[arrow] branch main updated: GH-36323: [Python] Fix Timestamp scalar repr error on values outside datetime range (#36942)

[kou]

This is an automated email from the ASF dual-hosted git repository.

kou pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/arrow.git


The following commit(s) were added to refs/heads/main by this push:
     new 112f949718 GH-36323: [Python] Fix Timestamp scalar repr error on 
values outside datetime range (#36942)
112f949718 is described below

commit 112f94971882750731fabebd499ab0f817ca3839
Author: Ashish Bailkeri <47304318+aboss...@users.noreply.github.com>
AuthorDate: Mon Jul 31 16:57:01 2023 -0400

    GH-36323: [Python] Fix Timestamp scalar repr error on values outside 
datetime range (#36942)
    
    
    
    ### Rationale for this change
    
    https://github.com/apache/arrow/issues/36323
    
    ### What changes are included in this PR?
    
    Changed the way repr is handled for TimestampScalar
    
    ### Are these changes tested?
    
    I have added a very basic test for this change to see whether it will error 
or not if outside the range.
    
    ### Are there any user-facing changes?
    
    The functionality of TimestampScalar's repr now uses the `strftime` 
function.
    
    * Closes: #36323
    
    Lead-authored-by: Ashish Bailkeri <ashishbailkeri...@gmail.com>
    Co-authored-by: Ashish Bailkeri <47304318+aboss...@users.noreply.github.com>
    Signed-off-by: Sutou Kouhei <k...@clear-code.com>
---
 python/pyarrow/scalar.pxi                    | 17 +++++++++++++++++
 python/pyarrow/tests/test_convert_builtin.py |  2 +-
 python/pyarrow/tests/test_scalars.py         | 12 ++++++++++++
 python/pyarrow/types.pxi                     |  4 ++--
 4 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/python/pyarrow/scalar.pxi b/python/pyarrow/scalar.pxi
index 74f5aa4213..aff1c311ab 100644
--- a/python/pyarrow/scalar.pxi
+++ b/python/pyarrow/scalar.pxi
@@ -522,6 +522,23 @@ cdef class TimestampScalar(Scalar):
 
         return _datetime_from_int(sp.value, unit=dtype.unit(), tzinfo=tzinfo)
 
+    def __repr__(self):
+        """
+        Return the representation of TimestampScalar using `strftime` to avoid
+        original repr datetime values being out of range.
+        """
+        cdef:
+            CTimestampScalar* sp = <CTimestampScalar*> self.wrapped.get()
+            CTimestampType* dtype = <CTimestampType*> sp.type.get()
+
+        if not dtype.timezone().empty():
+            type_format = str(_pc().strftime(self, 
format="%Y-%m-%dT%H:%M:%S%z"))
+        else:
+            type_format = str(_pc().strftime(self))
+        return '<pyarrow.{}: {!r}>'.format(
+            self.__class__.__name__, type_format
+        )
+
 
 cdef class DurationScalar(Scalar):
     """
diff --git a/python/pyarrow/tests/test_convert_builtin.py 
b/python/pyarrow/tests/test_convert_builtin.py
index af4c91a894..cf2535a3c6 100644
--- a/python/pyarrow/tests/test_convert_builtin.py
+++ b/python/pyarrow/tests/test_convert_builtin.py
@@ -1353,7 +1353,7 @@ def test_sequence_timestamp_from_int_with_unit():
     assert len(arr_s) == 1
     assert arr_s.type == s
     assert repr(arr_s[0]) == (
-        "<pyarrow.TimestampScalar: datetime.datetime(1970, 1, 1, 0, 0, 1)>"
+        "<pyarrow.TimestampScalar: '1970-01-01T00:00:01'>"
     )
     assert str(arr_s[0]) == "1970-01-01 00:00:01"
 
diff --git a/python/pyarrow/tests/test_scalars.py 
b/python/pyarrow/tests/test_scalars.py
index 2aaefe16ae..a989301fe5 100644
--- a/python/pyarrow/tests/test_scalars.py
+++ b/python/pyarrow/tests/test_scalars.py
@@ -154,6 +154,18 @@ def test_hashing_struct_scalar():
     assert hash1 == hash2
 
 
+def test_timestamp_scalar():
+    a = repr(pa.scalar("0000-01-01").cast(pa.timestamp("s")))
+    assert a == "<pyarrow.TimestampScalar: '0000-01-01T00:00:00'>"
+    b = repr(pa.scalar(datetime.datetime(2015, 1, 1), type=pa.timestamp('s', 
tz='UTC')))
+    assert b == "<pyarrow.TimestampScalar: '2015-01-01T00:00:00+0000'>"
+    c = repr(pa.scalar(datetime.datetime(2015, 1, 1), type=pa.timestamp('us')))
+    assert c == "<pyarrow.TimestampScalar: '2015-01-01T00:00:00.000000'>"
+    d = repr(pc.assume_timezone(
+        pa.scalar("2000-01-01").cast(pa.timestamp("s")), "America/New_York"))
+    assert d == "<pyarrow.TimestampScalar: '2000-01-01T00:00:00-0500'>"
+
+
 def test_bool():
     false = pa.scalar(False)
     true = pa.scalar(True)
diff --git a/python/pyarrow/types.pxi b/python/pyarrow/types.pxi
index fbd4f8a94b..12ad2fc4b6 100644
--- a/python/pyarrow/types.pxi
+++ b/python/pyarrow/types.pxi
@@ -3605,9 +3605,9 @@ def timestamp(unit, tz=None):
 
     >>> from datetime import datetime
     >>> pa.scalar(datetime(2012, 1, 1), type=pa.timestamp('s', tz='UTC'))
-    <pyarrow.TimestampScalar: datetime.datetime(2012, 1, 1, 0, 0, 
tzinfo=<UTC>)>
+    <pyarrow.TimestampScalar: '2012-01-01T00:00:00+0000'>
     >>> pa.scalar(datetime(2012, 1, 1), type=pa.timestamp('us'))
-    <pyarrow.TimestampScalar: datetime.datetime(2012, 1, 1, 0, 0)>
+    <pyarrow.TimestampScalar: '2012-01-01T00:00:00.000000'>
 
     Returns
     -------