joyhaldar commented on code in PR #16638:
URL: https://github.com/apache/iceberg/pull/16638#discussion_r3353243414
##########
data/src/test/java/org/apache/iceberg/data/BaseFormatModelTests.java:
##########
@@ -696,49 +733,390 @@ void testReaderBuilderReuseContainers(FileFormat
fileFormat) throws IOException
}
@ParameterizedTest
- @FieldSource("FILE_FORMATS")
- void testReaderSchemaEvolutionNewColumnWithDefault(FileFormat fileFormat)
throws IOException {
+ @FieldSource("FORMAT_AND_PRIMITIVE_DEFAULTS")
+ void testReaderSchemaEvolutionNewColumnWithDefault(
+ FileFormat fileFormat, Type.PrimitiveType type, Literal<?> defaultValue)
throws IOException {
assumeSupports(fileFormat, FEATURE_READER_DEFAULT);
+
DataGenerator dataGenerator = new DataGenerators.DefaultSchema();
Schema writeSchema = dataGenerator.schema();
List<Record> genericRecords = dataGenerator.generateRecords();
writeGenericRecords(fileFormat, writeSchema, genericRecords);
- String defaultStringValue = "default_value";
- int defaultIntValue = 42;
-
int maxFieldId =
writeSchema.columns().stream().mapToInt(Types.NestedField::fieldId).max().orElse(0);
List<Types.NestedField> evolvedColumns =
Lists.newArrayList(writeSchema.columns());
evolvedColumns.add(
- Types.NestedField.required("col_f")
+ Types.NestedField.optional("col_with_default")
.withId(maxFieldId + 1)
- .ofType(Types.StringType.get())
- .withInitialDefault(Literal.of(defaultStringValue))
- .build());
- evolvedColumns.add(
- Types.NestedField.optional("col_g")
- .withId(maxFieldId + 2)
- .ofType(Types.IntegerType.get())
- .withInitialDefault(Literal.of(defaultIntValue))
+ .ofType(type)
+ .withInitialDefault(defaultValue)
.build());
Schema evolvedSchema = new Schema(evolvedColumns);
- readAndAssertGenericRecords(
+ readAndAssertGenericRecords(fileFormat, evolvedSchema, genericRecords);
+ }
+
+ @ParameterizedTest
+ @FieldSource("FILE_FORMATS")
+ void testDefaultValues(FileFormat fileFormat) throws IOException {
+ assumeSupports(fileFormat, FEATURE_READER_DEFAULT);
+
+ Schema writeSchema =
+ new Schema(
+ Types.NestedField.required(1, "id", Types.LongType.get()),
+ Types.NestedField.optional("data")
+ .withId(2)
+ .ofType(Types.StringType.get())
+ .withInitialDefault(Literal.of("wrong!"))
+ .withDoc("Should not produce default value")
+ .build());
+
+ List<Record> genericRecords = RandomGenericData.generate(writeSchema, 10,
1L);
+ writeGenericRecords(fileFormat, writeSchema, genericRecords);
+
+ Schema expectedSchema =
+ new Schema(
+ Types.NestedField.required(1, "id", Types.LongType.get()),
+ Types.NestedField.optional("data")
+ .withId(2)
+ .ofType(Types.StringType.get())
+ .withInitialDefault(Literal.of("wrong!"))
+ .build(),
+ Types.NestedField.required("missing_str")
+ .withId(6)
+ .ofType(Types.StringType.get())
+ .withInitialDefault(Literal.of("orange"))
+ .build(),
+ Types.NestedField.optional("missing_int")
+ .withId(7)
+ .ofType(Types.IntegerType.get())
+ .withInitialDefault(Literal.of(34))
+ .build());
+
+ readAndAssertEngineRecords(
+ fileFormat,
+ expectedSchema,
+ genericRecords,
+ record -> {
+ Record expected = GenericRecord.create(expectedSchema);
+ expected.setField("id", record.getField("id"));
+ expected.setField("data", record.getField("data"));
+ expected.setField("missing_str", "orange");
+ expected.setField("missing_int", 34);
+ return expected;
+ });
+ }
+
+ @ParameterizedTest
+ @FieldSource("FILE_FORMATS")
+ void testNullDefaultValue(FileFormat fileFormat) throws IOException {
+ assumeSupports(fileFormat, FEATURE_READER_DEFAULT);
+
+ Schema writeSchema =
+ new Schema(
+ Types.NestedField.required(1, "id", Types.LongType.get()),
+ Types.NestedField.optional("data")
+ .withId(2)
+ .ofType(Types.StringType.get())
+ .withInitialDefault(Literal.of("wrong!"))
+ .withDoc("Should not produce default value")
+ .build());
+
+ List<Record> genericRecords = RandomGenericData.generate(writeSchema, 10,
1L);
+ writeGenericRecords(fileFormat, writeSchema, genericRecords);
+
+ Schema expectedSchema =
+ new Schema(
+ Types.NestedField.required(1, "id", Types.LongType.get()),
+ Types.NestedField.optional("data")
+ .withId(2)
+ .ofType(Types.StringType.get())
+ .withInitialDefault(Literal.of("wrong!"))
+ .build(),
+ Types.NestedField.optional("missing_date")
+ .withId(3)
+ .ofType(Types.DateType.get())
+ .build());
+
+ readAndAssertEngineRecords(
+ fileFormat,
+ expectedSchema,
+ genericRecords,
+ record -> {
+ Record expected = GenericRecord.create(expectedSchema);
+ expected.setField("id", record.getField("id"));
+ expected.setField("data", record.getField("data"));
+ expected.setField("missing_date", null);
+ return expected;
+ });
+ }
+
+ @ParameterizedTest
+ @FieldSource("FILE_FORMATS")
+ void testNestedDefaultValue(FileFormat fileFormat) throws IOException {
+ assumeSupports(fileFormat, FEATURE_READER_DEFAULT);
+
+ Schema writeSchema =
+ new Schema(
+ Types.NestedField.required(1, "id", Types.LongType.get()),
+ Types.NestedField.optional("data")
+ .withId(2)
+ .ofType(Types.StringType.get())
+ .withInitialDefault(Literal.of("wrong!"))
+ .withDoc("Should not produce default value")
+ .build(),
+ Types.NestedField.optional("nested")
+ .withId(3)
+ .ofType(
+ Types.StructType.of(
+ Types.NestedField.required(4, "inner",
Types.StringType.get())))
+ .withDoc("Used to test nested field defaults")
+ .build());
+
+ List<Record> genericRecords = RandomGenericData.generate(writeSchema, 10,
1L);
+ writeGenericRecords(fileFormat, writeSchema, genericRecords);
+
+ Schema expectedSchema =
+ new Schema(
+ Types.NestedField.required(1, "id", Types.LongType.get()),
+ Types.NestedField.optional("data")
+ .withId(2)
+ .ofType(Types.StringType.get())
+ .withInitialDefault(Literal.of("wrong!"))
+ .build(),
+ Types.NestedField.optional("nested")
+ .withId(3)
+ .ofType(
+ Types.StructType.of(
+ Types.NestedField.required(4, "inner",
Types.StringType.get()),
+ Types.NestedField.optional("missing_inner_float")
+ .withId(5)
+ .ofType(Types.FloatType.get())
+ .withInitialDefault(Literal.of(-0.0F))
+ .build()))
+ .withDoc("Used to test nested field defaults")
+ .build());
+
+ readAndAssertEngineRecords(
+ fileFormat,
+ expectedSchema,
+ genericRecords,
+ record -> {
+ Record expected = copy(record, writeSchema, expectedSchema);
+
+ Record writtenNested = (Record) record.getField("nested");
+ if (writtenNested != null) {
+ Record expectedNested =
+
GenericRecord.create(expectedSchema.findField("nested").type().asStructType());
+ expectedNested.setField("inner", writtenNested.getField("inner"));
+ expectedNested.setField("missing_inner_float", -0.0F);
+ expected.setField("nested", expectedNested);
+ }
+ return expected;
+ });
+ }
+
+ @ParameterizedTest
+ @FieldSource("FILE_FORMATS")
+ void testMapNestedDefaultValue(FileFormat fileFormat) throws IOException {
+ assumeSupports(fileFormat, FEATURE_READER_DEFAULT);
+
+ Schema writeSchema =
+ new Schema(
+ Types.NestedField.required(1, "id", Types.LongType.get()),
+ Types.NestedField.optional("data")
+ .withId(2)
+ .ofType(Types.StringType.get())
+ .withInitialDefault(Literal.of("wrong!"))
+ .withDoc("Should not produce default value")
+ .build(),
+ Types.NestedField.optional("nested_map")
+ .withId(3)
+ .ofType(
+ Types.MapType.ofOptional(
+ 4,
+ 5,
+ Types.StringType.get(),
+ Types.StructType.of(
+ Types.NestedField.required(6, "value_str",
Types.StringType.get()))))
+ .withDoc("Used to test nested map value field defaults")
+ .build());
+
+ List<Record> genericRecords = RandomGenericData.generate(writeSchema, 10,
1L);
+ writeGenericRecords(fileFormat, writeSchema, genericRecords);
+
+ Schema expectedSchema =
+ new Schema(
+ Types.NestedField.required(1, "id", Types.LongType.get()),
+ Types.NestedField.optional("data")
+ .withId(2)
+ .ofType(Types.StringType.get())
+ .withInitialDefault(Literal.of("wrong!"))
+ .build(),
+ Types.NestedField.optional("nested_map")
+ .withId(3)
+ .ofType(
+ Types.MapType.ofOptional(
+ 4,
+ 5,
+ Types.StringType.get(),
+ Types.StructType.of(
+ Types.NestedField.required(6, "value_str",
Types.StringType.get()),
+ Types.NestedField.optional("value_int")
+ .withId(7)
+ .ofType(Types.IntegerType.get())
+ .withInitialDefault(Literal.of(34))
+ .build())))
+ .withDoc("Used to test nested field defaults")
+ .build());
+
+ readAndAssertEngineRecords(
fileFormat,
- evolvedSchema,
+ expectedSchema,
genericRecords,
record -> {
- Record expected = copy(record, writeSchema, evolvedSchema);
- expected.setField("col_f", defaultStringValue);
- expected.setField("col_g", defaultIntValue);
+ Record expected = copy(record, writeSchema, expectedSchema);
+
+ @SuppressWarnings("unchecked")
+ Map<Object, Record> writtenMap = (Map<Object, Record>)
expected.getField("nested_map");
+ if (writtenMap != null) {
+ Types.StructType valueType =
+ expectedSchema
+ .findField("nested_map")
+ .type()
+ .asMapType()
+ .valueType()
+ .asStructType();
+ Map<Object, Record> rebuilt = Maps.newLinkedHashMap();
+ writtenMap.forEach(
+ (key, val) ->
+ rebuilt.put(
+ key,
+ val == null
+ ? null
+ : GenericRecord.create(valueType)
+ .copy("value_str", val.getField("value_str"),
"value_int", 34)));
+ expected.setField("nested_map", rebuilt);
+ }
return expected;
});
}
+ @ParameterizedTest
+ @FieldSource("FILE_FORMATS")
+ void testListNestedDefaultValue(FileFormat fileFormat) throws IOException {
+ assumeSupports(fileFormat, FEATURE_READER_DEFAULT);
+
+ Schema writeSchema =
+ new Schema(
+ Types.NestedField.required(1, "id", Types.LongType.get()),
+ Types.NestedField.optional("data")
+ .withId(2)
+ .ofType(Types.StringType.get())
+ .withInitialDefault(Literal.of("wrong!"))
+ .withDoc("Should not produce default value")
+ .build(),
+ Types.NestedField.optional("nested_list")
+ .withId(3)
+ .ofType(
+ Types.ListType.ofOptional(
+ 4,
+ Types.StructType.of(
+ Types.NestedField.required(5, "element_str",
Types.StringType.get()))))
+ .withDoc("Used to test nested field defaults")
+ .build());
+
+ List<Record> genericRecords = RandomGenericData.generate(writeSchema, 10,
1L);
+ writeGenericRecords(fileFormat, writeSchema, genericRecords);
+
+ Schema expectedSchema =
+ new Schema(
+ Types.NestedField.required(1, "id", Types.LongType.get()),
+ Types.NestedField.optional("data")
+ .withId(2)
+ .ofType(Types.StringType.get())
+ .withInitialDefault(Literal.of("wrong!"))
+ .build(),
+ Types.NestedField.optional("nested_list")
+ .withId(3)
+ .ofType(
+ Types.ListType.ofOptional(
+ 4,
+ Types.StructType.of(
+ Types.NestedField.required(5, "element_str",
Types.StringType.get()),
+ Types.NestedField.optional("element_int")
+ .withId(7)
+ .ofType(Types.IntegerType.get())
+ .withInitialDefault(Literal.of(34))
+ .build())))
+ .withDoc("Used to test nested field defaults")
+ .build());
+
+ readAndAssertEngineRecords(
+ fileFormat,
+ expectedSchema,
+ genericRecords,
+ record -> {
+ Record expected = copy(record, writeSchema, expectedSchema);
+
+ @SuppressWarnings("unchecked")
+ List<Record> writtenList = (List<Record>)
expected.getField("nested_list");
+ if (writtenList != null) {
+ Types.StructType elementType =
+ expectedSchema
+ .findField("nested_list")
+ .type()
+ .asListType()
+ .elementType()
+ .asStructType();
+ List<Record> rebuilt =
+ writtenList.stream()
+ .map(
+ el ->
+ el == null
+ ? null
+ : GenericRecord.create(elementType)
+ .copy(
+ "element_str",
+ el.getField("element_str"),
+ "element_int",
+ 34))
+ .collect(Collectors.toList());
+ expected.setField("nested_list", rebuilt);
+ }
+ return expected;
Review Comment:
Done.
--
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]
