mapleFU commented on code in PR #35989:
URL: https://github.com/apache/arrow/pull/35989#discussion_r1237393575
##########
cpp/src/parquet/statistics_test.cc:
##########
@@ -377,6 +377,35 @@ class TestStatistics : public PrimitiveTypedTest<TestType>
{
ASSERT_EQ(total->max(), std::max(statistics1->max(), statistics2->max()));
}
+ void TestMergeEmpty() {
+ EncodedStatistics encoded_statistics1;
+ // NOTE: currently, has_null_count_ in Statistics is always true.
+ auto statistics1 = Statistics::Make(this->schema_.Column(0),
&encoded_statistics1,
+ /*num_values=*/1000);
+ auto s1 =
std::dynamic_pointer_cast<TypedStatistics<TestType>>(statistics1);
+
+ EXPECT_FALSE(statistics1->HasMinMax());
+ EXPECT_FALSE(statistics1->HasDistinctCount());
+
+ EncodedStatistics encoded_statistics2;
+ encoded_statistics2.has_distinct_count = true;
+ encoded_statistics2.distinct_count = 500;
+ auto statistics2 = Statistics::Make(this->schema_.Column(0),
&encoded_statistics2,
+ /*num_values=*/1000);
+
+ EXPECT_FALSE(statistics2->HasMinMax());
+ EXPECT_TRUE(statistics2->HasDistinctCount());
+ auto s2 =
std::dynamic_pointer_cast<TypedStatistics<TestType>>(statistics2);
+
+ auto total = MakeStatistics<TestType>(this->schema_.Column(0));
+ total->Merge(*s1);
+ total->Merge(*s2);
+
+ EXPECT_FALSE(total->HasDistinctCount());
+ EXPECT_FALSE(total->HasMinMax());
+ EXPECT_EQ(2000, total->num_values());
Review Comment:
Updated
--
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]
