amol- commented on code in PR #13409:
URL: https://github.com/apache/arrow/pull/13409#discussion_r917804146
##########
python/pyarrow/_dataset.pyx:
##########
@@ -432,6 +447,73 @@ cdef class Dataset(_Weakrefable):
use_threads=use_threads,
coalesce_keys=coalesce_keys,
output_type=InMemoryDataset)
+cdef class FilteredDataset(Dataset):
+ """
+ A Dataset with an applied filter.
+
+ Parameters
+ ----------
+ dataset : Dataset
+ The dataset to which the filter should be applied.
+ expression : Expression
+ The filter that should be applied to the dataset.
+ """
+
+ def __init__(self, dataset, expression):
+ self.init(<shared_ptr[CDataset]>(<Dataset>dataset).wrapped)
+ self._filter = expression
+
+ cdef void init(self, const shared_ptr[CDataset]& sp):
+ Dataset.init(self, sp)
+ self._filter = None
+
+ def filter(self, expression):
+ """Apply an additional row filter to the filtered dataset.
+
+ Parameters
+ ----------
+ expression : Expression
+ The filter that should be applied to the dataset.
+
+ Returns
+ -------
+ FilteredDataset
+ """
+ cdef:
+ FilteredDataset filtered_dataset
+
+ if self._filter is not None:
+ new_filter = self._filter & expression
+ else:
+ new_filter = expression
+ filtered_dataset = self.__class__.__new__(self.__class__)
+ filtered_dataset.init(self.wrapped)
+ filtered_dataset._filter = new_filter
+ return filtered_dataset
+
+ cdef Scanner _make_scanner(self, options):
+ if "filter" in options:
+ raise ValueError(
+ "Passing filter in scanner option is not valid for
FilteredDataset."
Review Comment:
Good point, I made it error as I tweaked the original behaviour in the
change request from Antoine, but I guess we can just and it. I guess it's just
a matter of documenti it properly as some people might expect that like for
`Dataset` passing a `filter` overrides the existing one, instead of extending
it.
--
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: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
