stevenzwu commented on code in PR #12692:
URL: https://github.com/apache/iceberg/pull/12692#discussion_r2067584705
##########
spark/v3.5/spark/src/main/java/org/apache/iceberg/spark/actions/RewriteDataFilesSparkAction.java:
##########
@@ -120,36 +111,39 @@ protected RewriteDataFilesSparkAction self() {
@Override
public RewriteDataFilesSparkAction binPack() {
- Preconditions.checkArgument(
- rewriter == null, "Must use only one rewriter type (bin-pack, sort,
zorder)");
- this.rewriter = new SparkBinPackDataRewriter(spark(), table);
+ checkRunnerIsUnset();
+ this.runner = new SparkBinPackFileRewriteRunner(spark(), table);
return this;
}
@Override
public RewriteDataFilesSparkAction sort(SortOrder sortOrder) {
- Preconditions.checkArgument(
- rewriter == null, "Must use only one rewriter type (bin-pack, sort,
zorder)");
- this.rewriter = new SparkSortDataRewriter(spark(), table, sortOrder);
+ checkRunnerIsUnset();
+ this.runner = new SparkSortFileRewriteRunner(spark(), table, sortOrder);
return this;
}
@Override
public RewriteDataFilesSparkAction sort() {
- Preconditions.checkArgument(
- rewriter == null, "Must use only one rewriter type (bin-pack, sort,
zorder)");
- this.rewriter = new SparkSortDataRewriter(spark(), table);
+ checkRunnerIsUnset();
+ this.runner = new SparkSortFileRewriteRunner(spark(), table);
return this;
}
@Override
public RewriteDataFilesSparkAction zOrder(String... columnNames) {
- Preconditions.checkArgument(
- rewriter == null, "Must use only one rewriter type (bin-pack, sort,
zorder)");
- this.rewriter = new SparkZOrderDataRewriter(spark(), table,
Arrays.asList(columnNames));
+ checkRunnerIsUnset();
+ this.runner = new SparkZOrderFileRewriteRunner(spark(), table,
Arrays.asList(columnNames));
return this;
}
+ private void checkRunnerIsUnset() {
+ Preconditions.checkArgument(
+ runner == null,
+ "Rewriter type already set to %s",
+ runner == null ? null : runner.description());
Review Comment:
when check fails, `runner` is ensured to be not null. do we need the null
check?
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
