smaheshwar-pltr commented on code in PR #2230:
URL: https://github.com/apache/iceberg-python/pull/2230#discussion_r2222476542
##########
pyiceberg/table/__init__.py:
##########
@@ -1659,10 +1659,108 @@ def __init__(
self.row_filter = _parse_row_filter(row_filter)
self.selected_fields = selected_fields
self.case_sensitive = case_sensitive
- self.snapshot_id = snapshot_id
self.options = options
self.limit = limit
+ @abstractmethod
+ def projection(self) -> Schema: ...
+
+ @abstractmethod
+ def plan_files(self) -> Iterable[ScanTask]: ...
+
+ @abstractmethod
+ def to_arrow(self) -> pa.Table: ...
+
+ def select(self: A, *field_names: str) -> A:
+ 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(self: A, expr: Union[str, BooleanExpression]) -> A:
+ return self.update(row_filter=And(self.row_filter,
_parse_row_filter(expr)))
+
+ def with_case_sensitive(self: A, case_sensitive: bool = True) -> A:
+ return self.update(case_sensitive=case_sensitive)
+
+ def update(self: A, **overrides: Any) -> A:
+ """Create a copy of this table scan with updated fields."""
+ from inspect import signature
+
+ # Extract those attributes that are constructor parameters. We don't
use self.__dict__ as the kwargs to the
+ # constructors because it may contain additional attributes that are
not part of the constructor signature.
+ params = signature(type(self).__init__).parameters.keys() - {"self"}
# Skip "self" parameter
+ kwargs = {param: getattr(self, param) for param in params} # Assume
parameters are attributes
+
+ return type(self)(**{**kwargs, **overrides})
+
+ def to_pandas(self, **kwargs: Any) -> pd.DataFrame:
+ """Read a Pandas DataFrame eagerly from this Iceberg table scan.
+
+ Returns:
+ pd.DataFrame: Materialized Pandas Dataframe from the Iceberg table
scan
+ """
+ return self.to_arrow().to_pandas(**kwargs)
+
+ def to_duckdb(self, table_name: str, connection:
Optional[DuckDBPyConnection] = None) -> DuckDBPyConnection:
Review Comment:
Highlighting this also - `to_duckdb` and `to_ray` were previously only
present on `DataScan`, not even on `TableScan`. With the change here moving
them to `AbstractTableScan`, `TableScan` now has these additional methods. I
felt like this was fine. Curious for reviewers' thoughts!
(Again, the motivation here was to reduce duplication)
--
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]
