amogh-jahagirdar commented on code in PR #15268:
URL: https://github.com/apache/iceberg/pull/15268#discussion_r2785137434
##########
spark/v4.1/spark/src/main/java/org/apache/iceberg/spark/source/BaseReader.java:
##########
@@ -252,5 +251,40 @@ protected <V> V getOrLoad(String key, Supplier<V>
valueSupplier, long valueSize)
return cache.getOrLoad(table().name(), key, valueSupplier, valueSize);
}
}
+
+ // field lookup for serializable tables that assumes fetching historic
schemas is expensive
+ private static class FieldLookup implements Function<Integer,
Types.NestedField> {
+ private final Table table;
+
+ private volatile Map<Integer, Types.NestedField> historicSchemaFields;
+
+ private FieldLookup(Table table) {
+ this.table = table;
+ }
+
+ @Override
+ public Types.NestedField apply(Integer id) {
+ Types.NestedField field = table.schema().findField(id);
+ return field != null ? field : historicSchemaFields().get(id);
+ }
+
+ private Map<Integer, Types.NestedField> historicSchemaFields() {
+ if (historicSchemaFields == null) {
+ synchronized (this) {
+ if (historicSchemaFields == null) {
+ this.historicSchemaFields =
Schema.indexFields(historicSchemas(table));
+ }
+ }
+ }
+
+ return historicSchemaFields;
+ }
+
+ private static Collection<Schema> historicSchemas(Table table) {
+ return table.schemas().values().stream()
+ .filter(schema -> schema.schemaId() != table.schema().schemaId())
+ .collect(Collectors.toList());
+ }
+ }
Review Comment:
To add, I would just test our remote planning with this change, make sure
things behave as expected. I was planning on doing that for 1.11 release voting
anyways.
--
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]
