mxm commented on code in PR #14148:
URL: https://github.com/apache/iceberg/pull/14148#discussion_r2367134668
##########
flink/v2.0/flink/src/test/java/org/apache/iceberg/flink/data/TestFlinkParquetReader.java:
##########
@@ -216,29 +223,32 @@ public void testTwoLevelList() throws IOException {
private void writeAndValidate(
Iterable<Record> iterable, Schema writeSchema, Schema expectedSchema)
throws IOException {
- File testFile = File.createTempFile("junit", null, temp.toFile());
- assertThat(testFile.delete()).isTrue();
+ OutputFile output = new InMemoryOutputFile();
try (FileAppender<Record> writer =
- Parquet.write(Files.localOutput(testFile))
Review Comment:
What's the reason for moving from local file to in memory?
##########
flink/v2.0/flink/src/main/java/org/apache/iceberg/flink/data/FlinkParquetReaders.java:
##########
@@ -102,51 +104,39 @@ public ParquetValueReader<RowData> struct(
if (fieldType.getId() != null) {
int id = fieldType.getId().intValue();
readersById.put(id, ParquetValueReaders.option(fieldType, fieldD,
fieldReaders.get(i)));
- typesById.put(id, fieldType);
- if (idToConstant.containsKey(id)) {
- maxDefinitionLevelsById.put(id, fieldD);
- }
}
}
}
- List<Types.NestedField> expectedFields =
- expected != null ? expected.fields() : ImmutableList.of();
+ int constantDefinitionLevel = type.getMaxDefinitionLevel(currentPath());
+ List<Types.NestedField> expectedFields = expected.fields();
List<ParquetValueReader<?>> reorderedFields =
Lists.newArrayListWithExpectedSize(expectedFields.size());
- // Defaulting to parent max definition level
- int defaultMaxDefinitionLevel =
type.getMaxDefinitionLevel(currentPath());
for (Types.NestedField field : expectedFields) {
int id = field.fieldId();
- ParquetValueReader<?> reader = readersById.get(id);
- if (idToConstant.containsKey(id)) {
- // containsKey is used because the constant may be null
- int fieldMaxDefinitionLevel =
- maxDefinitionLevelsById.getOrDefault(id,
defaultMaxDefinitionLevel);
- reorderedFields.add(
- ParquetValueReaders.constant(idToConstant.get(id),
fieldMaxDefinitionLevel));
- } else if (id == MetadataColumns.ROW_POSITION.fieldId()) {
- reorderedFields.add(ParquetValueReaders.position());
- } else if (id == MetadataColumns.IS_DELETED.fieldId()) {
- reorderedFields.add(ParquetValueReaders.constant(false));
- } else if (reader != null) {
- reorderedFields.add(reader);
- } else if (field.initialDefault() != null) {
- reorderedFields.add(
- ParquetValueReaders.constant(
- RowDataUtil.convertConstant(field.type(),
field.initialDefault()),
- maxDefinitionLevelsById.getOrDefault(id,
defaultMaxDefinitionLevel)));
- } else if (field.isOptional()) {
- reorderedFields.add(ParquetValueReaders.nulls());
- } else {
- throw new IllegalArgumentException(
- String.format("Missing required field: %s", field.name()));
- }
+ ParquetValueReader<?> reader =
+ ParquetValueReaders.replaceWithMetadataReader(
+ id, readersById.get(id), idToConstant,
constantDefinitionLevel);
+ reorderedFields.add(defaultReader(field, reader,
constantDefinitionLevel));
Review Comment:
Just curious, how did you decide to make this refactoring? You consolidate
several branches of the if statement.
--
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: issues-unsubscr...@iceberg.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org
For additional commands, e-mail: issues-h...@iceberg.apache.org
