Skip to content

Core, Spark 4.0: Remove usage of deprecated avro/DataReader class #14387

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

Merged
merged 1 commit into from
Oct 31, 2025
Merged

Core, Spark 4.0: Remove usage of deprecated avro/DataReader class #14387

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
2 changes: 1 addition & 1 deletion core/src/main/java/org/apache/iceberg/data/avro/DataReader.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,7 @@
import org.apache.iceberg.types.Types;

/**
* @deprecated will be removed in 2.0.0; use {@link PlannedDataReader} instead.
* @deprecated will be removed in 1.12.0; use {@link PlannedDataReader} instead.
Copy link
Contributor

@pvary pvary Oct 21, 2025

Choose a reason for hiding this comment

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

I would like to ask you to check this with the community first.

Copy link
Contributor

@nastra nastra Oct 22, 2025

Choose a reason for hiding this comment

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

deprecating this earlier makes sense to me

*/
@Deprecated
public class DataReader<T> implements DatumReader<T>, SupportsRowPosition {
Expand Down
4 changes: 2 additions & 2 deletions ...3.4/spark/src/main/java/org/apache/iceberg/spark/actions/RewriteTablePathSparkAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,8 +51,8 @@
import org.apache.iceberg.actions.RewriteTablePath;
import org.apache.iceberg.avro.Avro;
import org.apache.iceberg.data.Record;
import org.apache.iceberg.data.avro.DataReader;
import org.apache.iceberg.data.avro.DataWriter;
import org.apache.iceberg.data.avro.PlannedDataReader;
import org.apache.iceberg.data.orc.GenericOrcReader;
import org.apache.iceberg.data.orc.GenericOrcWriter;
import org.apache.iceberg.data.parquet.GenericParquetReaders;
Expand Down Expand Up @@ -725,7 +725,7 @@ private static CloseableIterable<Record> positionDeletesReader(
return Avro.read(inputFile)
.project(deleteSchema)
.reuseContainers()
.createReaderFunc(DataReader::create)
.createReaderFunc(fileSchema -> PlannedDataReader.create(deleteSchema))
.build();

case PARQUET:
Expand Down
47 changes: 39 additions & 8 deletions ...3.4/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteTablePathsAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -387,28 +387,59 @@ public void testDeleteDataFile() throws Exception {
}

@Test
public void testPositionDeletes() throws Exception {
public void testPositionDeletesParquet() throws Exception {
runPositionDeletesTest("parquet");
}

@Test
public void testPositionDeletesAvro() throws Exception {
runPositionDeletesTest("avro");
}

@Test
public void testPositionDeletesOrc() throws Exception {
runPositionDeletesTest("orc");
}

private void runPositionDeletesTest(String fileFormat) throws Exception {
Table tableWithPosDeletes =
createTableWithSnapshots(
tableDir.toFile().toURI().toString().concat("tableWithPosDeletes").concat(fileFormat),
2,
Map.of(TableProperties.DELETE_DEFAULT_FILE_FORMAT, fileFormat));

List<Pair<CharSequence, Long>> deletes =
Lists.newArrayList(
Pair.of(
table.currentSnapshot().addedDataFiles(table.io()).iterator().next().location(),
tableWithPosDeletes
.currentSnapshot()
.addedDataFiles(tableWithPosDeletes.io())
.iterator()
.next()
.location(),
0L));

File file = new File(removePrefix(table.location() + "/data/deeply/nested/deletes.parquet"));
File file =
new File(
removePrefix(
tableWithPosDeletes.location() + "/data/deeply/nested/deletes." + fileFormat));
DeleteFile positionDeletes =
FileHelpers.writeDeleteFile(
table, table.io().newOutputFile(file.toURI().toString()), deletes)
tableWithPosDeletes,
tableWithPosDeletes.io().newOutputFile(file.toURI().toString()),
deletes)
.first();

table.newRowDelta().addDeletes(positionDeletes).commit();
tableWithPosDeletes.newRowDelta().addDeletes(positionDeletes).commit();

assertThat(spark.read().format("iceberg").load(table.location()).collectAsList()).hasSize(1);
assertThat(spark.read().format("iceberg").load(tableWithPosDeletes.location()).collectAsList())
.hasSize(1);

RewriteTablePath.Result result =
actions()
.rewriteTablePath(table)
.rewriteTablePath(tableWithPosDeletes)
.stagingLocation(stagingLocation())
.rewriteLocationPrefix(table.location(), targetTableLocation())
.rewriteLocationPrefix(tableWithPosDeletes.location(), targetTableLocation())
.execute();

// We have one more snapshot, an additional manifest list, and a new (delete) manifest,
Expand Down
4 changes: 2 additions & 2 deletions ...3.5/spark/src/main/java/org/apache/iceberg/spark/actions/RewriteTablePathSparkAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,8 +51,8 @@
import org.apache.iceberg.actions.RewriteTablePath;
import org.apache.iceberg.avro.Avro;
import org.apache.iceberg.data.Record;
import org.apache.iceberg.data.avro.DataReader;
import org.apache.iceberg.data.avro.DataWriter;
import org.apache.iceberg.data.avro.PlannedDataReader;
import org.apache.iceberg.data.orc.GenericOrcReader;
import org.apache.iceberg.data.orc.GenericOrcWriter;
import org.apache.iceberg.data.parquet.GenericParquetReaders;
Expand Down Expand Up @@ -725,7 +725,7 @@ private static CloseableIterable<Record> positionDeletesReader(
return Avro.read(inputFile)
.project(deleteSchema)
.reuseContainers()
.createReaderFunc(DataReader::create)
.createReaderFunc(fileSchema -> PlannedDataReader.create(deleteSchema))
.build();

case PARQUET:
Expand Down
47 changes: 39 additions & 8 deletions ...3.5/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteTablePathsAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -387,28 +387,59 @@ public void testDeleteDataFile() throws Exception {
}

@Test
public void testPositionDeletes() throws Exception {
public void testPositionDeletesParquet() throws Exception {
runPositionDeletesTest("parquet");
}

@Test
public void testPositionDeletesAvro() throws Exception {
runPositionDeletesTest("avro");
}

@Test
public void testPositionDeletesOrc() throws Exception {
runPositionDeletesTest("orc");
}

private void runPositionDeletesTest(String fileFormat) throws Exception {
Table tableWithPosDeletes =
createTableWithSnapshots(
tableDir.toFile().toURI().toString().concat("tableWithPosDeletes").concat(fileFormat),
2,
Map.of(TableProperties.DELETE_DEFAULT_FILE_FORMAT, fileFormat));

List<Pair<CharSequence, Long>> deletes =
Lists.newArrayList(
Pair.of(
table.currentSnapshot().addedDataFiles(table.io()).iterator().next().location(),
tableWithPosDeletes
.currentSnapshot()
.addedDataFiles(tableWithPosDeletes.io())
.iterator()
.next()
.location(),
0L));

File file = new File(removePrefix(table.location() + "/data/deeply/nested/deletes.parquet"));
File file =
new File(
removePrefix(
tableWithPosDeletes.location() + "/data/deeply/nested/deletes." + fileFormat));
DeleteFile positionDeletes =
FileHelpers.writeDeleteFile(
table, table.io().newOutputFile(file.toURI().toString()), deletes)
tableWithPosDeletes,
tableWithPosDeletes.io().newOutputFile(file.toURI().toString()),
deletes)
.first();

table.newRowDelta().addDeletes(positionDeletes).commit();
tableWithPosDeletes.newRowDelta().addDeletes(positionDeletes).commit();

assertThat(spark.read().format("iceberg").load(table.location()).collectAsList()).hasSize(1);
assertThat(spark.read().format("iceberg").load(tableWithPosDeletes.location()).collectAsList())
.hasSize(1);

RewriteTablePath.Result result =
actions()
.rewriteTablePath(table)
.rewriteTablePath(tableWithPosDeletes)
.stagingLocation(stagingLocation())
.rewriteLocationPrefix(table.location(), targetTableLocation())
.rewriteLocationPrefix(tableWithPosDeletes.location(), targetTableLocation())
.execute();

// We have one more snapshot, an additional manifest list, and a new (delete) manifest,
Expand Down
4 changes: 2 additions & 2 deletions ...4.0/spark/src/main/java/org/apache/iceberg/spark/actions/RewriteTablePathSparkAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,8 +51,8 @@
import org.apache.iceberg.actions.RewriteTablePath;
import org.apache.iceberg.avro.Avro;
import org.apache.iceberg.data.Record;
import org.apache.iceberg.data.avro.DataReader;
import org.apache.iceberg.data.avro.DataWriter;
import org.apache.iceberg.data.avro.PlannedDataReader;
import org.apache.iceberg.data.orc.GenericOrcReader;
import org.apache.iceberg.data.orc.GenericOrcWriter;
import org.apache.iceberg.data.parquet.GenericParquetReaders;
Expand Down Expand Up @@ -725,7 +725,7 @@ private static CloseableIterable<Record> positionDeletesReader(
return Avro.read(inputFile)
.project(deleteSchema)
.reuseContainers()
.createReaderFunc(DataReader::create)
.createReaderFunc(fileSchema -> PlannedDataReader.create(deleteSchema))
.build();

case PARQUET:
Expand Down
47 changes: 39 additions & 8 deletions ...4.0/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteTablePathsAction.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -387,28 +387,59 @@ public void testDeleteDataFile() throws Exception {
}

@Test
public void testPositionDeletes() throws Exception {
public void testPositionDeletesParquet() throws Exception {
runPositionDeletesTest("parquet");
}

@Test
public void testPositionDeletesAvro() throws Exception {
runPositionDeletesTest("avro");
}

@Test
public void testPositionDeletesOrc() throws Exception {
runPositionDeletesTest("orc");
}

private void runPositionDeletesTest(String fileFormat) throws Exception {
Table tableWithPosDeletes =
createTableWithSnapshots(
tableDir.toFile().toURI().toString().concat("tableWithPosDeletes").concat(fileFormat),
2,
Map.of(TableProperties.DELETE_DEFAULT_FILE_FORMAT, fileFormat));

List<Pair<CharSequence, Long>> deletes =
Lists.newArrayList(
Pair.of(
table.currentSnapshot().addedDataFiles(table.io()).iterator().next().location(),
tableWithPosDeletes
.currentSnapshot()
.addedDataFiles(tableWithPosDeletes.io())
.iterator()
.next()
.location(),
0L));

File file = new File(removePrefix(table.location() + "/data/deeply/nested/deletes.parquet"));
File file =
new File(
removePrefix(
tableWithPosDeletes.location() + "/data/deeply/nested/deletes." + fileFormat));
DeleteFile positionDeletes =
FileHelpers.writeDeleteFile(
table, table.io().newOutputFile(file.toURI().toString()), deletes)
tableWithPosDeletes,
tableWithPosDeletes.io().newOutputFile(file.toURI().toString()),
deletes)
.first();

table.newRowDelta().addDeletes(positionDeletes).commit();
tableWithPosDeletes.newRowDelta().addDeletes(positionDeletes).commit();

assertThat(spark.read().format("iceberg").load(table.location()).collectAsList()).hasSize(1);
assertThat(spark.read().format("iceberg").load(tableWithPosDeletes.location()).collectAsList())
.hasSize(1);

RewriteTablePath.Result result =
actions()
.rewriteTablePath(table)
.rewriteTablePath(tableWithPosDeletes)
.stagingLocation(stagingLocation())
.rewriteLocationPrefix(table.location(), targetTableLocation())
.rewriteLocationPrefix(tableWithPosDeletes.location(), targetTableLocation())
.execute();

// We have one more snapshot, an additional manifest list, and a new (delete) manifest,
Expand Down