smaheshwar-pltr commented on code in PR #3511:
URL: https://github.com/apache/iceberg-python/pull/3511#discussion_r3417663718
##########
pyiceberg/table/__init__.py:
##########
@@ -1707,20 +1706,127 @@ def __init__(
row_filter: str | BooleanExpression = ALWAYS_TRUE,
selected_fields: tuple[str, ...] = ("*",),
case_sensitive: bool = True,
- snapshot_id: int | None = None,
options: Properties = EMPTY_DICT,
limit: int | None = None,
- catalog: Catalog | None = None,
- table_identifier: Identifier | None = None,
):
self.table_metadata = table_metadata
self.io = io
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 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 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: 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 to_pandas(self, **kwargs: Any) -> pd.DataFrame:
+ """Read a Pandas DataFrame eagerly from this Iceberg table.
+
+ Returns:
+ pd.DataFrame: Materialized Pandas Dataframe from the Iceberg table
+ """
+ return self.to_arrow().to_pandas(**kwargs)
+
+ def to_duckdb(self, table_name: str, connection: DuckDBPyConnection | None
= None) -> DuckDBPyConnection:
+ """Shorthand for loading the Iceberg Table in DuckDB.
+
+ Returns:
+ DuckDBPyConnection: In memory DuckDB connection with the Iceberg
table.
+ """
+ import duckdb
+
+ con = connection or duckdb.connect(database=":memory:")
+ con.register(table_name, self.to_arrow())
+
+ return con
+
+ def to_ray(self) -> ray.data.dataset.Dataset:
+ """Read a Ray Dataset eagerly from this Iceberg table.
+
+ Returns:
+ ray.data.dataset.Dataset: Materialized Ray Dataset from the
Iceberg table
+ """
+ import ray
+
+ return ray.data.from_arrow(self.to_arrow())
+
+ def to_polars(self) -> pl.DataFrame:
+ """Read a Polars DataFrame from this Iceberg table.
+
+ Returns:
+ pl.DataFrame: Materialized Polars Dataframe from the Iceberg table
+ """
+ import polars as pl
+
+ result = pl.from_arrow(self.to_arrow())
+ if isinstance(result, pl.Series):
+ result = result.to_frame()
+
+ return result
+
+
+S = TypeVar("S", bound="TableScan", covariant=True)
+
+
+class TableScan(BaseScan, ABC):
Review Comment:
[AI reviewer aid] `TableScan`'s public surface is unchanged: it now
subclasses the new `BaseScan` but keeps `snapshot_id`, `catalog`,
`table_identifier`, `snapshot()`, `projection()`, `use_ref()`, and abstract
`count()`. The large diff is `TableScan` being moved below `BaseScan`, not
renamed or removed.
##########
pyiceberg/table/__init__.py:
##########
@@ -1817,20 +1816,127 @@ def __init__(
row_filter: str | BooleanExpression = ALWAYS_TRUE,
selected_fields: tuple[str, ...] = ("*",),
case_sensitive: bool = True,
- snapshot_id: int | None = None,
options: Properties = EMPTY_DICT,
limit: int | None = None,
- catalog: Catalog | None = None,
- table_identifier: Identifier | None = None,
):
self.table_metadata = table_metadata
self.io = io
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 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 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: 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 to_pandas(self, **kwargs: Any) -> pd.DataFrame:
+ """Read a Pandas DataFrame eagerly from this Iceberg table.
+
+ Returns:
+ pd.DataFrame: Materialized Pandas Dataframe from the Iceberg table
+ """
+ return self.to_arrow().to_pandas(**kwargs)
+
+ def to_duckdb(self, table_name: str, connection: DuckDBPyConnection | None
= None) -> DuckDBPyConnection:
+ """Shorthand for loading the Iceberg Table in DuckDB.
+
+ Returns:
+ DuckDBPyConnection: In memory DuckDB connection with the Iceberg
table.
+ """
+ import duckdb
+
+ con = connection or duckdb.connect(database=":memory:")
+ con.register(table_name, self.to_arrow())
+
+ return con
+
+ def to_ray(self) -> ray.data.dataset.Dataset:
+ """Read a Ray Dataset eagerly from this Iceberg table.
+
+ Returns:
+ ray.data.dataset.Dataset: Materialized Ray Dataset from the
Iceberg table
+ """
+ import ray
+
+ return ray.data.from_arrow(self.to_arrow())
+
+ def to_polars(self) -> pl.DataFrame:
+ """Read a Polars DataFrame from this Iceberg table.
+
+ Returns:
+ pl.DataFrame: Materialized Polars Dataframe from the Iceberg table
+ """
+ import polars as pl
+
+ result = pl.from_arrow(self.to_arrow())
+ if isinstance(result, pl.Series):
+ result = result.to_frame()
+
+ return result
+
+
+S = TypeVar("S", bound="TableScan", covariant=True)
+
+
+class TableScan(BaseScan):
Review Comment:
[AI reviewer aid] `TableScan`'s public surface is unchanged — it now
subclasses the new `BaseScan` but keeps `snapshot_id`, `catalog`,
`table_identifier`, `snapshot()`, `projection()`, `use_ref()` and abstract
`count()`. The large diff is `TableScan` being moved below `BaseScan`, not
renamed or removed. The `, ABC` base was also dropped as redundant: `BaseScan`
already extends `ABC`, so `TableScan` keeps the identical MRO, `ABCMeta`
metaclass, and abstractness (still non-instantiable) — no behavioural change.
--
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]
