Use openhouse.dataloader namespace and correct PyIceberg import

integrations/python/dataloader/pyproject.toml

@@ -1,5 +1,9 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
 [project]
-name = "openhouse-dataloader"
+name = "openhouse.dataloader"
 version = "0.0.1"
 description = "A Python library for distributed data loading of OpenHouse tables"
 readme = "README.md"
@@ -9,6 +13,9 @@ dependencies = ["datafusion==51.0.0", "pyiceberg==0.10.0"]
 [project.optional-dependencies]
 dev = ["ruff>=0.9.0", "pytest>=8.0.0"]
 
+[tool.hatch.build.targets.wheel]
+packages = ["src/openhouse"]
+
 [tool.ruff]
 line-length = 120
 target-version = "py312"

integrations/python/dataloader/src/openhouse/dataloader/__init__.py

@@ -2,5 +2,5 @@
 
 from openhouse.dataloader.data_loader import DataLoaderContext, OpenHouseDataLoader
 
-__version__ = version("openhouse-dataloader")
+__version__ = version("openhouse.dataloader")
 __all__ = ["OpenHouseDataLoader", "DataLoaderContext"]

integrations/python/dataloader/src/openhouse/dataloader/data_loader_split.py

@@ -2,7 +2,7 @@
 
 from datafusion.plan import LogicalPlan
 from pyarrow import RecordBatch
-from pyiceberg.io import FileScanTask
+from pyiceberg.table import FileScanTask
 
 from openhouse.dataloader.udf_registry import UDFRegistry
 

integrations/python/dataloader/tests/test_data_loader.py

@@ -1,3 +1,16 @@
+from openhouse.dataloader import DataLoaderContext, OpenHouseDataLoader, __version__
+from openhouse.dataloader.data_loader_split import DataLoaderSplit
+
+
+def test_package_imports():
+    """Test that package imports work correctly"""
+    assert OpenHouseDataLoader is not None
+    assert DataLoaderContext is not None
+    assert DataLoaderSplit is not None
+    assert isinstance(__version__, str)
+    assert len(__version__) > 0
+
+
 def test_data_loader():
     """Test placeholder until real tests are added"""
     pass