singhpk234 commented on code in PR #4807:
URL: https://github.com/apache/iceberg/pull/4807#discussion_r887150631
##########
spark/v3.2/spark-extensions/src/test/java/org/apache/iceberg/spark/extensions/TestMetadataTables.java:
##########
@@ -319,6 +319,81 @@ public void testAllFilesPartitioned() throws Exception {
TestHelpers.assertEqualsSafe(filesTableSchema.asStruct(), expectedFiles,
actualFiles);
}
+ @Test
+ public void testSnapshotReferencesMetatable() throws Exception {
+ // Create table and insert data
+ sql("CREATE TABLE %s (id bigint, data string) " +
+ "USING iceberg " +
+ "PARTITIONED BY (data) " +
+ "TBLPROPERTIES" +
+ "('format-version'='2', 'write.delete.mode'='merge-on-read')",
tableName);
+
+ List<SimpleRecord> recordsA = Lists.newArrayList(
+ new SimpleRecord(1, "a"),
+ new SimpleRecord(2, "a")
+ );
+ spark.createDataset(recordsA, Encoders.bean(SimpleRecord.class))
+ .coalesce(1)
+ .writeTo(tableName)
+ .append();
+
+ List<SimpleRecord> recordsB = Lists.newArrayList(
+ new SimpleRecord(1, "b"),
+ new SimpleRecord(2, "b")
+ );
+ spark.createDataset(recordsB, Encoders.bean(SimpleRecord.class))
+ .coalesce(1)
+ .writeTo(tableName)
+ .append();
+
+ Table table = Spark3Util.loadIcebergTable(spark, tableName);
+ Long currentSnapshotId = table.currentSnapshot().snapshotId();
+
+ // Create branch
+ table.manageSnapshots()
+ .createBranch("testBranch", currentSnapshotId)
+ .setMaxRefAgeMs("testBranch", 10)
+ .setMinSnapshotsToKeep("testBranch", 20)
+ .setMaxSnapshotAgeMs("testBranch", 30)
+ .commit();
+ // Create Tag
+ table.manageSnapshots()
+ .createTag("testTag", currentSnapshotId)
+ .setMaxRefAgeMs("testTag", 50)
+ .commit();
+ // Check refs table
+ List<Row> references = spark.sql("SELECT * FROM " + tableName +
".refs").collectAsList();
+ Assert.assertEquals("Refs table should return 3 rows", 3,
references.size());
+ List<Row> branches = spark.sql("SELECT * FROM " + tableName + ".refs WHERE
type='BRANCH'").collectAsList();
+ Assert.assertEquals("Refs table should return 2 branches", 2,
branches.size());
+ List<Row> tags = spark.sql("SELECT * FROM " + tableName + ".refs WHERE
type='TAG'").collectAsList();
+ Assert.assertEquals("Refs table should return 1 tag", 1, tags.size());
+
+ // Check branch entries in refs table
+ List<Row> mainBranch =
+ spark.sql("SELECT * FROM " + tableName + ".refs WHERE name = 'main'
AND type='BRANCH'").collectAsList();
+ Assert.assertEquals("main", mainBranch.get(0).getAs("name"));
+ Assert.assertEquals("BRANCH", mainBranch.get(0).getAs("type"));
+ Assert.assertEquals(currentSnapshotId,
mainBranch.get(0).getAs("snapshot_id"));
+
+ List<Row> testBranch =
+ spark.sql("SELECT * FROM " + tableName + ".refs WHERE name =
'testBranch' AND type='BRANCH'").collectAsList();
+ Assert.assertEquals("testBranch", testBranch.get(0).getAs("name"));
+ Assert.assertEquals("BRANCH", testBranch.get(0).getAs("type"));
+ Assert.assertEquals(currentSnapshotId,
testBranch.get(0).getAs("snapshot_id"));
+ Assert.assertEquals(Long.valueOf(10),
testBranch.get(0).getAs("max_reference_age_in_ms"));
+ Assert.assertEquals(Integer.valueOf(20),
testBranch.get(0).getAs("min_snapshots_to_keep"));
+ Assert.assertEquals(Long.valueOf(30),
testBranch.get(0).getAs("max_snapshot_age_in_ms"));
Review Comment:
[minor] should we also add an UT that is doing projection on top of the
meta-table ? presently all selects are `select *`
--
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]
