Repository navigation
Data, MR: IcebergInputFormat to read encrypted delete files #18484
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
pvary
merged 3 commits into
apache:main
from
gaborkaszab:main_IcebergInputFormat_decryption
Nov 18, 2026
Merged
Changes from all commits
Commits
Show all changes
3 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Some comments aren't visible on the classic Files Changed page.
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
160 changes: 160 additions & 0 deletions
160
mr/src/test/java/org/apache/iceberg/mr/mapreduce/TestIcebergInputFormatEncryption.java
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,160 @@ | ||
| /* | ||
| * 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.mr.mapreduce; | ||
|
|
||
| import static org.apache.iceberg.types.Types.NestedField.optional; | ||
| import static org.apache.iceberg.types.Types.NestedField.required; | ||
| import static org.assertj.core.api.Assertions.assertThat; | ||
|
|
||
| import java.io.File; | ||
| import java.io.IOException; | ||
| import java.util.List; | ||
| import org.apache.hadoop.conf.Configuration; | ||
| import org.apache.hadoop.mapreduce.RecordReader; | ||
| import org.apache.hadoop.mapreduce.TaskAttemptContext; | ||
| import org.apache.hadoop.mapreduce.TaskAttemptID; | ||
| import org.apache.hadoop.mapreduce.task.TaskAttemptContextImpl; | ||
| import org.apache.iceberg.CombinedScanTask; | ||
| import org.apache.iceberg.DataFile; | ||
| import org.apache.iceberg.DeleteFile; | ||
| import org.apache.iceberg.Files; | ||
| import org.apache.iceberg.PartitionSpec; | ||
| import org.apache.iceberg.Schema; | ||
| import org.apache.iceberg.SchemaParser; | ||
| import org.apache.iceberg.SerializableTable; | ||
| import org.apache.iceberg.SortOrder; | ||
| import org.apache.iceberg.Table; | ||
| import org.apache.iceberg.TestTables; | ||
| import org.apache.iceberg.data.FileHelpers; | ||
| import org.apache.iceberg.data.GenericRecord; | ||
| import org.apache.iceberg.data.Record; | ||
| import org.apache.iceberg.encryption.EncryptingFileIO; | ||
| import org.apache.iceberg.encryption.EncryptionManager; | ||
| import org.apache.iceberg.encryption.EncryptionTestHelpers; | ||
| import org.apache.iceberg.io.CloseableIterable; | ||
| import org.apache.iceberg.io.OutputFile; | ||
| import org.apache.iceberg.mr.InputFormatConfig; | ||
| import org.apache.iceberg.types.Types; | ||
| import org.apache.iceberg.util.Pair; | ||
| import org.apache.iceberg.util.StructLikeSet; | ||
| import org.junit.jupiter.api.AfterEach; | ||
| import org.junit.jupiter.api.BeforeEach; | ||
| import org.junit.jupiter.api.Test; | ||
| import org.junit.jupiter.api.io.TempDir; | ||
|
|
||
| class TestIcebergInputFormatEncryption { | ||
| private static final Schema SCHEMA = | ||
| new Schema( | ||
| required(1, "id", Types.LongType.get()), optional(2, "data", Types.StringType.get())); | ||
|
|
||
| @TempDir private File tableDir; | ||
|
|
||
| private Table table; | ||
|
|
||
| @BeforeEach | ||
| void createTable() { | ||
| EncryptionManager encryptionManager = EncryptionTestHelpers.createEncryptionManager(); | ||
| TestTables.TestTableOperations ops = | ||
| new TestTables.TestTableOperations( | ||
| "encrypted", | ||
| tableDir, | ||
| EncryptingFileIO.combine(new TestTables.LocalFileIO(), encryptionManager)) { | ||
| @Override | ||
| public EncryptionManager encryption() { | ||
| return encryptionManager; | ||
| } | ||
| }; | ||
|
|
||
| this.table = | ||
| TestTables.create( | ||
| tableDir, | ||
| "encrypted", | ||
| SCHEMA, | ||
| PartitionSpec.unpartitioned(), | ||
| SortOrder.unsorted(), | ||
| 3, | ||
| ops); | ||
| } | ||
|
|
||
| @AfterEach | ||
| void dropTable() { | ||
| TestTables.clearTables(); | ||
| } | ||
|
|
||
| @Test | ||
| void readEncryptedDataFilesWithDV() throws IOException, InterruptedException { | ||
| Record first = record(1L, "a"); | ||
| Record second = record(2L, "b"); | ||
| Record third = record(3L, "c"); | ||
| DataFile firstFile = | ||
| FileHelpers.writeDataFile(table, outputFile("first.parquet"), List.of(first, second)); | ||
| DataFile secondFile = | ||
| FileHelpers.writeDataFile(table, outputFile("second.parquet"), List.of(third)); | ||
| table.newAppend().appendFile(firstFile).appendFile(secondFile).commit(); | ||
|
|
||
| DeleteFile dv = | ||
| FileHelpers.writeDeleteFile(table, null, List.of(Pair.of(firstFile.location(), 0L)), 3) | ||
| .first(); | ||
| table.newRowDelta().addDeletes(dv).commit(); | ||
|
|
||
| assertThat(firstFile.keyMetadata()).isNotNull(); | ||
| assertThat(secondFile.keyMetadata()).isNotNull(); | ||
| assertThat(dv.keyMetadata()).isNotNull(); | ||
|
|
||
| StructLikeSet expected = StructLikeSet.create(SCHEMA.asStruct()); | ||
| expected.add(second); | ||
| expected.add(third); | ||
|
|
||
| assertThat(readWithInputFormat()).isEqualTo(expected); | ||
| } | ||
|
|
||
| private StructLikeSet readWithInputFormat() throws IOException, InterruptedException { | ||
| Configuration conf = new Configuration(); | ||
| conf.set(InputFormatConfig.TABLE_SCHEMA, SchemaParser.toJson(table.schema())); | ||
| TaskAttemptContext context = new TaskAttemptContextImpl(conf, new TaskAttemptID()); | ||
| IcebergInputFormat<Record> inputFormat = new IcebergInputFormat<>(); | ||
| Table serializableTable = SerializableTable.copyOf(table); | ||
|
|
||
| StructLikeSet actual = StructLikeSet.create(SCHEMA.asStruct()); | ||
| try (CloseableIterable<CombinedScanTask> tasks = table.newScan().planTasks()) { | ||
| for (CombinedScanTask task : tasks) { | ||
| IcebergSplit split = new IcebergSplit(serializableTable, conf, task); | ||
| try (RecordReader<Void, Record> reader = inputFormat.createRecordReader(split, context)) { | ||
| reader.initialize(split, context); | ||
| while (reader.nextKeyValue()) { | ||
| actual.add(reader.getCurrentValue()); | ||
| } | ||
| } | ||
| } | ||
| } | ||
|
|
||
| return actual; | ||
| } | ||
|
|
||
| private static Record record(long id, String data) { | ||
| Record record = GenericRecord.create(SCHEMA); | ||
| record.setField("id", id); | ||
| record.setField("data", data); | ||
| return record; | ||
| } | ||
|
|
||
| private OutputFile outputFile(String fileName) { | ||
| return Files.localOutput(new File(tableDir, fileName)); | ||
| } | ||
| } | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
same question