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: allow dispatching items to nested tables when specified parent_table_name equals resource.table_name #2106

Open
wants to merge 3 commits into
base: devel
Choose a base branch
from
Open

fix: allow dispatching items to nested tables when specified parent_table_name equals resource.table_name #2106

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b8b5ecd
test: add test with hint for parent table
joscha Nov 28, 2024
0605d80
Merge remote-tracking branch 'upstream' into joscha/mark-parent-table
joscha Dec 9, 2024
6fa2e06
style: indentation
joscha Dec 9, 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
6 changes: 5 additions & 1 deletion dlt/common/schema/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -511,7 +511,11 @@ def diff_table(
partial_table[k] = v # type: ignore

# this should not really happen
if is_nested_table(tab_a) and (resource := tab_b.get("resource")):
if (
is_nested_table(tab_a)
and (resource := tab_b.get("resource"))
and resource != tab_a.get("parent")
):
raise TablePropertiesConflictException(
schema_name, table_name, "resource", resource, tab_a.get("parent")
)
Expand Down
22 changes: 22 additions & 0 deletions tests/pipeline/test_pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -667,6 +667,28 @@ def with_table_hints():
assert_data_table_counts(pipeline, {"table_a": 2, "table_b": 2, "table_c": 1})


def test_mark_parent_table() -> None:
@dlt.resource()
def my_table():
yield {"id": 1}
yield dlt.mark.with_hints(
{"id": 10},
dlt.mark.make_hints(table_name="my_other_table", parent_table_name="my_table"),
)

pipeline_name = "pipe_" + uniq_id()
pipeline = dlt.pipeline(pipeline_name=pipeline_name, destination="duckdb")
info = pipeline.run(my_table)
assert_load_info(info)
assert pipeline.last_trace.last_normalize_info.row_counts == {
"_dlt_pipeline_state": 1,
"my_table": 1,
"my_other_table": 1,
}
# check table counts
assert_data_table_counts(pipeline, {"my_table": 1, "my_other_table": 1})


def test_restore_state_on_dummy() -> None:
pipeline_name = "pipe_" + uniq_id()
p = dlt.pipeline(pipeline_name=pipeline_name, destination=DUMMY_COMPLETE)
Expand Down
Loading