rdblue commented on a change in pull request #2293:
URL: https://github.com/apache/iceberg/pull/2293#discussion_r587735828
##########
File path:
spark/src/test/java/org/apache/iceberg/actions/TestRewriteDataFilesAction.java
##########
@@ -377,4 +378,101 @@ private void writeDF(Dataset<Row> df) {
.mode("append")
.save(tableLocation);
}
+
+ @Test
+ public void testRewriteToOutputPartitionSpec() {
+ PartitionSpec spec = PartitionSpec.builderFor(SCHEMA)
+ .identity("c1")
+ .build();
+ Map<String, String> options = Maps.newHashMap();
+ Table table = TABLES.create(SCHEMA, spec, options, tableLocation);
+
+ table.updateSpec().addField(Expressions.truncate("c2", 2)).commit();
+
+ Assert.assertEquals("Should have 2 partitions specs", 2,
table.specs().size());
+
+ List<ThreeColumnRecord> records1 = Lists.newArrayList(
+ new ThreeColumnRecord(1, "AAAAAAAAAA", "AAAA"),
+ new ThreeColumnRecord(1, "AAAAAAAAAA", "CCCC")
+ );
+ writeRecords(records1);
+
+ List<ThreeColumnRecord> records2 = Lists.newArrayList(
+ new ThreeColumnRecord(1, "BBBBBBBBBB", "BBBB"),
+ new ThreeColumnRecord(1, "BBBBBBBBBB", "DDDD")
+ );
+ writeRecords(records2);
+
+ List<ThreeColumnRecord> records3 = Lists.newArrayList(
+ new ThreeColumnRecord(2, "AAAAAAAAAA", "EEEE"),
+ new ThreeColumnRecord(2, "AAAAAAAAAA", "GGGG")
+ );
+ writeRecords(records3);
+
+ List<ThreeColumnRecord> records4 = Lists.newArrayList(
+ new ThreeColumnRecord(2, "BBBBBBBBBB", "FFFF"),
+ new ThreeColumnRecord(2, "BBBBBBBBBB", "HHHH")
+ );
+ writeRecords(records4);
+
+ table.refresh();
+
+ CloseableIterable<FileScanTask> tasks = table.newScan().planFiles();
+ List<DataFile> dataFiles =
Lists.newArrayList(CloseableIterable.transform(tasks, FileScanTask::file));
+ Assert.assertEquals("Should have 8 data files before rewrite", 8,
dataFiles.size());
+
+ Actions actions = Actions.forTable(table);
+ RewriteDataFilesActionResult result = actions
+ .rewriteDataFiles()
+ .outputSpecId(0)
+ .execute();
+ Assert.assertEquals("Action should rewrite 8 data files", 8,
result.deletedDataFiles().size());
+ Assert.assertEquals("Action should add 2 data file", 2,
result.addedDataFiles().size());
+
+ table.refresh();
+
+ CloseableIterable<FileScanTask> tasks2 = table.newScan().planFiles();
+ List<DataFile> dataFiles2 =
Lists.newArrayList(CloseableIterable.transform(tasks2, FileScanTask::file));
+ Assert.assertEquals("Should have 2 data files after rewrite", 2,
dataFiles2.size());
+
+ // Should still have all the same data
+ List<ThreeColumnRecord> expectedRecords = Lists.newArrayList();
+ expectedRecords.addAll(records1);
+ expectedRecords.addAll(records2);
+ expectedRecords.addAll(records3);
+ expectedRecords.addAll(records4);
+
+ Dataset<Row> resultDF = spark.read().format("iceberg").load(tableLocation);
+ List<ThreeColumnRecord> actualRecords = resultDF.sort("c1", "c2", "c3")
+ .as(Encoders.bean(ThreeColumnRecord.class))
+ .collectAsList();
+
+ Assert.assertEquals("Rows must match", expectedRecords, actualRecords);
+
+ List<ThreeColumnRecord> expectedFilteredRecords =
Lists.newArrayList(records2);
Review comment:
Great, thanks for catching this! I was trying to find some time to look
at it but I'm glad you were able to track it down.
----------------------------------------------------------------
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.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
