Skip to content

fix: Add missing metadata fields #40

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

Merged
merged 4 commits into from
Aug 14, 2023
Merged

fix: Add missing metadata fields #40

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
3f998c0
Add missing metadata fields
hermanschaaf Aug 14, 2023
edf4ae2
Add test
hermanschaaf Aug 14, 2023
b7c69b0
Fmt
hermanschaaf Aug 14, 2023
8136150
Merge main into branch
hermanschaaf Aug 14, 2023
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
2 changes: 2 additions & 0 deletions cloudquery/sdk/schema/arrow.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,3 +7,5 @@
METADATA_FALSE = b"false"
METADATA_TABLE_NAME = b"cq:table_name"
METADATA_TABLE_DESCRIPTION = b"cq:table_description"
METADATA_TABLE_TITLE = b"cq:table_title"
METADATA_TABLE_DEPENDS_ON = b"cq:table_depends_on"
20 changes: 18 additions & 2 deletions cloudquery/sdk/schema/table.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,20 +57,36 @@ def from_arrow_schema(cls, schema: pa.Schema) -> Table:
columns = []
for field in schema:
columns.append(Column.from_arrow_field(field))
parent = None
if arrow.METADATA_TABLE_DEPENDS_ON in schema.metadata:
parent = Table(
name=schema.metadata[arrow.METADATA_TABLE_DEPENDS_ON].decode("utf-8"),
columns=[],
)
return cls(
name=schema.metadata[arrow.METADATA_TABLE_NAME].decode("utf-8"),
name=schema.metadata.get(arrow.METADATA_TABLE_NAME, b"").decode("utf-8"),
title=schema.metadata.get(arrow.METADATA_TABLE_TITLE, b"").decode("utf-8"),
columns=columns,
description=schema.metadata.get(arrow.METADATA_TABLE_DESCRIPTION).decode(
"utf-8"
),
is_incremental=schema.metadata.get(
arrow.METADATA_INCREMENTAL, arrow.METADATA_FALSE
)
== arrow.METADATA_TRUE,
parent=parent,
)

def to_arrow_schema(self):
fields = []
md = {
arrow.METADATA_TABLE_NAME: self.name,
arrow.METADATA_TABLE_DESCRIPTION: self.description,
# arrow.METADATA_CONSTRAINT_NAME:
arrow.METADATA_TABLE_TITLE: self.title,
arrow.METADATA_TABLE_DEPENDS_ON: self.parent.name if self.parent else "",
arrow.METADATA_INCREMENTAL: arrow.METADATA_TRUE
if self.is_incremental
else arrow.METADATA_FALSE,
}
for column in self.columns:
fields.append(column.to_arrow_field())
Expand Down
18 changes: 16 additions & 2 deletions tests/schema/test_table.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,22 @@


def test_table():
table = Table("test_table", [Column("test_column", pa.int32())])
table.to_arrow_schema()
table = Table(
name="test_table",
columns=[Column("test_column", pa.int32())],
title="Test Table",
description="Test description",
parent=Table(name="parent_table", columns=[]),
relations=[],
is_incremental=True,
)
sch = table.to_arrow_schema()
got = Table.from_arrow_schema(sch)
assert got.name == table.name
assert got.title == table.title
assert got.description == table.description
assert got.is_incremental == table.is_incremental
assert got.parent.name == table.parent.name


def test_filter_dfs_warns_no_matches():
Expand Down