bryanck commented on code in PR #5137:
URL: https://github.com/apache/iceberg/pull/5137#discussion_r907663011
##########
arrow/src/main/java/org/apache/iceberg/arrow/vectorized/GenericArrowVectorAccessorFactory.java:
##########
@@ -372,22 +365,26 @@ public final Utf8StringT getUTF8String(int rowId) {
private static class DictionaryStringAccessor<DecimalT, Utf8StringT, ArrayT,
ChildVectorT extends AutoCloseable>
extends ArrowVectorAccessor<DecimalT, Utf8StringT, ArrayT,
ChildVectorT> {
- private final Utf8StringT[] decodedDictionary;
+ private final Dictionary dictionary;
+ private final StringFactory<Utf8StringT> stringFactory;
private final IntVector offsetVector;
+ private final Utf8StringT[] cache;
DictionaryStringAccessor(IntVector vector, Dictionary dictionary,
StringFactory<Utf8StringT> stringFactory) {
super(vector);
this.offsetVector = vector;
- this.decodedDictionary = IntStream.rangeClosed(0, dictionary.getMaxId())
- .mapToObj(dictionary::decodeToBinary)
- .map(binary -> stringFactory.ofBytes(binary.getBytes()))
- .toArray(genericArray(stringFactory.getGenericClass()));
+ this.dictionary = dictionary;
+ this.stringFactory = stringFactory;
+ this.cache = genericArray(stringFactory.getGenericClass(),
dictionary.getMaxId() + 1);
Review Comment:
To support a 0-based index of getMaxId(), you need a size that is one bigger
--
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]
