RussellSpitzer commented on code in PR #4377:
URL: https://github.com/apache/iceberg/pull/4377#discussion_r851320047
##########
spark/v3.2/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteDataFilesAction.java:
##########
@@ -1038,6 +1046,152 @@ public void testInvalidAPIUsage() {
"Cannot set strategy", () ->
actions().rewriteDataFiles(table).sort(SortOrder.unsorted()).binPack());
}
+ @Test
+ public void testRewriteJobOrderBytesAsc() {
+ Table table = createTablePartitioned(4, 2);
+ writeRecords(1, SCALE, 1);
+ writeRecords(2, SCALE, 2);
+ writeRecords(3, SCALE, 3);
+ writeRecords(4, SCALE, 4);
+ table.updateProperties().set(TableProperties.FORMAT_VERSION, "2").commit();
+
+ BaseRewriteDataFilesSparkAction basicRewrite =
+ (org.apache.iceberg.spark.actions.BaseRewriteDataFilesSparkAction)
+ basicRewrite(table)
+ .binPack();
+ List<Long> expected = toGroupStream(table, basicRewrite)
+ .mapToLong(RewriteFileGroup::sizeInBytes)
+ .boxed()
+ .collect(Collectors.toList());
+
+ BaseRewriteDataFilesSparkAction jobOrderRewrite =
+ (org.apache.iceberg.spark.actions.BaseRewriteDataFilesSparkAction)
+ basicRewrite(table)
+ .option(RewriteDataFiles.REWRITE_JOB_ORDER,
RewriteJobOrder.BYTES_ASC.orderName())
+ .binPack();
+ List<Long> actual = toGroupStream(table, jobOrderRewrite)
+ .mapToLong(RewriteFileGroup::sizeInBytes)
+ .boxed()
+ .collect(Collectors.toList());
+
+ expected.sort(Comparator.naturalOrder());
+ Assert.assertEquals("Size in bytes order should be ascending", actual,
expected);
+ Collections.reverse(expected);
+ Assert.assertNotEquals("Size in bytes order should be ascending", actual,
expected);
+ }
+
+ @Test
+ public void testRewriteJobOrderBytesDesc() {
+ Table table = createTablePartitioned(4, 2);
+ writeRecords(1, SCALE, 1);
+ writeRecords(2, SCALE, 2);
+ writeRecords(3, SCALE, 3);
+ writeRecords(4, SCALE, 4);
+ table.updateProperties().set(TableProperties.FORMAT_VERSION, "2").commit();
+
+ BaseRewriteDataFilesSparkAction basicRewrite =
+ (org.apache.iceberg.spark.actions.BaseRewriteDataFilesSparkAction)
+ basicRewrite(table)
+ .binPack();
+ List<Long> expected = toGroupStream(table, basicRewrite)
+ .mapToLong(RewriteFileGroup::sizeInBytes)
+ .boxed()
+ .collect(Collectors.toList());
+
+ BaseRewriteDataFilesSparkAction jobOrderRewrite =
+ (org.apache.iceberg.spark.actions.BaseRewriteDataFilesSparkAction)
+ basicRewrite(table)
+ .option(RewriteDataFiles.REWRITE_JOB_ORDER,
RewriteJobOrder.BYTES_DESC.orderName())
+ .binPack();
+ List<Long> actual = toGroupStream(table, jobOrderRewrite)
+ .mapToLong(RewriteFileGroup::sizeInBytes)
+ .boxed()
+ .collect(Collectors.toList());
+
+ expected.sort(Comparator.reverseOrder());
+ Assert.assertEquals("Size in bytes order should be descending", actual,
expected);
+ Collections.reverse(expected);
+ Assert.assertNotEquals("Size in bytes order should be descending", actual,
expected);
Review Comment:
Should not be ascending
--
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]
