maxdebayser commented on code in PR #7831:
URL: https://github.com/apache/iceberg/pull/7831#discussion_r1280674118
##########
python/pyiceberg/io/pyarrow.py:
##########
@@ -1025,3 +1040,291 @@ def map_key_partner(self, partner_map:
Optional[pa.Array]) -> Optional[pa.Array]
def map_value_partner(self, partner_map: Optional[pa.Array]) ->
Optional[pa.Array]:
return partner_map.items if isinstance(partner_map, pa.MapArray) else
None
+
+
+_PRIMITIVE_TO_PHYSICAL = {
+ BooleanType(): "BOOLEAN",
+ IntegerType(): "INT32",
+ LongType(): "INT64",
+ FloatType(): "FLOAT",
+ DoubleType(): "DOUBLE",
+ DateType(): "INT32",
+ TimeType(): "INT64",
+ TimestampType(): "INT64",
+ TimestamptzType(): "INT64",
+ StringType(): "BYTE_ARRAY",
+ UUIDType(): "FIXED_LEN_BYTE_ARRAY",
+ BinaryType(): "BYTE_ARRAY",
+}
+_PHISICAL_TYPES = ["BOOLEAN", "INT32", "INT64", "INT96", "FLOAT", "DOUBLE",
"BYTE_ARRAY", "FIXED_LEN_BYTE_ARRAY"]
+
+
+class StatsAggregator:
+ def __init__(self, iceberg_type: PrimitiveType, physical_type_string: str,
trunc_length: Optional[int] = None) -> None:
+ self.current_min: Any = None
+ self.current_max: Any = None
+ self.trunc_length = trunc_length
+
+ assert physical_type_string in _PHISICAL_TYPES, f"Unknown physical
type {physical_type_string}"
+ if physical_type_string == "INT96":
+ raise NotImplementedError("Statistics not implemented for INT96
physical type")
+ assert (
+ _PRIMITIVE_TO_PHYSICAL[iceberg_type] == physical_type_string
+ ), f"Unexpected physical type {physical_type_string} for
{iceberg_type}, expected {_PRIMITIVE_TO_PHYSICAL[iceberg_type]}"
+
+ self.primitive_type = iceberg_type
+
+ def serialize(self, value: Any) -> bytes:
+ if type(value) == date:
Review Comment:
Since this commit already has test cases that depend on this conversion, can
we address the refactoring in that issue?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
