nastra commented on code in PR #13562:
URL: https://github.com/apache/iceberg/pull/13562#discussion_r2251192722
##########
arrow/src/main/java/org/apache/iceberg/arrow/vectorized/VectorizedArrowReader.java:
##########
@@ -508,6 +440,168 @@ public static VectorizedReader<?>
replaceWithMetadataReader(
return reader;
}
+ private static final class LogicalTypeVisitorResult {
+ private final FieldVector vec;
+ private final Integer typeWidth;
+ private final ReadType readType;
+
+ LogicalTypeVisitorResult(FieldVector vec, ReadType readType, Integer
typeWidth) {
+ this.vec = vec;
+ this.typeWidth = typeWidth;
+ this.readType = readType;
+ }
+ }
+
+ private final class LogicalTypeVisitor
+ implements
LogicalTypeAnnotation.LogicalTypeAnnotationVisitor<LogicalTypeVisitorResult> {
+ private final Field arrowField;
+ private final PrimitiveType primitive;
+
+ LogicalTypeVisitor(Field arrowField, PrimitiveType primitive) {
+ this.arrowField = arrowField;
+ this.primitive = primitive;
+ }
+
+ @Override
+ public Optional<LogicalTypeVisitorResult> visit(
+ LogicalTypeAnnotation.StringLogicalTypeAnnotation stringLogicalType) {
+ return visitEnumJsonBsonString();
+ }
+
+ @Override
+ public Optional<LogicalTypeVisitorResult> visit(
+ LogicalTypeAnnotation.EnumLogicalTypeAnnotation enumLogicalType) {
+ return visitEnumJsonBsonString();
+ }
+
+ @Override
+ public Optional<LogicalTypeVisitorResult> visit(
+ LogicalTypeAnnotation.UUIDLogicalTypeAnnotation uuidLogicalType) {
+ FieldVector vector = arrowField.createVector(rootAlloc);
+ ((FixedSizeBinaryVector) vector).allocateNew(batchSize);
+ return Optional.of(
+ new LogicalTypeVisitorResult(vector, ReadType.UUID,
primitive.getTypeLength()));
+ }
+
+ @Override
+ public Optional<LogicalTypeVisitorResult> visit(
+ LogicalTypeAnnotation.DecimalLogicalTypeAnnotation decimalLogicalType)
{
+ FieldVector vector = arrowField.createVector(rootAlloc);
+ switch (primitive.getPrimitiveTypeName()) {
+ case BINARY:
+ case FIXED_LEN_BYTE_ARRAY:
+ ((FixedSizeBinaryVector) vector).allocateNew(batchSize);
+ return Optional.of(
+ new LogicalTypeVisitorResult(
+ vector, ReadType.FIXED_LENGTH_DECIMAL,
primitive.getTypeLength()));
+ case INT64:
+ ((BigIntVector) vector).allocateNew(batchSize);
+ return Optional.of(
+ new LogicalTypeVisitorResult(
+ vector, ReadType.LONG_BACKED_DECIMAL, (int)
BigIntVector.TYPE_WIDTH));
+ case INT32:
+ ((IntVector) vector).allocateNew(batchSize);
+ return Optional.of(
+ new LogicalTypeVisitorResult(
+ vector, ReadType.INT_BACKED_DECIMAL, (int)
IntVector.TYPE_WIDTH));
+ default:
+ throw new UnsupportedOperationException(
+ "Unsupported base type for decimal: " +
primitive.getPrimitiveTypeName());
+ }
+ }
+
+ @Override
+ public Optional<LogicalTypeVisitorResult> visit(
+ LogicalTypeAnnotation.DateLogicalTypeAnnotation dateLogicalType) {
+ FieldVector vector = arrowField.createVector(rootAlloc);
+ ((DateDayVector) vector).allocateNew(batchSize);
+ return Optional.of(
+ new LogicalTypeVisitorResult(vector, ReadType.INT, (int)
IntVector.TYPE_WIDTH));
+ }
+
+ @Override
+ public Optional<LogicalTypeVisitorResult> visit(
+ LogicalTypeAnnotation.TimeLogicalTypeAnnotation timeLogicalType) {
+ FieldVector vector = arrowField.createVector(rootAlloc);
+ ((TimeMicroVector) vector).allocateNew(batchSize);
+ return Optional.of(
+ new LogicalTypeVisitorResult(vector, ReadType.LONG, (int)
TimeMicroVector.TYPE_WIDTH));
+ }
+
+ @Override
+ public Optional<LogicalTypeVisitorResult> visit(
+ LogicalTypeAnnotation.TimestampLogicalTypeAnnotation
timestampLogicalType) {
+ FieldVector vector = arrowField.createVector(rootAlloc);
+ switch (timestampLogicalType.getUnit()) {
+ case MILLIS:
+ ((BigIntVector) vector).allocateNew(batchSize);
+ return Optional.of(
+ new LogicalTypeVisitorResult(
+ vector, ReadType.TIMESTAMP_MILLIS, (int)
BigIntVector.TYPE_WIDTH));
+ case MICROS:
+ if (((Types.TimestampType) icebergField.type()).shouldAdjustToUTC())
{
+ ((TimeStampMicroTZVector) vector).allocateNew(batchSize);
+ } else {
+ ((TimeStampMicroVector) vector).allocateNew(batchSize);
+ }
+
+ return Optional.of(
+ new LogicalTypeVisitorResult(vector, ReadType.LONG, (int)
BigIntVector.TYPE_WIDTH));
+ case NANOS:
+ if (((Types.TimestampNanoType)
icebergField.type()).shouldAdjustToUTC()) {
+ ((TimeStampNanoTZVector) vector).allocateNew(batchSize);
+ } else {
+ ((TimeStampNanoVector) vector).allocateNew(batchSize);
+ }
+
+ return Optional.of(
+ new LogicalTypeVisitorResult(vector, ReadType.LONG, (int)
BigIntVector.TYPE_WIDTH));
+ }
+
+ return Optional.empty();
+ }
+
+ @Override
+ public Optional<LogicalTypeVisitorResult> visit(
+ LogicalTypeAnnotation.IntLogicalTypeAnnotation intLogicalType) {
+ FieldVector vector = arrowField.createVector(rootAlloc);
+
+ if (intLogicalType.getBitWidth() == 8
Review Comment:
maybe extract `intLogicalType.getBitWidth()` into a var so that the code
gets shorter
--
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]
