GH-30117: [C++][Python] Add "Z" to the end of timestamp print string when tz defined (#39272)

AlenkaF · rok · web-flow · commit a288364d971a · 2024-01-08T14:26:13.000+01:00
### What changes are included in this PR? This PR updates the PrettyPrint for Timestamp type so that "Z" is printed at the end of the output string if the timezone has been defined. This way we add minimum information about the values being stored in UTC. ### Are these changes tested? Yes. ### Are there any user-facing changes? There is a change in how `TimestampArray` prints out the data. With this change "Z" would be added to the end of the string if the timezone is defined. * Closes: #30117 Lead-authored-by: AlenkaF <frim.alenka@gmail.com> Co-authored-by: Alenka Frim <AlenkaF@users.noreply.github.com> Co-authored-by: Rok Mihevc <rok@mihevc.org> Signed-off-by: Joris Van den Bossche <jorisvandenbossche@gmail.com>
diff --git a/cpp/src/arrow/pretty_print_test.cc b/cpp/src/arrow/pretty_print_test.cc
@@ -350,10 +350,10 @@ TEST_F(TestPrettyPrint, DateTimeTypes) {
     std::vector<int64_t> values = {
         0, 1, 2, 678 + 1000000 * (5 + 60 * (4 + 60 * (3 + 24 * int64_t(1)))), 4};
     static const char* expected = R"expected([
-  1970-01-01 00:00:00.000000,
-  1970-01-01 00:00:00.000001,
+  1970-01-01 00:00:00.000000Z,
+  1970-01-01 00:00:00.000001Z,
   null,
-  1970-01-02 03:04:05.000678,
+  1970-01-02 03:04:05.000678Z,
   null
 ])expected";
     CheckPrimitive<TimestampType, int64_t>(timestamp(TimeUnit::MICRO, "Transylvania"),
diff --git a/cpp/src/arrow/util/formatting.h b/cpp/src/arrow/util/formatting.h
@@ -470,7 +470,8 @@ class StringFormatter<TimestampType> {
   using value_type = int64_t;
 
   explicit StringFormatter(const DataType* type)
-      : unit_(checked_cast<const TimestampType&>(*type).unit()) {}
+      : unit_(checked_cast<const TimestampType&>(*type).unit()),
+        timezone_(checked_cast<const TimestampType&>(*type).timezone()) {}
 
   template <typename Duration, typename Appender>
   Return<Appender> operator()(Duration, value_type value, Appender&& append) {
@@ -503,6 +504,9 @@ class StringFormatter<TimestampType> {
     std::array<char, buffer_size> buffer;
     char* cursor = buffer.data() + buffer_size;
 
+    if (timezone_.size() > 0) {
+      detail::FormatOneChar('Z', &cursor);
+    }
     detail::FormatHH_MM_SS(arrow_vendored::date::make_time(since_midnight), &cursor);
     detail::FormatOneChar(' ', &cursor);
     detail::FormatYYYY_MM_DD(timepoint_days, &cursor);
@@ -516,6 +520,7 @@ class StringFormatter<TimestampType> {
 
  private:
   TimeUnit::type unit_;
+  std::string timezone_;
 };
 
 template <typename T>
diff --git a/cpp/src/arrow/util/formatting_util_test.cc b/cpp/src/arrow/util/formatting_util_test.cc
@@ -522,6 +522,34 @@ TEST(Formatting, Timestamp) {
     AssertFormatting(formatter, -2203932304LL * 1000000000LL + 8,
                      "1900-02-28 12:34:56.000000008");
   }
+
+  {
+    auto timestamp_types = {timestamp(TimeUnit::SECOND, "US/Eastern"),
+                            timestamp(TimeUnit::SECOND, "+01:00")};
+    for (auto ty : timestamp_types) {
+      StringFormatter<TimestampType> formatter(ty.get());
+
+      AssertFormatting(formatter, 0, "1970-01-01 00:00:00Z");
+    }
+  }
+
+  {
+    auto ty = timestamp(TimeUnit::MILLI, "Pacific/Maruesas");
+    StringFormatter<TimestampType> formatter(ty.get());
+    AssertFormatting(formatter, 0, "1970-01-01 00:00:00.000Z");
+  }
+
+  {
+    auto ty = timestamp(TimeUnit::MICRO, "-42:00");
+    StringFormatter<TimestampType> formatter(ty.get());
+    AssertFormatting(formatter, 0, "1970-01-01 00:00:00.000000Z");
+  }
+
+  {
+    auto ty = timestamp(TimeUnit::NANO, "Mars/Mariner_Valley");
+    StringFormatter<TimestampType> formatter(ty.get());
+    AssertFormatting(formatter, 0, "1970-01-01 00:00:00.000000000Z");
+  }
 }
 
 TEST(Formatting, Interval) {
diff --git a/python/pyarrow/tests/test_types.py b/python/pyarrow/tests/test_types.py
@@ -487,6 +487,17 @@ def test_timestamp():
             pa.timestamp(invalid_unit)
 
 
+def test_timestamp_print():
+    for unit in ('s', 'ms', 'us', 'ns'):
+        for tz in ('UTC', 'Europe/Paris', 'Pacific/Marquesas',
+                   'Mars/Mariner_Valley', '-00:42', '+42:00'):
+            ty = pa.timestamp(unit, tz=tz)
+            arr = pa.array([0], ty)
+            assert "Z" in str(arr)
+        arr = pa.array([0], pa.timestamp(unit))
+        assert "Z" not in str(arr)
+
+
 def test_time32_units():
     for valid_unit in ('s', 'ms'):
         ty = pa.time32(valid_unit)
