rambleraptor commented on code in PR #3512:
URL: https://github.com/apache/iceberg-python/pull/3512#discussion_r3455804526
##########
pyiceberg/table/__init__.py:
##########
@@ -2263,6 +2341,180 @@ def count(self) -> int:
return res
+IAS = TypeVar("IAS", bound="IncrementalAppendScan", covariant=True)
+
+
+class IncrementalAppendScan(BaseScan):
+ """An incremental scan of a table's data that accumulates appended data
between two snapshots.
+
+ Args:
+ row_filter:
+ A string or BooleanExpression that describes the
+ desired rows
+ selected_fields:
+ A tuple of strings representing the column names
+ to return in the output dataframe.
+ case_sensitive:
+ If True column matching is case sensitive
+ options:
+ Additional Table properties as a dictionary of
+ string key value pairs to use for this scan.
+ limit:
+ An integer representing the number of rows to
+ return in the scan result. If None, fetches all
+ matching rows.
+ from_snapshot_id_exclusive:
+ Optional ID of the "from" snapshot, to start the incremental scan
from, exclusively. When the scan is
+ ultimately planned, this must not be None. The snapshot does not
need to be present in the table metadata
+ (it may have been expired), as long as it is the parent of some
ancestor of the "to" snapshot.
+ to_snapshot_id_inclusive:
+ Optional ID of the "to" snapshot, to end the incremental scan at,
inclusively.
+ Omitting it will default to the table's current snapshot.
+ """
+
+ from_snapshot_id_exclusive: int | None
+ to_snapshot_id_inclusive: int | None
+
+ def __init__(
+ self,
+ table_metadata: TableMetadata,
+ io: FileIO,
+ row_filter: str | BooleanExpression = ALWAYS_TRUE,
+ selected_fields: tuple[str, ...] = ("*",),
+ case_sensitive: bool = True,
+ from_snapshot_id_exclusive: int | None = None,
+ to_snapshot_id_inclusive: int | None = None,
+ options: Properties = EMPTY_DICT,
+ limit: int | None = None,
+ ):
+ super().__init__(
+ table_metadata=table_metadata,
+ io=io,
+ row_filter=row_filter,
+ selected_fields=selected_fields,
+ case_sensitive=case_sensitive,
+ options=options,
+ limit=limit,
+ )
+ self.from_snapshot_id_exclusive = from_snapshot_id_exclusive
Review Comment:
We should make this a private variable and then expose it out with a getter.
The methods below are trying to make it explicit how to change these
variables, so we should make it impossible to change them directly.
##########
pyiceberg/table/__init__.py:
##########
@@ -2263,6 +2341,180 @@ def count(self) -> int:
return res
+IAS = TypeVar("IAS", bound="IncrementalAppendScan", covariant=True)
+
+
+class IncrementalAppendScan(BaseScan):
+ """An incremental scan of a table's data that accumulates appended data
between two snapshots.
+
+ Args:
+ row_filter:
+ A string or BooleanExpression that describes the
+ desired rows
+ selected_fields:
+ A tuple of strings representing the column names
+ to return in the output dataframe.
+ case_sensitive:
+ If True column matching is case sensitive
+ options:
+ Additional Table properties as a dictionary of
+ string key value pairs to use for this scan.
+ limit:
+ An integer representing the number of rows to
+ return in the scan result. If None, fetches all
+ matching rows.
+ from_snapshot_id_exclusive:
+ Optional ID of the "from" snapshot, to start the incremental scan
from, exclusively. When the scan is
+ ultimately planned, this must not be None. The snapshot does not
need to be present in the table metadata
+ (it may have been expired), as long as it is the parent of some
ancestor of the "to" snapshot.
+ to_snapshot_id_inclusive:
+ Optional ID of the "to" snapshot, to end the incremental scan at,
inclusively.
+ Omitting it will default to the table's current snapshot.
+ """
+
+ from_snapshot_id_exclusive: int | None
+ to_snapshot_id_inclusive: int | None
+
+ def __init__(
+ self,
+ table_metadata: TableMetadata,
+ io: FileIO,
+ row_filter: str | BooleanExpression = ALWAYS_TRUE,
+ selected_fields: tuple[str, ...] = ("*",),
+ case_sensitive: bool = True,
+ from_snapshot_id_exclusive: int | None = None,
+ to_snapshot_id_inclusive: int | None = None,
+ options: Properties = EMPTY_DICT,
+ limit: int | None = None,
+ ):
+ super().__init__(
+ table_metadata=table_metadata,
+ io=io,
+ row_filter=row_filter,
+ selected_fields=selected_fields,
+ case_sensitive=case_sensitive,
+ options=options,
+ limit=limit,
+ )
+ self.from_snapshot_id_exclusive = from_snapshot_id_exclusive
+ self.to_snapshot_id_inclusive = to_snapshot_id_inclusive
+
+ def from_snapshot_exclusive(self: IAS, from_snapshot_id_exclusive: int |
None) -> IAS:
Review Comment:
What do you think about changing this to
`update_from_snapshot_id_exclusive`? (same for inclusive below)
The variables are public, so we have both a variable and a method and it can
be unclear which to use.
--
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]
