jun-he commented on code in PR #5462:
URL: https://github.com/apache/iceberg/pull/5462#discussion_r951041061
##########
python/pyiceberg/transforms.py:
##########
@@ -215,6 +227,243 @@ def __repr__(self) -> str:
return f"BucketTransform(num_buckets={self._num_buckets})"
+class YearTransform(Transform[S, int]):
+ """Transforms a datetime value into a year value.
+
+ Example:
+ >>> transform = YearTransform()
+ >>> transform.transform(TimestampType())(1512151975038194)
+ 47
+ """
+
+ __root__: Literal["year"] = Field(default="year")
+ _source_type: IcebergType = PrivateAttr()
+
+ def transform(self, source: IcebergType) -> Callable[[Optional[S]],
Optional[int]]:
+ source_type = type(source)
+ if source_type == DateType:
+
+ def year_func(v):
+ return datetime.days_to_years(v)
+
+ elif source_type in {TimestampType, TimestamptzType}:
+
+ def year_func(v):
+ return datetime.micros_to_years(v)
+
+ else:
+ raise ValueError(f"Cannot apply year transform for type: {source}")
+
+ return lambda v: year_func(v) if v else None
+
+ def can_transform(self, source: IcebergType) -> bool:
+ return type(source) in {
+ DateType,
+ TimestampType,
+ TimestamptzType,
+ }
+
+ def result_type(self, source: IcebergType) -> IcebergType:
+ return IntegerType()
+
+ @property
+ def preserves_order(self) -> bool:
+ return True
+
+ @property
+ def time_order(self) -> int:
Review Comment:
👌
--
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]
