rdblue commented on code in PR #6233:
URL: https://github.com/apache/iceberg/pull/6233#discussion_r1028282275
##########
python/pyiceberg/table/__init__.py:
##########
@@ -199,16 +223,143 @@ def use_ref(self, name: str):
raise ValueError(f"Cannot scan unknown ref={name}")
- def select(self, *field_names: str) -> TableScan:
+ def select(self, *field_names: str) -> S:
if "*" in self.selected_fields:
return self.update(selected_fields=field_names)
return
self.update(selected_fields=tuple(set(self.selected_fields).intersection(set(field_names))))
- def filter_rows(self, new_row_filter: BooleanExpression) -> TableScan:
+ def filter_rows(self, new_row_filter: BooleanExpression) -> S:
return self.update(row_filter=And(self.row_filter, new_row_filter))
- def filter_partitions(self, new_partition_filter: BooleanExpression) ->
TableScan:
+ def filter_partitions(self, new_partition_filter: BooleanExpression) -> S:
return self.update(partition_filter=And(self.partition_filter,
new_partition_filter))
- def with_case_sensitive(self, case_sensitive: bool = True) -> TableScan:
+ def with_case_sensitive(self, case_sensitive: bool = True) -> S:
return self.update(case_sensitive=case_sensitive)
+
+
+class ScanTask(ABC):
+ pass
+
+
+@dataclass(init=False)
+class FileScanTask(ScanTask):
+ file: DataFile
+ start: int
+ length: int
+
+ def __init__(self, data_file: DataFile, start: Optional[int] = None,
length: Optional[int] = None):
+ self.file = data_file
Review Comment:
This is `file` in the JVM version, which is why I went with that. The JVM
one is way more complicated than we need it to be, so I'll have to think about
how we want to structure the task classes.
--
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]
