nastra commented on code in PR #9020:
URL: https://github.com/apache/iceberg/pull/9020#discussion_r1396839286
##########
spark/v3.5/spark/src/test/java/org/apache/iceberg/spark/actions/TestRewriteManifestsAction.java:
##########
@@ -649,6 +659,249 @@ public void
testRewriteLargeManifestsEvolvedUnpartitionedV1Table() throws IOExce
assertThat(manifests).hasSizeGreaterThanOrEqualTo(2);
}
+ @Test
+ public void testRewriteSmallDeleteManifestsNonPartitionedTable() throws
IOException {
+ assumeThat(formatVersion).isGreaterThan(1);
+
+ PartitionSpec spec = PartitionSpec.unpartitioned();
+ Map<String, String> options = Maps.newHashMap();
+ options.put(TableProperties.FORMAT_VERSION, String.valueOf(formatVersion));
+ options.put(TableProperties.SNAPSHOT_ID_INHERITANCE_ENABLED,
snapshotIdInheritanceEnabled);
+ Table table = TABLES.create(SCHEMA, spec, options, tableLocation);
+
+ // commit data records
+ List<ThreeColumnRecord> records =
+ Lists.newArrayList(
+ new ThreeColumnRecord(1, null, "AAAA"),
+ new ThreeColumnRecord(2, "BBBBBBBBBB", "BBBB"),
+ new ThreeColumnRecord(3, "CCCCCCCCCC", "CCCC"),
+ new ThreeColumnRecord(4, "DDDDDDDDDD", "DDDD"));
+ writeRecords(records);
+
+ // commit a position delete file to remove records where c1 = 1 OR c1 = 2
+ List<Pair<CharSequence, Long>> posDeletes = generatePosDeletes("c1 = 1 OR
c1 = 2");
+ Pair<DeleteFile, CharSequenceSet> posDeleteWriteResult =
writePosDeletes(table, posDeletes);
+ table
+ .newRowDelta()
+ .addDeletes(posDeleteWriteResult.first())
+ .validateDataFilesExist(posDeleteWriteResult.second())
+ .commit();
+
+ // commit an equality delete file to remove all records where c1 = 3
+ DeleteFile eqDeleteFile = writeEqDeletes(table, "c1", 3);
+ table.newRowDelta().addDeletes(eqDeleteFile).commit();
+
+ // the current snapshot should contain 1 data manifest and 2 delete
manifests
+ List<ManifestFile> originalManifests =
table.currentSnapshot().allManifests(table.io());
+ assertThat(originalManifests).hasSize(3);
+
+ SparkActions actions = SparkActions.get();
+
+ RewriteManifests.Result result =
+ actions
+ .rewriteManifests(table)
+ .option(RewriteManifestsSparkAction.USE_CACHING, useCaching)
+ .execute();
+
+ // the original delete manifests must be combined
+ assertThat(result.rewrittenManifests()).hasSize(2);
Review Comment:
nit: you can usually combine those checks into a single line:
```
assertThat(result.rewrittenManifests())
.hasSize(2)
.allMatch(m -> m.content() == ManifestContent.DELETES);
assertThat(result.addedManifests())
.hasSize(1)
.allMatch(m -> m.content() == ManifestContent.DELETES);
```
--
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
