spec the resulting DataFile is bound to — + // typically tbl.Spec(). The zero value [iceberg.PartitionSpec]{} is + // equivalent to *iceberg.UnpartitionedSpec and is accepted for + // unpartitioned tables. + Spec iceberg.PartitionSpec + + // Format identifies the on-disk file format of the file being + // described and selects the internal FileFormat implementation used + // to extract per-column statistics from Metadata. + Format iceberg.FileFormat + + // Metadata is the format-specific, in-memory file metadata object + // produced by the external writer (for example + // *parquet/metadata.FileMetaData when Format is + // [iceberg.ParquetFile]). + Metadata any Review Comment: Done. Chose to keep `any` for forward-compat and documented the invariant loudly on `Format`, `Metadata`, and the function doc. -- 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]
