RussellSpitzer commented on code in PR #7636:
URL: https://github.com/apache/iceberg/pull/7636#discussion_r1204427426
##########
spark/v3.4/spark/src/test/java/org/apache/iceberg/spark/source/TestDataSourceOptions.java:
##########
@@ -285,29 +286,37 @@ public void testIncrementalScanOptions() throws
IOException {
"Cannot set only end-snapshot-id for incremental scans. Please,
set start-snapshot-id too.");
// test (1st snapshot, current snapshot] incremental scan.
- List<SimpleRecord> result =
+ Dataset<Row> resultDf1 =
spark
.read()
.format("iceberg")
.option("start-snapshot-id", snapshotIds.get(3).toString())
- .load(tableLocation)
- .orderBy("id")
- .as(Encoders.bean(SimpleRecord.class))
- .collectAsList();
- Assert.assertEquals("Records should match", expectedRecords.subList(1, 4),
result);
+ .load(tableLocation);
+ List<SimpleRecord> result1 =
+
resultDf1.orderBy("id").as(Encoders.bean(SimpleRecord.class)).collectAsList();
+ Assert.assertEquals("Records should match", expectedRecords.subList(1, 4),
result1);
+ Assert.assertEquals("Unprocessed count should match record count", 3,
resultDf1.count());
+
+ Row row1 = resultDf1.agg(functions.min("id"), functions.max("id")).head();
+ Assert.assertEquals("min value should match", 2, row1.getInt(0));
+ Assert.assertEquals("max value should match", 4, row1.getInt(1));
// test (2nd snapshot, 3rd snapshot] incremental scan.
- Dataset<Row> resultDf =
+ Dataset<Row> resultDf2 =
Review Comment:
incrementalResult (again could just be two test cases, not picky about that
or naming here but we should choose one)
--
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]
