Add is_min_exact/is_max_exact

kou · Jul 11, 2024 · b99948d · b99948d
1 parent c2ba4ed
commit b99948d
Show file tree

Hide file tree

Showing 3 changed files with 22 additions and 3 deletions.
diff --git a/cpp/src/arrow/array/statistics.h b/cpp/src/arrow/array/statistics.h
@@ -43,16 +43,23 @@ struct ARROW_EXPORT ArrayStatistics {
   /// \brief The number of distinct values, may not be set
   std::optional<int64_t> distinct_count = std::nullopt;
 
-  /// \brief The current minimum value buffer, may not be set
+  /// \brief The minimum value buffer, may not be set
   std::optional<ElementBufferType> min_buffer = std::nullopt;
 
-  /// \brief The current maximum value buffer, may not be set
+  /// \brief Whether the minimum value is exact or not, may not be set
+  std::optional<bool> is_min_exact = std::nullopt;
+
+  /// \brief The maximum value buffer, may not be set
   std::optional<ElementBufferType> max_buffer = std::nullopt;
 
+  /// \brief Whether the maximum value is exact or not, may not be set
+  std::optional<bool> is_max_exact = std::nullopt;
+
   /// \brief Check two Statistics for equality
   bool Equals(const ArrayStatistics& other) const {
     return null_count == other.null_count && distinct_count == other.distinct_count &&
-           min_buffer == other.min_buffer && max_buffer == other.max_buffer;
+           min_buffer == other.min_buffer && is_min_exact == other.is_min_exact &&
+           max_buffer == other.max_buffer && is_max_exact == other.is_max_exact;
   }
 };
 

diff --git a/cpp/src/parquet/arrow/arrow_statistics_test.cc b/cpp/src/parquet/arrow/arrow_statistics_test.cc
@@ -192,8 +192,12 @@ TEST(TestStatisticsRead, Boolean) {
   ASSERT_EQ(false, statistics->distinct_count.has_value());
   ASSERT_EQ(true, statistics->min().has_value());
   ASSERT_EQ(true, statistics->min().value());
+  ASSERT_EQ(true, statistics->is_min_exact.has_value());
+  ASSERT_EQ(true, statistics->is_min_exact.value());
   ASSERT_EQ(true, statistics->max().has_value());
   ASSERT_EQ(true, statistics->max().value());
+  ASSERT_EQ(true, statistics->is_min_exact.has_value());
+  ASSERT_EQ(true, statistics->is_min_exact.value());
 }
 
 TEST(TestStatisticsRead, Int8) {
@@ -206,8 +210,12 @@ TEST(TestStatisticsRead, Int8) {
   ASSERT_EQ(false, statistics->distinct_count.has_value());
   ASSERT_EQ(true, statistics->min().has_value());
   ASSERT_EQ(-1, statistics->min().value());
+  ASSERT_EQ(true, statistics->is_min_exact.has_value());
+  ASSERT_EQ(true, statistics->is_min_exact.value());
   ASSERT_EQ(true, statistics->max().has_value());
   ASSERT_EQ(1, statistics->max().value());
+  ASSERT_EQ(true, statistics->is_min_exact.has_value());
+  ASSERT_EQ(true, statistics->is_min_exact.value());
 }
 
 }  // namespace parquet::arrow
diff --git a/cpp/src/parquet/arrow/reader_internal.cc b/cpp/src/parquet/arrow/reader_internal.cc
@@ -350,7 +350,9 @@ Status TransferInt(RecordReader* reader,
       auto typed_statistics =
           static_cast<::parquet::TypedStatistics<ParquetType>*>(statistics);
       array_statistics->min_buffer = static_cast<ArrowCType>(typed_statistics->min());
+      array_statistics->is_min_exact = true;
       array_statistics->max_buffer = static_cast<ArrowCType>(typed_statistics->max());
+      array_statistics->is_max_exact = true;
     }
   }
   auto array = std::make_shared<ArrayType<ArrowType>>(std::move(array_data));
@@ -412,7 +414,9 @@ Status TransferBool(RecordReader* reader,
     if (statistics->HasMinMax()) {
       auto bool_statistics = static_cast<::parquet::BoolStatistics*>(statistics);
       array_statistics->min_buffer = bool_statistics->min();
+      array_statistics->is_min_exact = true;
       array_statistics->max_buffer = bool_statistics->max();
+      array_statistics->is_max_exact = true;
     }
   }
   auto array = std::make_shared<BooleanArray>(std::move(array_data));