Skip to content

Core: Fix RewriteTablePath Incremental Replication #12172

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
szehon-ho merged 5 commits into from
Feb 8, 2025
Merged

Core: Fix RewriteTablePath Incremental Replication #12172

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
2e1da73
Core: Rewrite Table Path supports incremental replication
barronfuentes Jan 31, 2025
4cc0820
Merge branch 'main' of https://github.com/StateFarmIns/iceberg into r…
barronfuentes Feb 3, 2025
31a79e5
Merge branch 'main' of https://github.com/StateFarmIns/iceberg into r…
barronfuentes Feb 4, 2025
e72c89b
Assert data of source and target table are equal after incremental re…
barronfuentes Feb 7, 2025
4a5210c
Merge branch 'main' of https://github.com/StateFarmIns/iceberg into r…
barronfuentes Feb 7, 2025
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
15 changes: 6 additions & 9 deletions core/src/main/java/org/apache/iceberg/RewriteTablePathUtil.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,6 @@
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.stream.Collectors;
import java.util.stream.StreamSupport;
import org.apache.iceberg.data.Record;
import org.apache.iceberg.deletes.PositionDelete;
Expand Down Expand Up @@ -225,11 +224,7 @@ public static RewriteResult<ManifestFile> rewriteManifestList(
OutputFile outputFile = io.newOutputFile(outputPath);

List<ManifestFile> manifestFiles = manifestFilesInSnapshot(io, snapshot);
List<ManifestFile> manifestFilesToRewrite =
manifestFiles.stream()
.filter(mf -> manifestsToRewrite.contains(mf.path()))
.collect(Collectors.toList());
manifestFilesToRewrite.forEach(
manifestFiles.forEach(
mf ->
Preconditions.checkArgument(
mf.path().startsWith(sourcePrefix),
Expand All @@ -245,13 +240,15 @@ public static RewriteResult<ManifestFile> rewriteManifestList(
snapshot.parentId(),
snapshot.sequenceNumber())) {

for (ManifestFile file : manifestFilesToRewrite) {
for (ManifestFile file : manifestFiles) {
ManifestFile newFile = file.copy();
((StructLike) newFile).set(0, newPath(newFile.path(), sourcePrefix, targetPrefix));
writer.add(newFile);

result.toRewrite().add(file);
result.copyPlan().add(Pair.of(stagingPath(file.path(), stagingDir), newFile.path()));
if (manifestsToRewrite.contains(file.path())) {
result.toRewrite().add(file);
result.copyPlan().add(Pair.of(stagingPath(file.path(), stagingDir), newFile.path()));
}
}
return result;
} catch (IOException e) {
Expand Down
45 changes: 45 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 @@ -235,6 +235,51 @@ public void testStartVersion() throws Exception {
.isEqualTo(0);
}

@Test
public void testIncrementalRewrite() throws Exception {
String location = newTableLocation();
Table sourceTable =
TABLES.create(SCHEMA, PartitionSpec.unpartitioned(), Maps.newHashMap(), location);
List<ThreeColumnRecord> recordsA =
Lists.newArrayList(new ThreeColumnRecord(1, "AAAAAAAAAA", "AAAA"));
Dataset<Row> dfA = spark.createDataFrame(recordsA, ThreeColumnRecord.class).coalesce(1);

// Write first increment to source table
dfA.select("c1", "c2", "c3").write().format("iceberg").mode("append").save(location);
spark.read().format("iceberg").load(location).show();
Comment thread
barronfuentes marked this conversation as resolved.
Outdated
assertThat(spark.read().format("iceberg").load(location).count()).isEqualTo(1);

// Replicate first increment to target table
RewriteTablePath.Result result =
actions()
.rewriteTablePath(sourceTable)
.rewriteLocationPrefix(sourceTable.location(), targetTableLocation())
.execute();
copyTableFiles(result);
assertThat(spark.read().format("iceberg").load(targetTableLocation()).count()).isEqualTo(1);

// Write second increment to source table
List<ThreeColumnRecord> recordsB =
Lists.newArrayList(new ThreeColumnRecord(1, "BBBBBBBBB", "BBB"));
Dataset<Row> dfB = spark.createDataFrame(recordsB, ThreeColumnRecord.class).coalesce(1);
dfB.select("c1", "c2", "c3").write().format("iceberg").mode("append").save(location);
assertThat(spark.read().format("iceberg").load(location).count()).isEqualTo(2);

// Replicate second increment to target table
Table sourceTableIncrement = TABLES.load(location);
Comment thread
barronfuentes marked this conversation as resolved.
Outdated
Table targetTable = TABLES.load(targetTableLocation());
String targetTableMetadata = currentMetadata(targetTable).metadataFileLocation();
String startVersion = fileName(targetTableMetadata);
RewriteTablePath.Result resultB =
Comment thread
barronfuentes marked this conversation as resolved.
Outdated
actions()
.rewriteTablePath(sourceTableIncrement)
.rewriteLocationPrefix(sourceTable.location(), targetTableLocation())
.startVersion(startVersion)
.execute();
copyTableFiles(resultB);
assertThat(spark.read().format("iceberg").load(targetTableLocation()).count()).isEqualTo(2);
Comment thread
barronfuentes marked this conversation as resolved.
Outdated
}

@Test
public void testTableWith3Snapshots(@TempDir Path location1, @TempDir Path location2)
throws Exception {
Expand Down