acryl-datahub-cloud 0.3.14.1rc3__tar.gz → 0.3.14.1rc5__tar.gz

{acryl_datahub_cloud-0.3.14.1rc3 → acryl_datahub_cloud-0.3.14.1rc5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: acryl-datahub-cloud
-Version: 0.3.14.1rc3
+Version: 0.3.14.1rc5
 Requires-Python: >=3.10
 Requires-Dist: avro-gen3==0.7.16
 Requires-Dist: acryl-datahub
@@ -9,93 +9,93 @@ Requires-Dist: pytz
 Requires-Dist: types-croniter
 Requires-Dist: tzlocal
 Provides-Extra: datahub-lineage-features
-Requires-Dist: pandas; extra == "datahub-lineage-features"
-Requires-Dist: pydantic<2; extra == "datahub-lineage-features"
+Requires-Dist: tenacity; extra == "datahub-lineage-features"
 Requires-Dist: pyarrow; extra == "datahub-lineage-features"
-Requires-Dist: duckdb; extra == "datahub-lineage-features"
 Requires-Dist: opensearch-py==2.4.2; extra == "datahub-lineage-features"
-Requires-Dist: tenacity; extra == "datahub-lineage-features"
+Requires-Dist: duckdb; extra == "datahub-lineage-features"
+Requires-Dist: pandas; extra == "datahub-lineage-features"
+Requires-Dist: pydantic<2; extra == "datahub-lineage-features"
 Provides-Extra: datahub-reporting-forms
-Requires-Dist: pandas; extra == "datahub-reporting-forms"
-Requires-Dist: pydantic<2; extra == "datahub-reporting-forms"
 Requires-Dist: pyarrow; extra == "datahub-reporting-forms"
 Requires-Dist: boto3; extra == "datahub-reporting-forms"
-Requires-Dist: duckdb; extra == "datahub-reporting-forms"
 Requires-Dist: termcolor==2.5.0; extra == "datahub-reporting-forms"
+Requires-Dist: duckdb; extra == "datahub-reporting-forms"
+Requires-Dist: pandas; extra == "datahub-reporting-forms"
+Requires-Dist: pydantic<2; extra == "datahub-reporting-forms"
 Provides-Extra: datahub-reporting-extract-graph
-Requires-Dist: pandas; extra == "datahub-reporting-extract-graph"
-Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-graph"
 Requires-Dist: pyarrow; extra == "datahub-reporting-extract-graph"
 Requires-Dist: boto3; extra == "datahub-reporting-extract-graph"
-Requires-Dist: duckdb; extra == "datahub-reporting-extract-graph"
 Requires-Dist: opensearch-py==2.4.2; extra == "datahub-reporting-extract-graph"
+Requires-Dist: duckdb; extra == "datahub-reporting-extract-graph"
+Requires-Dist: pandas; extra == "datahub-reporting-extract-graph"
+Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-graph"
 Provides-Extra: datahub-reporting-extract-sql
-Requires-Dist: pandas; extra == "datahub-reporting-extract-sql"
-Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-sql"
 Requires-Dist: pyarrow; extra == "datahub-reporting-extract-sql"
 Requires-Dist: boto3; extra == "datahub-reporting-extract-sql"
 Requires-Dist: duckdb; extra == "datahub-reporting-extract-sql"
+Requires-Dist: pandas; extra == "datahub-reporting-extract-sql"
+Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-sql"
 Provides-Extra: datahub-usage-reporting
-Requires-Dist: pandas; extra == "datahub-usage-reporting"
-Requires-Dist: elasticsearch==7.13.4; extra == "datahub-usage-reporting"
-Requires-Dist: pyarrow<=18.0.0; extra == "datahub-usage-reporting"
-Requires-Dist: termcolor==2.5.0; extra == "datahub-usage-reporting"
-Requires-Dist: pydantic<2; extra == "datahub-usage-reporting"
 Requires-Dist: pyarrow; extra == "datahub-usage-reporting"
 Requires-Dist: boto3; extra == "datahub-usage-reporting"
-Requires-Dist: scipy<=1.14.1; extra == "datahub-usage-reporting"
-Requires-Dist: polars==1.30.0; extra == "datahub-usage-reporting"
-Requires-Dist: duckdb; extra == "datahub-usage-reporting"
 Requires-Dist: opensearch-py==2.4.2; extra == "datahub-usage-reporting"
+Requires-Dist: duckdb; extra == "datahub-usage-reporting"
 Requires-Dist: numpy<2; extra == "datahub-usage-reporting"
+Requires-Dist: termcolor==2.5.0; extra == "datahub-usage-reporting"
+Requires-Dist: scipy<=1.14.1; extra == "datahub-usage-reporting"
+Requires-Dist: polars==1.30.0; extra == "datahub-usage-reporting"
+Requires-Dist: pyarrow<=18.0.0; extra == "datahub-usage-reporting"
+Requires-Dist: pandas; extra == "datahub-usage-reporting"
+Requires-Dist: elasticsearch==7.13.4; extra == "datahub-usage-reporting"
+Requires-Dist: pydantic<2; extra == "datahub-usage-reporting"
 Provides-Extra: datahub-metadata-sharing
 Requires-Dist: tenacity; extra == "datahub-metadata-sharing"
 Provides-Extra: datahub-action-request-owner
 Requires-Dist: tenacity; extra == "datahub-action-request-owner"
 Provides-Extra: acryl-cs-issues
-Requires-Dist: zenpy; extra == "acryl-cs-issues"
-Requires-Dist: slack-sdk; extra == "acryl-cs-issues"
 Requires-Dist: openai; extra == "acryl-cs-issues"
+Requires-Dist: zenpy; extra == "acryl-cs-issues"
 Requires-Dist: jinja2; extra == "acryl-cs-issues"
+Requires-Dist: slack-sdk; extra == "acryl-cs-issues"
 Provides-Extra: datahub-forms-notifications
 Requires-Dist: tenacity; extra == "datahub-forms-notifications"
 Provides-Extra: all
-Requires-Dist: slack-sdk; extra == "all"
-Requires-Dist: openai; extra == "all"
-Requires-Dist: polars==1.30.0; extra == "all"
 Requires-Dist: tenacity; extra == "all"
-Requires-Dist: zenpy; extra == "all"
-Requires-Dist: pandas; extra == "all"
-Requires-Dist: elasticsearch==7.13.4; extra == "all"
-Requires-Dist: pyarrow<=18.0.0; extra == "all"
-Requires-Dist: termcolor==2.5.0; extra == "all"
-Requires-Dist: jinja2; extra == "all"
-Requires-Dist: pydantic<2; extra == "all"
-Requires-Dist: pyarrow; extra == "all"
 Requires-Dist: boto3; extra == "all"
-Requires-Dist: scipy<=1.14.1; extra == "all"
-Requires-Dist: numpy<2; extra == "all"
+Requires-Dist: slack-sdk; extra == "all"
 Requires-Dist: duckdb; extra == "all"
+Requires-Dist: numpy<2; extra == "all"
+Requires-Dist: scipy<=1.14.1; extra == "all"
+Requires-Dist: pyarrow<=18.0.0; extra == "all"
+Requires-Dist: elasticsearch==7.13.4; extra == "all"
+Requires-Dist: pandas; extra == "all"
+Requires-Dist: zenpy; extra == "all"
+Requires-Dist: pyarrow; extra == "all"
 Requires-Dist: opensearch-py==2.4.2; extra == "all"
+Requires-Dist: openai; extra == "all"
+Requires-Dist: jinja2; extra == "all"
+Requires-Dist: termcolor==2.5.0; extra == "all"
+Requires-Dist: polars==1.30.0; extra == "all"
+Requires-Dist: pydantic<2; extra == "all"
 Provides-Extra: dev
-Requires-Dist: pandas; extra == "dev"
-Requires-Dist: acryl-datahub[dev]; extra == "dev"
-Requires-Dist: slack-sdk; extra == "dev"
-Requires-Dist: elasticsearch==7.13.4; extra == "dev"
-Requires-Dist: pyarrow<=18.0.0; extra == "dev"
-Requires-Dist: termcolor==2.5.0; extra == "dev"
+Requires-Dist: tenacity; extra == "dev"
 Requires-Dist: zenpy; extra == "dev"
-Requires-Dist: jinja2; extra == "dev"
-Requires-Dist: openai; extra == "dev"
-Requires-Dist: pydantic<2; extra == "dev"
 Requires-Dist: pyarrow; extra == "dev"
 Requires-Dist: boto3; extra == "dev"
+Requires-Dist: opensearch-py==2.4.2; extra == "dev"
+Requires-Dist: slack-sdk; extra == "dev"
+Requires-Dist: openai; extra == "dev"
+Requires-Dist: duckdb; extra == "dev"
+Requires-Dist: numpy<2; extra == "dev"
+Requires-Dist: elasticsearch==7.13.4; extra == "dev"
+Requires-Dist: jinja2; extra == "dev"
+Requires-Dist: termcolor==2.5.0; extra == "dev"
 Requires-Dist: scipy<=1.14.1; extra == "dev"
 Requires-Dist: polars==1.30.0; extra == "dev"
-Requires-Dist: numpy<2; extra == "dev"
-Requires-Dist: duckdb; extra == "dev"
-Requires-Dist: opensearch-py==2.4.2; extra == "dev"
-Requires-Dist: tenacity; extra == "dev"
+Requires-Dist: pyarrow<=18.0.0; extra == "dev"
+Requires-Dist: pandas; extra == "dev"
+Requires-Dist: acryl-datahub[dev]; extra == "dev"
+Requires-Dist: pydantic<2; extra == "dev"
 Dynamic: provides-extra
 Dynamic: requires-dist
 Dynamic: requires-python

{acryl_datahub_cloud-0.3.14.1rc3 → acryl_datahub_cloud-0.3.14.1rc5}/src/acryl_datahub_cloud/_codegen_config.json

@@ -1,6 +1,6 @@
 {
   "name": "acryl-datahub-cloud",
-  "version": "0.3.14.1rc3",
+  "version": "0.3.14.1rc5",
   "install_requires": [
     "avro-gen3==0.7.16",
     "acryl-datahub"

{acryl_datahub_cloud-0.3.14.1rc3 → acryl_datahub_cloud-0.3.14.1rc5}/src/acryl_datahub_cloud/datahub_reporting/datahub_dataset.py

@@ -271,7 +271,7 @@ class DataHubBasedS3Dataset:
             )
 
     def _generate_schema_metadata(
-        self, duckdb_columns: List[Tuple[str, str]]
+        self, duckdb_columns: List[Tuple[str, Any]]
     ) -> SchemaMetadataClass:
         def get_type_from_dtype(dtype: str) -> SchemaFieldDataTypeClass:
             if "int" in dtype or "float" in dtype or "number" in dtype:
@@ -302,7 +302,7 @@ class DataHubBasedS3Dataset:
         )
         for column in duckdb_columns:
             # generate data type
-            data_type = column[1].lower()
+            data_type = str(column[1]).lower()
             schema_metadata.fields.append(
                 SchemaFieldClass(
                     fieldPath=column[0],
@@ -341,7 +341,7 @@ class DataHubBasedS3Dataset:
                 # generate min, max, avg, distinct count, null count
                 column_name = column[0]
                 logger.info(f"Generating field profile for {column_name}")
-                data_type = column[1].lower()
+                data_type = str(column[1]).lower()
                 if "int" in data_type or "float" in data_type:
                     query = (
                         f"SELECT COUNT(DISTINCT {column_name}), COUNT(*) - COUNT({column_name}), MIN({column_name}), MAX({column_name}), AVG({column_name})"

{acryl_datahub_cloud-0.3.14.1rc3 → acryl_datahub_cloud-0.3.14.1rc5}/src/acryl_datahub_cloud.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: acryl-datahub-cloud
-Version: 0.3.14.1rc3
+Version: 0.3.14.1rc5
 Requires-Python: >=3.10
 Requires-Dist: avro-gen3==0.7.16
 Requires-Dist: acryl-datahub
@@ -9,93 +9,93 @@ Requires-Dist: pytz
 Requires-Dist: types-croniter
 Requires-Dist: tzlocal
 Provides-Extra: datahub-lineage-features
-Requires-Dist: pandas; extra == "datahub-lineage-features"
-Requires-Dist: pydantic<2; extra == "datahub-lineage-features"
+Requires-Dist: tenacity; extra == "datahub-lineage-features"
 Requires-Dist: pyarrow; extra == "datahub-lineage-features"
-Requires-Dist: duckdb; extra == "datahub-lineage-features"
 Requires-Dist: opensearch-py==2.4.2; extra == "datahub-lineage-features"
-Requires-Dist: tenacity; extra == "datahub-lineage-features"
+Requires-Dist: duckdb; extra == "datahub-lineage-features"
+Requires-Dist: pandas; extra == "datahub-lineage-features"
+Requires-Dist: pydantic<2; extra == "datahub-lineage-features"
 Provides-Extra: datahub-reporting-forms
-Requires-Dist: pandas; extra == "datahub-reporting-forms"
-Requires-Dist: pydantic<2; extra == "datahub-reporting-forms"
 Requires-Dist: pyarrow; extra == "datahub-reporting-forms"
 Requires-Dist: boto3; extra == "datahub-reporting-forms"
-Requires-Dist: duckdb; extra == "datahub-reporting-forms"
 Requires-Dist: termcolor==2.5.0; extra == "datahub-reporting-forms"
+Requires-Dist: duckdb; extra == "datahub-reporting-forms"
+Requires-Dist: pandas; extra == "datahub-reporting-forms"
+Requires-Dist: pydantic<2; extra == "datahub-reporting-forms"
 Provides-Extra: datahub-reporting-extract-graph
-Requires-Dist: pandas; extra == "datahub-reporting-extract-graph"
-Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-graph"
 Requires-Dist: pyarrow; extra == "datahub-reporting-extract-graph"
 Requires-Dist: boto3; extra == "datahub-reporting-extract-graph"
-Requires-Dist: duckdb; extra == "datahub-reporting-extract-graph"
 Requires-Dist: opensearch-py==2.4.2; extra == "datahub-reporting-extract-graph"
+Requires-Dist: duckdb; extra == "datahub-reporting-extract-graph"
+Requires-Dist: pandas; extra == "datahub-reporting-extract-graph"
+Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-graph"
 Provides-Extra: datahub-reporting-extract-sql
-Requires-Dist: pandas; extra == "datahub-reporting-extract-sql"
-Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-sql"
 Requires-Dist: pyarrow; extra == "datahub-reporting-extract-sql"
 Requires-Dist: boto3; extra == "datahub-reporting-extract-sql"
 Requires-Dist: duckdb; extra == "datahub-reporting-extract-sql"
+Requires-Dist: pandas; extra == "datahub-reporting-extract-sql"
+Requires-Dist: pydantic<2; extra == "datahub-reporting-extract-sql"
 Provides-Extra: datahub-usage-reporting
-Requires-Dist: pandas; extra == "datahub-usage-reporting"
-Requires-Dist: elasticsearch==7.13.4; extra == "datahub-usage-reporting"
-Requires-Dist: pyarrow<=18.0.0; extra == "datahub-usage-reporting"
-Requires-Dist: termcolor==2.5.0; extra == "datahub-usage-reporting"
-Requires-Dist: pydantic<2; extra == "datahub-usage-reporting"
 Requires-Dist: pyarrow; extra == "datahub-usage-reporting"
 Requires-Dist: boto3; extra == "datahub-usage-reporting"
-Requires-Dist: scipy<=1.14.1; extra == "datahub-usage-reporting"
-Requires-Dist: polars==1.30.0; extra == "datahub-usage-reporting"
-Requires-Dist: duckdb; extra == "datahub-usage-reporting"
 Requires-Dist: opensearch-py==2.4.2; extra == "datahub-usage-reporting"
+Requires-Dist: duckdb; extra == "datahub-usage-reporting"
 Requires-Dist: numpy<2; extra == "datahub-usage-reporting"
+Requires-Dist: termcolor==2.5.0; extra == "datahub-usage-reporting"
+Requires-Dist: scipy<=1.14.1; extra == "datahub-usage-reporting"
+Requires-Dist: polars==1.30.0; extra == "datahub-usage-reporting"
+Requires-Dist: pyarrow<=18.0.0; extra == "datahub-usage-reporting"
+Requires-Dist: pandas; extra == "datahub-usage-reporting"
+Requires-Dist: elasticsearch==7.13.4; extra == "datahub-usage-reporting"
+Requires-Dist: pydantic<2; extra == "datahub-usage-reporting"
 Provides-Extra: datahub-metadata-sharing
 Requires-Dist: tenacity; extra == "datahub-metadata-sharing"
 Provides-Extra: datahub-action-request-owner
 Requires-Dist: tenacity; extra == "datahub-action-request-owner"
 Provides-Extra: acryl-cs-issues
-Requires-Dist: zenpy; extra == "acryl-cs-issues"
-Requires-Dist: slack-sdk; extra == "acryl-cs-issues"
 Requires-Dist: openai; extra == "acryl-cs-issues"
+Requires-Dist: zenpy; extra == "acryl-cs-issues"
 Requires-Dist: jinja2; extra == "acryl-cs-issues"
+Requires-Dist: slack-sdk; extra == "acryl-cs-issues"
 Provides-Extra: datahub-forms-notifications
 Requires-Dist: tenacity; extra == "datahub-forms-notifications"
 Provides-Extra: all
-Requires-Dist: slack-sdk; extra == "all"
-Requires-Dist: openai; extra == "all"
-Requires-Dist: polars==1.30.0; extra == "all"
 Requires-Dist: tenacity; extra == "all"
-Requires-Dist: zenpy; extra == "all"
-Requires-Dist: pandas; extra == "all"
-Requires-Dist: elasticsearch==7.13.4; extra == "all"
-Requires-Dist: pyarrow<=18.0.0; extra == "all"
-Requires-Dist: termcolor==2.5.0; extra == "all"
-Requires-Dist: jinja2; extra == "all"
-Requires-Dist: pydantic<2; extra == "all"
-Requires-Dist: pyarrow; extra == "all"
 Requires-Dist: boto3; extra == "all"
-Requires-Dist: scipy<=1.14.1; extra == "all"
-Requires-Dist: numpy<2; extra == "all"
+Requires-Dist: slack-sdk; extra == "all"
 Requires-Dist: duckdb; extra == "all"
+Requires-Dist: numpy<2; extra == "all"
+Requires-Dist: scipy<=1.14.1; extra == "all"
+Requires-Dist: pyarrow<=18.0.0; extra == "all"
+Requires-Dist: elasticsearch==7.13.4; extra == "all"
+Requires-Dist: pandas; extra == "all"
+Requires-Dist: zenpy; extra == "all"
+Requires-Dist: pyarrow; extra == "all"
 Requires-Dist: opensearch-py==2.4.2; extra == "all"
+Requires-Dist: openai; extra == "all"
+Requires-Dist: jinja2; extra == "all"
+Requires-Dist: termcolor==2.5.0; extra == "all"
+Requires-Dist: polars==1.30.0; extra == "all"
+Requires-Dist: pydantic<2; extra == "all"
 Provides-Extra: dev
-Requires-Dist: pandas; extra == "dev"
-Requires-Dist: acryl-datahub[dev]; extra == "dev"
-Requires-Dist: slack-sdk; extra == "dev"
-Requires-Dist: elasticsearch==7.13.4; extra == "dev"
-Requires-Dist: pyarrow<=18.0.0; extra == "dev"
-Requires-Dist: termcolor==2.5.0; extra == "dev"
+Requires-Dist: tenacity; extra == "dev"
 Requires-Dist: zenpy; extra == "dev"
-Requires-Dist: jinja2; extra == "dev"
-Requires-Dist: openai; extra == "dev"
-Requires-Dist: pydantic<2; extra == "dev"
 Requires-Dist: pyarrow; extra == "dev"
 Requires-Dist: boto3; extra == "dev"
+Requires-Dist: opensearch-py==2.4.2; extra == "dev"
+Requires-Dist: slack-sdk; extra == "dev"
+Requires-Dist: openai; extra == "dev"
+Requires-Dist: duckdb; extra == "dev"
+Requires-Dist: numpy<2; extra == "dev"
+Requires-Dist: elasticsearch==7.13.4; extra == "dev"
+Requires-Dist: jinja2; extra == "dev"
+Requires-Dist: termcolor==2.5.0; extra == "dev"
 Requires-Dist: scipy<=1.14.1; extra == "dev"
 Requires-Dist: polars==1.30.0; extra == "dev"
-Requires-Dist: numpy<2; extra == "dev"
-Requires-Dist: duckdb; extra == "dev"
-Requires-Dist: opensearch-py==2.4.2; extra == "dev"
-Requires-Dist: tenacity; extra == "dev"
+Requires-Dist: pyarrow<=18.0.0; extra == "dev"
+Requires-Dist: pandas; extra == "dev"
+Requires-Dist: acryl-datahub[dev]; extra == "dev"
+Requires-Dist: pydantic<2; extra == "dev"
 Dynamic: provides-extra
 Dynamic: requires-dist
 Dynamic: requires-python

{acryl_datahub_cloud-0.3.14.1rc3 → acryl_datahub_cloud-0.3.14.1rc5}/src/acryl_datahub_cloud.egg-info/SOURCES.txt

@@ -485,6 +485,7 @@ src/acryl_datahub_cloud/sdk/entities/__init__.py
 src/acryl_datahub_cloud/sdk/entities/assertion.py
 src/acryl_datahub_cloud/sdk/entities/monitor.py
 src/acryl_datahub_cloud/sdk/entities/subscription.py
+tests/test_datahub_dataset.py
 tests/test_datahub_form_reporting.py
 tests/test_datahub_restore.py
 tests/test_forms_notifications_source.py

acryl_datahub_cloud-0.3.14.1rc5/tests/test_datahub_dataset.py

@@ -0,0 +1,127 @@
+from unittest.mock import patch
+
+import pytest
+
+from acryl_datahub_cloud.datahub_reporting.datahub_dataset import (
+    DataHubBasedS3Dataset,
+    DatasetMetadata,
+    FileStoreBackedDatasetConfig,
+)
+
+
+class MockDuckDBType:
+    """Mock DuckDB type object that doesn't have a lower() method"""
+
+    def __init__(self, type_name: str):
+        self.type_name = type_name
+
+    def __str__(self) -> str:
+        return self.type_name
+
+
+@pytest.fixture
+def mock_config() -> FileStoreBackedDatasetConfig:
+    return FileStoreBackedDatasetConfig(
+        dataset_name="test_dataset",
+        bucket_prefix="s3://test-bucket/test-prefix",
+        store_platform="s3",
+    )
+
+
+@pytest.fixture
+def mock_dataset_metadata() -> DatasetMetadata:
+    return DatasetMetadata(
+        displayName="Test Dataset",
+        description="Test dataset for unit tests",
+    )
+
+
+@pytest.fixture
+def dataset(
+    mock_config: FileStoreBackedDatasetConfig, mock_dataset_metadata: DatasetMetadata
+) -> DataHubBasedS3Dataset:
+    with patch("boto3.client"):
+        return DataHubBasedS3Dataset(mock_config, mock_dataset_metadata)
+
+
+def test_generate_schema_metadata_with_string_types(
+    dataset: DataHubBasedS3Dataset,
+) -> None:
+    """Test that _generate_schema_metadata handles string column types correctly"""
+    # Test with string types (old behavior)
+    duckdb_columns = [
+        ("column1", "VARCHAR"),
+        ("column2", "INTEGER"),
+        ("column3", "DOUBLE"),
+    ]
+
+    schema_metadata = dataset._generate_schema_metadata(duckdb_columns)
+
+    assert len(schema_metadata.fields) == 3
+    assert schema_metadata.fields[0].fieldPath == "column1"
+    assert schema_metadata.fields[1].fieldPath == "column2"
+    assert schema_metadata.fields[2].fieldPath == "column3"
+
+
+def test_generate_schema_metadata_with_duckdb_type_objects(
+    dataset: DataHubBasedS3Dataset,
+) -> None:
+    """Test that _generate_schema_metadata handles DuckDB type objects correctly"""
+    # Test with DuckDB type objects (new behavior that caused the bug)
+    duckdb_columns = [
+        ("column1", MockDuckDBType("VARCHAR")),
+        ("column2", MockDuckDBType("INTEGER")),
+        ("column3", MockDuckDBType("DOUBLE")),
+    ]
+
+    # This should not raise an AttributeError
+    schema_metadata = dataset._generate_schema_metadata(duckdb_columns)
+
+    assert len(schema_metadata.fields) == 3
+    assert schema_metadata.fields[0].fieldPath == "column1"
+    assert schema_metadata.fields[1].fieldPath == "column2"
+    assert schema_metadata.fields[2].fieldPath == "column3"
+
+
+def test_generate_dataset_profile_and_schema_with_duckdb_types_simple(
+    dataset: DataHubBasedS3Dataset,
+) -> None:
+    """Test that _generate_dataset_profile_and_schema handles DuckDB type objects without AttributeError"""
+    # Test the core issue: calling str(column[1]).lower() should work with DuckDB type objects
+
+    # Test with mock DuckDB columns that have type objects instead of strings
+    duckdb_columns = [
+        ("form_urn", MockDuckDBType("VARCHAR")),
+        ("count", MockDuckDBType("BIGINT")),
+    ]
+
+    # This should not raise AttributeError: 'MockDuckDBType' object has no attribute 'lower'
+    try:
+        schema_metadata = dataset._generate_schema_metadata(duckdb_columns)
+        # If we get here, the fix worked
+        assert len(schema_metadata.fields) == 2
+        assert schema_metadata.fields[0].fieldPath == "form_urn"
+        assert schema_metadata.fields[1].fieldPath == "count"
+    except AttributeError as e:
+        if "lower" in str(e):
+            pytest.fail(f"The fix didn't work - still getting AttributeError: {e}")
+        else:
+            # Some other AttributeError, re-raise it
+            raise
+
+
+def test_column_type_conversion() -> None:
+    """Test that str() conversion works on various column type objects"""
+    # Test string types
+    assert str("VARCHAR").lower() == "varchar"
+
+    # Test mock DuckDB type objects
+    mock_type = MockDuckDBType("INTEGER")
+    assert str(mock_type).lower() == "integer"
+
+    # Test None (edge case)
+    assert str(None).lower() == "none"
+
+
+if __name__ == "__main__":
+    pytest.main([__file__])