fix pre-1970 timestamp roundtrip

Author: HuaHuaY

cpp/src/parquet/arrow/arrow_reader_writer_test.cc

@@ -74,6 +74,7 @@
 #include "parquet/page_index.h"
 #include "parquet/properties.h"
 #include "parquet/test_util.h"
+#include "parquet/types.h"
 
 using arrow::Array;
 using arrow::ArrayData;
@@ -4149,14 +4150,26 @@ INSTANTIATE_TEST_SUITE_P(Repetition_type, TestNestedSchemaRead,
                          ::testing::Values(Repetition::REQUIRED, Repetition::OPTIONAL));
 
 TEST(TestImpalaConversion, ArrowTimestampToImpalaTimestamp) {
-  // June 20, 2017 16:32:56 and 123456789 nanoseconds
-  int64_t nanoseconds = INT64_C(1497976376123456789);
+  {
+    // June 20, 2017 16:32:56 and 123456789 nanoseconds
+    int64_t timestamp = INT64_C(1497976376123456789);
+    Int96 impala_timestamp = {{UINT32_C(632093973), UINT32_C(13871), UINT32_C(2457925)}};
+    ASSERT_EQ(timestamp, ::parquet::Int96GetNanoSeconds(impala_timestamp));
 
-  Int96 calculated;
+    Int96 calculated;
+    ::parquet::internal::NanosecondsToImpalaTimestamp(timestamp, &calculated);
+    ASSERT_EQ(impala_timestamp, calculated);
+  }
+  {
+    // January 1, 1970 07:59:59 and 999999000 nanoseconds
+    int64_t timestamp = INT64_C(-1000);
+    Int96 impala_timestamp = {{UINT32_C(2437872664), UINT32_C(20116), UINT32_C(2440587)}};
+    ASSERT_EQ(timestamp, ::parquet::Int96GetNanoSeconds(impala_timestamp));
 
-  Int96 expected = {{UINT32_C(632093973), UINT32_C(13871), UINT32_C(2457925)}};
-  ::parquet::internal::NanosecondsToImpalaTimestamp(nanoseconds, &calculated);
-  ASSERT_EQ(expected, calculated);
+    Int96 calculated;
+    ::parquet::internal::NanosecondsToImpalaTimestamp(timestamp, &calculated);
+    ASSERT_EQ(impala_timestamp, calculated);
+  }
 }
 
 void TryReadDataFile(const std::string& path,

cpp/src/parquet/column_writer.h

@@ -259,14 +259,15 @@ constexpr int64_t kJulianEpochOffsetDays = INT64_C(2440588);
 
 template <int64_t UnitPerDay, int64_t NanosecondsPerUnit>
 inline void ArrowTimestampToImpalaTimestamp(const int64_t time, Int96* impala_timestamp) {
-  int64_t julian_days = (time / UnitPerDay) + kJulianEpochOffsetDays;
-  (*impala_timestamp).value[2] = (uint32_t)julian_days;
+  int32_t julian_days = static_cast<int32_t>(time / UnitPerDay + kJulianEpochOffsetDays) +
+                        (time < 0 ? -1 : 0);
+  impala_timestamp->value[2] = static_cast<uint32_t>(julian_days);
 
-  int64_t last_day_units = time % UnitPerDay;
-  auto last_day_nanos = last_day_units * NanosecondsPerUnit;
+  uint64_t last_day_units = time % UnitPerDay + (time < 0 ? UnitPerDay : 0);
+  uint64_t last_day_nanos = last_day_units * NanosecondsPerUnit;
   // impala_timestamp will be unaligned every other entry so do memcpy instead
   // of assign and reinterpret cast to avoid undefined behavior.
-  std::memcpy(impala_timestamp, &last_day_nanos, sizeof(int64_t));
+  std::memcpy(impala_timestamp, &last_day_nanos, sizeof(uint64_t));
 }
 
 constexpr int64_t kSecondsInNanos = INT64_C(1000000000);