This is an automated email from the ASF dual-hosted git repository.
fokko pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/iceberg-python.git
The following commit(s) were added to refs/heads/main by this push:
new da70e109 Fix StaticTable._metadata_location_from_version_hint metadata
location format ERROR (#2609)
da70e109 is described below
commit da70e10940c03697ae123ba98be109917b0751af
Author: chao qian <[email protected]>
AuthorDate: Mon Oct 20 21:47:37 2025 +0800
Fix StaticTable._metadata_location_from_version_hint metadata location
format ERROR (#2609)
<!--
Thanks for opening a pull request!
-->
<!-- In the case this PR will resolve an issue, please replace
${GITHUB_ISSUE_ID} below with the actual Github issue id. -->
# Rationale for this change
To fix StaticTable._metadata_location_from_version_hint metadata
location format ERROR:
```python
if content.endswith(".metadata.json"):
return os.path.join(metadata_location, "metadata", content)
elif content.isnumeric():
return os.path.join(metadata_location, "metadata",
"v%s.metadata.json").format(content)
else:
return os.path.join(metadata_location, "metadata",
"%s.metadata.json").format(content)
```
Closes #2608
## Are these changes tested?
Yes.
Added 2 more cases with numeric and non numeric metadata version hints.
## Are there any user-facing changes?
No
<!-- In the case of user-facing changes, please add the changelog label.
-->
---
pyiceberg/table/__init__.py | 4 ++--
tests/conftest.py | 29 +++++++++++++++++++++++++----
tests/table/test_init.py | 18 ++++++++++++++----
3 files changed, 41 insertions(+), 10 deletions(-)
diff --git a/pyiceberg/table/__init__.py b/pyiceberg/table/__init__.py
index d6433eea..8b7f4d16 100644
--- a/pyiceberg/table/__init__.py
+++ b/pyiceberg/table/__init__.py
@@ -1624,9 +1624,9 @@ class StaticTable(Table):
if content.endswith(".metadata.json"):
return os.path.join(metadata_location, "metadata", content)
elif content.isnumeric():
- return os.path.join(metadata_location, "metadata",
"v%s.metadata.json").format(content)
+ return os.path.join(metadata_location, "metadata",
f"v{content}.metadata.json")
else:
- return os.path.join(metadata_location, "metadata",
"%s.metadata.json").format(content)
+ return os.path.join(metadata_location, "metadata",
f"{content}.metadata.json")
@classmethod
def from_metadata(cls, metadata_location: str, properties: Properties =
EMPTY_DICT) -> StaticTable:
diff --git a/tests/conftest.py b/tests/conftest.py
index 2b571d73..21f33858 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -1135,22 +1135,43 @@ def example_table_metadata_v3() -> Dict[str, Any]:
return EXAMPLE_TABLE_METADATA_V3
[email protected](scope="session")
-def table_location(tmp_path_factory: pytest.TempPathFactory) -> str:
+def generate_table_location_with_version_hint(
+ tmp_path_factory: pytest.TempPathFactory, content_in_version_hint: str,
metadata_filename: str
+) -> str:
from pyiceberg.io.pyarrow import PyArrowFileIO
- metadata_filename = f"{uuid.uuid4()}.metadata.json"
metadata_location = str(tmp_path_factory.getbasetemp() / "metadata" /
metadata_filename)
version_hint_location = str(tmp_path_factory.getbasetemp() / "metadata" /
"version-hint.text")
metadata = TableMetadataV2(**EXAMPLE_TABLE_METADATA_V2)
ToOutputFile.table_metadata(metadata,
PyArrowFileIO().new_output(location=metadata_location), overwrite=True)
with
PyArrowFileIO().new_output(location=version_hint_location).create(overwrite=True)
as s:
- s.write(metadata_filename.encode("utf-8"))
+ s.write(content_in_version_hint.encode("utf-8"))
return str(tmp_path_factory.getbasetemp())
[email protected](scope="session")
+def table_location_with_version_hint_full(tmp_path_factory:
pytest.TempPathFactory) -> str:
+ content_in_version_hint = str(uuid.uuid4())
+ metadata_filename = f"{content_in_version_hint}.metadata.json"
+ return generate_table_location_with_version_hint(tmp_path_factory,
content_in_version_hint, metadata_filename)
+
+
[email protected](scope="session")
+def table_location_with_version_hint_numeric(tmp_path_factory:
pytest.TempPathFactory) -> str:
+ content_in_version_hint = "1234567890"
+ metadata_filename = f"v{content_in_version_hint}.metadata.json"
+ return generate_table_location_with_version_hint(tmp_path_factory,
content_in_version_hint, metadata_filename)
+
+
[email protected](scope="session")
+def table_location_with_version_hint_non_numeric(tmp_path_factory:
pytest.TempPathFactory) -> str:
+ content_in_version_hint = "non_numberic"
+ metadata_filename = f"{content_in_version_hint}.metadata.json"
+ return generate_table_location_with_version_hint(tmp_path_factory,
content_in_version_hint, metadata_filename)
+
+
@pytest.fixture(scope="session")
def metadata_location(tmp_path_factory: pytest.TempPathFactory) -> str:
from pyiceberg.io.pyarrow import PyArrowFileIO
diff --git a/tests/table/test_init.py b/tests/table/test_init.py
index 5f64738d..95c5d822 100644
--- a/tests/table/test_init.py
+++ b/tests/table/test_init.py
@@ -356,10 +356,20 @@ def test_static_table_gz_same_as_table(table_v2: Table,
metadata_location_gz: st
assert static_table.metadata == table_v2.metadata
-def test_static_table_version_hint_same_as_table(table_v2: Table,
table_location: str) -> None:
- static_table = StaticTable.from_metadata(table_location)
- assert isinstance(static_table, Table)
- assert static_table.metadata == table_v2.metadata
+def test_static_table_version_hint_same_as_table(
+ table_v2: Table,
+ table_location_with_version_hint_full: str,
+ table_location_with_version_hint_numeric: str,
+ table_location_with_version_hint_non_numeric: str,
+) -> None:
+ for table_location in [
+ table_location_with_version_hint_full,
+ table_location_with_version_hint_numeric,
+ table_location_with_version_hint_non_numeric,
+ ]:
+ static_table = StaticTable.from_metadata(table_location)
+ assert isinstance(static_table, Table)
+ assert static_table.metadata == table_v2.metadata
def test_static_table_io_does_not_exist(metadata_location: str) -> None:
