Skip to content
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

Use write.target-file-size-bytes config, previously Long.MAX_VALUE was used #412

Merged
merged 1 commit into from
Sep 8, 2024
Merged

Use write.target-file-size-bytes config, previously Long.MAX_VALUE was used #412

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
15 changes: 11 additions & 4 deletions ...ink/src/main/java/io/debezium/server/iceberg/tableoperator/IcebergTableWriterFactory.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,10 +12,14 @@
import org.apache.iceberg.io.BaseTaskWriter;
import org.apache.iceberg.io.OutputFileFactory;
import org.apache.iceberg.io.UnpartitionedWriter;
import org.apache.iceberg.util.PropertyUtil;
import org.eclipse.microprofile.config.inject.ConfigProperty;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import static org.apache.iceberg.TableProperties.WRITE_TARGET_FILE_SIZE_BYTES;
import static org.apache.iceberg.TableProperties.WRITE_TARGET_FILE_SIZE_BYTES_DEFAULT;

/**
* Iceberg Table Writer Factory to get TaskWriter for the table. upsert modes used to return correct writer.
*
Expand All @@ -37,6 +41,9 @@ public BaseTaskWriter<Record> create(Table icebergTable) {
OutputFileFactory fileFactory = IcebergUtil.getTableOutputFileFactory(icebergTable, format);
// equality Field Ids
Set<Integer> equalityFieldIds = icebergTable.schema().identifierFieldIds();
long targetFileSize =
PropertyUtil.propertyAsLong(
icebergTable.properties(), WRITE_TARGET_FILE_SIZE_BYTES, WRITE_TARGET_FILE_SIZE_BYTES_DEFAULT);
BaseTaskWriter<Record> writer;

// 1. TABLE DONT HAVE identifierFieldIds
Expand All @@ -52,12 +59,12 @@ public BaseTaskWriter<Record> create(Table icebergTable) {
if (icebergTable.spec().isUnpartitioned()) {
// table is un partitioned use un partitioned append writer
writer = new UnpartitionedWriter<>(
icebergTable.spec(), format, appenderFactory, fileFactory, icebergTable.io(), Long.MAX_VALUE);
icebergTable.spec(), format, appenderFactory, fileFactory, icebergTable.io(), targetFileSize);

} else {
// table is partitioned use partitioned append writer
writer = new PartitionedAppendWriter(
icebergTable.spec(), format, appenderFactory, fileFactory, icebergTable.io(), Long.MAX_VALUE, icebergTable.schema());
icebergTable.spec(), format, appenderFactory, fileFactory, icebergTable.io(), targetFileSize, icebergTable.schema());
}

}
Expand All @@ -69,12 +76,12 @@ else if (icebergTable.spec().isUnpartitioned()) {
// running with upsert mode + un partitioned table
writer = new UnpartitionedDeltaWriter(icebergTable.spec(), format, appenderFactory, fileFactory,
icebergTable.io(),
Long.MAX_VALUE, icebergTable.schema(), equalityFieldIds, true, upsertKeepDeletes);
targetFileSize, icebergTable.schema(), equalityFieldIds, true, upsertKeepDeletes);
} else {
// running with upsert mode + partitioned table
writer = new PartitionedDeltaWriter(icebergTable.spec(), format, appenderFactory, fileFactory,
icebergTable.io(),
Long.MAX_VALUE, icebergTable.schema(), equalityFieldIds, true, upsertKeepDeletes);
targetFileSize, icebergTable.schema(), equalityFieldIds, true, upsertKeepDeletes);
}

return writer;
Expand Down