Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Flink 1.20: Support default values in Parquet reader #11839

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

Flink 1.20: Support default values in Parquet reader #11839

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 16 additions & 8 deletions flink/v1.20/flink/src/main/java/org/apache/iceberg/flink/data/FlinkParquetReaders.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,6 +89,7 @@ public ParquetValueReader<RowData> message(
}

@Override
@SuppressWarnings("checkstyle:CyclomaticComplexity")
public ParquetValueReader<RowData> struct(
Types.StructType expected, GroupType struct, List<ParquetValueReader<?>> fieldReaders) {
// match the expected struct's order
Expand Down Expand Up @@ -120,6 +121,7 @@ public ParquetValueReader<RowData> struct(
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 =
Expand All @@ -133,15 +135,21 @@ public ParquetValueReader<RowData> struct(
} else if (id == MetadataColumns.IS_DELETED.fieldId()) {
reorderedFields.add(ParquetValueReaders.constant(false));
types.add(null);
} else if (reader != null) {
reorderedFields.add(reader);
types.add(typesById.get(id));
} else if (field.initialDefault() != null) {
reorderedFields.add(
ParquetValueReaders.constant(
RowDataUtil.convertConstant(field.type(), field.initialDefault()),
maxDefinitionLevelsById.getOrDefault(id, defaultMaxDefinitionLevel)));
types.add(typesById.get(id));
} else if (field.isOptional()) {
reorderedFields.add(ParquetValueReaders.nulls());
types.add(null);
} else {
ParquetValueReader<?> reader = readersById.get(id);
if (reader != null) {
reorderedFields.add(reader);
types.add(typesById.get(id));
} else {
reorderedFields.add(ParquetValueReaders.nulls());
types.add(null);
}
throw new IllegalArgumentException(
String.format("Missing required field: %s", field.name()));
}
}

Expand Down
23 changes: 23 additions & 0 deletions flink/v1.20/flink/src/main/java/org/apache/iceberg/flink/data/RowDataUtil.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@

import java.math.BigDecimal;
import java.nio.ByteBuffer;
import java.util.List;
import org.apache.avro.generic.GenericData;
import org.apache.avro.util.Utf8;
import org.apache.flink.api.common.typeutils.TypeSerializer;
Expand All @@ -30,6 +31,7 @@
import org.apache.flink.table.data.TimestampData;
import org.apache.flink.table.runtime.typeutils.RowDataSerializer;
import org.apache.flink.table.types.logical.RowType;
import org.apache.iceberg.StructLike;
import org.apache.iceberg.types.Type;
import org.apache.iceberg.types.Types;
import org.apache.iceberg.util.ByteBuffers;
Expand Down Expand Up @@ -63,6 +65,27 @@ public static Object convertConstant(Type type, Object value) {
return ByteBuffers.toByteArray((ByteBuffer) value);
case BINARY: // byte[]
return ByteBuffers.toByteArray((ByteBuffer) value);
case STRUCT: // struct
Types.StructType structType = (Types.StructType) type;

if (structType.fields().isEmpty()) {
return new GenericRowData(0);
}

List<Types.NestedField> fields = structType.fields();
Object[] values = new Object[fields.size()];
StructLike struct = (StructLike) value;

GenericRowData data = new GenericRowData(fields.size());
for (int index = 0; index < fields.size(); index++) {
Types.NestedField field = fields.get(index);
Type fieldType = field.type();
values[index] =
convertConstant(fieldType, struct.get(index, fieldType.typeId().javaClass()));
data.setField(index, values[index]);
}

return data;
case TIME: // int mills instead of long
return (int) ((Long) value / 1000);
case TIMESTAMP: // TimestampData
Expand Down