nssalian commented on code in PR #1607: URL: https://github.com/apache/iceberg-go/pull/1607#discussion_r3937012732
########## table/variant_residual.go: ########## @@ -0,0 +1,316 @@ +// 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 ( + "context" + "fmt" + "log/slog" + "strconv" + "strings" + + "github.com/apache/arrow-go/v18/arrow" + "github.com/apache/arrow-go/v18/arrow/array" + "github.com/apache/arrow-go/v18/arrow/compute" + "github.com/apache/arrow-go/v18/arrow/extensions" + "github.com/apache/arrow-go/v18/arrow/memory" + "github.com/apache/iceberg-go" + "github.com/google/uuid" +) + +// augmentSchemaWithExtracts returns fileSchema plus one primitive column per variant extract term. +func augmentSchemaWithExtracts(fileSchema *iceberg.Schema, cols []iceberg.VariantExtractColumn) *iceberg.Schema { + fields := fileSchema.Fields() + for _, c := range cols { + fields = append(fields, iceberg.NestedField{ + ID: c.FieldID, + Name: c.Name, + Type: c.Term.Type().(iceberg.PrimitiveType), + }) + } + + return iceberg.NewSchemaWithIdentifiers(fileSchema.ID, fileSchema.IdentifierFieldIDs, fields...) +} + +// buildExtractColumn materializes one variant extract term into a typed Arrow array over rec. +func buildExtractColumn(col iceberg.VariantExtractColumn, rec arrow.RecordBatch, mem memory.Allocator) (arrow.Array, arrow.Field, error) { + typ := col.Term.Type().(iceberg.PrimitiveType) + dt, err := TypeToArrowType(typ, false, false) + if err != nil { + return nil, arrow.Field{}, err + } + + bldr := array.NewBuilder(mem, dt) + defer bldr.Release() + + n := int(rec.NumRows()) + varName := col.Term.Ref().Field().Name + arr := resolveVariantSource(rec, col.Term.Ref().Field().ID, col.SourcePath) + if arr == nil { + return nil, arrow.Field{}, fmt.Errorf("%w: variant extract column %q not found in file", iceberg.ErrInvalidArgument, varName) + } + varr, ok := arr.(*extensions.VariantArray) + if !ok { + return nil, arrow.Field{}, fmt.Errorf("%w: variant extract column %q is not a VariantArray (got %T)", iceberg.ErrInvalidArgument, varName, arr) + } + + for i := range n { + if varr.IsNull(i) { + bldr.AppendNull() + + continue + } + + v, verr := varr.Value(i) + if verr != nil { + slog.Warn("variant extract: skipping undecodable variant value", "column", varName, "row", i, "err", verr) + bldr.AppendNull() + + continue + } + + lit, ok := col.Term.ExtractValue(v) + if !ok { + bldr.AppendNull() + + continue + } + + if aerr := appendExtractLiteral(bldr, lit); aerr != nil { + return nil, arrow.Field{}, aerr + } + } + + field := arrow.Field{ + Name: col.Name, + Type: dt, + Nullable: true, + Metadata: arrow.NewMetadata([]string{ArrowParquetFieldIDKey}, []string{strconv.Itoa(col.FieldID)}), + } + + return bldr.NewArray(), field, nil +} + +// resolveVariantSource locates the extract's source array by field id, descending +// nested structs; it falls back to the file-schema path when field ids are absent. +func resolveVariantSource(rec arrow.RecordBatch, fieldID int, sourcePath string) arrow.Array { + for i, f := range rec.Schema().Fields() { + if a := descendByFieldID(f, rec.Column(i), fieldID); a != nil { + return a + } + } + if sourcePath == "" { + return nil + } Review Comment: Fixed this. This now carries structured path segments from the schema (columnPathSegments walks the nested fields) instead of re-splitting the flattened name, so a column literally named a.b stays one segment. Added TestBuildExtractColumnDottedName. -- 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]
