RussellSpitzer commented on code in PR #7585:
URL: https://github.com/apache/iceberg/pull/7585#discussion_r1192713437
##########
spark/v3.4/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteDataFilesAction.java:
##########
@@ -1384,6 +1384,99 @@ public void testRewriteJobOrderFilesDesc() {
Assert.assertNotEquals("Number of files order should not be ascending",
actual, expected);
}
+ @Test
+ public void testZOrderSortPartitionEvolution() {
+ int originalFiles = 20;
+ Table table = createTable(originalFiles);
+ shouldHaveLastCommitUnsorted(table, "c2");
+ shouldHaveFiles(table, originalFiles);
+
+ Stream.of(Expressions.bucket("c1", 2), Expressions.bucket("c2", 4))
+ .forEach(expr -> table.updateSpec().addField(expr).commit());
+
+ long dataSizeBefore = testDataSize(table);
+
+ RewriteDataFiles.Result result =
+ basicRewrite(table)
+ .zOrder("c2", "c3")
+ .option(
+ SortStrategy.MAX_FILE_SIZE_BYTES,
+ Integer.toString((averageFileSize(table) / 2) + 2))
+ // Divide files in 2
+ .option(
+ RewriteDataFiles.TARGET_FILE_SIZE_BYTES,
+ Integer.toString(averageFileSize(table) / 2))
+ .option(SortStrategy.MIN_INPUT_FILES, "1")
+ .execute();
+
+ Assert.assertEquals("Should have 1 fileGroups", 1,
result.rewriteResults().size());
+ assertThat(result.rewrittenBytesCount()).isEqualTo(dataSizeBefore);
+ }
+
+ @Test
+ public void testRewriteWithDifferentOutputSpecIds() {
+ Table table = createTable(10);
+ shouldHaveFiles(table, 10);
+
+ table.updateProperties().set("write.spark.fanout.enabled",
"true").commit();
+ table.replaceSortOrder().asc("c1").asc("c2").commit();
+
+ Stream.of(Expressions.bucket("c1", 2), Expressions.bucket("c2", 4))
+ .forEach(expr -> table.updateSpec().addField(expr).commit());
+
+ performRewriteAndAssertForAllTableSpecs(table, "bin-pack");
+ performRewriteAndAssertForAllTableSpecs(table, "sort");
+ performRewriteAndAssertForAllTableSpecs(table, "zOrder");
+ }
+
+ private void performRewriteAndAssertForAllTableSpecs(Table table, String
strategy) {
+ assertThat(strategy).isIn("bin-pack", "sort", "zOrder");
Review Comment:
seems unnecessary? This is just checking that the lines directly above are
correct?
--
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]
