stevenzwu commented on a change in pull request #2105:
URL: https://github.com/apache/iceberg/pull/2105#discussion_r568837059
##########
File path:
flink/src/main/java/org/apache/iceberg/flink/source/FlinkSplitGenerator.java
##########
@@ -21,29 +21,46 @@
import java.io.IOException;
import java.io.UncheckedIOException;
+import java.util.ArrayList;
import java.util.List;
import org.apache.iceberg.CombinedScanTask;
import org.apache.iceberg.Table;
import org.apache.iceberg.TableProperties;
import org.apache.iceberg.TableScan;
import org.apache.iceberg.expressions.Expression;
+import org.apache.iceberg.flink.source.split.IcebergSourceSplit;
import org.apache.iceberg.io.CloseableIterable;
import org.apache.iceberg.relocated.com.google.common.collect.Lists;
-class FlinkSplitGenerator {
+public class FlinkSplitGenerator {
private FlinkSplitGenerator() {
}
static FlinkInputSplit[] createInputSplits(Table table, ScanContext context)
{
- List<CombinedScanTask> tasks = tasks(table, context);
- FlinkInputSplit[] splits = new FlinkInputSplit[tasks.size()];
- for (int i = 0; i < tasks.size(); i++) {
- splits[i] = new FlinkInputSplit(i, tasks.get(i));
+ try (CloseableIterable<CombinedScanTask> tasksIterable = planTasks(table,
context)) {
+ List<CombinedScanTask> tasks = Lists.newArrayList(tasksIterable);
+ FlinkInputSplit[] splits = new FlinkInputSplit[tasks.size()];
+ for (int i = 0; i < tasks.size(); i++) {
+ splits[i] = new FlinkInputSplit(i, tasks.get(i));
+ }
+ return splits;
+ } catch (IOException e) {
+ throw new UncheckedIOException("Failed to process tasks iterable", e);
+ }
+ }
+
+ public static List<IcebergSourceSplit> planIcebergSourceSplits(
+ Table table, ScanContext context) {
+ try (CloseableIterable<CombinedScanTask> tasksIterable = planTasks(table,
context)) {
+ List<IcebergSourceSplit> splits = new ArrayList<>();
Review comment:
thx. fixed two places in this PR
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
