Skip to content

Spark: Fix RewriteTablePathSparkAction failing on retry when rewritin… #16421

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
MarigWeizhi wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Spark: Fix RewriteTablePathSparkAction failing on retry when rewritin… #16421

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
4 changes: 4 additions & 0 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 @@ -768,26 +768,30 @@ private static PositionDeleteWriter<Record> positionDeletesWriter(
format, EncryptedFiles.plainAsEncryptedOutput(outputFile))
.partition(partition)
.spec(spec)
.overwrite()
.build();
} else {
return switch (format) {
case AVRO ->
Avro.writeDeletes(outputFile)
.createWriterFunc(DataWriter::create)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
.buildPositionWriter();
case PARQUET ->
Parquet.writeDeletes(outputFile)
.createWriterFunc(GenericParquetWriter::create)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
.buildPositionWriter();
case ORC ->
ORC.writeDeletes(outputFile)
.createWriterFunc(GenericOrcWriter::buildWriter)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
Expand Down
47 changes: 47 additions & 0 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 @@ -426,6 +426,53 @@ public void testPositionDeletesOrc() throws Exception {
runPositionDeletesTest("orc");
}

@TestTemplate
public void testRerunWithPositionDeletesReusingStagingLocation() throws Exception {
assumeThat(formatVersion).isEqualTo(2);

Table tableWithPosDeletes =
createTableWithSnapshots(
tableDir.toFile().toURI().toString().concat("tableWithPosDeletesRerun"),
2,
Map.of(TableProperties.DELETE_DEFAULT_FILE_FORMAT, "parquet"));

List<Pair<CharSequence, Long>> deletes =
Lists.newArrayList(
Pair.of(
SnapshotChanges.builderFor(tableWithPosDeletes)
.build()
.addedDataFiles()
.iterator()
.next()
.location(),
0L));
File file =
new File(
removePrefix(tableWithPosDeletes.location() + "/data/deeply/nested/deletes.parquet"));
DeleteFile positionDeletes =
FileHelpers.writeDeleteFile(
tableWithPosDeletes,
tableWithPosDeletes.io().newOutputFile(file.toURI().toString()),
deletes,
formatVersion)
.first();
tableWithPosDeletes.newRowDelta().addDeletes(positionDeletes).commit();

actions()
.rewriteTablePath(tableWithPosDeletes)
.stagingLocation(stagingLocation())
.rewriteLocationPrefix(tableWithPosDeletes.location(), targetTableLocation())
.execute();

RewriteTablePath.Result rerun =
actions()
.rewriteTablePath(tableWithPosDeletes)
.stagingLocation(stagingLocation())
.rewriteLocationPrefix(tableWithPosDeletes.location(), targetTableLocation())
.execute();
assertThat(rerun.rewrittenDeleteFilePathsCount()).isEqualTo(1);
}

private void runPositionDeletesTest(String fileFormat) throws Exception {
Table tableWithPosDeletes =
createTableWithSnapshots(
Expand Down
4 changes: 4 additions & 0 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 @@ -768,26 +768,30 @@ private static PositionDeleteWriter<Record> positionDeletesWriter(
format, EncryptedFiles.plainAsEncryptedOutput(outputFile))
.partition(partition)
.spec(spec)
.overwrite()
.build();
} else {
return switch (format) {
case AVRO ->
Avro.writeDeletes(outputFile)
.createWriterFunc(DataWriter::create)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
.buildPositionWriter();
case PARQUET ->
Parquet.writeDeletes(outputFile)
.createWriterFunc(GenericParquetWriter::create)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
.buildPositionWriter();
case ORC ->
ORC.writeDeletes(outputFile)
.createWriterFunc(GenericOrcWriter::buildWriter)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
Expand Down
47 changes: 47 additions & 0 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 @@ -426,6 +426,53 @@ public void testPositionDeletesOrc() throws Exception {
runPositionDeletesTest("orc");
}

@TestTemplate
public void testRerunWithPositionDeletesReusingStagingLocation() throws Exception {
assumeThat(formatVersion).isEqualTo(2);

Table tableWithPosDeletes =
createTableWithSnapshots(
tableDir.toFile().toURI().toString().concat("tableWithPosDeletesRerun"),
2,
Map.of(TableProperties.DELETE_DEFAULT_FILE_FORMAT, "parquet"));

List<Pair<CharSequence, Long>> deletes =
Lists.newArrayList(
Pair.of(
SnapshotChanges.builderFor(tableWithPosDeletes)
.build()
.addedDataFiles()
.iterator()
.next()
.location(),
0L));
File file =
new File(
removePrefix(tableWithPosDeletes.location() + "/data/deeply/nested/deletes.parquet"));
DeleteFile positionDeletes =
FileHelpers.writeDeleteFile(
tableWithPosDeletes,
tableWithPosDeletes.io().newOutputFile(file.toURI().toString()),
deletes,
formatVersion)
.first();
tableWithPosDeletes.newRowDelta().addDeletes(positionDeletes).commit();

actions()
.rewriteTablePath(tableWithPosDeletes)
.stagingLocation(stagingLocation())
.rewriteLocationPrefix(tableWithPosDeletes.location(), targetTableLocation())
.execute();

RewriteTablePath.Result rerun =
actions()
.rewriteTablePath(tableWithPosDeletes)
.stagingLocation(stagingLocation())
.rewriteLocationPrefix(tableWithPosDeletes.location(), targetTableLocation())
.execute();
assertThat(rerun.rewrittenDeleteFilePathsCount()).isEqualTo(1);
}

private void runPositionDeletesTest(String fileFormat) throws Exception {
Table tableWithPosDeletes =
createTableWithSnapshots(
Expand Down
4 changes: 4 additions & 0 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 @@ -768,26 +768,30 @@ private static PositionDeleteWriter<Record> positionDeletesWriter(
format, EncryptedFiles.plainAsEncryptedOutput(outputFile))
.partition(partition)
.spec(spec)
.overwrite()
.build();
} else {
return switch (format) {
case AVRO ->
Avro.writeDeletes(outputFile)
.createWriterFunc(DataWriter::create)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
.buildPositionWriter();
case PARQUET ->
Parquet.writeDeletes(outputFile)
.createWriterFunc(GenericParquetWriter::create)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
.buildPositionWriter();
case ORC ->
ORC.writeDeletes(outputFile)
.createWriterFunc(GenericOrcWriter::buildWriter)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
Expand Down
47 changes: 47 additions & 0 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 @@ -426,6 +426,53 @@ public void testPositionDeletesOrc() throws Exception {
runPositionDeletesTest("orc");
}

@TestTemplate
public void testRerunWithPositionDeletesReusingStagingLocation() throws Exception {
assumeThat(formatVersion).isEqualTo(2);

Table tableWithPosDeletes =
createTableWithSnapshots(
tableDir.toFile().toURI().toString().concat("tableWithPosDeletesRerun"),
2,
Map.of(TableProperties.DELETE_DEFAULT_FILE_FORMAT, "parquet"));

List<Pair<CharSequence, Long>> deletes =
Lists.newArrayList(
Pair.of(
SnapshotChanges.builderFor(tableWithPosDeletes)
.build()
.addedDataFiles()
.iterator()
.next()
.location(),
0L));
File file =
new File(
removePrefix(tableWithPosDeletes.location() + "/data/deeply/nested/deletes.parquet"));
DeleteFile positionDeletes =
FileHelpers.writeDeleteFile(
tableWithPosDeletes,
tableWithPosDeletes.io().newOutputFile(file.toURI().toString()),
deletes,
formatVersion)
.first();
tableWithPosDeletes.newRowDelta().addDeletes(positionDeletes).commit();

actions()
.rewriteTablePath(tableWithPosDeletes)
.stagingLocation(stagingLocation())
.rewriteLocationPrefix(tableWithPosDeletes.location(), targetTableLocation())
.execute();

RewriteTablePath.Result rerun =
actions()
.rewriteTablePath(tableWithPosDeletes)
.stagingLocation(stagingLocation())
.rewriteLocationPrefix(tableWithPosDeletes.location(), targetTableLocation())
.execute();
assertThat(rerun.rewrittenDeleteFilePathsCount()).isEqualTo(1);
}

private void runPositionDeletesTest(String fileFormat) throws Exception {
Table tableWithPosDeletes =
createTableWithSnapshots(
Expand Down
4 changes: 4 additions & 0 deletions ...4.1/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 @@ -768,26 +768,30 @@ private static PositionDeleteWriter<Record> positionDeletesWriter(
format, EncryptedFiles.plainAsEncryptedOutput(outputFile))
.partition(partition)
.spec(spec)
.overwrite()
.build();
} else {
return switch (format) {
case AVRO ->
Avro.writeDeletes(outputFile)
.createWriterFunc(DataWriter::create)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
.buildPositionWriter();
case PARQUET ->
Parquet.writeDeletes(outputFile)
.createWriterFunc(GenericParquetWriter::create)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
.buildPositionWriter();
case ORC ->
ORC.writeDeletes(outputFile)
.createWriterFunc(GenericOrcWriter::buildWriter)
.overwrite()
.withPartition(partition)
.rowSchema(rowSchema)
.withSpec(spec)
Expand Down
47 changes: 47 additions & 0 deletions ...4.1/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 @@ -426,6 +426,53 @@ public void testPositionDeletesOrc() throws Exception {
runPositionDeletesTest("orc");
}

@TestTemplate
public void testRerunWithPositionDeletesReusingStagingLocation() throws Exception {
assumeThat(formatVersion).isEqualTo(2);

Table tableWithPosDeletes =
createTableWithSnapshots(
tableDir.toFile().toURI().toString().concat("tableWithPosDeletesRerun"),
2,
Map.of(TableProperties.DELETE_DEFAULT_FILE_FORMAT, "parquet"));

List<Pair<CharSequence, Long>> deletes =
Lists.newArrayList(
Pair.of(
SnapshotChanges.builderFor(tableWithPosDeletes)
.build()
.addedDataFiles()
.iterator()
.next()
.location(),
0L));
File file =
new File(
removePrefix(tableWithPosDeletes.location() + "/data/deeply/nested/deletes.parquet"));
DeleteFile positionDeletes =
FileHelpers.writeDeleteFile(
tableWithPosDeletes,
tableWithPosDeletes.io().newOutputFile(file.toURI().toString()),
deletes,
formatVersion)
.first();
tableWithPosDeletes.newRowDelta().addDeletes(positionDeletes).commit();

actions()
.rewriteTablePath(tableWithPosDeletes)
.stagingLocation(stagingLocation())
.rewriteLocationPrefix(tableWithPosDeletes.location(), targetTableLocation())
.execute();

RewriteTablePath.Result rerun =
actions()
.rewriteTablePath(tableWithPosDeletes)
.stagingLocation(stagingLocation())
.rewriteLocationPrefix(tableWithPosDeletes.location(), targetTableLocation())
.execute();
assertThat(rerun.rewrittenDeleteFilePathsCount()).isEqualTo(1);
}

private void runPositionDeletesTest(String fileFormat) throws Exception {
Table tableWithPosDeletes =
createTableWithSnapshots(
Expand Down