Revanth14 commented on code in PR #1492: URL: https://github.com/apache/iceberg-go/pull/1492#discussion_r3635490058
########## catalog/rest/scan_task_decoder_test.go: ########## @@ -0,0 +1,544 @@ +// 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 rest + +import ( + "encoding/json" + "testing" + + "github.com/apache/iceberg-go" + "github.com/apache/iceberg-go/table" + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +func TestDecodeScanTasksFullPayload(t *testing.T) { + t.Parallel() + + metadata := newScanTaskDecoderMetadata() + var wire ScanTasks + require.NoError(t, json.Unmarshal([]byte(`{ + "file-scan-tasks": [{ + "data-file": { + "spec-id": 7, + "partition": [34, "2026-07-17", "78797A21"], + "content": "data", + "file-path": "s3://bucket/table/data.parquet", + "file-format": "parquet", + "file-size-in-bytes": 4096, + "record-count": 100, + "key-metadata": "0A0B", + "split-offsets": [4, 128], + "sort-order-id": 3, + "first-row-id": 99, + "column-sizes": {"keys": [1, 2], "values": [800, 1200]}, + "value-counts": {"keys": [1, 2], "values": [100, 100]}, + "null-value-counts": {"keys": [1, 2], "values": [0, 1]}, + "nan-value-counts": {"keys": [7], "values": [2]}, + "lower-bounds": { + "keys": [8, 9], + "values": ["01000000", "02000000"] + }, + "upper-bounds": { + "keys": [8, 9], + "values": ["05000000", "0A000000"] + } + }, + "delete-file-references": [0, 1, 2], + "residual-filter": {"type": "eq", "term": "id", "value": 34} + }], + "delete-files": [ + { + "spec-id": 7, + "partition": [34, "2026-07-17", "78797A21"], + "content": "position-deletes", + "file-path": "s3://bucket/table/pos-delete.parquet", + "file-format": "parquet", + "file-size-in-bytes": 512, + "record-count": 5 + }, + { + "spec-id": 7, + "partition": [34, "2026-07-17", "78797A21"], + "content": "equality-deletes", + "file-path": "s3://bucket/table/eq-delete.parquet", + "file-format": "parquet", + "file-size-in-bytes": 256, + "record-count": 3, + "equality-ids": [1, 2] + }, + { + "spec-id": 7, + "partition": [34, "2026-07-17", "78797A21"], + "content": "position-deletes", + "file-path": "s3://bucket/table/deletes.puffin", + "file-format": "puffin", + "file-size-in-bytes": 1024, + "record-count": 7, + "referenced-data-file": "s3://bucket/table/data.parquet", + "content-offset": 25, + "content-size-in-bytes": 50 + } + ] + }`), &wire)) + + tasks, err := DecodeScanTasks(wire, metadata, metadata.schema, iceberg.AlwaysTrue{}) + require.NoError(t, err) + require.Len(t, tasks, 1) + + task := tasks[0] + assert.Equal(t, "s3://bucket/table/data.parquet", task.File.FilePath()) + assert.Equal(t, int64(4096), task.Length) + assert.Zero(t, task.Start) + assert.Equal(t, map[int]any{ + 1000: int64(34), + 1001: iceberg.Date(20651), + 1002: []byte("xyz!"), + }, task.File.Partition()) + assert.Equal(t, []byte{0x0a, 0x0b}, task.File.KeyMetadata()) + assert.Equal(t, []int64{4, 128}, task.File.SplitOffsets()) + assert.Equal(t, intPtr(3), task.File.SortOrderID()) + assert.Equal(t, int64Ptr(99), task.FirstRowID) + assert.Equal(t, map[int]int64{1: 800, 2: 1200}, task.File.ColumnSizes()) + assert.Equal(t, map[int]int64{1: 100, 2: 100}, task.File.ValueCounts()) + assert.Equal(t, map[int]int64{1: 0, 2: 1}, task.File.NullValueCounts()) + assert.Equal(t, map[int]int64{7: 2}, task.File.NaNValueCounts()) + + // These vectors mirror Java TestContentFileParser: bounds are hexadecimal + // encodings of raw Iceberg binary values, not typed JSON single-values. + assert.Equal(t, []byte{1, 0, 0, 0}, task.File.LowerBoundValues()[8]) + assert.Equal(t, []byte{2, 0, 0, 0}, task.File.LowerBoundValues()[9]) + assert.Equal(t, []byte{5, 0, 0, 0}, task.File.UpperBoundValues()[8]) + assert.Equal(t, []byte{10, 0, 0, 0}, task.File.UpperBoundValues()[9]) + + require.NotNil(t, task.Residual) + assert.True(t, task.Residual.Equals(iceberg.EqualTo(iceberg.Reference("id"), int64(34)))) + require.Len(t, task.DeleteFiles, 1) + assert.Equal(t, "s3://bucket/table/pos-delete.parquet", task.DeleteFiles[0].FilePath()) + require.Len(t, task.EqualityDeleteFiles, 1) + assert.Equal(t, []int{1, 2}, task.EqualityDeleteFiles[0].EqualityFieldIDs()) + require.Len(t, task.DeletionVectorFiles, 1) + dv := task.DeletionVectorFiles[0] + assert.Equal(t, iceberg.PuffinFile, dv.FileFormat()) + assert.Equal(t, stringPtr("s3://bucket/table/data.parquet"), dv.ReferencedDataFile()) + assert.Equal(t, int64Ptr(25), dv.ContentOffset()) + assert.Equal(t, int64Ptr(50), dv.ContentSizeInBytes()) +} + +func TestDecodeScanTasksUsesFallbackAndAcceptsSpecConstants(t *testing.T) { + t.Parallel() + + metadata := newScanTaskDecoderMetadata() + fallback := iceberg.GreaterThan(iceberg.Reference("id"), int64(10)) + wire := validScanTasksWire() + + tasks, err := DecodeScanTasks(wire, metadata, metadata.schema, fallback) + require.NoError(t, err) + require.Len(t, tasks, 1) + assert.Same(t, fallback, tasks[0].Residual) + + wire.FileScanTasks[0].ResidualFilter = json.RawMessage(`{"type":"false"}`) + tasks, err = DecodeScanTasks(wire, metadata, metadata.schema, fallback) + require.NoError(t, err) + assert.True(t, tasks[0].Residual.Equals(iceberg.AlwaysFalse{})) +} + +func TestDecodeScanTasksKeepsDeleteReferencesEnvelopeLocal(t *testing.T) { + t.Parallel() + + metadata := newScanTaskDecoderMetadata() + first := validScanTasksWire() + first.FileScanTasks[0].DeleteFileReferences = []int{0} + first.DeleteFiles[0].FilePath = "s3://bucket/table/first-delete.parquet" + second := validScanTasksWire() + second.FileScanTasks[0].DataFile.FilePath = "s3://bucket/table/second-data.parquet" + second.FileScanTasks[0].DeleteFileReferences = []int{0} + second.DeleteFiles[0].FilePath = "s3://bucket/table/second-delete.parquet" + + firstTasks, err := DecodeScanTasks(first, metadata, metadata.schema, nil) + require.NoError(t, err) + secondTasks, err := DecodeScanTasks(second, metadata, metadata.schema, nil) + require.NoError(t, err) + + require.Len(t, firstTasks, 1) + require.Len(t, firstTasks[0].DeleteFiles, 1) + assert.Equal(t, "s3://bucket/table/first-delete.parquet", firstTasks[0].DeleteFiles[0].FilePath()) + require.Len(t, secondTasks, 1) + require.Len(t, secondTasks[0].DeleteFiles, 1) + assert.Equal(t, "s3://bucket/table/second-delete.parquet", secondTasks[0].DeleteFiles[0].FilePath()) +} + +func TestDecodeScanTasksDerivesDeletionVectorTargetWhenOmitted(t *testing.T) { + t.Parallel() + + metadata := newScanTaskDecoderMetadata() + wire := validScanTasksWire() + wire.FileScanTasks[0].DeleteFileReferences = []int{0} + wire.DeleteFiles[0].FileFormat = "puffin" + wire.DeleteFiles[0].ContentOffset = int64Ptr(10) + wire.DeleteFiles[0].ContentSizeInBytes = int64Ptr(20) + + tasks, err := DecodeScanTasks(wire, metadata, metadata.schema, nil) + require.NoError(t, err) + require.Len(t, tasks, 1) + require.Len(t, tasks[0].DeletionVectorFiles, 1) + assert.Equal(t, stringPtr("s3://bucket/table/data.parquet"), tasks[0].DeletionVectorFiles[0].ReferencedDataFile()) +} + +func TestRESTValueMapMatchesJavaContentFileParser(t *testing.T) { Review Comment: Added a focused `LiteralFromBytes` test covering int, decimal, and timestamp bounds. It pins the expected little-endian encoding for int/timestamp and two's-complement big-endian encoding for decimal, while keeping the decoder's output as raw bytes. Thanks for the suggestion! -- 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]
