Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix(airbyte-cdk): Fix RequestOptionsProvider for PerPartitionWithGlobalCursor #254

Merged
merged 4 commits into from
Jan 23, 2025
Merged

fix(airbyte-cdk): Fix RequestOptionsProvider for PerPartitionWithGlobalCursor #254

Show file tree
Hide file tree
Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
4444893
Fix RequestOptionsProvider for PerPartitionWithGlobalCursor
tolik0 Jan 23, 2025
50a968e
Fix PerPartitionCursor
tolik0 Jan 23, 2025
7795937
Add test for request options provider from substream partition router
tolik0 Jan 23, 2025
f0f8c87
Fix docstring
tolik0 Jan 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 17 additions & 18 deletions airbyte_cdk/sources/declarative/incremental/per_partition_cursor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -222,6 +222,8 @@ def get_request_params(
next_page_token: Optional[Mapping[str, Any]] = None,
) -> Mapping[str, Any]:
if stream_slice:
if self._to_partition_key(stream_slice.partition) not in self._cursor_per_partition:
self.create_cursor_for_partition(self._to_partition_key(stream_slice.partition))
return self._partition_router.get_request_params( # type: ignore # this always returns a mapping
stream_state=stream_state,
stream_slice=StreamSlice(partition=stream_slice.partition, cursor_slice={}),
Expand All @@ -244,6 +246,8 @@ def get_request_headers(
next_page_token: Optional[Mapping[str, Any]] = None,
) -> Mapping[str, Any]:
if stream_slice:
if self._to_partition_key(stream_slice.partition) not in self._cursor_per_partition:
self.create_cursor_for_partition(self._to_partition_key(stream_slice.partition))
return self._partition_router.get_request_headers( # type: ignore # this always returns a mapping
stream_state=stream_state,
stream_slice=StreamSlice(partition=stream_slice.partition, cursor_slice={}),
Expand All @@ -266,6 +270,8 @@ def get_request_body_data(
next_page_token: Optional[Mapping[str, Any]] = None,
) -> Union[Mapping[str, Any], str]:
if stream_slice:
if self._to_partition_key(stream_slice.partition) not in self._cursor_per_partition:
self.create_cursor_for_partition(self._to_partition_key(stream_slice.partition))
return self._partition_router.get_request_body_data( # type: ignore # this always returns a mapping
stream_state=stream_state,
stream_slice=StreamSlice(partition=stream_slice.partition, cursor_slice={}),
Expand All @@ -288,6 +294,8 @@ def get_request_body_json(
next_page_token: Optional[Mapping[str, Any]] = None,
) -> Mapping[str, Any]:
if stream_slice:
if self._to_partition_key(stream_slice.partition) not in self._cursor_per_partition:
self.create_cursor_for_partition(self._to_partition_key(stream_slice.partition))
return self._partition_router.get_request_body_json( # type: ignore # this always returns a mapping
stream_state=stream_state,
stream_slice=StreamSlice(partition=stream_slice.partition, cursor_slice={}),
Expand All @@ -303,21 +311,6 @@ def get_request_body_json(
raise ValueError("A partition needs to be provided in order to get request body json")

def should_be_synced(self, record: Record) -> bool:
if (
record.associated_slice
and self._to_partition_key(record.associated_slice.partition)
not in self._cursor_per_partition
):
partition_state = (
self._state_to_migrate_from
if self._state_to_migrate_from
else self._NO_CURSOR_STATE
)
cursor = self._create_cursor(partition_state)

self._cursor_per_partition[
self._to_partition_key(record.associated_slice.partition)
] = cursor
return self._get_cursor(record).should_be_synced(
self._convert_record_to_cursor_record(record)
)
Expand Down Expand Up @@ -356,8 +349,14 @@ def _get_cursor(self, record: Record) -> DeclarativeCursor:
)
partition_key = self._to_partition_key(record.associated_slice.partition)
if partition_key not in self._cursor_per_partition:
raise ValueError(
"Invalid state as stream slices that are emitted should refer to an existing cursor"
)
self.create_cursor_for_partition(partition_key)
cursor = self._cursor_per_partition[partition_key]
return cursor

def create_cursor_for_partition(self, partition_key: str) -> None:
tolik0 marked this conversation as resolved.
Show resolved Hide resolved
partition_state = (
self._state_to_migrate_from if self._state_to_migrate_from else self._NO_CURSOR_STATE
)
cursor = self._create_cursor(partition_state)

self._cursor_per_partition[partition_key] = cursor
2 changes: 1 addition & 1 deletion airbyte_cdk/sources/declarative/parsers/model_to_component_factory.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2374,7 +2374,7 @@ def create_simple_retriever(
if (
not isinstance(stream_slicer, DatetimeBasedCursor)
or type(stream_slicer) is not DatetimeBasedCursor
) and not isinstance(stream_slicer, PerPartitionWithGlobalCursor):
):
# Many of the custom component implementations of DatetimeBasedCursor override get_request_params() (or other methods).
# Because we're decoupling RequestOptionsProvider from the Cursor, custom components will eventually need to reimplement
# their own RequestOptionsProvider. However, right now the existing StreamSlicer/Cursor still can act as the SimpleRetriever's
Expand Down
Loading