pvary commented on code in PR #15514:
URL: https://github.com/apache/iceberg/pull/15514#discussion_r2895393592
##########
spark/v4.1/spark/src/test/java/org/apache/iceberg/spark/source/TestSparkReaderDeletes.java:
##########
@@ -738,6 +741,78 @@ public void testEqualityDeleteWithSchemaEvolution() throws
IOException {
assertThat(actual).hasSize(expectedRecordCount);
}
+ /**
+ * Covers a bug where equality deletes columns are appended to the required
schema in a different
+ * order than the table schema, which can cause different deleteSchema
orderings, poisoning the
+ * cache.
+ */
+ @TestTemplate
+ public void testEqualityDeletesAppliedWithCachedFieldReordering() throws
IOException {
+ Schema eqDeleteTestSchema =
+ new Schema(
+ Types.NestedField.optional(1, "id", Types.IntegerType.get()),
+ Types.NestedField.optional(2, "a", Types.IntegerType.get()),
+ Types.NestedField.optional(3, "b", Types.IntegerType.get()));
+ PartitionSpec spec =
PartitionSpec.builderFor(eqDeleteTestSchema).bucket("id", 1).build();
+
+ Table eqTestTable = createTable(EQ_CACHE_TABLE, eqDeleteTestSchema, spec);
+
+ GenericRecord record = GenericRecord.create(eqDeleteTestSchema);
+ List<Record> data = Lists.newArrayList();
+ for (int i = 0; i < 10; i++) {
+ data.add(record.copy("id", i, "a", i * 10, "b", i * 100));
+ }
+
+ DataFile dataFile =
+ FileHelpers.writeDataFile(
+ eqTestTable,
+ Files.localOutput(File.createTempFile("junit", null,
temp.toFile())),
+ TestHelpers.Row.of(0),
+ data);
+ eqTestTable.newAppend().appendFile(dataFile).commit();
+
+ Schema deleteSchema =
+ new Schema(
+ Types.NestedField.optional(3, "b", Types.IntegerType.get()),
+ Types.NestedField.optional(2, "a", Types.IntegerType.get()));
+
+ Record eqDel = GenericRecord.create(deleteSchema);
+ List<Record> deletes =
+ Lists.newArrayList(
+ eqDel.copy("b", 0, "a", 0),
+ eqDel.copy("b", 100, "a", 10),
+ eqDel.copy("b", 200, "a", 20));
+
+ DeleteFile eqFile =
+ FileHelpers.writeDeleteFile(
+ eqTestTable,
+ Files.localOutput(File.createTempFile("junit", null,
temp.toFile())),
+ TestHelpers.Row.of(0),
+ deletes,
+ deleteSchema);
+ eqTestTable.newRowDelta().addDeletes(eqFile).commit();
+
+ String tableRef = TableIdentifier.of("default", EQ_CACHE_TABLE).toString();
+ int expectedRows = 7;
Review Comment:
nit: maybe a little bit easier to understand?
```suggestion
int expectedRows = data.size() - delete.size();
```
--
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]
