GH-36619: [Python] Parquet statistics string representation misleading (

#36626)

### Rationale for this change

If `Statistics.has_distinct_count` is false, the printout still shows a `distinct_count` value (`0`).

### What changes are included in this PR?

Update the `distinct_count` property  of `Statistics` class to check for `has_distinct_count` value.

### Are these changes tested?

The tests for `distinct_count` are already included in `test_parquet_column_statistics_api` and only needed to be updated.
* Closes: #36619

Authored-by: AlenkaF <frim.alenka@gmail.com>
Signed-off-by: Antoine Pitrou <antoine@python.org>

python/pyarrow/_parquet.pyx

@@ -175,17 +175,18 @@ cdef class Statistics(_Weakrefable):
     @property
     def null_count(self):
         """Number of null values in chunk (int)."""
-        return self.statistics.get().null_count()
+        if self.has_null_count:
+            return self.statistics.get().null_count()
+        else:
+            return None
 
     @property
     def distinct_count(self):
-        """
-        Distinct number of values in chunk (int).
-
-        If this is not set, will return 0.
-        """
-        # This seems to be zero if not set. See: ARROW-11793
-        return self.statistics.get().distinct_count()
+        """Distinct number of values in chunk (int)."""
+        if self.has_distinct_count:
+            return self.statistics.get().distinct_count()
+        else:
+            return None
 
     @property
     def num_values(self):

python/pyarrow/tests/parquet/test_metadata.py

@@ -161,33 +161,33 @@ def test_parquet_metadata_lifetime(tempdir):
         'distinct_count'
     ),
     [
-        ([1, 2, 2, None, 4], pa.uint8(), 'INT32', 1, 4, 1, 4, 0),
-        ([1, 2, 2, None, 4], pa.uint16(), 'INT32', 1, 4, 1, 4, 0),
-        ([1, 2, 2, None, 4], pa.uint32(), 'INT32', 1, 4, 1, 4, 0),
-        ([1, 2, 2, None, 4], pa.uint64(), 'INT64', 1, 4, 1, 4, 0),
-        ([-1, 2, 2, None, 4], pa.int8(), 'INT32', -1, 4, 1, 4, 0),
-        ([-1, 2, 2, None, 4], pa.int16(), 'INT32', -1, 4, 1, 4, 0),
-        ([-1, 2, 2, None, 4], pa.int32(), 'INT32', -1, 4, 1, 4, 0),
-        ([-1, 2, 2, None, 4], pa.int64(), 'INT64', -1, 4, 1, 4, 0),
+        ([1, 2, 2, None, 4], pa.uint8(), 'INT32', 1, 4, 1, 4, None),
+        ([1, 2, 2, None, 4], pa.uint16(), 'INT32', 1, 4, 1, 4, None),
+        ([1, 2, 2, None, 4], pa.uint32(), 'INT32', 1, 4, 1, 4, None),
+        ([1, 2, 2, None, 4], pa.uint64(), 'INT64', 1, 4, 1, 4, None),
+        ([-1, 2, 2, None, 4], pa.int8(), 'INT32', -1, 4, 1, 4, None),
+        ([-1, 2, 2, None, 4], pa.int16(), 'INT32', -1, 4, 1, 4, None),
+        ([-1, 2, 2, None, 4], pa.int32(), 'INT32', -1, 4, 1, 4, None),
+        ([-1, 2, 2, None, 4], pa.int64(), 'INT64', -1, 4, 1, 4, None),
         (
             [-1.1, 2.2, 2.3, None, 4.4], pa.float32(),
-            'FLOAT', -1.1, 4.4, 1, 4, 0
+            'FLOAT', -1.1, 4.4, 1, 4, None
         ),
         (
             [-1.1, 2.2, 2.3, None, 4.4], pa.float64(),
-            'DOUBLE', -1.1, 4.4, 1, 4, 0
+            'DOUBLE', -1.1, 4.4, 1, 4, None
         ),
         (
             ['', 'b', chr(1000), None, 'aaa'], pa.binary(),
-            'BYTE_ARRAY', b'', chr(1000).encode('utf-8'), 1, 4, 0
+            'BYTE_ARRAY', b'', chr(1000).encode('utf-8'), 1, 4, None
         ),
         (
             [True, False, False, True, True], pa.bool_(),
-            'BOOLEAN', False, True, 0, 5, 0
+            'BOOLEAN', False, True, 0, 5, None
         ),
         (
             [b'\x00', b'b', b'12', None, b'aaa'], pa.binary(),
-            'BYTE_ARRAY', b'\x00', b'b', 1, 4, 0
+            'BYTE_ARRAY', b'\x00', b'b', 1, 4, None
         ),
     ]
 )