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

🐛 follow up to #35471: update the cartesian stream slicer #35865

Merged
merged 4 commits into from
Mar 7, 2024
Merged

🐛 follow up to #35471: update the cartesian stream slicer #35865

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
6ca1757
update the cartesian stream slicer
girarda Mar 6, 2024
38a776f
whitespace
girarda Mar 6, 2024
8f356df
format
girarda Mar 7, 2024
d0f29d4
format
girarda Mar 7, 2024
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
16 changes: 10 additions & 6 deletions .../python/airbyte_cdk/sources/declarative/stream_slicers/cartesian_product_stream_slicer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ def get_request_params(
) -> Mapping[str, Any]:
return dict(
ChainMap(
*[
*[ # type: ignore # ChainMap expects a MutableMapping[Never, Never] for reasons
s.get_request_params(stream_state=stream_state, stream_slice=stream_slice, next_page_token=next_page_token)
for s in self.stream_slicers
]
Expand All @@ -60,7 +60,7 @@ def get_request_headers(
) -> Mapping[str, Any]:
return dict(
ChainMap(
*[
*[ # type: ignore # ChainMap expects a MutableMapping[Never, Never] for reasons
s.get_request_headers(stream_state=stream_state, stream_slice=stream_slice, next_page_token=next_page_token)
for s in self.stream_slicers
]
Expand All @@ -76,7 +76,7 @@ def get_request_body_data(
) -> Mapping[str, Any]:
return dict(
ChainMap(
*[
*[ # type: ignore # ChainMap expects a MutableMapping[Never, Never] for reasons
s.get_request_body_data(stream_state=stream_state, stream_slice=stream_slice, next_page_token=next_page_token)
for s in self.stream_slicers
]
Expand All @@ -89,10 +89,10 @@ def get_request_body_json(
stream_state: Optional[StreamState] = None,
stream_slice: Optional[StreamSlice] = None,
next_page_token: Optional[Mapping[str, Any]] = None,
) -> Optional[Mapping]:
) -> Mapping[str, Any]:
return dict(
ChainMap(
*[
*[ # type: ignore # ChainMap expects a MutableMapping[Never, Never] for reasons
s.get_request_body_json(stream_state=stream_state, stream_slice=stream_slice, next_page_token=next_page_token)
for s in self.stream_slicers
]
Expand All @@ -101,4 +101,8 @@ def get_request_body_json(

def stream_slices(self) -> Iterable[StreamSlice]:
sub_slices = (s.stream_slices() for s in self.stream_slicers)
return (dict(ChainMap(*a)) for a in itertools.product(*sub_slices))
product = itertools.product(*sub_slices)
for stream_slice_tuple in product:
partition = dict(ChainMap(*[s.partition for s in stream_slice_tuple]))
cursor_slice = dict(ChainMap(*[s.cursor_slice for s in stream_slice_tuple]))
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It feels weird that we would have multiple cursor here but I guess it has always been like that. I'm just wondering if we should fail loudly because we don't understand this business case or just let it happen and have an undetermined behavior

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

agreed. fixed

yield StreamSlice(partition=partition, cursor_slice=cursor_slice)
55 changes: 39 additions & 16 deletions ...hon/unit_tests/sources/declarative/stream_slicers/test_cartesian_product_stream_slicer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
from airbyte_cdk.sources.declarative.partition_routers.list_partition_router import ListPartitionRouter
from airbyte_cdk.sources.declarative.requesters.request_option import RequestOption, RequestOptionType
from airbyte_cdk.sources.declarative.stream_slicers.cartesian_product_stream_slicer import CartesianProductStreamSlicer
from airbyte_cdk.sources.declarative.types import StreamSlice


@pytest.mark.parametrize(
Expand All @@ -17,7 +18,9 @@
(
"test_single_stream_slicer",
[ListPartitionRouter(values=["customer", "store", "subscription"], cursor_field="owner_resource", config={}, parameters={})],
[{"owner_resource": "customer"}, {"owner_resource": "store"}, {"owner_resource": "subscription"}],
[StreamSlice(partition={"owner_resource": "customer"}, cursor_slice={}),
StreamSlice(partition={"owner_resource": "store"}, cursor_slice={}),
StreamSlice(partition={"owner_resource": "subscription"}, cursor_slice={})],
),
(
"test_two_stream_slicers",
Expand All @@ -26,14 +29,34 @@
ListPartitionRouter(values=["A", "B"], cursor_field="letter", config={}, parameters={}),
],
[
{"owner_resource": "customer", "letter": "A"},
{"owner_resource": "customer", "letter": "B"},
{"owner_resource": "store", "letter": "A"},
{"owner_resource": "store", "letter": "B"},
{"owner_resource": "subscription", "letter": "A"},
{"owner_resource": "subscription", "letter": "B"},
StreamSlice(partition={"owner_resource": "customer", "letter": "A"}, cursor_slice={}),
StreamSlice(partition={"owner_resource": "customer", "letter": "B"}, cursor_slice={}),
StreamSlice(partition={"owner_resource": "store", "letter": "A"}, cursor_slice={}),
StreamSlice(partition={"owner_resource": "store", "letter": "B"}, cursor_slice={}),
StreamSlice(partition={"owner_resource": "subscription", "letter": "A"}, cursor_slice={}),
StreamSlice(partition={"owner_resource": "subscription", "letter": "B"}, cursor_slice={}),
],
),
(
"test_singledatetime",
[
DatetimeBasedCursor(
start_datetime=MinMaxDatetime(datetime="2021-01-01", datetime_format="%Y-%m-%d", parameters={}),
end_datetime=MinMaxDatetime(datetime="2021-01-03", datetime_format="%Y-%m-%d", parameters={}),
step="P1D",
cursor_field=InterpolatedString.create("", parameters={}),
datetime_format="%Y-%m-%d",
cursor_granularity="P1D",
config={},
parameters={},
),
],
[
StreamSlice(partition={}, cursor_slice={"start_time": "2021-01-01", "end_time": "2021-01-01"}),
StreamSlice(partition={}, cursor_slice={"start_time": "2021-01-02", "end_time": "2021-01-02"}),
StreamSlice(partition={}, cursor_slice={"start_time": "2021-01-03", "end_time": "2021-01-03"}),
],
),
(
"test_list_and_datetime",
[
Expand All @@ -50,15 +73,15 @@
),
],
[
{"owner_resource": "customer", "start_time": "2021-01-01", "end_time": "2021-01-01"},
{"owner_resource": "customer", "start_time": "2021-01-02", "end_time": "2021-01-02"},
{"owner_resource": "customer", "start_time": "2021-01-03", "end_time": "2021-01-03"},
{"owner_resource": "store", "start_time": "2021-01-01", "end_time": "2021-01-01"},
{"owner_resource": "store", "start_time": "2021-01-02", "end_time": "2021-01-02"},
{"owner_resource": "store", "start_time": "2021-01-03", "end_time": "2021-01-03"},
{"owner_resource": "subscription", "start_time": "2021-01-01", "end_time": "2021-01-01"},
{"owner_resource": "subscription", "start_time": "2021-01-02", "end_time": "2021-01-02"},
{"owner_resource": "subscription", "start_time": "2021-01-03", "end_time": "2021-01-03"},
StreamSlice(partition={"owner_resource": "customer"}, cursor_slice={"start_time": "2021-01-01", "end_time": "2021-01-01"}),
StreamSlice(partition={"owner_resource": "customer"}, cursor_slice={"start_time": "2021-01-02", "end_time": "2021-01-02"}),
StreamSlice(partition={"owner_resource": "customer"}, cursor_slice={ "start_time": "2021-01-03", "end_time": "2021-01-03"}),
StreamSlice(partition={"owner_resource": "store"}, cursor_slice={"start_time": "2021-01-01", "end_time": "2021-01-01"}),
StreamSlice(partition={"owner_resource": "store"}, cursor_slice={"start_time": "2021-01-02", "end_time": "2021-01-02"}),
StreamSlice(partition={"owner_resource": "store"}, cursor_slice={"start_time": "2021-01-03", "end_time": "2021-01-03"}),
StreamSlice(partition={"owner_resource": "subscription"}, cursor_slice={"start_time": "2021-01-01", "end_time": "2021-01-01"}),
StreamSlice(partition={"owner_resource": "subscription"}, cursor_slice={"start_time": "2021-01-02", "end_time": "2021-01-02"}),
StreamSlice(partition={"owner_resource": "subscription"}, cursor_slice={"start_time": "2021-01-03", "end_time": "2021-01-03"}),
],
),
],
Expand Down
Loading