Merge branch 'main' into up037

Author: kevinjqliu

Makefile

@@ -32,9 +32,9 @@ else
 endif
 
 ifeq ($(COVERAGE),1)
-  TEST_RUNNER = uv run python -m coverage run --parallel-mode --source=pyiceberg -m
+  TEST_RUNNER = uv run $(PYTHON_ARG) python -m coverage run --parallel-mode --source=pyiceberg -m
 else
-  TEST_RUNNER = uv run python -m
+  TEST_RUNNER = uv run $(PYTHON_ARG) python -m
 endif
 
 ifeq ($(KEEP_COMPOSE),1)
@@ -70,7 +70,7 @@ setup-venv: ## Create virtual environment
 	uv venv $(PYTHON_ARG)
 
 install-dependencies: setup-venv ## Install all dependencies including extras
-	uv sync --all-extras
+	uv sync $(PYTHON_ARG) --all-extras
 
 install: install-uv install-dependencies ## Install uv and dependencies
 
@@ -84,7 +84,7 @@ check-license: ## Check license headers
 	./dev/check-license
 
 lint: ## Run code linters via prek (pre-commit hooks)
-	uv run prek run -a
+	uv run $(PYTHON_ARG) prek run -a
 
 # ===============
 # Testing Section
@@ -101,7 +101,7 @@ test-integration-setup: ## Start Docker services for integration tests
 	docker compose -f dev/docker-compose-integration.yml kill
 	docker compose -f dev/docker-compose-integration.yml rm -f
 	docker compose -f dev/docker-compose-integration.yml up -d --wait
-	uv run python dev/provision.py
+	uv run $(PYTHON_ARG) python dev/provision.py
 
 test-integration-exec: ## Run integration tests (excluding provision)
 	$(TEST_RUNNER) pytest tests/ -m integration $(PYTEST_ARGS)
@@ -133,10 +133,10 @@ test-coverage: COVERAGE=1
 test-coverage: test test-integration test-s3 test-adls test-gcs coverage-report ## Run all tests with coverage and report
 
 coverage-report: ## Combine and report coverage
-	uv run coverage combine
-	uv run coverage report -m --fail-under=$(COVERAGE_FAIL_UNDER)
-	uv run coverage html
-	uv run coverage xml
+	uv run $(PYTHON_ARG) coverage combine
+	uv run $(PYTHON_ARG) coverage report -m --fail-under=$(COVERAGE_FAIL_UNDER)
+	uv run $(PYTHON_ARG) coverage html
+	uv run $(PYTHON_ARG) coverage xml
 
 # ================
 # Documentation
@@ -145,13 +145,13 @@ coverage-report: ## Combine and report coverage
 ##@ Documentation
 
 docs-install: ## Install docs dependencies (included in default groups)
-	uv sync --group docs
+	uv sync $(PYTHON_ARG) --group docs
 
 docs-serve: ## Serve local docs preview (hot reload)
-	uv run mkdocs serve -f mkdocs/mkdocs.yml
+	uv run $(PYTHON_ARG) mkdocs serve -f mkdocs/mkdocs.yml
 
 docs-build: ## Build the static documentation site
-	uv run mkdocs build -f mkdocs/mkdocs.yml --strict
+	uv run $(PYTHON_ARG) mkdocs build -f mkdocs/mkdocs.yml --strict
 
 # ===================
 # Project Maintenance

dev/.rat-excludes

@@ -5,5 +5,3 @@ build
 .gitignore
 uv.lock
 mkdocs/*
-setup.cfg
-(^|.*/)[^/]*\.egg-info(/.*)?$

pyiceberg/avro/decoder.py

@@ -181,6 +181,6 @@ def new_decoder(b: bytes) -> BinaryDecoder:
     except ModuleNotFoundError:
         import warnings
 
-        warnings.warn("Falling back to pure Python Avro decoder, missing Cython implementation")
+        warnings.warn("Falling back to pure Python Avro decoder, missing Cython implementation", stacklevel=2)
 
         return StreamingBinaryDecoder(b)

pyiceberg/expressions/__init__.py

@@ -131,7 +131,7 @@ class Term(Generic[L], ABC):
     """A simple expression that evaluates to a value."""
 
 
-class Bound(ABC):
+class Bound:
     """Represents a bound value expression."""
 
 

pyiceberg/io/__init__.py

@@ -340,7 +340,7 @@ def _infer_file_io_from_scheme(path: str, properties: Properties) -> FileIO | No
                 if file_io := _import_file_io(file_io_path, properties):
                     return file_io
         else:
-            warnings.warn(f"No preferred file implementation for scheme: {parsed_url.scheme}")
+            warnings.warn(f"No preferred file implementation for scheme: {parsed_url.scheme}", stacklevel=2)
     return None
 
 

pyiceberg/io/pyarrow.py

@@ -232,7 +232,7 @@ def _import_retry_strategy(impl: str) -> S3RetryStrategy | None:
         class_ = getattr(module, class_name)
         return class_()
     except (ModuleNotFoundError, AttributeError):
-        warnings.warn(f"Could not initialize S3 retry strategy: {impl}")
+        warnings.warn(f"Could not initialize S3 retry strategy: {impl}", stacklevel=2)
         return None
 
 
@@ -2768,7 +2768,7 @@ def _get_parquet_writer_kwargs(table_properties: Properties) -> Dict[str, Any]:
         f"{TableProperties.PARQUET_BLOOM_FILTER_COLUMN_ENABLED_PREFIX}.*",
     ]:
         if unsupported_keys := fnmatch.filter(table_properties, key_pattern):
-            warnings.warn(f"Parquet writer option(s) {unsupported_keys} not implemented")
+            warnings.warn(f"Parquet writer option(s) {unsupported_keys} not implemented", stacklevel=2)
 
     compression_codec = table_properties.get(TableProperties.PARQUET_COMPRESSION, TableProperties.PARQUET_COMPRESSION_DEFAULT)
     compression_level = property_as_int(

pyiceberg/table/__init__.py

@@ -663,7 +663,7 @@ def delete(
             self.table_metadata.properties.get(TableProperties.DELETE_MODE, TableProperties.DELETE_MODE_DEFAULT)
             == TableProperties.DELETE_MODE_MERGE_ON_READ
         ):
-            warnings.warn("Merge on read is not yet supported, falling back to copy-on-write")
+            warnings.warn("Merge on read is not yet supported, falling back to copy-on-write", stacklevel=2)
 
         if isinstance(delete_filter, str):
             delete_filter = _parse_row_filter(delete_filter)
@@ -731,7 +731,7 @@ def delete(
                             overwrite_snapshot.append_data_file(replaced_data_file)
 
         if not delete_snapshot.files_affected and not delete_snapshot.rewrites_needed:
-            warnings.warn("Delete operation did not match any records")
+            warnings.warn("Delete operation did not match any records", stacklevel=2)
 
     def upsert(
         self,
@@ -1502,7 +1502,7 @@ def _do_commit(self, updates: Tuple[TableUpdate, ...], requirements: Tuple[Table
         try:
             self.catalog._delete_old_metadata(self.io, self.metadata, response.metadata)
         except Exception as e:
-            warnings.warn(f"Failed to delete old metadata after commit: {e}")
+            warnings.warn(f"Failed to delete old metadata after commit: {e}", stacklevel=2)
 
         self.metadata = response.metadata
         self.metadata_location = response.metadata_location
@@ -1728,7 +1728,7 @@ def projection(self) -> Schema:
                             schema for schema in self.table_metadata.schemas if schema.schema_id == snapshot.schema_id
                         )
                     except StopIteration:
-                        warnings.warn(f"Metadata does not contain schema with id: {snapshot.schema_id}")
+                        warnings.warn(f"Metadata does not contain schema with id: {snapshot.schema_id}", stacklevel=2)
             else:
                 raise ValueError(f"Snapshot not found: {self.snapshot_id}")
 
@@ -1783,7 +1783,7 @@ def with_case_sensitive(self: S, case_sensitive: bool = True) -> S:
     def count(self) -> int: ...
 
 
-class ScanTask(ABC):
+class ScanTask:
     pass
 
 

pyiceberg/table/snapshots.py

@@ -187,7 +187,7 @@ class Summary(IcebergBaseModel, Mapping[str, str]):
 
     def __init__(self, operation: Operation | None = None, **data: Any) -> None:
         if operation is None:
-            warnings.warn("Encountered invalid snapshot summary: operation is missing, defaulting to overwrite")
+            warnings.warn("Encountered invalid snapshot summary: operation is missing, defaulting to overwrite", stacklevel=2)
             operation = Operation.OVERWRITE
         super().__init__(operation=operation, **data)
         self._additional_properties = data

pyproject.toml

@@ -45,6 +45,13 @@ dependencies = [
     "zstandard>=0.13.0,<1.0.0"
 ]
 
+[project.urls]
+Homepage = "https://py.iceberg.apache.org/"
+Repository = "https://github.com/apache/iceberg-python"
+
+[project.scripts]
+pyiceberg = "pyiceberg.cli.console:run"
+
 [project.optional-dependencies]
 pyarrow = [
     "pyarrow>=17.0.0",
@@ -93,13 +100,6 @@ pyiceberg-core = ["pyiceberg-core>=0.5.1,<0.8.0"]
 datafusion = ["datafusion>=45,<49"]
 gcp-auth = ["google-auth>=2.4.0"]
 
-[project.urls]
-Homepage = "https://py.iceberg.apache.org/"
-Repository = "https://github.com/apache/iceberg-python"
-
-[project.scripts]
-pyiceberg = "pyiceberg.cli.console:run"
-
 [dependency-groups]
 dev = [
     "pytest==7.4.4",

ruff.toml

@@ -59,8 +59,6 @@ select = [
 ]
 ignore = [
     "E501",
-    "B024",
-    "B028",
     "UP035",
     "UP006"
 ]