wgtmac commented on code in PR #55351:
URL: https://github.com/apache/arrow/pull/55351#discussion_r4438297016
##########
cpp/src/parquet/arrow/arrow_reader_writer_test.cc:
##########
@@ -3453,6 +3453,22 @@ TEST(ArrowReadWrite, ListWithNoValues) {
CheckSimpleRoundtrip(table, 2, props_store_schema);
}
+TEST(ArrowReadWrite, NestedDictionaryMultipleRowGroups) {
+ // GH-45087: reading several row groups at once yields one chunk per row
group
+ // for a nested dictionary leaf, and the chunks have different dictionaries.
+ using ::arrow::field;
+
+ auto dict_type = ::arrow::dictionary(::arrow::int32(), ::arrow::utf8());
+ for (const auto& type : {list(dict_type), ::arrow::large_list(dict_type)}) {
+ ARROW_SCOPED_TRACE("type = ", type->ToString());
+ auto array =
+ ::arrow::ArrayFromJSON(type, R"([["a"], ["b", "a"], ["c", "a"],
["b"]])");
+ auto table = ::arrow::Table::Make(::arrow::schema({field("root", type)}),
{array});
Review Comment:
Good point! That sounds good to me.
--
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]
