emkornfield commented on a change in pull request #2115:
URL: https://github.com/apache/iceberg/pull/2115#discussion_r788247681
##########
File path: python/iceberg/api/expressions/residual_evaluator.py
##########
@@ -15,98 +15,158 @@
# specific language governing permissions and limitations
# under the License.
+from .expression import Expression
from .expressions import Expressions, ExpressionVisitors
+from .literals import Literal
from .predicate import BoundPredicate, Predicate, UnboundPredicate
+from .reference import BoundReference
+from ..partition_spec import PartitionSpec
+from ..struct_like import StructLike
class ResidualEvaluator(object):
+ """
+ Finds the residuals for an {@link Expression} the partitions in the given
{@link PartitionSpec}.
- def __init__(self, spec, expr):
+ A residual expression is made by partially evaluating an expression using
partition values. For
+ example, if a table is partitioned by day(utc_timestamp) and is read with
a filter expression
+ utc_timestamp >= a and utc_timestamp <= b, then there are 4 possible
residuals expressions
+ for the partition data, d:
+
+
+ + If d > day(a) and d < day(b), the residual is always true
+ + If d == day(a) and d != day(b), the residual is utc_timestamp >= b
+ + if d == day(b) and d != day(a), the residual is utc_timestamp <= b
+ + If d == day(a) == day(b), the residual is utc_timestamp >= a and
utc_timestamp <= b
+
+ Partition data is passed using StructLike. Residuals are returned by
residualFor(StructLike).
+
+ """
+ @staticmethod
+ def unpartitioned(expr: Expression) -> 'UnpartitionedEvaluator':
+ return UnpartitionedEvaluator(expr)
+
+ @staticmethod
+ def of(spec: PartitionSpec, expr: Expression, case_sensitive=True) ->
'ResidualEvaluator':
+ if len(spec.fields) > 0:
+ return ResidualEvaluator(spec, expr, case_sensitive=case_sensitive)
+ else:
+ return ResidualEvaluator.unpartitioned(expr)
+
+ def __init__(self, spec, expr, case_sensitive=True):
self._spec = spec
self._expr = expr
+ self._case_sensitive = case_sensitive
self.__visitor = None
- def _visitor(self):
+ def _visitor(self) -> 'ResidualVisitor':
if self.__visitor is None:
- self.__visitor = ResidualVisitor()
+ self.__visitor = ResidualVisitor(self._spec,
+ self._expr,
+ self._case_sensitive)
return self.__visitor
- def residual_for(self, partition_data):
+ def residual_for(self, partition_data: StructLike) -> Expression:
+ """
+ Returns a residual expression for the given partition values.
+
+ Parameters
+ ----------
+ partition_data: StructLike
+ partition data values
+
+ Returns
+ -------
+ Expression
+ the residual of this evaluator's expression from the partition
values
+ """
return self._visitor().eval(partition_data)
class ResidualVisitor(ExpressionVisitors.BoundExpressionVisitor):
- def __init__(self):
+ def __init__(self, spec, expr, case_sensitive=True):
Review comment:
type annotations for spec and expr?
--
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]
