rdblue commented on a change in pull request #3501:
URL: https://github.com/apache/iceberg/pull/3501#discussion_r766894812
##########
File path:
flink/v1.13/flink/src/main/java/org/apache/iceberg/flink/source/FlinkSplitPlanner.java
##########
@@ -22,33 +22,58 @@
import java.io.IOException;
import java.io.UncheckedIOException;
import java.util.List;
+import org.apache.flink.annotation.Internal;
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 {
- private FlinkSplitGenerator() {
+@Internal
+public class FlinkSplitPlanner {
+ private FlinkSplitPlanner() {
}
- 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));
+ static FlinkInputSplit[] planInputSplits(Table table, ScanContext context) {
+ 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);
+ }
+ }
+
+ /**
+ * This returns splits for the FLIP-27 source
+ */
+ public static List<IcebergSourceSplit> planIcebergSourceSplits(
+ Table table, ScanContext context) {
+ try (CloseableIterable<CombinedScanTask> tasksIterable = planTasks(table,
context)) {
+ List<IcebergSourceSplit> splits = Lists.newArrayList();
+ tasksIterable.forEach(task ->
splits.add(IcebergSourceSplit.fromCombinedScanTask(task)));
+ return splits;
+ } catch (IOException e) {
+ throw new UncheckedIOException("Failed to process task iterable: ", e);
}
- return splits;
}
- private static List<CombinedScanTask> tasks(Table table, ScanContext
context) {
+ static CloseableIterable<CombinedScanTask> planTasks(Table table,
ScanContext context) {
TableScan scan = table
.newScan()
.caseSensitive(context.caseSensitive())
.project(context.project());
+ if (context.includeColumnStats()) {
+ scan = scan.includeColumnStats();
+ }
Review comment:
I think this is a reasonable addition. I think the motivation is to
change the file in just this PR and not in the others that are part of FLIP-27.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
