openinx commented on a change in pull request #3248:
URL: https://github.com/apache/iceberg/pull/3248#discussion_r725870777
##########
File path: spark/src/main/java/org/apache/iceberg/spark/data/SparkOrcWriter.java
##########
@@ -126,30 +127,106 @@ public SparkOrcValueWriter primitive(Type.PrimitiveType
iPrimitive, TypeDescript
}
}
- private static class StructWriter implements SparkOrcValueWriter {
- private final List<SparkOrcValueWriter> writers;
+ private static class InternalRowWriter extends
GenericOrcWriter.StructWriter<InternalRow> {
+ private final List<FieldGetter<?>> fieldGetters;
- StructWriter(List<SparkOrcValueWriter> writers) {
- this.writers = writers;
- }
+ InternalRowWriter(List<OrcValueWriter<?>> writers, List<TypeDescription>
orcTypes) {
+ super(writers);
+ this.fieldGetters = Lists.newArrayListWithExpectedSize(orcTypes.size());
- List<SparkOrcValueWriter> writers() {
- return writers;
+ for (int i = 0; i < orcTypes.size(); i++) {
+ fieldGetters.add(createFieldGetter(orcTypes.get(i)));
+ }
}
@Override
- public void nonNullWrite(int rowId, int column, SpecializedGetters data,
ColumnVector output) {
- InternalRow value = data.getStruct(column, writers.size());
- StructColumnVector cv = (StructColumnVector) output;
- for (int c = 0; c < writers.size(); ++c) {
- writers.get(c).write(rowId, c, value, cv.fields[c]);
- }
+ public Class<?> getJavaClass() {
+ return InternalRow.class;
}
@Override
public Stream<FieldMetrics<?>> metrics() {
- return writers.stream().flatMap(SparkOrcValueWriter::metrics);
+ return writers().stream().flatMap(OrcValueWriter::metrics);
+ }
+
+ @Override
+ protected Object get(InternalRow struct, int index) {
+ return fieldGetters.get(index).getFieldOrNull(struct, index);
+ }
+ }
+
+ static FieldGetter<?> createFieldGetter(TypeDescription fieldType) {
+ final FieldGetter<?> fieldGetter;
+ switch (fieldType.getCategory()) {
+ case BOOLEAN:
+ fieldGetter = (row, ordinal) -> row.getBoolean(ordinal);
+ break;
+ case BYTE:
+ fieldGetter = (row, ordinal) -> row.getByte(ordinal);
+ break;
+ case SHORT:
+ fieldGetter = (row, ordinal) -> row.getShort(ordinal);
+ break;
+ case DATE:
+ case INT:
+ fieldGetter = (row, ordinal) -> row.getInt(ordinal);
+ break;
+ case LONG:
+ case TIMESTAMP:
+ case TIMESTAMP_INSTANT:
+ fieldGetter = (row, ordinal) -> row.getLong(ordinal);
+ break;
+ case FLOAT:
+ fieldGetter = (row, ordinal) -> row.getFloat(ordinal);
+ break;
+ case DOUBLE:
+ fieldGetter = (row, ordinal) -> row.getDouble(ordinal);
+ break;
+ case BINARY:
+ fieldGetter = (row, ordinal) -> row.getBinary(ordinal);
+ // getBinary always makes a copy, so we don't need to worry about it
+ // being changed behind our back.
+ break;
+ case DECIMAL:
+ fieldGetter = (row, ordinal) ->
+ row.getDecimal(ordinal, fieldType.getPrecision(),
fieldType.getScale());
+ break;
+ case STRING:
+ case CHAR:
+ case VARCHAR:
+ fieldGetter = (row, ordinal) -> row.getUTF8String(ordinal);
+ break;
+ case STRUCT:
+ fieldGetter = (row, ordinal) -> row.getStruct(ordinal,
fieldType.getChildren().size());
+ break;
+ case LIST:
+ fieldGetter = (row, ordinal) -> row.getArray(ordinal);
+ break;
+ case MAP:
+ fieldGetter = (row, ordinal) -> row.getMap(ordinal);
+ break;
+ default:
+ throw new IllegalArgumentException();
Review comment:
A more clear message is necessary for this exception I think.
--
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]
