Skip to content

MR: Pass partition constants to the format model read builder #18037

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.

Sign up for GitHub

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

Open
thswlsqls wants to merge 1 commit into
base: main
Choose a base branch
from
+58 −0
Open

MR: Pass partition constants to the format model read builder #18037

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 7 additions & 0 deletions mr/src/main/java/org/apache/iceberg/mr/mapreduce/IcebergInputFormat.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,7 @@
import java.io.UncheckedIOException;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.concurrent.ExecutorService;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.InputFormat;
Expand All @@ -45,6 +46,7 @@
import org.apache.iceberg.TableScan;
import org.apache.iceberg.data.DeleteFilter;
import org.apache.iceberg.data.GenericDeleteFilter;
import org.apache.iceberg.data.IdentityPartitionConverters;
import org.apache.iceberg.data.InternalRecordWrapper;
import org.apache.iceberg.data.Record;
import org.apache.iceberg.encryption.EncryptedFiles;
Expand All @@ -63,6 +65,7 @@
import org.apache.iceberg.mr.Catalogs;
import org.apache.iceberg.mr.InputFormatConfig;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
import org.apache.iceberg.util.PartitionUtil;
import org.apache.iceberg.util.SerializationUtil;
import org.apache.iceberg.util.ThreadPools;

Expand Down Expand Up @@ -313,6 +316,9 @@ private CloseableIterable<T> openTask(FileScanTask currentTask, Schema readSchem
encryptionManager.decrypt(
EncryptedFiles.encryptedInput(io.newInputFile(file.location()), file.keyMetadata()));

Map<Integer, ?> partition =

@pvary pvary Sep 10, 2026

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

could we call it idToConstant, or just immediately set on the builder in line 337?

PartitionUtil.constantsMap(currentTask, IdentityPartitionConverters::convertConstant);

ReadBuilder<Record, ?> readBuilder =
FormatModelRegistry.readBuilder(file.format(), Record.class, inputFile);

Expand All @@ -328,6 +334,7 @@ private CloseableIterable<T> openTask(FileScanTask currentTask, Schema readSchem
(CloseableIterable<T>)
readBuilder
.project(readSchema)
.idToConstant(partition)
.split(currentTask.start(), currentTask.length())
.caseSensitive(caseSensitive)
.filter(currentTask.residual())
Expand Down
51 changes: 51 additions & 0 deletions mr/src/test/java/org/apache/iceberg/mr/TestIcebergInputFormats.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.UUID;
import java.util.concurrent.ExecutorService;
import java.util.function.Function;
import org.apache.hadoop.conf.Configuration;
Expand All @@ -47,19 +48,26 @@
import org.apache.iceberg.CatalogUtil;
import org.apache.iceberg.DataFile;
import org.apache.iceberg.FileFormat;
import org.apache.iceberg.Files;
import org.apache.iceberg.Parameter;
import org.apache.iceberg.ParameterizedTestExtension;
import org.apache.iceberg.Parameters;
import org.apache.iceberg.PartitionSpec;
import org.apache.iceberg.Schema;
import org.apache.iceberg.StructLike;
import org.apache.iceberg.Table;
import org.apache.iceberg.TestHelpers.Row;
import org.apache.iceberg.catalog.Catalog;
import org.apache.iceberg.catalog.TableIdentifier;
import org.apache.iceberg.data.FileHelpers;
import org.apache.iceberg.data.GenericFileWriterFactory;
import org.apache.iceberg.data.GenericRecord;
import org.apache.iceberg.data.Record;
import org.apache.iceberg.expressions.Expressions;
import org.apache.iceberg.hadoop.HadoopCatalog;
import org.apache.iceberg.hadoop.HadoopTables;
import org.apache.iceberg.io.DataWriter;
import org.apache.iceberg.io.OutputFile;
import org.apache.iceberg.mr.mapred.Container;
import org.apache.iceberg.mr.mapred.MapredIcebergInputFormat;
import org.apache.iceberg.mr.mapreduce.IcebergInputFormat;
Expand Down Expand Up @@ -298,6 +306,49 @@ private void validateIdentityPartitionProjections(
}
}

@TestTemplate
void identityPartitionValuesMissingFromDataFile() throws Exception {
Table table = helper.createTable(LOG_SCHEMA, IDENTITY_PARTITION_SPEC);

// Tables imported with add_files/migrate have data files that do not physically store the
// identity partition columns; their values only exist in the manifest entry. See
// TableMigrationUtil#listPartition, which reads the partition values from Hive metadata.
Schema fileSchema = withColumns("id", "message");
Record record = GenericRecord.create(fileSchema);
record.setField("id", 1);
record.setField("message", "hello");

DataFile dataFile =
writeFileWithSchema(table, fileSchema, Row.of("2020-03-20", "info"), record);
table.newAppend().appendFile(dataFile).commit();

builder.project(LOG_SCHEMA);
List<Record> records = testInputFormat.create(builder.conf()).getRecords();

assertThat(records).hasSize(1);
assertThat(records.get(0).getField("date")).isEqualTo("2020-03-20");
assertThat(records.get(0).getField("level")).isEqualTo("info");
assertThat(records.get(0).getField("id")).isEqualTo(1);
assertThat(records.get(0).getField("message")).isEqualTo("hello");
}

private DataFile writeFileWithSchema(
Table table, Schema fileSchema, StructLike partition, Record record) throws IOException {
OutputFile outputFile =
Files.localOutput(temp.resolve("partial-schema-" + UUID.randomUUID()).toFile());
DataWriter<Record> writer =
new GenericFileWriterFactory.Builder(table)
.dataFileFormat(fileFormat)
.dataSchema(fileSchema)
.build()
.newDataWriter(FileHelpers.encrypt(outputFile), table.spec(), partition);
try (writer) {
writer.write(record);
}

return writer.toDataFile();
}

@TestTemplate
public void testSnapshotReads() throws Exception {
helper.createUnpartitionedTable();
Expand Down
Loading