You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@arrow.apache.org by "pitrou (via GitHub)" <gi...@apache.org> on 2023/06/14 14:47:04 UTC
[GitHub] [arrow] pitrou commented on a diff in pull request #35958: GH-35926: [C++][Parquet] Testing disable ColumnIndex by disable statistics
pitrou commented on code in PR #35958:
URL: https://github.com/apache/arrow/pull/35958#discussion_r1229734947
##########
cpp/src/parquet/arrow/arrow_reader_writer_test.cc:
##########
@@ -5350,6 +5350,70 @@ TEST_F(ParquetPageIndexRoundTripTest, SimpleRoundTrip) {
/*null_counts=*/{1}}));
}
+TEST_F(ParquetPageIndexRoundTripTest, SimpleRoundTripWithStatsDisabled) {
+ auto writer_properties = WriterProperties::Builder()
+ .enable_write_page_index()
+ ->disable_statistics()
+ ->build();
+ auto schema = ::arrow::schema({::arrow::field("c0", ::arrow::int64()),
+ ::arrow::field("c1", ::arrow::utf8()),
+ ::arrow::field("c2", ::arrow::list(::arrow::int64()))});
+ WriteFile(writer_properties, ::arrow::TableFromJSON(schema, {R"([
+ [1, "a", [1] ],
+ [2, "b", [1, 2] ],
+ [3, "c", [null] ],
+ [null, "d", [] ],
+ [5, null, [3, 3, 3]],
+ [6, "f", null ]
+ ])"}));
+
+ ReadPageIndexes(/*expect_num_row_groups=*/1, /*expect_num_pages=*/1);
+ for (auto& column_index : column_indexes_) {
+ // Means page is empty.
Review Comment:
Which page is empty? I don't understand this comment.
##########
cpp/src/parquet/arrow/arrow_reader_writer_test.cc:
##########
@@ -5350,6 +5350,70 @@ TEST_F(ParquetPageIndexRoundTripTest, SimpleRoundTrip) {
/*null_counts=*/{1}}));
}
+TEST_F(ParquetPageIndexRoundTripTest, SimpleRoundTripWithStatsDisabled) {
+ auto writer_properties = WriterProperties::Builder()
+ .enable_write_page_index()
+ ->disable_statistics()
+ ->build();
+ auto schema = ::arrow::schema({::arrow::field("c0", ::arrow::int64()),
+ ::arrow::field("c1", ::arrow::utf8()),
+ ::arrow::field("c2", ::arrow::list(::arrow::int64()))});
+ WriteFile(writer_properties, ::arrow::TableFromJSON(schema, {R"([
+ [1, "a", [1] ],
+ [2, "b", [1, 2] ],
+ [3, "c", [null] ],
+ [null, "d", [] ],
+ [5, null, [3, 3, 3]],
+ [6, "f", null ]
+ ])"}));
+
+ ReadPageIndexes(/*expect_num_row_groups=*/1, /*expect_num_pages=*/1);
+ for (auto& column_index : column_indexes_) {
+ // Means page is empty.
Review Comment:
Why not test against `ColumnIndexObject{}` instead?
--
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: github-unsubscribe@arrow.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org